Enhancing Diagnostic Decision-Making: Ensemble Learning Techniques for Reliable Stress Level Classification.

An intense level of academic pressure causes students to experience stress, and if this stress is not addressed, it can cause adverse mental and physical effects. Since the pandemic situation, students have received more assignments and other tasks due to the shift of classes to an online mode. Students may not realize that they are stressed, but it may be evident from other factors, including sleep deprivation and changes in eating habits. In this context, this paper presents a novel ensemble learning approach that proposes an architecture for stress level classification. It analyzes certain factors such as the sleep hours, productive time periods, screen time, weekly assignments and their submission statuses, and the studying methodology that contribute to stress among the students by collecting a survey from the student community. The survey data are preprocessed to categorize stress levels into three categories: highly stressed, manageable stress, and no stress. For the analysis of the minority class, oversampling methodology is used to remove the imbalance in the dataset, and decision tree, random forest classifier, AdaBoost, gradient boost, and ensemble learning algorithms with various combinations are implemented. To assess the model's performance, different metrics were used, such as the confusion matrix, accuracy, precision, recall, and F1 score. The results showed that the efficient ensemble learning academic stress classifier gave an accuracy of 93.48% and an F1 score of 93.14%. Fivefold cross-validation was also performed, and an accuracy of 93.45% was achieved. The receiver operating characteristic curve (ROC) value gave an accuracy of 98% for the no-stress category, while providing a 91% true positive rate for manageable and high-stress classes. The proposed ensemble learning with fivefold cross-validation outperformed various state-of-the-art algorithms to predict the stress level accurately. By using these results, students can identify areas for improvement, thereby reducing their stress levels and altering their academic lifestyles, thereby making our stress prediction approach more effective.

A Novel Prognostic Model Using Chaotic CNN with Hybridized Spoofing for Enhancing Diagnostic Accuracy in Epileptic Seizure Prediction.

Epileptic seizure detection has undergone progressive advancements since its conception in the 1970s. From proof-of-concept experiments in the latter part of that decade, it has now become a vibrant area of clinical and laboratory research. In an effort to bring this technology closer to practical application in human patients, this study introduces a customized approach to selecting electroencephalogram (EEG) features and electrode positions for seizure prediction. The focus is on identifying precursors that occur within 10 min of the onset of abnormal electrical activity during a seizure. However, there are security concerns related to safeguarding patient EEG recordings against unauthorized access and network-based attacks. Therefore, there is an urgent need for an efficient prediction and classification method for encrypted EEG data. This paper presents an effective system for analyzing and recognizing encrypted EEG information using Arnold transform algorithms, chaotic mapping, and convolutional neural networks (CNNs). In this system, the EEG time series from each channel is converted into a 2D spectrogram image, which is then encrypted using chaotic algorithms. The encrypted data is subsequently processed by CNNs coupled with transfer learning (TL) frameworks. To optimize the fusion parameters of the ensemble learning classifiers, a hybridized spoofing optimization method is developed by combining the characteristics of corvid and gregarious-seeking agents. The evaluation of the model's effectiveness yielded the following results: 98.9 ± 0.3% accuracy, 98.2 ± 0.7% sensitivity, 98.6 ± 0.6% specificity, 98.6 ± 0.6% precision, and an F1 measure of 98.9 ± 0.6%. When compared with other state-of-the-art techniques applied to the same dataset, this novel strategy demonstrated one of the most effective seizure detection systems, as evidenced by these results.

Investigation of CeO2 nanoparticles on the performance enhancement of InsulatingOils.

