Machine Learning Enhanced Predictive Accuracy and Vulnerability Assessment in Smart Systems through Device Behavior Analysis
Subject Areas : IT Strategy
Shubham Minhass
1
,
Ritu Chauhan
2
*
,
Harleen Kaur
3
1 - Amity Institute of Information Technology, Amity university, Noida, UP
2 - Amity Institute of Information Technology, Amity university, Noida, UP
3 - Jamia Hamdard, department of Computer Science
Keywords: Machine learning, predictive model, Smart Devices, Google Home Mini, Alexa, IoT,
Abstract :
The Internet of Things (IoT) is growing at a rapid pace, which has increased the demand for reliable models for efficient IoT data analysis. This study examines how well several different algorithms for machine learning perform in predicting the outputs of two popular Internet of Things devices: Alexa and the Google Home Mini. We compared the training accuracy of logistic regression, decision tree classifiers, random forests, Naïve Bayes, and KNN models to find the best fit for each device. Precisely anticipating the behavior of devices is crucial as connected equipment becomes more and more integrated into intelligent settings. Our results demonstrate notable variations in the models' prediction accuracy: When it came to predicting how both devices would behave, Naive Bayes and random forest models outperformed KNN every time. This emphasizes how crucial it is to use the best algorithm for enhancing IoT the device's efficiency forecasts. We draw attention to the wider implications for IoT applications in domains including home automation, industrial automation, and healthcare, which go beyond our direct results. Precise forecasting resulted in smarter and more effective systems, which improve daily living and production in many industries. We argue that future studies should concentrate on creating machine learning models that are more advanced and able to handle the dynamic and complicated nature of IoT data. This study lays the groundwork for increasing precision in this developing sector while offering insightful information on the function of machine learning on the Internet of Things.
[1] Bandyopadhyay, D., & Sen, J. (2011). Internet of things: Applications and challenges in technology and standardization. Wireless Personal Communications,58(1),49 69.
[2] A. Ghaffari, and A. Mahdavi, “Embedding Virtual Machines in Cloud Computing Based on Big Bang–Big Crunch Algorithm,” Journal of Information Systems and Telecommunication (JIST), vol. 28, no. 7, pp. 305-315, 2020.
[3] Gubbi, J., Buyya, R., Marusic, S., & Palaniswami, M. (2013). Internet of Things (IoT): A vision, architectural elements, and future directions. Future Generation Computer Systems, 29(7), 1645–1660. https://doi.org/10.1016/j.future.2013.01.010
[4] Han, B., Zhang, Y., Chen, S., Liu, H., & Yu, Y. (2021). Human-centric IoT: A survey. IEEE Internet of Things Journal, 8(5), 3475–3494.
[5] He, L., Huang, X., Wang, Z., & Wang, S. (2019). An IoT-based intelligent home monitoring system using deep learning. Journal of Network and Computer Applications, 126, 9–18.
[6] Nazarpour, M., & Shokouhyar, S. (2022). Detection of Attacks and Anomalies in the Internet of Things System using Neural Networks Based on Training with PSO Algorithms, Fuzzy PSO, Comparative PSO and Mutative PSO. Journal of Information Systems and Telecommunication (JIST), 4(40), 270.
[7] Islam, M. R., Islam, M. R., Islam, M. R., & Hossain, M. S. (2019). A comparative analysis of machine learning algorithms for the prediction of stock prices. International Journal of Computers and Applications, 179(23), 44–50.
[8] Tehrani, Y. H., Fazel, Z., & Atarodi, S. M. (2018). A survey of two dominant low power and long range communication technologies. Journal of Information Systems and Telecommunication, 6(2), 60-66.
[9] Kanchan, A, and Agarwal, S. (2021). Internet of Things: A comprehensive review on architecture, applications, and future directions. Journal of Ambient Intelligence and Humanized Computing, 12(1), 1087–1110.
[10] Kavitha, M., & Saranya, T. (2018). IoT-based home automation system using deep learning. International Journal of Engineering and Technology, 7(4.22), 33–36.
[11] Kim, K. H., Kim, H. G., Kim, T. J., & Kim, S. W. (2019). A survey on IoT security technologies for IoT-based smart homes. Journal of Information Processing Systems, 15(2), 256–276.
[12] Kumar, P., Sharma, S., & Kumar, A. (2019). A study on the use of machine learning algorithms in predicting credit scores. Journal of Emerging Technologies and Innovative Research, 6(4), 207–212.
[13] Kussul, E., & Baidyk, T. (2020). Satellite big data analytics for disaster management: A review. International Journal of Disaster Risk Reduction, 49, 101759.
[14] Li, X., Wang, K., & Ma, J. (2019). A survey of machine learning for big data processing. EURASIP Journal on Wireless Communications and Networking, 2019(1), 1–20.
[15] Liu, Y., & Yang, S. (2021). Internet of Things (IoT) for supply chain management: A review. International Journal of Production Research, 59(18)
[16] Mukhopadhyay, S., Sung, A. H., & Lu, S. (2021). Internet of things: Challenges, advances, and applications. CRC Press.
[17] McGrath, M. J., Hussain, M. S., & Karim, S. (2020). The Internet of things: A review of the literature and future directions. Journal of Industrial Integration and Management, 5(1), 1–23.
[18] Atzori, L., Iera, A., & Morabito, G. (2010). The Internet of things: A survey. Computer Networks, 54(15), 2787–2805. https://doi.org/10.1016/j.comnet.2010.05.010
[19] Dlay, S. S., Al-Sumaiti, S. A., & Al-Nuaimi, W. A. (2017). Internet of Things (IoT): Review of its security and privacy challenges. IEEE Access, 5, 16667–16677.
[20] Khazaei, M. (2022). Dynamic Tree-Based Routing: Applied in Wireless Sensor Network and IOT. Journal of Information Systems and Telecommunication (JIST), 3(39), 191.
[21] Suresh, A. M. Shehabeldin, and S. S. Al-Saqabi, "A Comprehensive Review on Internet of Things: Challenges and Future Directions," IEEE Access, vol. 7, pp. 68638-68659, 2019.
[22] Zandhessami, H., Alborzi, M., & Khayyatian, M. (2022). Reducing Energy Consumption in Sensor-Based Internet of Things Networks Based on Multi-Objective Optimization Algorithms. Journal of Information Systems and Telecommunication (JIST), 3(39), 180.
[23] Hamidi, H. (2016). Safe use of the internet of things for privacy enhancing. Journal of Information Systems and Telecommunication, 4(3), 145-151.
[24] Lopes, G. S., Da Silva, M. A., & Guimaraes, J. S. (2018). A survey on Internet of things: Architecture, security, and privacy. Journal of Network and Computer Applications, 108, 82–93.
[25] Fernandes, J. P., Gomes, D. A., & Khan, M. S. (2020). A comprehensive review on Internet of things: Applications, challenges, and future directions. Journal of Ambient Intelligence and Humanized Computing, 11(5), 2025–2055.
[26] Das, P. R., Pati, N. P., & Nayak, S. K. (2020). A review on the Internet of Things (IoT): Architecture, applications, security, and future directions. Journal of Network and Systems Management, 28(4), 1227–1253.
[27] Ahmed, T., Hussain, M., & Karim, S. (2019). Internet of Things (IoT) for smart agriculture: A comprehensive review. IEEE Access, 7, 139934–139951.
[28] Wang, Y., Guo, L., Li, Y., & Li, Y. A review of Internet of things.