A novel support vector machine-based 1-day, single-dose prediction model of genotoxic hepatocarcinogenicity in rats.

The development of a rapid and accurate model for determining the genotoxicity and carcinogenicity of chemicals is crucial for effective cancer risk assessment. This study aims to develop a 1-day, single-dose model for identifying genotoxic hepatocarcinogens (GHCs) in rats. Microarray gene expression data from the livers of rats administered a single dose of 58 compounds, including 5 GHCs, was obtained from the Open TG-GATEs database and used for the identification of marker genes and the construction of a predictive classifier to identify GHCs in rats. We identified 10 gene markers commonly responsive to all 5 GHCs and used them to construct a support vector machine-based predictive classifier. In the silico validation using the expression data of the Open TG-GATEs database indicates that this classifier distinguishes GHCs from other compounds with high accuracy. To further assess the model's effectiveness and reliability, we conducted multi-institutional 1-day single oral administration studies on rats. These studies examined 64 compounds, including 23 GHCs, with gene expression data of the marker genes obtained via quantitative PCR 24 h after a single oral administration. Our results demonstrate that qPCR analysis is an effective alternative to microarray analysis. The GHC predictive model showed high accuracy and reliability, achieving a sensitivity of 91% (21/23) and a specificity of 93% (38/41) across multiple validation studies in three institutions. In conclusion, the present 1-day single oral administration model proves to be a reliable and highly sensitive tool for identifying GHCs and is anticipated to be a valuable tool in identifying and screening potential GHCs.

Information theory characteristics improve the prediction of lithium response in bipolar disorder patients using a support vector machine classifier.

AIM: Bipolar disorder (BD) is a mood disorder with a high morbidity and death rate. Lithium (Li), a prominent mood stabilizer, is often used as a first-line treatment. However, clinical studies have shown that Li is fully effective in roughly 30% of BD patients. Our goal in this study was to use features derived from information theory to improve the prediction of the patient's response to Li as well as develop a diagnostic algorithm for the disorder. METHODS: We have performed electrophysiological recordings in patient-derived dentate gyrus (DG) granule neurons (from a total of 9 subjects) for three groups: 3 control individuals, 3 BD patients who respond to Li treatment (LR), and 3 BD patients who do not respond to Li treatment (NR). The recordings were analyzed by the statistical tools of modern information theory. We used a Support Vector Machine (SVM) and Random forest (RF) classifiers with the basic electrophysiological features with additional information theory features. RESULTS: Information theory features provided further knowledge about the distribution of the electrophysiological entities and the interactions between the different features, which improved classification schemes. These newly added features significantly improved our ability to distinguish the BD patients from the control individuals (an improvement from 60% to 74% accuracy) and LR from NR patients (an improvement from 81% to 99% accuracy). CONCLUSION: The addition of Information theory-derived features provides further knowledge about the distribution of the parameters and their interactions, thus significantly improving the ability to discriminate and predict the LRs from the NRs and the patients from the controls.

ResNet-SVM: Fusion based glioblastoma tumor segmentation and classification.

Computerized segmentation of brain tumor based on magnetic resonance imaging (MRI) data presents an important challenging act in computer vision. In image segmentation, numerous studies have explored the feasibility and advantages of employing deep neural network methods to automatically detect and segment brain tumors depicting on MRI. For training the deeper neural network, the procedure usually requires extensive computational power and it is also very time-consuming due to the complexity and the gradient diffusion difficulty. In order to address and help solve this challenge, we in this study present an automatic approach for Glioblastoma brain tumor segmentation based on deep Residual Learning Network (ResNet) to get over the gradient problem of deep Convolutional Neural Networks (CNNs). Using the extra layers added to a deep neural network, ResNet algorithm can effectively improve the accuracy and the performance, which is useful in solving complex problems with a much rapid training process. An additional method is then proposed to fully automatically classify different brain tumor categories (necrosis, edema, and enhancing regions). Results confirm that the proposed fusion method (ResNet-SVM) has an increased classification results of accuracy (AC = 89.36%), specificity (SP = 92.52%) and precision (PR = 90.12%) using 260 MRI data for the training and 112 data used for testing and validation of Glioblastoma tumor cases. Compared to the state-of-the art methods, the proposed scheme provides a higher performance by identifying Glioblastoma tumor type.

