Impact of Steady – State Genetic Algorithm and Internet – of – Things (IOT) on the Enhancement of Fall Detection System and Rehabilitation Gaming Exercises for Elderly People


  • V. Muralidharan Research Scholar, Dept. of Computer Science Government Arts College (Grade-I), (Affiliated to Bharathidasan University), Ariyalur-621713
  • V. Vijayalakshmi Assistant Professor& Head, Dept. of Computer Science, Government Arts College (Grade-I), (Affiliated to Bharathidasan University), Ariyalur-621713


SSGA, IOT, 2×2 confusion matrix, 3×3 confusion matrix, Binary classification method, MIRA, RGB


Old age is inevitable. Fall in elders is one of the important crises which leads them to severe injuries and also causes mortality sometimes to them. There is an urgent need for the development of fall detection system every - were throughout the world. There is tremendous growth in the medical field to save the elders from these disasters. Presently, IOT occupies an important place in the life of elderly people. In order to prevent the problem of fall detection in elders, we use Kinect sensor and IOT devices. Our approach in this work from different angles includes data collection, data transmission and data analysis. The performance of the rehabilitants is estimated through the ability of the performer to achieve the rehabilitation goal of the individual. While playing rehabilitation gaming exercises with the help of Kinect an IOT device, we get parametric values test 1, test 2 and test 3 of each patient through which we can calculate certain classifiers which is used for comparing the F1 – weighted average of steady state genetic algorithm with that of some of the supervised machine learning algorithms like KNN, logistic regression and MP – CNN. The proposed algorithm is applied on an UT – Kinect dataset to check its performance. We can make use of UT – Kinect dataset to recognized depth sequence. Single stationary Kinect Xbox 360 is utilized to captured videos. Each patient is asked to perform the action three times and thereby three channels are recorded. The three channels are RGB, depth and skeleton joints and are synchronized. The rate of frame is 30 f/s. In this paper, we analyze Logistic Regression and Steady – State Genetic Algorithm (SSGA). We prove in this paper, the F1 – weighted average of SSGA (84.2) is higher than other supervised machine learning algorithms like KNN (69.9), Logistic Regression (75) and MP – CNN. (78.6)   


Download data is not yet available.


J. Liang, X. Yu and H. Li, "Collaborative Energy-Efficient Moving in Internet of Things: Genetic Fuzzy Tree Versus Neural Networks," in IEEE Internet of Things Journal, vol. 6, no. 4, pp. 6070-6078, Aug. 2019.doi: 10.1109/JIoT.2018.2869910.

Z. Shen, H. Yu, L. Yu, C. Miao, Y. Chen and V. R. Lesser, "Dynamic Generation of Internet of Things Organizational Structures Through Evolutionary Computing," in IEEE Internet of Things Journal, vol. 5, no. 2, pp. 943-954, April 2018.doi: 10.1109/JIoT.2018.2795548.

Y. Zhang, P. Li and X. Wang, "Intrusion Detection for IoT Based on Improved Genetic Algorithm and Deep Belief Network," in IEEE Access, vol. 7, pp. 31711-31722, 2019. doi: 10.1109/ACCESS.2019.2903723.

B. Hussain, Q. U. Hasan, N. Javaid, M. Guizani, A. Almogren and A. Alamri, "An Innovative Heuristic Algorithm for IoT-Enabled Smart Homes for Developing Countries," in IEEE Access, vol. 6, pp. 15550- 15575, 2018. doi: 10.1109/ACCESS.2018.2809778.

H. Wang, W. Huangfu, Y. Liu, C. Gong, Y. Ren and W. Liu, "Spatial Feature Aware Genetic Algorithm of Network Base Station Configuration for Internet of Things," 2018 Sixth International Symposium on Computing and Networking Workshops (CANDARW), Takayama, 2018, pp. 53-58. doi: 10.1109/CANDARW.2018.00018.

Jorge Araque, César Peña, Gonzalo Moreno, “Synthesis for a Knee Rehabilitation Mechanism Applying Genetic Algorithms”, International Journal of Applied Engineering Research ISSN 0973-4562 Volume 13, Number 19 (2018) pp. 14451-14456, Research India Publications.

