International Journal of Wireless and Mobile Computing (29 papers in press)

Regular Issues

• Research on a laser cutting path planning method based on improved ant colony optimisation  
  by Naigong Yu, Qiao Xu, Zhen Zhang 
  Abstract: Laser cutting path planning for fabric patterns is critical to cutting efficiency. The ant colony optimisation algorithm commonly used in this field is constrained by the complete cutting and cannot plan a true global optimal path, resulting in large empty strokes. To solve this problem, this paper proposes an ant colony optimisation method based on virtual segmentation of multiple feature points for path planning of laser cutting. The method first changes the feature point selection strategy of traditional ant colony optimisation and increases the number of feature points in a single pattern. Then the single closed pattern is virtually divided into multiple open contours. Finally, the optimal cutting path is planned based on the solution of the travelling salesman problem. Experiments show that the cutting planning path obtained by the proposed method has a higher degree of compression on the idle stroke and significantly improves the laser cutting efficiency.
  Keywords: laser cutting; path planning; ant colony optimisation; virtual segmentation.
  
  
• Performance analysis of downlink precoding techniques in massive MIMO under perfect and imperfect channel state information in single and multi-cell scenarios  
  by Chanchal Soni, Namit Gupta 
  Abstract: The novel Optimised Max-Min Zero forcing precoder (OM2ZFP) scheme is proposed in this work. The optimization is incorporated with the chimp optimization strategy (CPO) to maximise the spectral efficiency, achievable sum rate, max-min rate, and minimise BER. The designed precoder model is contemplated under single cell perfect CSI, single-cell imperfect CSI and multiple cells perfect CSI, multi-cell imperfect CSI. Three pre-coding schemes, zero forcing (ZF), Maximum Ratio Pre-coding (MRT) and Minimum Mean Square Error (MMSE) precoder techniques, are implemented in the Matlab platform to manifest the effects of the novel designed precoder. The performance of the achievable sum rate is analysed under three cases, namely case I (fixed users and varying antenna), case II (fixed and varying) and case III (varying channel estimation error). The results show that the increasing number of antenna and users enhance the spectral efficiency, downlink transmits power and achievable sum rate performance.
  Keywords: massive MIMO; precoder; downlink transmission; antenna; optimisation; spectral efficiency; achievable sum rate.
  
  
• An improved fuzzy clustering log anomaly detection method  
  by Shuqian He, WenJuan Jiang, Zhengjie Deng, Xuechao Sun, Chun Shi 
  Abstract: Logs are semi-structured text data generated by log statements in software code. Owing to the relatively small amount of abnormal data in log data, there is a situation of data imbalance, which causes a large number of false negatives and false positives in most existing log anomaly detection methods. This paper proposes a fuzzy clustering anomaly detection model for unbalanced data, which can effectively deal with the problem of data imbalance and can effectively detect singular anomalies. We introduce an imbalance compensation factor to improve the fuzzy clustering method, and use this method to build an anomaly detection model for anomaly detection of real log data. Experiments on real data sets show that our proposed method can be effectively applied to log-based anomaly detection. Furthermore, the proposed log-based anomaly detection algorithms outperform other the state-of-the-art algorithms in terms of the accuracy, recall and F1 measurement.
  Keywords: distributed information system; log data; anomaly detection; artificial intelligence for IT operations; fuzzy clustering; imbalanced datasets; unsupervised learning; machine learning.
  
  
• Research on wireless routing problem based on dynamic polycephalus algorithm  
  by Zhang Yi, Yang Zhengquan 
  Abstract: The efficiency of the traditional Physarum Polycephalum Model (PPM) is low for wireless planning problems. Also, other heuristic algorithms are easy to fall into local optimum and usually require a large training set to find the optimal parameter combination. Aiming at these problems, we propose a new dynamic model of Physarum Polydynia (DMOP2) algorithm combined with PPM in this paper. This algorithm can judge the irrelevant nodes according to the traffic matrix after each iteration and then delete them and re-establish a new distance matrix when solving the routing problem. The improvements not only reduce the time consumed by calculation but also improve the accuracy of calculation pressure. Simulation experiments in random network and real road network prove the feasibility and effectiveness of the proposed algorithm in solving the path planning problem, and the experimental results show that the efficiency is significantly improved compared with PPM.
  Keywords: wireless planning; Physarum Polycephalum model; dynamic model.
  
