International Journal of Intelligent Networks最新文献

{"title":"Cross-domain resource orchestration for end-to-end network slicing: A bid-level truthful hierarchical auction approach","authors":"Yongwen Liu,&nbsp;Rui Chen,&nbsp;Dongqing Liu","doi":"10.1016/j.ijin.2026.09.002","DOIUrl":"10.1016/j.ijin.2026.09.002","url":null,"abstract":"<div><div>Open Radio Access Network (O-RAN) architectures turn end-to-end network slicing into a tightly coupled multi-resource allocation problem, in which tenants must jointly acquire radio spectrum, transport bandwidth, and edge computing resources under capacity and budget constraints. Combinatorial auctions offer a natural modeling framework; however, exact winner determination is computationally intractable, and coupling heuristic allocations with Vickrey–Clarke–Groves (VCG) payments undermines incentive compatibility. To address these challenges, this paper develops a hierarchical greedy combinatorial auction (HG-CA) mechanism. The allocation problem is formulated as a binary integer program that captures cross-layer resource dependencies and is efficiently approximated via a hierarchy-aware greedy allocation rule. The mechanism further integrates structured bid generation, capacity-normalized allocation, and a critical-value payment scheme that secures bid-level truthfulness without requiring an optimal allocation. We prove that the proposed mechanism is dominant-strategy incentive-compatible at the bid level and individually rational, and we delimit this guarantee from the stronger tenant-level notion, which is characterized empirically. Simulation results show that HG-CA achieves empirically near-optimal social welfare with strong scalability, while significantly improving fairness and provider revenue over heuristic VCG-based benchmarks. These results demonstrate its effectiveness for large-scale multi-resource allocation in network slicing systems.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 121-134"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149051094","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":"DRCNet: Decoupled residual correction network for multivariate time series forecasting","authors":"Bin Yao ,&nbsp;Tie Wang ,&nbsp;Muhammad Bilal","doi":"10.1016/j.ijin.2026.05.002","DOIUrl":"10.1016/j.ijin.2026.05.002","url":null,"abstract":"<div><div>Accurate prediction of solar radiation energy can precisely assess the power generation capacity of photovoltaic systems, thereby optimizing grid dispatch and ensuring the stability of power supply. The prevailing methodology employs temporal models or spatiotemporal graph neural networks, which are used to extract the meteorological dependencies for solar radiation or conduct site-specific modeling. However, these studies overlearn the geographical features of the training domain, and lack the extrapolation continuity of unknown coordinates in space. To resolve these problems, this study constructs a decoupled residual correction network, which separates the region-invariant time series rules from geographically specific deviations through a dual-path parallel network. The first path uses a frequency-embedded encoder for general time series prediction based on multivariate variables. The second path uses an independent network to predict amplitude and vertical offsets from geographical features and residual features. Cross-regional zero-shot extrapolation verification utilized data from 12 sites (11 source domains and 1 target domain). DRCNet achieved the best performance on all four datasets, with the average absolute error (MAE) reduced to below 0.1 (specifically ranging from 0.062 to 0.095), significantly outperforming the second-best model Crossformer (0.36). Our codes will be released at <span><span>https://github.com/Phoenix-Snow/lab-explore-DRCNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 19-30"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148167858","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":"Dual-personalized federated fast convergence model for efficient service recommendation","authors":"Donghui Fan,&nbsp;Song Liang,&nbsp;Liang Han,&nbsp;Jingyi Zhang,&nbsp;Jian Zhuang,&nbsp;Jintao Wu","doi":"10.1016/j.ijin.2026.07.005","DOIUrl":"10.1016/j.ijin.2026.07.005","url":null,"abstract":"<div><div>Service recommendation in edge Service-Oriented Architecture (SOA) environments must balance privacy protection, recommendation accuracy, and the limited computing resources of user devices. Many existing federated recommendation methods protect raw interaction data, but often still rely on broad client participation, complex scoring models, or user-feature uploads for client grouping. This paper proposes a Dual-Personalized Federated Fast Convergence Model (DPFedFast) for efficient service recommendation. Compared with FedFast, DPFedFast introduces three technical improvements: first, clients are sampled according to the similarity of locally trained rating-function parameters rather than explicit user information; second, the recommendation model is simplified by adopting a lightweight single-layer neural rating function to reduce edge-side computation and communication; and third, a dual personalization mechanism separately updates personalized rating-function parameters and item embeddings to preserve user-specific preferences under the lightweight design. Extensive experiments conducted on four real-world datasets demonstrate the effectiveness of DPFedFast.