Data-driven learning of chaotic dynamical systems using Discrete-Temporal Sobolev Networks

We introduce the Discrete-Temporal Sobolev Network (DTSN), a neural network loss function that assists dynamical system forecasting by minimizing variational differences between the network output and the training data via a temporal Sobolev norm. This approach is entirely data-driven, architecture agnostic, and does not require derivative information from the estimated system. The DTSN is particularly well suited to chaotic dynamical systems as it minimizes noise in the network output which is crucial for such sensitive systems. For our test cases we consider discrete approximations of the Lorenz-63 system and the Chua circuit. For the network architectures we use the Long Short-Term Memory (LSTM) and the Transformer. The performance of the DTSN is compared with the standard MSE loss for both architectures, as well as with the Physics Informed Neural Network (PINN) loss for the LSTM. The DTSN loss is shown to substantially improve accuracy for both architectures, while requiring less information than the PINN and without noticeably increasing computational time, thereby demonstrating its potential to improve neural network forecasting of dynamical systems.

Spatio-Temporal Image-Based Encoded Atlases for EEG Emotion Recognition

Emotion recognition plays an essential role in human-human interaction since it is a key to understanding the emotional states and reactions of human beings when they are subject to events and engagements in everyday life. Moving towards human-computer interaction, the study of emotions becomes fundamental because it is at the basis of the design of advanced systems to support a broad spectrum of application areas, including forensic, rehabilitative, educational, and many others. An effective method for discriminating emotions is based on ElectroEncephaloGraphy (EEG) data analysis, which is used as input for classification systems. Collecting brain signals on several channels and for a wide range of emotions produces cumbersome datasets that are hard to manage, transmit, and use in varied applications. In this context, the paper introduces the Empátheia system, which explores a different EEG representation by encoding EEG signals into images prior to their classification. In particular, the proposed system extracts spatio-temporal image encodings, or atlases, from EEG data through the Processing and transfeR of Interaction States and Mappings through Image-based eNcoding (PRISMIN) framework, thus obtaining a compact representation of the input signals. The atlases are then classified through the Empátheia architecture, which comprises branches based on convolutional, recurrent, and transformer models designed and tuned to capture the spatial and temporal aspects of emotions. Extensive experiments were conducted on the Shanghai Jiao Tong University (SJTU) Emotion EEG Dataset (SEED) public dataset, where the proposed system significantly reduced its size while retaining high performance. The results obtained highlight the effectiveness of the proposed approach and suggest new avenues for data representation in emotion recognition from EEG signals.

LieWaves: dataset for lie detection based on EEG signals and wavelets

This study introduces an electroencephalography (EEG)-based dataset to analyze lie detection. Various analyses or detections can be performed using EEG signals. Lie detection using EEG data has recently become a significant topic. In every aspect of life, people find the need to tell lies to each other. While lies told daily may not have significant societal impacts, lie detection becomes crucial in legal, security, job interviews, or situations that could affect the community. This study aims to obtain EEG signals for lie detection, create a dataset, and analyze this dataset using signal processing techniques and deep learning methods. EEG signals were acquired from 27 individuals using a wearable EEG device called Emotiv Insight with 5 channels (AF3, T7, Pz, T8, AF4). Each person took part in two trials: one where they were honest and another where they were deceitful. During each experiment, participants evaluated beads they saw before the experiment and stole from them in front of a video clip. This study consisted of four stages. In the first stage, the LieWaves dataset was created with the EEG data obtained during these experiments. In the second stage, preprocessing was carried out. In this stage, the automatic and tunable artifact removal (ATAR) algorithm was applied to remove the artifacts from the EEG signals. Later, the overlapping sliding window (OSW) method was used for data augmentation. In the third stage, feature extraction was performed. To achieve this, EEG signals were analyzed by combining discrete wavelet transform (DWT) and fast Fourier transform (FFT) including statistical methods (SM). In the last stage, each obtained feature vector was classified separately using Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and CNNLSTM hybrid algorithms. At the study's conclusion, the most accurate result, achieving a 99.88% accuracy score, was produced using the LSTM and DWT techniques. With this study, a new data set was introduced to the literature, and it was aimed to eliminate the deficiencies in this field with this data set. Evaluation results obtained from the data set have shown that this data set can be effective in this field.

Leveraging a 7-Layer Long Short-Term Memory Model for Early Detection and Prevention of Diabetes in Oman: An Innovative Approach

This study develops a 7-layer Long Short-Term Memory (LSTM) model to enhance early diabetes detection in Oman, aligning with the theme of 'Artificial Intelligence in Healthcare'. The model focuses on addressing the increasing prevalence of Type 2 diabetes, projected to impact 23.8% of Oman's population by 2050. It employs LSTM neural networks to manage factors contributing to this rise, including obesity and genetic predispositions, and aims to bridge the gap in public health awareness and prevention. The model's performance is evaluated through various metrics. It achieves an accuracy of 99.40%, specificity and sensitivity of 100% for positive cases, a recall of 99.34% for negative cases, an F1 score of 96.24%, and an AUC score of 94.51%. These metrics indicate the model's capability in diabetes detection. The implementation of this LSTM model in Oman's healthcare system is proposed to enhance early detection and prevention of diabetes. This approach reflects an application of AI in addressing a significant health concern, with potential implications for similar healthcare challenges relating to globally diagnostic capabilities, representing a significant leap forward in healthcare technology in Oman.

FUZ-SMO: A fuzzy slime mould optimizer for mitigating false alarm rates in the classification of underwater datasets using deep convolutional neural networks

Sonar sound datasets are of significant importance in the domains of underwater surveillance and marine research as they enable experts to discern intricate patterns within the depths of the water. Nevertheless, the task of classifying sonar sound datasets continues to pose significant challenges. In this study, we present a novel approach aimed at enhancing the precision and efficacy of sonar sound dataset classification. The integration of deep long-short-term memory (DLSTM) and convolutional neural networks (CNNs) models is employed in order to capitalize on their respective advantages while also utilizing distinctive feature engineering techniques to achieve the most favorable outcomes. Although DLSTM networks have demonstrated effectiveness in tasks involving sequence classification, attaining their optimal performance necessitates careful adjustment of hyperparameters. While traditional methods such as grid and random search are effective, they frequently encounter challenges related to computational inefficiencies. This study aims to investigate the unexplored capabilities of the fuzzy slime mould optimizer (FUZ-SMO) in the context of LSTM hyperparameter tuning, with the objective of addressing the existing research gap in this area. Drawing inspiration from the adaptive behavior exhibited by slime moulds, the FUZ-SMO proposes a novel approach to optimization. The amalgamated model, which combines CNN, LSTM, fuzzy, and SMO, exhibits a notable improvement in classification accuracy, outperforming conventional LSTM architectures by a margin of 2.142%. This model not only demonstrates accelerated convergence milestones but also displays significant resilience against overfitting tendencies.

An LSTM-based adversarial variational autoencoder framework for self-supervised neural decoding of behavioral choices

Objective. This paper presents data-driven solutions to address two challenges in the problem of linking neural data and behavior: 1) unsupervised analysis of behavioral data and automatic label generation from behavioral observations, and 2) extraction of subject-invariant features for the development of generalized neural decoding models. Approach. For behavioral analysis and label generation, an unsupervised method, which employs an autoencoder to transform behavior data into a cluster-friendly feature space is presented. The model iteratively refines the assigned clusters with soft clustering assignment loss, and gradually improves the learned feature representations. To address subject variability in decoding neural activity, adversarial learning in combination with a long short-term memory-based adversarial variational autoencoder (LSTM-AVAE) model is employed. By using an adversary network to constrain the latent representations, the model captures shared information among subjects' neural activity, making it proper for cross-subject transfer learning. Main results. The proposed approach is evaluated using cortical recordings of Thy1-GCaMP6s transgenic mice obtained via widefield calcium imaging during a motivational licking behavioral experiment. The results show that the proposed model achieves an accuracy of 89.7% in cross-subject neural decoding, outperforming other well-known autoencoder-based feature learning models. These findings suggest that incorporating an adversary network eliminates subject dependency in representations, leading to improved cross-subject transfer learning performance, while also demonstrating the effectiveness of LSTM-based models in capturing the temporal dependencies within neural data. Significance. Results demonstrate the feasibility of the proposed framework in unsupervised clustering and label generation of behavioral data, as well as achieving high accuracy in cross-subject neural decoding, indicating its potentials for relating neural activity to behavior.

