International Journal of Intelligent Networks最新文献

{"title":"Improving spam botnet detection through convolutional model and geolocation feature enhancement in a novel three-class classification task","authors":"Florentino Benedictus ,&nbsp;Muhammad Aidiel Rachman Putra ,&nbsp;Tohari Ahmad ,&nbsp;Choiru Za’in ,&nbsp;Tony de Souza-Daw","doi":"10.1016/j.ijin.2025.08.001","DOIUrl":"10.1016/j.ijin.2025.08.001","url":null,"abstract":"<div><div>Botnet detection remains a critical and challenging area in the field of information security, primarily due to the intricate architectures and sophisticated attack mechanisms employed by botnets. The significant influence of botnets on spam traffic is well-documented; however, much of the existing literature predominantly focuses on binary classification, distinguishing only between botnet and non-botnet traffic. This paper introduces a novel approach aimed at addressing this limitation by implementing an IP mapping mechanism leveraging geolocation data to enhance the quality of botnet datasets. These enriched datasets are subsequently utilized within a Convolutional Neural Network (CNN) framework to facilitate three-class classification. The proposed model differentiates among non-botnet traffic, spam botnets, and non-spam botnets, with the distinction between botnet classes driven by the substantial impact of spam botnets. The experimental results demonstrate that the proposed model achieves an average accuracy of 97.89%, along with a precision of 80.72%, recall of 72.40%, and F1-score of 73.71% across various scenarios using three distinct datasets.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 185-203"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145010305","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improving distributed systems failure prediction via multi-objective feature selection and deep forest","authors":"Zhidan Yuan ,&nbsp;Yikai Zhang ,&nbsp;Yingqi Yu ,&nbsp;Taizhi Lv ,&nbsp;Tao Huang","doi":"10.1016/j.ijin.2025.07.002","DOIUrl":"10.1016/j.ijin.2025.07.002","url":null,"abstract":"<div><div>Distributed systems failure prediction uses Key Performance Indicator (KPI) metrics to train machine learning models to identify potential system failures. Currently, this approach faces the challenge of KPI metrics redundancy. Although existing studies have used feature selection methods to address this issue, the optimal number of KPI metrics remains difficult to determine. Furthermore, existing failure prediction models have not achieved satisfactory performance. To address the aforementioned challenges, we propose a failure prediction method, MOFSDF, which leverages multi-objective optimization and the deep forest model. The method aims to achieve optimal failure prediction performance with the fewest KPI metrics. MOFSDF frames the selection of KPI metrics as a multi-objective optimization problem, where the objective is to minimize the number of KPI metrics while simultaneously maximizing the model’s performance. This optimization process is achieved through the NSGA-III algorithm. Furthermore, the integration of the deep forest model guarantees both the robustness and generalization capabilities of the failure prediction model. We use the ZTE dataset for the empirical study. The results demonstrate that MOFSDF significantly outperforms other comparative methods across multiple dimensions. Compared to nine classical models, the <span><math><mrow><mi>A</mi><mi>c</mi><mi>c</mi><mi>u</mi><mi>r</mi><mi>a</mi><mi>c</mi><mi>y</mi></mrow></math></span> improvement ranges from 1.1% to 97.9%, while the <span><math><mrow><mi>M</mi><mi>a</mi><mi>c</mi><mi>r</mi><mi>o</mi><mo>−</mo><mi>F</mi><mn>1</mn></mrow></math></span> improvement ranges from 1.1% to 179.4%. The <span><math><mrow><mi>K</mi><mi>a</mi><mi>p</mi><mi>p</mi><mi>a</mi></mrow></math></span> and <span><math><mrow><mi>H</mi><mi>a</mi><mi>m</mi><mi>m</mi><mi>i</mi><mi>n</mi><mi>g</mi><mspace></mspace><mi>L</mi><mi>o</mi><mi>s</mi><mi>s</mi></mrow></math></span> also show significant improvements. Moreover, the findings from the ablation studies further substantiate the rationale and effectiveness of the component configuration within MOFSDF.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 151-165"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144867150","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GAN-based solar radiation forecast optimization for satellite communication networks","authors":"Chao Chen ,&nbsp;Xin Liu ,&nbsp;Shizhong Zhao ,&nbsp;Muhammad Bilal","doi":"10.1016/j.ijin.2025.07.004","DOIUrl":"10.1016/j.ijin.2025.07.004","url":null,"abstract":"<div><div>Accurate short-term solar radiation forecasting is essential for the stable operation and dispatch of photovoltaic power generation systems. Advanced encoder–decoder architectures, utilizing satellite remote sensing data, are now primary techniques for this forecasting task. However, these methods encounter significant limitations, particularly as forecast horizons extend. In such scenarios, predictions often exhibit spatial texture degradation and distortions in radiation intensity. This significantly reduces precision and reliability, making it difficult to meet the