Support vector machine based methodology for classification of thermal images pertaining to breast cancer.

Breast cancer has been and continues to be a cause of major health concern for women. It is more prevalent in old age, but its incidence has increased in recent years in groups below 50 years old, as in India. According to the Indian Council of Medical Research (ICMR) 2020, 50% of all the cases are in the age group of 25-50 where the numbers are staggering and constantly rising. The increase in incidence over the years indicates an urging need for innovative approaches to enhance breast cancer detection early. Thermography is non-contact imaging modalities and has potential to detect breast cancer at an early stage. Though thermography has capable of detecting breast cancer early, the challenge lies in the interpretation of the breast thermograms with respect to features and subsequent analysis. The present work discusses image acquisition, image processing related pre-processing, segmentation, and feature extraction. The extracted features were analyzed using ANOVA (Analysis of variance) statistical analysis. Statistical analyses were done in order to find the appropriate feature on the whole and quadrant breast. Statistical analysis results clearly reveal existence of thermal symmetry for the healthy subjects (p value > .05) in both whole and quadrant breast regions. In the case of abnormal subjects, whole breast analyses revealed the significance (p value < .05) for features like mean, variance, standard deviation, kurtosis, skewness, entropy, energy, homogeneity and contrast whereas upper outer quadrant analyses showed significance for all above features except contrast. The well correlated features of upper outer quadrant and whole breast were given as input for the Support Vector Machine - Radial Basis Function (SVM - RBF) classifier with grid search method. The results revealed that whole breast analysis has achieved 92.86% accuracy and upper outer quadrant breast analysis has achieved 85.71% accuracy. The results clearly indicate the involvement of upper outer quadrant and whole breast in early detection of breast cancer using thermal imaging.

Classification of Glaucoma Stages Using Image Empirical Mode Decomposition from Fundus Images.

One of the most prevalent causes of visual loss and blindness is glaucoma. Conventionally, instrument-based tools are employed for glaucoma screening. However, they are inefficient, time-consuming, and manual. Hence, computerized methodologies are needed for fast and accurate diagnosis of glaucoma. Therefore, we proposed a Computer-Aided Diagnosis (CAD) method for the classification of glaucoma stages using Image Empirical Mode decomposition (IEMD). In this study, IEMD is applied to decompose the preprocessed fundus photographs into different Intrinsic Mode Functions (IMFs) to capture the pixel variations. Then, the significant texture-based descriptors have been computed from the IMFs. A dimensionality reduction approach called Principal Component Analysis (PCA) has been employed to pick the robust descriptors from the retrieved feature set. We used the Analysis of Variance (ANOVA) test for feature ranking. Finally, the LS-SVM classifier has been employed to classify glaucoma stages. The proposed CAD system achieved a classification accuracy of 94.45% for the binary classification on the RIM-ONE r12 database. Our approach demonstrated better glaucoma classification performance than the existing automated systems.

Diffuse Reflectance Spectroscopy for Black Carbon Screening of Agricultural Soils under Industrial Anthropopressure.

Visible and near-infrared spectroscopy (VIS-NIRS) is a fast and simple method increasingly used in soil science. This study aimed to investigate VIS-NIRS applicability to predict soil black carbon (BC) content and the method's suitability for rapid BC-level screening. Forty-three soil samples were collected in an agricultural area remaining under strong industrial impact. Soil texture, pH, total nitrogen (Ntot) and total carbon (Ctot), soil organic carbon (SOC), soil organic matter (SOM), and BC were analyzed. Samples were divided into three classes according to BC content (low, medium, and high BC content) and scanned in the 350-2500 nm range. A support vector machine (SVM) was used to develop prediction models of soil properties. Partial least-square with SVM (PLS-SVM) was used to classify samples for screening purposes. Prediction models of soil properties were at best satisfactory (Ntot: R2 = 0.76, RMSECV = 0.59 g kg-1, RPIQ = 0.65), due to large kurtosis and data skewness. The RMSECV were large (16.86 g kg-1 for SOC), presumably due to the limited number of samples available and the wide data spread. Given our results, the VIS-NIRS method seems efficient for classifying soil samples from an industrialized area according to BC content level (training accuracy of 77% and validation accuracy of 81%).