LSTM Short-Term Wind Power Prediction Method Based on Data Preprocessing and Variational Modal Decomposition for Soft Sensors

Soft sensors have been extensively utilized to approximate real-time power prediction in wind power generation, which is challenging to measure instantaneously. The short-term forecast of wind power aims at providing a reference for the dispatch of the intraday power grid. This study proposes a soft sensor model based on the Long Short-Term Memory (LSTM) network by combining data preprocessing with Variational Modal Decomposition (VMD) to improve wind power prediction accuracy. It does so by adopting the isolation forest algorithm for anomaly detection of the original wind power series and processing the missing data by multiple imputation. Based on the process data samples, VMD technology is used to achieve power data decomposition and noise reduction. The LSTM network is introduced to predict each modal component separately, and further sum reconstructs the prediction results of each component to complete the wind power prediction. From the experimental results, it can be seen that the LSTM network which uses an Adam optimizing algorithm has better convergence accuracy. The VMD method exhibited superior decomposition outcomes due to its inherent Wiener filter capabilities, which effectively mitigate noise and forestall modal aliasing. The Mean Absolute Percentage Error (MAPE) was reduced by 9.3508%, which indicates that the LSTM network combined with the VMD method has better prediction accuracy.

Energy Expenditure Prediction from Accelerometry Data Using Long Short-Term Memory Recurrent Neural Networks

The accurate estimation of energy expenditure from simple objective accelerometry measurements provides a valuable method for investigating the effect of physical activity (PA) interventions or population surveillance. Methods have been evaluated previously, but none utilize the temporal aspects of the accelerometry data. In this study, we investigated the energy expenditure prediction from acceleration measured at the subjects' hip, wrist, thigh, and back using recurrent neural networks utilizing temporal elements of the data. The acceleration was measured in children (N = 33) performing a standardized activity protocol in their natural environment. The energy expenditure was modelled using Multiple Linear Regression (MLR), stacked long short-term memory (LSTM) networks, and combined convolutional neural networks (CNN) and LSTM. The correlation and mean absolute percentage error (MAPE) were 0.76 and 19.9% for the MLR, 0.882 and 0.879 and 14.22% for the LSTM, and, with the combined LSTM-CNN, the best performance of 0.883 and 13.9% was achieved. The prediction error for vigorous intensities was significantly different (p < 0.01) from those of the other intensity domains: sedentary, light, and moderate. Utilizing the temporal elements of movement significantly improves energy expenditure prediction accuracy compared to other conventional approaches, but the prediction error for vigorous intensities requires further investigation.

Adaptive control for uncrewed aerial vehicles based on communication information optimization in complex environments

The utilization of drone technology thrives in diverse domains, including aviation, military operations, and logistics. The pervasive adoption of this technology aims to enhance efficiency while mitigating hazards and expenditures. In complex contexts, the governing parameters of uncrewed aerial vehicles (UAV) require real-time adjustments for flight safety and efficacy. To improve the attitude estimation accuracy, this article introduces a ATT-Bi-LSTM framework for optimizing UAVs through adaptive parameter control, which integrates the state information gleaned from communication signals. The ATT-Bi-LSTM achieves data feature extraction by means of a two-layer Bidirectional Long Short-Term Memory (BI-LSTM) at its inception to enhance the feature. Subsequently, it harnesses the attention mechanism to amplify the LSTM network's output, thereby enabling the optimal control of UAV positioning. During the empirical phase, we employ optical system data for the comparative validation of the model. The outcomes underscore the commendable performance of the proposed framework in this study, particularly with regard to the three pivotal position indicators: yaw, pitch, and roll. In the comparison of indicators such as RMSR and MAE, the proposed model has the lowest error, which provides algorithm support and important reference for future UAV optimization control research.

Splice site recognition - deciphering Exon-Intron transitions for genetic insights using Enhanced integrated Block-Level gated LSTM model

Bioinformatics is a contemporary interdisciplinary area focused on analyzing the growing number of genome sequences. Gene variants are differences in DNA sequences among individuals within a population. Splice site recognition is a crucial step in the process of gene expression, where the coding sequences of genes are joined together to form mature messenger RNA (mRNA). These genetic variants that disrupt genes are believed to be the primary reason for neuro-developmental disorders like ASD (Autism Spectrum Disorder) is a neuro-developmental disorder that is diagnosed in individuals, families, and society and occurs as the developmental delay in one among the hundred genes that are associated with these disorders. Missense variants, premature stop codons, or deletions alter both the quality and quantity of encoded proteins. Predicting genes within exons and introns presents main challenges, such as dealing with sequencing errors, short reads, incomplete genes, overlapping, and more. Although many traditional techniques have been utilized in creating an exon prediction system, the primary challenge lies in accurately identifying the length and spliced strand location classification of exons in conjunction with introns. From now on, the suggested approach utilizes a Deep Learning algorithm to analyze intricate and extensive genomic datasets. M-LSTM is utilized to categorize three binary combinations (EI as 1, IE as 2, and none as 3) using spliced DNA strands. The M-LSTM system is able to sequence extensive datasets, ensuring that long information can be stored without any impact on the current input or output. This enables it to recognize and address long-term connections and problems with rapidly increasing gradients. The proposed model is compared internally with Naïve Bayes and Random Forest to assess its efficacy. Additionally, the proposed model's performance is forecasted by utilizing probabilistic parameters like recall, F1-score, precision, and accuracy to assess the effectiveness of the proposed system.

ECG-based cardiac arrhythmias detection through ensemble learning and fusion of deep spatial-temporal and long-range dependency features

Cardiac arrhythmia is one of the prime reasons for death globally. Early diagnosis of heart arrhythmia is crucial to provide timely medical treatment. Heart arrhythmias are diagnosed by analyzing the electrocardiogram (ECG) of patients. Manual analysis of ECG is time-consuming and challenging. Hence, effective automated detection of heart arrhythmias is important to produce reliable results. Different deep-learning techniques to detect heart arrhythmias such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Transformer, and Hybrid CNN-LSTM were proposed. However, these techniques, when used individually, are not sufficient to effectively learn multiple features from the ECG signal. The fusion of CNN and LSTM overcomes the limitations of CNN in the existing studies as CNN-LSTM hybrids can extract spatiotemporal features. However, LSTMs suffer from long-range dependency issues due to which certain features may be ignored. Hence, to compensate for the drawbacks of the existing models, this paper proposes a more comprehensive feature fusion technique by merging CNN, LSTM, and Transformer models. The fusion of these models facilitates learning spatial, temporal, and long-range dependency features, hence, helping to capture different attributes of the ECG signal. These features are subsequently passed to a majority voting classifier equipped with three traditional base learners. The traditional learners are enriched with deep features instead of handcrafted features. Experiments are performed on the MIT-BIH arrhythmias database and the model performance is compared with that of the state-of-art models. Results reveal that the proposed model performs better than the existing models yielding an accuracy of 99.56%.

Performance evaluation of deep learning based stream nitrate concentration prediction model to fill stream nitrate data gaps at low-frequency nitrate monitoring basins

Accurate and frequent nitrate estimates can provide valuable information on the nitrate transport dynamics. The study aimed to develop a data-driven modeling framework to estimate daily nitrate concentrations at low-frequency nitrate monitoring sites using the daily nitrate concentration and stream discharge information of a neighboring high-frequency nitrate monitoring site. A Long Short-Term Memory (LSTM) based deep learning (DL) modeling framework was developed to predict daily nitrate concentrations. The DL modeling framework performance was compared with two well-established statistical models, including LOADEST and WRTDS-Kalman, in three selected basins in Iowa, USA: Des Moines, Iowa, and Cedar River. The developed DL model performed well with NSE >0.70 and KGE >0.70 for 67% and 79% nitrate monitoring sites, respectively. DL and WRTDS-Kalman models performed better than the LOADEST in nitrate concentration and load estimation for all low-frequency sites. The average NSE performance of the DL model in daily nitrate estimation is 20% higher than that of the WRTDS-Kalman model at 18 out of 24 sites (75%). The WRTDS-Kalman model showed unrealistic fluctuations in the estimated daily nitrate time series when the model received limited observed nitrate data (less than 50) for simulation. The DL model indicated superior performance in winter months' nitrate prediction (60% of cases) compared to WRTDS-Kalman models (33% of cases). The DL model also better represented the exceedance days from the USEPA maximum contamination level (MCL). Both the DL and WRTDS-Kalman models demonstrated similar performance in annual stream nitrate load estimation, and estimated values are close to actual nitrate loads.

