IEEE Open Journal of the Computer Society最新文献

{"title":"Real-Time Automated Cyber Threat Classification and Emerging Threat Detection Framework","authors":"Alemayehu Tilahun Haile;Surafel Lemma Abebe;Henock Mulugeta Melaku","doi":"10.1109/OJCS.2025.3580235","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3580235","url":null,"abstract":"Automating cyber threat intelligence (CTI) collection and analysis in real time is critical for the timely detection and mitigation of cyber threats. Cybersecurity researchers have recently recommended CTI as a proactive and robust method for automated cyber threat prediction. This automated solution collects and analyzes real-time data from social media, cybersecurity forums, and hacker forums where cybersecurity analysts and hackers discuss cybersecurity-related topics to discover potential threats. In this article, we propose a comprehensive framework that automates both cyber threat classification and emerging threat detection using real-time data from surface, deep, and dark web sources. We collected real-time data from hackers and security forums to construct binary and multiclass cyber threat classifications. We employed a labeled leaked dataset to be considered as ground truth for classification. Machine and deep learning techniques were used to perform the classification. Latent Dirichlet allocation (LDA) and nonnegative matrix factorization (NMF) were used to analyze topic distribution over time and identify emerging threats. This approach allows for the identification of zero-day attacks and other emerging threats by monitoring shifts in topics. Using a support vector machine with the bag-of-words (binary term weight) model achieved the highest accuracies of 93.67 and 96.35 for binary and multiclass classifications, respectively. Moreover, LDA and NMF were used to extract the top topics from various numbers of topics. The LDA model is well suited for identifying emerging trends and useful for real-time threat monitoring in cybersecurity.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"921-930"},"PeriodicalIF":0.0,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11037544","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550518","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":"ABMF-Net: An Attentive Bayesian Multi-Stage Deep Learning Model for Robust Forecasting of Electricity Price and Demand","authors":"MD Nazmul Hossain Mir;Arindam Kishor Biswas;Md Shariful Alam Bhuiyan;Md. Golam Rabbani Abir;M. F. Mridha;Md. Jakir Hossen","doi":"10.1109/OJCS.2025.3579522","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3579522","url":null,"abstract":"This article presents a novel deep learning model, the Attentive Bayesian Multi-Stage Forecasting Network (ABMF-Net), designed for robust forecasting of electricity price (USD/MWh) and demand (MW). The model incorporates an attention-based data selection mechanism, an encoder-decoder structure with masked time-series prediction, and a Bayesian neural network to generate both point and interval forecasts. Furthermore, a multi-objective Salp Swarm Algorithm (MSSA) is used to optimize forecasting accuracy and stability. Experimental evaluation on four real-world datasets from the Australian electricity market demonstrates that ABMF-Net achieves a MAPE as low as 1.89%, MAE of 0.67, RMSE of 0.98, and FICP of 0.98, outperforming LSTM, GRU, and Transformer models. Seasonal evaluations confirm the model’s robustness across high-variability conditions. These results position ABMF-Net as a high-performing and reliable forecasting model for modern electricity markets.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"896-907"},"PeriodicalIF":0.0,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11034710","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144519399","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":"A Physics-Guided Bayesian Neural Network for Sensor Fault Detection in Wind Turbines","authors":"MD Azam Khan;Arifur Rahman;Farhad Uddin Mahmud;Kanchon Kumar Bishnu;Hadiur Rahman Nabil;M. F. Mridha;Md. Jakir Hossen","doi":"10.1109/OJCS.2025.3577588","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3577588","url":null,"abstract":"Predictive maintenance is essential for ensuring the reliability and efficiency of wind energy systems. Traditional deep learning models for sensor fault detection rely solely on data-driven patterns, often lacking interpretability and robustness. This article proposes a Physics-Guided Bayesian Neural Network (PINN-BNN) model that integrates physics-informed learning with Bayesian inference to improve fault detection in wind turbines. The proposed approach enforces domain-specific constraints to ensure physically consistent predictions while quantifying uncertainty for risk-aware decision-making. The model is evaluated using a real-world wind turbine sensor dataset, achieving an accuracy of 97.6%, a recall of 91.8%, and an AUC-ROC of 0.987. The SHapley Additive exPlanations (SHAP) analysis reveals that gearbox temperature, blade vibration, and generator torque are the most critical features influencing failure