IEEE Open Journal of the Computer Society最新文献

{"title":"Kolmogorov-Arnold Vision Transformer for Image Reconstruction in Lung Electrical Impedance Tomography","authors":"Ibrar Amin;Shuaikai Shi;Hasan AlMarzouqi;Zeyar Aung;Waqar Ahmed;Panos Liatsis","doi":"10.1109/OJCS.2025.3559390","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3559390","url":null,"abstract":"Electrical impedance tomography is a non-invasive and non-ionizing imaging technique, which can provide real-time monitoring of the internal structures and function of the human body, and has been particularly popular in lung monitoring. However, the associated inverse problem is ill-posed, leading to suboptimal image quality with low spatial resolution, which hinders its practical use in the clinical settings. To achieve reliable image reconstruction, this work proposes a novel deep learning approach, applied to lung monitoring. The proposed model is a hybrid of the vision transformer and the recently introduced Kolmogorov Arnold Network (KAN). The fully connected layers in the transformer are replaced with KAN layers, which enhances its ability to learn the complex relationship between the voltage measurements and the conductivity distribution within the lungs. In comparison with the use of convolutional models and Vision Transformer, the proposed method achieves outstanding performance with a mean squared error of 0.0045, structural similarity index of 0.96, relative error of 0.11, and correlation coefficient of 0.98.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"519-530"},"PeriodicalIF":0.0,"publicationDate":"2025-04-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10960369","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143896479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust Joint Active and Passive Beamforming for Reconfigurable Intelligent Surface Assisted Full-Duplex Transmissions Under Imperfect Channels","authors":"Li-Hsiang Shen;Chia-Jou Ku;Kai-Ten Feng","doi":"10.1109/OJCS.2025.3556710","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3556710","url":null,"abstract":"The sixth-generation (6G) wireless technology recognizes the potential of reconfigurable intelligent surfaces (RIS) as an effective technique for intelligently manipulating channel paths through reflection to serve desired users. Full-duplex (FD) systems, enabling simultaneous transmission and reception from a base station (BS), offer the theoretical advantage of doubled spectrum efficiency. However, the presence of strong self-interference (SI) in FD systems significantly degrades performance, which can be mitigated by leveraging the capabilities of RIS. Moreover, accurately obtaining channel state information (CSI) from RIS poses a critical challenge. Our objective is to maximize downlink (DL) user data rates while ensuring quality-of-service (QoS) for uplink (UL) users under imperfect CSI from reflected channels. To address this, we propose a robust active BS and passive RIS beamforming (RAPB) scheme for RIS-FD, accounting for both SI and imperfect CSI. RAPB incorporates distributionally robust design, conditional value-at-risk (CVaR), and penalty convex-concave programming (PCCP) techniques. Simulation results demonstrate the UL/DL rate improvement are achieved by considering different levels of imperfect CSI. The proposed RAPB schemes validate their effectiveness across different RIS deployments and RIS/BS configurations. Benefited from robust beamforming, RAPB outperforms the existing methods in terms of non-robustness, deployment without RIS, conventional approximation, and half-duplex systems.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"502-518"},"PeriodicalIF":0.0,"publicationDate":"2025-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10946837","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143892521","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced Hydro-Informatic Modeling Through Feedforward Neural Network, Federated Learning, and Explainable AI for Enhancing Flood Prediction","authors":"Shahariar Hossain Mahir;Md Tanjum An Tashrif;Md Ahsan Karim;Dipanjali Kundu;Anichur Rahman;Md. Amir Hamza;Fahmid Al Farid;Abu Saleh Musa Miah;Sarina Mansor","doi":"10.1109/OJCS.2025.3556424","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3556424","url":null,"abstract":"Flood prediction is one of the most critical challenges facing today's world. Predicting the probable time of a flood and the area that might get affected is the main goal of it, and more so for a region like Sylhet, Bangladesh where transboundary water flows and climate change have increased the risk of disasters. Accurate flood detection plays a vital role in mitigating these impacts by allowing timely early warnings and strategic planning. Recent advancements in flood prediction research include the development of robust, accurate, and low-cost flood models designed for urban deployment. By applying and utilizing powerful deep learning models show promise in improving the accuracy of prediction and prevention. But those models faced significant issues related to scalability, data privacy concerns and limitations of cross-border data sharing including the inaccuracies in prediction models due to changing climate patterns. To address this, our research adopts the Federated Learning (FL) framework