Ain Shams Engineering Journal最新文献

{"title":"Deep neural networks for speech enhancement and speech recognition: A systematic review","authors":"Sureshkumar Natarajan ,&nbsp;Syed Abdul Rahman Al-Haddad ,&nbsp;Faisul Arif Ahmad ,&nbsp;Raja Kamil ,&nbsp;Mohd Khair Hassan ,&nbsp;Syaril Azrad ,&nbsp;June Francis Macleans ,&nbsp;Sadiq H. Abdulhussain ,&nbsp;Basheera M. Mahmmod ,&nbsp;Nurbek Saparkhojayev ,&nbsp;Aigul Dauitbayeva","doi":"10.1016/j.asej.2025.103405","DOIUrl":"10.1016/j.asej.2025.103405","url":null,"abstract":"<div><div>The field of speech signal processing has undergone significant transformation through extensive research. There is growing interest in Speech Enhancement (SE) and Automatic Speech Recognition (ASR), with SE serving as a crucial preliminary step to enhance ASR performance. This paper addresses key challenges, particularly the need to maintain speech quality and improve intelligibility in ASR systems. Recently, deep learning techniques have emerged as powerful tools for tackling these challenges. This systematic review examines speech enhancement and recognition techniques, emphasizing denoising, acoustic modeling, and beamforming. Various deep learning architectures, such as Deep Neural Networks (DNN), Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, and Hybrid Neural Networks, are reviewed to highlight their roles in enhancement and recognition. The review specifically details their usage, the features utilized in each study, the databases employed, performance, and limitations, all presented in a structured tabular format. This approach provides valuable insights into the strengths and weaknesses of each method, guiding future advancements in the field. In particular, it emphasizes that LSTM-RNN models excel in temporal signal processing, while hybrid models demonstrate superior performance in optimizing task outcomes. The paper conducts a comprehensive statistical analysis of 187 research papers that exclusively utilize deep neural networks to address the challenges of speech enhancement and recognition, presenting the latest advances in the field. The review examines publications from 2012 to 2024, shedding light on research trends and patterns, while the proposed solutions aim to bridge gaps for researchers in this evolving domain.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103405"},"PeriodicalIF":6.0,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887190","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An AI-based badminton smash detection using residual-shuffle network optimized based on upgraded pufferfish optimizer","authors":"Weimin Peng,&nbsp;Wangtian Zheng","doi":"10.1016/j.asej.2025.103414","DOIUrl":"10.1016/j.asej.2025.103414","url":null,"abstract":"<div><div>The growth in the field of sports analytics has observed a paradigm shift with the advent of artificial intelligence (AI) and deep learning techniques. The accurate detection of smashes in badminton is significant for strategic decision-making and performance enhancement. This research presents an innovative AI-based framework, called DeepSmash, which uses a Residual-Shuffle Network (ResNet) optimized by an upgraded Pufferfish Optimizer (UPO) to automatically detect badminton smashes from broadcasted video footage. By a combination of the strengths of ResNet’s hierarchical feature representation and UPO’s efficient parameter tuning, the model achieves high-precision recognition of smashes, drops, clears, net actions, and lifts. A comprehensive comparative analysis with state-of-the-art models demonstrates the superiority of our proposed approach, underscoring its potential to revolutionize sports analytics and athlete performance enhancement. This innovation not only sets a new benchmark for AI applications in sports technology but also covers the way for the development of more efficient sports analytics tools.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103414"},"PeriodicalIF":6.0,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887189","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Application of Fibonacci wavelets using operational matrix and differential transform method to study rectangular porous fin for nonlinear temperature in moving condition","authors":"Azhar Iqbal ,&nbsp;Vivek ,&nbsp;Tayyaba Akram ,&nbsp;Wei Sin Koh ,&nbsp;Abdullah M. Alsharif","doi":"10.1016/j.asej.2025.103412","DOIUrl":"10.1016/j.asej.2025.103412","url":null,"abstract":"<div><div>In this study, a novel numerical technique, the Fibonacci Wavelet Collocation Method (FWCM), is developed to analyze the nonlinear temperature distribution in a permeable moving fin within a rectangular domain. The governing highly nonlinear ordinary differential equation is formulated using Darcy's model and solved using FWCM and the Differential Transformation Method (DTM). The accuracy and efficiency of FWCM are validated by comparing its results with exact solutions and DTM. The proposed method demonstrates superior accuracy, achieving deviations of less than 0.001% from exact solutions, while DTM exhibits relatively higher errors. Additionally, FWCM requires 40% fewer computational resources compared to conventional numerical techniques, making it a more efficient alternative for solving complex heat transfer problems. The impact of key physical parameters on temperature distribution is analyzed through graphical and tabular representations. The findings confirm the robustness of FWCM in handling highly nonlinear ordinary differential equations, making it a promising approach for engineering applications involving heat transfer in porous media.