International Journal of Bio-Inspired Computation (27 papers in press)

Regular Issues

• Multi-Objective Jaya War Strategy Optimisation Enabled Cloud Storage in Blockchain Network for Internet of Medical Things Applications  
  by Kavita Shelke, Subhash Shinde 
  Abstract: The internet of medical things (IoMT) includes accessibility and is adequate for medical areas. Diverse techniques are developed based on cloud storage for IoMT applications, but these methods failed to obtain sufficient security in less time. In this research, a Jaya war strategy optimisation (Jaya WSO)-based cloud storage in a blockchain network is introduced for IoMT. Firstly, transactions are generated in IoMT and fed to the base station (BS). Then, it is passed to peers in the blockchain and the ledger is stored in respective peers. For each peer, blocks are selected optimally by Jaya WSO, which is an integration of the Jaya algorithm with war strategy optimisation (WSO) and the multi-objectives. The Jaya WSO attained minimal query probability, storage cost and local space occupancy of 0.428, 20.766 and 52.7 respectively and maximal values of trust level and sensitivity level of 0.849 and 0.916 respectively for block size = 2.
  Keywords: internet of medical things; IoMT; blockchain; Jaya algorithm; war strategy optimisation; WSO; cloud storage.
  DOI: 10.1504/IJBIC.2024.10066976
   
  
• Design of Logic Circuit for All Optical Sampling Gate Based on FIBER-FWM Nonlinear Fiber  
  by Yunhu Wu, Yarang Yang, Wei Zheng, Saidiwaerdi Maimaiti, Hui Peng 
  Abstract: To solve the problems of limited sampling bandwidth and low sampling rate in existing optical sampling techniques, an all optical sampling gate logic circuit design based on FIBRE-FHM nonlinear fibre is adopted to measure high-speed optical signals, improving the bandwidth of traditional sampling methods. This design addresses significant limitations posed by electronic bottlenecks in high-speed optical signal measurement. Utilising the four-wave mixing (FWM) model of a semiconductor optical amplifier (SOA), a sampling gate is realised via a logic circuit leveraging nonlinear effects. These results confirm that after nonlinear processing, the pulse width increases by 80% to 0.1
  Keywords: light sampling; nonlinear fibre; logic circuit; semiconductor optical amplifier; SOA; four-wave mixing; FWM.
  DOI: 10.1504/IJBIC.2024.10067779
   
  
• Prediction of International Shipping Container Throughput Based on Particle Swarm Optimisation and Grey Wolf Optimisation  
  by Xia Zhao 
  Abstract: In order to improve the prediction accuracy for port container throughput in international shipping, PCA is first used to reduce the dimension of the input SVR indicators, thereby reducing the dimension of the SVR input; Secondly, GWO is used to improve PSO, and a port container throughput prediction model based on GWO-PSO-SVR is constructed, thereby improving the prediction accuracy of SVR for port container throughput. Results show that the improved PSO performs well in the test function; Based on data from Tianjin Port, the SVR prediction results indicate that its MAPE index is the lowest, at 12.96, which is closest to the true value.
  Keywords: Particle Swarm Optimization; Grey Wolf Optimization Algorithm; SVR prediction model; MAPE indicators; PCA.
  DOI: 10.1504/IJBIC.2024.10068325
   
  
• Research on Philosophy Sentence Segmentation Algorithm Based on BERT Pre-training and Deep Learning Network  
  by Dan Cheng 
  Abstract: To improve the accuracy of sentence breaking in ancient philosophy texts, based on BERT pre-training and deep learning network, an ancient philosophy sentence segmentation algorithm with high accuracy is proposed. Based on Lattice model, BERT model is used to encode ancient philosophical texts into word vectors, and Flat-Lattice Transformer (FLT) position coding method is adopted to determine the interaction relationship between vectors. Then, sentence segmentation situation of ancient philosophical texts is predicted. Finally, sentence segmentation accuracy of ancient philosophical texts is improved. The simulation results show that compared with Lattice-LAN, BERT-Bi-LSTM-CRF and Bi-LSTM-CRF models, the proposed algorithm has obvious advantages in the accuracy of ancient philosophy sentence segmentation. Moreover, accuracy, recall, and F-value of the proposed algorithm are 82.82%, 70.71%, and 76.29%, respectively, which improves the sentence segmentation accuracy of ancient philosophical texts and has certain reference value.
  Keywords: philosophy sentence segmentation; BERT pre-training; deep learning; LSTM model; FLT position coding.
  DOI: 10.1504/IJBIC.2024.10068326
   
