International Journal of Intelligent Information and Database Systems (30 papers in press)

Regular Issues

• Subway tunnel deformation monitoring based on 3D laser scanning technology  
  by Xiaoming Ji, Xu Wu, Yan Bao 
  Abstract: As urban infrastructure, particularly subway systems, gets more intricate, it becomes crucial to prioritise the upkeep of its structural stability and safety. To guarantee the safety, structural stability, and operational effectiveness of subway tunnels, the study proposes using the TunnelScanPro framework, which uses 3D laser scanning technology to monitor and analyse changes in the design and form of subway tunnels over time. This study uses a three-dimensional laser scanning technology to monitor changes in the geometries of subway tunnels. More specifically, the study focuses on using visual information to evaluate the structural integrity and safety of the tunnels. The paper aims to use 3D laser scanning technology to offer insights and methods that may be used in practical situations to help with proactive monitoring and repair of subway tunnels. The TunnelScanPro framework detected deformations in subway tunnels with 95% accuracy. Safety improved 40% and high-risk deformations decreased significantly, according to the study.
  Keywords: subway tunnelling; deformation monitoring; 3D laser scanning; infrastructure safety; visual analysis; urban transportation; structural integrity.
  
  
• Hybrid optimised deep residual network with trust parameters for intrusion detection in IoT  
  by Asha Rawat, Harsh Namdev Bhor, Jayprabha Terdale, Varsha Bhole, Anuradha Thakare, Vishal Ratansing Patil 
  Abstract: Security issues are still challenging due to the availability of brilliant skills and hacking tools. Thus, detecting the intrusion in the IoT environment is crucial. Hence, this research introduces a novel optimised deep residual network based on the trust and KDD parameters. Here, an efficient mayfly spider monkey optimisation (MSMO) is proposed for tuning the adjustable parameters of the intrusion detector named deep residual network (DRN), which is modelled by hybridising the social behaviour of the mayfly in the mayfly optimisation algorithm (MA) with the foraging behaviour of the spider monkey based on the fission property of the spider monkey optimisation (SMO) to obtain the global best solution. Here, the trust factors and the KDD Cup features are considered for learning the classifier. The proposed model obtained better performance in accuracy of 0.913, precision of 0.919, false alarm rate of 0.084, and recall of 0.958.
  Keywords: intrusion detection; deep residual networks; optimisation; trust factors; KDD Cup features.
  
  
• Convolution-based adaptive ResUNet3 + with attention-based ensemble convolution networks for COVID-19 segmentation and classification  
  by S. Salini, B. SelvaPriya 
  Abstract: In 2018, residual U-shaped network (Res-UNet) and dense U-shaped network (Dense-UNet) were born based on the U-Net architecture. Inspired by dense and residual connections, respectively, Res-UNet and Dense-UNet substitute a kind of dense or residual connection for each U-Net sub-module. The community of artificial intelligence has produced a variety of deep learning models with the intention of recognising COVID-19 based on the visual features of chest X-rays. It is unfortunate that this is the case since constructing really deployable clinical models often requires segmentation as a crucial precursor step. Other applications in radiology typically need segmentation. It might be difficult to differentiate COVID-19 from other pulmonary disorders due to the fact that many lung diseases have similar visual characteristics with COVID-19. Using a segmentation module and an ensemble classifier, we have constructed our deep learning pipeline with the intention of assisting in the clarification of the diagnosis of individuals who are suspected of having COVID-19. Following the completion of an exhaustive comparison investigation, we are able to show that our most advantageous model is capable of effectively achieving an accuracy of 91% and a sensitivity of 92%.
  Keywords: COVID-19 classification; visualisation check; dataset description.
  