  
• A trusted management mechanism based on trust domain in hierarchical internet of things  
  by Mingchun Wang, Jia Lou, Yedong Yuan, Chunzi Chen 
  Abstract: Existing trusted models usually authenticate the identity and behaviour of sensing nodes, without considering the role of sensing nodes in the process of interaction and transmission of information. Therefore, in view of the hierarchical wireless sensor network architecture of the internet of things, this paper proposes a new hierarchical trusted management mechanism based on trusted domain. The mechanism abstracts different nodes in the hierarchical structure of the internet of things, gives them different identities, and calculates the trust value of the sensing nodes by using similarity weighted reconciliation method. The experimental results show that the proposed scheme is feasible and effective.
  Keywords: trusted domain; trusted management; similarity weighted reconciliation; trust value; hierarchical structure.
  
  
• Automatic modulation recognition based on channel and spatial attention mechanism  
  by Tianjun Peng, Guangxue Yue 
  Abstract: With the complexity of the wireless communication environment, automatic modulation recognition (AMR) of wireless communication signals has become a significant challenge. Most existing researches improve the model recognition performance by designing high-complexity architectures or providing supplementary feature information. This paper proposes a novel AMR framework named CCSGNet. The convolutional neural network (CNN) and bidirectional gate recurrent unit (BiGRU) are employed in CCSGNet to reduce the spectral and time variation of the signals, furthermore, the channel and spatial attention are employed to fully extract local and global features of signals. In order to reduce the training time cost of the model, we propose a piecewise adaptive learning rate tuning method to improve the training of the model. The comparisons with several common learning rate tuning methods on CCSGNet show that the proposed method achieves convergence in 25 training epochs, reducing the training time cost of the model. Moreover, CCSGNet improves the recognition accuracy of 16QAM and 64QAM by 6.47%-50.95% and 4.54%-25.66%, respectively.
  Keywords: automatic modulation recognition; attention mechanism; learning rate; deep learning.
  
  
• Optimisation of a high-speed optical OFDM system for indoor atmospheric conditions  
  by B. Sridhar, S. Sridhar, Naresh K. Darimireddy 
  Abstract: VLC provides high security and broadband functionality for optical communication in free space. In particular, this proposed work focuses on analysing receiving power distribution patterns and signal-to-noise ratios for indoor and vehicle applications. The optical systems of indoor communications are more suitable than wireless radio systems. The significant advantage of optical wireless communication (OWC) is providing high-speed data up to 2.5 Gbps at a low cost. In indoor areas such as auditoriums and public places, the OWC systems are more suitable. But optical signals are distorted by the signal propagation effects due to obstacles, walls, etc. The proposed system is an OFDM-based system that can transmit multiple channels and connects many modems over a given indoor area. Proposed methods initially focus on the LED/LD transmitter sources placement at the ceiling of indoor space and observed signal power distribution; in an IM/DD-based OWC system, the information signal must be accurate and nonnegative. The proposed asymmetric optical OFDM (ACO-OFDM) system is implemented for indoor communications, and the system's performance is evaluated with the Bit error rate. In particular, the performance of the specific M-QAM ACO-OFDM method with adaptive frequency is assessed by using theoretical analysis and simulations. Compared to the M-QAM ACO-OFDM method, the ACO-OFDM and DCO-OFDM showed lower spectral efficiency performance for the OWC system in the frequency selective channel.
  Keywords: ACO-OFDM; indoor networks; power distribution; clipping; bit error rate.
  
  
• Optimal cuckoo-based resource allocation in wireless network  
  by S. Mary Evanchalin, R. Ravi 
  Abstract: Efficient resource allocation in wireless networks is becoming essential due to the growing demand for wireless communication services. However, the usual resource allocation is not sufficient for wireless networks. Methods: The Cuckoo-based Flooding Protocol (CbFP) is presented in this research as an innovative method to improve resource allocation and data transmission in wireless networks. The key objective of this work is allocating the resource in an optimal way; for that, the cuckoo search fitness function was utilised. The data packets are sent to the target node by the nodes based on the allocated resources. Results: The effectiveness of the framework was evaluated using the ns3 tool. To validate the improvements, the results were compared with existing models. The model achieved an impressive throughput of 50 Mbps with a minimal transmission delay 10 ms and a packet drop 3%. Hence, the introduced model is highly suitable for the wireless network application to allocate resources optimally.
  Keywords: cuckoo search fitness function; flooding protocol; resource allocation; wireless network.
  DOI: 10.1504/IJWMC.2025.10075619
   