A Novel IDS with a Dynamic Access Control Algorithm to Detect and Defend Intrusion at IoT Nodes

The Internet of Things (IoT) is the underlying technology that has enabled connecting daily apparatus to the Internet and enjoying the facilities of smart services. IoT marketing is experiencing an impressive 16.7% growth rate and is a nearly USD 300.3 billion market. These eye-catching figures have made it an attractive playground for cybercriminals. IoT devices are built using resource-constrained architecture to offer compact sizes and competitive prices. As a result, integrating sophisticated cybersecurity features is beyond the scope of the computational capabilities of IoT. All of these have contributed to a surge in IoT intrusion. This paper presents an LSTM-based Intrusion Detection System (IDS) with a Dynamic Access Control (DAC) algorithm that not only detects but also defends against intrusion. This novel approach has achieved an impressive 97.16% validation accuracy. Unlike most of the IDSs, the model of the proposed IDS has been selected and optimized through mathematical analysis. Additionally, it boasts the ability to identify a wider range of threats (14 to be exact) compared to other IDS solutions, translating to enhanced security. Furthermore, it has been fine-tuned to strike a balance between accurately flagging threats and minimizing false alarms. Its impressive performance metrics (precision, recall, and F1 score all hovering around 97%) showcase the potential of this innovative IDS to elevate IoT security. The proposed IDS boasts an impressive detection rate, exceeding 98%. This high accuracy instills confidence in its reliability. Furthermore, its lightning-fast response time, averaging under 1.2 s, positions it among the fastest intrusion detection systems available.

Detecting cyberbullying using deep learning techniques: a pre-trained glove and focal loss technique

This study investigates the effectiveness of various deep learning and classical machine learning techniques in identifying instances of cyberbullying. The study compares the performance of five classical machine learning algorithms and three deep learning models. The data undergoes pre-processing, including text cleaning, tokenization, stemming, and stop word removal. The experiment uses accuracy, precision, recall, and F1 score metrics to evaluate the performance of the algorithms on the dataset. The results show that the proposed technique achieves high accuracy, precision, and F1 score values, with the Focal Loss algorithm achieving the highest accuracy of 99% and the highest precision of 86.72%. However, the recall values were relatively low for most algorithms, indicating that they struggled to identify all relevant data. Additionally, the study proposes a technique using a convolutional neural network with a bidirectional long short-term memory layer, trained on a pre-processed dataset of tweets using GloVe word embeddings and the focal loss function. The model achieved high accuracy, precision, and F1 score values, with the GRU algorithm achieving the highest accuracy of 97.0% and the NB algorithm achieving the highest precision of 96.6%.

Advertisement design in dynamic interactive scenarios using DeepFM and long short-term memory (LSTM)

This article addresses the evolving landscape of data advertising within network-based new media, seeking to mitigate the accuracy limitations prevalent in traditional film and television advertising evaluations. To overcome these challenges, a novel data-driven nonlinear dynamic neural network planning approach is proposed. Its primary objective is to augment the real-time evaluation precision and accuracy of film and television advertising in the dynamic interactive realm of network media. The methodology primarily revolves around formulating a design model for visual advertising in film and television, customized for the dynamic interactive milieu of network media. Leveraging DeepFM+long short-term memory (LSTM) modules in deep learning neural networks, the article embarks on constructing a comprehensive information statistics and data interest model derived from two public datasets. It further engages in feature engineering for visual advertising, crafting self-learning association rules that guide the data-driven design process and system flow. The article concludes by benchmarking the proposed visual neural network model against other models, using F1 and root mean square error (RMSE) metrics for evaluation. The findings affirm that the proposed model, capable of handling dynamic interactions among images, visual text, and more, excels in capturing nonlinear and feature-mining aspects. It exhibits commendable robustness and generalization capabilities within various contexts.

Deep Reinforcement Learning-Empowered Cost-Effective Federated Video Surveillance Management Framework

Video surveillance systems are integral to bolstering safety and security across multiple settings. With the advent of deep learning (DL), a specialization within machine learning (ML), these systems have been significantly augmented to facilitate DL-based video surveillance services with notable precision. Nevertheless, DL-based video surveillance services, which necessitate the tracking of object movement and motion tracking (e.g., to identify unusual object behaviors), can demand a significant portion of computational and memory resources. This includes utilizing GPU computing power for model inference and allocating GPU memory for model loading. To tackle the computational demands inherent in DL-based video surveillance, this study introduces a novel video surveillance management system designed to optimize operational efficiency. At its core, the system is built on a two-tiered edge computing architecture (i.e., client and server through socket transmission). In this architecture, the primary edge (i.e., client side) handles the initial processing tasks, such as object detection, and is connected via a Universal Serial Bus (USB) cable to the Closed-Circuit Television (CCTV) camera, directly at the source of the video feed. This immediate processing reduces the latency of data transfer by detecting objects in real time. Meanwhile, the secondary edge (i.e., server side) plays a vital role by hosting a dynamically controlling threshold module targeted at releasing DL-based models, reducing needless GPU usage. This module is a novel addition that dynamically adjusts the threshold time value required to release DL models. By dynamically optimizing this threshold, the system can effectively manage GPU usage, ensuring resources are allocated efficiently. Moreover, we utilize federated learning (FL) to streamline the training of a Long Short-Term Memory (LSTM) network for predicting imminent object appearances by amalgamating data from diverse camera sources while ensuring data privacy and optimized resource allocation. Furthermore, in contrast to the static threshold values or moving average techniques used in previous approaches for the controlling threshold module, we employ a Deep Q-Network (DQN) methodology to manage threshold values dynamically. This approach efficiently balances the trade-off between GPU memory conservation and the reloading latency of the DL model, which is enabled by incorporating LSTM-derived predictions as inputs to determine the optimal timing for releasing the DL model. The results highlight the potential of our approach to significantly improve the efficiency and effective usage of computational resources in video surveillance systems, opening the door to enhanced security in various domains.

Research on Fault Prediction Method of Elevator Door System Based on Transfer Learning

The elevator door system plays a crucial role in ensuring elevator safety. Fault prediction is an invaluable tool for accident prevention. By analyzing the sound signals generated during operation, such as component wear and tear, the fault of the system can be accurately determined. This study proposes a GNN-LSTM-BDANN deep learning model to account for variations in elevator operating environments and sound signal acquisition methods. The proposed model utilizes the historical sound data from other elevators to predict the remaining useful life (RUL) of the target elevator door system. Firstly, the opening and closing sounds of other elevators is collected, followed by the extraction of relevant sound signal characteristics including A-weighted sound pressure level, loudness, sharpness, and roughness. These features are then transformed into graph data with geometric structure representation. Subsequently, the Graph Neural Networks (GNN) and long short-term memory networks (LSTM) are employed to extract deeper features from the data. Finally, transfer learning based on the improved Bhattacharyya Distance domain adversarial neural network (BDANN) is utilized to transfer knowledge learned from historical sound data of other elevators to predict RUL for the target elevator door system effectively. Experimental results demonstrate that the proposed method can successfully predict potential failure timeframes for different elevator door systems.

Prediction of riverine daily minimum dissolved oxygen concentrations using hybrid deep learning and routine hydrometeorological data

Dissolved oxygen (DO) depletion is a severe threat to aquatic ecosystems. Hence, using easily available routine hydrometeorological variables without DO as inputs to predict the daily minimum DO concentration in rivers has huge practical significance in the watershed management. The daily minimum DO concentrations at the outlet of the Oyster River watershed in New Hampshire, USA, were predicted by a set of deep learning neural networks using meteorological data and high-frequency water level, water temperature, and specific conductance (CTD) data measured within the watershed. The dependent variable, DO concentration, was measured at the outlet. From April 2013 to March 2018, the dataset was separated into training, validation, and test portions with a ratio of 5:3:3. A Long Short-Term Memory (LSTM) model and a hybrid Convolutional Neural Networks (CNN-LSTM) model were trained and evaluated for predicting the daily minimum DO concentration. The hybrid CNN-LSTM model exhibited the better predictive stability but the comparable accuracy (the mean R2 value = 0.865) compared with the pure LSTM model (the mean R2 value = 0.839). The model performance (both the stability and accuracy) was improved by aggregating the input data frequency from 15 min of raw data to 24 h. Likewise, the modeling performance didn't benefit from including 'forecasted' meteorological data at the predicted time step in the input dataset. This study provided an efficient and low-cost approach to predict the water quality in rivers and streams to realize the scientific watershed management.

Advancing Phishing Email Detection: A Comparative Study of Deep Learning Models

Phishing is one of the most dangerous attacks targeting individuals, organizations, and nations. Although many traditional methods for email phishing detection exist, there is a need to improve accuracy and reduce false-positive rates. Our work investigates one-dimensional CNN-based models (1D-CNNPD) to detect phishing emails in order to address these challenges. Additionally, further improvement is achieved with the augmentation of the base 1D-CNNPD model with recurrent layers, namely, LSTM, Bi-LSTM, GRU, and Bi-GRU, and experimented with the four resulting models. Two benchmark datasets were used to evaluate the performance of our models: Phishing Corpus and Spam Assassin. Our results indicate that, in general, the augmentations improve the performance of the 1D-CNNPD base model. Specifically, the 1D-CNNPD with Bi-GRU yields the best results. Overall, the performance of our models is comparable to the state of the art of CNN-based phishing email detection. The Advanced 1D-CNNPD with Leaky ReLU and Bi-GRU achieved 100% precision, 99.68% accuracy, an F1 score of 99.66%, and a recall of 99.32%. We observe that increasing model depth typically leads to an initial performance improvement, succeeded by a decline. In conclusion, this study highlights the effectiveness of augmented 1D-CNNPD models in detecting phishing emails with improved accuracy. The reported performance measure values indicate the potential of these models in advancing the implementation of cybersecurity solutions to combat email phishing attacks.