predictions. Bayesian uncertainty estimation further improves interpretability by assigning confidence levels to each prediction. A comparative study with ten baseline models, including Long Short-Term Memory (LSTM), Transformer-based models, and traditional machine learning classifiers, demonstrates that the PINN-BNN model outperforms existing approaches while maintaining computational efficiency with a training time of 39.8 minutes and an inference time of 1.7 ms per sample. The integration of physics-informed learning ensures that the model generalizes well to varying environmental conditions, reducing false negatives and minimizing unexpected system failures. The proposed methodology presents a step toward interpretable and reliable predictive maintenance in wind energy systems.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"931-942"},"PeriodicalIF":0.0,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11027711","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550391","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":"VoiceTalk: A No-Code Approach for Creating Voice-Controlled Smart Home Applications","authors":"Yun-Wei Lin;Yi-Bing Lin;Yi-Feng Wu;Pei-Hsuan Shen","doi":"10.1109/OJCS.2025.3576725","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3576725","url":null,"abstract":"This article introduces VoiceTalk, a no-code approach that develops voice-controlled smart home applications without requiring programming expertise. At its core, VoiceTalk utilizes IoTtalk, an IoT application development platform for managing a diverse range of IoT devices. IoTtalk employs a two-tier microservices architecture, enabling users to define and chain applications through an intuitive drag-and-drop line interface. Leveraging its microservice architecture, VoiceTalk integrates IoTtalk with Google Home, offering a no-code solution for voice-controlled applications. VoiceTalk leverages its understanding of smart appliances in the room/house to generate specific prompts. We have compared the translation accuracy of 7 Automatic Speech Recognition (ASR) systems. We make two contributions. First, the no-code VoiceTalk platform significantly simplifies the development of Google Home-like applications. Second, by integrating ASRs with a commercial LLM such as GPT, we dramatically reduce voice-to-text translation errors, for examples, from 5.13% to 0.54% for the Web Speech API and from 2.25% to zero for Whisper Medium. For small-sized open-source LLMs such as Llama 3.2 3B, the errors are reduced to 0.72% for the Web Speech API and to zero for Whisper Medium. Furthermore, Device LLM Agent of VoiceTalk can be easily extended to integrate IoTtalk with other voice platforms, such as AWS Alexa.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"874-883"},"PeriodicalIF":0.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11023638","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144502874","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":"Explainable AI for Lightweight Network Traffic Classification Using Depthwise Separable Convolutions","authors":"Mustafa Ghaleb;Mosab Hamdan;Abdulaziz Y. Barnawi;Muhammad Gambo;Abubakar Danasabe;Saheed Bello;Aliyu Habib","doi":"10.1109/OJCS.2025.3576495","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3576495","url":null,"abstract":"With the rapid growth of internet usage and the increasing number of connected devices, there is a critical need for advanced Network Traffic Classification (NTC) solutions to ensure optimal performance and robust security. Traditional NTC methods, such as port-based analysis and deep packet inspection, struggle to cope with modern network complexities, particularly dynamic port allocation and encrypted traffic. Recently, Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) have been employed to develop classification models to accomplish this task. Existing models for NTC often require significant computational resources due to their large number of parameters, leading to slower inference times and higher memory consumption. To overcome these limitations, we introduce a lightweight NTC model based on Depthwise Separable Convolutions and compare its performance against CNN, RNN, and state-of-the-art models. In terms of computational efficiency, our proposed lightweight CNN exhibits a markedly reduced computational footprint. It utilizes only 30,611 parameters and 0.627 MFLOPS, achieving inference times of 1.49 seconds on the CPU and 0.43 seconds on the GPU. This corresponds to roughly 4× fewer FLOPS than the RNN baseline and 16× fewer than the CNN baseline, while also offering an ultracompact design compared to state-of-the-art models. Such efficiency makes it exceptionally well-suited for real-time applications in resource-constrained environments. In addition, we have integrated eXplainable Artificial Intelligence techniques, specifically LIME and SHAP, to provide valuable insights into model predictions. LIME and SHAP help interpret the contribution of each feature in decision-making, enhancing the transparency and trust in the model’s predictions, without compromising its lightweight nature. To support reproducibility and foster collaborative development, all associated code and resources have been made publicly available.