Measurement of 3D Wrist Angles by Combining Textile Stretch Sensors and AI Algorithm

The wrist is one of the most complex joints in our body, composed of eight bones. Therefore, measuring the angles of this intricate wrist movement can prove valuable in various fields such as sports analysis and rehabilitation. Textile stretch sensors can be easily produced by immersing an E-band in a SWCNT solution. The lightweight, cost-effective, and reproducible nature of textile stretch sensors makes them well suited for practical applications in clothing. In this paper, wrist angles were measured by attaching textile stretch sensors to an arm sleeve. Three sensors were utilized to measure all three axes of the wrist. Additionally, sensor precision was heightened through the utilization of the Multi-Layer Perceptron (MLP) technique, a subtype of deep learning. Rather than fixing the measurement values of each sensor to specific axes, we created an algorithm utilizing the coupling between sensors, allowing the measurement of wrist angles in three dimensions. Using this algorithm, the error angle of wrist angles measured with textile stretch sensors could be measured at less than 4.5°. This demonstrated higher accuracy compared to other soft sensors available for measuring wrist angles.

From consistent subjective assessment of skin sensitivity severity to its accurate objective scoring

BACKGROUND

Sensitive skin (SenS) is a syndrome leading to unpleasant sensations with little visible signs. Grading its severity generally relies on questionnaires or subjective ratings.

MATERIALS AND METHODS

The SenS status of 183 subjects was determined by trained assessors. Answers from a four-item questionnaire were converted into numerical scores, leading to a 0-15 SenS index that was asked twice or thrice. Parameters from hyperspectral images were used as input for a multi-layer perceptron (MLP) neural network to predict the four-item questionnaire score of subjects. The resulting model was used to evaluate the soothing effect of a cosmetic cream applied to one hemiface, comparing it to that of a placebo applied to the other hemiface.

RESULTS

The four-item questionnaire score accurately predicts SenS assessors' classification (92.7%) while providing insight into SenS severity. Most subjects providing repeatable replies are non-SenS, but accepting some variability in answers enables identifying subjects with consistent replies encompassing a majority of SenS subjects. The MLP neural network model predicts the SenS score of subjects with consistent replies from full-face hyperspectral images (R2 Validation set  = 0.969). A similar quality is obtained with hemiface images. Comparing the effect of applying a soothing cosmetic to that of a placebo revealed that subjects with the highest instrumental index (> 5) show significant SenS improvement.

CONCLUSION

A four-item questionnaire enables calculating a SenS index grading its severity. Objective evaluation using hyperspectral images with an MLP neural network accurately predicts SenS severity and its favourable evolution upon the application of a soothing cream.

Discovering effect of intuitionistic fuzzy transformation in multi-layer perceptron for heart disease prediction: a study

Cardiovascular disease (CVD) is the one of the most fatal diseases in the world we have seen in last two decades. For heart disease detection, imprecision in clinical parameters may occur due to error in taking readings or in measuring devices or environmental conditions etc. Hence, introducing fuzzy set theory in feature engineering may give better results as it deals with uncertainty. But in fuzzy set theory, only one uncertainty is considered, which is membership degree or degree of belongingness. Intuitionistic fuzzy set (IFS) considers two uncertainties - membership degree and non-membership degree and so IFS may provide efficient results. To reduce the risk of heart disease, an advanced deep learning algorithm will play a significant role in heart disease prediction that will help physicians to diagnose early. In this paper, we have established a transformation of patient features using i) intuitionistic fuzzy parameters, where Sugeno-type fuzzy complement is used and ii) fuzzy parameters, where gamma membership function is used. These transformed attributes are applied on Deep Learning prediction algorithm as Multi-layer Perceptron (MLP). The novelty of the paper lies from feature transformation to deep learning. It is observed that intuitionistic fuzzy transformation approach, keeping model parameters intact, significantly outperforms non-fuzzy method and gammy fuzzy Transformation, which is reflected in evaluation mechanisms.

Advancing single-cell RNA-seq data analysis through the fusion of multi-layer perceptron and graph neural network

The advancement of single-cell sequencing technology has smoothed the ability to do biological studies at the cellular level. Nevertheless, single-cell RNA sequencing (scRNA-seq) data presents several obstacles due to the considerable heterogeneity, sparsity and complexity. Although many machine-learning models have been devised to tackle these difficulties, there is still a need to enhance their efficiency and accuracy. Current deep learning methods often fail to fully exploit the intrinsic interconnections within cells, resulting in unsatisfactory results. Given these obstacles, we propose a unique approach for analyzing scRNA-seq data called scMPN. This methodology integrates multi-layer perceptron and graph neural network, including attention network, to execute gene imputation and cell clustering tasks. In order to evaluate the gene imputation performance of scMPN, several metrics like cosine similarity, median L1 distance and root mean square error are used. These metrics are utilized to compare the efficacy of scMPN with other existing approaches. This research utilizes criteria such as adjusted mutual information, normalized mutual information and integrity score to assess the efficacy of cell clustering across different approaches. The superiority of scMPN over current single-cell data processing techniques in cell clustering and gene imputation investigations is shown by the experimental findings obtained from four datasets with gold-standard cell labels. This observation demonstrates the efficacy of our suggested methodology in using deep learning methodologies to enhance the interpretation of scRNA-seq data.

