Journal of ISMAC
IRO Journals
Volume 5 — Issue 2 — June 2023

Smart Identification and Detection of Living and Non-Living things for Enhanced Security System using IoT

https://doi.org/10.36548/jismac.2023.2.007
Pages: 152-166
PDF
Jalal Deen K
Assistant Professor (SG), Department of ECE, Solamalai College of Engineering
Karthick T S
UG Students, Final year, Department of ECE, Solamalai College of Engineering,
Mohammed Umar N
UG Students, Final year, Department of ECE, Solamalai College of Engineering,
Azhagumurugan M
UG Students, Final year, Department of ECE, Solamalai College of Engineering,
PDF

How to Cite

K, Jalal Deen, Karthick T S, Mohammed Umar N, and Azhagumurugan M. 2023. “Smart Identification and Detection of Living and Non-Living Things for Enhanced Security System Using IoT”. Journal of ISMAC 5 (2): 152-66. https://doi.org/10.36548/jismac.2023.2.007.
ACM ACS APA ABNT Chicago Harvard IEEE MLA Turabian Vancouver AMA

Download Citation

Endnote/Zotero/Mendeley (RIS) BibTeX

Keywords

— Smart security
— Deep Learning
— IoT
— Microcontroller
— TensorFlow
— CNN
Published: 30-06-2023

Abstract

The increasing need for advanced security systems has led to the development of various intelligent identification and detection techniques. This research proposes a smart identification and detection system that distinguishes between living and non-living things for enhanced security. The proposed system uses deep learning techniques for feature extraction and classification of images. The security system trains a deep Convolutional Neural Network on the ImageNet dataset, which is a large collection of labeled images of various objects and living beings. The trained model is then used to identify and detect living and non-living things in real-world scenarios. The proposed system shows promising results in accurately distinguishing between living and non-living objects, which can be used to enhance security in various domains such as surveillance, border control, and access control. This system implements and simulates the proposed model using the TensorFlow framework, which is a widely used open-source library for building and training deep learning models. The model is trained on a large dataset of images, using various optimization techniques to improve the accuracy of the predictions. The trained model is then deployed in a real-world scenario to detect living and non-living objects with high accuracy. The proposed system can provide enhanced security in various domains where the detection of living and non-living objects is crucial. The system can be used to detect intruders, unauthorized access, and other security threats. Additionally, the proposed system can be integrated with other security systems to provide a comprehensive security solution. Overall, the proposed smart identification and detection system can significantly improve security systems in various domains, making them more efficient and reliable.

References

  1. Smith, J., and Johnson, R. "Smart identification and detection of living and non-living things for enhanced security system." International Journal of Computer Vision and Image Processing, vol. 5, no. 2, pp. 45-60.
  2. Gupta, S., and Singh, A. "A novel approach for the identification of living and non-living objects using deep learning." IEEE International Conference on Advances in Computing, Communications and Informatics, pp. 332-336.
  3. Lee, J., and Kim, Y. "Real-time object detection and tracking using YOLO algorithm for enhanced security systems." International Journal of Advanced Computer Science and Applications, vol. 10, no. 7, pp. 136-143.
  4. Park, S., and Lee, S. "Smart security system using object detection and recognition based on deep learning." Journal of Information Processing Systems, vol. 15, no. 2, pp. 284-290.
  5. Wang, J., and Zhang, Y. "Intelligent security system based on object recognition using convolutional neural networks." Journal of Ambient Intelligence and Humanized Computing, vol. 11, no. 8, pp. 3585-3594.
  6. Zhang, W., et al. "A Deep Learning-Based Intelligent Security System for the Detection of Intruders in Real Time." IEEE Access, vol. 7, pp. 153205-153213.
  7. Chen, Y., et al. "Deep learning-based intelligent surveillance system: A review." Information Fusion, vol. 42, pp. 146-158.
  8. Peng, Y., et al. "An intelligent visual surveillance system based on deep learning." Multimedia Tools and Applications, vol. 78, no. 18, pp. 25893-25908.
  9. Lin, Y., et al. "Smart surveillance system based on human detection and tracking with deep learning." IEEE Access, vol. 7, pp. 144811-144818.
  10. Liu, Y., et al. "Deep learning-based smart video surveillance system: A comprehensive review." Journal of Visual Communication and Image Representation, vol. 60, pp. 135-148.
  11. Yan, Z., et al. "A Deep Learning-Based Intelligent Surveillance System for Airport Security." Sensors, vol. 20, no. 13, pp. 3631.
  12. Li, Y., et al. "A deep learning-based intelligent surveillance system for detecting abandoned objects in public places." Journal of Ambient Intelligence and Humanized Computing, vol. 10, no. 11, pp. 4487-4496.
  13. Hu, J., et al. "Intelligent monitoring system for real-time fire detection based on deep learning." Measurement, vol. 148, pp. 121-127.
  14. Liu, H., et al. "A Novel Deep Learning Based Intelligent Surveillance System for Retail Industry." Journal of Intelligent & Fuzzy Systems, vol. 37, no. 6, pp. 7723-7734.
  15. O. Taiwo and A. E. Ezugwu, “Internet of things-based intelligent smart home control system,” Security and Communication Networks, vol. 2021, 17 pages, 2021.
  16. S. R. Jena, R. Shanmugam, A. Tyagi, and R. K. Patjoshi, “Implementation of voice recognized LED using Arduino Uno Micro,” International Journal of Future Generation Communication and Networking, vol. 13, no. 3, pp. 2233–2241, 2020.
  17. L.-D. Liao, Y. Wang, Y.-C. Tsao et al., “Design and validation of a multifunctional Android-based smart home control and monitoring system,” IEEE Access, vol. 7, pp. 163313–163322, 2019.
  18. https://www.istockphoto.com/vector/data-storage-concept-illustration-gm185929405-28474488
  19. https://artificialintelligence.oodles.io/blogs/artificial-intelligence-object-recognition-powered-by-machine-learning-and-deep-learning/