Use of support vector machine and cellular automata methods to evaluate impact of irrigation project on LULC.

Land use and land cover (LULC) both define the earth's surface both anthropogenically and naturally. It helps maintain global balance but changes in land use create inequality. The LULC modification adversely affects physical parameters such as infiltration, groundwater recharge, surface runoff, ground temperature, and air quality. It is high time to monitor land use changes globally. Remote sensing and GIS techniques help to monitor these changes with a low budget and time. Various types of LULC classifiers have been invented to classify the LULC types. Maximum likelihood is a popular LULC classifier, but nowadays, support vector machine (SVM) classifier is gaining popularity because it provides a more accurate LULC than the maximum likelihood classifier. Therefore, in this study, the SVM classification technique has been applied to produce good accuracy LULC maps. Using the SVM classifier, six LULC maps are produced from 1995 to 2020 for the Shali reservoir area in India which is a medium irrigation project irrigating ~ 3211 hectares of land per year. It plays an important role in the agricultural production of the region by providing irrigation water in monsoon and post-monsoon seasons. The impact of LULC change on the environment is also studied. The LULC forecast maps are also created using the cellular automata (CA) model and MOLUSCE plugin. Kappa coefficient and validation methods are used to validate the LULC and simulated maps. Both maps produce high accuracy with a kappa coefficient of 0.9. Secondary data, collected from the governmental gazette, such as population, crop production, and water level is also used to justify the results. The simulated map shows that 4% of agricultural land and built-up area may increase from 2020 to 2030. Overall, it has been proven that the SVM and CA models can produce accurate classified results.

Design of an SVM Classifier Assisted Intelligent Receiver for Reliable Optical Camera Communication.

Embedding optical camera communication (OCC) commercially as a favorable complement of radio-frequency technology has led to the desire for an intelligent receiver system that is eligible to communicate with an accurate light-emitting diode (LED) transmitter. To shed light on this issue, a novel scheme for detecting and recognizing data transmitting LEDs has been elucidated in this paper. Since the optically modulated signal is captured wirelessly by a camera that plays the role of the receiver for the OCC technology, the process to detect LED region and retrieval of exact information from the image sensor is required to be intelligent enough to achieve a low bit error rate (BER) and high data rate to ensure reliable optical communication within limited computational abilities of the most used commercial cameras such as those in smartphones, vehicles, and mobile robots. In the proposed scheme, we have designed an intelligent camera receiver system that is capable of separating accurate data transmitting LED regions removing other unwanted LED regions employing a support vector machine (SVM) classifier along with a convolutional neural network (CNN) in the camera receiver. CNN is used to detect every LED region from the image frame and then essential features are extracted to feed into an SVM classifier for further accurate classification. The receiver operating characteristic curve and other key performance parameters of the classifier have been analyzed broadly to evaluate the performance, justify the assistance of the SVM classifier in recognizing the accurate LED region, and decode data with low BER. To investigate communication performances, BER analysis, data rate, and inter-symbol interference have been elaborately demonstrated for the proposed intelligent receiver. In addition, BER against distance and BER against data rate have also been exhibited to validate the effectiveness of our proposed scheme comparing with only CNN and only SVM classifier based receivers individually. Experimental results have ensured the robustness and applicability of the proposed scheme both in the static and mobile scenarios.

A novel hybrid atlas-free hierarchical graph-based segmentation of newborn brain MRI using wavelet filter banks.

