International Journal of Innovative Computing and Applications (8 papers in press)

Regular Issues

• Fuzzy Control based Multiple Power Sources for Industrial Drives Applications  
  by Ravindranath Tagore Yad'apalli, Rajani Kandipati, RamaKoteswara Rao Alla, Myneni Hareesh 
  Abstract: The renewable energy sources exhibit a prominent role in order to power the industrial drives or electric vehicles (EVs) related esteemed applications. Importantly, throughout a day the solar irradiation may not be constant. Therefore, the peak power should be tracked from the solar photovoltaic (SPV) panel (SPV-P) with respect to the varying solar irradiation conditions. Moreover, the fuel cells (FCs) are widely used in many power generation applications such as commercial or industrial applications. Therefore, this paper highlights the application of multi-power source vector controlled induction motor (VCIM) drive through an efficient power conditioning unit (PCU).The modelling aspects are presented for both the fuel cell and solar PV systems. The PCU comprises of the boost converter and the multilevel inverter (MLI). The boost converter is effectuated with the fuzzy logic control (FLC) as well as the perturbation and observation (P&O) algorithm for the maximum power point tracking (MPPT) of the solar PV panel. The MATLAB based simulation results are presented with an emphasis on the torque ripples of the VCIM drive.
  Keywords: Solar energy; fuel cells; power conditioning units; vector control.
  DOI: 10.1504/IJICA.2026.10074832
   
  
• Multidimensional Crime Prediction Technique Optimisation Combining Feature Extraction and GAN  
  by Manna Xie 
  Abstract: With rising public safety concerns, effective crime prediction has become critical. Traditional methods struggle with incomplete feature extraction and limited multidimensional data handling. This study proposes a multidimensional crime prediction model integrating feature extraction with Generative Adversarial Networks (GAN). The model achieves deep integration of spatial correlation and temporal dependence through a combined graph convolutional network and Transformer architecture. A variational autoencoder optimizes the GAN, addressing vanishing gradients and data bias. Experimental results show that after 200 iterations, the model’s loss value reaches 0.019, outperforming comparison algorithms (0.036, 0.064, 0.085). In robbery crime prediction, the model achieves 86.3% accuracy, exceeding the best comparison at 83.2%. These results demonstrate that the proposed model significantly enhances crime prediction performance across multiple crime types, offering an intelligent and efficient forecasting approach.
  Keywords: GCN; Transformer; GAN; VA; Multidimensional data; Crime prediction.
  DOI: 10.1504/IJICA.2026.10075652
   
  
• YOLOv8-enhanced temporal modelling for semantic classification of ethically sensitive video content  
  by Chelsi Sen, Kuldeep Kumar Yogi 
  Abstract: This paper presents a smart, efficient, and interpretable deep learning framework for content-based video classification, specifically targeting context-rich categories such as vulgar, kissing, accidental, abusive, and fighting scenes. The proposed approach employs YOLOv8-based object detection to guide an attention-weighted keyframe selection mechanism, thereby ensuring that only the most informative frames are retained for the processing. These selected keyframes were passed through a hybrid deep architecture combining ResNet50 for spatial feature extraction and Bi-LSTM for temporal sequence modelling. Extensive experiments were conducted on benchmark datasets, including UCF101, NudeNet, CADP, and a custom dataset curated for rare categories. An accuracy of 92.34% and an F1-score of 91.12% were achieved by the proposed model, performing better than the traditional models of 3D CNN, Conv-LSTM, and ResNet50 with dense frame sampling by 48%. Class AUC values of more than 0.94 were obtained in the analysis of the proposed model.
  Keywords: attention mechanism; classification framework; deep learning; DL; LSTM; learning methods; neural networks; sensitive content; YOLO.
  DOI: 10.1504/IJICA.2026.10078185
   
  
• Wireless Inertial Motion Capture System and Pose Trajectory Fusion Algorithm for Animation and Film Design  
  by Shifeng Wang 
  Abstract: The film and animation industry increasingly demand real-time performance and accuracy. Traditional optical motion capture methods face limitations due to environmental lighting and equipment constraints, often failing to meet high production standards. To address this issue, this study proposes a motion capture system that integrates an error-state Kalman filter and improved adaptive damped least squares. The system fuses data from multiple inertial measurement unit sensors through the error-state Kalman filter and optimises pose trajectories with the improved adaptive damped least squares, significantly enhancing motion capture performance. Experimental results show that the proposed system achieves a pose estimation error converging to 1.5 degrees within 2.5 s, and the trajectories closely match the optical ground truth. During dynamic tasks, the system exhibited absolute orientation errors of 2.44
  Keywords: Motion capture system; Pose trajectory fusion algorithm; Inertial measurement unit; Kalman filter; Animation and film design.
  DOI: 10.1504/IJICA.2026.10078298
   