Predicting metabolite-disease associations based on auto-encoder and non-negative matrix factorization

Metabolism refers to a series of orderly chemical reactions used to maintain life activities in organisms. In healthy individuals, metabolism remains within a normal range. However, specific diseases can lead to abnormalities in the levels of certain metabolites, causing them to either increase or decrease. Detecting these deviations in metabolite levels can aid in diagnosing a disease. Traditional biological experiments often rely on a lot of manpower to do repeated experiments, which is time consuming and labor intensive. To address this issue, we develop a deep learning model based on the auto-encoder and non-negative matrix factorization named as MDA-AENMF to predict the potential associations between metabolites and diseases. We integrate a variety of similarity networks and then acquire the characteristics of both metabolites and diseases through three specific modules. First, we get the disease characteristics from the five-layer auto-encoder module. Later, in the non-negative matrix factorization module, we extract both the metabolite and disease characteristics. Furthermore, the graph attention auto-encoder module helps us obtain metabolite characteristics. After obtaining the features from three modules, these characteristics are merged into a single, comprehensive feature vector for each metabolite-disease pair. Finally, we send the corresponding feature vector and label to the multi-layer perceptron for training. The experiment demonstrates our area under the receiver operating characteristic curve of 0.975 and area under the precision-recall curve of 0.973 in 5-fold cross-validation, which are superior to those of existing state-of-the-art predictive methods. Through case studies, most of the new associations obtained by MDA-AENMF have been verified, further highlighting the reliability of MDA-AENMF in predicting the potential relationships between metabolites and diseases.

[Hyperspectral imaging technology distinguishes between Puerariae Lobatae Radix and Puerariae Lobatae Caulis]

Puerariae Lobatae Radix, the dried root of Pueraria lobata, is a traditional Chinese medicine with a long history. Puerariae Lobatae Caulis as an adulterant is always mixed into Puerariae Lobatae Radix for sales in the market. This study employed hyperspectral imaging(HSI) to distinguish between the two products. VNIR lens(spectral scope of 410-990 nm) and SWIR lens(spectral scope of 950-2 500 nm) were used for image acquiring. Multi-layer perceptron(MLP), partial least squares discriminant analysis(PLS-DA), and support vector machine(SVM) were employed to establish the full-waveband models and select the effective wavelengths for the distinguishing between Puerariae Lobatae Caulis and Puerariae Lobatae Radix, which provided technical and data support for the development of quick inspection equipment based on HSI. The results showed that MLP model outperformed PLS-DA and SVM models in the accuracy of discrimination with full wavebands in VNIR, SWIR, and VNIR+SWIR lens, which were 95.26%, 99.11%, and 99.05%, respectively. The discriminative band selection(DBS) algorithm was employed to select the effective wavelengths, and the discrimination accuracy was 93.05%, 98.05%, and 98.74% in the three different spectral scopes, respectively. On this basis, the MLP model combined with the effective wavelengths within the range of 2 100-2 400 nm can achieve the accuracy of 97.74%, which was close to that obtained with the full waveband. This waveband can be used to develop quick inspection devices based on HSI for the rapid and non-destructive distinguishing between Puerariae Lobatae Radix and Puerariae Lobatae Caulis.

Predicting Prediabetes Using Simple a Multi-Layer Perceptron Neural Network Model

In over 60% of patients with prediabetes, the evolution to diabetes can be stopped by changing lifestyle. Application of prediabetes criteria existing in accredited guidelines is very useful, representing an effective way to avoid prediabetes and diabetes. Although these guidelines imposed by the international diabetes federation are constantly updated, many doctors do not apply, mainly due to lack of time, the recommended steps for diagnosis and treatment. In this paper, a multi-layer perpeptron neural network model for prediabetes prediction is proposed, based on a dataset with 125 persons (men and women), with the following features: gender (S), serum glucose (G), serum triglycerides (TG), serum high-density lipoprotein cholesterol (HDL), waist circumference (WC) and systolic blood pressure (SBP). The output feature in the dataset (prediabetes or not) was based on a standardized medical criterion named Adult Treatment Panel III Guidelines (ATP III), which specifies that prediabetes diagnostic can be establish if at least three of five parameters are outside the scale of their normal values. Satisfactory results were obtained in evaluating the model.

ConMLP: MLP-Based Self-Supervised Contrastive Learning for Skeleton Data Analysis and Action Recognition

Human action recognition has drawn significant attention because of its importance in computer vision-based applications. Action recognition based on skeleton sequences has rapidly advanced in the last decade. Conventional deep learning-based approaches are based on extracting skeleton sequences through convolutional operations. Most of these architectures are implemented by learning spatial and temporal features through multiple streams. These studies have enlightened the action recognition endeavor from various algorithmic angles. However, three common issues are observed: (1) The models are usually complicated; therefore, they have a correspondingly higher computational complexity. (2) For supervised learning models, the reliance on labels during training is always a drawback. (3) Implementing large models is not beneficial to real-time applications. To address the above issues, in this paper, we propose a multi-layer perceptron (MLP)-based self-supervised learning framework with a contrastive learning loss function (ConMLP). ConMLP does not require a massive computational setup; it can effectively reduce the consumption of computational resources. Compared with supervised learning frameworks, ConMLP is friendly to the huge amount of unlabeled training data. In addition, it has low requirements for system configuration and is more conducive to being embedded in real-world applications. Extensive experiments show that ConMLP achieves the top one inference result of 96.9% on the NTU RGB+D dataset. This accuracy is higher than the state-of-the-art self-supervised learning method. Meanwhile, ConMLP is also evaluated in a supervised learning manner, which has achieved comparable performance to the state of the art of recognition accuracy.