Objective: The newborn brain MRI (magnetic resonance imaging) tissue segmentation plays a vital part in assessment of primary brain growth. In the newborn stage (nearly less than 28 days old), in T1- as well as T2-weighted MR images similar levels of intensity are exhibited by WM and GM, makes segmentation of the tissue extremely challenging. In this newborn stage for tissue segmentation, very few methods are developed. Hence the development of accurate brain tissue segmentation of neonate is prime objective of this paper.Methods: In this research work, we propose a novel hybrid atlas-free hierarchical graph-based tissue segmentation method for newborn infants. Wavelet filter banks are a class of deep models wherein filters and local neighborhood processes are used alternately for efficient segmentation on the raw input images, and fuzzy-based SVM (support vector machine) is used for precise tissue classification.Results: Specifically, from T1, T2 images multimodality information are used as inputs and then as outputs the segmentation maps are generated. The proposed approach considerably outperforms preceding methods of tissue segmentation as reflected in results. With this approach, the newborn MRI images that are even suffered from noise, poor resolution or the low contrasted images are also segmented more effectively with precision of 90% and sensitivity 98%.Conclusion: In addition, our findings indicate that the incorporation of multi-modality image led to significant improvements in performance. Thus, the proposed work effectively tackles the unreliability as well as the other issues faced with the prior methodologies with an interactive accurate segmentation outline.

Air quality warning system based on a localized PM2.5 soft sensor using a novel approach of Bayesian regularized neural network via forward feature selection.

It is highly significant to develop efficient soft sensors to estimate the concentration of hazardous pollutants in a region to maintain environmental safety. In this paper, an air quality warning system based on a robust PM2.5 soft sensor and support vector machine (SVM) classifier is reported. The soft sensor for the estimation of PM2.5 concentration is proposed using a novel approach of Bayesian regularized neural network (BRNN) via forward feature selection (FFS). Zuoying district of Taiwan is selected as the region of study for implementation of the estimation system because of the high pollution in the region. Descriptive statistics of various pollutants in Zuoying district is computed as part of the study. Moreover, seasonal variation of particulate matter (PM) concentration is analyzed to evaluate the impact of various seasons on the increased levels of PM in the region. To investigate the linear dependence of concentration of different pollutants to the concentration of PM2.5, Pearson correlation coefficient, Kendall's tau coefficient, and Spearman coefficient are computed. To achieve high performance for the PM2.5 estimation, selection of appropriate forward features from the input variables is carried out using FFS technique and Bayesian regularization is incorporated to the neural network system to avoid the overfitting problem. The comparative evaluation of performance of BRNN/FFS estimation system with various other methods shows that our proposed estimation system has the lowest mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE). Moreover, the coefficient of determination (R-squared) is around 0.95 for the proposed estimation method, which denotes a good fit. Evaluation of the SVM classifier showed good performance indicating that the proposed air quality warning system is efficient.

A Screening CAD Tool for the Detection of Microcalcification Clusters in Mammograms.

Breast cancer is the most common cancer diagnosed in women worldwide. Up to 50% of non-palpable breast cancers are detected solely through microcalcification clusters in mammograms. This article presents a novel and completely automated algorithm for the detection of microcalcification clusters in a mammogram. A multiscale 2D non-linear energy operator is proposed for enhancing the contrast between the microcalcifications and the background. Several texture, shape, intensity, and histogram of oriented gradients (HOG)-based features are used to distinguish microcalcifications from other brighter mammogram regions. A new majority class data reduction technique based on data distribution is proposed to counter data imbalance problem. The algorithm is able to achieve 100% sensitivity with 2.59, 1.78, and 0.68 average false positives per image on Digital Database for Screening Mammography (scanned film), INbreast (direct radiography) database, and PGIMER-IITKGP mammogram (direct radiography) database, respectively. Thus, it might be used as a second reader as well as a screening tool to reduce the burden on radiologists.

Diagnosis of Thyroid Nodules Based on Local Non-quantitative Multi-Directional Texture Descriptor with Rotation Invariant Characteristics for Ultrasound Image.