  
• A novel hybrid model integrating 1DCNN and WSVM for enhanced chronic disease prediction  
  by Fatma Zohra Tassadit Ait Mesbah, M’hamed Bilal Abidine, Belkacem Fergani 
  Abstract: Chronic diseases require ongoing care and are often diagnosed late, leading to complications and even death. An effective predictive system for rapid and intelligent diagnosis of these pathologies is crucial. This study proposes a hybrid 1DCNN-LDA-WSVM model that combines a 1D convolutional neural network (CNN), linear discriminant analysis (LDA), and weighted support vector machine (WSVM). This model explores the joint application of 1DCNN and LDA for the extraction and selection of pertinent deep features from datasets. The WSVM is employed as a binary classifier to address the issue of minority class overweighting in SVM modeling. Evaluation across four medical datasets demonstrates enhanced performance with predictive accuracy rates of 95%, 99%, 98%, and 99% on the CHDD, PIDD, WBCD, and CKDD datasets, respectively. These results underscore the model's capability to increase precision in forecasting chronic diseases.
  Keywords: disease prediction; dimensionality reduction; deep learning; DL; machine learning; ML; weighted support vector machine; WSVM.
  
  
• A New Feature Selection Approach Based on New Multi-Exhaustive Search  
  by Fatma Zohra Debba, Lynda Dib, Khaled Berrahil 
  Abstract: Feature selection (FS) is the mechanism of selecting a smaller subset of informative features from the entire dataset in order to improve the performance of the classification model and the result comprehensibility. It contains two essential aspects: feature evaluators and search methods to find the appropriate features in the search space. Among the search methods already proposed, there is the Exhaustive Search (ES) which, unlike other search methods, guarantees to find the optimal subset because all possible combinations of features are tested against a predetermined criterion. But the major drawback of this search method is that it becomes computationally unfeasible, especially with large data sets. To overcome this drawback and take advantage of its optimality, we propose in this paper a new search method called Multi-Exhaustive Search (MES) in which we adjust the use of the ES in order to find the best subset in very low computational time. As
  Keywords: Feature Selection; Search Methods; Exhaustive Search; Multi-Exhaustive Search; Classification; Machine Learning.
  
  
• Deep learning-based hybrid optimisation for multiclass plant disease detection using leaf images in a distributed environment  
  by Bandi Ranjitha, Arpakkam Karuppan Sampath 
  Abstract: A novel module is designed for multi-class plant disease detection named fractional geese jellyfish search optimisation enabled deep convolutional neural network (FGJSO_DCNN). The input plant leaf image is partitioned utilising enhanced fuzzy c-means clustering (FCM). In the mapper phase, pre-processing is performed by an adaptive Kalman filter (AKF), and leaf disease segmentation is carried out by Link-net, which is trained to employ FGJSO. The augmentation progress is conducted to alter the provided image. The progression of feature extraction is carried out and it is given to the reducer phase. On the other hand in the reducer phase, plant disease classification is accomplished in terms of first level classification using DCNN tuned by FGJSO and second level classification that is detection progress is performed by FGJSO_DCNN. The suggested FGJSO_DCNN model achieved a maximum accuracy of 0.915, TPR of 0.908, FPR of 0.080, F1-score of 0.918, and precision of 0.928.
  Keywords: plant disease detection; MapReduce framework; wild geese migration optimisation; GMO; jellyfish search optimisation; JSO; deep convolutional neural network; deep CNNs.
  
  
• Document-level sentiment analysis using Jaya chimp optimisation algorithm-enabled deep residual network  
  by Manoj L. Bangare, Sampath Arpakkam Karuppan, Debarati Ghosal, Ashwin Perti, Sanjay Nakharu Prasad Kumar 
  Abstract: Document-level sentiment classification automates the process of categorising text reviews on a single topic as representing negative or positive sentiments. Users and customers are intended to share comments and reviews about their products on various social network sites. One of these processing steps is the classification of emotions associated with the reviews. Therefore, this research paper introduces a robust sentiment analysis method, named Jaya chimp optimisation algorithm-enabled deep residual network (JayaChOA-enabled DRN) for document-level sentiment classification. The input is pre-processed and tokenised, and then the key features are extracted. Moreover, the DRN classifier is used for the sentiment classification where the optimal weights are computed using the JayaChOA. Meanwhile, the introduced JayaChOA is implemented by the incorporation of Jaya optimiser and chimp optimisation algorithm (ChOA). The JayaChOA-based DRN obtained the highest precision of 0.914, F-measure of 0.919, and recall of 0.925 using K-fold.
  Keywords: sentiment analysis; deep learning; chimp optimisation algorithm; Jaya optimiser; natural language processing; NLP.
  
