International Journal of Intelligent Systems最新文献

{"title":"An Overview of Robot Embodied Intelligence Based on Multimodal Models: Tasks, Models, and System Schemes","authors":"Yao Cong,&nbsp;Hongwei Mo","doi":"10.1155/int/5124400","DOIUrl":"https://doi.org/10.1155/int/5124400","url":null,"abstract":"<div>\u0000 <p>The exploration of embodied intelligence has garnered widespread consensus in the field of artificial intelligence (AI), aiming to achieve artificial general intelligence (AGI). Classical AI models, which rely on labeled data for learning, struggle to adapt to dynamic, unstructured environments due to their offline learning paradigms. Conversely, embodied intelligence emphasizes interactive learning, acquiring richer information through environmental interactions for training, thereby enabling autonomous learning and action. Early embodied tasks primarily centered on navigation. With the surge in popularity of large language models (LLMs), the focus shifted to integrating LLMs/multimodal large models (MLM) with robots, empowering them to tackle more intricate tasks through reasoning and planning, leveraging the prior knowledge imparted by LLM/MLM. This work reviews initial embodied tasks and corresponding research, categorizes various current embodied intelligence schemes deployed in robotics within the context of LLM/MLM, summarizes the perception–planning–action (PPA) paradigm, evaluates the performance of MLM across different schemes, and offers insights for future development directions in this domain.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/5124400","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144281404","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial Intelligence in Melanoma Detection: A Review of Current Technologies and Future Directions","authors":"Fakhre Alam,&nbsp;Asad Ullah,&nbsp;Dilawar Shah,&nbsp;Shujaat Ali,&nbsp;Muhammad Tahir","doi":"10.1155/int/3164952","DOIUrl":"https://doi.org/10.1155/int/3164952","url":null,"abstract":"<div>\u0000 <p>Early and accurate identification of malignant melanoma continues to be a major challenge for clinicians in the field. Traditional diagnostic approaches, including physical examination, histology, imaging, and nodal assessments, are frequently costly, require significant expertise, and can display large variations among clinicians. These factors may result in missed or misdiagnosis, which often significantly affects a patient’s prognosis. We examine in detail how the application of AI methods such as machine learning and deep learning can be used to advance early detection and identification of melanoma. We review various AI algorithms, including standard classifiers, ensemble techniques, and complex deep learning models. Hybrid models that combine convolutional neural networks (CNNs) and support vector machines (SVMs) are emphasized in this review, as they show enhanced performance and improved resistance to variations in the diagnostician’s input. Better utility of transfer learning and data augmentation approaches is discussed to overcome the challenges posed by small and unbalanced medical datasets. The authors consider the combination of various types of medical information for more effective cancer diagnosis. However, significant obstacles, including model explainability, privacy safeguarding, and clinical evaluation, still need to be addressed. Extensive efforts are needed to overcome these barriers if AI systems are to be effectively adopted within healthcare environments. We suggest that AI offers the opportunity to revolutionize melanoma care by enabling rapid decision support and individualized treatment plans. Realizing this opportunity will depend on effective partnerships between researchers, clinicians, and industry to bring together advances in technology and their effective implementation in the healthcare system.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/3164952","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144273354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Abnormal Traffic Detection Method Based on DCNN-GRU Architecture in SDN","authors":"Xueyuan Duan,&nbsp;Kun Wang,&nbsp;Yu Fu,&nbsp;Taotao Liu,&nbsp;Yihan Yu,&nbsp;Jianqiao Xu,&nbsp;Lu Wang","doi":"10.1155/int/2846238","DOIUrl":"https://doi.org/10.1155/int/2846238","url":null,"abstract":"<div>\u0000 <p>In response to the centralized single-architecture abnormal traffic detection method in Software Defined Network (SDN), which consumes massive computational and network resources, and may lead to the decline of service quality of SDN network, this paper proposes a large-scale abnormal traffic detection method of SDN network based on Distributed Convolutional Neural Networks and Gate Recurrent Unit (DCNN-GRU) architecture. This method utilizes lightweight detection agents based on CNN deployed on each controller to extract traffic features preliminarily. Then it inputs the feature data into the GRU-based deep detection model hosted in the cloud for collaborative training and completes the final abnormal detection task. Since the feature extraction tasks are distributed across multiple controllers, the cloud server only needs to relearn and classify the extracted feature data, which is less costly than directly extracting feature information from the original traffic data and occupies less bandwidth resources than transmitting complete data packets. The experiment shows that the method achieves an abnormal detection accuracy of 0.9939, a recall rate of 0.9831, and a false alarm rate of only 0.0244, obtaining a higher precision and lower false alarm rate than traditional detection methods.