  
• An evolutionary game theory model for emergency supply allocation in disaster relief  
  by Liang Zhao, Junmei Li 
  Abstract: In the face of increasingly frequent emergencies such as natural disasters and public health crises, the efficiency and fairness of emergency supply allocation has become a critical concern. This paper proposes an evolutionary game model involving three key stakeholders the government, relief workers and disaster victims to analyse their strategic behaviours in emergency supply distribution. Under bounded rationality and information asymmetry, the model constructs a tripartite evolutionary game framework, derives replicator dynamic equations and identifies evolutionarily stable strategies for each party. Results show that emergency stockpiles, transportation efficiency and surplus levels significantly influence strategic choices. In particular, the shift to innovative disaster relief becomes stable when its capacity exceeds the combined capacity and surplus of the traditional model. Simulations further confirm that optimised reserves and cooperative distribution enhance system stability and promote rational responses from victims.
  Keywords: emergency material deployment; evolutionary game; strategy selection; evolutionary stabilisation strategy.
  DOI: 10.1504/IJWMC.2025.10075620
   
  
• MultiParamNet: a multi-parameter fusion approach for anomaly detection in DC power supply systems  
  by Yu Zhang, Chuanqi Shen, Jinlong Zhang, Lutong Zhang, Luansong Yue, Mingyue Fan, Wei Liu, Qing Lei, Shengnan Cui 
  Abstract: To address the limitations of traditional abnormal state detection methods for Direct Current (DC) power systems, this paper proposes an intelligent anomaly detection approach based on multi-parameter fusion. The proposed method fully exploits the temporal dependencies and cross-domain correlations among multiple heterogeneous parameters, including voltage, current, temperature, battery state, communication signals and control logic, thereby constructing a unified high-dimensional feature representation. A deep temporal modelling network is developed by integrating Gated Recurrent Units (GRU) with a multi-scale attention mechanism, enabling accurate perception of dynamic operating states and early identification of abnormal behaviours. Furthermore, a contrastive learning-based self-supervised pre-training strategy is introduced to enhance the models generalisation capability and feature discrimination under limited labelled data. An isolation forest algorithm is then employed for graded classification and interpretability analysis of multiple types of anomalies. Experiments conducted on real-world data sets from a DC power supply system demonstrate that the proposed method achieves a high anomaly detection accuracy of 95.2%, significantly outperforming traditional statistical models and state-of-the-art deep learning approaches.
  Keywords: multi-parameter fusion; anomaly detection; deep temporal modeling; self-supervised learning; operational state assessment.
  DOI: 10.1504/IJWMC.2025.10075924
   
  
• Research on flow table overflow attacks in software defined networks based on machine learning  
  by Dawei Li, Chuntao Li, Yingze Ye, Mingxuan Guo 
  Abstract: Software Defined Network (SDN) switches have limited flow table capacity and are vulnerable to flow table overflow attacks. This paper proposes a method named FTsec to protect SDN switches, which analyses flow table entries based on machine learning to enhance the detection and mitigation capability of attacks. The source address validation method is adopted to locate and block the source of spoofed source address attacks, and correlation between flow table feature and network topology is used to trace the root cause of attack. Experimental results show that FTsec can effectively detect and suppress the flow table overflow attack, significantly reduce the risk of flow table overflow. Especially when dealing with spoofed source address attack, it can limit the average proportion of attack flow table entries to less than 7%. At the same time, the average CPU load is only increased by 1.4%, which shows the feasibility of deploying FTsec in SDN.
  Keywords: software defined network; flow table overflow attacks; source address validation; flow table feature.
  DOI: 10.1504/IJWMC.2026.10076916
   