The traditional texture feature lacks the directional analysis of graphical element, so it could not better distinguish the thyroid nodule texture image formed by the rotation of graphical element. A non-quantifiable local feature is adopted in this paper to design a robust texture descriptor so as to enhance the robustness of the texture classification in the rotation and scale changes, which can improve the diagnostic accuracy of thyroid nodules in ultrasound images. First of all, the concept of local feature with rotational symmetry is introduced. It is found that many rotation invariant local features are rotational symmetric to a certain degree. Therefore, we propose a novel local feature to describe the rotation invariant properties of the texture. In order to deal with the change of rotation and scale of ultrasound thyroid nodules in image, Pairwise rotation-invariant spatial context feature is adopted to analyze the texture feature, which can combine with the scale information without increasing the dimension of the local feature. The fadopted local features have strong robustness to rotation and gray intensity variation. The experimental results show that our proposed method outperforms the existing algorithms on thyroid ultrasound data sets, which greatly improve the Diagnosis accuracy of thyroid nodules.

Prediction analysis and quality assessment of microwell array images.

Microwell arrays are widely used for the analysis of fluorescent-labelled biomaterials. For rapid detection and automated analysis of microwell arrays, the computational image analysis is required. Support Vector Machines (SVM) can be used for this task. Here, we present a SVM-based approach for the analysis of microwell arrays consisting of three distinct steps: labeling, training for feature selection, and classification into three classes. The three classes are filled, partially filled, and unfilled microwells. Next, the partially filled wells are analyzed by SVM and their tendency towards filled or unfilled tested through applying a Gaussian filter. Through this, all microwells can be categorized as either filled or unfilled by our algorithm. Therefore, this SVM-based computational image analysis allows for an accurate and simple classification of microwell arrays.

Automatic Organ Segmentation for CT Scans Based on Super-Pixel and Convolutional Neural Networks.

Accurate segmentation of specific organ from computed tomography (CT) scans is a basic and crucial task for accurate diagnosis and treatment. To avoid time-consuming manual optimization and to help physicians distinguish diseases, an automatic organ segmentation framework is presented. The framework utilized convolution neural networks (CNN) to classify pixels. To reduce the redundant inputs, the simple linear iterative clustering (SLIC) of super-pixels and the support vector machine (SVM) classifier are introduced. To establish the perfect boundary of organs in one-pixel-level, the pixels need to be classified step-by-step. First, the SLIC is used to cut an image into grids and extract respective digital signatures. Next, the signature is classified by the SVM, and the rough edges are acquired. Finally, a precise boundary is obtained by the CNN, which is based on patches around each pixel-point. The framework is applied to abdominal CT scans of livers and high-resolution computed tomography (HRCT) scans of lungs. The experimental CT scans are derived from two public datasets (Sliver 07 and a Chinese local dataset). Experimental results show that the proposed method can precisely and efficiently detect the organs. This method consumes 38 s/slice for liver segmentation. The Dice coefficient of the liver segmentation results reaches to 97.43%. For lung segmentation, the Dice coefficient is 97.93%. This finding demonstrates that the proposed framework is a favorable method for lung segmentation of HRCT scans.

Development of a Computer-Aided Differential Diagnosis System to Distinguish Between Usual Interstitial Pneumonia and Non-specific Interstitial Pneumonia Using Texture- and Shape-Based Hierarchical Classifiers on HRCT Images.

A computer-aided differential diagnosis (CADD) system that distinguishes between usual interstitial pneumonia (UIP) and non-specific interstitial pneumonia (NSIP) using high-resolution computed tomography (HRCT) images was developed, and its results compared against the decision of a radiologist. Six local interstitial lung disease patterns in the images were determined, and 900 typical regions of interest were marked by an experienced radiologist. A support vector machine classifier was used to train and label the regions of interest of the lung parenchyma based on the texture and shape characteristics. Based on the regional classifications of the entire lung using HRCT, the distributions and extents of the six regional patterns were characterized through their CADD features. The disease division index of every area fraction combination and the asymmetric index between the left and right lungs were also evaluated. A second SVM classifier was employed to classify the UIP and NSIP, and features were selected through sequential-forward floating feature selection. For the evaluation, 54 HRCT images of UIP (n = 26) and NSIP (n = 28) patients clinically diagnosed by a pulmonologist were included and evaluated. The classification accuracy was measured based on a fivefold cross-validation with 20 repetitions using random shuffling. For comparison, thoracic radiologists assessed each case using HRCT images without clinical information or diagnosis. The accuracies of the radiologists' decisions were 75 and 87%. The accuracies of the CADD system using different features ranged from 70 to 81%. Finally, the accuracy of the proposed CADD system after sequential-forward feature selection was 91%.