  
• Data aggregation in wireless sensor networks using Bayesian-based data encryption and fragmentation modelling  
  by L. Rajesh, H.S. Mohan, M.K. Bindiya 
  Abstract: This paper proposes a model for data fragmentation and modelling in wireless sensor networks (WSNs) using the Bayesian fuzzy clustering (BFC) technique. Initially, WSN nodes are simulated, and the shuffled shepherd squirrel search optimisation algorithm (SSSSOA) is accomplished for choosing the cluster head (CH). Later, route maintenance operation is performed using the link quality metrics. Hierarchical fractional bidirectional least-mean-square (HFBLMS) is employed for data reduction and data aggregation. After that, the security of the nodes is ensured during data transmission using trust metrics. Besides, the proposed BFC approach is used in the data fragmentation and modelling phase where the elliptic curve cryptography (ECC) encryption and the adaptive data partitioning process are performed. Finally, the decryption and the de-blocking operations are performed. The introduced BFC approach achieved a detection ratio of 81.13%, delay of 0.105 s, packet deliver ration (PDR) of 98.13%, and energy of 2.502 J.
  Keywords: wireless sensor networks; data aggregation; shuffled shepherd optimisation; squirrel search algorithm; Bayesian fuzzy clustering; BFC.
  
  
• Prediction of cardiovascular disease using intelligent nextgen machine learning algorithmic breakthroughs  
  by M. Rohini, S. Oswalt Manoj 
  Abstract: Cardiovascular disease (CVD) is a prevalent and life-threatening condition that affects middle-aged and elderly individuals, leading to severe complications due to unhealthy lifestyles. The goal of the study was to train the prospective machine learning model that introduces a novel approach by integrating generative pre-trained models, combined with attention mechanisms, to refine feature selection to detect cardiac disease at an early stage. The analysis of clinical data demands distinct challenges in the context of generative model learning due to data complexity and the diverse nature of disease markers. Addressing these, the proposed study significantly improved the predictive accuracy by refining the models ability to recognise patterns specific to cardiac conditions. The gradient boosting (GB) algorithm emerged as the most effective optimal predictor, with 97.86% accuracy, 98.52% sensitivity, and 99.72% ROC for CVD classification.
  Keywords: machine learning; ML; gradient boosting; GB; logistic regression; LR; cardiovascular disease; CVD; gene prediction.
  
  
• Automated organised tour planning with blockchain: an innovative solution  
  by Asmaa Boughrara, Nourhene Aicha Daoud, Nedjma Louiza Harkati 
  Abstract: The traditional travel planning process often involves hiring a travel agency, which can be costly for budget-conscious travellers. Additionally, the tourism industry faces challenges such as fraud, lack of transparency, and inefficient data management. To address these issues, we propose a decentralised platform that automates the creation of organised tours by combining the services of registered stakeholders. Our approach leverages blockchain technology to ensure transparency, security, and data integrity throughout the travel planning and booking process. Additionally, we implement a customised proof-of-reputation mechanism to encourage responsible behaviour among stakeholders.
  Keywords: organised tour; blockchain; proof-of-reputation; node weight; automated planning; tourism efficiency.
  
  
• A context-enriched dataset for recommender systems  
  by Rim Dridi 
  Abstract: Recommender systems play a key role in modern applications. Recognising the importance of user context, researchers have developed context-aware recommender systems (CARS) to generate more personalised and relevant recommendations. Even though there are several approaches working for this kind of recommendation, suitable and publicly available datasets including users contextual ratings are limited, and generally, even these are not large enough to assess CARS properly. To mitigate the contextual datasets availability problem, we propose an enrichment methodology to generate large datasets to be used for context-aware recommender systems evaluation. Our work aims to enrich existing large recommendation datasets by including contextual information to describe users expressed preferences linked to their corresponding contexts. Our assessment with the generated large contextual datasets has revealed promising findings when compared to publicly available contextual datasets.
  Keywords: recommender system; context; dataset; enrichment.
  