  
• An integrated model for long-term water consumption prediction  
  by Fang He, Tianyu Zhao, Fanhao Kong 
  Abstract: This article focuses on prediction model in long-term water consumption. The principal component analysis (PCA) was utilized to diminish dimensionalities. The Hodrick-Prescott (HP) filter decomposition technique was applied to perform PCA and separate the time series into their respective trend and cyclical series. The Grey Model (GM) was applied to predict the trend series of water consumption, while the Bayesian Optimized Least Squares Support Vector Machine (BOLSSVM) model was utilized to predict the cyclical series. Thus a PCA-GM-BOLSSVM model was constructed. Based on the water consumption data from 2008 to 2022 in Wuhan, the PCA-GM-BOLSSVM model reduced the mean relative and absolute errors by 28.71% and 27.82%, compared to the PCA-GM-LSSVM model. Compared to the ANN model, the PCA-GM-BOLSSVM model achieved an 80.63% and 80.33% reduction in mean relative and absolute errors. The PCA-GM-BOLSSVM model enhanced fitting accuracy and reduced error rates.
  Keywords: water consumption prediction; principal component analysis; HP filter decomposition; GM-BOLSSVM model.
  DOI: 10.1504/IJWMC.2026.10077356
   
  
• A mobile task offloading cluster framework based on resource clustering and heartbeat mechanism  
  by Wentao Li, Songquan Zhu, Qinglei Qi, Jie Zhao, Cong Zhao 
  Abstract: The rapid proliferation and high dynamism of heterogeneous mobile devices challenge traditional offloading methods, which struggle with resource volatility and frequent node changes. To address these issues, this paper proposes a Mobile Task Offloading Cluster (MTOC) framework that integrates resource clustering analysis with heartbeat monitoring. The framework designates a mobile device, referred to as the control node, to dynamically select nearby workers, employs clustering techniques to characterize and predict real-time resource states, and introduces an interference-aware Quality of Service (QoS) model for evaluating both computation and communication delays. Furthermore, a cosine similarity-based state recognition and dynamic task allocation strategy mitigates execution interference in complex scenarios. To enhance robustness, a heuristic online task recovery mechanism leverages periodic heartbeat signals to anticipate failures and reallocate workloads. Experimental results demonstrate that MTOC achieves adaptive scheduling in heterogeneous environments, ensuring reliable, efficient, and stable task execution while significantly improving resource utilisation.
  Keywords: mobile task offloading; resource clustering; dynamic scheduling; task allocation; mobile computing.
  DOI: 10.1504/IJWMC.2026.10077517
   
  
• Particle-SPA optimisation-based wireless sensor network for secured data transmission  
  by Salman Arafath Mohammed 
  Abstract: In wireless sensor networks (WSN), security is the main concern of developing security protocols that inspires numerous scholars to discover security solutions in an efficient manner that adds few advantages, like low power consumption, flexible communication, and low cost. However, there exist few limitations, like impossible to choose the expected cluster precisely, the limited capability of the sensor nodes, and low efficiency. Thus, this research proposes a particle-spa optimization for enabling optimal clustering and routing in WSN depending on the parameters such as energy and trust. The developed algorithm follows featured-sparrow and swarm characteristics, to perform the routing that supports the data transfer in a secure manner. The developed method applied in WSN clustering and routing highlights the achievements with maximal alive nodes, normalized energy, delay, and throughput of 40, 0.354066, 0.001282 ms, and 0.036726 when the simulation with 200 nodes are available at round-1500.
  Keywords: secured routing; routing protocol; wireless sensor network; particle-SPA optimisation; data transmission.
  DOI: 10.1504/IJWMC.2024.10077841
   
  
• Intelligent fake review identification e-commerce with multi-attention residual shrinkage-CNN  
  by Madhavi Samala, Abdul Ahad 
  Abstract: With the rise of e-commerce, customer choices are heavily dictated by internet reviews, which also attract spammers who generate fake reviews to manipulate product reputation.Detection of such spam reviews is still a significant challenge since existing methods often suffer from poor feature representation, insufficient capacity to model contextual dependencies, and lesser ability to adapt to spammer evolving patterns. To overcome these limitations, this research proposes the intelligent fake reviews detection framework based on Multitask Multi-Attention Residual Shrinkage-CNN in e-commerce websites (IFRD-MMARSCNN-ECW). The framework utilizes the Computational Metaphor Processing Model (CMPM) for sophisticated pre-processing, and then the Adaptive Spatiotemporal Transformer (AST) for aspect-based extraction of features. MMARSCNN is used for classification, and optimization using Black-Winged Kite Algorithm (BWKA) to enhance accuracy. Experimental testing on the Deceptive Opinion Spam Corpus Dataset shows that IFRD-MMARSCNN-ECW attains an accuracy of 99.1%, and ROC of 0.99, significantly outperforming existing models.
  Keywords: adaptive spatiotemporal transformer; black-winged kite algorithm; computational metaphor processing model; e-commerce website; intelligent fake reviews detection.
  DOI: 10.1504/IJWMC.2026.10077923
   