Connectivity Analysis and Feature Classification in Attention Deficit Hyperactivity Disorder Sub-Types: A Task Functional Magnetic Resonance Imaging Study.

Attention deficit hyperactivity disorder (ADHD) is a pervasive neuropsychiatric disorder. Patients with different ADHD subtypes show different behaviors under different stimuli and thus might require differential approaches to treatment. This study explores connectivity differences between ADHD subtypes and attempts to classify these subtypes based on neuroimaging features. A total of 34 patients (13 ADHD-IA and 21 ADHD-C subtypes) underwent functional magnetic resonance imaging (fMRI) with six task paradigms. Connectivity differences between ADHD subtypes were assessed for the whole brain in each task paradigm. Connectivity measures of the identified regions were used as features for the support vector machine classifier to distinguish between ADHD subtypes. The effectiveness of connectivity measures of the regions were tested by predicting ADHD-related Diagnostic and Statistical Manual of Mental Disorders (DSM) scores. Significant connectivity differences between ADHD subtypes were identified mainly in the frontal, cingulate, and parietal cortices and partially in the temporal, occipital cortices and cerebellum. Classifier accuracy for distinguishing between ADHD subtypes was 91.18 % for both gambling punishment and emotion task paradigms. Linear prediction under the two task paradigms showed significant correlation with DSM hyperactive/impulsive score. Our study identified important brain regions from connectivity analysis based on an fMRI paradigm using gambling punishment and emotion task paradigms. The regions and associated connectivity measures could serve as features to distinguish between ADHD subtypes.

Hierarchical fusion of features and classifier decisions for Alzheimer's disease diagnosis.

Pattern classification methods have been widely investigated for analysis of brain images to assist the diagnosis of Alzheimer's disease (AD) and its early stage such as mild cognitive impairment (MCI). By considering the nature of pathological changes, a large number of features related to both local brain regions and interbrain regions can be extracted for classification. However, it is challenging to design a single global classifier to integrate all these features for effective classification, due to the issue of small sample size. To this end, we propose a hierarchical ensemble classification method to combine multilevel classifiers by gradually integrating a large number of features from both local brain regions and interbrain regions. Thus, the large-scale classification problem can be divided into a set of small-scale and easier-to-solve problems in a bottom-up and local-to-global fashion, for more accurate classification. To demonstrate its performance, we use the spatially normalized grey matter (GM) of each MR brain image as imaging features. Specifically, we first partition the whole brain image into a number of local brain regions and, for each brain region, we build two low-level classifiers to transform local imaging features and the inter-region correlations into high-level features. Then, we generate multiple high-level classifiers, with each evaluating the high-level features from the respective brain regions. Finally, we combine the outputs of all high-level classifiers for making a final classification. Our method has been evaluated using the baseline MR images of 652 subjects (including 198 AD patients, 225 MCI patients, and 229 normal controls (NC)) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The experimental results show that our classification method can achieve the accuracies of 92.0% and 85.3% for classifications of AD versus NC and MCI versus NC, respectively, demonstrating very promising classification performance compared to the state-of-the-art classification methods.

Intra-V1 functional networks and classification of observed stimuli.