  
• Design of an English translation computer intelligent scoring system based on block chain  
  by Lingzhi Xu, Xinxin Zhang 
  Abstract: This paper aims to design an intelligent English translation scoring system based on blockchain technology to improve the efficiency and accuracy of translation scoring. In the intelligent scoring system, blockchain provides a secure, transparent and tamper-proof way to record data. By recording each translation result as a transaction record in the blockchain, the system can ensure the integrity and reliability of the data in the scoring process. The fairness and credibility of the scoring results are guaranteed. At the beginning of this paper, the theoretical knowledge and process of block chain are introduced closely following the theme, and then the block chain model is studied, and the Bayesian formula, conditional probability, N-ary model and HMM model are introduced, and finally proposed BLEU evaluation method. Based on these research methods, this paper designs and implements an intelligent English translation computer scoring system.
  Keywords: English translation; block chain; intelligent scoring system; BLEU evaluation method; system design.
  
  
• Triple attention-enhanced transformer-based federated meta-learning for epileptic seizure detection  
  by Ashwini Patil, Megharani Patil 
  Abstract: In neurological healthcare, accurately identifying seizure occurrences from the electroencephalogram (EEG) signals is essential, implying the epileptic seizure detection task. data privacy, epileptic knowledge scarcity, non-independent and identically distributed (non-IID) characteristics, and inter-patient variability pose research constraints to the traditional centralised learning systems. To develop a reliable and private-preserving model for patient-specific knowledge-aware epileptic seizure detection, this paper suggests a unique model that combines meta-learning with federated learning (FL). The proposed approach applies the ternary feature extraction and hybrid augmentation methods to enhance the comprehensive learning of EEG features over data scarcity. Subsequently, the design of the transformer-based model in federated meta-learning architecture significantly captures the intricate relationships with long-range dependencies in the sequential EEG signals of each federated client while performing task-specific learning within each local EEG data. Thus, the stacked transformer encoder with triple attention in the local model inherently learns the discriminative ictal and non-ictal EEG patterns with the updates of patient-specific learning through the collaborative training across the patients by meta-learning and federated clients by FL, improving the epileptic seizure detection performance.
  Keywords: epileptic seizure detection; ternary feature extraction; hybrid augmentation; stacked transformer encoder with triple attention; federated learning; FL; meta-learning; transformer; and multi-head self-attention.
  
  
• Enhanced imputation genetic algorithm: a novel approach for data intelligent imputation  
  by V. Amala Deepa, T. Lucia Agnes Beena 
  Abstract: The imputation of missing data in multivariate datasets has been used to enhance the accuracy and reliability of statistical analyses and the machine learning model, especially when the integrity of data can directly impact their decisions; healthcare and finance are basic examples. Methods become biased or inaccurate in these traditional imputation methods as they are not complex enough for multivariate data. It introduces an entirely novel data imputation method called the enhanced imputation genetic algorithm. Such enables dynamic control over genetic operators with the means that crossover and mutation rates may contribute toward achieving some balancing of exploration and exploitation and further enhancing this by embedding higher-level statistical distances in an improved fitness version, thereby providing EIGA the necessary tool for upholding statistical property for the datasets involved. Due of its genetic diversity, EIGA avoids time convergence, unlike many classic genetic algorithms. Iris, adults, and cardio benchmark datasets show that EIGA reduces RMSE and MAD best. RMSE improved from 0.1668 to 0.1654 and MAD from 0.0479 to 0.0455 on iris with 60% missing data. EIGA, however computationally expensive, is another good alternative for complicated datasets that need more precise imputation.
  Keywords: data intelligent imputation; dynamic crossover; dynamic mutation; genetic algorithm; fitness function; missing data; multivariate data; imputed data; root mean square error; RMSE; mean absolute deviation; MAD; enhanced imputation genetic algorithm; EIGA.
  DOI: 10.1504/IJIIDS.2025.10070762
   
  

Special Issue on: Knowledge Extraction and Mining to Enhance Intelligent Information Systems

• MS-ConvNeXt: a deep-learning method for tomato leaf diseases identification  
  by Yunchao Li 
  Abstract: Existing deep learning methods for tomato leaf disease identification are challenged by the multi-scale disease regions and complex backgrounds in tomato leaf images. A network for tomato leaf disease is proposed. In the proposed network, a cross-channel-and-spatial attention mechanism is first introduced in the ConvNeXt block (called A-ConvNeXt block) to avoid interference of invalid features from the complex backgrounds. Then, a multiscale feature mechanism is integrated into the backbone constructed by the A-ConvNeXt block to extract features across multiscale diseases. The fine multiscale and silence features are extracted to address the limitations on tomato leaf diseases. Experimental results on laboratory and natural datasets show that the identification accuracy reached 95.67%, which outperformed many other existing networks in comparison experiments. The proposed network may effectively improve tomato leaf disease identification and provide decision-making information for practical applications in modern agriculture.
  Keywords: tomato leaf disease identification; attention mechanism; multiscale feature mechanism; deep learning.
  