in an effort to train state-of-the-art deep learning models like Long Short-Term Memory Recurrent Neural Network (LSTM-RNN), Feed-Forward Neural Network (FNN) and Temporal Fusion Transformer-Convolutional Neural Network (TFT -CNN) on a 78-year dataset of rainfall, river flow, and meteorological variables from Sylhet and its upstream regions in Meghalaya and Assam, India. This approach promotes data privacy and allows collaborative learning while working under cross-border data-sharing constraints, therefore improving the accuracy of prediction. The results showed that the best-performing FNN model achieved an R-squared value of 0.96, a Mean Absolute Error (MAE) value of 0.02, Percent bias (PBIAS) value of 0.4185 and lower Root Mean Square Error (RMSE) in the FL environment. Explainable AI techniques, such as SHAP, sheds light on the most significant role played by upstream rainfall and river dynamics, particularly from Cherrapunji and the Surma-Kushiyara river system, in driving flood events in Sylhet. These results demonstrate the effectiveness of privacy-preserving and AI-driven methodology implemented. These are being used in improving flood prediction and provide actionable insights for policymakers and disaster management authorities to pave the way toward scalable, transnational strategies that can be applied to mitigate the effects of flooding in vulnerable regions.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"726-738"},"PeriodicalIF":0.0,"publicationDate":"2025-03-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10946125","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144206068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DiffCoR: Exposing AI-Generated Image by Using Stable Diffusion Model Based on Consistent Representation Learning","authors":"Van-Nhan Tran;Piljoo Choi;Hoanh-Su Le;Suk-Hwan Lee;Ki-Ryong Kwon","doi":"10.1109/OJCS.2025.3575507","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3575507","url":null,"abstract":"Diffusion-based generative models have significantly advanced the field of image synthesis, presenting additional challenges regarding the integrity and authenticity of digital images. Consequently, the identification of AI-generated images has become a critical problem in image forensics. However, there is a lack of literature addressing the detection of images generated by diffusion models. In this article, our focus is on developing a model capable of detecting images generated through both GAN techniques and diffusion models. We propose DiffCoR, a novel detection method for identifying AI-generated images. It consists of two main modules: Stable Diffusion Processing (SDP) and Image Representation Learning (IRL). The SDP module uses a pre-trained Stable Diffusion model to reconstruct input images via reverse diffusion and captures subtle manipulations through reconstruction discrepancies. The IRL module applies self-supervised learning with Latent Consistency Loss (LCL) to extract robust, invariant features, ensuring consistent latent representations across augmented views. We also incorporate frequency domain analysis using Discrete Fourier Transform (DFT) to enhance manipulation detection. Additionally, we introduce ForensicsImage, a publicly available dataset of over 400,000 real and AI-generated images from LSUN-Bedroom, CelebA-HQ, CelebDFv2, and various diffusion models. Experiments on ForensicsImage and GenImage show that DiffCoR achieves state-of-the-art performance, with strong cross-dataset generalization, making it suitable for real-world use in digital forensics, content verification, and social media moderation.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"1353-1365"},"PeriodicalIF":0.0,"publicationDate":"2025-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11018794","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144918328","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic Classifying of Requirements-Relevant Contents From App Reviews in the Arabic Language","authors":"Abualsoud A. Hanani;Alaa R. Isaac;Abdallatif Abu-Issa","doi":"10.1109/OJCS.2025.3573499","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3573499","url":null,"abstract":"The market for mobile application development continues to thrive with billions of users and millions of apps. Collecting software requirements for mobile apps has to cope with this trend, so as for the software to compete in this crowded scene. Therefore, efforts to analyze mobile app reviews for requirements have shown a similar trend of increase. Among the billions of mobile users, there are hundreds of millions of Arabic-speaking users. According to our knowledge, this study would be one of the first studies in the field of mining mobile app reviews for the assistance of requirements engineering, to direct its focus on Arabic reviews. The main contribution of this study is to provide a framework for mining mobile app reviews in Arabic. A dataset of 7604 Arabic app reviews has been constructed and manually annotated by six experts. Each categorization aims at assisting one or more processes of software requirements engineering. Three configurations of deep neural networks, namely, CNN, LSTM, and BLSTM, were used to classify the app reviews into the considered categories of software requirements from the Arabic