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 109-118"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148735528","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":"TraffiPrompt: Network-aware multimodal prompt learning with motion-aware temporal modeling for driving video anomaly detection","authors":"Ruifeng Gao ,&nbsp;Chenghan He ,&nbsp;Ming Liu","doi":"10.1016/j.ijin.2026.05.003","DOIUrl":"10.1016/j.ijin.2026.05.003","url":null,"abstract":"<div><div>Driving video anomaly detection is crucial for intelligent transportation systems, yet remains challenging because raw video streams are high-dimensional, expensive to transmit, and hard to process under real-time latency and bandwidth constraints. To address this issue, we propose TraffiPrompt, a network-aware multimodal framework that combines normality-guided prompt learning with motion-aware temporal modeling under coarse temporal supervision. The framework first builds a compact multi-source visual representation for feature-level transmission, then enhances it with a motion-aware branch and ego-motion compensation to capture dynamic irregularities. It further introduces prompt-guided semantic alignment with anomaly-category prompts, normal prompts, traffic-context auxiliary prompts, and video captions to strengthen cross-modal interaction. We also adopt stagewise self-training with pseudo-label refinement to improve temporal localization. Experiments on DoTA show that TraffiPrompt achieves over 0.90 AUC while maintaining strong recall at tIoU thresholds of 0.30 and 0.50. Additional efficiency and delay analyses further clarify the practical characteristics of the proposed feature-level temporal head.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"7 ","pages":"Pages 40-49"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148167859","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":"Design and research of multi-heterogeneous network security intrusion detection system based on TensorFlow framework","authors":"Chuanfeng Lin,&nbsp;Bo Hong,&nbsp;Yuwei Xie","doi":"10.1016/j.ijin.2025.10.002","DOIUrl":"10.1016/j.ijin.2025.10.002","url":null,"abstract":"<div><div>Traditional intrusion detection systems (IDS) face challenges in complex and heterogeneous network environments, particularly in terms of accuracy, adaptability, and performance. This study presents an advanced IDS integrating the TensorFlow framework with heuristic optimization algorithms, including genetic and crow search algorithms, to address these challenges. The proposed system employs deep learning for feature extraction and classification while optimizing detection paths to enhance performance. Experimental results demonstrate that the system achieves a detection accuracy of 96.7 %, representing a 15 % improvement over traditional methods, with a corresponding 20 % increase in processing speed. The false positive and negative rates are measured at 2.3 % and 1.4 %, respectively. Quantitative analysis shows this work provides measurable improvements in intrusion detection for heterogeneous networks.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 305-313"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145839252","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 in indoor localization prediction using Received Signal Strength Indicator and Wi-Fi network","authors":"Hani Attar ,&nbsp;Walaa Saber Ismail ,&nbsp;Mohamed Hafez ,&nbsp;Shaimaa Bahaa ,&nbsp;Mohanad A. Deif ,&nbsp;M. Khosravi ,&nbsp;Howida Youssry","doi":"10.1016/j.ijin.2025.10.001","DOIUrl":"10.1016/j.ijin.2025.10.001","url":null,"abstract":"<div><div>Indoor usage of smartphones and electronic devices can be a source of information to detect the indoor location, which is known as localization that can be applied in large human health services and workplaces for example. Though the Global Positioning System (GPS) provides many effective location services using satellite signals, indoor localization is not included. Therefore, several technologies have been used for indoor localization, including Wireless Fidelity (Wi-Fi), Bluetooth Low Energy (BLE), and Received Signal Strength Indicator (RSSI), it has resulted in the proposal of Machine Learning (ML)-based indoor localization methodologies. Unlike the RSSI that indicates how well your device can hear a signal in a Wi-Fi network, this paper proposes indoor localization prediction using ML techniques based on Wi-Fi RSSI fingerprinting methodologies, encompassing data preprocessing, such as Data Cleansing (DC), Future Tuning (FT), and Feature Selection (FS). The proposed ML prediction models for indoor localization classifiers investigation in this paper are Support Vector Machine (SVM), K Nearest Neighbors (KNN), Decision Trees (DT), Random Forest (RF), and Linear Regression (LR). Moreover, a comprehensive performance comparison for the proposed prediction models is performed in this paper using nine datasets with different areas in a total of 31,470 records. The results show that KNN achieved the best performance for all parameters, making it the most recommended classifier for RSSI fingerprinting schemes.