  
• Research on Bi-Objective Charge Batch Planning Optimisation Method based on Improved -Constraint Framework  
  by Congxin Li, Liangliang Sun 
  Abstract: Charge batch planning (CHBP) is the basis of steelmaking-continuous casting section batch planning (SCCSBP). With the rapid development of the market-oriented demand of steel enterprises in the direction of multi-species, small batch, and just-in-time delivery, the integrated production process of SCCSBP dramatically increases the functional requirements of flexibility, material yield, and time-dynamic balancing of the CHBP. Therefore, the preparation of a high-quality CHBP is of great significance to improve the efficiency of steelmaking production and reduce material and energy consumption. A bi-objective mathematical model is established, and a cooperative optimisation framework combining an improved -constraint method (IECM) with branch-and-cut (B&C) is developed. Employing a bisection method-based heuristic, can rapidly detect the valid number of sub-problems, thus avoiding the computational burden of redundant sub-problems in traditional -constraint method (ECM). Meanwhile, this method can obtain multiple Pareto non-dominated solutions, providing more schemes for synergistic optimisation at each stage. The B&C can acquire high-quality solutions for sub-problems. Finally, simulation experiments with actual production data validate that the proposed method reduces the objective function values by 7.19%, 7.22% and 0.16% compared to the linear weighting method, traditional ECM and multi-objective optimisation method, respectively; and reduces the CPU time by 46%, 80.7% and 73.64%, respectively.
  Keywords: charge batch planning; steelmaking-continuous casting; improved ε-constraint; Pareto.
  DOI: 10.1504/IJBIC.2024.10068460
   
  
• A Fractional Order Proportional Controller for Control Liquid Level in Nonlinear Spherical Tank System  
  by S.P. Selvaraj, R. Thiyagarajan, Mohanraj Kalidass 
  Abstract: In order to keep the process level at the specified operational parameters and attain peak performance, the Fractional Order Proportional-Resonant (FOPR) Controller was proposed for a spherical tank. All of the parameters in the operating circumstances are tuned by the proposed controller. The FOPR approach is less reactive and is used to manage liquid levels. It is implemented in real time, has cost effective, and has good time domain features. The FOPR controller's servo responses for various operating regions are recorded. The findings are contrasted to methods: glow swarm optimisation based proportional integral (GSO-PI) controllers, Bacterial Foraging Optimisation, and Particle Swarm Optimization. Compared to existing approaches, the proposed FOPR controller can give little overshoot, minimal settling time, faster rise time, and minimal integral standard error (ISE) and integral absolute error (IAE) values. It also produces a highly stable output over the tank's full span at various operating positions.
  Keywords: Fractional Order Proportional-Resonant (FOPR); Bacterial Foraging Optimization (BFO)Glow Swarm Optimization based controller; Particle Swarm Optimization (PSO); Integral Standard Error (ISE); IAE.
  DOI: 10.1504/IJBIC.2024.10068480
   
  
• Efficient VM Selection from Over-utilised PMs: a Grasshopper-Based Approach for Cloud Resource Optimisation  
  by Jaspreet Singh, Navpreet Kaur Walia 
  Abstract: Efficient resource allocation is critical for optimising performance and controlling operational costs in cloud computing environments. In this proposed work, a comprehensive two-segment study is presented, in which the first segment relies on grasshopper based optimisation while the second segment relies on conditional-MBFD. The grasshopper algorithm effectively addresses the intricate challenge of selecting virtual machines (VMs) from overutilised physical machines (PMs) in dynamic cloud environments, thus reshaping resource allocation paradigms. The contributions outlined in this proposed work are rigorously examined through comprehensive comparative evaluations. These evaluations compare grasshopper based approach against well-established optimisation algorithms such as artificial bee colony (ABC), particle swarm optimisation (PSO), and firefly. Additionally, the proposed work strategies are validated against state-of-the-art algorithms. These meticulous comparisons highlight the resounding superiority of proposed strategies in minimising power consumption, reducing SLA violations, and optimising resource utilisation in cloud computing environments. Meanwhile, the conditional-MBFD algorithm astutely fine tunes resource allocation.
  Keywords: allocation and migration; cloud computing; grasshopper optimisation algorithm; GOA; swarm intelligence; SI.
  DOI: 10.1504/IJBIC.2024.10068593
   