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103412"},"PeriodicalIF":6.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adaptive barrier function terminal sliding mode control for nonlinear systems subject to uncertain bounded perturbations","authors":"ZiKai Wang ,&nbsp;Kuo-Hsien Hsia ,&nbsp;Saleh Mobayen ,&nbsp;Omid Mofid ,&nbsp;Pawel Skruch","doi":"10.1016/j.asej.2025.103418","DOIUrl":"10.1016/j.asej.2025.103418","url":null,"abstract":"<div><div>This research proposes a tracking control strategy for perturbed and uncertain nonlinear systems by incorporating an adaptive barrier function within a terminal sliding mode control framework. The proposed approach leverages terminal sliding mode control, integrated with the global convergence principle, to ensure global finite-time tracking performance. Additionally, the adaptive barrier function mechanism is employed to effectively mitigate the impact of system perturbations and uncertainties, enhancing overall robustness and stability in nonlinear system control. The key findings and advantages of the proposed method are summarized as: (1) The use of terminal sliding mode control enhances the system’s robustness; (2) Since the controller derivative is continuous except for a discontinuous sign function, integrating the barrier function-based control signal effectively minimizes chattering; (3) By incorporating an adaptive barrier-tuning function, the method ensures robustness against system uncertainties, disturbances, and nonlinearities while mitigating the chattering effect; (4) The proposed method improves tracking accuracy and reduces chattering caused by switching laws; (5) This novel approach holds significant potential for real-world applications, particularly in tracking control scenarios involving input saturations and time delays in uncertain nonlinear systems. Additionally, the proposed approach is highly adaptable for practical applications as it employs two adaptation rules to handle uncertainties and disturbances with unknown upper bounds under specific conditions. Numerical simulation and experimental validation on a rotary inverted pendulum system demonstrate the effectiveness and feasibility of the proposed control scheme for the trajectory tracking control of the real nonlinear system, which confirms the compatibility of the proposed method in real applications.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103418"},"PeriodicalIF":6.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143887188","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mobile manipulation planning analysis of a novel leg-arm integration hexapod robot based on the center of mass kinematics theory","authors":"Yi Zheng ,&nbsp;Sixian Rao ,&nbsp;Jiapeng Gao ,&nbsp;Jiong Kong","doi":"10.1016/j.asej.2025.103439","DOIUrl":"10.1016/j.asej.2025.103439","url":null,"abstract":"<div><div>This study introduces a hexapod robot with integrated leg-arm mechanisms for stable mobile manipulation through center of mass (COM) kinematics planning. The design features two transformable limbs achieving dual-arm manipulation while maintaining stability through coordinated four-leg compensation. Subsequently, a complete COM kinematics model is established, encompassing leg branches, leg-arm branches, and a full-body system, providing the theoretical basis for mobile manipulation planning. In addition, by leveraging the analysis of the (3 + 1) static gait characteristics to establish a planar COM trajectory and foot-end motion patterns, combined with the COM height definition and inverse COM kinematics implementation, precise leg motion control is achieved using an effective workspace trajectory to joint space trajectory mapping. Compared with conventional kinematic approaches, this method demonstrates superior walking stability and payload handling capability through systematic virtual prototype simulations and prototype experiments. This work advances legged robotics by solving simultaneous locomotion-manipulation challenges through whole-body COM regulation.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103439"},"PeriodicalIF":6.