Journal of Electrical and Computer Engineering

Cardiovascular disease is a major cause of death worldwide, and the COVID-19 pandemic has only made the situation worse. The purpose of this work is to explore various time-frequency analysis methods that can be used to classify heart sound signals and identify multiple abnormalities in the heart, such as aortic stenosis, mitral stenosis, and mitral valve prolapse. The signal has been modified using three techniques—tunable quality wavelet transform (TQWT), discrete wavelet transform (DWT), and empirical mode decomposition—to detect heart signal abnormality. The proposed model detects heart signal abnormality at two stages, the user end and the clinical end. At the user end, binary classification of signals is performed, and if signals are abnormal then further classification is done at the clinic. The approach starts with signal preprocessing and uses the discrete wavelet transform (DWT) coefficients to train the hybrid model, which consists of one long short-term memory (LSTM) network layer and three convolutional neural network (CNN) layers. This method produced comparable results, with a classification accuracy for signals, through the utilization of the CNN and LSTM model. Combining the CNN’s skill in feature extraction with the LSTM’s capacity to record time-dependent features improves the efficacy of the model. Identifying issues early and initiating appropriate medication can alleviate the burden associated with heart valve diseases.

Noise is an undesirable and disturbing effect that degrades the quality of an image. The importance of noise reduction in images and its wide-ranging applications are essential. Most popular image noise filters rely on static parameters that are often challenging to fine-tune. Dynamically adapting these static parameters for image noise filters is a critical area of research. In this study, a combination model between the features of complex networks and artificial neural networks is proposed to automatically find the noise reduction parameter of the block-matching and 3D filtering method. Experimental results on the black and white MRI image set have shown that the model correctly predicted the parameters of the BM3D filter and removed the noise in the images of those MRI images. The model gave high denoising results with PSNR of 51.94 and SSIM of 0.998.

Automatic speech recognition (ASR) is a field of research that focuses on the ability of computers to process and interpret speech feedback from humans and to provide the highest degree of accuracy in recognition. Speech is one of the simplest ways to convey a message in a basic context, and ASR refers to the ability of machines to process and accept speech data from humans with the greatest degree of accuracy. As the human-to-machine interface continues to evolve, speech recognition is expected to become increasingly important. However, the Arabic language has distinct features that set it apart from other languages, such as the dialect and the pronunciation of words. Until now, insufficient attention has been devoted to continuous Arabic speech recognition research for independent speakers with a limited database. This research proposed two techniques for the recognition of Arabic speech. The first uses a combination of convolutional neural network (CNN) and long short-term memory (LSTM) encoders, and an attention-based decoder, and the second is based on the Sphinx-4 recognizer, which includes pocket sphinx, base sphinx, and sphinx train, with various types and number of features to be extracted (filter bank and mel frequency cepstral coefficients (MFCC)) based on the CMU Sphinx tool, which generates a language model for different sentences spoken by different speakers. These approaches were tested on a dataset containing 7 hours of spoken Arabic from 11 Arab countries, covering the Levant, Gulf, and African regions, which make up the Arab world, and achieved promising results. CNN-LSTM achieved a word error rate (WER) of 3.63% using 120 features for filter bank and 4.04% WER using 39 features for MFCC, respectively, while the Sphinx-4 recognizer technique achieved 8.17% WER and an accuracy of 91.83% using 25 features for MFCC and 8 Gaussian mixtures, respectively, when tested on the same benchmark dataset.

This paper focuses on the active cell balancing of lithium-ion battery packs. An improved single-input, multioutput, bi-switch flyback converter was proposed to achieve effective balancing. The proposed topology simplifies the control logic by utilising a single MOSFET switch for energy transfer and two complementary pulses to control the cell-selecting switches. The proposed topology can decrease the number of switching devices as well as the size and cost of the system. The bi-switch flyback converter eliminates the need for a separate buffer circuit to minimise leakage and electromagnetic inductance. Losses and energy efficiency were analysed at each end of the proposed topology. The appropriate MATLAB simulations investigated the balancing characteristics of various state of charge (SOC) imbalances. A comparison is made between the balancing speed and energy transfer efficiency of the proposed topology and a conventional topology that employs a multi-input and multi-output flyback converter in a static mode. The results of the MATLAB simulation were validated by the OPAL-RT (OP5700) real-time simulator. The balancing data of the proposed topology were compared using MATLAB simulation and real-time simulation. This work may reduce the time required to assemble and commission the hardware for the proposed topology’s real-time implementation.

The Internet of Things (IoT) constitutes a sophisticated network that interconnects devices, optimizing functionality across various domains of human activity. Recent literature projections anticipate a significant increase, with estimates exceeding 50 billion connected devices by 2025. Despite its transformative potential, the IoT landscape confronts formidable privacy and security challenges, encompassing intricate issues such as data acquisition, anonymization, retention, sharing practices, and behavioural profiling. Effectively addressing these challenges mandates the development of scalable solutions, innovative management strategies, and adaptable policy frameworks. In this paper, we conduct an exhaustive examination of major IoT applications, alongside associated privacy and security concerns. We systematically categorize prevalent privacy, security, and interoperability issues within the context of the IoT layered architecture. The review highlights current research initiatives focused on developing energy-efficient devices, optimizing microprocessors, and fostering interdisciplinary collaborations to address the challenges in the IoT landscape. To efficaciously manage risks in this dynamic landscape, stakeholders must implement comprehensive strategies that span stringent data protection legislation, extensive user education initiatives, and the deployment of robust authorization and authentication frameworks. This paper aims to empower industry leaders, policymakers, and researchers by providing actionable solutions, not just insights, to navigate the complexities of the IoT landscape effectively. Future research initiatives should prioritize the fortification of security measures for large-scale IoT deployments, the formulation of user-centric privacy solutions, and the standardization of interoperability protocols. By establishing a robust foundational framework, our paper endeavours to spearhead the discourse on IoT applications, privacy paradigms, and security frameworks, paving the way towards a resilient and interconnected future.

Wireless Sensor Network (WSN) has inexpensive, small, and less energy sensor nodes, which are allocated in random ways in particular areas for measuring the phenomenon or events in that field. In recent days, WSN has played a vital role in various applications, like industrial monitoring, medical treatments, agricultural monitoring, and military operations. However, the security challenges and network lifetime are the main issues in the existing methods. In order to overcome these issues, the Taylor-Spotted Cat Optimization (Taylor-SCO) approach is devised in this paper. Here, the Cluster Heads (CHs) are selected based on the developed optimization method, named Taylor CSO. Moreover, the delay, distance, and energy parameters are considered for effective Cluster Head Selection (CHS). Here, route maintenance is also done for increasing network lifetime and reducing complexities. In addition, the Modified K-Vertex Disjoint Paths Routing (KVDPR) model is established for routing. The modification of KVDPR is carried out using several factors, such as link reliability, throughput, and various trust factors. Moreover, the developed Taylor-SCO algorithm is developed by combining the Spotted Hyena Optimizer (SHO), Cat Swarm Optimization (CSO) algorithm, and Taylor series. The Taylor-SCO achieved better performance with energy consumption, trust, and throughput of 0.00037 J, 0.51, and 793160 kbps.