Recurrent neural network-based simultaneous cardiac T1, T2, and T1ρ mapping

The purpose of the current study was to explore the feasibility of training a deep neural network to accelerate the process of generating T1, T2, and T1ρ maps for a recently proposed free-breathing cardiac multiparametric mapping technique, where a recurrent neural network (RNN) was utilized to exploit the temporal correlation among the multicontrast images. The RNN-based model was developed for rapid and accurate T1, T2, and T1ρ estimation. Bloch simulation was performed to simulate a dataset of more than 10 million signals and time correspondences with different noise levels for network training. The proposed RNN-based method was compared with a dictionary-matching method and a conventional mapping method to evaluate the model's effectiveness in phantom and in vivo studies at 3 T, respectively. In phantom studies, the RNN-based method and the dictionary-matching method achieved similar accuracy and precision in T1, T2, and T1ρ estimations. In in vivo studies, the estimated T1, T2, and T1ρ values obtained by the two methods achieved similar accuracy and precision for 10 healthy volunteers (T1: 1228.70 ± 53.80 vs. 1228.34 ± 52.91 ms, p > 0.1; T2: 40.70 ± 2.89 vs. 41.19 ± 2.91 ms, p > 0.1; T1ρ: 45.09 ± 4.47 vs. 45.23 ± 4.65 ms, p > 0.1). The RNN-based method can generate cardiac multiparameter quantitative maps simultaneously in just 2 s, achieving 60-fold acceleration compared with the dictionary-matching method. The RNN-accelerated method offers an almost instantaneous approach for reconstructing accurate T1, T2, and T1ρ maps, being much more efficient than the dictionary-matching method for the free-breathing multiparametric cardiac mapping technique, which may pave the way for inline mapping in clinical applications.

Predicting quantum emitter fluctuations with time-series forecasting models

2D materials have important fundamental properties allowing for their use in many potential applications, including quantum computing. Various Van der Waals materials, including Tungsten disulfide (WS2), have been employed to showcase attractive device applications such as light emitting diodes, lasers and optical modulators. To maximize the utility and value of integrated quantum photonics, the wavelength, polarization and intensity of the photons from a quantum emission (QE) must be stable. However, random variation of emission energy, caused by the inhomogeneity in the local environment, is a major challenge for all solid-state single photon emitters. In this work, we assess the random nature of the quantum fluctuations, and we present time series forecasting deep learning models to analyse and predict QE fluctuations for the first time. Our trained models can roughly follow the actual trend of the data and, under certain data processing conditions, can predict peaks and dips of the fluctuations. The ability to anticipate these fluctuations will allow physicists to harness quantum fluctuation characteristics to develop novel scientific advances in quantum computing that will greatly benefit quantum technologies.

Novel deep learning framework for detection of epileptic seizures using EEG signals

Introduction

Epilepsy is a chronic neurological disorder characterized by abnormal electrical activity in the brain, often leading to recurrent seizures. With 50 million people worldwide affected by epilepsy, there is a pressing need for efficient and accurate methods to detect and diagnose seizures. Electroencephalogram (EEG) signals have emerged as a valuable tool in detecting epilepsy and other neurological disorders. Traditionally, the process of analyzing EEG signals for seizure detection has relied on manual inspection by experts, which is time-consuming, labor-intensive, and susceptible to human error. To address these limitations, researchers have turned to machine learning and deep learning techniques to automate the seizure detection process.

Methods

In this work, we propose a novel method for epileptic seizure detection, leveraging the power of 1-D Convolutional layers in combination with Bidirectional Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) and Average pooling Layer as a single unit. This unit is repeatedly used in the proposed model to extract the features. The features are then passed to the Dense layers to predict the class of the EEG waveform. The performance of the proposed model is verified on the Bonn dataset. To assess the robustness and generalizability of our proposed architecture, we employ five-fold cross-validation. By dividing the dataset into five subsets and iteratively training and testing the model on different combinations of these subsets, we obtain robust performance measures, including accuracy, sensitivity, and specificity.

Results

Our proposed model achieves an accuracy of 99-100% for binary classifications into seizure and normal waveforms, 97.2%-99.2% accuracy for classifications into normal-interictal-seizure waveforms, 96.2%-98.4% accuracy for four class classification and accuracy of 95.81%-98% for five class classification.

Discussion

Our proposed models have achieved significant improvements in the performance metrics for the binary classifications and multiclass classifications. We demonstrate the effectiveness of the proposed architecture in accurately detecting epileptic seizures from EEG signals by using EEG signals of varying lengths. The results indicate its potential as a reliable and efficient tool for automated seizure detection, paving the way for improved diagnosis and management of epilepsy.

Deep learning-based forecasting of electricity consumption

Building energy management systems (BEMS) are integrated computerized systems that track and manage the energy use of many pieces of building-related machinery and equipment, including lighting, power systems, and HVAC systems. Modern buildings must have BEMSs in order to reduce energy usage while maintaining comfort. Not only for energy-saving purposes, BEMS is essential in enhancing the quality of the energy supply, which helps to gain a better understanding of how energy is used and the building's energy usage. When the dynamics of a building's energy usage are known, it is possible to determine which changes are most likely to reduce consumption. Numerous connected devices, operating modes, energy usage, and environmental factors can all be monitored and controlled in real-time using BEMS. Changing operating times and setting points to maximize comfort and efficiency is made simple by this. In this paper, we have primarily addressed the two significant issues of model optimization and electricity consumption forecasts. Future forecasting has been done using the LSTM based time series approach. We generated data on the amount of electricity consumed by a hospital facility and tested our suggested methodologies on actual data. The findings gained demonstrated that the strategies were successful with both types of data. On actual data, the trend in electricity consumption can be accurately predicted. Several model optimizers enhanced the suggested methods' performance as well. Our objective function gain accuracy result of 95%.

Assessment of surrogate models for flood inundation: The physics-guided LSG model vs. state-of-the-art machine learning models

Hydrodynamic models can accurately simulate flood inundation but are limited by their high computational demand that scales non-linearly with model complexity, resolution, and domain size. Therefore, it is often not feasible to use high-resolution hydrodynamic models for real-time flood predictions or when a large number of predictions are needed for probabilistic flood design. Computationally efficient surrogate models have been developed to address this issue. The recently developed Low-fidelity, Spatial analysis, and Gaussian Process Learning (LSG) model has shown strong performance in both computational efficiency and simulation accuracy. The LSG model is a physics-guided surrogate model that simulates flood inundation by first using an extremely coarse and simplified (i.e. low-fidelity) hydrodynamic model to provide an initial estimate of flood inundation. Then, the low-fidelity estimate is upskilled via Empirical Orthogonal Functions (EOF) analysis and Sparse Gaussian Process models to provide accurate high-resolution predictions. Despite the promising results achieved thus far, the LSG model has not been benchmarked against other surrogate models. Such a comparison is needed to fully understand the value of the LSG model and to provide guidance for future research efforts in flood inundation simulation. This study compares the LSG model to four state-of-the-art surrogate flood inundation models. The surrogate models are assessed for their ability to simulate the temporal and spatial evolution of flood inundation for events both within and beyond the range used for model training. The models are evaluated for three distinct case studies in Australia and the United Kingdom. The LSG model is found to be superior in accuracy for both flood extent and water depth, including when applied to flood events outside the range of training data used, while achieving high computational efficiency. In addition, the low-fidelity model is found to play a crucial role in achieving the overall superior performance of the LSG model.

Multimodal audio-visual robot fusing 3D CNN and CRNN for player behavior recognition and prediction in basketball matches

Introduction

Intelligent robots play a crucial role in enhancing efficiency, reducing costs, and improving safety in the logistics industry. However, traditional path planning methods often struggle to adapt to dynamic environments, leading to issues such as collisions and conflicts. This study aims to address the challenges of path planning and control for logistics robots in complex environments.

Methods

The proposed method integrates information from different perception modalities to achieve more accurate path planning and obstacle avoidance control, thereby enhancing the autonomy and reliability of logistics robots. Firstly, a 3D convolutional neural network (CNN) is employed to learn the feature representation of objects in the environment for object recognition. Next, long short-term memory (LSTM) is used to model spatio-temporal features and predict the behavior and trajectory of dynamic obstacles. This enables the robot to accurately predict the future position of obstacles in complex environments, reducing collision risks. Finally, the Dijkstra algorithm is applied for path planning and control decisions to ensure the robot selects the optimal path in various scenarios.

