{"title":"EnFeSTDroid: Ensembled feature selection techniques based Android malware detection","authors":"Suruchi Jain , Hemant Goyal , Anshul Arora , Dhirendra Kumar","doi":"10.1016/j.compeleceng.2025.110763","DOIUrl":"10.1016/j.compeleceng.2025.110763","url":null,"abstract":"<div><div>Android smartphones have gained widespread popularity since 2008, making them frequent targets for malware. To address these threats, researchers have developed various detection models. Most existing techniques either use a single feature selection technique or combine a very few selection techniques, which can lead to overlooking other important features. In this study, we propose a novel method that first extracts permissions from applications. Then, it applies six different feature selection techniques, namely Information Gain, Extra Tree Classifier, Chi-Square, Mean Term Frequency (MTF), Inverse Document Frequency (IDF), and Mean Term Frequency–Inverse Document Frequency (MTF–IDF), to rank the permissions from the most to least significant. Furthermore, it applies Friedman’s and Post hoc Nemenyi tests to combine the rankings and identify the most relevant and distinguishing features for classifying malware. The results show that our proposed model could accurately classify 96.27% of the samples. Our work is novel and significant, as we have combined six feature selection techniques to enable the model to leverage the advantages of all the methods, rather than relying on a single or a few techniques. The proposed work also outperforms several other existing works in the literature.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"129 ","pages":"Article 110763"},"PeriodicalIF":4.9,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145327336","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Je-Seok Ham , Jia Huang , Peng Jiang , Jinyoung Moon , Yongjin Kwon , Srikanth Saripalli , Changick Kim
{"title":"Multimodal understanding with GPT-4o to enhance generalizable pedestrian behavior prediction","authors":"Je-Seok Ham , Jia Huang , Peng Jiang , Jinyoung Moon , Yongjin Kwon , Srikanth Saripalli , Changick Kim","doi":"10.1016/j.compeleceng.2025.110741","DOIUrl":"10.1016/j.compeleceng.2025.110741","url":null,"abstract":"<div><div>Pedestrian behavior prediction is one of the most critical tasks in urban driving scenarios, playing a key role in ensuring road safety. Traditional learning-based methods have relied on vision models for pedestrian behavior prediction. However, fully understanding pedestrians’ behaviors in advance is very challenging due to the complex driving environments and the multifaceted interactions between pedestrians and road elements. Additionally, these methods often show a limited understanding of driving environments not included in the training. The emergence of Multimodal Large Language Models (MLLMs) provides an innovative approach to addressing these challenges through advanced reasoning capabilities. This paper presents OmniPredict, the first study to apply GPT-4o(mni), a state-of-the-art MLLM, for pedestrian behavior prediction in urban driving scenarios. We assessed the model using the JAAD and WiDEVIEW datasets, which are widely used for pedestrian behavior analysis. Our method utilized multiple contextual modalities and achieved 67% accuracy in a zero-shot setting without any task-specific training, surpassing the performance of the latest MLLM baselines by 10%. Furthermore, when incorporating additional contextual information, the experimental results demonstrated a significant increase in prediction accuracy across four behavior types (crossing, occlusion, action, and look). We also validated the model s generalization ability by comparing its responses across various road environment scenarios. OmniPredict exhibits strong generalization capabilities, demonstrating robust decision-making in diverse and unseen driving rare scenarios. These findings highlight the potential of MLLMs to enhance pedestrian behavior prediction, paving the way for safer and more informed decision-making in road environments.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"129 ","pages":"Article 110741"},"PeriodicalIF":4.9,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145327337","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Md. Fatin Ishraque , Sk.A. Shezan , Innocent Kamwa , Yang Li , GM Shafiullah , Naveed Ahmad , Farooq Ahmad
