This paper presents a novel deep learning-based approach for anomaly detection in surveillance films. A deep network that has been trained to recognize objects and human activity in movies forms the foundation of the suggested approach. In order to detect anomalies in surveillance films, the proposed method combines the strengths of 3D-convolutional neural network (3DCNN) and convolutional long short-term memory (ConvLSTM). From the video frames, the 3DCNN is utilized to extract spatiotemporal features,while ConvLSTM is employed to record temporal relationships between frames. The technique was evaluated on five large-scale datasets from the actual world (UCFCrime, XDViolence, UBIFights, CCTVFights, UCF101) that had both indoor and outdoor video clips as well as synthetic datasets with a range of object shapes, sizes, and behaviors. The results further demonstrate that combining 3DCNN with ConvLSTM can increase precision and reduce false positives, achieving a high accuracy and area under the receiver operating characteristic-area under the curve (ROC-AUC) in both indoor and outdoor scenarios when compared to cuttingedge techniques mentioned in the comparison.
1 June 2024 in International Journal of Theoretical and Applied Research
The scientific community is paying more attention to the highly developed field of anomaly detection in video surveillance. Intelligent systems that can automatically spot unusual events in streaming videos are in high demand. This survey article gives a thorough summary of the several methods for spotting irregularities in surveillance videos. Both conventional methods—such as statistical modeling and motion analysis—and more current strategies—such as deep learning and artificial intelligence—are included in these methodologies. The study also identifies each technique's advantages and disadvantages as well as prospective uses in real-world situations. It also covers the difficulties in developing efficient anomaly detection algorithms for surveillance movies and points out potential future research topics. Overall, it is a useful tool for academics and professionals involved in the study of violent behavior detection (VioBD). It proposes a road map for future research on anomaly identification in surveillance films and provides insights into the state of the field now. To ensure the best possible performance of the anomaly detection system, it is crucial to keep in mind that the success of anomaly identification in surveillance videos significantly depends on the availability and quality of training data. As a result, future studies should concentrate on creating reliable feature extraction methods and enhancing the readability of anomaly detection models. The survey also says that in order for large-scale video data to be used in real-world applications that use anomaly detection systems, future studies should look into new ways to make these systems more scalable and effective.
Federated Learning (FL) is a privacy-focused technique for training models; however, most existing unlearning techniques in FL fall significantly short of the efficiency and situational awareness required by the GDPR. The paper introduces two new unlearning methods: EG-FedUnlearn, a gradient-based technique that eliminates the effect of specific target clients without retraining, and OFU-Ontology, an ontology-based approach that ranks data importance to facilitate forgetting contextually. EG-FedUnlearn directly eliminates the contributions of specific target data by reversing the gradient, whereas OFU-Ontology utilizes semantic relevance to prioritize forgetting data of the least importance, thereby minimizing the unlearning-induced degradation of models. The results of experiments on seven benchmark datasets demonstrate the good performance of both algorithms. OFU-Ontology yields 98% accuracy of unlearning while maintaining high model utility with very limited accuracy loss under class-based deletion on MNIST (e.g., 95%), surpassing FedEraser and VeriFi on the multiple metrics of residual influence, communication overhead, and computational cost. These results indicate that the cooperation of efficient unlearning algorithms with semantic reasoning, minimized unlearning costs, and operational performance in a distributed environment. This paper becomes the first to incorporate ontological knowledge into federated unlearning, thereby opening new avenues for scalable and intelligent private machine learning systems.
This research introduces a novel deep learning-based approach for anomaly identification in surveillance films. The suggested approach is built on a deep network that has been taught to recognise objects and human activity in films. The technique was evaluated on five large-scale datasets from the real world, including UCF-Crime, XD-Violence, UBI-Fights, and CCTV-Fights, UCF-101, as well as on artificial datasets with various object sizes, appearances, and activity types. We extract features from video frames using a 3D-convolutional neural network (3D-CNN), followed by convolutional short-term memory (ConvLSTM), and then conduct classification and recognition based on these characteristics. The results demonstrate that, when compared to state-of-the-art approaches described in the comparison, the suggested method achieves high accuracy and AUC in both indoor and outdoor scenarios..
1 August 2023 in International Journal of Electrical and Computer Engineering (IJECE)
In last decade, numerous meta-heuristic algorithms have been proposed for dealing the complexity and difficulty of numerical optimization problems in the realworld which is growing continuously recently, but only a few algorithms have caught researchers’ attention. In this study, a new swarm-based meta-heuristic algorithm called Rhizostoma optimization algorithm (ROA) is proposed for solving the optimization problems based on simulating the social movement of Rhizostoma octopus (barrel jellyfish) in the ocean. ROA is intended to mitigate the two optimization problems of trapping in local optima and slow convergence. ROA is proposed with three different movement strategies (simulated annealing (SA), fast simulated annealing (FSA), and Levy walk (LW)) and tested with 23 standard mathematical benchmark functions, two classical engineering problems, and various real-world datasets including three widely used datasets to predict the students’ performance. Comparing the ROA algorithm with the latest meta-heuristic optimization algorithms and a recent published research proves that ROA is a very competitive algorithm with a high ability in optimization performance with respect to local optima avoidance, the speed of convergence and the exploration/exploitation balance rate, as it is effectively applicable for performing optimization tasks.
Early and accurate date palm disease detection is the key to successful smart farming ecosystem sustainability. In this paper, we introduce DoST-DPD, a new Dual-Stream Transformer architecture for multimodal disease diagnosis utilizing RGB, thermal and NIR imaging. In contrast with standard deep learning approaches, our model receives ontology-based semantic supervision (via per-dataset OWL ontologies), enabling knowledge injection via SPARQL-driven reasoning during training. This structured knowledge layer not only improves multimodal feature correspondence but also restricts label consistency for improving generalization performance, particularly in early disease diagnosis. We tested our proposed method on a comprehensive set of five benchmarks (PlantVillage, PlantDoc, Figshare, Mendeley, and Kaggle Date Palm) together with domain-specific ontologies. An ablation study validates the effectiveness of incorporating ontology supervision, consistently improving the performance across Accuracy, Precision, Recall, F1-Score and AUC. We achieve state-of-the-art performance over five widely recognized baselines (PlantXViT, Multi-ViT, ERCP-Net, andResNet), with our model DoST-DPD achieving the highest Accuracy of 99.3% and AUC of 98.2% on the PlantVillage dataset. In addition, ontology-driven attention maps and semantic consistency contributed to high interpretability and robustness in multiple crop and imaging modalities. Results: This work presents a scalable roadmap for ontology-integrated AI systems in agriculture and illustrates how structured semantic reasoning can directly benefit multimodal plant disease detection systems. The proposed model demonstrates competitive performance across multiple datasets and highlights the unique advantage of integrating ontology-guided supervision in multimodal crop disease detection.