Development of machine learning models to predict posterior capsule rupture based on the EUREQUO registry

PURPOSE

To evaluate the performance of different probabilistic classifiers to predict posterior capsule rupture (PCR) prior to cataract surgery.

METHODS

Three probabilistic classifiers were constructed to estimate the probability of PCR: a Bayesian network (BN), logistic regression (LR) model, and multi-layer perceptron (MLP) network. The classifiers were trained on a sample of 2 853 376 surgeries reported to the European Registry of Quality Outcomes for Cataract and Refractive Surgery (EUREQUO) between 2008 and 2018. The performance of the classifiers was evaluated based on the area under the precision-recall curve (AUPRC) and compared to existing scoring models in the literature. Furthermore, direct risk factors for PCR were identified by analysing the independence structure of the BN.

RESULTS

The MLP network predicted PCR overall the best (AUPRC 13.1 ± 0.41%), followed by the BN (AUPRC 8.05 ± 0.39%) and the LR model (AUPRC 7.31 ± 0.15%). Direct risk factors for PCR include preoperative best-corrected visual acuity (BCVA), year of surgery, operation type, anaesthesia, target refraction, other ocular comorbidities, white cataract, and corneal opacities.

CONCLUSIONS

Our results suggest that the MLP network performs better than existing scoring models in the literature, despite a relatively low precision at high recall. Consequently, implementing the MLP network in clinical practice can potentially decrease the PCR rate.

Intelligent based hybrid renewable energy resources forecasting and real time power demand management system for resilient energy systems

The rapid growth of hybrid renewable Distributed Energy Resources (DERs) generation possess various challenges with inaccurate forecast models in stochastic power systems. The prime objective of this research is to maximum utilization of scheduled power from hybrid renewable based DERs to maintain the load-demand profile with reduce distributed grid burden. The proposed mixed input-based cascaded artificial neural network ( C A N N M F ) is realized for the prediction of a short-term based hourly solar irradiance and wind speed. The testing approach is performed through a historical hourly dataset of the proposed site. Further, the normalized data sets are divided into hourly-based samples for validating the load demand power with respect to the variation in metrological data. In this paper, Adaptive Neuro-Fuzzy Inference System (ANFIS) model is simulated for short-term power demand prediction. This adaptive methodology is an effective approach for load-demand management which is based on cross-entropy. It also confirmed that during testing, the forecasting mean error and cross-entropy are less than 5% under a specific time slap of an individual day. The regression analysis is performed through the time series fitting simulation tool at different time horizons. The performance evaluation of the designed model is compared with the multi-layer perceptron model. Simulation results display the proposed mixed input-based cascaded system has enhanced accuracy and optimal performance than the multi-output correlated perceptron model.

A novel network architecture combining central-peripheral deviation with image-based convolutional neural networks for diffusion tensor imaging studies

Brain imaging research is a very challenging topic due to complex structure and lack of explicitly identifiable features in the image. With the advancement of magnetic resonance imaging (MRI) technologies, such as diffusion tensor imaging (DTI), developing classification methods to improve clinical diagnosis is crucial. This paper proposes a classification method for DTI data based on a novel neural network strategy that combines a convolutional neural network (CNN) with a multilayer neural network using central-peripheral deviation (CPD), which reflects diffusion dynamics in the white matter by spatially evaluating the deviation of diffusion coefficients between the inner and outer parts of the brain. In our method, a multilayer perceptron (MLP) using CPD is combined with the final layers for classification after reducing the dimensions of images in the convolutional layers of the neural network architecture. In terms of training loss and the classification error, the proposed classification method improves the existing image classification with CNN. For real data analysis, we demonstrate how to process raw DTI image data sets obtained from a traumatic brain injury study (MagNeTS) and a brain atlas construction study (ICBM), and apply the proposed approach to the data, successfully improving classification performance with two age groups.

A Multimodal Classification Architecture for the Severity Diagnosis of Glaucoma Based on Deep Learning

Glaucoma is an optic neuropathy that leads to characteristic visual field defects. However, there is no cure for glaucoma, so the diagnosis of its severity is essential for its prevention. In this paper, we propose a multimodal classification architecture based on deep learning for the severity diagnosis of glaucoma. In this architecture, a gray scale image of the visual field is first reconstructed with a higher resolution in the preprocessing stage, and more subtle feature information is provided for glaucoma diagnosis. We then use multimodal fusion technology to integrate fundus images and gray scale images of the visual field as the input of this architecture. Finally, the inherent limitation of convolutional neural networks (CNNs) is addressed by replacing the original classifier with the proposed classifier. Our architecture is trained and tested on the datasets provided by the First Affiliated Hospital of Kunming Medical University, and the results show that the proposed architecture achieves superior performance for glaucoma diagnosis.