{"title":"Novel intelligent model following controller and PQ droop controller operated nuclear-PV-biogas hybrid microgrid and EV charging station","authors":"Md. Fatin Ishraque , Sk.A. Shezan , Innocent Kamwa , Yang Li , GM Shafiullah , Naveed Ahmad , Farooq Ahmad","doi":"10.1016/j.compeleceng.2025.110756","DOIUrl":"10.1016/j.compeleceng.2025.110756","url":null,"abstract":"<div><div>The increasing adoption of electric vehicles (EVs) has led to significant challenges in the management of renewable-powered grid-connected electric vehicle charging stations (EVCS), particularly in maintaining grid stability. This paper introduces a novel Intelligent Model-Following Controller (IMFC) for EVCS integrated with a hybrid microgrid consisting of nuclear, photovoltaic (PV), and biogas power sources. The proposed IMFC aims to improve voltage and frequency stability, as well as overall energy management, compared to traditional controllers such as the PQ Droop Controller (PQDC). A comprehensive simulation study is conducted to evaluate the performance of both controllers under various dynamic conditions. A comparative analysis is conducted between IMFC and a PQDC to assess their performance in real-world scenarios to control the power system responses (active power, reactive power, voltage and frequency) of the hybrid system. Two consecutive three-phase faults have been implemented within the system and the transient response have been analyzed for both the controllers. The results show that the IMFC achieves a renewable fraction of 89.1%, with a cost of energy of $0.0132/kWh, and an internal rate of return (IRR) of 73%, demonstrating its economic feasibility and environmental benefits. The IMFC outperforms the PQDC in terms of transient response and system resilience, reducing the transient recovery time to 1.5 s, compared to 2.2 s for PQDC. Additionally, the IMFC provides better frequency regulation with a peak deviation of ±0.04 p.u., as opposed to ±0.1 p.u. for PQDC. These findings highlight the superiority of the IMFC in ensuring stable, efficient, and sustainable operation of hybrid renewable-powered EVCS.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"129 ","pages":"Article 110756"},"PeriodicalIF":4.9,"publicationDate":"2025-10-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Amr Magdy , M. Hassaballah , Marghny H. Mohamed , Mohammed M. Abdelsamea , Khalid N. Ismail
{"title":"HMSA-Net: A hierarchical multi-scale aggregation network for multimodal biomedical image segmentation","authors":"Amr Magdy , M. Hassaballah , Marghny H. Mohamed , Mohammed M. Abdelsamea , Khalid N. Ismail","doi":"10.1016/j.compeleceng.2025.110780","DOIUrl":"10.1016/j.compeleceng.2025.110780","url":null,"abstract":"<div><div>Medical image segmentation plays a vital role in clinical workflows such as disease diagnosis, treatment planning, and outcome monitoring. However, achieving robust segmentation across different anatomical regions, imaging modalities, and resolution scales remains a significant challenge. This paper presents a novel segmentation model, Hierarchical Multi-Scale Aggregation Network (HMSA-Net), designed to enhance segmentation performance in medical imaging. HMSA-Net follows a hierarchical encoder–decoder structure, where the encoder is built upon Res2Net, leveraging bottleneck layers to effectively extract multi-scale contextual features. The decoder integrates Hierarchical Attention Refinement Blocks (HARBs), which employ convolutional layers and squeeze-and-excitation mechanisms to dynamically recalibrate channel-wise feature responses, improving the model’s ability to emphasize critical anatomical structures. Additionally, HMSA-Net incorporates a multi-scale aggregation module, enabling effective fusion of features at different resolutions, thereby refining segmentation accuracy. Experimental evaluations on the BraTS2020 dataset demonstrate the model’s effectiveness, achieving Dice scores of 0.89 for whole tumor (WT), 0.81 for tumor core (TC), and 0.73 for enhancing tumor (ET). Furthermore, HMSA-Net was assessed on three unimodal medical imaging datasets: CVC ClinicDB, the 2018 Data Science Bowl, and ISIC-2018 skin lesion segmentation, achieving Dice scores of 90.5, 87.8, and 88.2, respectively. These results validate HMSA-Net’s capability to serve as a robust segmentation framework across both 2D and 3D medical imaging modalities.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"129 ","pages":"Article 110780"},"PeriodicalIF":4.9,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324074","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"A comprehensive methodology to design an LCC/LCC compensated DD-DD coupler for efficiency maximization in IPT systems","authors":"K. Satya Prakash, P.C. Sekhar","doi":"10.1016/j.compeleceng.2025.110778","DOIUrl":"10.1016/j.compeleceng.2025.110778","url":null,"abstract":"<div><div>Charging pads and compensation play a significant role in the inductive power charging system of electric vehicles. Its output power and efficiency depend on the precise magnetic design and the compensation tuning. In this connection, this paper develops a comprehensive strategy for designing <em>LCC/LCC</em> compensated Double D – Double D (DD) pads in a DC link capacitor-less bi-directional charging system to achieve the intended power output and coupling coefficient with maximized efficiency. By defining different dimensional attributes of the DD-DD structure, their effect on the magnetic and electrical performance parameters of the charger is assessed by varying the attributes’ values for the considered compensation parameters. The values of these attributes are optimized with the intent to steer the design towards the desired specifications. Subsequently, a methodology for selecting the optimal compensation variables for maximizing the efficiency at the desired power is established. Moreover, the work depicts the impact of output voltage on the optimal combination of the variables and the superiority of the developed formulation. To validate the proposed methodology, a 1 kW experimental prototype capable of bidirectional power transfer between the grid and a vehicle is developed. With a coupling coefficient of 0.3 and operating at 85 kHz, the developed prototype achieved an efficiency of 94 %.