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/2846238","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144256102","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"MCOA: A Multistrategy Collaborative Enhanced Crayfish Optimization Algorithm for Engineering Design and UAV Path Planning","authors":"Yaning Xiao,&nbsp;Hao Cui,&nbsp;Ruba Abu Khurma,&nbsp;Abdelazim G. Hussien,&nbsp;Pedro A. Castillo","doi":"10.1155/int/5054424","DOIUrl":"https://doi.org/10.1155/int/5054424","url":null,"abstract":"<div>\u0000 <p>The crayfish optimization algorithm (COA) is a recent bionic optimization technique that mimics the summer sheltering, foraging, and competitive behaviors of crayfish. Although COA has outperformed some classical metaheuristic (MH) algorithms in preliminary studies, it still manifests the shortcomings of falling into local optimal stagnation, slow convergence speed, and exploration–exploitation imbalance in addressing intractable optimization problems. To alleviate these limitations, this study introduces a novel modified crayfish optimization algorithm with multiple search strategies, abbreviated as MCOA. First, specular reflection learning is implemented in the initial iterations to enrich population diversity and broaden the search scope. Then, the location update equation in the exploration procedure of COA is supplanted by the expanded exploration strategy adopted from Aquila optimizer (AO), endowing the proposed algorithm with a more efficient exploration power. Subsequently, the motion characteristics inherent to Lévy flight are embedded into local exploitation to aid the search agent in converging more efficiently toward the global optimum. Finally, a vertical crossover operator is meticulously designed to prevent trapping in local optima and to balance exploration and exploitation more robustly. The proposed MCOA is compared against twelve advanced optimization algorithms and nine similar improved variants on the IEEE CEC2005, CEC2019, and CEC2022 test sets. The experimental results demonstrate the reliable optimization capability of MCOA, which separately achieves the minimum Friedman average ranking values of 1.1304, 1.7000, and 1.3333 on the three test benchmarks. In most test cases, MCOA can outperform other comparison methods regarding solution accuracy, convergence speed, and stability. The practicality of MCOA has been further corroborated through its application to seven engineering design issues and unmanned aerial vehicle (UAV) path planning tasks in complex three-dimensional environments. Our findings underscore the competitive edge and potential of MCOA for real-world engineering applications. The source code for MCOA can be accessed at https://doi.org/10.24433/CO.5400731.v1.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/5054424","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Intelligent Management Frameworks for Global Cooperation","authors":"Ana M. Gonzalez de Miguel,&nbsp;Antonio Sarasa-Cabezuelo","doi":"10.1155/int/1706422","DOIUrl":"https://doi.org/10.1155/int/1706422","url":null,"abstract":"<div>\u0000 <p>This paper presents the definition, use, and evaluation of intelligent management frameworks for global cooperation. The research work brings new concepts and ideas to design new management models and artificial intelligence solutions in sustainable environments. An intelligent management framework is a flexible and efficient vertical association of models, architectures, and processes. It is a mixed (architectural and methodological) association of services and procedures across IT departments of global organizations. The paper presents a general top-down approach to design these frameworks for global, cooperative models of intelligence. The approach includes five levels of abstraction and three refinement techniques. These elements are used to design an evaluation case study with global services and process-oriented cooperation for current sustainable targets in education. In our future work, we will implement these management solutions for government organizations currently involved with digital transformations.