Evaluation of the Performance of a Composite Profile at Elevated Temperatures Using Finite Element and Hybrid Artificial Intelligence Techniques

It is very important to keep structures and constructional elements in service during and after exposure to elevated temperatures. Investigation of the structural behaviour of different components and structures at elevated temperatures is an approach to manipulate the serviceability of the structures during heat exposure. Channel connectors are widely used shear connectors not only for their appealing mechanical properties but also for their workability and cost-effective nature. In this study, a finite element (FE) evaluation was performed on an authentic composite model, and the behaviour of the channel shear connector at elevated temperature was examined. Furthermore, a novel hybrid intelligence algorithm based on a feature-selection trait with the incorporation of particle swarm optimization (PSO) and multi-layer perceptron (MLP) algorithms has been developed to predict the slip response of the channel. The hybrid intelligence algorithm that uses artificial neural networks is performed on derived data from the FE study. Finally, the obtained numerical results are compared with extreme learning machine (ELM) and radial basis function (RBF) results. The MLP-PSO represented dramatically accurate results for slip value prediction at elevated temperatures. The results proved the active presence of the channels, especially to improve the stiffness and loading capacity of the composite beam. Although the height enhances the ductility, stiffness is significantly reduced at elevated temperatures. According to the results, temperature, failure load, the height of connector and concrete block strength are the key governing parameters for composite floor design against high temperatures.

Comparative performance analysis of support vector regression and artificial neural network for prediction of municipal solid waste generation

The evolution of machine learning (ML) algorithms provides researchers and engineers with state-of-the-art tools to dynamically model complex relationships. The design and operation of municipal solid waste (MSW) management systems require accurate estimation of generation rates. In this study, we applied rapid, non-linear and non-parametric data driven ML algorithms independently, multi-layer perceptron artificial neural network (MLP-ANN) and support vector regression (SVR) models to predict annual MSW generation rates in Bahrain. Models were trained and tested with MSW generation data for period of 1997-2019. The population, gross domestic product, annual tourist numbers, annual electricity consumption and total annual CO₂ emissions were selected as explanatory variables and incorporated into developed models. The zero score normalization (ZSN) and minimum maximum normalization (MMN) methods were utilized to improve the quality of data and subsequently enhances the performance of ML algorithms. Statistical metrics were employed to discriminate performance of MLP-ANN and SVR models. The linear, polynomial, radial basis function (RBF) and sigmoid kernel functions were investigated to find the optimal SVR model. Results showed that RBF-SVR model with R² value of 0.97% and 4.82% and absolute forecasting error (AFE) for the period of 2008 and 2019 exhibits superior prediction and robustness in comparison to MLP-ANN. The efficacy of MLP-ANN model was also reasonably successful with R² value of 0.94. It was shown that MMN pre-processing generated optimal MLP-ANN model while ZSN pre-processing produced optimal RBF-SVR model. This work also highlights the importance of application of ML modelling approaches to plan and implement their roadmap for waste management systems by policymakers.

Artificial Intelligence-Enabled DDoS Detection for Blockchain-Based Smart Transport Systems

A smart public transport system is expected to be an integral part of our human lives to improve our mobility and reduce the effect of our carbon footprint. The safety and ongoing maintenance of the smart public transport system from cyberattacks are vitally important. To provide more comprehensive protection against potential cyberattacks, we propose a novel approach that combines blockchain technology and a deep learning method that can better protect the smart public transport system. By the creation of signed and verified blockchain blocks and chaining of hashed blocks, the blockchain in our proposal can withstand unauthorized integrity attack that tries to forge sensitive transport maintenance data and transactions associated with it. A hybrid deep learning-based method, which combines autoencoder (AE) and multi-layer perceptron (MLP), in our proposal can effectively detect distributed denial of service (DDoS) attempts that can halt or block the urgent and critical exchange of transport maintenance data across the stakeholders. The experimental results of the hybrid deep learning evaluated on three different datasets (i.e., CICDDoS2019, CIC-IDS2017, and BoT-IoT) show that our deep learning model is effective to detect a wide range of DDoS attacks achieving more than 95% F1-score across all three datasets in average. The comparison of our approach with other similar methods confirms that our approach covers a more comprehensive range of security properties for the smart public transport system.

Use of Artificial Neural Network Model for Rice Quality Prediction Based on Grain Physical Parameters

The main goal of this study was to test the ability of an artificial neural network (ANN) for rice quality prediction based on grain physical parameters and to conduct a comparison with multiple linear regression (MLR) using 66 samples in duplicate. The parameters used for rice quality prediction are related to biochemical composition (starch, amylose, ash, fat, and protein concentration) and pasting parameters (peak viscosity, trough, breakdown, final viscosity, and setback). These parameters were estimated based on grain appearance (length, width, length/width ratio, total whiteness, vitreous whiteness, and chalkiness), and milling yield (husked, milled, head) data. The MLR models were characterized by very low coefficient determination (R2 = 0.27-0.96) and a root-mean-square error (RMSE) (0.08-0.56). Meanwhile, the ANN models presented a range for R2 = 0.97-0.99, being characterized for R2 = 0.98 (training), R2 = 0.88 (validation), and R2 = 0.90 (testing). According to these results, the ANN algorithms could be used to obtain robust models to predict both biochemical and pasting profiles parameters in a fast and accurate form, which makes them suitable for application to simultaneous qualitative and quantitative analysis of rice quality. Moreover, the ANN prediction method represents a promising approach to estimate several targeted biochemical and viscosity parameters with a fast and clean approach that is interesting to industry and consumers, leading to better assessment of rice classification for authenticity purposes.