  
• A novel multi-sensor fusion approach for enhanced navigation in autonomous driving  
  by Qinghai Liao, Feiyang Cheng, Ji Yu, Zhengguang Ao, Zhiquan Deng, Liang Huang, Huiyun Li 
  Abstract: The limitations of single-sensor SLAM technologies in addressing the intricate requirements of modern intelligent vehicles have prompted a shift towards multi-sensor fusion SLAM as a prominent area of research. In response, this paper proposes a tightly-coupled SLAM system integrating LiDAR, cameras, and IMUs to boost the location accuracy and mapping capabilities. The system processes multi-sensor data upfront to enable effective backend optimisation. Specifically, it integrates LiDAR odometry directly within the vision-inertial framework as inter-frame constraints to streamline computational complexity. Moreover, to counter the progressive error accumulation typical of odometry-based methods, loop closure detection is incorporated, enhancing the quality of localisation and mapping. The effectiveness is substantiated through experiments on public datasets, confirming its proficiency in accurate positioning and navigation. The experimental results demonstrate that the proposed multi-sensor fusion SLAM system maintains high accuracy and reliability across different speeds and environmental conditions, with improvements in trajectory estimation due to loop closure.
  Keywords: autonomous driving; SLAM; multi-sensor fusion; pose estimation; LiDAR odometry.
  
  
• Artificial intelligence-based visual communication approach for intelligent graphic design  
  by Beiyi Liu 
  Abstract: By leveraging AI technology, the optimisation of image colour features can be significantly enhanced to further improve the visual impact of graphic design images. Through the incorporation of advanced algorithms, we introduce a cutting-edge graphic design method rooted in visual communication technology. Utilising AI-powered algorithms, we meticulously extract the pixel intensity and luminance components of the graphic design image through this visual communication method. These extracted features allow for precise adjustments to the images global brightness using multi-scale retinex techniques, thereby enhancing local contrast. Additionally, the colour of the enhanced image is restored and corrected to achieve an optimised visual effect, ensuring that the final output is both aesthetically pleasing and technically refined. Simulation results demonstrate that the local area colour information and contrast of the graphic design image are significantly improved, leading to a more engaging and visually appealing outcome. Furthermore, the AI-powered method exhibits excellent noise suppression capabilities, enhancing the users willingness to engage with and browse the graphic design image. This integration of AI technology promises to revolutionise the field of graphic design, delivering more impactful and engaging visual experiences.
  Keywords: artificial intelligence; visual communication; intelligent graphic design; multi-scale retinex.
  
  

Special Issue on: Multi-modal Information Learning and Analytics on Data Integration

• Design and optimisation of electrical information collection and transmission system based on multimodal information analysis  
  by Jinyin Peng, Xiangjin Zhu 
  Abstract: In order to improve the comprehensiveness of power information collection and the flexibility of transmission systems, this article combines multimodal information analysis to conduct in-depth research on system design and optimisation from the perspective of software and hardware structure, and tests it from four aspects: data collection quality, data transmission efficiency, accuracy, and system security. The results show that in terms of data transmission accuracy, the average power data transmission accuracy test result of the system in this article reaches about 92.93%; the average test result of AC simulation transmission accuracy reaches about 93.11%; the average accuracy test result of working condition data transmission reaches about 91.68%. From the experimental results, it can be seen that under traditional finite network technology, the transmission accuracy test results of the electrical energy data, AC analogue quantity, and operating condition data of the five test nodes are about 83.91%.
  Keywords: electrical information; multimodal information analysis; data collection and transmission; system design and optimisation; power monitoring.
  