Results

Experimental results demonstrate the effectiveness of the proposed method in terms of path planning accuracy and obstacle avoidance performance. The method outperforms traditional approaches, showing significant improvements in both aspects.

Discussion

The intelligent path planning and control scheme presented in this paper enhances the practicality of logistics robots in complex environments, thereby promoting efficiency and safety in the logistics industry.

Prediction of air pollutant concentrations based on the long short-term memory neural network

In recent years, environmental problems caused by air pollutants have received increasing attention. Effective prediction of air pollutant concentrations is an important way to protect the public from harm. Recently, due to extreme climate and social development, the forest fire frequency has increased. During the biomass combustion process caused by forest fires, the content of particulate matter (PM) in the atmosphere increases significantly. However, most existing air pollutant concentration prediction methods do not consider the considerable impact of forest fires, and effective long-term prediction models have not been established to provide early warnings for harmful gases. Therefore, in this paper, we collected a daily air quality data set (aerodynamic diameter smaller than 2.5 µm, PM2.5) for Heilongjiang Province, China, from 2017 to 2023 and A novel Long Short-Term Memory (LSTM) model was proposed to effectively predict the situation of air pollutants. The model could automatically extract information of the effective time step from the historical data set and combine forest fire disturbance and climate data as auxiliary data to improve the model prediction ability. Moreover, we created artificial neural network (ANN) and permissive regression (support vector machine, SVR) models for comparative experiments. The results showed that the precision accuracy of the developed LSTM model is higher. Unlike the other models, the LSTM neural network model could effectively predict the concentration of air pollutants in long-term series. Regarding long-term observation missions (7 days), the proposed model performed well and stably, with R2 reaching over 88%.

BREATH-Net: a novel deep learning framework for NO2 prediction using bi-directional encoder with transformer

Air pollution poses a significant challenge in numerous urban regions, negatively affecting human well-being. Nitrogen dioxide (NO2) is a prevalent atmospheric pollutant that can potentially exacerbate respiratory ailments and cardiovascular disorders and contribute to cancer development. The present study introduces a novel approach for monitoring and predicting Delhi's nitrogen dioxide concentrations by leveraging satellite data and ground data from the Sentinel 5P satellite and monitoring stations. The research gathers satellite and monitoring data over 3 years for evaluation. Exploratory data analysis (EDA) methods are employed to comprehensively understand the data and discern any discernible patterns and trends in nitrogen dioxide levels. The data subsequently undergoes pre-processing and scaling utilizing appropriate techniques, such as MinMaxScaler, to optimize the model's performance. The proposed forecasting model uses a hybrid architecture of the Transformer and BiLSTM models called BREATH-Net. BiLSTM models exhibit a strong aptitude for effectively managing sequential data by adeptly capturing dependencies in both the forward and backward directions. Conversely, transformers excel in capturing extensive relationships over extended distances in temporal data. The results of this study will illustrate the proposed model's efficacy in predicting the levels of NO2 in Delhi. If effectively executed, this model can significantly enhance strategies for controlling urban air quality. The findings of this research show a significant improvement of RMSE = 9.06 compared to other state-of-the-art models. This study's primary objective is to contribute to mitigating respiratory health issues resulting from air pollution through satellite data and deep learning methodologies.

Meteorological factors cannot be ignored in machine learning-based methods for predicting dengue, a systematic review

In recent years, there has been a rapid increase in the application of machine learning methods about predicting the incidence of dengue fever. However, the predictive factors and models employed in different studies vary greatly. Hence, we conducted a systematic review to summarize machine learning methods and predictors in previous studies. We searched PubMed, ScienceDirect, and Web of Science databases for articles published up to July 2023. The selected papers included not only the forecast of dengue incidence but also machine learning methods. A total of 23 papers were included in this study. Predictive factors included meteorological factors (22, 95.7%), historical dengue data (14, 60.9%), environmental factors (4, 17.4%), socioeconomic factors (4, 17.4%), vector surveillance data (2, 8.7%), and internet search data (3, 13.0%). Among meteorological factors, temperature (20, 87.0%), rainfall (20, 87.0%), and relative humidity (14, 60.9%) were the most commonly used. We found that Support Vector Machine (SVM) (6, 26.1%), Long Short-Term Memory (LSTM) (5, 21.7%), Random Forest (RF) (4, 17.4%), Least Absolute Shrinkage and Selection Operator (LASSO) (2, 8.7%), ensemble model (2, 8.7%), and other models (4, 17.4%) were identified as the best models based on evaluation metrics used in each article. These results indicate that meteorological factors are important predictors that cannot be ignored and SVM and LSTM algorithms are the most commonly used models in dengue fever prediction with good predictive performance. This review will contribute to the development of more robust early dengue warning systems and promote the application of machine learning methods in predicting climate-related infectious diseases.

CLINet: A novel deep learning network for ECG signal classification

Machine learning is poised to revolutionize medicine with algorithms that spot cardiac arrhythmia. An automated diagnostic approach can boost the efficacy of diagnosing life-threatening arrhythmia disorders in routine medical procedures. In this paper, we propose a deep learning network CLINet for ECG signal classification. Our network uses convolution, LSTM and involution layers to bring their unique advantages together. For both convolution and involution layers, we use multiple, large size kernels for multi-scale representation learning. CLINet does not require complicated pre-processing and can handle electrocardiograms of any length. Our network achieves 99.90% accuracy on the ICCAD dataset and 99.94% accuracy on the MIT-BIH dataset. With only 297 K parameters, our model can be easily embedded in smart wearable devices. The source code of CLINet is available at https://github.com/CandleLabAI/CLINet-ECG-Classification-2024.

Machine learning parallel system for integrated process-model calibration and accuracy enhancement in sewer-river system

The process-based water system models have been transitioning from single-functional to integrated multi-objective and multi-functional since the worldwide digital upgrade of urban water system management. The proliferation of model complexity results in more significant uncertainty and computational requirements. However, conventional model calibration methods are insufficient in dealing with extensive computational time and limited monitoring samples. Here we introduce a novel machine learning system designed to expedite parameter optimization with limited data and boost efficiency in parameter search. MLPS, termed the machine learning parallel system for fast parameter search of integrated process-based models, aims to enhance both the performance and efficiency of the integrated model by ensuring its comprehensiveness, accuracy, and stability. MLPS was constructed upon the concept of model surrogation + algorithm optimization using Ant Colony Optimization (ACO) coupled with Long Short-Term Memory (LSTM). The optimization results of the Integrated sewer network and urban river model demonstrate that the average relative percentage difference of the predicted river pollutant concentrations increases from 1.1 to 6.0, and the average absolute percent bias decreases from 124.3% to 8.8%. The model outputs closely align with the monitoring data, and parameter calibration time is reduced by 89.94%. MLPS enables the efficient optimization of integrated process-based models, facilitating the application of highly precise complex models in environmental management. The design of MLPS also presents valuable insights for optimizing complex models in other fields.

Voice Synthesis Improvement by Machine Learning of Natural Prosody

Since the advent of modern computing, researchers have striven to make the human-computer interface (HCI) as seamless as possible. Progress has been made on various fronts, e.g., the desktop metaphor (interface design) and natural language processing (input). One area receiving attention recently is voice activation and its corollary, computer-generated speech. Despite decades of research and development, most computer-generated voices remain easily identifiable as non-human. Prosody in speech has two primary components-intonation and rhythm-both often lacking in computer-generated voices. This research aims to enhance computer-generated text-to-speech algorithms by incorporating melodic and prosodic elements of human speech. This study explores a novel approach to add prosody by using machine learning, specifically an LSTM neural network, to add paralinguistic elements to a recorded or generated voice. The aim is to increase the realism of computer-generated text-to-speech algorithms, to enhance electronic reading applications, and improved artificial voices for those in need of artificial assistance to speak. A computer that is able to also convey meaning with a spoken audible announcement will also improve human-to-computer interactions. Applications for the use of such an algorithm may include improving high-definition audio codecs for telephony, renewing old recordings, and lowering barriers to the utilization of computing. This research deployed a prototype modular platform for digital speech improvement by analyzing and generalizing algorithms into a modular system through laboratory experiments to optimize combinations and performance in edge cases. The results were encouraging, with the LSTM-based encoder able to produce realistic speech. Further work will involve optimizing the algorithm and comparing its performance against other approaches.