demands of high-precision applications. To address these limitations, this paper proposes GAN-Solar, a novel quality optimization model for short-term solar radiation forecasting based on Generative Adversarial Networks (GANs). GAN-Solar utilizes an ED-AttUNet model, enhanced with conditional inputs, as its generator. A discriminator, incorporating residual structures, progressive downsampling, and conditional information, is employed to distinguish between real and generated forecasts. This adversarial process, guided by a hybrid loss function and a discriminator treated as a learnable objective function, refines the forecast quality. Experimental results on summer solar radiation data demonstrate that GAN-Solar significantly improves forecast quality. It reduces the Root Mean Square Error by approximately 3.2% and increases the Structural Similarity Index from 0.84 to 0.87 when compared to the baseline ED-AttUNet model. The proposed method effectively mitigates issues of texture degradation and intensity distortion, leading to clearer and more accurate solar radiation predictions.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 89-96"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144771588","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Resource optimization algorithm for 5G core network integrating NFV and SDN technologies","authors":"Chunxue Xu","doi":"10.1016/j.ijin.2025.04.001","DOIUrl":"10.1016/j.ijin.2025.04.001","url":null,"abstract":"<div><div>The growth in network demand has driven the development of new network technologies. However, traditional network architecture cannot meet the huge traffic of transportation and different business needs. To address this issue, a specific network service function chain is formed based on the network function virtualization. Dynamic resource awareness algorithms are introduced to construct an adaptive migration model based on network function virtualization. Based on the Multi-Armed Bandit (MAB) algorithm, a dynamic routing model based on MAB is constructed by using a greedy algorithm to search for random actions. When the nodes were 200 and 500, the migration costs of the adaptive migration model based on network function virtualization were 1000 and 3000, respectively. The average migration was 350 and 900 respectively, while destination nodes' average resource occupancy rates were 52 % and 58 %, respectively. When the path failure rates were 4 % and 20 %, the algorithm's safe path rates were 96.25 % and 92.75 %. For fixed and mobile nodes, the link load rate of the dynamic routing model based on the MAB algorithm was low and the load growth was relatively stable. This dynamic routing model's link delay is significantly less than the Dijkstra algorithm. These two models can maximize server resource utilization, reduce cost consumption, and achieve maximum overall benefits.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 36-46"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143943165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SMS spam detection using BERT and multi-graph convolutional networks","authors":"Linjie Shen ,&nbsp;Yanbin Wang ,&nbsp;Zhao Li ,&nbsp;Wenrui Ma","doi":"10.1016/j.ijin.2025.06.002","DOIUrl":"10.1016/j.ijin.2025.06.002","url":null,"abstract":"<div><div>The surge in smartphone usage has significantly increased Short Message Service (SMS) traffic and, consequently, SMS spam, posing risks such as phishing, financial losses, and privacy breaches. Traditional rule-based and blacklist methods fail against evolving spamming techniques, prompting the adoption of machine learning and deep learning approaches. However, models like Convolutional Neural Networks and Recurrent Neural Networks struggle to capture global co-occurrence patterns and complex semantics, while transformer-based models like Bidirectional Encoder Representations from Transformers (BERT) lack explicit syntactic and co-occurrence modeling. To address these limitations, we propose the BERT with Triple-Graph Convolutional Networks (BERT-G3CN) model, the first framework to integrate BERT word embeddings with graph embeddings from Co-occurrence, Heterogeneous, and Integrated Syntactic Graphs. This multigraph approach captures diverse features and models both global and local structures using tailored Graph Convolutional Networks. Experiments on two benchmark datasets demonstrate that BERT-G3CN achieves superior accuracy of 99.28 % and 93.78 %, representing an improvement of approximately 2–3 % over competitive baselines.