Conference Publications
Permanent URI for this collection
Browse
Recent Submissions
1 - 5 of 9
-
PublicationUnauthorized parking notification system( 2023)This paper focuses on development of an parking notification system on Raspberry Pi. In parking system, Automatic License Plate Recognition (ALPR) is becoming an increasingly practical security solution, while security and possession are the most discussed issues nowadays. However, similar systems on the market currently only focus on security, which only provides authorization at carpark entrance to prevent unauthorized personnel from entering the compound. There may be an infringement of ownership happens, where a parking lot owned by a person occupied by irresponsible car owner. Besides, although there are subscription-based services available for ALPR, but most of them are expensive due to their deeply customized high accuracy, and may be unaffordable to everyone. Most carpark systems also lack of the ability to send notification to lot owner with unauthorized vehicle information. Therefore, this study is aimed to design a system that able to check authorization at both entrance site and parking lot site, to implement an open-source solution to the system, and to equip notification ability to the system. In this study, license plate detection/localization was implemented to get the Region of Interest (ROI) from input images. License plate character recognition was then executed to perform authorization checking with database. After the authorization checking is completed, the result with relevant information will be sent as notification to parking lot owners. The performance of plate detection algorithms will be evaluated based on their accuracy. The plate detection algorithm with Haar Cascade Classifier had produced a high segmentation accuracy, which is 96.875%. Meanwhile, for the overall system accuracy (also known as OCR/plate recognition accuracy) had achieved 71.875% for Malaysian License Plate. In conclusion, a system with ALPR and notification abilities that emphasis on both security and possession is successfully developed.
4 -
PublicationSmart pandemic-safe premise system( 2023)Ensuring hygiene, limiting number of people in a closed space and adhere to normal body temperature are concerns to be living in the COVID-19 pandemic era. To date, not only software but also hardware-based works have been developed to address the concerning issue. Nevertheless, most of the works focused in one concerned issue and not many attempted to integrate into the same device. This work integrated three parts which are temperature display, automatic sanitizer dispenser, and entrance and exit with limit counter in the same device for a premise by incorporating the use of temperature, ultrasonic and infrared (IR) sensors on top of Arduino microcontroller board. The developed device buzzes when body temperature exceed 38 degree Celcius, counts people in and out in a premise and allows 20 people to enter the premises at one time and releases hand-sanitizer when hand is detected. The developed work helps to maintain health and preventing disease, especially through cleanliness and limiting number of people to promote physical distancing in a premise. On top of that, automatic sanitizer dispenser may reduce environmental pollution via reduction of sanitizer bottles. This system also reduces dependability to man-power and concurrently reduces the risk of infection to workers.
5 2 -
PublicationMulti-classification of freshness from leftover-cooked food in Malaysian foods using machine learning(AIP Publishing, 2023)The objective of this study is to implement machine learning (ML) to identify and classify the level of contamination in leftover cooked foods based on its aroma. An evaluation on the smell profiles using as a model local Malaysian lunch or evening foods that have always been stored as leftover cooked food is done in this study. To capture the data, a simple e-nose application is built and affixed to the food containers, which will accommodate four types of sensors sensitive to different gases and is programmed using the Arduino platform. To determine the aroma categorization of leftover Malaysian cuisine, samples are examined using RStudio. The results in this study demonstrated satisfactory performances by k-Nearest Neighbours (k-NN), Support Vector Machines (SVM), and Random Forest (RF) with accuracies ranging from 87.5% to 100% using the oversampling and undersampling techniques. Unfortunately, Linear Discriminant Analysis (LDA) gave poor performances (19.64% – 58.93%) in classifying the contamination level of the samples. Hence, the results obtained gave an indication that the electronic nose presented in this research was a promising for classification of contamination level for leftover cooked foods, allowing food to be better anticipated as to whether it is still edible or not.
1 8 -
PublicationFall detection system for monitoring elderly people using YOLOv7-pose detection model( 2023)The elderly population in the world is continuing to grow at an unparalleled rate and it is important to keep in mind about the safety of the aging population. Falls have become one of the major reasons leading to injury to them and if timely help is not provided, it could lead to serious complications. There are various traditional methods that have been used to detect human falls and wearable devices are one of these methods that contain sensors like accelerometer, gyroscope, barometers, etc. These devices are highly instrumental in computing various parameters based on which the fall will be detected. However, these devices have certain limitations, as they are complex for the elderly people to understand and use. The accuracy of such devices is very low and there are high chances for false alarms as well. Hence, applying a vision-based object detection algorithm for detecting these human falls is highly significant in order to overcome such challenges faced by wearable devices. In this research work, an Object detection based Automated Fall Detection System has been proposed wherein, the YOLOv7 (You Only Look Once) pose model is used to discriminate the fall and non-fall activity. Given a video, the YOLOv7 model will first distinctly separate all the video frames and then pre-process these frames. This pre-processed data is sent for estimating the pose of the person. This resulting output is further subjected to classification as fall or non-fall activity. The dataset used in our approach are self-generated videos that cover a set of daily human activities. The strength of the proposed method has been proved through various performance measures like precision and classification accuracy.
10 1 -
PublicationImmersive Technologies: A Literature Review on Brand Engagement and Consumer Behaviour( 2023)The evolution of marketing through digital means has been greatly influenced by the emergence of virtual influencers on social media and the incorporation of immersive technologies such as AR, VR, and XR. This study examines the development of virtual influencers as an emerging frontier in consumer interaction, highlighting their unique benefits compared to traditional influencers and their potential for tailored and managed brand promotion. Digital avatars provide a unique method to engage audiences, but they also present ethical dilemmas and require scientific evidence to confirm their efficacy. The methodology includes a comprehensive literature study on many aspects of digital marketing, such as the influence of immersive technologies on brand storytelling and engagement, and the significance of gamification and video-based learning in improving user interaction from 2013 to 2024. The analysis highlights a significant deficiency in existing research about the enduring impacts of these technologies on brand loyalty and consumer behaviour. The digital age requires creative marketing methods that are ethical and align with consumers' desire for authenticity and engagement. Future studies should further investigate these aspects to ensure that virtual influencers and immersive technology are used properly to cultivate significant brand connections.
8 3