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"129 ","pages":"Article 110778"},"PeriodicalIF":4.9,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324152","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mani R. , Dharminder Chaudhary , A. Padmavathi , Cheng-Chi Lee
{"title":"Security analysis and designing unilateral and bilateral two party ideal-lattice based authenticated key establishment protocol for anonymous mobile communication","authors":"Mani R. , Dharminder Chaudhary , A. Padmavathi , Cheng-Chi Lee","doi":"10.1016/j.compeleceng.2025.110750","DOIUrl":"10.1016/j.compeleceng.2025.110750","url":null,"abstract":"<div><div>A two-party authenticated key establishment based on lattices allows two entities to set up a shared secret key securely over a vulnerable transmission medium while ensuring authentication of the participating parties. Given quantum computers promising danger to conventional cryptographic systems, lattice-based protocols utilize quantum-resistant cryptographic primitives (Ring Learning With Error) to provide security guarantees. Many lattice-based authentication key exchange protocols have been designed in the last few years. In this article, the authors have performed a security analysis and they have designed unilateral and bilateral two party ideal-lattice based authenticated key establishment protocols (depending on whether authentication is one-sided (unilateral) or mutual (bilateral), their applications vary) for anonymous mobile communication. In unilateral authentication (HTTPS/TLS 1.3), only one party (typically a server) proves its identity, while the other remains anonymous or does not require explicit authentication. In bilateral authentication (Signal, WhatsApp, Telegram), both parties verify each other’s identities before establishing a secure session. The proposed scheme incorporates forward-secure properties to ensure that even if the long-term key are compromised, the confidentiality of past communication does not hamper. This protocol also provides anonymity, essential for safeguarding individual liberties and preserving confidentiality in sensitive communication scenarios. The protocol possesses a minimum number of exchanged messages and can reduce the number of communication rounds to help minimize the communication overhead.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110750"},"PeriodicalIF":4.9,"publicationDate":"2025-10-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhe Fu , Shuo Yuan , Pengjun Cao , Jing Wei , Heng Wang , Gaoxiang Zhang , Bizheng Luo , Hong Zhang
{"title":"Open-world object detection with multi-dataset image–label matching","authors":"Zhe Fu , Shuo Yuan , Pengjun Cao , Jing Wei , Heng Wang , Gaoxiang Zhang , Bizheng Luo , Hong Zhang","doi":"10.1016/j.compeleceng.2025.110742","DOIUrl":"10.1016/j.compeleceng.2025.110742","url":null,"abstract":"<div><div>In real-world scenarios, many categories appear in target scenes that were not encountered during training, making existing video object detection methods unsuitable for open-world applications. This paper proposes an open-world object detection method based on multi-dataset image–label matching to tackle the challenges of open-world object detection. First, a multi-dataset image–label matching training strategy is proposed, which aligns image features with label text features from multiple datasets, an innovative matching classification loss function is designed to guide model training. Then, an image–label deep fusion module is constructed to strengthen the model’s ability to understand the correspondence between visual and textual descriptions, thereby improving the accuracy of matching label texts to corresponding regions in images. A decoupled, staged training method is employed, independently training the proposal generation and category classification stages to better adapt to the diversity and uncertainty of open-world scenarios. Finally, extensive comparative and ablation experiments validate the proposed method’s effectiveness on the open-world dataset LVIS, achieving an average improvement of about 2 percentage points over baseline methods in various evaluation metrics. Additionally, visualizations across different scenes are presented to intuitively demonstrate the method’s efficacy and advanced performance.