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 233-243"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145465328","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":"QoE-aware edge server placement in mobile edge computing using an enhanced genetic algorithm","authors":"Jinxiang Sha ,&nbsp;Jintao Wu ,&nbsp;Mingliang Wang ,&nbsp;Yonglin Pu ,&nbsp;Sheng Lu ,&nbsp;Muhammad Bilal","doi":"10.1016/j.ijin.2025.07.003","DOIUrl":"10.1016/j.ijin.2025.07.003","url":null,"abstract":"<div><div>Mobile Edge Computing (MEC) enhances service quality by decentralizing computational resources to network edges, thereby reducing latency and improving Quality of Service (QoS). However, the spatial distribution of edge servers critically impacts network transmission efficiency, while heterogeneous user perceptions of QoS metrics frequently lead to suboptimal Quality of Experience (QoE). Current research on Edge Server Placement (ESP) predominantly focuses on localized optimization of QoS metrics, yet fails to adequately incorporate systematic QoE modeling and coordinated optimization frameworks, leading to significant discrepancies between actual user experience and satisfaction with resource allocation. To address this gap, this study establishes a formalized QoE-aware Edge Server Placement (EESP) framework by rigorously characterizing the interdependence between QoE and QoS. We first prove the NP-completeness of the EESP problem through computational complexity analysis. Subsequently, we develop an Integer Linear Programming-based exact solver (EESP-O) for small-scale scenarios and propose an Enhanced Genetic Algorithm (EESP-EGA) for large-scale deployments. The EESP-EGA integrates adaptive crossover probability mechanisms and elite retention strategies to achieve near-optimal solutions for complex real-world configurations. Experimental evaluations conducted on a broad range of real-world datasets demonstrate that the proposed method outperforms several existing representative approaches in terms of QoE.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 65-78"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694327","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":"Secure digital asset trading technology based on MPC and blockchain","authors":"Hongguo Zhang,&nbsp;Yuxin Sun,&nbsp;Kaiqi Zhang,&nbsp;Zhibo Guan,&nbsp;Chao Ma,&nbsp;Hai Huang","doi":"10.1016/j.ijin.2025.11.004","DOIUrl":"10.1016/j.ijin.2025.11.004","url":null,"abstract":"<div><div>With the rapid expansion of digital asset trading, the contradiction between data sharing and privacy protection has increasingly become a significant challenge in the Internet environment. To address this issue, this paper proposes a secure multi-party computation scheme based on blockchain technology. Firstly, in response to the risk of data leakage in distributed storage scenarios, a threshold-based encryption algorithm is designed, utilizing a distributed key protection mechanism to effectively prevent single-point failures and data breaches. Secondly, a smart contract system is developed: the ERC721 contract is used to confirm the ownership of data assets, the ERC20 contract facilitates the transfer of usage rights, and the threshold decryption contract ensures secure multi-party computation and compliant incentive distribution. The collaboration of these three types of contracts enables comprehensive on-chain management of data assets, covering the entire process from ownership confirmation and circulation to compliant usage. In addition, this paper integrates non-interactive zero-knowledge proofs into the multi-party interaction process, allowing public verification of data consistency and computational validity on the blockchain. Finally, experiments are conducted to evaluate the impact of computation latency, communication overhead, and encryption parameters on system performance. The proposed scheme demonstrates significant performance improvements over mainstream SMPC protocols, with a 95.4 % reduction in key generation time and a 19.5 % reduction in ciphertext decryption time. Meanwhile, the scheme effectively resists various semi-malicious attacks, ensuring data security and privacy.