  
• Optimising path planning and obstacle avoidance algorithm for electrical robots using multimodal information learning techniques  
  by Yang Qiu, Bo Zhou, Lingxiao Chen 
  Abstract: In response to the problems of poor adaptability to complex environments, low success rate of obstacle avoidance, and low accuracy of path planning in traditional path planning and obstacle avoidance algorithms, this paper uses multimodal information learning technology to optimise the path planning and obstacle avoidance algorithms of electric robots. Compared with traditional obstacle avoidance algorithms, optimising obstacle avoidance algorithms using deep learning techniques in multimodal information learning and constructing obstacle avoidance algorithms based on vision and dynamic programming can effectively improve the success rate of obstacle avoidance for electric robots. The average pathfinding time of the six groups studied in this article is 58.59 seconds, which is 4.94 seconds and 3.21 seconds lower than the average values of the ant algorithm and A * algorithm, respectively; in a dynamic obstacle environment, the obstacle avoidance success rate of the algorithm studied in this paper is 96.67%.
  Keywords: obstacle avoidance algorithm; path planning; multimodal information learning technology; electrified robot; Q-learning algorithm; ant colony optimisation; ACO.
  
  
• Application of differential privacy technology in multi-modal data sharing  
  by Zhihai Lu, Bin Wang, Nuanqing Ouyang 
  Abstract: The advent of data-driven technologies and artificial intelligence (AI) has led to an increasing demand for the sharing and analysing sensitive information. However, the paramount concern of preserving individual privacy poses a significant challenge. Hence, an algorithm named differential privacy in data sharing for AI (PrivShareAI) has been utilised. The objective is to enable secure and privacy-preserving data sharing in AI by implementing differential privacy measures and maintaining a balance between utility and privacy. The data-sharing paradigm uses sensitivity limits, noise-enhanced queries, and a universal, secure architecture enabled by a trusted server to encourage shared learning while maintaining maximum privacy. The proposed models efficiency is evaluated with baseline comparison studies with the following metrics: privacy guarantee, accuracy on varying parameters, privacy-utility trade-off, and privacy loss and accuracy measure.
  Keywords: artificial intelligence; differential privacy; data sharing; accuracy; Gaussian noise; gradients; privacy guarantee.
  
  
• Multimodal fake data detection and filtering using GANs and contrast learning  
  by Yuanjie Zou 
  Abstract: In recent years, artificial intelligence (AI) has become an integral part of online education, improving ITS, online courses, and learning management systems (LMS). Online education is predicting students knowledge acquisition based on clickstream data. The lack of focus on student interaction with the content and quizzes offered in lecture videos is a major hurdle to online education. Therefore, this paper proposes a multimodal fake data detection and filtering-based generative adversarial network (MFDDF-GAN) to predict student performance in online learning. MFDDF-GAN aims to ensure that all material used in online education is authentic, of high quality, has protected users, is effective in communication. This MFDDF-GAN approach takes advantage of the information already included in the click sequences rather than relying on characteristics. The experimental results show that the MFDDF-GAN technique produces actionable insights into learning analytics related to video-watching learning performance and knowledge acquisition.
  Keywords: online learning; generative adversarial networks; GANs; support vector machine; SVM; student learning performance.
  
  
• Multi-modal and multi-objective joint optimal planning of medium voltage distribution system based on genetic algorithm  
  by Yigang Tao, Jing Tan, Min Li, Juncheng Zhang, Chunli Zhou 
  Abstract: In order to understand the multi-objective joint optimisation planning problem of medium voltage distribution systems, research on multi-objective joint optimisation planning of medium voltage distribution systems based on genetic algorithm is proposed. This article first focuses on the problem of uneven equipment utilisation efficiency in medium and low-voltage distribution networks and studies the coordination and coordination between medium-voltage lines and connected distribution transformers. Secondly, based on the electricity consumption characteristics of the user industry, a method for estimating the maximum load of distribution transformers based on industry demand coefficients is studied. Finally, a certain actual power grid is selected as an example for verification. The experimental results show that the coordination planning method proposed in this article can effectively guide the reasonable configuration of medium voltage lines and connected transformers, and provide a scientific method for designing user access planning schemes.
  Keywords: medium voltage distribution; multi-objective collaboration; genetic algorithm; GA.
  