Introduction: Previous studies suggest that co-fluctuations in neural activity within V1 (measured with fMRI) carry information about observed stimuli, potentially reflecting various cognitive mechanisms. This study explores the neural sources shaping this information by using different fMRI preprocessing methods. The common response to stimuli shared by all individuals can be emphasized by using inter-subject correlations or de-emphasized by deconvolving the fMRI with hemodynamic response functions (HRFs) before calculating the correlations. The latter approach shifts the balance towards participant-idiosyncratic activity. Methods: Here, we used multivariate pattern analysis of intra-V1 correlation matrices to predict the Level or Shape of observed Navon letters employing the types of correlations described above. We assessed accuracy in inter-subject prediction of specific conjunctions of properties, and attempted intra-subject cross-classification of stimulus properties (i.e., prediction of one feature despite changes in the other). Weight maps from successful classifiers were projected onto the visual field. A control experiment investigated eye-movement patterns during stimuli presentation. Results: All inter-subject classifiers accurately predicted the Level and Shape of specific observed stimuli. However, successful intra-subject cross-classification was achieved only for stimulus Level, but not Shape, regardless of preprocessing scheme. Weight maps for successful Level classification differed between inter-subject correlations and deconvolved correlations. The latter revealed asymmetries in visual field link strength that corresponded to known perceptual asymmetries. Post-hoc measurement of eyeball fMRI signals did not find differences in gaze between stimulus conditions, and a control experiment (with derived simulations) also suggested that eye movements do not explain the stimulus-related changes in V1 topology. Discussion: Our findings indicate that both inter-subject common responses and participant-specific activity contribute to the information in intra-V1 co-fluctuations, albeit through distinct sub-networks. Deconvolution, that enhances subject-specific activity, highlighted interhemispheric links for Global stimuli. Further exploration of intra-V1 networks promises insights into the neural basis of attention and perceptual organization.

Automatic Detection and Classification of Hypertensive Retinopathy with Improved Convolution Neural Network and Improved SVM.

Hypertensive retinopathy (HR) results from the microvascular retinal changes triggered by hypertension, which is the most common leading cause of preventable blindness worldwide. Therefore, it is necessary to develop an automated system for HR detection and evaluation using retinal images. We aimed to propose an automated approach to identify and categorize the various degrees of HR severity. A new network called the spatial convolution module (SCM) combines cross-channel and spatial information, and the convolution operations extract helpful features. The present model is evaluated using publicly accessible datasets ODIR, INSPIREVR, and VICAVR. We applied the augmentation to artificially increase the dataset of 1200 fundus images. The different HR severity levels of normal, mild, moderate, severe, and malignant are finally classified with the reduced time when compared to the existing models because in the proposed model, convolutional layers run only once on the input fundus images, which leads to a speedup and reduces the processing time in detecting the abnormalities in the vascular structure. According to the findings, the improved SVM had the highest detection and classification accuracy rate in the vessel classification with an accuracy of 98.99% and completed the task in 160.4 s. The ten-fold classification achieved the highest accuracy of 98.99%, i.e., 0.27 higher than the five-fold classification accuracy and the improved KNN classifier achieved an accuracy of 98.72%. When computation efficiency is a priority, the proposed model's ability to quickly recognize different HR severity levels is significant.

A New Wrist-Forearm Rehabilitation Protocol Integrating Human Biomechanics and SVM-Based Machine Learning for Muscle Fatigue Estimation.

In this research, a new remote rehabilitation system was developed that integrates an IoT-based connected robot intended for wrist and forearm rehabilitation. In fact, the mathematical model of the wrist and forearm joints was developed and integrated into the main controller. The proposed new rehabilitation protocol consists of three main sessions: the first is dedicated to the extraction of the passive components of the dynamic model of wrist-forearm biomechanics while the active components are extracted in the second session. The third session consists of performing continuous exercises using the determined dynamic model of the forearm-wrist joints, taking into account the torque generated by muscle fatigue. The main objective of this protocol is to determine the state level of the affected wrist and above all to provide a dynamic model in which the torque generated by the robot and the torque supplied by the patient are combined, taking into account the constraints of fatigue. A Support Vector Machine (SVM) classifier is designed for the estimation of muscle fatigue based on the features extracted from the electromyography (EMG) signal acquired from the patient. The results show that the developed rehabilitation system allows a good progression of the joint's range of motion as well as the resistive-active torques.