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 79-88"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144738183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Transformer based framework for nuclei segmentation and cell counting on microscopic images of multiple organs","authors":"H.P. Ramya Shree,&nbsp;Minavathi,&nbsp;M.S. Dinesh","doi":"10.1016/j.ijin.2025.11.003","DOIUrl":"10.1016/j.ijin.2025.11.003","url":null,"abstract":"<div><div>Segmentation of cell nuclei in microscopic images is a vital task in cell counting, essential for cancer diagnosis and cancer grading. Also, it is more challenging due to the presence of overlapping nuclei which complicates the process of accurately distinguishing and separating individual nuclei. This study introduces an approach that combines Transformer-based encoder integrated with a U-Net architecture to improve the accuracy of nuclei segmentation. The proposed model was trained and validated on the 2018 Data Science Bowl dataset and demonstrated state-of-the-art performance, with a Dice-Similarity-Coefficient (DSC) of 92.6 % and an Intersection-over-Union (IoU) of 86.22 %. These metrics highlight the effectiveness of leveraging Transformers for capturing global contextual information, combined with the localized feature extraction capability of U-Net and enhancing segmentation accuracy. Additionally, a post-processing step was applied to refine the segmentation masks, improving boundary delineation and resolving overlapping nuclei. However, there exists several CNN models and deep learning models, this combination of advanced architectural design and post-processing techniques establishes a reliable framework for addressing the challenges of nuclei segmentation in biomedical imaging applications.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 283-292"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prostate cancer detection in intelligent big data systems using omnipresent AI with Fox and Golden Jackal Optimizers","authors":"Akshat Gaurav ,&nbsp;Varsha Arya ,&nbsp;Kwok Tai Chui ,&nbsp;Brij B. Gupta","doi":"10.1016/j.ijin.2025.07.005","DOIUrl":"10.1016/j.ijin.2025.07.005","url":null,"abstract":"<div><div>Prostate cancer is one of the most critical health concerns, making early detection essential for improved patient outcomes. In this context, this work used the ability of omnipresent AI and big data to provide accurate and fast prostate cancer detection. Golden Jackal Optimization (GJO) for hyperparameter optimization and the Fox optimizer for feature selection used to optimize the performance of CNN model. After training for five epochs, the model achieved an accuracy of 72%. Comparative analysis with models such as GRU, LSTM, and traditional classifiers demonstrates that the proposed method provides a robust and scalable solution for large-scale, data-driven healthcare applications.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 166-175"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144903518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A hybrid deep reinforcement learning and genetic algorithm approach for optimized resource allocation and reconfigurable intelligent surface deployment in 6G holographic communication","authors":"Brice Jibia ,&nbsp;Richard Mbondjo Essomba ,&nbsp;Steyve Nyatte ,&nbsp;Jacques Matanga ,&nbsp;Jean-Francois Essiben ,&nbsp;Severin Nguiya","doi":"10.1016/j.ijin.2025.11.001","DOIUrl":"10.1016/j.ijin.2025.11.001","url":null,"abstract":"<div><div>The advent of 6G holographic communication demands extremely high data rates and ultra-low latency, creating unprecedented challenges for resource allocation and Reconfigurable Intelligent Surface (RIS) configuration. To address these requirements, we propose a novel hybrid framework that integrates deep neural networks (DNN), genetic algorithms (GA), and deep reinforcement learning (DRL) to jointly optimize resource allocation and RIS deployment. The DNN first predicts future channel states and holographic traffic requirements, enabling the GA to perform proactive multi-objective optimization. The DRL agent then refines these solutions in real time, adapting to dynamic channel and traffic variations. Simulation results demonstrate the superiority of the proposed method over benchmark approaches. The hybrid DNN-GA-DRL achieves an average throughput of 6.55 Gbps, a latency of 0.1 ms, energy efficiency of 9.5 × 10⁸ bits/Joule, and spectral efficiency of 6.0 bps/Hz, while maintaining near-perfect QoS satisfaction (99.8 % throughput, 99.9 % latency). Compared to state-of-the-art GA, DRL, and hybrid baselines, our framework consistently delivers higher efficiency, lower delay, and superior adaptability. These findings confirm the effectiveness of combining predictive intelligence, evolutionary search, and real-time reinforcement learning for enabling seamless, immersive holographic communications in future 6G networks.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 265-282"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Machine Learning-enhanced loT and Wireless Sensor Networks for predictive analysis and maintenance in wind turbine systems","authors":"Lei Gong, Yanhui Chen","doi":"10.1016/j.ijin.2024.02.002","DOIUrl":"https://doi.org/10.1016/j.ijin.2024.02.002","url":null,"abstract":"","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"24 10","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139882379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Personal internet of things networks: An overview of 3GPP architecture, applications, key technologies, and future trends","authors":"Fariha Eusufzai, Aldrin Nippon Bobby, Farzana Shabnam, S. Sabuj","doi":"10.1016/j.ijin.2024.02.001","DOIUrl":"https://doi.org/10.1016/j.ijin.2024.02.001","url":null,"abstract":"","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139878827","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}