reviews. Furthermore, two word embeddings were utilized, on pre-trained models; Fasttext and Word2Vec, produced by this study. The sentimental analysis results show that the LSTM classifier with the Fasttext word embeddings gives the best F1-score, 79.17%. However, the BLSTM classifier with the fastText embeddings outperforms the other classifiers, with an F1-score of 69.83%, when used for identifying the sub-categories of the user perspective main category. The F1-score for classifying the sub-categories of the intention and topics with the LSTM and using fastText embeddings is 82.68% and 85,02%, respectively. These results outperform the other configurations of the classifiers and word embeddings. These results demonstrate the potential of our system to serve as a robust tool for automating software requirement extraction from Arabic app reviews, particularly in contexts where real-time user feedback is critical to agile development cycles.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"862-873"},"PeriodicalIF":0.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11015261","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308517","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of Computationally Efficient Identity-Based Proxy Signatures","authors":"Saddam Hussain;Ali Tufail;Haji Awg Abdul Ghani Naim;Muhammad Asghar Khan;Gordana Barb","doi":"10.1109/OJCS.2025.3573638","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3573638","url":null,"abstract":"Proxy signatures (PS) are important cryptographic primitives widely used in digital signature applications across various domains. This survey explores PS security solutions in Identity-Based settings, including Short Identity-Based Proxy Signature (SIBPS), Identity-Based Proxy Signature with Message Recovery (IBPSMR), and Identity-Based Designated Verifier Signature (IBDVS). It also determines the performance of IBPS to address security requirements for delegation within resource-limited environments such as IoT devices and cloud computing. The evaluation determines performance bottlenecks while optimizing the computational complexity and communication overhead to support the practical and real-world implementation of IBPS. The findings reveal that IBPS schemes suffer from significant computation time and communication overhead due to heavy bilinear pairing operations. To evaluate and compare these schemes, we employ the Evaluation based on Distance from Average Solution (EDAS) model, which ranks the IBPS schemes according to their relative performance. The results indicate that the scheme proposed by Sarde et al., 2015 achieves the best performance, with a computation time of 6.9118 milliseconds and a communication overhead of 2464 bits. It is followed by the scheme from Jenefa and Shen et al., 2024 which records 7.7743 milliseconds and 2848 bits, and the scheme from Gu et al., 2015 with 6.2194 milliseconds and 3104 bits, respectively. Finally, we explored potential directions for future research.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"846-861"},"PeriodicalIF":0.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11015719","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Unbounded Depth ElGamal-Based Asymmetric Updatable Encryption Technique","authors":"Mostefa Kara;Ammar Boukrara;Mohammad Hammoudeh;Muhamad Felemban;Samir Guediri","doi":"10.1109/OJCS.2025.3551877","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3551877","url":null,"abstract":"This article introduces an ElGamal-based asymmetric updatable encryption scheme, tailored to address the challenges of secure key rotation in cryptographic systems. The proposed solution enables ciphertexts encrypted under an old key to be efficiently and securely updated to a new key without decryption, ensuring data confidentiality and integrity. By leveraging ElGamal's inherent mathematical properties, the scheme provides unbounded depth for key updates, asymmetric encryption capabilities, and independence from specific ciphertext structures. Lightweight pseudorandom generators (PRGs) are used to facilitate secure and efficient management of the random values required for encryption and re-encryption processes. The proposed approach demonstrates robust forward and backward security, ensuring resilience against information leakage even in the event of key compromise. Comprehensive performance evaluations highlight its efficiency, with minimal computational and communication overhead, making it suitable for large-scale systems and resource-constrained environments. Comparative analysis further confirms its superiority over existing techniques in encryption speed, ciphertext update time, and scalability. This work provides a practical and secure framework for managing frequent key updates in diverse applications, including cloud storage, the Internet of Things, and secure communication networks.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"491-501"},"PeriodicalIF":0.