Machine Learning Methods and Synthetic Data Generation to Predict Large Wildfires

Wildfires are becoming more frequent in different parts of the globe, and the ability to predict when and where they will occur is a complex process. Identifying wildfire events with high probability of becoming a large wildfire is an important task for supporting initial attack planning. Different methods, including those that are physics-based, statistical, and based on machine learning (ML) are used in wildfire analysis. Among the whole, those based on machine learning are relatively novel. In addition, because the number of wildfires is much greater than the number of large wildfires, the dataset to be used in a ML model is imbalanced, resulting in overfitting or underfitting the results. In this manuscript, we propose to generate synthetic data from variables of interest together with ML models for the prediction of large wildfires. Specifically, five synthetic data generation methods have been evaluated, and their results are analyzed with four ML methods. The results yield an improvement in the prediction power when synthetic data are used, offering a new method to be taken into account in Decision Support Systems (DSS) when managing wildfires.

Automatic Detection of a Student's Affective States for Intelligent Teaching Systems

AutoTutor is an automated computer tutor that simulates human tutors and holds conversations with students in natural language. Using data collected from AutoTutor, the following determinations were sought: Can we automatically classify affect states from intelligent teaching systems to aid in the detection of a learner’s emotional state? Using frequency patterns of AutoTutor feedback and assigned user emotion in a series of pairs, can the next pair of feedback/emotion series be predicted? Through a priori data mining approaches, we found dominant frequent item sets that predict the next set of responses. Thirty-four participants provided 200 turns between the student and the AutoTutor. Two series of attributes and emotions were concatenated into one row to create a record of previous and next set of emotions. Feature extraction techniques, such as multilayer-perceptron and naive Bayes, were performed on the dataset to perform classification for affective state labeling. The emotions ‘Flow’ and ‘Frustration’ had the highest classification of all the other emotions when measured against other emotions and their respective attributes. The most common frequent item sets were ‘Flow’ and ‘Confusion’.

Application of artificial intelligence neural network modeling to predict the generation of domestic, commercial and construction wastes

Reliable prediction of municipal solid waste (MSW) generation rates is a significant element of planning and implementation of sustainable solid waste management strategies. In this study, the multi-layer perceptron artificial neural network (MLP-ANN) is applied to verify the prediction of annual generation rates of domestic, commercial and construction and demolition (C&D) wastes from the year 1997 to 2016 in Askar Landfill site in the Kingdom of Bahrain. The proposed robust predictive models incorporated selected explanatory variables to reflect the influence of social, demographical, economic, geographical and touristic factors upon waste generation rates (WGRs). The Mean Squared Error (MSE) and coefficient of determination (R²) are used as performance indicators to evaluate effectiveness of the developed models. MLP-ANN models exhibited strong accuracy in predictions with high R² and low MSE values. The R² values for domestic, commercial and C&D wastes are 0.95, 0.99 and 0.91, respectively. Our results show that the developed MLP-ANN models are effective for the prediction of WGRs from different sources and could be considered as a cost-effective approach for planning integrated MSW management systems.

Diagnosis of diabetes in pregnant woman using a Chaotic-Jaya hybridized extreme learning machine model

As stated by World Health Organization (WHO) report, 246 million individuals have suffered with diabetes disease over worldwide and it is anticipated that by 2025 this estimation can cross 380 million. So, the proper and quick diagnosis of this disease is turned into a significant challenge for the machine learning researchers. This paper aims to design a robust model for diagnosis of diabetes using a hybrid approach of Chaotic-Jaya (CJaya) algorithm with Extreme Learning Machine (ELM), which is named as CJaya-ELM. In this paper, Jaya algorithm with Chaotic learning approach is used to optimize the random parameters of ELM classifier. Here, to assess the efficacy of the designed model, Pima Indian diabetes dataset is considered. Here, the designed model CJaya-ELM, has been compared with basic ELM, Teaching Learning Based Optimization algorithm (TLBO) optimized ELM (TLBO-ELM), Multi-Layer Perceptron (MLP), Jaya algorithm optimized MLP (Jaya-MLP), TLBO algorithm optimized MLP (TLBO-MLP) and CJaya algorithm optimized MLP models. CJaya-ELM model resulted in the highest testing accuracy of 0.9687, sensitivity of 1, specificity of 0.9688 with 0.9782 area under curve (AUC) value. Results reveal that CJaya-ELM model effectively classifies both the positive and negative samples of Pima and outperforms the competitors.