Integrating nanotechnology in dielectric fluid significantly inhibits losses and boosts overall dielectric fluid performance. There has been research done on the effects of introducing various nanoparticles, such as titania, alumina, silica nanodiamonds, etc. In this paper, a novel nanoparticle, Ceria (CeO2), has been used, and its properties were examined using the FTIR (Fourier Transform Infrared) spectrum, the XRD (X-ray Diffraction) spectrum, the SEM (Scanning Electron Microscopy), and the TEM (Transmission Electron Microscopy). This paper illustrates an efficient dielectric fluid prepared by the successful dispersion of Cerium Oxide (CeO2) nanoparticles in various concentrations into four commercial oils, namely mineral oil, rapeseed oil, synthetic ester oil, and soybean oil, to enhance and improve their dielectric characteristics. The performance investigation emphasises breakdown strength enhancement and other dielectric properties of the colloidal solution comprising different nanoparticle (NP) concentrations. Various commercial oils are used as a base in nano-oil to diversify their applicability as dielectric fluids by measuring the correlation in dielectric parameters and statistically assessing their applicability with normal and Weibull distributions. The obtained experimental data sets were analyzed using the Statistics and Machine Learning Toolbox in MATLAB. The aging measurement has been done only on mineral oil, and results were matched using a predictive model of statistics and the Machine Learning Toolbox in MATLAB. Well-dispersed CeO2 NPs in the insulating oils lead to a significant increase in AC breakdown strength. The effect of ageing on the dielectric properties of nano oils yields better results than conventionally aged oil. It has been observed that the breakdown voltage is enhanced by up to 30% for mineral oil at an optimal concentration of 0.01 g/L, 9% for synthetic ester oil at 0.03 g/L, 18% for rapeseed oil at 0.02 g/L, and 19% for soybean oil at 0.03 g/L nanoparticle concentration. Following the dispersion of CeO2 nanoparticles, the dielectric constant of all insulating oils has also significantly improved. The overall experimental results are promising and show the potential of the CeO2 NPs-based nano oil as an efficient and highly performing dielectric oil for different power applications.

Design and Development of a Non-Contact ECG-Based Human Emotion Recognition System Using SVM and RF Classifiers.

Emotion recognition becomes an important aspect in the development of human-machine interaction (HMI) systems. Positive emotions impact our lives positively, whereas negative emotions may cause a reduction in productivity. Emotionally intelligent systems such as chatbots and artificially intelligent assistant modules help make our daily life routines effortless. Moreover, a system which is capable of assessing the human emotional state would be very helpful to assess the mental state of a person. Hence, preventive care could be offered before it becomes a mental illness or slides into a state of depression. Researchers have always been curious to find out if a machine could assess human emotions precisely. In this work, a unimodal emotion classifier system in which one of the physiological signals, an electrocardiogram (ECG) signal, has been used is proposed to classify human emotions. The ECG signal was acquired using a capacitive sensor-based non-contact ECG belt system. The machine-learning-based classifiers developed in this work are SVM and random forest with 10-fold cross-validation on three different sets of ECG data acquired for 45 subjects (15 subjects in each age group). The minimum classification accuracies achieved with SVM and RF emotion classifier models are 86.6% and 98.2%, respectively.

Intelligent Bi-LSTM with Architecture Optimization for Heart Disease Prediction in WBAN through Optimal Channel Selection and Feature Selection.

Wireless Body Area Network (WBAN) is a trending technology of Wireless Sensor Networks (WSN) to enhance the healthcare system. This system is developed to monitor individuals by observing their physical signals to offer physical activity status as a wearable low-cost system that is considered an unremarkable solution for continuous monitoring of cardiovascular health. Various studies have discussed the uses of WBAN in Personal Health Monitoring systems (PHM) based on real-world health monitoring models. The major goal of WBAN is to offer early and fast analysis of the individuals but it is not able to attain its potential by utilizing conventional expert systems and data mining. Multiple kinds of research are performed in WBAN based on routing, security, energy efficiency, etc. This paper suggests a new heart disease prediction under WBAN. Initially, the standard patient data regarding heart diseases are gathered from benchmark datasets using WBAN. Then, the channel selections for data transmission are carried out through the Improved Dingo Optimizer (IDOX) algorithm using a multi-objective function. Through the selected channel, the data are transmitted for the deep feature extraction process using One Dimensional-Convolutional Neural Networks (ID-CNN) and Autoencoder. Then, the optimal feature selections are done through the IDOX algorithm for getting more suitable features. Finally, the IDOX-based heart disease prediction is done by Modified Bidirectional Long Short-Term Memory (M-BiLSTM), where the hyperparameters of BiLSTM are tuned using the IDOX algorithm. Thus, the empirical outcomes of the given offered method show that it accurately categorizes a patient's health status founded on abnormal vital signs that is useful for providing the proper medical care to the patients.

Optimized S-Curve Transformation and Wavelets-Based Fusion for Contrast Elevation of Breast Tomograms and Mammograms.