  
• Optimal defence resource allocation in urban correlated lifeline networks based on game attack and defence  
  by Hongliang Ni, Xudong Zhao, Benwei Hou 
  Abstract: The urban lifeline network, which includes critical infrastructure elements such as power, water, and transportation systems, is essential for the functioning of a city. Despite the significant impact of deliberate attacks on urban lifeline networks, most research on network resilience has focused on natural disasters. In this paper, we propose a strategy game model for both attackers and defenders of urban lifeline networks under deliberate attacks. The model, which combines game theory and risk theory, aims to identify optimal pre-disaster protection strategies. Considering the possibility of different types of attackers, combining the characteristics of both attackers and defenders, constructing the strategy solutions of both attackers and defenders, solving the attack and defence strategies of the complete information game, determining the Bayesian Nash equilibrium point, and finding the optimal strategy combinations of both attackers and defenders. Our experimental results demonstrate that the proposed model is effective in guiding the selection of optimal protection strategies. Specifically, our model helps to identify the best response strategies for attackers and defenders under different scenarios, which can improve the resilience of urban lifeline networks against deliberate attacks.
  Keywords: urban lifeline network; game theory; Bayesian game; Nash equilibrium.
  DOI: 10.1504/IJWMC.2024.10078042
   
  
• Grid load balancing with V2G and deep reinforcement learning  
  by R. Sasirega, S. Prakash 
  Abstract: Charging and discharging maximization of electric vehicles remains a challenge primarily attributed to grid condition changes and different energy requirements. This paper presents an innovative solution to this problem using deep reinforcement learning, which changes the charging and discharging schedules of electric vehicles depending on the real time frame. A hybrid feature selection method that merges the Pelican Optimization Algorithm (POA) and Gannet optimization algorithm (GOA) is utilized to select the relevant features necessary for effective training of the proposed model. For optimal charging and discharging rates, the theoretical concepts of the Deep Q-Learning (DQL) algorithm were incorporated. The proposed approach delivered impressive results, with a peak demand of just 110 kW and a total energy usage of 3200 kWh, showcasing its stellar performance in managing the grid load. Moreover, it boasted a grid stability index of 0.92, converged in 20 seconds, and achieved an outstanding model accuracy of 95%.
  Keywords: deep Q-learning; EV charging/discharging; V2G technology; optimisation; feature selection.
  DOI: 10.1504/IJWMC.2025.10078075
   
  
• A cross-domain adaptive deep learning framework for encrypted-decrypted traffic correlation and IoT terminal traceability  
  by Libin Li, Tingting Yang, Kai Ma, Yueming Wang, Yongjiao Cao 
  Abstract: Encrypted traffic analysis poses a persistent and formidable challenge for IoT network security, especially in tracing terminal devices concealed behind Network Address Translation (NAT) gateways. This study introduces TCG-Net, a novel framework that enables robust encrypted-decrypted traffic correlation and precise IoT terminal traceability without payload inspection. The framework systematically integrates three innovative modules: a Temporal Spectral Analysis Module (TSAM) that distils stable periodic signatures from noisy traffic data; a Cross-Modal Attention Fusion Network (CMAF-Net) that performs principled alignment of encrypted and decrypted representations in a shared latent space; and a Graph Attention-based Mapping (GAM) module that constructs an interpretable address-translation graph for terminal identification. Comprehensive experiments on three public datasets (CIC-IoT-2023, CICIDS-2017, and TON_IoT-2022) demonstrate that TCG-Net decisively outperforms state-ofthe-art baselines, achieving 98.2% matching accuracy and 95.4% traceability accuracy. The results validate our central hypothesis that stable spectral-temporal patterns are the key to enabling secure, scalable, and privacy-preserving traceability in complex IoT ecosystems.
  Keywords: encrypted traffic analysis; IoT traceability; cross-domain learning; time-series analysis; graph attention network.
  DOI: 10.1504/IJWMC.2026.10078264
   