  
• Communication algorithm of parallel database HPDB system based on computer intelligent network and data integration  
  by Zhenhua Dai, Tingting Wu, Jun Li 
  Abstract: Traditional database systems are replaced with high-performance parallel databases with intricate and time-consuming querying and data processing demands. As the need exists for processing queries in multiple distinct relations, the database systems are ideally suited for parallel execution. This paper proposes an AINF-HPDB system designed for a parallel high-performance database (HPDB) system using adaptive intent-based network framework (AINF) computer intelligence architecture. The suggested approach utilises flexible and innovative capabilities to optimise communication interactions within the parallel HPDB system. The proposed idea aims to maximise throughput in the operation of the parallel database system, minimise latency, and utilise the intelligence and adaptability of network components to improve data transfer efficiency. To maximise performance and efficiency during large dataset handling across various sectors, the proposed idea finds application in the financial services industry for trading at high frequencies, telecommunications for managing networks, scientific studies for simulations, and internet of things for data-intensive applications.
  Keywords: high-performance database system; computer intelligent network; adaptive intent-based networking framework; adaptive routing; load balancing.
  
  
• Evaluation of digital twin resource allocation and multimodal information learning in internet of vehicles  
  by Ke Wang, Zunhai Gao 
  Abstract: The construction of modern intelligent transportation infrastructure has brought many inconveniences to transportation due to its large number of vehicles, high traffic density. This article applies digital twins to intelligent transportation devices in the internet of vehicles, and studies and analyses the composition of intelligent transportation IoT systems and the application of digital twins in intelligent transportation. First, the intelligent transportation equipment of different vehicles was tested, and then the digital twin intelligent transportation equipment was used to configure resources. The results showed that the average satisfaction score of the intelligent transportation equipment improved by digital twin technology was 7.73 points, while the average satisfaction score of traditional intelligent transportation equipment was 8.26 points, an increase of about 6.9%. Research has shown that intelligent transportation devices based on digital twin vehicle networking can allocate resources more reasonably, ensure the safety of road vehicles, and avoid traffic accidents.
  Keywords: car networking; digital twins; intelligent transportation; internet of things; IoT; internet of vehicles; IoV.
  
  
• Spatiotemporal fusion strategies in multi-modal sensor target detection and tracking  
  by Le Zhang 
  Abstract: Although significant progress has been made in the research of object detection and tracking algorithms in recent years, there are still some unresolved issues that affect the practicality of the algorithms. This article mainly studies the optimal and suboptimal filtering algorithms used to process various linear and nonlinear models in target tracking, and then uses different filtering algorithms to filter and estimate the motion states of multiple targets, aiming to improve the accuracy of target tracking, and analyses and compares the advantages and disadvantages of these algorithms and their application scenarios. The experimental results show that the target tracking accuracy of the multi-sensor algorithm studied in this paper has been improved by 39.1%. While maintaining the same accuracy of 5.976 times, the time limit of the image information fusion algorithm studied in this paper is 142.187 ms, and the efficiency of the optimised algorithm is 142.187 ms.
  Keywords: multi-sensor; intelligent monitoring; target detection; target tracking; image information fusion algorithm.
  
  
• Optimisation of logistics management mode of blockchain logistics supply chain based on heuristic algorithm  
  by Chunxiang Guo, Pengfei Jiao 
  Abstract: Intelligent equipment such as automatic sorting systems and self-driving vehicles play a key role in modern logistics systems and can significantly improve the efficiency of logistics operations; From the perspective of W, the logistics enterprise in S city, Based on the results of four experiments, it can be seen that if the enterprise wants to optimise its logistics management mode, Then the ant colony optimisation (ACO) can be prioritised in the heuristic algorithm type, And take the satisfaction rate to judge the effect before and after the use of the algorithm as the standard, A 48% increase in the satisfaction rate before and after use. At the same time, with the continuous research of heuristic algorithms, the research of supply chain logistics management mode of blockchain logistics enterprises is also facing new opportunities and challenges.
  Keywords: logistics management mode; logistics supply chain; blockchain technology; heuristic algorithm.
  