Implementation of Analog Perceptron as an Essential Element of Configurable Neural Networks

Perceptron is an essential element in neural network (NN)-based machine learning, however, the effectiveness of various implementations by circuits is rarely demonstrated from chip testing. This paper presents the measured silicon results for the analog perceptron circuits fabricated in a 0.6 μm/±2.5 V complementary metal oxide semiconductor (CMOS) process, which are comprised of digital-to-analog converter (DAC)-based multipliers and phase shifters. The results from the measurement convinces us that our implementation attains the correct function and good performance. Furthermore, we propose the multi-layer perceptron (MLP) by utilizing analog perceptron where the structure and neurons as well as weights can be flexibly configured. The example given is to design a 2-3-4 MLP circuit with rectified linear unit (ReLU) activation, which consists of 2 input neurons, 3 hidden neurons, and 4 output neurons. Its experimental case shows that the simulated performance achieves a power dissipation of 200 mW, a range of working frequency from 0 to 1 MHz, and an error ratio within 12.7%. Finally, to demonstrate the feasibility and effectiveness of our analog perceptron for configuring a MLP, seven more analog-based MLPs designed with the same approach are used to analyze the simulation results with respect to various specifications, in which two cases are used to compare to their digital counterparts with the same structures.

Systematic Comparison of the Influence of Different Data Preprocessing Methods on the Performance of Gait Classifications Using Machine Learning

Human movements are characterized by highly non-linear and multi-dimensional interactions within the motor system. Therefore, the future of human movement analysis requires procedures that enhance the classification of movement patterns into relevant groups and support practitioners in their decisions. In this regard, the use of data-driven techniques seems to be particularly suitable to generate classification models. Recently, an increasing emphasis on machine-learning applications has led to a significant contribution, e.g., in increasing the classification performance. In order to ensure the generalizability of the machine-learning models, different data preprocessing steps are usually carried out to process the measured raw data before the classifications. In the past, various methods have been used for each of these preprocessing steps. However, there are hardly any standard procedures or rather systematic comparisons of these different methods and their impact on the classification performance. Therefore, the aim of this analysis is to compare different combinations of commonly applied data preprocessing steps and test their effects on the classification performance of gait patterns. A publicly available dataset on intra-individual changes of gait patterns was used for this analysis. Forty-two healthy participants performed 6 sessions of 15 gait trials for 1 day. For each trial, two force plates recorded the three-dimensional ground reaction forces (GRFs). The data was preprocessed with the following steps: GRF filtering, time derivative, time normalization, data reduction, weight normalization and data scaling. Subsequently, combinations of all methods from each preprocessing step were analyzed by comparing their prediction performance in a six-session classification using Support Vector Machines, Random Forest Classifiers, Multi-Layer Perceptrons, and Convolutional Neural Networks. The results indicate that filtering GRF data and a supervised data reduction (e.g., using Principal Components Analysis) lead to increased prediction performance of the machine-learning classifiers. Interestingly, the weight normalization and the number of data points (above a certain minimum) in the time normalization does not have a substantial effect. In conclusion, the present results provide first domain-specific recommendations for commonly applied data preprocessing methods and might help to build more comparable and more robust classification models based on machine learning that are suitable for a practical application.

Automated method for detecting and reading seven-segment digits from images of blood glucose metres and blood pressure monitors

There is an increasing need for fast and accurate transfer of readings from blood glucose metres and blood pressure monitors to a smartphone mHealth application, without a dependency on Bluetooth technology. Most of the medical devices recommended for home monitoring use a seven-segment display to show the recorded measurement to the patient. We aimed to achieve accurate detection and reading of the seven-segment digits displayed on these medical devices using an image taken in a realistic scenario by a smartphone camera. A synthetic dataset of seven-segment digits was developed in order to train and test a digit classifier. A dataset containing realistic images of blood glucose metres and blood pressure monitors using a variety of smartphone cameras was also created. The digit classifier was evaluated on a dataset of seven-segment digits manually extracted from the medical device images. These datasets along with the code for its development have been made public. The developed algorithm first preprocessed the input image using retinex with two bilateral filters and adaptive histogram equalisation. Subsequently, the digit segments were automatically located within the image by two techniques operating in parallel: Maximally Stable Extremal Regions (MSER) and connected components of a binarised image. A filtering and clustering algorithm was then designed to combine digit segments to form seven-segment digits. The resulting digits were classified using a Histogram of Orientated Gradients (HOG) feature set and a neural network trained on the synthetic digits. The model achieved 93% accuracy on digits found on the medical devices. The digit location algorithm achieved a F1 score of 0.87 and 0.80 on images of blood glucose metres and blood pressure monitors respectively. Very few assumptions were made of the locations of the digits on the devices so that the proposed algorithm can be easily implemented on new devices.

Deceleration Planning Algorithm Based on Classified Multi-Layer Perceptron Models for Smart Regenerative Braking of EV in Diverse Deceleration Conditions

The smart regenerative braking system (SRS) is an autonomous version of one-pedal driving in electric vehicles. To implement SRS, a deceleration planning algorithm is necessary to generate the deceleration used in automatic regenerative control. To reduce the discomfort from the automatic regeneration, the deceleration should be similar to human driving. In this paper, a deceleration planning algorithm based on multi-layer perceptron (MLP) is proposed. The MLP models can mimic the human driving behavior by learning the driving data. In addition, the proposed deceleration planning algorithm has a classified structure to improve the planning performance in each deceleration condition. Therefore, the individual MLP models were designed according to three different deceleration conditions: car-following, speed bump, and intersection. The proposed algorithm was validated through driving simulations. Then, time to collision and similarity to human driving were analyzed. The results show that the minimum time to collision was 1.443 s and the velocity root-mean-square error (RMSE) with human driving was 0.302 m/s. Through the driving simulation, it was validated that the vehicle moves safely with desirable velocity when SRS is in operation, based on the proposed algorithm. Furthermore, the classified structure has more advantages than the integrated structure in terms of planning performance.