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143878978","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Integrating data overlaps and nonlinear dynamics: A novel approach to the Davey-Stewartson system in optical fluid model","authors":"Syeda Sarwat Kazmi ,&nbsp;Muhammad Bilal Riaz ,&nbsp;Adil Jhangeer","doi":"10.1016/j.asej.2025.103420","DOIUrl":"10.1016/j.asej.2025.103420","url":null,"abstract":"<div><div>In this study, the newly developed (2 + 1)-dimensional Davey-Stewartson system, characterized by parabolic law nonlinearity, is examined. This equation is recognized as significant for modeling surface wave patterns in finite-depth conditions. The model is initially transformed into lower dimensions using the wave transformation. Various soliton solutions, including kink, anti-kink, periodic, and chirped solitons, are derived using the generalized logistic equation method. These soliton structures have practical applications in fields such as optical pulse propagation in fiber optics, signal transmission in communication systems, energy transport in ocean engineering, and biological wave modeling, particularly in understanding nonlinear wave dynamics in shallow water and geophysical flows. To deepen our understanding of the physics behind these solutions, they are visualized using various representations, including 3D plots, 2D plots, density plots, and polar plots. Following this, a phase portrait analysis is conducted on the critical points of the unperturbed dynamical system. Subsequently, an outward force is introduced, and the perturbed system's behavior is examined using advanced chaos detection techniques. These include Poincaré maps, time series graphs, multistability analysis, chaotic attractors, return maps, power spectra, and Lyapunov exponents. A newly introduced bidirectional scatter plot approach is employed to perform a comparative analysis of solution behaviors, effectively highlighting overlapping regions and distinctions within their solution spaces through data points. This study contributes to the understanding of nonlinear wave systems and provides new tools for future research in applied mathematics.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103420"},"PeriodicalIF":6.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143881772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing CSK performance in QLED-based VLC: A multi-objective optimization approach","authors":"Serkan Vela ,&nbsp;Gökçe Hacıoğlu","doi":"10.1016/j.asej.2025.103433","DOIUrl":"10.1016/j.asej.2025.103433","url":null,"abstract":"<div><div>Optimizing constellation points for Color Shift Keying (CSK) modulation in Quadrichromatic Light Emitting Diode (QLED)-based Visible Light Communication (VLC) systems poses a significant challenge. Balancing high data rates with crucial illumination quality metrics—luminous flux, Correlated Color Temperature (CCT), and Color Rendering Index (CRI)—is essential, yet often neglected in favor of communication speed. This paper introduces a novel multi-objective optimization framework utilizing the NSGA-II algorithm specifically designed for QLED-based VLC CSK constellations. Our approach simultaneously optimizes data rate (throughput), luminous flux, CCT adherence, and CRI. We demonstrate substantial performance improvements compared to both the IEEE 802.15.7 standard and prior optimization studies reported in the literature.</div><div>For 4-CSK modulation across tested CCTs (3500K, 5000K, 6500K), our method achieves gains of up to 77.28% in throughput, 349.12% in luminous flux, and 7.18% in CRI relative to the IEEE standard, while also significantly outperforming the prior study, particularly in throughput and luminous flux (e.g., achieving 66.78% vs. 77.28% throughput gain and 139.66% vs. 55% flux gain at 5000K compared to the prior study and IEEE respectively). Similar substantial advantages are observed for 8-CSK (achieving up to 64.41% throughput gain, 314.89% luminous flux gain, and 14.25% CRI gain compared to benchmarks) and 16-CSK (up to 47.80% throughput gain, 258.66% luminous flux gain, and 7.27% CRI gain).</div><div>These findings underscore the proposed framework's effectiveness in achieving a superior balance between communication performance and illumination quality compared to existing standards and methods. This research offers valuable insights for designing more efficient, high-quality, and adaptable QLED-based VLC systems suitable for diverse application requirements.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103433"},"PeriodicalIF":6.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143881765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced EEG signal processing with deep autoencoders and hybrid Mamba classifier for accurate classification of chronic neuropathic pain etiologies","authors":"Ümit Şentürk","doi":"10.1016/j.asej.2025.103436","DOIUrl":"10.1016/j.asej.2025.103436","url":null,"abstract":"<div><div>This study introduces a groundbreaking framework that leverages deep autoencoders and a novel hybrid Mamba classifier to enhance the objective classification of chronic neuropathic pain (CNP) etiologies using EEG signals, addressing a critical gap in pain diagnostics. Chronic neuropathic pain is a multifaceted condition characterized by diverse symptoms and etiologies, making accurate diagnosis challenging due to reliance