College of Agriculture, Engineering
and Science (CAES)

Boosting Home Security

Share on facebook
Share on twitter
Share on linkedin
Share on whatsapp
Share on email

Ms Olutosin Taiwo will present on Enhanced deep learning based intelligent smart home control and security systems at the Postgraduate Research and Innovation Symposium (PRIS 2021) hosted by UKZN’s College of Agriculture, Engineering and Science (CAES).

A PhD student under the supervision of Dr Absalom E Ezugwu, she obtained her BSc in Computer Science from Olabisi Onabanjo University, Nigeria, and her MSc in Computer Science in 2017 from the Federal University of Agriculture, Abeokuta, Nigeria. Her research interest lies in the Internet of Things (IoT) with a specialisation in smart home automation.

Taiwo is investigating the use of IoT technologies and Artificial Intelligence (AI) models to solve daily problems associated with home safety, security, and healthy living. The work is novel in that it employs the walking pattern classification. ‘The research aims to design and develop a ubiquitous, cloud-based intelligent home automation system,’ explained Taiwo. These systems control, monitor and oversee the security of a home and its environment via an Android mobile application. The system consists of two modules, one that controls and monitors electrical appliances and environmental factors, and another that oversees home security by detecting motion and capturing images. An enhanced deep learning model is used to classify the features of the image captured and to determine if it is that of a regular home occupant or an intruder, before sending an alarm to the user.

‘Experimentation of our work shows that the CNN models outperform other models by yielding an accuracy of 98%,’ said Taiwo. Existing industrial products use biometrics verification such as finger printing, face detection and iris detection for authentication. IoT technology and AI is a unique way to classify detected humans or pets in the home.

Taiwo has published two conference publications and two journal articles from this work, with two further publications under review. She presented two papers at the online International Conference on Computational Science and Its Applications – ICCSA 2020. She said that she owes her academic success to her supervisor, whom she thanked for his ‘innumerable technical and professional contributions to this research.’

To learn more about Taiwo’s research as well as other CAES researchers at PRIS 2021, visit pris.ukzn.ac.za

Words: Samantha Ngcongo

Photograph: Supplied