For the purpose of accuracy in detection and diagnosis, Computer-Aided Diagnosis (CAD) is preferred by radiologists for the analysis of Breast Cancer. However, the presence of noise, artifacts, and poor contrast in breast images during acquisition highlights the need for sophisticated enhancement techniques for the proper visualization of region-of-interest (ROI). In this work, contrast elevation of breast mammographic and tomographic images is performed with an improved S-Curve transform using the Particle Swarm Optimization (PSO) algorithm. The enhanced images are assessed using dedicated quality metrics such as the Enhancement Measure (EME) and Absolute Mean Brightness Error (AMBE) measurement. Although the enhancement techniques help in attaining better images, certain features relevant for diagnosis purposes are removed during the enhancement process, creating contradictions for radiological interpretation. Hence, to ensure the retention of diagnostic features from original breast tomograms and mammograms, a Discrete Wavelet Transform (DWT)-based fusion approach is incorporated, which fuses the original and contrast-enhanced images (with optimized s-curve transformation function) using the maximum fusion rule. The fusion performance is thereafter measured using the Image Quality Index (IQI), Standard Deviation (SD), and Entropy (E) as fusion metrics.

A Deep Learning-Based Framework for Retinal Disease Classification.

This study addresses the problem of the automatic detection of disease states of the retina. In order to solve the abovementioned problem, this study develops an artificially intelligent model. The model is based on a customized 19-layer deep convolutional neural network called VGG-19 architecture. The model (VGG-19 architecture) is empowered by transfer learning. The model is designed so that it can learn from a large set of images taken with optical coherence tomography (OCT) and classify them into four conditions of the retina: (1) choroidal neovascularization, (2) drusen, (3) diabetic macular edema, and (4) normal form. The training datasets (taken from publicly available sources) consist of 84,568 instances of OCT retinal images. The datasets exhibit all four classes of retinal disease mentioned above. The proposed model achieved a 99.17% classification accuracy with 0.995 specificities and 0.99 sensitivity, making it better than the existing models. In addition, the proper statistical evaluation is done on the predictions using such performance measures as (1) area under the receiver operating characteristic curve, (2) Cohen's kappa parameter, and (3) confusion matrix. Experimental results show that the proposed VGG-19 architecture coupled with transfer learning is an effective technique for automatically detecting the disease state of a retina.

Improved Mucoadhesion, Permeation and In Vitro Anticancer Potential of Synthesized Thiolated Acacia and Karaya Gum Combination: A Systematic Study.

Thiolation of polymers is one of the most appropriate approaches to impart higher mechanical strength and mucoadhesion. Thiol modification of gum karaya and gum acacia was carried out by esterification with 80% thioglycolic acid. FTIR, DSC and XRD confirmed the completion of thiolation reaction. Anticancer potential of developed thiomer was studied on cervical cancer cell lines (HeLa) and more than 60% of human cervical cell lines (HeLa) were inhibited at concentration of 5 µg/100 µL. Immobilized thiol groups were found to be 0.8511 mmol/g as determined by Ellman's method. Cytotoxicity studies on L929 fibroblast cell lines indicated thiomers were biocompatible. Bilayered tablets were prepared using Ivabradine hydrochloride as the model drug and synthesized thiolated gums as mucoadhesive polymer. Tablets prepared using thiolated polymers in combination showed more swelling, mucoadhesion and residence time as compared to unmodified gums. Thiol modification controlled the release of the drug for 24 h and enhanced permeation of the drug up to 3 fold through porcine buccal mucosa as compared to tablets with unmodified gums. Thiolated polymer showed increased mucoadhesion and permeation, anticancer potential, controlled release and thus can be utilized as a novel excipient in formulation development.

A Highly Compact Antipodal Vivaldi Antenna Array for 5G Millimeter Wave Applications.