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"908-920"},"PeriodicalIF":0.0,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11023864","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144550390","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":"Sybil-Resilient Publisher Selection Mechanism in Blockchain-Based MCS Systems","authors":"Ankit Agrawal;Ashutosh Bhatia;Kamlesh Tiwari","doi":"10.1109/OJCS.2025.3565620","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3565620","url":null,"abstract":"In Blockchain-based Mobile CrowdSensing (BMCS) systems, publishers (data collectors) can exploit the ability to create multiple blockchain identities, enabling Sybil attacks. Selfish, malicious, and collusive Sybil behaviors undermine both reward and majority-based data validation mechanisms, discouraging honest participation and threatening system integrity. Existing solutions often fail to address these issues, particularly in environments dominated by selfish or malicious publishers. This article proposes a novel two-phase publisher selection mechanism to mitigate Sybil attacks in BMCS systems. Phase-I employs a modified Proof-of-Stake (PoS) mechanism with carefully calibrated parameters, including staked amount, coinage, reputation, and randomness. The strategic combination of staked amount and coinage increases the difficulty of Sybil attacks as the system scales over time. Phase-II introduces a lightweight, reputation-based Proof-of-Work (PoW) mechanism tailored for Mobile CrowdSensing (MCS) environments, where puzzle difficulty adjusts dynamically based on the publisher's reputation. Reputation and penalization mechanisms are central to the proposed mechanism, ensuring robust prevention of task domination, selfish behavior, and malicious activities while fostering honest participation. Comprehensive on-chain and off-chain simulations demonstrate the proposed mechanism's effectiveness in mitigating Sybil attacks, reducing their impact, and promoting fair participation.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"586-598"},"PeriodicalIF":0.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10979902","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143949190","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":"SwinSegFormer: Advancing Aerial Image Semantic Segmentation for Flood Detection","authors":"Muhammad Tariq Shaheen;Hafsa Iqbal;Numan Khurshid;Haleema Sadia;Nasir Saeed","doi":"10.1109/OJCS.2025.3565185","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3565185","url":null,"abstract":"Semantic segmentation of aerial images is essential for unmanned aerial vehicle (UAV) applications in disaster management, particularly for identifying the flood-affected areas. Traditional techniques face challenges in capturing global semantic information due to their limited receptive fields, and high computational requirement. To address these issues, we propose a novel transformer-based model named SwinSegFormer, which feature a hierarchical encoder that efficiently generates multi-scale high-resolution features along with a lightweight decoder to reduce computational overhead. The proposed model is trained on FloodNet dataset and demonstrates efficient performance on challenging classes such as vehicles, pools, and flooded and non-flooded roads, which are crucial for effective disaster management. Additionally, we developed a post-processing module to categorize areas into flooded and non-flooded. The model achieves a validation mIoU of 75.1%, mDice of 85.4%, and mACC of 87.1%, representing a 10-12% improvement over state-of-the-art vision transformer-based methods. The effectiveness of model is further evaluated on real-world unlabeled flood imagery, highlighting its potential for supporting first aid activities during floods. Relevant codes are available at: <uri>https://github.com/Shaheen1998/SwinSegFormer</uri>.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"645-657"},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10979465","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144090765","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":"Addressing Security Orchestration Challenges in Next-Generation Networks: A Comprehensive Overview","authors":"Sadeep Batewela;Pasika Ranaweera;Madhusanka Liyanage;Engin Zeydan;Mika Ylianttila","doi":"10.1109/OJCS.2025.3564788","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3564788","url":null,"abstract":"Security Orchestration (SO) plays a pivotal role in ensuring robust, scalable, and efficient management of security mechanisms in next-generation 5G and beyond 5G (B5G) networks. This paper presents a comprehensive analysis of the technical challenges related to Security Orchestration (SO) in these advanced network technologies, focusing on key areas such as network security monitoring, interface standardization, privacy, scalability, multi-domain orchestration, and policy implementation. Additionally, we discuss lessons learned from existing works, identify remaining research gaps, and propose future directions for enhancing SO in 5G and B5G environments. Emerging technologies such as artificial intelligence (AI), blockchain, quantum computing and trusted execution environments (TEE) are also examined for their potential to address these challenges. The paper provides a taxonomy of SO-related issues and offers a roadmap for researchers and practitioners to navigate the evolving landscape of security in 5G and B5G networks.