  
• Day-ahead power prediction of photovoltaic power generation based on WOA-BiGRU-AT model  
  by Yi Zhang, Wenzhen Meng 
  Abstract: At present, photovoltaic power generation is developing rapidly worldwide, and more accurate photovoltaic power prediction technology plays a significant role in developing photovoltaic power generation. To improve the accuracy of the current traditional photovoltaic power prediction model, a photovoltaic power prediction algorithm based on the WOA-BiGRU-AT model is proposed in this paper. The Attention mechanism is added to accelerate the convergence rate of the model. Then, by simulating the phenomenon of whale predation in nature, the super parameters of the BiGRU-AT model are optimized in the forward propagation process. The experimental results show that the model predicts the dataset better than the existing models.
  Keywords: day-ahead generation power prediction; wireless sensor; BiGRU; bi-directional gated recurrent unit; WOA; whale optimisation algorithm; attention mechanism.
  DOI: 10.1504/IJWMC.2024.10078265
   
  
• Computer simulation research of lithium battery materials: fusion of first-principle calculation and ANSYS simulation  
  by Juan Cui, Cong Zhong 
  Abstract: This study provides theoretical support and technical guidance for optimizing the performance of lithium-ion battery anode materials by integrating first-principles calculations and ANSYS simulation technology. Addressing the shortcomings of existing simulation methods in terms of accuracy and efficiency in describing electronic structure and ion migration, and their inability to support high-throughput screening of new materials, a novel ANSYS-FP method is proposed, combining first-principles calculations and ANSYS multiphysics simulation. This method uses atomic-scale parameters calculated precisely in first-principles calculations as input to the ANSYS simulation and utilizes macroscopic simulation results as feedback to guide the optimization of the first-principles model, forming a cross-scale closed loop. This method outperforms methods without first-principles calculations in both simulation speed and mean absolute error, with most data points concentrated within the 98% to 99% accuracy range. This approach can efficiently support high-throughput screening of anode materials, significantly shortening the development cycle of new materials.
  Keywords: lithium batteries; negative electrode material; computer simulation; first principles; multi-physics field simulations; multiscale simulation.
  DOI: 10.1504/IJWMC.2026.10078385
   
  
• An optimised radial-based flooding routing mechanism for energy management and security in wireless network  
  by S. Mary Evanchalin, R. Ravi 
  Abstract: The advancement of the wireless network has increased the use of communication and information-sharing technologies in numerous applications. The key issues that suppress the efficiency of wireless networks are energy utilisation and security. Often a high energy consumption node remains malicious. Several prediction and energy efficient models exist, but they lack energy management due to limitation of control features and nodes' random behaviour. So, the intelligent attributes are required for the node monitoring and energy management. Therefore, a novel Pufferfish-based Radial Flooding Routing (PbRFR) model is developed in this research to enrich the energy efficiency and security of wireless networks. Primarily, the required communication nodes were established in the network. The model analyses the behaviour of the nodes to detect the higher energy-utilising malware nodes. Subsequently, the detected nodes were removed from the wireless communication environment and gained the finest outcome.
  Keywords: wireless network; security; pufferfish optimisation; cluster head; routing.
  DOI: 10.1504/IJWMC.2025.10075621
   
  
• Optimisation of BiLSTM for end mills wear predictive study  
  by Chunlong Zou, Lin Zhou, Chen Wang, Xuxiang Lu 
  Abstract: An effective method of milling tool wear monitoring is important to improve product quality and extend the life of milling tools. A Genetic Algorithm (GA) optimised Bidirectional Long- and Short-Term Memory Neural Network (BiLSTM) deep learning model (GA-BiLSTM) is proposed to monitor the wear value of end mills. First, the important time-domain, frequency-domain and time-frequency features of the cutting tool wear signal are extracted by wavelet transform, and then processed by cross-validation and correlation analysis to obtain the input time-series samples for the prediction model. Then, the model parameters of the BiLSTM are optimised by GA, mainly optimising the learning rate (Learning Rate), generation (Epoch) and loss rate (Dropout). At last, the comparison experiment of different models is carried out: GA-BiLSTM is better than RNN, LSTM, CNN-BiLSTM and its evaluation index MAE and RMSE are lower than the comparison model, and the model operation time cost is in the reasonable scope. It shows that GA-BiLSTM method is effective and feasible, and improves the precision of wear prediction.
  Keywords: milling tool wear; genetic algorithm; BiLSTM; wear monitoring.
  DOI: 10.1504/IJWMC.2025.10076158
   