Comparative study of respiratory sounds classification methods based on cepstral analysis and artificial neural networks

In this paper, we investigated and evaluated various machine learning-based approaches for automatically detecting wheezing sounds. We conducted a comprehensive comparison of these proposed systems, assessing their classification performance through metrics such as Sensitivity, Specificity, and Accuracy. The main approach to developing a machine learning-based system for classifying respiratory sounds involved the combination of a technique for extracting features from an unknown input sound with a classification method to determine its belonging class. The characterization techniques used in this study are based on the cepstral analysis, which was extensively employed in the automatic speech recognition field. While MFCC (Mel-Frequency Cepstral Coefficients) feature extraction methods are commonly used in respiratory sounds classification, our study introduces a novelty by employing GFCC (Gammatone-Frequency Cepstral Coefficients) and BFCC (Bark-Frequency Cepstral Coefficients) for this purpose. For the classification task, we employed two types of neural networks: the MLP (Multilayer Perceptron), a feedforward neural network, and a variant of the LSTM (Long Short-Term Memory) recurrent neural network called BiLSTM (Bidirectional LSTM). The proposed classification systems are evaluated using a database consisting of 497 wheezing segments and 915 normal respiratory segments, which are recorded from individuals diagnosticated with asthma and individuals without any respiratory issues, respectively. The highest classification performance was achieved by the BFCC-BiLSTM model, which demonstrated an exceptional accuracy rate of 99.8%.

Comparison of simulation and predictive efficacy for hemorrhagic fever with renal syndrome incidence in mainland China based on five time series models

Background

Hemorrhagic fever with renal syndrome (HFRS) is a zoonotic infectious disease commonly found in Asia and Europe, characterized by fever, hemorrhage, shock, and renal failure. China is the most severely affected region, necessitating an analysis of the temporal incidence patterns in the country.

Methods

We employed Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Nonlinear AutoRegressive with eXogenous inputs (NARX), and a hybrid CNN-LSTM model to model and forecast time series data spanning from January 2009 to November 2023 in the mainland China. By comparing the simulated performance of these models on training and testing sets, we determined the most suitable model.

Results

Overall, the CNN-LSTM model demonstrated optimal fitting performance (with Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE), and Mean Absolute Error (MAE) of 93.77/270.66, 7.59%/38.96%, and 64.37/189.73 for the training and testing sets, respectively, lower than those of individual CNN or LSTM models).

Conclusion

The hybrid CNN-LSTM model seamlessly integrates CNN's data feature extraction and LSTM's recurrent prediction capabilities, rendering it theoretically applicable for simulating diverse distributed time series data. We recommend that the CNN-LSTM model be considered as a valuable time series analysis tool for disease prediction by policy-makers.

Suction detection and suction suppression of centrifugal blood pump based on the FFT-GAPSO-LSTM model and speed modulation

Centrifugal blood pumps are important devices used to treat heart failure. However, they are prone to high-risk suction events that pose a threat to human health when operating at high speeds. To address these issues, a normal suction detection method and a suction suppression method based on the FFT-GAPSO-LSTM model and speed modulation were proposed. The innovation of this suction detection method lies in the application of the genetic particle swarm optimisation (GAPSO) and the fast Fourier transform (FFT) feature extraction method to the long-term and short-term memory (LSTM) model, thereby improving the accuracy of suction detection. After detecting signs of suction, the suction suppression method designed in this study based on variable-speed modulation immediately takes effect, enabling the centrifugal blood pump to quickly return to its normal state by controlling the speed. The suction detection method was divided into four steps. First, a mathematical model of the coupling of the cardiovascular system and the centrifugal blood pump was established, and a real-time blood flow curve was obtained through model simulation. Second, the signal was preprocessed by adding Gaussian white noise and low-pass filtering to make the blood flow signal close to actual working conditions while retaining the original characteristics. Subsequently, through fast Fourier transform (FFT) analysis of the processed curve, the spectral characteristics that can characterise the working state of the centrifugal blood pump were extracted. Finally, the parameters of the LSTM model were optimised using the GAPSO, and the improved LSTM model was used to train and test the blood flow spectrum feature set. The results show that the suction detection method of the FFT-GAPSO-LSTM model can effectively detect whether centrifugal blood pump suction occurs and has certain advantages over other methods. In addition, the simulation results of the suction suppression were excellent and could effectively suppress the occurrence of suction. These results provide a reference for the design of centrifugal blood pump control systems.

Random forest regression for prediction of Covid-19 daily cases and deaths in Turkey

During pandemic periods, there is an intense flow of patients to hospitals. Depending on the disease, many patients may require hospitalization. In some cases, these patients must be taken to intensive care units and emergency interventions must be performed. However, finding a sufficient number of hospital beds or intensive care units during pandemic periods poses a big problem. In these periods, fast and effective planning is more important than ever. Another problem experienced during pandemic periods is the burial of the dead in case the number of deaths increases. This is also a situation that requires due planning. We can learn some lessons from Covid 19 pandemic and be prepared for the future ones. In this paper, statistical properties of the daily cases and daily deaths in Turkey, which is one of the most affected countries by the pandemic in the World, are studied. It is found that the characteristics are nonstationary. Then, random forest regression is applied to predict Covid-19 daily cases and deaths. In addition, seven other machine learning models, namely bagging, AdaBoost, gradient boosting, XGBoost, decision tree, LSTM and ARIMA regressors are built for comparison. The performance of the models are measured using accuracy, coefficient of variation, root-mean-square score and relative error metrics. When random forest regressors are employed, test data related to daily cases are predicted with an accuracy of 92.30% and with an r2 score of 0.9893. Besides, daily deaths are predicted with an accuracy of 91.39% and with an r2 score of 0.9834. The closest rival in predictions is the bagging regressor. Nevertheless, the results provided by this algoritm changed in different runs and this fact is shown in the study, as well. Comparisons are based on test data. Comparisons with the earlier works are also provided.

Spatiotemporal evolution of deformation and LSTM prediction model over the slope of the deep excavation section at the head of the South-North Water Transfer Middle Route Canal

Slope deformation is one of the focal issues of concern during the normal operation and maintenance of the South-North Water Transfer Middle Route Project. To study the slope deformation evolution in the deep excavation section at the head of the canal, we applied 88 views of Sentinel-1A ascending image data from 2017 to 2019 and MT-InSAR(Multi-temporal InSAR) deformation monitoring technology to obtain long-time series deformation rates and cumulative deformation fields over the slope in the study area. Based on the analysis of the time-series monitoring data of the deformation field sample points, a LSTM (Long Short Term Memory Network) slope deformation predictive model was constructed to predict the slope deformation for the next 12 months at 12 sample points of the deep excavation slope. The impact of rainfall on slope deformation was investigated, and the reliability of the LSTM model was verified by using the measured data. The results show that the average annual deformation rate of the slope ranges from 10mm/a to 25mm/a, the maximum cumulative deformation is about 60 mm, and the slope of the excavated section is generally in an uplifted state. The rainfall-induced repeated uplift or subsidence of the canal slopes together with the peak deformation was closely related to the amount of rainfall during the wet season, and the longer the duration of the wet season, the more obvious the crest. Among the12 sample sites, the minimum and maximum deformation predicted using the LSTM model were 51.7 mm and 73.9 mm respectively, with the lowest correlation coefficient of 0.994 and the highest of 0.999. The maximum and minimum values of RMSE (Root Mean Square Error) were 4.4 mm and 3.6 mm respectively, indicating reliable prediction results. The results of the study can provide reference for the prevention and control of geological hazards in the South-North Water Transfer Canal.

Using wavelet transform and hybrid CNN - LSTM models on VOC & ultrasound IoT sensor data for non-visual maize disease detection

Early detection of plant diseases is crucial for safeguarding crop yield, especially in regions vulnerable to food insecurity, such as Sub-Saharan Africa. One of the significant contributors to maize crop yield loss is the Northern Leaf Blight (NLB), which traditionally takes 14-21 days to visually manifest on maize. This study introduces a novel approach for detecting NLB as early as 4-5 days using Internet of Things (IoT) sensors, which can identify the disease before any visual symptoms appear. Utilizing Convolutional Neural Networks (CNN) and Long Short Term Memory (LSTM) models, nonvisual measurements of Total Volatile Organic Compounds (VOCs) and ultrasound emissions from maize plants were captured and analyzed. A controlled experiment was conducted on four maize varieties, and the data obtained were used to develop and validate a hybrid CNN-LSTM model for VOC classification and an LSTM model for ultrasound anomaly detection. The hybrid CNN-LSTM model, enhanced with wavelet data preprocessing, achieved an F1 score of 0.96 and an Area under the ROC Curve (AUC) of 1.00. In contrast, the LSTM model exhibited an impressive 99.98% accuracy in identifying anomalies in ultrasound emissions. Our findings underscore the potential of IoT sensors in early disease detection, paving the way for innovative disease prevention strategies in agriculture. Future work will focus on optimizing the models for IoT device deployment, incorporating chatbot technology, and more sensor data will be incorporated for improved accuracy and evaluation of the models in a field environment.