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"669-687"},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10977990","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144108318","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":"Optimized Multi-Modal Conformer-Based Framework for Continuous Sign Language Recognition","authors":"Neena Aloysius;Geetha M;Prema Nedungadi","doi":"10.1109/OJCS.2025.3564828","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3564828","url":null,"abstract":"This study introduces Efficient ConSignformer, a novel framework advancing Continuous Sign Language Recognition (CSLR) by optimizing the Conformer-based CSLR model, ConSignformer. Central to this advancement is the Sign Query Attention (SQA) module, a computationally efficient self-attention mechanism that enhances both performance and scalability, resulting in the Efficient Conformer. Efficient ConSignformer integrates video embeddings from dual-modal CNN pipelines that process heatmaps and RGB videos, along with temporal learning layers tailored for each modality. These embeddings are further refined using the Efficient Conformer for the fused data from two modalities. To improve recognition accuracy, we employ an innovative task-adaptive supervised pretraining strategy for Efficient Conformer on a curated dataset of continuous Indian Sign Language (ISL). This strategy enables the model to effectively capture intricate data relationships during end-to-end training. Experimental results highlight the significant contributions of the SQA module and the pretraining strategy, with our model achieving competitive performance on benchmark datasets, PHOENIX-2014 and PHOENIX-2014 T. Notably, Efficient ConSignformer excels in recognizing longer sign sequences, leveraging a computationally lightweight Conformer backbone.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"739-749"},"PeriodicalIF":0.0,"publicationDate":"2025-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10978102","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144205883","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":"Large Language Model Enhanced Particle Swarm Optimization for Hyperparameter Tuning for Deep Learning Models","authors":"Saad Hameed;Basheer Qolomany;Samir Brahim Belhaouari;Mohamed Abdallah;Junaid Qadir;Ala Al-Fuqaha","doi":"10.1109/OJCS.2025.3564493","DOIUrl":"https://doi.org/10.1109/OJCS.2025.3564493","url":null,"abstract":"Determining the ideal architecture for deep learning models, such as the number of layers and neurons, is a difficult and resource-intensive process that frequently relies on human tuning or computationally costly optimization approaches. While Particle Swarm Optimization (PSO) and Large Language Models (LLMs) have been individually applied in optimization and deep learning, their combined use for enhancing convergence in numerical optimization tasks remains underexplored. Our work addresses this gap by integrating LLMs into PSO to reduce model evaluations and improve convergence for deep learning hyperparameter tuning. The proposed LLM-enhanced PSO method addresses the difficulties of efficiency and convergence by using LLMs (particularly ChatGPT-3.5 and Llama3) to improve PSO performance, allowing for faster achievement of target objectives. Our method speeds up search space exploration by substituting underperforming particle placements with best suggestions offered by LLMs. Comprehensive experiments across three scenarios—(1) optimizing the Rastrigin function, (2) using Long Short-Term Memory (LSTM) networks for time series regression, and (3) using Convolutional Neural Networks (CNNs) for material classification—show that the method significantly improves convergence rates and lowers computational costs. Depending on the application, computational complexity is lowered by 20% to 60% compared to traditional PSO methods. Llama3 achieved a 20% to 40% reduction in model calls for regression tasks, whereas ChatGPT-3.5 reduced model calls by 60% for both regression and classification tasks, all while preserving accuracy and error rates. This groundbreaking methodology offers a very efficient and effective solution for optimizing deep learning models, leading to substantial computational performance improvements across a wide range of applications.","PeriodicalId":13205,"journal":{"name":"IEEE Open Journal of the Computer Society","volume":"6 ","pages":"574-585"},"PeriodicalIF":0.0,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10976715","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143929883","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}