Page 227 - Kaleidoscope Academic Conference Proceedings 2024

Innovation and Digital Transformation for a Sustainable World

Table 4 – Appliance Control Convolutional Neural Networks," in IEEE
Transactions on Pattern Analysis and Machine
Class Label Gesture Appliance Control Intelligence, vol. 41, no. 4, pp. 956-970, 2019.
4 Light ON
[6] ITU-T J1612 “The architecture for a smart home
gateway” International Telecommunication Union
Recommendation https://www.itu.int/rec/T-REC-
5 Light OFF
J.1612-202307-I/en.

[7] ITU-T J1611 “Functional requirements for a smart
home gateway” International Telecommunication
5. CONCLUSION Union Recommendation https://www.itu.int/rec/T-
REC-J.1611-202210-I.
The proposed system culminates in a comprehensive
approach to gesture-driven smart home automation [8] Alnuaim A, Zakariah M, Hatamleh WA, Tarazi H,
leveraging IoT. Through the integration of advanced
Tripathi V, Amoatey ET. “Human-Computer
machine learning techniques such as deep learning, transfer Interaction with Hand Gesture Recognition Using
learning, and attention mechanism, the system is capable of
ResNet and MobileNet,” Comput. Intell. Neurosci.,
accurately recognizing and responding to hand gestures in Mar 26, 2022.
real-time. The proposed system architecture, modular in
design, seamlessly integrates continuous camera feed, [9] Nogales, R.E.; Benalcázar, M.E., “Hand Gesture
gesture recognition modules, and IoT, demonstrating
Recognition Using Automatic Feature Extraction
enhanced computational capabilities and efficiency. The and Deep Learning Algorithms with Memory,” Big
attention mechanism with dynamic learning rate enhances
Data and Cognitive Computing. 2023; 7(2):102.
the system's adaptability and performance, making it a potent
tool for real-world gesture recognition systems. Achieving
[10] Hand gesture Recognition Dataset
impressive testing accuracy of 98.24%, and 99.16% on train https://www.kaggle.com/datasets/aryarishabh/hand
accuracy, the system demonstrates its efficacy in real-world
-gesture-recognition-dataset (accessed March
applications. The low latency of 0.195 seconds for 20 11,2024)
consecutive predictions further emphasizes the system's real-
time responsiveness and practical utility. Overall, the [11] J. S. Peixoto, A. R. Cukla, M. A. de Souza Leite
proposed system represents a significant advancement in
Cuadros, D. Welfer and D. F. Tello Gamarra,
gesture-driven smart home automation, showcasing the "Gesture Recognition using Fast DTW and Deep
transformative potential of leveraging IoT and advanced
Learning Methods in the MSRC-12 and the NTU
computational techniques for enhancing human-computer RGB+D Databases," in IEEE Latin America
interaction in smart environments. The working model offers
Transactions, vol. 20, no. 9, pp. 2189-2195, Sept.
a practical solution for functional requirements for a smart
home gateway under ITU-T Recommendation J.1611. 2022.
[12] Ganji. N, Gandreti. S and Krishnaiah. T. R, "Home
REFERENCES
Automation Using Voice and Gesture Control,” 7th
International Conference on Communication and
[1] “Smartify-India’s Leading Home Automation
Electronics Systems (ICCES), Coimbatore, India,
Store.” Smartify . https://smartify.in/ (accessed Feb pp. 394-400, 2022.
23,2024)
[13] Kurian. B, Regi. J, John. D, P. H and Mahesh. T. Y,
[2] “Smart Home Use Case – FIBARO” Fibaro. Smart "Visual Gesture- Based Home Automation,” 3rd
Home Use Case - FIBARO Home | FIBARO
International Conference on Advances in
https://www.fibaro.com/en/smart-home-in-use/ Computing, Communication, Embedded and
(accessed March 11,2024)
Secure Systems (ACCESS), Kalady, Ernakulam,
India, pp.286-290, 2023.
[3] J. -H. Song and S. -J. Kang, "3D Hand Pose
Estimation via Graph-Based Reasoning," in IEEE
[14] L. Zhao, X. Lu, Q. Bao and M. Wang, "In-Place
Access, vol. 9, pp. 35824-35833, 2021.
Gestures Classification via Long-term Memory
Augmented Network," IEEE International
[4] Aggarwal, A., Bhutani, N., Kapur, R. et al. Real-
Symposium on Mixed and Augmented Reality
time hand gesture recognition using multiple deep (ISMAR), Singapore, Singapore, 2022, pp. 224-
learning architectures. SIViP 17, 3963–3971, 2023.
233, 2022.
[5] Ge. Le, Liang. H, Yuan. J and Thalmann. D, "Real-
Time 3D Hand Pose Estimation with 3D

– 183 –