Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{163359,
        author = {Abhishek kumar  and Sneha singh  and Sandeep Kumar},
        title = {ANOMALOUS EVENT DETECTION USING LSTM METHODOLOGY},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {10},
        number = {11},
        pages = {885-894},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=163359},
        abstract = {Anomaly detection is a significant issue that has been studied in a variety of study fields and application domains. It refers to the extraordinary occurrences, events, or observations that significantly deviate from the majority of the data and do not fit into a predetermined description of typical behavior. Anomalous events may be categorized as, driving vehicles on footpath, people running on road, snatching people’s purse in public, etc. Such events need to be reported immediately in fear of getting too late to report such events if they become a big issue in future. Wide-spread uses for anomaly detection include military surveillance for enemy activities, insurance, or healthcare, detecting intrusions to improve cyber security, identifying faults in safety-critical systems, and fraud detection for credit cards, insurance, or healthcare. The process of anomaly identification can be challenging when applied to the analysis of event sequence data because the sequential and temporal character of such data gives rise to a variety of definitions and adaptable types of abnormalities. This in turn makes it more challenging to interpret abnormalities that are discovered.
However, this paper outlines an effective strategy for spotting irregularities in videos. Recent convolutional neural network applications, particularly in image recognition, have shown promise for convolutional layers. Contrarily, convolutional neural networks require labels as learning signals and are under supervision. Spatiotemporal architecture is thereby put forth for finding anomalies in films with packed situations. The two key parts of our architecture are one for representing spatial information and the other for understanding how the spatial features change over time. After the analysis of the anomalies, the conclusion of the test if the any abnormal event is detected is sent to nearby police station with fraction of seconds. So, if there is an inappropriate action then the police can take action in time. },
        keywords = {Anomaly, Anomalous events, abnormalities, convolutional neural network, spatiotemporal architecture.},
        month = {},
        }