Heuristics of Machine Learning for Home Intrusion Detection Application
Chatharajupalli Navya Sneha1, Illuri Sreenidhi2, Penke Satyanarayana3

1Chatharajupalli Navya Sneha*, Department of Electronics and Computer Engineering, KLEF, Andhra Pradesh, India.
2Illuri Sreenidhi, department of Electronics and Computer Engineering, KLEF, Andhra Pradesh, India
3Penke Satyanarayana, Department of Electronics and Computer Engineering, KLEF, Andhra Pradesh, India

Manuscript received on November 11, 2019. | Revised Manuscript received on 20 November, 2019. | Manuscript published on December 10, 2019. | PP: 2298-2301 | Volume-9 Issue-2, December 2019. | Retrieval Number: B7408129219/2019©BEIESP | DOI: 10.35940/ijitee.B7408.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Security has become a very vital role in present modern world. We need security for various applications and for our data. In particular security in home application is very crucial. So to serve this purpose in an efficient and easy manner we developed an intrusion system where in HOG (Histogram of Oriented Gradients) algorithm is used to detect person and an API to give alerts for intrusion. HOG is the Machine Learning (ML) algorithm used particularly for the person detection. The API used here is TWILIO which is the most suitable API for sending messages within seconds and accurately. Since every system is becoming automated we focused more on implementing the HOG and making the system to learn by itself and perform accurate results. In this paper we explained how HOG algorithm is implemented to detect the person entering the house and send the alerts as the person is detected. The accuracy of the model along with further developments that can be possible is given in detail. 
Keywords: Machine Learning (ML), Histogram of Oriented Gradients (HOG), Open Source Computer Vision (OpenCV), Scale-Invariant Feature Transform Descriptors (SIFT), Amazon Web Services (AWS), Global System for Mobile Communications (GSM), Support Vector Machine (SVM)
Scope of the Article: Machine Learning