High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery

In this study, we propose a novel long short-term memory (LSTM) neural network model that leverages color features (HSV: hue, saturation, value) extracted from street images to estimate air quality with particulate matter (PM) in four typical European environments: urban, suburban, villages, and the harbor. To evaluate its performance, we utilize concentration data for eight parameters of ambient PM (PM1.0, PM2.5, and PM10, particle number concentration, lung-deposited surface area, equivalent mass concentrations of ultraviolet PM, black carbon, and brown carbon) collected from a mobile monitoring platform during the nonheating season in downtown Augsburg, Germany, along with synchronized street view images. Experimental comparisons were conducted between the LSTM model and other deep learning models (recurrent neural network and gated recurrent unit). The results clearly demonstrate a better performance of the LSTM model compared with other statistically based models. The LSTM-HSV model achieved impressive interpretability rates above 80%, for the eight PM metrics mentioned above, indicating the expected performance of the proposed model. Moreover, the successful application of the LSTM-HSV model in other seasons of Augsburg city and various environments (suburbs, villages, and harbor cities) demonstrates its satisfactory generalization capabilities in both temporal and spatial dimensions. The successful application of the LSTM-HSV model underscores its potential as a versatile tool for the estimation of air pollution after presampling of the studied area, with broad implications for urban planning and public health initiatives.

Multitask Learning for Mental Health: Depression, Anxiety, Stress (DAS) Using Wearables

This study investigates the prediction of mental well-being factors-depression, stress, and anxiety-using the NetHealth dataset from college students. The research addresses four key questions, exploring the impact of digital biomarkers on these factors, their alignment with conventional psychology literature, the time-based performance of applied methods, and potential enhancements through multitask learning. The findings reveal modality rankings aligned with psychology literature, validated against paper-based studies. Improved predictions are noted with temporal considerations, and further enhanced by multitasking. Mental health multitask prediction results show aligned baseline and multitask performances, with notable enhancements using temporal aspects, particularly with the random forest (RF) classifier. Multitask learning improves outcomes for depression and stress but not anxiety using RF and XGBoost.

Prevalence and risk factors analysis of postpartum depression at early stage using hybrid deep learning model

Postpartum Depression Disorder (PPDD) is a prevalent mental health condition and results in severe depression and suicide attempts in the social community. Prompt actions are crucial in tackling PPDD, which requires a quick recognition and accurate analysis of the probability factors associated with this condition. This concern requires attention. The primary aim of our research is to investigate the feasibility of anticipating an individual's mental state by categorizing individuals with depression from those without depression using a dataset consisting of text along with audio recordings from patients diagnosed with PPDD. This research proposes a hybrid PPDD framework that combines Improved Bi-directional Long Short-Term Memory (IBi-LSTM) with Transfer Learning (TL) based on two Convolutional Neural Network (CNN) architectures, respectively CNN-text and CNN audio. In the proposed model, the CNN section efficiently utilizes TL to obtain crucial knowledge from text and audio characteristics, whereas the improved Bi-LSTM module combines written material and sound data to obtain intricate chronological interpersonal relationships. The proposed model incorporates an attention technique to augment the effectiveness of the Bi-LSTM scheme. An experimental analysis is conducted on the PPDD online textual and speech audio dataset collected from UCI. It includes textual features such as age, women's health tracks, medical histories, demographic information, daily life metrics, psychological evaluations, and 'speech records' of PPDD patients. Data pre-processing is applied to maintain the data integrity and achieve reliable model performance. The proposed model demonstrates a great performance in better precision, recall, accuracy, and F1-score over existing deep learning models, including VGG-16, Base-CNN, and CNN-LSTM. These metrics indicate the model's ability to differentiate among women at risk of PPDD vs. non-PPDD. In addition, the feature importance analysis demonstrates that specific risk factors substantially impact the prediction of PPDD. The findings of this research establish a basis for improved precision and promptness in assessing the risk of PPDD, which may ultimately result in earlier implementation of interventions and the establishment of support networks for women who are susceptible to PPDD.

Unlocking the potential of LSTM for accurate salary prediction with MLE, Jeffreys prior, and advanced risk functions

This article aims to address the challenge of predicting the salaries of college graduates, a subject of significant practical value in the fields of human resources and career planning. Traditional prediction models often overlook diverse influencing factors and complex data distributions, limiting the accuracy and reliability of their predictions. Against this backdrop, we propose a novel prediction model that integrates maximum likelihood estimation (MLE), Jeffreys priors, Kullback-Leibler risk function, and Gaussian mixture models to optimize LSTM models in deep learning. Compared to existing research, our approach has multiple innovations: First, we successfully improve the model's predictive accuracy through the use of MLE. Second, we reduce the model's complexity and enhance its interpretability by applying Jeffreys priors. Lastly, we employ the Kullback-Leibler risk function for model selection and optimization, while the Gaussian mixture models further refine the capture of complex characteristics of salary distribution. To validate the effectiveness and robustness of our model, we conducted experiments on two different datasets. The results show significant improvements in prediction accuracy, model complexity, and risk performance. This study not only provides an efficient and reliable tool for predicting the salaries of college graduates but also offers robust theoretical and empirical foundations for future research in this field.

An efficient consolidation of word embedding and deep learning techniques for classifying anticancer peptides: FastText+BiLSTM

Anticancer peptides (ACPs) are a group of peptides that exhibit antineoplastic properties. The utilization of ACPs in cancer prevention can present a viable substitute for conventional cancer therapeutics, as they possess a higher degree of selectivity and safety. Recent scientific advancements generate an interest in peptide-based therapies which offer the advantage of efficiently treating intended cells without negatively impacting normal cells. However, as the number of peptide sequences continues to increase rapidly, developing a reliable and precise prediction model becomes a challenging task. In this work, our motivation is to advance an efficient model for categorizing anticancer peptides employing the consolidation of word embedding and deep learning models. First, Word2Vec, GloVe, FastText, One-Hot-Encoding approaches are evaluated as embedding techniques for the purpose of extracting peptide sequences. Then, the output of embedding models are fed into deep learning approaches CNN, LSTM, BiLSTM. To demonstrate the contribution of proposed framework, extensive experiments are carried on widely-used datasets in the literature, ACPs250 and independent. Experiment results show the usage of proposed model enhances classification accuracy when compared to the state-of-the-art studies. The proposed combination, FastText+BiLSTM, exhibits 92.50% of accuracy for ACPs250 dataset, and 96.15% of accuracy for the Independent dataset, thence determining new state-of-the-art.

Enhancing drug discovery in schizophrenia: a deep learning approach for accurate drug-target interaction prediction - DrugSchizoNet

Drug discovery relies on the precise prognosis of drug-target interactions (DTI). Due to their ability to learn from raw data, deep learning (DL) methods have displayed outstanding performance over traditional approaches. However, challenges such as imbalanced data, noise, poor generalization, high cost, and time-consuming processes hinder progress in this field. To overcome the above challenges, we propose a DL-based model termed DrugSchizoNet for drug interaction (DI) prediction of Schizophrenia. Our model leverages drug-related data from the DrugBank and repoDB databases, employing three key preprocessing techniques. First, data cleaning eliminates duplicate or incomplete entries to ensure data integrity. Next, normalization is performed to enhance security and reduce costs associated with data acquisition. Finally, feature extraction is applied to improve the quality of input data. The three layers of the DrugSchizoNet model are the input, hidden and output layers. In the hidden layer, we employ dropout regularization to mitigate overfitting and improve generalization. The fully connected (FC) layer extracts relevant features, while the LSTM layer captures the sequential nature of DIs. In the output layer, our model provides confidence scores for potential DIs. To optimize the prediction accuracy, we utilize hyperparameter tuning through OB-MOA optimization. Experimental results demonstrate that DrugSchizoNet achieves a superior accuracy of 98.70%. The existing models, including CNN-RNN, DANN, CKA-MKL, DGAN, and CNN, across various evaluation metrics such as accuracy, recall, specificity, precision, F1 score, AUPR, and AUROC are compared with the proposed model. By effectively addressing the challenges of imbalanced data, noise, poor generalization, high cost and time-consuming processes, DrugSchizoNet offers a promising approach for accurate DTI prediction in Schizophrenia. Its superior performance demonstrates the potential of DL in advancing drug discovery and development processes.

The prediction of influenza-like illness using national influenza surveillance data and Baidu query data

BACKGROUND

Seasonal influenza and other respiratory tract infections are serious public health problems that need to be further addressed and investigated. Internet search data are recognized as a valuable source for forecasting influenza or other respiratory tract infection epidemics. However, the selection of internet search data and the application of forecasting methods are important for improving forecasting accuracy. The aim of the present study was to forecast influenza epidemics based on the long short-term memory neural network (LSTM) method, Baidu search index data, and the influenza-like-illness (ILI) rate.

METHODS

The official weekly ILI% data for northern and southern mainland China were obtained from the Chinese Influenza Center from 2018 to 2021. Based on the Baidu Index, search indices related to influenza infection over the corresponding time period were obtained. Pearson correlation analysis was performed to explore the association between influenza-related search queries and the ILI% of southern and northern mainland China. The LSTM model was used to forecast the influenza epidemic within the same week and at lags of 1-4 weeks. The model performance was assessed by evaluation metrics, including the mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE).