  
• Research on Sports Image Restoration Algorithm based on Deep Learning  
  by Xinjiao Zhang, Xuefei Tao 
  Abstract: To improve the sharpness and realism of sports image restoration, an image restoration method based on deep learning is proposed. The improved GAN (Generative Adversarial Network) is adopted for image denoising, and the improved RAiA-Net is used for image rain removal. The simulation results show that the peak signal-to-noise ratio and structural similarity of the improved GAN network reach 32.56 and 0.91, respectively, which are 3.45 and 0.04 higher than those of GAN network. The peak signal-to-noise ratio and structural similarity of RAiA-Net are 36.87 and 0.98 respectively, and the time consumption is shorter (0.43s), which has certain advantages and practicability. Compared with the standard GAN network, CBM3D network and CNN network, the designed network has better image denoising performance and better performance in peak signal-to-noise ratio and structural similarity indexes.
  Keywords: deep learning; image restoration; image denoising; image rain removal; generative adversarial network.
  DOI: 10.1504/IJBIC.2024.10068652
   
  
• DafVBM: Multimodal Deep Learning for Predicting Efficacy of Salvage Chemoradiotherapy  
  by Han Zhang, Xinwei Guo, Liang Gu, Zhenyu Lei, Masaaki Omura, Shangce Gao 
  Abstract: This study leverages multimodal deep learning to predict the efficacy of salvage chemoradiotherapy for aesophageal squamous cell carcinoma. The target patients are those with regional lymph node recurrence after curative resection. Predicting efficacy is challenging due to limited data and the reliance on manual feature selection. Integrating multimodal data and optimising its utilisation can significantly support treatment prediction. However, there is little research on fully integrating multimodal data. To address this, we conduct a retrospective study and design a multimodal architecture to process patient data, including images, text, and tabular features. The model employs attention mechanisms and Fourier transform paths for seamless feature fusion. Our comparative analysis shows significant performance improvements with multimodal data, achieving an average precision, recall, and F1-score of 91.96%, 91.18%, and 90.86%, with best scores of 97.20%, 97.10%, and 97.00%.
  Keywords: Multimodal model; esophageal squamous carcinoma; efficacy prediction.
  DOI: 10.1504/IJBIC.2024.10068835
   
  
• Optimized Dual Temporal Gated Multi-Graph Convolution Network Based Distributed Denial of Service Attack Detection in Cloud Computing  
  by Ramesh Babu Putchanuthala, Gopisetty Naga Rama Devi, Prabha Murugesan, Muniyandy Elangovan, Radhika Rathanasalam, Ramasamy SenthamilSelvan 
  Abstract: Distributed denial of service (DDoS) attacks are growing threat to network security, and existing methods attains higher false positive and false negatives when classifying attack and legitimate data, resulting in reduced accuracy. To overcome this, optimised dual temporal gated multi-graph convolution network based fennec fox optimisation for distributed denial of service attack detection in cloud computing (DTGMGCN-DoS-ADD-CC) is proposed. Initially, data adaptive Gaussian average filtering (DAGAF) pre-processes the CICIDS2017 dataset to correct mismatched values. Then swarm optimisation algorithm (DSOA) selects the transformed features, its used by multiple-graph convolution network with dual temporal gates (DTGMGCN) for precise detection of normal and attacked packet of information (API). The Fennec fox optimisation (FFO) fine-tunes DTGMGCNs weight parameters, further boosting performance. Experimental results show that DTGMGCN-DoS-ADD-CC achieves 99.37% accuracy, 98.9% sensitivity, and 98.95% specificity, outperforming existing methods. The improvement highlights robustness and efficacy of the DTGMGCN-DoS-ADD-CC approach for DDoS attack detection in cloud computing.
  Keywords: Dual Temporal Gated Multi-Graph Convolution Network; Fennec Fox Optimization; Cloud Computing; Distributed Denial of Service Attack Detection; Machine Learning.
  DOI: 10.1504/IJBIC.2024.10069266
   
