Article
Computer Science, Artificial Intelligence
Pradip Paithane, Sangeeta Kakarwal
Summary: The LMNS-net deep learning model is a fast and accurate approach for automatic pancreatic segmentation in clinical abdominal CT images. It utilizes a lightweight multiscale module to reduce computation time and achieve high accuracy. The model takes only 1-3 seconds for segmentation in the testing process, making it faster and more efficient than other approaches.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Haval I. Hussein, Abdulhakeem O. Mohammed, Masoud M. Hassan, Ramadhan J. Mstafa
Summary: Hundreds of millions of people worldwide have been affected by COVID-19, leading to significant damage to health, economy, and welfare. In order to detect infected patients and provide timely care, lightweight CNN-based diagnostic models were developed for automatic and early detection of COVID-19 from chest X-ray images. These models achieved high accuracy rates and reduced computational and memory requirements compared to existing heavyweight models.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Biotechnology & Applied Microbiology
Juntong Yun, Du Jiang, Ying Liu, Ying Sun, Bo Tao, Jianyi Kong, Jinrong Tian, Xiliang Tong, Manman Xu, Zifan Fang
Summary: This article proposes a real-time target detection method based on a lightweight convolutional neural network, improving target detection technology by reducing the number of model parameters and improving detection speed. Experimental results demonstrate the effectiveness and superiority of the proposed method in complex scenes, with tests on video and deployment on the Android platform also confirming its real-time performance and scalability.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2022)
Article
Computer Science, Information Systems
Longfeng Shen, Fenglan Qin, Hongying Zhu, Dengdi Sun, Hai Min
Summary: This paper proposes a lightweight single-image super-resolution network (EGARNet) based on extended group-enhanced convolution. By introducing residual learning and adjacent residual convolution, the shallow network features and deep high-frequency features are fused, which helps in reconstructing the image edge structure and balancing the relationship between model complexity and reconstructed image quality.
MULTIMEDIA SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
G. Sakthi Priya, N. Padmapriya
Summary: Deep learning models have better performance for image classification, but they require extensive memory usage and computational power. This paper introduces a lightweight deep learning architecture, PT-CNN, for multi-class texture classification, which is well suited for analyzing texture images.
NEURAL PROCESSING LETTERS
(2023)
Article
Biochemistry & Molecular Biology
Suliman Aladhadh, Saleh A. Almatroodi, Shabana Habib, Abdulatif Alabdulatif, Saeed Ullah Khattak, Muhammad Islam
Summary: In order to overcome the difficulty of identifying enhancers in gene regulation, researchers proposed a deep learning model based on a convolutional neural network (CNN) and attention-gated recurrent units (AttGRU). This model can identify enhancer sequences and their strengths based on the chromatin accessibility of DNA fragments. Experimental results showed that the proposed model achieved high accuracy for predicting enhancer sequences and strengths, comparable to state-of-the-art models, highlighting its importance.
Article
Plant Sciences
Siyu Quan, Jiajia Wang, Zhenhong Jia, Mengge Yang, Qiqi Xu
Summary: The rapid development of image processing technology and computing power has led to deep learning becoming one of the main methods for plant disease identification. A novel lightweight convolutional neural network is proposed to address the issues of computational complexity and deployment. Skip connections and optimized feature fusion weight parameters are introduced to achieve higher classification accuracy. The model is pre-trained on plant classification tasks instead of using ImageNet, which enhances performance and robustness. Experimental results show that the proposed model outperforms existing plant disease diagnosis models in terms of accuracy, parameter count, and complexity.
FRONTIERS IN PLANT SCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Xiangyu Guo, Mingliang Gao, Guofeng Zou, Alessandro Bruno, Abdellah Chehri, Gwanggil Jeon
Summary: Object counting task has attracted considerable interest, but the presence of background noise limits the performance. To tackle this issue, researchers proposed a group and graph attention network (GGANet) incorporating group channel attention (GCA) and learnable graph attention (LGA) modules. Experimental results show that this approach achieves superior counting performance on multiple datasets.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Multidisciplinary Sciences
Shuo Pan, Hai Yan, Zhuo Liu, Ning Chen, Yinghao Miao, Yue Hou
Summary: Texture is a crucial characteristic of roads, and recognizing pavement texture is important for road maintenance professionals. This paper proposes a few-shot learning model based on the Siamese network for pavement texture recognition. The model achieved high accuracy in classifying different pavement textures and created lightweight models that save storage and training time.
PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES
(2023)
Article
Engineering, Electrical & Electronic
Song Feng, Qinghang Zeng, Bin Fan, Jiufei Luo, Hong Xiao, Junhong Mao
Summary: This paper proposes a lightweight residual U-net convolutional neural network model for extracting lubricating oil wear debris morphological features, and experimental results demonstrate the accuracy and anti-interference performance of this method.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Artificial Intelligence
Yuantao Chen, Runlong Xia, Kai Yang, Ke Zou
Summary: The paper introduces a lightweight method for image inpainting that combines group convolution and attention mechanism to improve restoration quality and address the issue of information mobility between channels in traditional convolution processing. The use of a parallel discriminator structure throughout the network design phase ensures local and global consistency of the image inpainting process. Experimental results demonstrate that the proposed image inpainting network offers significantly lower inference time and resource usage compared to similar lightweight approaches, while maintaining quality.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Information Systems
Zixuan Ou, Wenbin Ye
Summary: In this article, we propose a lightweight network called Tiny-RadarNet for extracting features from raw data. Unlike traditional neural networks, we use a unique parallel 1-D depthwise convolutions structure to eliminate the need for standard convolutions and achieve significant parameter reduction. Furthermore, we treat fall detection as a matching problem using metric learning technique and introduce a dual loss function to improve the network's robustness against unobserved human motions.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Biotechnology & Applied Microbiology
Shuang Xu, Zhiqiang Chen, Weiyi Cao, Feng Zhang, Bo Tao
Summary: The retinal vessel segmentation algorithm based on residual convolution neural network is able to accurately identify retinal vessels in fundus images, with excellent performance in achieving complete retinal vessel segmentation, connected vessel stems and terminals. The algorithm has proven to be effective in detecting more capillaries, with superior accuracy and specificity compared to other methods.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Dan Zhang, Pan Li, Lei Zhao, Duanqing Xu, Dongming Lu
Summary: In this paper, a convolutional neural network for image denoising is proposed, which includes noise mapping block, texture compensation block, and composition block. The model achieves superior performance by learning noise mapping, enhancing details, and synthesizing outputs.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Medicine, General & Internal
Grace Ugochi Nneji, Happy Nkanta Monday, Goodness Temofe Mgbejime, Venkat Subramanyam R. Pathapati, Saifun Nahar, Chiagoziem Chima Ukwuoma
Summary: Breast cancer is a leading cause of death among women worldwide. A lightweight separable convolution network (LWSC) is proposed to automatically learn and classify breast cancer from histopathological images. The LWSC model implements separable convolution layers to obtain wider receptive fields, and utilizes bottleneck convolution layers to reduce model dimension. The evaluation results show that the LWSC model performs optimally with high accuracy, sensitivity, and specificity on multi-class categories, and achieves comparable performance to other models.
Article
Computer Science, Information Systems
Anichur Rahman, Md Sazzad Hossain, Ghulam Muhammad, Dipanjali Kundu, Tanoy Debnath, Muaz Rahman, Md Saikat Islam Khan, Prayag Tiwari, Shahab S. Band
Summary: Federated Learning (FL), Artificial Intelligence (AI), and Explainable Artificial Intelligence (XAI) are trending technologies in the healthcare field. This paper presents a comprehensive analysis of FL using AI for smart healthcare applications, addressing existing problems and proposing strategies for healthcare management using FL and AI.
CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS
(2023)
Article
Automation & Control Systems
Hamdi Altaheri, Ghulam Muhammad, Mansour Alsulaiman
Summary: This article proposes an attention-based temporal convolutional network (ATCNet) for EEG-based motor imagery classification. The ATCNet model utilizes multiple techniques to boost the performance of MI classification. The proposed model achieves high accuracy on the BCI Competition IV-2a dataset.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Civil
Ghulam Muhammad, M. Shamim Hossain
Summary: This paper proposes light convolutional neural network (CNN) models for cognitive networking in an intelligent transportation system (ITS). The models include a 1D CNN for processing 1D temporal data and a deep tree CNN for processing image data from car camera sensors. By processing data independently on edge devices, the load and time of model execution are reduced. The proposed method achieves an accuracy of approximately 94-96% and an information density of 4.4 when tested on a publicly available facial emotion database.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Md. Milon Islam, Sheikh Nooruddin, Fakhri Karray, Ghulam Muhammad
Summary: Human Activity Recognition (HAR) is crucial for smart healthcare applications. Existing frameworks dealing with single modality of data lead to decreased reliability and accuracy. This article proposes a multi-level feature fusion technique using multi-head CNN with CBAM for visual data and ConvLSTM for time-sensitive multi-source sensor information. Experimental results show that the developed HAR framework outperforms existing methods.
INFORMATION FUSION
(2023)
Article
Chemistry, Multidisciplinary
Thamer Alanazi, Khalid Babutain, Ghulam Muhammad
Summary: Unintentional falls, especially among older adults, can lead to severe injuries and negative impact on quality of life. To address this issue, a vision-based fall detection system is proposed to reduce fall frequency and associated healthcare and productivity costs. The system utilizes a human segmentation model and image fusion technique for preprocessing, and a 3D multi-stream CNN model for classification, achieving impressive accuracy, sensitivity, specificity, and precision.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Chemical
Jaspreet Singh, Gurpreet Singh, Deepali Gupta, Ghulam Muhammad, Ali Nauman
Summary: This article introduces an improved OCI-OLSR routing protocol that aims to enhance the performance of the regular OLSR protocol in wireless ad hoc networks. By optimizing control interval management, an advanced MPR selection process, reducing neighbor hold time, and decreasing flooding, the suggested protocol shows promise in terms of performance metrics under diverse conditions.
Article
Computer Science, Artificial Intelligence
Abdullah Lakhan, Tor-Morten Gronli, Ghulam Muhammad, Prayag Tiwari
Summary: This paper discusses the complex domain of digital healthcare for Alzheimer's disease and explores the use of convex optimization to optimize computation time and accuracy constraints. It introduces a novel scheme called EDCNNS to address these challenges.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Naseem Ahmad, Ghulam Muhammad, Kuldeep Singh Yadav, Rabul Hussain Laskar, Ashraf Hossain, Zulfiqar Ali
Summary: This paper proposes a cascaded deep learning framework for accurate iris center localization in facial images. Experimental results show that the framework is robust to illumination variations and pose variations.
Article
Computer Science, Artificial Intelligence
Zhiguo Qu, Yang Tang, Ghulam Muhammad, Prayag Tiwari
Summary: This paper proposes a novel personalized federated learning algorithm based on information fusion to solve the problem of information fusion and sharing in intelligent vehicle networking. The algorithm achieves personalized privacy protection by grading users' privacy based on their preferences and adding noise that satisfies their privacy preferences. It performs collaborative training of deep models among different in-vehicle terminals using a lightweight dynamic convolutional network architecture to generate personalized models. By keeping the last layer local instead of sharing all model parameters, it adds another layer of data confidentiality and makes it difficult for adversaries to infer the target vehicle terminal's image.
INFORMATION FUSION
(2023)
Article
Green & Sustainable Science & Technology
Arif Hussain Magsi, Leanna Vidya Yovita, Ali Ghulam, Ghulam Muhammad, Zulfiqar Ali
Summary: A threshold-based content caching mechanism is proposed to detect and prevent content poisoning attacks, along with the integration of a blockchain system for privacy protection and network extension. Experimental results show that the mechanism achieves a 100% accuracy in identifying and preventing attackers, while effectively filtering out malicious blocks.
Article
Computer Science, Information Systems
Arif Hussain Magsi, Syed Agha Hassnain Mohsan, Ghulam Muhammad, Suhni Abbasi
Summary: A Vehicular Ad hoc Network (VANET) improves transportation efficiency by efficient traffic management, driving safety, and delivering emergency messages. Named Data Networking (NDN) has gained attention as an alternative to TCP/IP in VANET due to its promising features. However, NDN in VANET is vulnerable to attacks, including the critical Interest Flooding Attack (IFA). This study proposes using machine learning classifiers at roadside units (RSUs) to detect and prevent IFA vehicles, with the Random Forest (RF) classifier achieving the highest accuracy of 94%. The proposed IFA detection technique contributes to network resource protection.
