Layer-wise learning based stochastic gradient descent method for the optimization of deep convolutional neural network

A comprehensive review on TiO2-based heterogeneous photocatalytic technologies for emerging pollutants removal from water and wastewater: From engineering aspects to modeling approaches

The increasing presence of emerging pollutants (EPs) in water poses significant environmental and health risks, necessitating effective treatment solutions. Originating from industrial, agricultural, and domestic sources, these contaminants threaten ecological and public health, underscoring the urgent need for innovative and efficient treatment methods. TiO2-based semiconductor photocatalysts have emerged as a promising approach for the degradation of EPs, leveraging their unique band structures and heterojunction schemes. However, few studies have examined the synergistic effects of operating conditions on these contaminants, representing a key knowledge gap in the field. This review addresses this gap by exploring recent trends in TiO2-driven heterogeneous photocatalysis for water and wastewater treatment, with an emphasis on photoreactor setups and configurations. Challenges in scaling up these photoreactors are also discussed. Furthermore, Machine Learning (ML) models play a crucial role in developing predictive frameworks for complex processes, highlighting intricate temporal dynamics essential for understanding EPs behavior. This capability integrates seamlessly with Computational Fluid Dynamics (CFD) modeling, which is also addressed in this review. Together, these approaches illustrate how CFD can simulate the degradation of EPs by effectively coupling chemical kinetics, radiative transfer, and hydrodynamics in both suspended and immobilized photocatalysts. By elucidating the synergy between ML and CFD models, this study offers new insights into overcoming traditional limitations in photocatalytic process design and optimizing operating conditions. Finally, this review presents recommendations for future directions and insights on optimizing and modeling photocatalytic processes.

Facial emotion recognition using deep quantum and advanced transfer learning mechanism

Introduction

Facial expressions have become a common way for interaction among humans. People cannot comprehend and predict the emotions or expressions of individuals through simple vision. Thus, in psychology, detecting facial expressions or emotion analysis demands an assessment and evaluation of decisions for identifying the emotions of a person or any group during communication. With the recent evolution of technology, AI (Artificial Intelligence) has gained significant usage, wherein DL (Deep Learning) based algorithms are employed for detecting facial expressions.

Methods

The study proposes a system design that detects facial expressions by extracting relevant features using a Modified ResNet model. The proposed system stacks building-blocks with residual connections and employs an advanced extraction method with quantum computing, which significantly reduces computation time compared to conventional methods. The backbone stem utilizes a quantum convolutional layer comprised of several parameterized quantum-filters. Additionally, the research integrates residual connections in the ResNet-18 model with the Modified up Sampled Bottle Neck Process (MuS-BNP), retaining computational efficacy while benefiting from residual connections.

Results

The proposed model demonstrates superior performance by overcoming the issue of maximum similarity within varied facial expressions. The system's ability to accurately detect and differentiate between expressions is measured using performance metrics such as accuracy, F1-score, recall, and precision.

Discussion

This performance analysis confirms the efficacy of the proposed system, highlighting the advantages of quantum computing in feature extraction and the integration of residual connections. The model achieves quantum superiority, providing faster and more accurate computations compared to existing methodologies. The results suggest that the proposed approach offers a promising solution for facial expression recognition tasks, significantly improving both speed and accuracy.

Asking the right questions for mutagenicity prediction from BioMedical text

Assessing the mutagenicity of chemicals is an essential task in the drug development process. Usually, databases and other structured sources for AMES mutagenicity exist, which have been carefully and laboriously curated from scientific publications. As knowledge accumulates over time, updating these databases is always an overhead and impractical. In this paper, we first propose the problem of predicting the mutagenicity of chemicals from textual information in scientific publications. More simply, given a chemical and evidence in the natural language form from publications where the mutagenicity of the chemical is described, the goal of the model/algorithm is to predict if it is potentially mutagenic or not. For this, we first construct a golden standard data set and then propose MutaPredBERT, a prediction model fine-tuned on BioLinkBERT based on a question-answering formulation of the problem. We leverage transfer learning and use the help of large transformer-based models to achieve a Macro F1 score of >0.88 even with relatively small data for fine-tuning. Our work establishes the utility of large language models for the construction of structured sources of knowledge bases directly from scientific publications.

Deep learning framework for rapid and accurate respiratory COVID-19 prediction using chest X-ray images

COVID-19 is a contagious disease that affects the human respiratory system. Infected individuals may develop serious illnesses, and complications may result in death. Using medical images to detect COVID-19 from essentially identical thoracic anomalies is challenging because it is time-consuming, laborious, and prone to human error. This study proposes an end-to-end deep-learning framework based on deep feature concatenation and a Multi-head Self-attention network. Feature concatenation involves fine-tuning the pre-trained backbone models of DenseNet, VGG-16, and InceptionV3, which are trained on a large-scale ImageNet, whereas a Multi-head Self-attention network is adopted for performance gain. End-to-end training and evaluation procedures are conducted using the COVID-19_Radiography_Dataset for binary and multi-classification scenarios. The proposed model achieved overall accuracies (96.33% and 98.67%) and F1_scores (92.68% and 98.67%) for multi and binary classification scenarios, respectively. In addition, this study highlights the difference in accuracy (98.0% vs. 96.33%) and F_1 score (97.34% vs. 95.10%) when compared with feature concatenation against the highest individual model performance. Furthermore, a virtual representation of the saliency maps of the employed attention mechanism focusing on the abnormal regions is presented using explainable artificial intelligence (XAI) technology. The proposed framework provided better COVID-19 prediction results outperforming other recent deep learning models using the same dataset.