  
• Optimal Path Selection for Mobile Sink Using Henry Gas Particle Swarm Optimisation and Energy Prediction Based on Deep Residual Network  
  by Aparna Ashok Kamble, Patil B.M 
  Abstract: The advantage of Wireless Sensor Network (WSN) anywhere at any time makes it one of the popular technologies. The most prominent issues faced by the WSN are energy availability and reliability. The energy prediction among the nodes acts as a significant factor to achieve reliability. Hence, this research proposes a mechanism for optimal path selection of MS nodes using a proposed approach named the Henry Gas Particle Swarm Optimization (HGPSO) algorithm. Here, the hybrid Harris Hawk Salp Swarm optimization (HHSSO) model along with the MS policy is employed for performing the CH selection effectively and is referred as EE-hHHSS. The Deep Residual Network (DRN) is exploited to predict energy. The proposed HGPSO-based DRN has achieved a maximum Packet Delivery Ratio (PDR) of 42.121%, maximum residual energy of 0.083J, minimum delay of 0.0000027089sec, minimum path distance of 13.357, and maximum number of alive nodes is 48 while analysing 50 nodes.
  Keywords: Wireless Sensor Network (WSN); Henry gas solubility optimization (HGSO); Particle Swarm Optimization (PSO); mobility model; Cluster Head (CH) selection.
  DOI: 10.1504/IJBIC.2024.10069450
   
  
• Contrastive Hypergraph Attention Reinforcement Learning for Asset Portfolio Management in Digital Auditing  
  by Xuan Liu, Xu Cao, Xinying Fang, Nan Gao 
  Abstract: Asset portfolio management (APM) is a critical task within digital auditing, aimed at continuously reallocating funds across a set of assets with the aim of maximising investment returns or suppressing risks. Recent APM methods have learned a policy function to generate appropriate portfolios in a reinforcement learning framework and have achieved encouraging progress. However, these methods ignore the fact that assets in portfolios may be broadly interrelated and affected by each other, and the asset relationship information is highly valuable in improving APM. In this paper, we introduce group-wise relationship information as additional environmental cues to improve portfolio policy learning for APM. We propose a dual-channel hypergraph attention network to jointly capture the heterogeneous fund-holding and industry-belonging relationships via attention-based information aggregation among assets. In addition, we introduce contrastive learning to provide extra supervision signals for higher modelling capacity. Experimental results demonstrate that this method yields significantly greater benefits compared to state-of-the-art methods for APM.
  Keywords: Asset portfolio management; Hypergraph learning; Contrastive learning; Attention;Reinforcement learning.
  DOI: 10.1504/IJBIC.2024.10069679
   
  
• Financial Fraud Detection Based on Distributed L  
  by Hongwei Chen, Jianpeng Wang, Lun Chen, Zexi Chen, Rong Gao, Xia Li 
  Abstract: With the growth of online payments, financial fraud has led to significant economic losses. Accurate fraud detection is therefore crucial for protecting consumer rights and ensuring the security of payment platforms. Current detection methods mainly rely on machine learning algorithms, but their performance is often limited by hyperparameter tuning constraints. To address this, we propose a Spark-based distributed L
  Keywords: fraud detection; sailfish optimiser; Lévy flight; Spark.
  DOI: 10.1504/IJBIC.2025.10069838
   
  
• MOWOA-D based Feature Selection Study for Pneumonia Detection  
  by Leyi Xiao, Yixuan Su, Xia Xie, Chaodong Fan 
  Abstract: AI's application in medical image analysis presents challenges in balancing solution diversity and convergence in high-dimensional datasets for accurate feature selection. To this end, we propose an improved multi-objective evolutionary algorithm (MOWOA-D) based on decomposition and Whale Optimization Algorithm (WOA) learning strategy. This algorithm integrates the WOA learning strategy into the original MOEA/D to optimize the search mechanism, ensuring accuracy and uniformity. Then we design a dynamic neighborhood reference strategy to select reference points based on the population's real-time state, guiding the generation of offspring and enhancing solution quality. We also use an adaptive binary mutation operator that introduce the Hamming distance and adjust mutation probability during iteration to balance exploration and exploitation. Experimental results indicate that MOWOA-D outperforms five multi-objective evolutionary algorithms in efficiency and uniformity. Feature selection experiments on the UCI database show improved classification accuracy and reduced data redundancy. Tests on pneumonia data demonstrate the method's practicability.
  Keywords: Multi-objective optimization; Feature selection; MOEA/D; Pneumonia; Whale optimization; Heuristic method; Dynamic reference strategy; Binary mutation operator; Hamming distance; Machine learning.
  DOI: 10.1504/IJBIC.2025.10070157
   