This paper presents a compact 1 × 4 antipodal Vivaldi antenna (AVA) array for 5G millimeter-wave applications. The designed antenna operates over 24.19 GHz-29.15 GHz and 30.28 GHz-40.47 GHz frequency ranges. The proposed antenna provides a high gain of 8 dBi to 13.2 dBi and the highest gain is obtained at 40.3 GHz. The proposed antenna operates on frequency range-2 (FR2) and covers n257, n258, n260, and n261 frequency bands of 5G communication. The corrugations and RT/Duroid 5880 substrate are used to reduce the antenna size to 24 mm × 28.8 mm × 0.254 mm, which makes the antenna highly compact. Furthermore, the corrugations play an important role in the front-to-back ratio improvement, which further enhances the gain of the antenna. The corporate feeding is optimized meticulously to obtain an enhanced bandwidth and narrow beamwidth. The radiation pattern does not vary over the desired operating frequency range. In addition, the experimental results of the fabricated antenna coincide with the simulated results. The presented antenna design shows a substantial improvement in size, gain, and bandwidth when compared to what has been reported for an AVA with nearly the same size, which makes the proposed antenna one of the best candidates for application in devices that operate in the millimeter frequency range.

Disjoint Spanning Tree Based Reliability Evaluation of Wireless Sensor Network.

Wireless sensor networks (WSNs) are becoming very common in numerous manufacturing industries; especially where it is difficult to connect a sensor to a sink. This is an evolving issue for researchers attempting to contribute to the proliferation of WSNs. Monitoring a WSN depends on the type of collective data the sensor nodes have acquired. It is necessary to quantify the performance of these networks with the help of network reliability measures to ensure the stable operation of WSNs. Reliability plays a key role in the efficacy of any large-scale application of WSNs. The communication reliability in a wireless sensor network is an influential parameter for enhancing network performance for secure, desirable, and successful communication. The reliability of WSNs must incorporate the design variables, coverage, lifetime, and connectivity into consideration; however, connectivity is the most important factor, especially in a harsh environment on a large scale. The proposed algorithm is a one-step approach, which starts with the recognition of a specific spanning tree only. It utilizes all other disjoint spanning trees, which are generated directly in a simple manner and consume less computation time and memory. A binary decision illustration is presented for the enumeration of K-coverage communication reliability. In this paper, the issue of computing minimum spanning trees was addressed and it is a pertinent method for further evaluating reliability for WSNs. This paper inspects the reliability of WSNs and proposes a method for evaluating the flow-oriented reliability of WSNs. Further, a modified approach for the sum-of-disjoint products to determine the reliability of WSN from the enumerated minimal spanning trees is proposed. The proposed algorithm when implemented for different sizes of WSNs demonstrates its applicability to WSNs of various scales. The proposed methodology is less complex and more efficient in terms of reliability.

Design of Quad-Port Ultra-Wideband Multiple-Input-Multiple-Output Antenna with Wide Axial-Ratio Bandwidth.

This article presents a compact, planar, quad-port ultra-wideband (UWB) multiple-input-multiple-output (MIMO) antenna with wide axial ratio bandwidth (ARBW). The proposed MIMO design consists of four identical square-shaped antenna elements, where each element is made up of a circular slotted ground plane and feed by a 50 Ω microstrip line. The circular polarization is achieved using a protruding hexagonal stub from the ground plane. The four elements of the MIMO antenna are placed orthogonally to each other to obtain high inter-element isolation. FR-4 dielectric substrate of size 45 × 45 × 1.6 mm3 is used for the antenna prototype, and a good agreement is noticed among the simulated and experimental results. The proposed MIMO antenna shows 3-dB ARBW of 52% (3.8-6.5 GHz) and impedance bandwidth (S11 ≤ -10 dB) of 144% (2.2-13.5 GHz).

Design of Quad-Port MIMO/Diversity Antenna with Triple-Band Elimination Characteristics for Super-Wideband Applications.

A compact, low-profile, coplanar waveguide (CPW)-fed quad-port multiple-input-multiple-output (MIMO)/diversity antenna with triple band-notched (Wi-MAX, WLAN, and X-band) characteristics is proposed for super-wideband (SWB) applications. The proposed design contains four similar truncated-semi-elliptical-self-complementary (TSESC) radiating patches, which are excited through tapered CPW feed lines. A complementary slot matching the radiating patch is introduced in the ground plane of the truncated semi-elliptical antenna element to obtain SWB. The designed MIMO/diversity antenna displays a bandwidth ratio of 31:1 and impedance bandwidth (|S11| ≤ - 10 dB) of 1.3-40 GHz. In addition, a complementary split-ring resonator (CSRR) is implanted in the resonating patch to eliminate WLAN (5.5 GHz) and X-band (8.5 GHz) signals from SWB. Further, an L-shaped slit is used to remove Wi-MAX (3.5 GHz) band interferences. The MIMO antenna prototype is fabricated, and a good agreement is achieved between the simulated and experimental outcomes.