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 253-264"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145579023","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":"Multi-relation-pattern knowledge graph embeddings for link prediction in hyperbolic space","authors":"Longxin Lin ,&nbsp;Huaibin Qin ,&nbsp;Quan Qi ,&nbsp;Rui Gu ,&nbsp;Pengxiang Zuo ,&nbsp;Yongqiang Cheng","doi":"10.1016/j.ijin.2025.02.002","DOIUrl":"10.1016/j.ijin.2025.02.002","url":null,"abstract":"<div><div>The aim of Knowledge Graph Embedding (KGE) is to acquire low-dimensional representations of entities and relationships for the purpose of predicting new valid triples, thereby enhancing the functionality of intelligent networks that rely on accurate data representation. In recommendation systems, for example, the model can enhance personalized suggestions by better understanding user-item relationships, especially when the relationships are hierarchical, such as in the case of user preferences across different product categories. Existing KGE models mostly learn embeddings in Euclidean space, which perform well in high-dimensional settings. However, in low-dimensional scenarios, these models struggle to accurately capture the hierarchical information of relationships in knowledge graphs (KG), a limitation that can adversely affect the performance of intelligent network systems where structured knowledge is critical for decision making and operational efficiency. Recently, the MuRP model was proposed, introducing the use of hyperbolic space for KG embedding. Using the properties of hyperbolic space, where the space near the center is small and the space away from the center is large, the MuRP model achieves effective KG embedding even in low-dimensional training conditions, making it particularly suitable for dynamic environments typical of intelligent networks. Therefore, this paper proposes a method that utilizes the characteristics of hyperbolic geometry to create an embedding model in hyperbolic space, combining translation and multi-dimensional rotation geometric transformations. This model accurately represents various relationship patterns in knowledge graphs, including symmetry, asymmetry, inversion, composition, hierarchy, and multiplicity, which are essential for enabling robust interactions in intelligent network frameworks. Experimental results demonstrate that the proposed model generally outperforms Euclidean space embedding models under low-dimensional training conditions and performs comparably to other hyperbolic KGE models. In experiments using the WN18RR dataset, the Hits@10 metric improved by 0.3% compared to the baseline model, and in experiments using the FB15k-237 dataset, the Hits@3 metric improved by 0.1% compared to the baseline model, validating the reliability of the proposed model and its potential contribution to advancing intelligent network applications.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 57-64"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071842","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":"Enhanced intelligent transportation network systems for optimized emergency medical services management","authors":"Yousef O. Sharrab ,&nbsp;Maymona A. Alshabatat ,&nbsp;Hani H. Attar ,&nbsp;Basma M. Irtahi ,&nbsp;Mohammad Ali H. Eljinini ,&nbsp;M. Khosravi ,&nbsp;Mohamed A. Hafez","doi":"10.1016/j.ijin.2025.11.010","DOIUrl":"10.1016/j.ijin.2025.11.010","url":null,"abstract":"<div><div>This work discusses and emphasizes improvements in emergency medical services (EMS) by using intelligent transportation systems (ITS), geographic information systems (GIS), network analysis approaches, interviews, questionnaires, and field studies. The aim is to study ambulance operation mechanisms, analyze the issues they face, and determine the efficiency and effectiveness of ambulance station locations in the civil defense centers in Amman city, which is regarded as a key point in the field of e-health, which improves the human health services by euthanizing the health system access. This study also seeks to find solutions to recent issues that ambulances face, such as late response time. The official local target is 9 min to calculate, while a 7-min threshold was used in GIS analysis to assess optimal coverage. The results show that GIS has a high impact on planning, location analysis, and network processes. Moreover, the results demonstrate that GIS can be effectively used to build a spatial allocation model for determining optimal ambulance service locations and thus help select the most suitable sites for service provision. However, the results show that the actual response time exceeded the 9-min target established by the Civil Defense Department, which is attributed to several factors such as road congestion, traffic light delays, bad weather conditions, and other reasons. This study suggests several recommendations to overcome ambulance traffic challenges in Amman city by implementing intelligent transportation systems in the management of EMS.</div></div>","PeriodicalId":100702,"journal":{"name":"International Journal of Intelligent Networks","volume":"6 ","pages":"Pages 314-333"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146077019","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}