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110742"},"PeriodicalIF":4.9,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Satin bird optimization and sliced Bi-directional gated recurrent unit based network intrusion detection system","authors":"WT Valavan, Nalini Joseph","doi":"10.1016/j.compeleceng.2025.110760","DOIUrl":"10.1016/j.compeleceng.2025.110760","url":null,"abstract":"<div><div>In recent times, the Intrusion Detection System (IDS) have played a crucial role in enhancing security and detecting anomalies in networks. Deep Learning (DL) algorithms have demonstrated high efficiency in capturing optimal features and achieving more accurate differentiation between normal and attack classes. As the amount of data increases, high-dimensional features make the training process more difficult. To overcome this, this article develops the Satin Bird Optimization (SBO) and Sliced Bi-directional Gated Recurrent Unit (SBi-GRU) technique to detect intrusions in a network. The SBO algorithm is designed to select significant features from entire feature set, thereby reducing the feature dimension and enhancing classification performance. The SBi-GRU network includes a slicing process, bi-directional structure, and GRU network. The slicing mechanism accelerates the training process and balances the effectiveness and performance. Subsequently, Multi-Head Self-Attention (MHA) is integrated with SBi-GRU to learn hidden patterns across various subspaces. The developed SBO and SBi-GRU algorithm achieved 99.99% accuracy on NSL-KDD, 99.99% accuracy on CIC-IDS 2018, and 98.98% accuracy on UNSW-NB15 when compared to other conventional algorithms such as Long Short-Term Memory (LSTM) and Auto-Encoder (AE).</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110760"},"PeriodicalIF":4.9,"publicationDate":"2025-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145324803","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Towards a LLM-based intelligent system for detecting propaganda within textual content","authors":"Angelo Gaeta , Vincenzo Loia , Angelo Lorusso , Francesco Orciuoli , Antonella Pascuzzo","doi":"10.1016/j.compeleceng.2025.110765","DOIUrl":"10.1016/j.compeleceng.2025.110765","url":null,"abstract":"<div><div>Large Language Models (LLMs) have emerged as versatile and powerful tools for a wide array of natural language processing tasks, ranging from text generation to semantic comprehension. Among their diverse applications, LLMs exhibit significant potential in detecting propaganda. This work presents a computational approach for identifying propaganda techniques within textual content, leveraging both proprietary and open-source LLMs. The approach not only detects the presence of propaganda but also identifies specific parts of the text where these techniques are employed. Central to this methodology is the careful selection of LLMs and the application of advanced prompting strategies, including role-playing, reduced context windowing, few-shot learning, and chain-of-thought reasoning, to enhance prompt design and model performance. The effectiveness of the proposed approach was assessed through quantitative metrics. Additionally, an LLM-based intelligent system implementing the approach was developed and described in terms of its components and functionalities. This system, realized as a software prototype, was evaluated in SemEval 2020 Task 11 news articles, showcasing notable improvements over state-of-the-art methods in propaganda detection.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110765"},"PeriodicalIF":4.9,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145319532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Priority based hybrid congestion management approach for improving sensor data transmission in IoT network","authors":"Anitha P. , H.S. Vimala , Shreyas J.","doi":"10.1016/j.compeleceng.2025.110764","DOIUrl":"10.1016/j.compeleceng.2025.110764","url":null,"abstract":"<div><div>The Internet of Things connects numerous devices in smart cities, enabling seamless data exchange. However, challenges like limited bandwidth, buffer overflows, and heavy traffic often lead to network congestion. To address this issue, a Priority-Based Hybrid Congestion Management approach is proposed. It optimizes data collection in IoT networks by prioritizing sensor data, dynamically adjusting transmission rates, and applying efficient data compression. It incorporates congestion detection, notification, and mitigation strategies to enhance network efficiency. Simulations carried out using Contiki OS and Cooja demonstrate that the proposed technique outperforms existing approaches, achieving a 20% increase in throughput, reducing energy consumption to 7.6 mJ per packet, improving fairness (0.98), reducing delay (12.6 ms), and improving packet delivery ratio. The findings confirm that the proposed technique effectively minimizes congestion while ensuring reliable data transmission in IoT networks, making it a robust solution for smart city applications.</div></div>","PeriodicalId":50630,"journal":{"name":"Computers & Electrical Engineering","volume":"128 ","pages":"Article 110764"},"PeriodicalIF":4.9,"publicationDate":"2025-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145320472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}