Sensors Driven AI-Based Agriculture Recommendation Model for Assessing Land Suitability

The world population is expected to grow by another two billion in 2050, according to the survey taken by the Food and Agriculture Organization, while the arable area is likely to grow only by 5%. Therefore, smart and efficient farming techniques are necessary to improve agriculture productivity. Agriculture land suitability assessment is one of the essential tools for agriculture development. Several new technologies and innovations are being implemented in agriculture as an alternative to collect and process farm information. The rapid development of wireless sensor networks has triggered the design of low-cost and small sensor devices with the Internet of Things (IoT) empowered as a feasible tool for automating and decision-making in the domain of agriculture. This research proposes an expert system by integrating sensor networks with Artificial Intelligence systems such as neural networks and Multi-Layer Perceptron (MLP) for the assessment of agriculture land suitability. This proposed system will help the farmers to assess the agriculture land for cultivation in terms of four decision classes, namely more suitable, suitable, moderately suitable, and unsuitable. This assessment is determined based on the input collected from the various sensor devices, which are used for training the system. The results obtained using MLP with four hidden layers is found to be effective for the multiclass classification system when compared to the other existing model. This trained model will be used for evaluating future assessments and classifying the land after every cultivation.

Prediction of MoRFs in Protein Sequences with MLPs Based on Sequence Properties and Evolution Information

Molecular recognition features (MoRFs) are one important type of intrinsically disordered proteins functional regions that can undergo a disorder-to-order transition through binding to their interaction partners. Prediction of MoRFs is crucial, as the functions of MoRFs are associated with many diseases and can therefore become the potential drug targets. In this paper, a method of predicting MoRFs is developed based on the sequence properties and evolutionary information. To this end, we design two distinct multi-layer perceptron (MLP) neural networks and present a procedure to train them. We develop a preprocessing process which exploits different sizes of sliding windows to capture various properties related to MoRFs. We then use the Bayes rule together with the outputs of two trained MLP neural networks to predict MoRFs. In comparison to several state-of-the-art methods, the simulation results show that our method is competitive.

Scenario-led modelling of broadleaf forest expansion in Wales

Significant changes in the composition and extent of the UK forest cover are likely to take place in the coming decades. Current policy targets an increase in forest area, for example, the Welsh Government aims for forest expansion by 2030, and a purposeful shift from non-native conifers to broadleaved tree species, as identified by the UK Forestry Standard Guidelines on Biodiversity. Using the example of Wales, we aim to generate an evidence-based projection of the impact of contrasting policy scenarios on the state of forests in the near future, with the view of stimulating debate and aiding decisions concerning plausible outcomes of different policies. We quantified changes in different land use and land cover (LULC) classes in Wales between 2007 and 2015 and used a multi-layer perceptron-Markov chain ensemble modelling approach to project the state of Welsh forests in 2030 under the current and an alternative policy scenario. The current level of expansion and restoration of broadleaf forest in Wales is sufficient to deliver on existing policy goals. We also show effects of a more ambitious afforestation policy on the Welsh landscape. In a key finding, the highest intensity of broadleaf expansion is likely to shift from southeastern to more central areas of Wales. The study identifies the key predictors of LULC change in Wales. High-resolution future land cover simulation maps using these predictors offer an evidence-based tool for forest managers and government officials to test the effects of existing and alternative policy scenarios.

An Artificial Neural Network Approach to Predict the Effects of Formulation and Process Variables on Prednisone Release from a Multipartite System

The impact of formulation and process variables on the in-vitro release of prednisone from a multiple-unit pellet system was investigated. Box-Behnken Response Surface Methodology (RSM) was used to generate multivariate experiments. The extrusion-spheronization method was used to produce pellets and dissolution studies were performed using United States Pharmacopoeia (USP) Apparatus 2 as described in USP XXIV. Analysis of dissolution test samples was performed using a reversed-phase high-performance liquid chromatography (RP-HPLC) method. Four formulation and process variables viz., microcrystalline cellulose concentration, sodium starch glycolate concentration, spheronization time and extrusion speed were investigated and drug release, aspect ratio and yield were monitored for the trained artificial neural networks (ANN). To achieve accurate prediction, data generated from experimentation were used to train a multi-layer perceptron (MLP) using back propagation (BP) and the Broyden-Fletcher-Goldfarb-Shanno (BFGS) 57 training algorithm until a satisfactory value of root mean square error (RMSE) was observed. The study revealed that the in-vitro release profile of prednisone was significantly impacted by microcrystalline cellulose concentration and sodium starch glycolate concentration. Increasing microcrystalline cellulose concentration retarded dissolution rate whereas increasing sodium starch glycolate concentration improved dissolution rate. Spheronization time and extrusion speed had minimal impact on prednisone release but had a significant impact on extrudate and pellet quality. This work demonstrated that RSM can be successfully used concurrently with ANN for dosage form manufacture to permit the exploration of experimental regions that are omitted when using RSM alone.