Non-linear polynomial filters for edge enhancement of mammogram lesions.

BACKGROUND AND OBJECTIVES: Computer aided analysis of mammograms has been employed by radiologists as a vital tool to increase the precision in the diagnosis of breast cancer. The efficiency of such an analysis is dependent on the employed mammogram enhancement approach; as its major role is to yield a visually improved image for radiologists. METHODS: Non-linear Polynomial Filtering (NPF) framework has been explored previously as a robust approach for contrast improvement of mammographic images. This paper presents the extension of NPF framework for sharpening and edge enhancement of mammogram lesions. Proposed NPF serves to provide enhancement of edges and sharpness of the lesion region (region-of-interest) in mammograms, in a manner to minimize the dependencies on pre-selected thresholds. In the present work, Logarithmic Image Processing (LIP) model has been employed for the purpose of improvement in visualization of mammograms based on Human Visual System (HVS) characteristics. RESULTS: The proposed NPF filtering framework yields mammograms with significant improvement in contrast, edges as well as sharpness of the lesion region. The performance of the proposed approach has been validated using state-of-art objective evaluation measures (of mammogram enhancement) like Contrast Improvement Index (CII), Peak Signal-to-Noise Ratio (PSNR), Average Signal-to-Noise Ratio (ASNR) and Combined Enhancement Measure (CEM); as well as subjective evaluation by radiologists' opinions. CONCLUSIONS: The proposed NPF provides a robust solution to perform noise controlled contrast as well as edge enhancement using a single filtering model. This leads to a better visualization of the fine lesion details predictive of their severity. The applicability of single filtering methodology for carrying out denoising, contrast and edge enhancement improves the worth of the overall framework.

An Improved CAD System for Breast Cancer Diagnosis Based on Generalized Pseudo-Zernike Moment and Ada-DEWNN Classifier.

In this paper, a novel framework of computer-aided diagnosis (CAD) system has been presented for the classification of benign/malignant breast tissues. The properties of the generalized pseudo-Zernike moments (GPZM) and pseudo-Zernike moments (PZM) are utilized as suitable texture descriptors of the suspicious region in the mammogram. An improved classifier- adaptive differential evolution wavelet neural network (Ada-DEWNN) is proposed to improve the classification accuracy of the CAD system. The efficiency of the proposed system is tested on mammograms from the Mammographic Image Analysis Society (mini-MIAS) database using the leave-one-out cross validation as well as on mammograms from the Digital Database for Screening Mammography (DDSM) database using 10-fold cross validation. The proposed method on MIAS-database attains a fair accuracy of 0.8938 and AUC of 0.935 (95 % CI = 0.8213-0.9831). The proposed method is also tested for in-plane rotation and found to be highly rotation invariant. In addition, the proposed classifier is tested and compared with some well-known existing methods using receiver operating characteristic (ROC) analysis using DDSM- database. It is concluded the proposed classifier has better area under the curve (AUC) (0.9289) and highly précised with 95 % CI, 0.8216 to 0.9834 and 0.0384 standard error.

Prediction of quantitative intrathoracic fluid volume to diagnose pulmonary oedema using LabVIEW.

Pulmonary oedema is a life-threatening disease that requires special attention in the area of research and clinical diagnosis. Computer-based techniques are rarely used to quantify the intrathoracic fluid volume (IFV) for diagnostic purposes. This paper discusses a software program developed to detect and diagnose pulmonary oedema using LabVIEW. The software runs on anthropometric dimensions and physiological parameters, mainly transthoracic electrical impedance (TEI). This technique is accurate and faster than existing manual techniques. The LabVIEW software was used to compute the parameters required to quantify IFV. An equation relating per cent control and IFV was obtained. The results of predicted TEI and measured TEI were compared with previously reported data to validate the developed program. It was found that the predicted values of TEI obtained from the computer-based technique were much closer to the measured values of TEI. Six new subjects were enrolled to measure and predict transthoracic impedance and hence to quantify IFV. A similar difference was also observed in the measured and predicted values of TEI for the new subjects.