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10938675","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143883489","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bilingual Bangla OCR for Rural Empowerment: Detecting Handwritten Queries and Agricultural Assistance","authors":"Mahanur Alam;Md. Johirul Islam Tutul;Md. Anwar Hussen Wadud;Md. Jakir Hossen;M. F. Mridha","doi":"10.1109/OJCS.2025.3573317","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3573317","url":null,"abstract":"Farmers in rural areas often struggle to access crucial agricultural information due to language barriers, low literacy rates, and limited exposure to digital tools. While many can write in Bangla, most agricultural resources are available only in English or require navigating complex systems, making it difficult for them to find relevant information. Existing Optical Character Recognition (OCR) technologies, which could help bridge this gap, are primarily designed for printed text and often fail to recognize handwritten Bangla script accurately. Issues such as biased datasets, diverse handwriting styles, and background noise further reduce accuracy, making these systems unreliable for real-world use. To tackle these challenges, we have developed a lightweight and unbiased OCR model specifically for handwritten Bangla text. Our solution integrates a custom Convolutional Neural Network (CNN) with InceptionV3, enhancing recognition accuracy while ensuring efficiency for low-resource devices like smartphones. Additionally, we incorporate a two-way translation feature, enabling seamless Bangla-to-English and English-to-Bangla conversion. This allows farmers to write in Bangla, translate content when needed, and access critical information in a way that best suits them. Our solution empowers rural farmers by enabling them to interact with digital platforms in their native language, bridging the gap between handwritten communication and modern technology. Beyond agriculture, this technology has far-reaching applications in tourism, healthcare, education, and government services, fostering digital inclusion. By advancing OCR for Bangla, our research promotes equitable access to technology, equipping communities with essential tools to improve productivity and quality of life in the digital era.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"943-954"},"PeriodicalIF":0.0,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11014544","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Membership Inference Attacks and Differential Privacy: A Study Within the Context of Generative Models","authors":"Borja Arroyo Galende;Patricia A. Apellániz;Juan Parras;Santiago Zazo;Silvia Uribe","doi":"10.1109/OJCS.2025.3572244","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3572244","url":null,"abstract":"Membership attacks pose a major issue in terms of secure machine learning, especially in cases in which real data are sensitive. Models tend to be overconfident in predicting labels from the training set. Nevertheless, its application has traditionally been limited to supervised models, while in the case of generative models we have found that there is a lack of theoretical foundations to bring this concept into the scene. Hence, this article provides the theoretical background in the context of membership inference attacks and their relationship to generative models, including the derivation of an evaluation metric. In addition, the link between these types of attack and differential privacy is shown to be a particular case. Lastly, we empirically show through simulations the intuition and application of the concepts derived.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"801-811"},"PeriodicalIF":0.0,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11008817","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144264198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comparison of Deep Learning Techniques for RF-Based Human Posture Detection Systems","authors":"Eugene Casmin;Miriam Rodrigues;Américo Alves;Rodolfo Oliveira","doi":"10.1109/OJCS.2025.3571587","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3571587","url":null,"abstract":"This article focuses on techniques for a human posture classification framework that implements radio frequency (RF) active systems. In the first step, we describe the general approach considered for human posture classification. To this effect, we propose four different solutions: one based on traditional signal processing (SP) techniques, where the detection is centred around a correlation of prior classification masks; a second based on a hybrid SP and deep learning (DL) technique, where the DL model is trained with supervised data gathered at a single distance to the target; a third based on a hybrid SP and DL technique trained with data gathered at multiple distances to the target; and a fourth that uses variational auto-encoder (VAE) for feature generation. Their performance is then compared on the basis of classification accuracy and computation time. We show that although the SP-based solution presents high accuracy, the hybrid SP/DL solutions are advantageous in terms of classification accuracy and robustness at multiple distances, albeit requiring higher computation time. We further show the slight edge that VAE-based solutions have over plain DL solutions in terms of accuracy.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"776-788"},"PeriodicalIF":0.0,"publicationDate":"2025-03-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11007508","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144232129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}