Fusion of k-Gabor features from medio-lateral-oblique and craniocaudal view mammograms for improved breast cancer diagnosis

Context

Computer-aided diagnosis (CAD) combining mammographic features from cranio-caudal (CC) and medio-lateral-oblique (MLO) views improve the diagnostic performance of breast cancer. This could help doctors incorrect diagnosis at the earlier stage thereby reducing mortality.

Aim

The aim of this study is to propose a breast cancer diagnostic technique for improving the diagnostic accuracy and reducing the false positive rate by fusing mammographic features from CC and MLO views.

Settings and Design

The MLO and CC view mammograms of same patients must be used to extract k-Gabor features and then fused to form a single feature vector.

Subjects and Methods

Mammograms from the digital database for screening mammography (DDSM) and INbreast datasets are collected. k-Gabor features extracted from both MLO and CC view mammograms are fused serially and reduced by principal component analysis (PCA) or genetic algorithm. The reduced features are classified using a multi-layer perceptron feed forward neural network with backpropagation learning algorithm.

Statistical Analysis Used

Various relevant performance metrics such as accuracy, sensitivity, specificity, discriminant power, Mathews correlation coefficient (MCC), F1 score and Kappa are used to analyze the classification results.

Results

The accuracy, sensitivity, specificity, discriminant power, MCC, F1 score, and Kappa obtained as 92.5%, 93%, 91.8%, 1.198, 0.845, 0.936, and 0.845, respectively, for DDSM. For INbreast, the above specified metrics are 87.5%, 90.9%, 85.7%, 0.980, 0.741, 0.833, and 0.734, respectively. The results show 4.4%, 4.3%, and 9.4% improvements in accuracy, sensitivity, and specificity, respectively, compared to the previous works.

Conclusions

Detailed analysis of the results implies that the serial fusion of k-Gabor features extracted from MLO and CC views with PCA reduction in CAD significantly improves the diagnostic performance.

Land Cover and Climate Change May Limit Invasiveness of Rhododendron ponticum in Wales

Invasive plant species represent a serious threat to biodiversity precipitating a sustained global effort to eradicate or at least control the spread of this phenomenon. Current distribution ranges of many invasive species are likely to be modified in the future by land cover and climate change. Thus, invasion management can be made more effective by forecasting the potential spread of invasive species. Rhododendron ponticum (L.) is an aggressive invasive species which appears well suited to western areas of the UK. We made use of MAXENT modeling environment to develop a current distribution model and to assess the likely effects of land cover and climatic conditions (LCCs) on the future distribution of this species in the Snowdonia National park in Wales. Six global circulation models (GCMs) and two representative concentration pathways (RCPs), together with a land cover simulation for 2050 were used to investigate species' response to future environmental conditions. Having considered a range of environmental variables as predictors and carried out the AICc-based model selection, we find that under all LCCs considered in this study, the range of R. ponticum in Wales is likely to contract in the future. Land cover and topographic variables were found to be the most important predictors of the distribution of R. ponticum. This information, together with maps indicating future distribution trends will aid the development of mitigation practices to control R. ponticum.

Genome-enabled prediction using probabilistic neural network classifiers

BACKGROUND

Multi-layer perceptron (MLP) and radial basis function neural networks (RBFNN) have been shown to be effective in genome-enabled prediction. Here, we evaluated and compared the classification performance of an MLP classifier versus that of a probabilistic neural network (PNN), to predict the probability of membership of one individual in a phenotypic class of interest, using genomic and phenotypic data as input variables. We used 16 maize and 17 wheat genomic and phenotypic datasets with different trait-environment combinations (sample sizes ranged from 290 to 300 individuals) with 1.4 k and 55 k SNP chips. Classifiers were tested using continuous traits that were categorized into three classes (upper, middle and lower) based on the empirical distribution of each trait, constructed on the basis of two percentiles (15-85 % and 30-70 %). We focused on the 15 and 30 % percentiles for the upper and lower classes for selecting the best individuals, as commonly done in genomic selection. Wheat datasets were also used with two classes. The criteria for assessing the predictive accuracy of the two classifiers were the area under the receiver operating characteristic curve (AUC) and the area under the precision-recall curve (AUCpr). Parameters of both classifiers were estimated by optimizing the AUC for a specific class of interest.

RESULTS

The AUC and AUCpr criteria provided enough evidence to conclude that PNN was more accurate than MLP for assigning maize and wheat lines to the correct upper, middle or lower class for the complex traits analyzed. Results for the wheat datasets with continuous traits split into two and three classes showed that the performance of PNN with three classes was higher than with two classes when classifying individuals into the upper and lower (15 or 30 %) categories.

CONCLUSIONS

The PNN classifier outperformed the MLP classifier in all 33 (maize and wheat) datasets when using AUC and AUCpr for selecting individuals of a specific class. Use of PNN with Gaussian radial basis functions seems promising in genomic selection for identifying the best individuals. Categorizing continuous traits into three classes generally provided better classification than when using two classes, because classification accuracy improved when classes were balanced.