  
• Comparative analysis of MU detector in LDPC coded LS MIMO OFDM  
  by Shefin Shoukath, P.A. Haris 
  Abstract: Large Scale Multiple Input Multiple Output (LS MIMO) combined with Orthogonal Frequency Division Multiplexing (OFDM) is a key technique by prevaling the fading effects of wireless channel. The application of Low Density Parity Check codes (LDPC) to LS MIMO OFDM systems with hundreds of antennas at the receiver has been proposed in this paper. MIMO technology with channel coding like Low Density Parity Check codes (LDPC) is a promising solution in achieving data rate transmission with low probability of error. The multiuser signals transmitted to the Base Station (BS) are detected by low complexity linear MMSE detector. LDPC coded LS MIMO OFDM system is designed so as to decode the symbols at low complexity with linear minimum distance which thus enables to attain low bit error rate. In this paper a comparative analysis of the performance of multiuser detector in LS MIMO OFDM is presented. Characteristics of multiuser detection in LDPC coded LS MIMO OFDM is analysed by Bit Error Rate (BER), outage probability and radiation pattern of the detected signal. Simulation outcomes indicates the detector performance of LDPC coded system outperform that of an uncoded system.
  Keywords: low density parity check coding; LS MIMO OFDM; multiuser detection; MMSE; scattering channel.
  DOI: 10.1504/IJWMC.2023.10075929
   
  
• Progression in FPGA logic blocks towards efficient hybrid architectures  
  by Neeti, Sunita Dahiya 
  Abstract: Ever since the introduction of FPGAs in 1980s, they have witnessed a tremendous growth and are being widely accepted as a compelling alternative medium for the design of digital circuits due to their re-programmability and faster time to market. However, the FPGAs suffer from a major drawback that they have significantly less logic density and lower speed-performance as compared to standard cells. These two important FPGA metrics, i.e., speed and area-efficiency, are primarily influenced by the logic block architecture. Hence, the proper selection of FPGA logic block architecture is vital for addressing the speed-area deficiencies. In this paper, a comprehensive literature survey over three decades of FPGA logic block architectures is presented, keeping in view their impact on device's speed and area efficiency. It is observed that there has been a considerable shift in the choice of FPGA designers from identical logic blocks towards hybrid logic blocks comprising different types of logic resources.
  Keywords: LUT; reconfigurable; logic block; hybrid; heterogeneous; fracturable.
  DOI: 10.1504/IJWMC.2024.10076339
   
  
• A navigation redirection model based on the entorhinal-hippocampal cognitive mechanism  
  by Jinhan Yan, Naigong Yu, Yishen Liao, Zexuan Lv 
  Abstract: Animals possess remarkable navigation abilities, accurately estimating their direction within the environment. This functionality is achieved by head direction cells through angular path integration. However, directional errors continuously accumulate during this process, necessitating redirection using environmental cues. Most methods calibrate orientation by placing visual landmarks at a distal distance, while few consider nearby landmarks. In this paper, we propose a computational model for navigation redirection based on proximal landmarks to reduce cumulative errors. The model uses goal-vector cells in the hippocampus and object-vector cells in the entorhinal cortex to represent vector information for landmarks. When the landmarks are reencountered, the vector information will be processed at the retrosplenial cortex to redirect. Comparing experimental results with previous methods in simulation and real-world environments reveals that our method achieves higher calibration accuracy and broader adaptability. Our method is also more physiologically plausible and lays the foundation for developing brain-inspired navigation techniques.
  Keywords: navigation redirection; head direction cells; entorhinal-hippocampal; goal-vector cells; object-vector cells.
  DOI: 10.1504/IJWMC.2024.10076912
   
  
• Construction of an online vocal teaching model based on node influence and knowledge graph  
  by Ming Tian 
  Abstract: In response to the cold start and data sparsity issues faced by online teaching resource recommendation methods, this study first proposes using a node influence model to measure the influence of entities in the knowledge graph. Then, a vocal teaching resource recommendation model and learning effectiveness evaluation model based on long short-term memory network are established. The results show that the recommendation accuracy of the proposed model is 68.23%, and the area under the curve is 73.76%, which is 5.06% and 7.34% higher than the traditional RippleNet model, respectively. The accuracy and recall of the proposed learning effect prediction model are 0.525 and 0.224, respectively, which are 87.43% and 25.45% higher than traditional long short-term memory networks. The experimental results have demonstrated the recommendation and evaluation performance of the proposed model, which helps to improve teaching effectiveness and promote the development of online vocal teaching.
  Keywords: node influence; vocal teaching; knowledge graph; resource recommendation.
  DOI: 10.1504/IJWMC.2025.10076197
   