  
• IoT-Based Plant Disease Detection Using Enhanced Elman Spike Neural Network with Capuchin Search Optimisation Algorithm  
  by D. Karunkuzhali, B. Meenakshi 
  Abstract: In recent years, the Internet of Things (IoT) has gained attention for its transformative role in agriculture. A main challenge in agriculture is early identification of plant disease which is needed to prevent crop loss and ensure food preservative. Typical plant disease detection techniques are often time-consuming and labor-intensive, making it important to replace them with automated systems. Therefore, IoT-Based Plant Disease Detection Using Enhanced Elman Spike Neural Network together with Capuchin Search Optimization Algorithm(IoT-PDD-OEESNN) is proposed in this paper for detecting potato plant. The input data is preprocessed using Altered phase preserving dynamic range compression (APPDRC) filtering model for extracting the leaf region of the image and also eliminates the noise and blur image. The proposed IoT-PDD-OEESNN approach is implemented in Python using certain metrics. The IoT-PDD-OEESNN method attains better accuracy of 30.12%, 26.75% and lower computation time of 27.18%, 26.29%, and 29.56% when analyzed with the existing methods.
  Keywords: Capuchin search optimization algorithm; Enhanced Elman Spike Neural Network; Gray-Level Co-Occurrence Matrix; Internet of Things; Plant village dataset and Variation Density Peaks Clustering.
  DOI: 10.1504/IJBIC.2025.10070546
   
  
• Efficient Data Retrieval Model based on Semantic Similarity Analysis using Chiroptera Buzzard Optimisation Tuned Deep CNN  
  by Ankush Raosaheb Deshmukh, Premchand B. Ambhore 
  Abstract: To extract meaningful insights, integrating the data classification and semantic text summarization is essential, aiding in the identification of contextually significant content. Most of the existing techniques encounter multiple challenges from the perspective of machine understanding, especially for languages with limited resources, and fail to learn the sequence of correlations effectively. Nevertheless, there is still much space for enhancing the speed of data retrieved because current approaches fail to take the spatial and semantic aspects into account. To tackle this issue, this research presents an efficient data retrieval model utilising Chiroptera Buzzard optimization adapted deep Convolutional Neural Network (CBO adapted deep CNN) for semantic similarity analysis. Specifically, the Chiroptera buzzard optimisation is utilised for feature selection and fine-tuning the hyperparameters of DCNN that improves the classification accuracy. Hence, the proposed model reduces the computational complexity and provides remarkable performance in terms of metrics attaining 99.98% accuracy, 99.53% recall, 99.93% precision, 99.84%Fbeta, 99.52%Cohen kappa, and 99.52% F1-score for 90% of training.
  Keywords: Data retrieval model; Convolutional Neural Network; Chiroptera buzzard optimization; Semantic Similarity Analysis; and Text summarization.
  DOI: 10.1504/IJBIC.2025.10070716
   
  
• SenseNet: Satellite Image Enhancement using Optimised Deep Denoiser for Cloud Removal  
  by Renuka Sandeep Gound, Sudeep D. Thepade 
  Abstract: The research focuses on devising a Hybrid CFO deep denoiser model to eliminate the blurring edges of cloud-covered boundaries in the RS image The need for reconstructing the high-quality satellite image is elaborated in this research article for which a proposed Hybrid CFO deep denoiser is developed The optimized learning of deep denoiser increases the reconstruction ability, which is the main focus of the research The satellite images are pre-processed and exposed to the reconstruction in such a way that the proposed Hybrid CFO deep denoiser reconstructs the high-quality satellite image without the influence of cloud The experimental results also demonstrate that the CFO-based deep denoiser exhibits higher performance in terms of PSNR, SSIM, and MSE, while compared with the existing denoiser The performance improvement of 2 165dB, 1 436% and 0 816% is obtained by the Hybrid CFO-deep denoiser concerning existing denoisers in terms of PSNR by maintaining the K-fold at 5.
  Keywords: Image enhancement; Satellite Image; Deep learning; Optimization; Cloud Removal.
  DOI: 10.1504/IJBIC.2025.10070740
   