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/1706422","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144244575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Space Ground Collaborative SFC Flow Scheduling Strategy in Satellite–Terrestrial Integrated Network–Enabled Internet of Vehicles Rescuing Based on Computation–Space–Time Graph","authors":"Yingjie Deng,&nbsp;Yu Liu,&nbsp;Yumei Wang,&nbsp;Konglin Zhu,&nbsp;Peng Wu,&nbsp;Lu Cao,&nbsp;Wen Sun,&nbsp;Jingwen Xu","doi":"10.1155/int/9914571","DOIUrl":"https://doi.org/10.1155/int/9914571","url":null,"abstract":"<div>\u0000 <p>The extensive coverage of satellite constellations has rendered the satellite–terrestrial integrated network (STIN) a pivotal solution for communication and computation services in internet of vehicles (IoVs) rescuing in remote or disaster areas with limited terrestrial networks. To optimise network resource utilisation and service quality, the integration of the service function chain (SFC) into STIN-enabled IoV rescuing systems has become essential. However, traditional SFC-based STIN systems encounter challenges in flow scheduling flexibility, stemming from the sequential execution of subtasks on satellites equipped with virtual network functions (VNFs). This leads to a trade-off between data volume reduction and the additional communication and computation energy costs incurred in the orbit. To address this issue, this paper introduces a space ground collaborative SFC (SGC-SFC) flow scheduling strategy. This strategy enables the execution of subtasks on either VNF-equipped satellites or the ground vehicle formation, contingent on network conditions. Firstly, we carry out a computation–space–time graph (CSTG) model specifically for the STIN-enabled IoV rescuing system with SFC. This model integrates the computational layer into the space–time graph (STG), accurately capturing the data volume reduction characteristics and sequential execution constraints of SFC in the STIN-enabled IoV rescuing system. Secondly, a SGC-SFC flow scheduling algorithm is designed to identify a set of feasible paths with minimal energy cost and maximum processable data volume. Simulation results validate the effectiveness and robustness of our proposed SGC-SFC under diverse conditions.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/9914571","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144220277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Convolutional Neural Networks for Plant Disease Detection: A Mobile Application Approach (Agri Bot)","authors":"Hegazi Ibrahim,&nbsp;Abdelmoty M. Ahmed,&nbsp;Belgacem Bouallegue,&nbsp;Mahmoud M. Khattab,&nbsp;Mohab Abd El-Fattah,&nbsp;Nesma Abd El-Mawla","doi":"10.1155/int/7644407","DOIUrl":"https://doi.org/10.1155/int/7644407","url":null,"abstract":"<div>\u0000 <p>Plant diseases imperil global food security, decimating crop yields and endangering farmers’ livelihoods. Rapid, accurate detection remains a challenge, particularly in resource-constrained environments lacking portable tools. Our contribution, Agri Bot, introduces a pioneering deep convolutional neural network (CNN) model, uniquely optimized for mobile deployment, transforming plant disease diagnosis. This novel model integrates a lightweight architecture with advanced feature extraction, achieving an exceptional 97.30% accuracy and 98.76% area under the curve (AUC). Unlike computationally intensive traditional CNNs, Agri Bot’s innovative design—featuring a hybrid convolutional autoencoder, max pooling, and dropout layers—ensures high-speed, real-time performance on mobile devices. Comparative studies reveal Agri Bot’s superiority, surpassing state-of-the-art models like VGG16 (71.48%) and ResNet50 (96.46%), while rivaling InceptionV3 (99.07%) with significantly lower computational demands. By delivering precise, accessible diagnostics to remote regions, Agri Bot revolutionizes agricultural disease management, enhancing crop resilience and global food security.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/7644407","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144171237","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multidomain Secure Communication and Intelligent Traffic Detection Model in VANETs","authors":"Qikun Zhang,&nbsp;Mengqi Liu,&nbsp;Ping Li,&nbsp;Junling Yuan,&nbsp;Hongfei Zhu","doi":"10.1155/int/2539516","DOIUrl":"https://doi.org/10.1155/int/2539516","url":null,"abstract":"<div>\u0000 <p>Vehicular ad-hoc network (VANET) plays a vital role in the intelligent transportation system. It is crucial to ensure secure communication among entities in the VANET for realizing an efficient transportation system. In this scenario, the current communication scheme is vulnerable to the leakage of private information from entities. The research primarily centers on single-domain vehicular networks, with only a limited number of researchers exploring cross-domain authentication among vehicle entities. Cross-domain communication schemes have received little attention from scholars. Furthermore, there are issues, including the susceptibility of in-vehicle conversations to eavesdropping, the vulnerability of long-distance transmissions to interruptions, and the exposure of wireless networks to traffic attacks. To address these issues, a multidomain secure communication and intelligent traffic detection model in VANET is proposed. This model offers several notable advantages as follows: (1) It employs a key self-verification algorithm for local computation and authentication of entity