A structure-protecting kernelized semi-supervised space adjustment for classification

We introduce a semi-supervised space adjustment framework in this paper. In the introduced framework, the dataset contains two subsets: (a) training data subset (space-one data (SOD)) and (b) testing data subset (space-two data (STD)). Our semi-supervised space adjustment framework learns under three assumptions: (I) it is assumed that all data points in the SOD are labeled, and only a minority of the data points in the STD are labeled (we call the labeled space-two data as LSTD), (II) the size of LSTD is very small comparing to the size of SOD, and (III) it is also assumed that the data of SOD and the data of STD have different distributions. We denote the unlabeled space-two data by ULSTD, which is equal to STD - LSTD. The aim is to map the training data, i.e., the data from the training labeled data subset and those from LSTD (note that all labeled data are considered to be training data, i.e., SOD ∪ LSTD) into a shared space (ShS). The mapped SOD, ULSTD, and LSTD into ShS are named MSOD, MULSTD, and MLSTD, respectively. The proposed method does the mentioned mapping in such a way that structures of the data points in SOD and MSOD, in STD and MSTD, in ULSTD and MULSTD, and in LSTD and MLSTD are the same. In the proposed method, the mapping is proposed to be done by a principal component analysis transformation on kernelized data. In the proposed method, it is tried to find a mapping that (a) can maintain the neighbors of data points after the mapping and (b) can take advantage of the class labels that are known in STD during transformation. After that, we represent and formulate the problem of finding the optimal mapping into a non-linear objective function. To solve it, we transform it into a semidefinite programming (SDP) problem. We solve the optimization problem with an SDP solver. The examinations indicate the superiority of the learners trained in the data mapped by the proposed approach to the learners trained in the data mapped by the state of the art methods.

Dynamic elite strategy mayfly algorithm

The mayfly algorithm (MA), as a newly proposed intelligent optimization algorithm, is found that easy to fall into the local optimum and slow convergence speed. To address this, an improved mayfly algorithm based on dynamic elite strategy (DESMA) is proposed in this paper. Specifically, it first determines the specific space near the best mayfly in the current population, and dynamically sets the search radius. Then generating a certain number of elite mayflies within this range. Finally, the best one among the newly generated elite mayflies is selected to replace the best mayfly in the current population when the fitness value of elite mayfly is better than that of the best mayfly. Experimental results on 28 standard benchmark test functions from CEC2013 show that our proposed algorithm outperforms its peers in terms of accuracy speed and stability.

An intelligent wireless communication model based on multi-feature fusion and quantile regression neural network

Throughout the wireless communication network planning process, efficient signal reception power estimation is of great significance for accurate 5 G network deployment. The wireless propagation model predicts the radio wave propagation characteristics within the target communication coverage area, making it possible to estimate cell coverage, inter-cell network interference, and communication rates, etc. In this paper, we develop a series of features by considering various factors in the signal transmission process, including the shadow coefficient, absorption coefficient in test area and base station area, distance attenuation coefficient, density, azimuth angle, relative height and ground feature index coefficient. Then we design a quantile regression neural network to predict reference signal receiving power (RSRP) by feeding the above features. The network structure is specially constructed to be generalized on various complex real environments. To prove the effectiveness of proposed features and deep learning model, extensive comparative ablation experiments are applied. Finally, we have achieved the precision rate (PR), recall rate (RR), and inadequate coverage recognition rate (PCRR) of 84.3%, 78.4%, and 81.2% on the public dataset, respectively. The comparison with a series of state-of-the-art machine learning methods illustrates the superiority of the proposed method.

Detection of the Deep-Sea Plankton Community in Marine Ecosystem with Underwater Robotic Platform

Variations in the quantity of plankton impact the entire marine ecosystem. It is of great significance to accurately assess the dynamic evolution of the plankton for monitoring the marine environment and global climate change. In this paper, a novel method is introduced for deep-sea plankton community detection in marine ecosystem using an underwater robotic platform. The videos were sampled at a distance of 1.5 m from the ocean floor, with a focal length of 1.5-2.5 m. The optical flow field is used to detect plankton community. We showed that for each of the moving plankton that do not overlap in space in two consecutive video frames, the time gradient of the spatial position of the plankton are opposite to each other in two consecutive optical flow fields. Further, the lateral and vertical gradients have the same value and orientation in two consecutive optical flow fields. Accordingly, moving plankton can be accurately detected under the complex dynamic background in the deep-sea environment. Experimental comparison with manual ground-truth fully validated the efficacy of the proposed methodology, which outperforms six state-of-the-art approaches.

Fuzzy segmentation and black widow-based optimal SVM for skin disease classification

The skin, which has seven layers, is the main human organ and external barrier. According to the World Health Organization (WHO), skin cancer is the fourth leading cause of non-fatal disease risk. In medicinal fields, skin disease classification is a major challenging issue due to inaccurate outputs, overfitting, larger computational cost, and so on. We presented a novel approach of support vector machine-based black widow optimization (SVM-BWO) for skin disease classification. Five different kinds of skin disease images are taken such as psoriasis, paederus, herpes, melanoma, and benign with healthy images which are chosen for this work. The pre-processing step is handled to remove the noises from the original input images. Thereafter, the novel fuzzy set segmentation algorithm subsequently segments the skin lesion region. From this, the color, gray-level co-occurrence matrix texture, and shape features are extracted for further process. Skin disease is classified with the usage of the SVM-BWO algorithm. The implementation works are handled in MATLAB-2018a, thereby the dataset images were collected from ISIC-2018 datasets. Experimentally, various kinds of performance analyses with state-of-the-art techniques are performed. Anyway, the proposed methodology outperforms better classification accuracy of 92% than other methods. Workflow diagram of the proposed methodology.