Search

In the present era of the Fourth Industrial Revolution, i.e., 4IR or Industry 4.0, the digital world has witnessed enormous technological advancement. Artificial Intelligence (AI), Machine learning (ML) such as supervised learning (SL), unsupervised learning (USL), semi-supervised learning, and reinforcement learning (RL) are the most exciting recent technologies in today's world. Learning algorithms such as web search engines like Google or Yahoo, E-Mail filtering, Social Media, Airlines, E-hailing ride/price matching are the most valuable features of ML in our daily lives. The e-hailing, which is a process of ordering a cab or taxi online through a digital app, relies on machine learning to perform ride fare calculations. This paper briefly explains how e-hailing providers build dynamic pricing using reinforcement learning and associated problems in the existing pricing algorithm. Often dynamic pricing terms are unfair/discriminated pricing, and it remains controversial amongst consumers. The article discusses how supervised learning can help address pricing issues linked to the dynamic pricing algorithm's reinforcement learnings. The expected outcome of this paper is to help play a reference in creating a practical solution that can resolve pricing issues that float around dynamic pricing algorithms. [ABSTRACT FROM AUTHOR]

One of the greatest issues in the past which is the lack of available information and difficulty in finding information has ironically taken a different turn in today's context of ever increasingly available information. Within the current day and age, information has become much easier to find and acquire. However, due to the availability and access of information, a new problem arises in the form of information overload. Information overload occurs when there is too much information available, which causes a difficulty in understanding a certain topic or issue. This results in difficulty when making decisions, confusion, frustration or overall lack of motivation to further pursuing the topic or issue. This can prove to be an issue for someone who is new to a certain field or someone who lacks a clear perspective on how to continue from where they are at currently. This research aims to develop a mobile application in order to reduce information overload and tackle the issues of facing a stagnating hobby, to make it more interesting by connecting users with each other to allow for discussion and socializing. Information overload will be dealt with using machine learning algorithms in order to understand the users' grasp on their hobbies while making sure that they are able to keep up and stay interested in the hobbies [ABSTRACT FROM AUTHOR]

Fires usually occur in homes due to unattended cooking, heating equipment, and faulty wiring. Fires cause threats to the community and may cause property damages or even death. To overcome that, fires should be detected early before it even starts. With the use of IoT technology, such risks can be controlled using sensors, switches, and microcontrollers. The aim of FireCheck: A Multi-Sensor Fire Detection and Monitoring System Application for Home is to help homeowners get a reliable, early detection of a potential fire occurring at home while they are away by monitoring the changes in the environment. By using this app, not only will homeowners be able to retrieve real-time data such as temperature, presence of gas/smoke, and presence of a person, but they will also be informed of any incidents via phone call. The methodology chosen for this project is Rapid Application Development (RAD) in which iterative development and prototyping will be used to approach the development. To develop this project, the software chosen are Arduino IDE to program the microprocessor, Android Studio to develop the mobile application, Firebase to store data from the sensors, and Circuito.io to design the circuit schematics. The hardware selected are the NodeMCU as the microprocessor, thermal, smoke/gas, and infrared sensors, and lastly, the GSM module to allow the NodeMCU to make calls. The system is able to receive and display real-time data on the application from the NodeMCU. The product is divided into modules and each module's functionality has been successfully tested. There are a few improvements that can be done to this project in the future for further improvement such as acquiring higher-quality sensors and adding notification functionalities. This project is expected to increase the time for users to react to a fire emergency along with reducing the risk of losses of damage and/or lives. [ABSTRACT FROM AUTHOR]

Malaysia has high density of shopping centers in the city. One famous spot for shopping is located at Petaling Jaya. It has few famous malls within a 10-km radius in the neighbourhood. Generally, about 10 to 30 percent of the visitors drive their own vehicles to the malls. This culture leads mall operators to the situation where car park become an indispensable facility for their malls and the traffic management inside car park an important issue to be discussed with. The bad attitude of Malaysian drivers can be seen by the increase of 22% of compound issued by city council in Kuala Lumpur. The inability to find and contact vehicle's owner in case of emergency incident would negatively impact the safety of visitors and cause traffic congestion in a car park. In order to solve this issue and assist car park management, a system to provide parked vehicles' information to authorized personnel is proposed. In this proposed system, a license plate recognition application has been developed for users to retrieve vehicles' information or register new vehicles by scanning at the vehicles' plate. The application uses MobileNet Single Shot Detector (SSD) algorithm to read license plate and query for vehicles' information from Firebase using the unique combination of plate number. In this paper, MobileNet SDD is compared with other light object detection algorithms such as You Only Look Once (YOLO) and other variants of SSD for their strengths and weaknesses. The vehicles identification methods used in car park are compared to show the trend of increasing use of License Plate Recognition (LPR) systems in shopping centres. The project is an attempt to take advantage of the LPR technology trend through proposing an extension to such a system on mobile device. This helps car park operators to get the owners' information without the hassle to manually key in details at a fixed location system. [ABSTRACT FROM AUTHOR]