  
• Fuel Cost Minimisation in Generator Systems with Valve-Point Effects Using Differential Evolution Algorithms  
  by Om Prakash, Saumya Das, J. Satheesh Kumar, Hashinur Islam Islam, Amrita Rai 
  Abstract: This research explores the effectiveness of the Differential Evolution (DE) optimization algorithm in solving Economic Load Dispatch (ELD) problems in electrical power systems. A population-based, stochastic optimization method with a reputation for simplicity and resilience, Differential Evolution has shown encouraging results in a range of real-world restricted optimization situations. The DE algorithm is used in this study to solve ELD scenarios, including both 5- and 13-generator systems. Systems with valve-point effects add complexity and non-linearity to the cost function and are given special consideration. The outside penalty method reframes the ELD problem as an unconstrained optimization problem to address system restrictions. The outcomes show that DE can minimize fuel costs while handling the dispatch problem's intrinsic non-convexities skilfully.
  Keywords: Economic Load Dispatch Problem; Differential Evolution; Multidimensional functions and. Global Optimisation.
  DOI: 10.1504/IJICA.2026.10078327
   
  
• Football Highlights Detection Based on Twin Comparison Algorithm and Multimodal Feature Fusion  
  by Xufeng Zhang 
  Abstract: To enhance the accuracy and robustness of football highlights detection (FHD), this study proposes an innovative method integrating Twin Comparison and multimodal features. It employs Twin Comparison for dual-threshold shot segmentation, classifying video scenes into four types: goals, corner kicks, penalty area attacks, and fouls. The approach uses a 3D convolutional neural network to extract spatiotemporal visual features and applies Mel-frequency cepstral coefficients for audio analysis. Multimodal information is integrated via post-fusion and classified using a Softmax classifier. Experiments demonstrated a shot segmentation precision of 92.4% and recall of 88.7%. The goal detection F1-score was 91.9%, while audio cheer detection reached 94.2%. The multimodal model achieved an average accuracy of 84.8%, an F1-score of 88.9%, and real-time processing at 33.5 FPS. The method significantly improves detection accuracy, effectively complements audiovisual features, and offers practical value for intelligent football video analysis, viewing experience, and content dissemination.
  Keywords: 3DCNN; Football match; Dual threshold segmentation; Multimodal feature fusion; MFCC.
  DOI: 10.1504/IJICA.2026.10078601
   
  
• A Framework for Indoor Visual Element Extraction Using an Improved Attention Generative Adversarial Network  
  by Miao Nie, Zhongping Sun 
  Abstract: Traditional generative adversarial networks (GAN) suffer from insufficient structural modelling and loss of details in indoor visual element extraction. This study proposes an improved attention GAN model framework that integrates spatial attention mechanisms and channel attention allocation mechanisms. This framework guides the generator to continuously optimise the feature expression process through the supervised feedback mechanism of the discriminator, thereby improving the accuracy and completeness of visual element extraction, ensuring feature recognition and reconstruction in complex image scenes. The experimental outcomes showed that the algorithms element extraction accuracy was 93.5%, the edge segmentation accuracy was 91.2%, and it exhibited stronger robustness in interference environments. The indoor element extraction model achieved an element extraction accuracy of over 90.3% on different datasets, demonstrating good convergence and generalisation ability. The structural similarity of the extracted element feature images reached 0.94, with a PSNR of 37.4 dB. The above results indicate that the improved attention GAN model can effectively identify various elements in complex indoor scenes and maintain a high degree of detail restoration in indoor visual element extraction. This study provides more reliable technical support for indoor environment understanding and intelligent design.
  Keywords: Indoor visual element extraction; Generate adversarial networks; Attention mechanism; Spatial attention; Channel attention.
  DOI: 10.1504/IJICA.2026.10078660
   
  
• Intelligent inspection and monitoring of minor defects in complex slopes using unmanned aerial vehicles based on improved YOLOv11-PEW architecture  
  by Yong Lu, Li Tian, Sheng Yuan 
  Abstract: To address the issues of missed detection of small targets, interference from complex backgrounds, and blurred boundaries in visual inspection of geological disasters, this paper proposes the YOLOv11-PEW model: it introduces a P2 microscopic inspection head to retain shallow features to reduce texture loss, embeds an efficient multi-scale attention (EMA) module to calibrate feature weights across space to suppress background noise, and uses the Wise-IoU (WIoU) loss function (LF) to optimize boundary regression accuracy. Experimental findings demonstrate that YOLOv11-PEW achieves a mAP@0.5 of 90.1% on the self-built slope dataset, a 5.8% improvement over the baseline (YOLOv11n). Furthermore, while ensuring compliance with the real-time inference standard for embedded edge devices (>30 FPS), it significantly improves the detection accuracy of extremely small targets (Area <32 x 32) by 14.6%. Visualisation analysis (Grad-CAM) further confirms that the model can accurately focus on the disease itself from diffuse background noise, demonstrating excellent robustness.
  Keywords: highway slope protection; detection of minor defects; YOLOv11; attention mechanism; unmanned aerial vehicle remote sensing.
  DOI: 10.1504/IJICA.2026.10078678