on subjective assessments. The primary aim of this research is to develop a data-driven, scalable solution capable of classifying six distinct CNP categories, including diabetes-related neuropathy, spinal cord injury (SCI), and trigeminal neuralgia, with exceptional precision. Our unique contribution lies in the integration of deep learning for EEG feature extraction and the hybrid Mamba classifier, combining the strengths of traditional and advanced machine learning techniques for unparalleled accuracy. Using a dataset of 36 patients, EEG signals were preprocessed through artifact removal, segmentation, and balancing via the SMOTE algorithm. The model achieved superior performance metrics, including 99% accuracy, precision, recall, F1-score, and Matthews Correlation Coefficient (MCC), along with an AUC of 0.99 across all categories, significantly outperforming traditional models like SVM (AUC 0.97) and logistic regression (AUC 0.83). By identifying distinct EEG patterns linked to different pain types, this approach not only ensures diagnostic reliability but also supports personalized treatment planning. These findings underscore the transformative potential of integrating EEG-based biomarkers with advanced computational techniques, setting a new standard in neurophysiological pain diagnostics. Future work will focus on expanding datasets, incorporating multimodal data, and enabling real-time applications to further enhance clinical impact and generalizability.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103436"},"PeriodicalIF":6.0,"publicationDate":"2025-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143877303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A high-power microwave continuous cracking system for hard ores","authors":"Feng Lin ,&nbsp;Ziyang Wang ,&nbsp;Yuntan Ao ,&nbsp;Shiping Li ,&nbsp;Xiangxin Su ,&nbsp;Yuxi Liu","doi":"10.1016/j.asej.2025.103440","DOIUrl":"10.1016/j.asej.2025.103440","url":null,"abstract":"<div><div>A pilot continuous high power microwave treatment system with a double-tube structure (to give adjustable ore thickness) and automatic reflection adjustment was designed. Sishanling granular iron ore was used as a research object. The action parameters of the system were designed and optimized and their rationality verified experimentally. The results of numerical simulation show that the position of the short-circuit plate has little effect on the uniformity of the temperature distribution, and the double-tube structure (pipe diameters 16 and 6 cm) and double-sided radiation can improve the heating uniformity of the ore. Compared to other particle sizes, when the size of the ore particles is 0–14 mm, the power critical point for large-scale arc phenomenon is higher (80 kW). The microwaves in a double-tube structure (pipe diameters 16 and 6 cm) significantly improved the efficiency of the ball milling and dissociation processes compared with a single-tube structure (pipe diameter 20 cm). Finally, a design scheme is proposed for ores with different microwave sensitivities (pipe diameters and ore particle sizes).</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103440"},"PeriodicalIF":6.0,"publicationDate":"2025-04-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143877435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Variance-based reconfigurable modules for mode decision in intra prediction algorithm","authors":"Vanila Sildas ,&nbsp;Premanand Venkatesh Chandramani ,&nbsp;R Srinivasan ,&nbsp;Rathinam Ananthanarayanan","doi":"10.1016/j.asej.2025.103403","DOIUrl":"10.1016/j.asej.2025.103403","url":null,"abstract":"<div><div>This work is to design and migrate the hardware architecture implementation from static configuration to dynamic reconfiguration by investigating the viability of five types of intra prediction mode decision based on Similarity index in H.264 video processing. The variance-based five Similarity indices of cosine Similarity, sum of absolute differences (SAD), sum of squared differences (SSD), Hamming distance, and Euclidean distance are proposed to identify the best mode selection in the H.264 intra prediction process. The input parameter for Similarity selection was the variance-based threshold of the original block. The Similarity-based mode decision algorithm is reconfigurable hardware units made to perform nine modes of operations. A reconfigurable hardware implementation of system-on-chip architecture is compared in terms of power usage, resource utilization, and reconfiguration time for all the Similarity procedures. The variance-based hamming distance intra prediction algorithm can achieve 44% computational complexity reduction to select the optimal mode with minimum hardware resource utilisation compared to other proposed techniques.</div></div>","PeriodicalId":48648,"journal":{"name":"Ain Shams Engineering Journal","volume":"16 7","pages":"Article 103403"},"PeriodicalIF":6.0,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143869446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}