  
• Student Performance Prediction (SPP)Model using HLRO-DMN  
  by L. Srinivasan, D. Kalaivani, C. Nalini, I. Gugan 
  Abstract: This research introduced the proposed hybrid leader remora optimisation algorithm with deep maxout network (HLRO_DMN) for accurately predicting the students performance. Initially, the input data acquired from the dataset is transformed into a suitable format using Yeo-Johnsons transformation. Then, the dice coefficient is employed for selecting optimal features, which combines the feature score obtained from the Fisher score and the Tversky index. In addition, the data augmentation is completed by the bootstrapping method, and the performance prediction is carried out by the DMN, wherein the weight of the DMN is tuned by the HLRO algorithm. Besides, the experimentation of HLRO_DMN attained the best result using certain metrics, like mean square error (MSE), Root mean square error (RMSE), and mean absolute error (MAE), and the accuracy of the corresponding values noted by the devised scheme are 5.4032, 0.175, 0.4444, and 91.314, respectively.
  Keywords: Remora Optimization algorithm; Deep Maxout network; Hybrid leader based optimization; Yeo-Johnson's transformation; Dice coefficient.
  DOI: 10.1504/IJBIC.2025.10071048
   
  
• Nash Game-Based Optimisation Strategy for Power-Heat-Cooling Interactive Shared Operation of Multiple Microgrids  
  by Hongbin Sun, Jianfeng Jia, Jingya Wen, Lei Kou 
  Abstract: The sharing of energy interactions within a multi-microgrid system can enhance the stability and reliability of system operations. This paper proposes an optimisation strategy for electricity-heat-cooling interaction sharing in multi-microgrids based on the Nash game. A cooperative microgrid model integrating electricity-heat-cooling systems is constructed, incorporating a combined heat and power (CHP) unit with carbon capture and an electricity-to-gas device. Subsequently, a multi-microgrid electricity-heat-cooling interaction sharing model is developed. This model is decomposed into two sub-problems: maximising the benefits of the microgrid alliance and redistributing cooperative benefits. The alternating direction method of multipliers (ADMM) is employed to solve these problems, effectively protecting the privacy of the microgrid entities. For the redistribution of cooperative benefits, an asymmetric mapping function is utilised to calculate each microgrids contribution, and the benefits are equitably redistributed based on these contributions. Finally, simulation results confirm the effectiveness of the proposed method, demonstrating that the multi-microgrid electric-heat-cold interaction sharing strategy maximises the alliances benefits and equitably allocates them according to the contribution of each microgrid.
  Keywords: nash game; electricity-to-gas conversion; carbon capture; electricity-heat-cooling interaction; alternating direction multiplier method.
  
  
• Spatial and Temporal Distribution of Ecosystem Service Values in the Northeast Tiger and Leopard National Park and Analysis of Driving Factors based on the Geographical Detector and Remote Sensing Classification  
  by Zhihan Wan, Hongxun Li 
  Abstract: This study provides a basis for research on the value of ecosystem services of Northeast Tiger and Leopard National Park (NTLNP) after the implementation of the natural protection project by analyzing the change of land use, temporal and spatial changes of ecosystem service value, and driving factors from 2000 to 2022. The results showed that the area of broad-leaved forest in NTLNP was the largest and the land use types changed from broad-leaved forest to mixed coniferous and broad-leaved forest and coniferous forest from 2000 to 2022; the ecosystem service value of NTLNP showed a trend of first decreasing and then increasing, with a total increase of 464.99 million yuan. The interaction between elevation and climate factors has a great influence on the value of ecosystem services, and natural factors have a binding effect on the spatial differentiation of ecosystem service value.
  Keywords: Northeast Tiger and Leopard National Park; ecosystem services value; driving factors; geographical detector.
  DOI: 10.1504/IJBIC.2025.10071729
   