Article
Telecommunications
Anichur Rahman, Md Jahidul Islam, Shahab S. Band, Ghulam Muhammad, Kamrul Hasan, Prayag Tiwari
Summary: Recent studies have highlighted the importance of new technologies such as Blockchain (BC), Software Defined Networking (SDN), and Smart Industrial Internet of Things (IIoT). These technologies offer data integrity, confidentiality, and integrity, particularly in industrial applications. Cloud computing, a well-established technology, is used to exchange sensitive information and provide remote access to computing and storage resources in the IIoT. However, cloud computing also presents significant security risks and challenges. To tackle these issues, this paper proposes a cloud computing platform for the IIoT that combines BC and SDN. The proposed architecture, named DistB-SDCloud, utilizes distributed BC for enhanced security, privacy, and integrity while maintaining flexibility and scalability. Furthermore, an SDN method is introduced to improve the durability, stability, and load balancing of the cloud infrastructure. The effectiveness of this implementation is experimentally tested using various parameters and monitoring attacks on the system.
DIGITAL COMMUNICATIONS AND NETWORKS
(2023)
Article
Chemistry, Multidisciplinary
Md. Ariful Islam, Vidhya Selvanathan, Puvaneswaran Chelvanathan, M. Mottakin, Mohammod Aminuzzaman, Mohd Adib Ibrahim, Ghulam Muhammad, Md. Akhtaruzzaman
Summary: NiOx NPs with different properties were successfully synthesized using four different nickel based-metal organic frameworks as precursors. Ni-TPA MOF derived NiOx NPs calcined at 600 degrees C were identified as the most suitable for hole transport layer application. The fabricated thin film exhibited a band energy gap of 3.25 eV and had a carrier concentration, hole mobility, and resistivity of 6.8 x 10(14) cm(-3), 4.7 x 10(14) ? cm, and 2.0 cm(2) V-1 s(-1), respectively. The device configuration of FTO/TiO2/CsPbBr3/NiOx/C achieved an efficiency of 13.9% with V-oc of 1.89 V, J(sc) of 11.07 mA cm(-2), and FF of 66.6%.
Article
Computer Science, Information Systems
Abdullah Almogahed, Mazni Omar, Nur Haryani Zakaria, Ghulam Muhammad, Salman A. AlQahtani
Summary: Refactoring is a widely used technique to improve software quality, but different refactoring techniques have varying effects on quality attributes. This study examines scenarios of using refactoring techniques and finds that this factor plays a significant role in determining their effects on software quality.
Article
Engineering, Biomedical
Esraa Hassan, M. Shamim Hossain, Abeer Saber, Samir Elmougy, Ahmed Ghoneim, Ghulam Muhammad
Summary: Biomedical image classification is crucial for computer vision tasks and clinical care. This paper proposes an architecture called MQCNN, based on the QCNN model and modified ResNet (50) pre-trained model, to enhance biomedical image classification in the MNIST medical dataset. Results show that MQCNN model outperforms other models in terms of accuracy, precision, recall, and F1 score.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2024)
Editorial Material
Computer Science, Theory & Methods
Kiho Lim, Christian Esposito, Tian Wang, Chang Choi
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Editorial Material
Computer Science, Theory & Methods
Jesus Carretero, Dagmar Krefting
Summary: Computational methods play a crucial role in bioinformatics and biomedicine, especially in managing large-scale data and simulating complex models. This special issue focuses on security and performance aspects in infrastructure, optimization for popular applications, and the integration of machine learning and data processing platforms to improve the efficiency and accuracy of bioinformatics.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Renhao Lu, Weizhe Zhang, Qiong Li, Hui He, Xiaoxiong Zhong, Hongwei Yang, Desheng Wang, Zenglin Xu, Mamoun Alazab
Summary: Federated Learning allows collaborative training of AI models with local data, and our proposed FedAAM scheme improves convergence speed and training efficiency through an adaptive weight allocation strategy and asynchronous global update rules.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Qiangqiang Jiang, Xu Xin, Libo Yao, Bo Chen
Summary: This paper proposes a multi-objective energy-efficient task scheduling technique (METSM) for edge heterogeneous multiprocessor systems. A mathematical model is established for the task scheduling problem, and a problem-specific algorithm (IMO) is designed for optimizing task scheduling and resource allocation. Experimental results show that the proposed algorithm can achieve optimal Pareto fronts and significantly save time and power consumption.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Editorial Material
Computer Science, Theory & Methods
Weimin Li, Lu Liu, Kevin I. K. Wang, Qun Jin