Ranadev, M. B. ., V. R. . Sheelavant, and R. L. . Chakrasali. “Predetermination of Performance Parameters of 3-Phase Induction Motor Using Numerical Technique Tools”. International Journal on Recent and Innovation Trends in Computing and Communication, vol. 10, no. 6, June 2022, pp. 63-69, doi:10.17762/ijritcc.v10i6.5628.

Junya Kusaka, Takenori Obo, Janos Botzheim, Naoyuki Kubota, “Joint angle estimation system for rehabilitation evaluation support”, 2014 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE).

Ewa Lach, “Dynamic Difficulty Adjustment for Serious Game Using Modified Evolutionary Algorithm”, International Conference on Artificial Intelligence and Soft Computing, 2017.

Garg, D. K. . (2022). Understanding the Purpose of Object Detection, Models to Detect Objects, Application Use and Benefits. International Journal on Future Revolution in Computer Science &Amp; Communication Engineering, 8(2), 01–04.

Gabriel Danciu, Iuliu Szekely, “Genetic Algorithm for Depth Images in RGB-D Cameras”, 2014 IEEE 20th International Symposium for Design and Technology in Electronic Packaging.

Kleber de O. Andrade, Thales B. Pasqual, Glauco A. P. Caurin, Marcio K. Crocomo, “Dynamic Difficulty Adjustment with Evolutionary Algorithm in Games for Rehabilitation Robotics”,

Diana Yacchirema, Jara Suárez de Puga, Carlos Palau, Manuel Esteve, “Fall detection system for elderly people using IoT and ensemble machine learning algorithm”, Personal and Ubiquitous Computing 2019.

Jamie Shotton, Andrew Blake, “Real-Time Human Pose Recognition in Parts from Single Depth Images”. Changhe Tu, Classification of Gait Anomalies from Kinect”.

Erik Acorn, Nikos Dipsis, “Sit – to – Stand Movement Recognition using Kinect.

Xavier Baro, Victor Ponce – Lopez, “Gesture and Action Recognition by Evolved Dynamic Sub gestures”.

Otsu, N.: A Threshold Selection Method from Gray-level Histograms. IEEE Transactions on Systems, Man and Cybernetics 9(1) (1979) 62-66.

Batenburg, K.J., Sijbers, J.: Adaptive thresholding of tomograms by projection distance minimization. Pattern Recognition 42(10) (2009) 2297-2305.

Batenburg, K.J., Sijbers, J.: Optimal threshold selection for tomogram segmentation by projection distance minimization. IEEE Trans. Med. Imaging 28(5) (2009) 676-686

Ahmed Cherif Megri, Sameer Hamoush, Ismail Zayd Megri, Yao Yu. (2021). Advanced Manufacturing Online STEM Education Pipeline for Early-College and High School Students. Journal of Online Engineering Education, 12(2), 01–06. Retrieved from

Barghout, L., Sheynin, J.: Real-world scene perception and perceptual organization: Lessons from computer vision. Journal of Vision 13(9) (2013) 709

Mobahi, H., Rao, S., Yang, A.Y., Sastry, S.S., Ma, Y. International Journal of Computer Vision 95(1) (2011) 86-98.

Rao, S., Mobahi, H., Yang, A.Y., Sastry, S., Ma, Y.: Natural image segmentation with adaptive texture and boundary encoding. In Zha, H., ichiro Taniguchi, R., Maybank, S.J., eds.: ACCV (1). Volume 5994 of Lecture Notes in Computer Science, Springer (2009) 135-146

Shapiro, L.G., Stockman, G.C.: Computer Vision. New Jersey, Prentice- Hall (2001).

Hermina, J. ., Karpagam, N. S. ., Deepika, P. ., Jeslet, D. S. ., & Komarasamy, D. (2022). A Novel Approach to Detect Social Distancing Among People in College Campus. International Journal of Intelligent Systems and Applications in Engineering, 10(2), 153–158. Retrieved from

Barghout, L.: Vision. Global Conceptual Context Changes Local Contrast Processing (Ph.D. Dissertation 2003). Updated to include Computer Vision Techniques. Scholars' Press (2014).

IOT device used for detecting fall in elders




How to Cite

V. . Muralidharan and V. . Vijayalakshmi, “Impact of Steady – State Genetic Algorithm and Internet – of – Things (IOT) on the Enhancement of Fall Detection System and Rehabilitation Gaming Exercises for Elderly People ”, Int J Intell Syst Appl Eng, vol. 10, no. 1s, pp. 45–55, Oct. 2022.