  
• A Novel Data-Driven External Operational Risk Level Distinguishing Approach for Catenary System of Heavy-Haul Railway  
  by Zhichun Zhang, Long Yan, Zhikun Wang, Tianqi Su, Tianjun Du, Lintao Wang, Miao Li 
  Abstract: The heavy-haul railway's catenary system is exposed to harsh outdoor conditions, making it vulnerable to weather-related malfunctions that can impact train safety and operations. This study presents a data-driven approach to identify the external operational risk level (EORL) of the catenary system. External risk factors are first identified, and key parameters are selected. Then, a combined method using multi-head attention (MHA), temporal convolutional network (TCN), and gated recurrent unit (GRU) is developed to assess the EORL. This approach effectively captures both short-term and long-term dependencies in time series data. The method is validated with real data from the Jingbian-Shenmu Railway, demonstrating its reliability and accuracy in distinguishing EORL for heavy-haul railways. The method is validated with real data from Jingbian-Shenmu Railway, and the proposed method achieved the best F1 score and accuracy of 99.71% and 99.45% for haze pollution and wildfire risk identification, respectively. It proves its reliability and accuracy in distinguishing heavy railroad EORL.
  Keywords: Catenary system; heavy-haul railway; weather conditions; data-driven; external operational risk level distinguishing.
  DOI: 10.1504/IJBIC.2025.10072013
   
  
• Cost-Effectiveness Oriented Maintenance and Inspection Policy Optimisation Strategy for High-Speed Overhead Contact Lines  
  by Dongkai Zhang, Kai Li, Xiaojie Sun, Jian Wang, Huiyuan Nie, Lei Kou, Meng Wang, Fei Yu 
  Abstract: The safety and stability of overhead contact lines (OCLs) are playing promising role in guaranteeing the economic and efficient operation of high-speed railway trains. In this paper, a cost-effectiveness oriented maintenance and inspection policy optimisation strategy is proposed, from a trade-off between the cost and OCLs performance. One integrates the delay time model and age reduction factor into maintenance cost modelling of OCLs under imperfect maintenance. Under the premise of system reliability, the optimal preventive maintenance policy is optimised by minimising the maintenance cost during life cycle of OCLs and solved by enumeration method. The another incorporates the imperfect inspection into inspection schedule modelling within a single preventive maintenance (PM) cycle, taking into account various inspection methods for different equipment defects. The optimal inspection time and methods are solved using a branch-and-cut global optimisation approach. The actual railway line is used to demonstrate the effectiveness of the proposed PM and inspection policy optimisation model.
  Keywords: Preventive maintenance; delay time; reliability; imperfect inspection; multiple defect types; multiple inspection methods.
  DOI: 10.1504/IJBIC.2025.10072135
   
  
• Research on Regional Low-Carbon Economy Analysis Model based on Improved SVM  
  by Na Xiao, Yan Liu 
  Abstract: In order to further grasp the level of low-carbon economic development in the region and provide feasible suggestions for regional development, this paper proposes a regional low-carbon economy analysis and prediction model based on multiple strategies improved sparrow search algorithm optimised SVM (ISSA-SVM). Where, support vector machine (SVM) is used as the basic prediction method, and sparrow search optimisation algorithm improved based on multi strategy and combine with PLS component extraction is introduced to optimise the parameters of SVM and further enhance its predictive performance. Simulation results show that the designed prediction model based on ISSA-SVM has good prediction performance. Furthermore, the prediction error rate of this model has always been stable below 2.5%, and its precision is high. Therefore, the proposed model can be used to analyse and predict the development level of low-carbon economy in practice, which has certain feasibility.
  Keywords: low-carbon economy; support vector machine; sparrow search algorithm; prediction model.
  DOI: 10.1504/IJBIC.2025.10072382
   
  
• Classification of Malaria Disease using Optimal Fire Hawks based Capsule Convolutional Vision Transformer Network  
  by Pallavi Bhanudas Salunkhe, Pravin Sahebrao Patil 
  Abstract: Malaria is a widespread harmful disease caused by parasites transmitted through infected mosquitoes. The primary challenge addressed in this paper is the low performance, high error rates, and poor segmentation accuracy in malaria disease classification using existing machine learning (ML) and deep learning (DL) techniques. To overcome these limitations, this study proposes an advanced malaria classification model using the optimal fire Hawks-based capsule convolutional vision transformer network (OFH_C2ViTNet). The input image was segmented using feature concatenation-based U-Net (FC-UNet) based on red blood cells, white blood cells, and malaria parasites. Finally, the suggested optimal fire Hawks-based capsule convolutional vision transformer network (OFH_C2ViTNet) was used to categorise malaria into difficult, trophozoite, gametocyte, ring, and schizont kinds. From the input images, the proposed model provides an efficient result for identifying the disease at an early stage. Experimental evaluation demonstrates that the proposed model achieves superior performance, with an accuracy of 97.42% and a precision of 98.68%, outperforming existing state-of-the-art methods in malaria detection.
  Keywords: Median Filtering; Contrast Enhancement; Feature Concatenation; Hawks Optimizer; Vision Transformer Network; Malaria Parasites.
  DOI: 10.1504/IJBIC.2025.10072835
   