keys. This approach mitigates the risks of identity impersonation attacks and key leakage results from third-party key escrow. (2) A multidomain communication scheme is devised to categorize vehicle-to-vehicle (V2V) scenarios into intradomain and interdomain, which correspond to situations where the communicating parties are within the same domain and across different domains, respectively. (3) We propose the implementation of new session message encryption algorithms for V2V communication. This involves generating dynamic random keys to ensure secure data sharing and facilitates long-distance cross-domain communication among vehicles. (4) An intelligent two-layer traffic detection paradigm is proposed to improve the efficiency of detecting attack traffic in vehicular networks. This paper provides security proofs and performance analysis of the proposed scheme. The experimental results demonstrate that within the communication module, the comparative scheme exhibits high computational demands and significant delays, whereas our approach provides superior security and better computational performance. Compared to the traditional detection model, our two-layer detection paradigm reduces model training time by 69–4477 ms and testing time by 9–1469 ms.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/2539516","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144171607","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Fire Detection and Suppression System for the Surveillance of a Wind Turbine Nacelle","authors":"Minsoo Lee,&nbsp;Eun Chan Do,&nbsp;Moon-Woo Park,&nbsp;Ki-Yong Oh","doi":"10.1155/int/6278987","DOIUrl":"https://doi.org/10.1155/int/6278987","url":null,"abstract":"<div>\u0000 <p>This paper proposes a novel fire detection and suppression system (FDSS) designed to detect and extinguish fires in the nacelle of a wind turbine. The FDSS incorporates three sensors: an infrared camera, an optical camera, and a 3D LiDAR, as well as a fire suppression system mounted on a pan and tilt control system. The FDSS features three key characteristics. First, an ensemble learning network simultaneously classifies and detects fire/smoke regions by integrating a classification neural network, an object detection neural network, and a cumulative alarm. This novel architecture significantly improves fire detection accuracy and reduces false alarm rates. Second, multimodal information precisely localizes overheat and fire/smoke regions, enabling the FDSS to automatically aim and extinguish fires by controlling the pan and tilt system. Third, a graph-based neural network accurately classifies the affected components in the nacelle using point cloud data from the 3D LiDAR. This novel neural network for object classification provides sufficient information for the location of a fire accident. Field and virtual experiments conducted in a fire test room and virtual nacelle environments demonstrate the FDSS’s effectiveness. Quantitative comparisons of three deep learning networks further highlight that these neural networks outperform other state-of-the-art deep learning models. Consequently, the FDSS provides a cost-effective and autonomous surveillance solution, enhancing the safe operation of wind turbines with advanced technologies in the fourth industrial revolution.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/6278987","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"BeGuard: An LSTM–Fused Defense Model Against Deepfakes in Competitive Activities–Related Social Networks","authors":"Yujie Li,&nbsp;Guoxu Liu,&nbsp;Chunlei Chen,&nbsp;Sunkyoung Kang,&nbsp;Andia Foroughi","doi":"10.1155/int/1282012","DOIUrl":"https://doi.org/10.1155/int/1282012","url":null,"abstract":"<div>\u0000 <p>We propose a novel defense mechanism for protecting users from deepfakes by analyzing their behaviors in competitive activities and their social interactions. The model dynamically embeds user behaviors based on their participation in competitive activities, capturing these activities’ temporal dynamics through long short–term memory networks. This allows the model to effectively identify patterns and changes in user behaviors. BeGuard also considers users’ social relationships, embedding the behaviors of their social friends to account for the influence of these connections on their actions. This results in a richer and more contextually aware behavioral representation. To improve detection accuracy, the model uses an attention mechanism to evaluate abnormal values in user behaviors, particularly those indicating potential deepfake content. This attention-based evaluation enhances the model’s capacity to detect subtle anomalies, providing a more effective defense against deepfakes in competitive activities–related social networks.</p>\u0000 </div>","PeriodicalId":14089,"journal":{"name":"International Journal of Intelligent Systems","volume":"2025 1","pages":""},"PeriodicalIF":5.0,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/int/1282012","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144108898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}