RESULTS

In total, 24 search queries in northern mainland China and 7 search queries in southern mainland China were found to be correlated and were used to construct the LSTM model, which included the same week and a lag of 1-4 weeks. The LSTM model showed that ILI% + mask with one lag week and ILI% + influenza name were good prediction modules, with reduced RMSE predictions of 16.75% and 4.20%, respectively, compared with the estimated ILI% for northern and southern mainland China.

CONCLUSIONS

The results illuminate the feasibility of using an internet search index as a complementary data source for influenza forecasting and the efficiency of using the LSTM model to forecast influenza epidemics.

Unsupervised novelty detection for time series using a deep learning approach

In the Smart Homes and IoT devices era, abundant available data offers immense potential for enhancing system intelligence. However, the need for effective anomaly detection models to identify and rectify unusual data and behaviors within Smart Home Systems (SHS) remains a critical challenge. This research delves into the relatively unexplored domain of novelty anomaly detection, particularly in the context of unlabeled datasets. Introducing the novel DeepMaly method, this approach provides a practical tool for SHS developers. Functioning seamlessly in an unsupervised manner, DeepMaly distinguishes between seasonal and actual anomalies through a unique process of training on unlabeled pristine features extracted from time series data. Leveraging a combination of Long Short-Term Memory (LSTM) and Deep Convolutional Neural Network (DCNN), the model is primed to detect anomalies in real-time. The research culminates in a comprehensive data prediction and classification process into normal and abnormal data based on specified anomaly thresholds and fraction percentages. Notably, this function operates seamlessly unsupervised, eliminating the need for labeled datasets. The study concludes with a complete data forecasting and sorting method that divides data into normal and abnormal categories based on defined anomaly thresholds and fraction percentages. Working in an unsupervised mode reduces the requirement for labeled datasets. The results highlight the model's prowess in new detection, which has been successfully applied to benchmark datasets. However, there is a restriction since deep learning algorithms can recognize noise as abnormalities. Finally, the investigation enhances SHS anomaly detection, providing a crucial tool for real-time anomaly identification in the ever-changing IoT and Smart Homes scene.

LSTMCNN: A hybrid machine learning model to unmask fake news

The widespread dissemination of false information across various online platforms has emerged as a matter of paramount concern due to the potential harm it poses to individuals, communities, and entire nations. Substantial efforts are currently underway in the research community to combat this issue. A burgeoning area of study gaining significant traction is the development of fake news identification techniques. However, this field faces formidable challenges primarily stemming from limited resources, including access to comprehensive datasets, computational resources, and evaluation tools. To overcome these challenges, researchers are exploring various methodologies. One promising approach involves the use of feature abstraction and vectorization techniques. In this context, we highly recommend utilizing the Python sci-kit-learn module, which offers many invaluable tools such as the Count Vectorizer and Tiff Vectorizer. These tools enable the efficient handling of text data by converting it into numerical representations, thereby facilitating subsequent analysis. Once the text data is appropriately transformed, the next crucial step involves feature selection. To achieve optimal results, researchers often employ feature selection methods based on misperception matrices. These methods allow for the exploration and selection of the most suitable features, which are essential for achieving the highest accuracy in fake news identification.

Optimizing Internet of Things Fog Computing: Through Lyapunov-Based Long Short-Term Memory Particle Swarm Optimization Algorithm for Energy Consumption Optimization

In the era of continuous development in Internet of Things (IoT) technology, smart services are penetrating various facets of societal life, leading to a growing demand for interconnected devices. Many contemporary devices are no longer mere data producers but also consumers of data. As a result, massive amounts of data are transmitted to the cloud, but the latency generated in edge-to-cloud communication is unacceptable for many tasks. In response to this, this paper introduces a novel contribution-a layered computing network built on the principles of fog computing, accompanied by a newly devised algorithm designed to optimize user tasks and allocate computing resources within rechargeable networks. The proposed algorithm, a synergy of Lyapunov-based, dynamic Long Short-Term Memory (LSTM) networks, and Particle Swarm Optimization (PSO), allows for predictive task allocation. The fog servers dynamically train LSTM networks to effectively forecast the data features of user tasks, facilitating proper unload decisions based on task priorities. In response to the challenge of slower hardware upgrades in edge devices compared to user demands, the algorithm optimizes the utilization of low-power devices and addresses performance limitations. Additionally, this paper considers the unique characteristics of rechargeable networks, where computing nodes acquire energy through charging. Utilizing Lyapunov functions for dynamic resource control enables nodes with abundant resources to maximize their potential, significantly reducing energy consumption and enhancing overall performance. The simulation results demonstrate that our algorithm surpasses traditional methods in terms of energy efficiency and resource allocation optimization. Despite the limitations of prediction accuracy in Fog Servers (FS), the proposed results significantly promote overall performance. The proposed approach improves the efficiency and the user experience of Internet of Things systems in terms of latency and energy consumption.

LSTM-SAGDTA: Predicting Drug-Target Binding Affinity with an Attention Graph Neural Network and LSTM Approach

INTRODUCTION

Drug development is a challenging and costly process, yet it plays a crucial role in improving healthcare outcomes. Drug development requires extensive research and testing to meet the demands for economic efficiency, cures, and pain relief.

METHODS

Drug development is a vital research area that necessitates innovation and collaboration to achieve significant breakthroughs. Computer-aided drug design provides a promising avenue for drug discovery and development by reducing costs and improving the efficiency of drug design and testing.

RESULTS

In this study, a novel model, namely LSTM-SAGDTA, capable of accurately predicting drug-target binding affinity, was developed. We employed SeqVec for characterizing the protein and utilized the graph neural networks to capture information on drug molecules. By introducing self-attentive graph pooling, the model achieved greater accuracy and efficiency in predicting drug-target binding affinity.

CONCLUSION

Moreover, LSTM-SAGDTA obtained superior accuracy over current state-of-the-art methods only by using less training time. The results of experiments suggest that this method represents a highprecision solution for the DTA predictor.

Spatial Decoding for Gaze Independent Brain-Computer Interface Based on Covert Visual Attention Shift Using Electroencephalography

The gaze-independent brain-computer interface (BCI) device is used to re-establish interaction for individuals who have abnormal eye movement. It may be possible to control the BCI by shifting your attention spatially. However, spatial attention is rarely employed to increase the effectiveness of target detection and is typically used to provide a simple "yes" or "no" response to the target recognition inquiry. To improve the effectiveness of detecting target, it is crucial to take advantage of the possible advantages of spatial attention. N2-posterior-contralateral (N2pc) component reflects correlates of visual spatial attention and is used to determine target position. In this study, a long-short-term memory (LSTM) network is used to answer "yes/no" questions by decoding covert spatial attention based on N2pc characteristics using EEG signals. The proposed LSTM-based model's average decoding accuracy is 92.79%. The target detection efficiency was successfully increased by about 4% when compared to conventional machine learning algorithms. The proposed model is tested on the independent dataset to validate its performance. The results of this work show that N2pc characteristics can be employed in gaze-independent BCIs for tracking covert attention shifts, which may help persons with poor eye mobility to connect with their environment.

Monitoring carbon emissions using deep learning and statistical process control: a strategy for impact assessment of governments' carbon reduction policies

Across the globe, governments are developing policies and strategies to reduce carbon emissions to address climate change. Monitoring the impact of governments' carbon reduction policies can significantly enhance our ability to combat climate change and meet emissions reduction targets. One promising area in this regard is the role of artificial intelligence (AI) in carbon reduction policy and strategy monitoring. While researchers have explored applications of AI on data from various sources, including sensors, satellites, and social media, to identify areas for carbon emissions reduction, AI applications in tracking the effect of governments' carbon reduction plans have been limited. This study presents an AI framework based on long short-term memory (LSTM) and statistical process control (SPC) for the monitoring of variations in carbon emissions, using UK annual CO2 emission (per capita) data, covering a period between 1750 and 2021. This paper used LSTM to develop a surrogate model for the UK's carbon emissions characteristics and behaviours. As observed in our experiments, LSTM has better predictive abilities than ARIMA, Exponential Smoothing and feedforward artificial neural networks (ANN) in predicting CO2 emissions on a yearly prediction horizon. Using the deviation of the recorded emission data from the surrogate process, the variations and trends in these behaviours are then analysed using SPC, specifically Shewhart individual/moving range control charts. The result shows several assignable variations between the mid-1990s and 2021, which correlate with some notable UK government commitments to lower carbon emissions within this period. The framework presented in this paper can help identify periods of significant deviations from a country's normal CO2 emissions, which can potentially result from the government's carbon reduction policies or activities that can alter the amount of CO2 emissions.