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Mohammed Riyadh Abdmeziem, Amina Ahmed Nacer, Nawfel Moundji Deroues
Summary: Internet of Things (IoT) devices have become ubiquitous and brought the need for group communications. However, security in group communications is challenging due to the asynchronous nature of IoT devices. This paper introduces an innovative approach using blockchain technology and smart contracts to ensure secure and scalable group communications.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Robert Sajina, Nikola Tankovic, Ivo Ipsic
Summary: This paper presents and evaluates a novel approach that utilizes an encoder-only transformer model to enable collaboration between agents learning two distinct NLP tasks. The evaluation results demonstrate that collaboration among agents, even when working towards separate objectives, can result in mutual benefits.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Hebert Cabane, Kleinner Farias
Summary: Event-driven architecture has been widely adopted in the software industry for its benefits in software modularity and performance. However, there is a lack of empirical evidence to support its impact on performance. This study compares the performance of an event-driven application with a monolithic application and finds that the monolithic architecture consumes fewer computational resources and has better response times.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Haroon Wahab, Irfan Mehmood, Hassan Ugail, Javier Del Ser, Khan Muhammad
Summary: Wireless capsule endoscopy (WCE) is a revolutionary diagnostic method for small bowel pathology. However, the manual analysis of WCE videos is cumbersome and the privacy concerns of WCE data hinder the adoption of AI-based diagnoses. This study proposes a federated learning framework for collaborative learning from multiple data centers, demonstrating improved anomaly classification performance while preserving data privacy.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Maruf Monem, Md Tamjid Hossain, Md. Golam Rabiul Alam, Md. Shirajum Munir, Md. Mahbubur Rahman, Salman A. AlQahtani, Samah Almutlaq, Mohammad Mehedi Hassan
Summary: Bitcoin, the largest cryptocurrency, faces challenges in broader adaption due to long verification times and high transaction fees. To tackle these issues, researchers propose a learning framework that uses machine learning to predict the ideal block size in each block generation cycle. This model significantly improves the block size, transaction fees, and transaction approval rate of Bitcoin, addressing the long wait time and broader adaption problem.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Rafael Duque, Crescencio Bravo, Santos Bringas, Daniel Postigo
Summary: This paper introduces the importance of user interfaces for digital twins and presents a technique called ADD for modeling requirements of Human-DT interaction. A study is conducted to assess the feasibility and utility of ADD in designing user interfaces, using the virtualization of a natural space as a case study.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Xiulin Li, Li Pan, Wei Song, Shijun Liu, Xiangxu Meng
Summary: This article proposes a novel multiclass multi-pool analytical model for optimizing the quality of composite service applications deployed in the cloud. By considering embarrassingly parallel services and using differentiated parallel processing mechanisms, the model provides accurate prediction results and significantly reduces job response time.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Seongwan Park, Woojin Jeong, Yunyoung Lee, Bumho Son, Huisu Jang, Jaewook Lee
Summary: In this paper, a novel MEV detection model called ArbiNet is proposed, which offers a low-cost and accurate solution for MEV detection without requiring knowledge of smart contract code or ABIs.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Sacheendra Talluri, Nikolas Herbst, Cristina Abad, Tiziano De Matteis, Alexandru Iosup
Summary: Serverless computing is increasingly used in data-processing applications. This paper presents ExDe, a framework for systematically exploring the design space of scheduling architectures and mechanisms, to help system designers tackle complexity.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)
Article
Computer Science, Theory & Methods
Chao Wang, Hui Xia, Shuo Xu, Hao Chi, Rui Zhang, Chunqiang Hu
Summary: This paper introduces a Federated Learning framework called FedBnR to address the issue of potential data heterogeneity in distributed entities. By breaking up the original task into multiple subtasks and reconstructing the representation using feature extractors, the framework improves the learning performance on heterogeneous datasets.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2024)