  
• Optimisation method of distribution network planning based on wireless communication and multimodal information learning  
  by Jun Jiang, Jiwu Liu, Qingzhu Li, Yangfu Luo, Zixin Li 
  Abstract: In this article, a new dispatching method was proposed based on the power demand and the existing problems in the current distribution network planning. Through physical communication, data interaction and communication between multiple nodes were achieved, which provided users with a more convenient and comfortable electricity experience. The intelligent optimisation algorithm can carry out planning calculation and decision-making by itself according to the users use, the planning can run more accurately and reasonably, and has strong performance. According to the mathematical model of intelligent optimisation algorithm, the distribution network planning problem has been solved efficiently. The application of wireless communication and intelligent optimisation algorithm in distribution network planning can not only decrease the cost of existing schemes and operation and management costs but also improve the network computing efficiency, which decreases the workload of operation and maintenance personnel and enables lines and distribution equipment to truly play their due role.
  Keywords: distribution grid; wireless communication; intelligent optimisation algorithm; physical communication.
  
  
• Multimodal social media disinformation detection by fusing images and BERT  
  by Lizhu Ye, Md Gapar Md Johar, Mohammed Hazim Alkawaz 
  Abstract: To address the diversity and fragmentation issues in false information detection (FID) on social media, this article proposed the MM-GCN-BERT model based on the advantages of GCN and BERT models, integrating multimodal fusion and cascading detection frameworks. By designing and optimizing the MM-GCN-BERT model, and combining specific experimental data to verify the performance of the MM-GCN-BERT model, experimental results were obtained. The results showed that the average F1 value of the MM-GCN-BERT model was 0.816, the average precision was 0.836, and the average recall was 0.797. The indicators of the model are all at a high level. It can be seen that the MM-GCN-BERT model has shown excellent performance in solving the problems of diversity and fragmentation in detecting false information on social media.
  Keywords: MM-GCN-BERT model; multimodal fusion; cascade detection framework; false information detection; FID; social media.
  
  
• Formal modelling of software security requirements based on improved clustering algorithm and multi-modal information fusion  
  by Tangsen Huang, Zhenhua Dai 
  Abstract: Manual analysis and verification are common means and methods of software security requirements that work at present, but they have the disadvantages of being long-consuming and low efficiency. In this paper, the k-means algorithm was used to distinguish feature points by k-value, calculate the probability of each point being selected as the cluster centre, and then obtain a new cluster number. Using the K-nearest neighbour (KNN) algorithm and spectral clustering principle, a clustering analysis method based on multi-attribute decision-making was constructed, which can better realise target recognition in a complex environment. The paper designed a contrast experiment based on the improved clustering algorithm. The results showed that the enhanced clustering algorithm can better model the software security requirements, this article include enhancing target recognition accuracy in complex environments using the k-means algorithm with variable k-values for clustering, integrating the KNN algorithm with spectral clustering principles for effective identification in complex environments.
  Keywords: clustering algorithm; software security; formal methods; model checking; multimodal information fusion; formal modelling.
  
  

Special Issue on: Machine Learning Algorithms for Anomaly Detection in Vanets

• Few-shot learning-based zero-day anomaly detection in vehicular networks using conditional GANs  
  by Haewon Byeon, Mohammed E. Seno, Aadam Quraishi, Azzah AlGhamdi, Mukesh Soni, Ihtiram Raza Khan, Mohammad Shabaz 
  Abstract: Detecting zero-day anomalies in vehicular networks poses significant challenges due to the lack of attack data. Anomaly-based detection methods are commonly used; however, complex and dynamic environments in vehicular ad hoc networks (VANETs) lead to diverse behavioural patterns, increasing the likelihood of high false alarm rates. This study proposes a few-shot learning-based zero-day anomaly detection method for vehicular networks using conditional generative adversarial networks (GANs). The proposed approach introduces a conditional GAN model with multiple generators and discriminators to enhance anomaly detection capabilities. To address data imbalance caused by the limited availability of attack samples, a collaborative focal loss function is incorporated into the discriminator to focus on hard-to-classify anomalies. Extensive experiments conducted on the F2MD vehicular network simulation platform demonstrate that the proposed method outperforms existing approaches in terms of detection accuracy and latency for zero-day anomalies. This provides an effective solution for enhancing anomaly detection in vehicular networks.
  Keywords: VANETS; anomaly detection; zero-day anomalies; few-shot learning; conditional generative adversarial networks; GANs.