  
• Sports tourism information recommendation modelling based on user preference fine granularity and improved LSTM network  
  by Liying He, Huimin Zhang, Yaping Wang 
  Abstract: Currently, there are issues such as insufficient user data in the sports tourism information recommendation, which leads to a lack of fine-grained analysis of user preferences and affects the recommendation effectiveness. To address these issues, this paper proposes to combine user preference fine granularity, and construct a sports tourism recommendation model based on Knowledge Graph (KG) combined Whale Optimisation Algorithm (WOA) optimised Bidirectional Long Short-Term Memory (BiLSTM). Through this model, personalised recommendations of sports tourism information can be achieved, improving the recommendation effect of sports tourism information. Experimental results show that Recall@k and NDCG@k indexes of the proposed model are increased by 6.83% and 9.05%, respectively, which are significantly better than comparison models. Therefore, the designed model has higher recommendation precision, which can achieve fine-grained analysis of user preferences and accurate recommendation of tourism information, meet the practical needs of sports tourism information recommendation, and has effectiveness.
  Keywords: user preference fine granularity; knowledge graph; WOA algorithm; BiLSTM network; sports tourism information recommendation.
  DOI: 10.1504/IJWMC.2025.10076567
   
  
• Cognitive distraction identification using physiological signals-based enhancing road safety through attributed multi-order graph convolutional network  
  by P.S. Soumya, S. Mythili 
  Abstract: Driver distraction, particularly cognitive distraction, is a major cause of road accidents. While visual and manual distractions manifest through observable physical behaviours, the cognitive distraction presents unique detection challenges. The existing methods are not easily scalable due to the high cost of data acquisition devices. In this paper, an Enhancing Road Safety through Attributed Multi-Order Graph Convolutional Network-Based Cognitive Distraction Identification using Physiological Signals (ERD-AMGCN-CDI-PS) is proposed. The ERD-AMGCN-CDI-PS utilises physiological signals from the DEAP and WESAD data sets. The input signals are pre-processing utilising Regularised Bias-Aware Ensemble Kalman Filter (RBAEKF) to remove noise and artifacts. The Synchro-Transient-Extracting Transform (STET) is used to extract visual features from pre-processing signals. These features are given to the Attributed Multi-Order Graph Convolutional Network (AMGCN) to identify cognitive distraction. The ERD-AMGCN-CDI-PS method achieves 19.56%, 10.88% and 19.60% higher accuracy and 19.83%, 11.57% and 19.65% lower False Positive Rate (FPR) over the existing techniques.
  Keywords: attributed multi-order graph convolutional network; cognitive distraction; regularised bias-aware ensemble Kalman filter; road safety; synchro-transient-extracting transform.
  DOI: 10.1504/IJWMC.2025.10074665
   
  
• Throughput improvement under device clustering and power allocation in NOMA-MTC system  
  by Sandeep Singh Rana, Gaurav Verma, O.P. Sahu 
  Abstract: The explosive growth of massive Machine-Type Communications (mMTC) has introduced significant challenges in efficient spectrum utilisation and scalable resource allocation due to massive connectivity and heterogeneous traffic demands. Orthogonal schemes struggle with dense deployments, making NOMA a promising yet complex solution due to its pairing and power allocation challenges. This paper proposes K-Means++ clustering for its stability and Q-Learning power allocation for its adaptability to efficiently utilise spectrum in a NOMA-enabled MTC system. The proposed Machine Learning (ML) framework leverages the potential of NOMA-MTC to enhance system throughput under power constraints by dynamically adapting power allocation to the number of devices within each cluster without imposing restrictions on cluster size. Simulation results demonstrate that the proposed K-Means++ with QL approach achieves approximately 20% higher throughput compared to Gaussian Mixture Model (GMM) clustering, while maintaining higher spectral efficiency and ensuring faster convergence of power allocation coefficients compared to traditional schemes.
  Keywords: device clustering; K-Means++; NOMA; power allocation; Q-learning.
  DOI: 10.1504/IJWMC.2025.10076915