Purpose The purpose of this research work is to introduce the augmented reality (AR) technology in disassembly operation to reduce the efforts of disassembly and time of disassembly. Design/methodology/approach In this research paper, Dijkstra's algorithm is applied to find an optimal disassembly sequence for car jack assembly. Based on the obtained disassembly sequence, the product is to be dismantled using a manual approach and with AR approach for a 3D printed car jack assembly to carry a comparison study in terms of time of disassembly and easiness. Findings In this paper, for generating optimal disassembly sequences, Dijkstra star graph algorithm is used. To carry the disassembly operation, AR approach is used. Originality/value The approach used here to execute the disassembly operation is novel due to its integration of the AR technology. As per the reviewed literature, no prior work has incorporated such integration to perform disassembly operations.
Purpose The advantage of unmanned aerial vehicles (UAVs) is that they transmit data at a rapid speed, secure architecture and safe data transmission through internet of things (IoT). The simulated results were used to compare the performance of the proposed model with those of existing algorithms. Design/methodology/approach This work focuses on addressing these security issues by proposing an energy-efficient secured layered architecture with topology control (EESL-TC) technique to provide efficient communication. The proposed model identifies malicious attacks during data transmission and performs the necessary actions to mitigate them, ensuring secure data transmission between ground stations (GS) and UAV users. Findings The proposed model identifies malicious attacks during data transmission and performs the necessary actions to mitigate them, ensuring secure data transmission between GS and UAV users. Additionally, a cross-layered architecture is used to reduce the energy consumption and clustering mechanism to manage mobility. The advantage of UAVs is that they transmit data at a rapid speed, secure architecture and safe data transmission through IoT. Originality/value The EESL-TC provides a high throughput, high delivery rate and reduced delay. The proposed secured layered architecture effectively mitigates wormhole and grayhole attacks, ensuring secure communication and improving network performance in UAV-based IoT networks.
Purpose The purpose of this study is to develop an efficient hybrid multicast routing protocol for vehicular ad hoc networks (VANETs) using the M/G/m/m queuing model. It aims to reduce communication overhead, improve routing efficiency and enhance data transmission reliability in dynamic vehicular environments. The research focuses on addressing challenges such as network congestion, delays, packet loss and scalability under varying vehicle density and mobility conditions. Design/methodology/approach The study adopts a simulation-based approach using a hybrid multicast routing protocol integrated with the M/G/m/m Markov queuing model. Distance-based pruning, priority scheduling and optimal forwarding techniques are applied to improve routing decisions. The system is modeled and evaluated using OMNeT++ simulations under varying vehicle densities. Performance metrics such as communication overhead, delay, bandwidth utilization and packet delivery efficiency are analyzed and compared with conventional methods. Findings The proposed model significantly improves network performance by reducing communication overhead by 75–95%, end-to-end delay by about 75% and increasing multicast efficiency up to 93%. Distance-based pruning achieves up to 90% improvement in reducing redundant transmissions. The model demonstrates strong scalability and consistent performance under high mobility and dense network conditions, ensuring better resource utilization and efficient data dissemination. Research limitations/implications The study is limited to simulation-based evaluation and does not include real-world deployment. Environmental factors such as signal interference, hardware constraints and real traffic conditions may affect performance. Future research can focus on real-time implementation, integration with emerging technologies like autonomous vehicles and unmanned aerial vehicles (UAVs) and further refinement of adaptive routing strategies to handle complex large-scale VANET environments. Practical implications The proposed routing protocol can be applied in intelligent transportation systems to enhance traffic management, accident prevention and real-time communication. It improves bandwidth utilization, reduces congestion and ensures timely delivery of safety messages such as road conditions and weather alerts. The model supports efficient communication in both low and high-density vehicular environments, making it suitable for real-world vehicular network applications. Social implications The improved VANET communication system contributes to safer roads by enabling timely dissemination of critical information such as accidents, traffic congestion and weather updates. It enhances public safety, reduces travel time and supports smart city development. Efficient communication also minimizes fuel consumption and environmental impact by optimizing traffic flow and reducing unnecessary delays. Originality/value This research introduces a novel integration of the M/G/m/m queuing model with hybrid multicast routing for VANETs. Unlike conventional approaches, it combines distance-based pruning, queuing theory and multicast efficiency to significantly reduce communication overhead while maintaining scalability and robustness. The study provides a comprehensive framework for improving vehicular communication systems and contributes to advancing intelligent transportation technologies.
Purpose Reliable power transmission is essential for uninterrupted electricity supply. Conductor defects can reduce system reliability and create operational risks if not detected early. Conventional inspection mainly depends on manual observation, which is labour intensive, time consuming and prone to human error. This study aims to develop an unmanned aerial vehicle (UAV)-assisted deep learning framework for detecting faults in power transmission conductors. Design/methodology/approach The proposed framework uses UAV-based image acquisition and YOLOv8s-based object detection. A total of 9,182 raw UAV images were initially collected using a UAV-mounted GoPro Hero7 Black camera. After removing blurred, redundant and near-duplicate images, 4,100 annotated conductor images were prepared for training, validation and testing. The dataset included two classes: Normal Conductor and Defective Conductor. RGB UAV images were used for YOLOv8s training, while thermal images were examined separately as complementary qualitative evidence for hotspot-related abnormalities. Findings The YOLOv8s detector achieved precision of 0.967, recall of 0.976, mAP@0.5 of 0.991 and mAP@0.5:0.95 of 0.815. The model also achieved an offline inference speed of approximately 59.17 FPS on an NVIDIA Tesla T4 GPU. These results indicate that the framework can accurately localize and classify normal and defective conductor regions under UAV-based outdoor inspection conditions. Originality/value This study presents a UAV-assisted YOLOv8s framework for conductor fault detection using a curated RGB image dataset with complementary thermal observations. The approach provides an accurate, efficient and safer alternative to conventional manual inspection.
Purpose Conventional plant disease detection is time-consuming and prone to human error. The purpose of this study is to propose an edge artificial intelligence (AI)-based deep learning framework for plant disease detection under real-field conditions. The model integrates convolutional neural networks (CNNs) with a Sliding Window Mean Absolute Deviation (SWMAD) preprocessing technique to address illumination variability and complex background conditions. Design/methodology/approach A dual-layer CNN model is developed for plant disease classification using HSV segmentation, flood-fill segmentation and SWMAD preprocessing to handle real-field variations. The model is trained on PlantVillage and real farm images and deployed via TensorFlow Lite for real-time offline detection. TensorFlow Lite is used to enable efficient on-device inference for deployment in resource-constrained environments. Findings Benchmark experiments conducted on the PlantVillage dataset achieved a classification accuracy of 99.91% under controlled conditions. On the hybrid dataset comprising PlantVillage and real-field images, the optimized CNN framework achieved a validation accuracy of 95.01% following extensive evaluation of optimizers, layer architectures and worker configurations. The integration of the proposed SWMAD preprocessing technique into the finalized architecture further improved the validation accuracy to 97.38%, demonstrating enhanced robustness and classification performance under practical agricultural conditions in the final deployed model. Originality/value The originality of this study lies in several novel contributions. First, we introduce an SWMAD-based preprocessing technique, which enhances local statistical variations in leaf images by capturing pixel-level deviations from neighborhood intensity means. Unlike, conventional preprocessing methods, SWMAD is specifically designed to handle real-field challenges such as illumination variation, noise and complex backgrounds. The improvement in validation accuracy demonstrates the effectiveness of the proposed approach in capturing more discriminative features compared to existing techniques, thereby improving overall model robustness and reliability in practical agricultural environments.