  
• Self-Improved Optimisation Model On Energy-Aware Resource Deployment Algorithm for Cloud Data Centres  
  by Prabha B, Kalangi Ruth Ramya, Charanjeet Singh 
  Abstract: The high processing demands of business, social, web, and scientific applications are driving a sharp rise in the demand for cloud computing. Most of the current cloud data centre resource management algorithms take CPU utilisation as the main consideration and increase CPU utilisation through virtual machine integration to reduce the energy consumption of cloud data centres. This work intends to propose a new cloud resource deployment model that includes three major aspects. Clustering is the initial phase, where clustering takes place by the Improved FCM-based clustering. Here, it is used to group the physical machines under the consideration of Energy and Distance. The process of deployment of the virtual machine is handled by Optimisation assisted Bi-GRU. Thereby, the proposed optimisation problem will be solved by Updated SSA with Baker Map Evaluation. The improved FCM with enhanced Jensen-Shannon distance has achieved a high accuracy value of 0.944.
  Keywords: Cloud Computing; Cloud Data Centers; Improved Fuzzy C Means based clustering; Resource Deployment; Updated Squirrel Search Algorithm with Baker Map Evaluation Algorithm.
  DOI: 10.1504/IJBIC.2025.10073095
   
  
• Attraction-Repulsion based Balance of Exploration and Exploitation in Many-Objective Optimisation with Application to Water Resources Allocation  
  by Yingnan Ma, Junlong Shen, Di Zhu, Renbin Xiao 
  Abstract: This paper addresses the critical issue of water resource allocation in the Yellow River Basin, a region characterized by severe water scarcity and heterogeneous spatial distribution. A novel many-objective evolutionary algorithm, MaOEA/AROA, is proposed, integrating attraction-repulsion mechanisms and co-evolution strategies to effectively balance exploration and exploitation in optimisation. From the Environmental, Social, and Governance (ESG) perspective, the model aims to minimize pollution, maximize equity, and enhance economic benefits, addressing the industrial, agricultural, and domestic water demands across nine provinces. The algorithm extends the single-objective attraction-repulsion optimisation paradigm to a many-objective framework, leveraging its strong development capability while maintaining diversity through a dual-population co-evolution approach. Experimental results demonstrate that MaOEA/AROA generates a diverse set of Pareto optimal solutions, offering flexible strategies to balance conflicting objectives and promote sustainable development. The algorithm's performance is validated on standard benchmark problems and applied to the Yellow River Basin, showcasing its practical utility in complex water resource allocation scenarios. Future work will focus on enhancing the model's robustness and incorporating dynamic water cycle considerations to further improve its applicability in real-world water resource management.
  Keywords: Many-objective optimisation; Attraction-repulsion optimisation; Indicator-based MaOEA; Co-evolution; Water resource allocation.
  DOI: 10.1504/IJBIC.2025.10073274
   
  
• A Competitive and Bi-Space Sparsity based Artificial Bee Colony Algorithm for Large-Scale Multi-Objective Optimisation  
  by Jiayao Qian, Jinyu Xu, Shitao Liao, Hui Wang 
  Abstract: This paper proposes a novel artificial bee colony (ABC) algorithm, called LMOABC, to enhance the global search capability of ABC in solving large-scale multi-objective optimization problems (LSMOPs). By introducing a competitive mechanism, the population is segregated into two distinct groups: ``losers'' and ``winners''. To achieve a trade-off between exploration and exploitation, employed bees perform the global search on the ``losers'', while onlooker bees conduct the local search on the ``winners''. Moreover, a bi-space sparsity method is designed in the scout bee stage, in which stagnated solutions are re-initialized to sparse regions. To verify the performance of LMOABC, nine well-known LSMOP benchmark problems with dimensions of 100, 500, and 1000 are tested. Experimental results show that it performs competitively compared to several recent LSMOEAs.
  Keywords: large-scale multi-objective optimization; artificial bee colony algorithm; multi-objective optimization; large-scale optimization; evolutionary algorithms.
  DOI: 10.1504/IJBIC.2025.10073447