Blinking Eyes Detection to Monitor Drowsy Drivers Due to Fatigue Using MATLAB Cascade Object Detector

Road accidents are incidents that should be avoided. One of the contributing factors of road accidents occurrence is drowsiness while driving due to fatigue. In this project, fatigue and drowsiness of a person can be detected by looking at the eye area. Drowsy situations are dangerous especially when driving a vehicle over long distances. When a person starts to feel drowsy, the eyes will start to blink more frequently. This characteristic can be used to monitor a driver’s fitness level. In this project the Viola-Jones algorithm using MATLAB cascade object detector was used to detect the presence of blinking eyes. The algorithm is consisted of three phases which are, selection of Haar-like characteristics, integrating a picture into the whole, and Classifiers in a cascading fashion. A number of 29 samples images consisting of the condition fatigue face and non-fatigue face was used. The obtained results obtained were calculated based on the accuracy value of the detected blinking eye. The result shows that both the total Area Under the Curve (AUC) values for faces with fatigue situations and non-fatigue situations are above acceptable values which is 0.5. This indicates both classifications are acceptable and can be used to detect the presence of blinking eyes which represent drowsiness.

Implementation of Long-Short Term Memory Neural Network (LSTM) for Predicting The Water Quality Parameters in Sungai Selangor

Predictions of future events must be factored into decision-making. Predictions of water quality are critical to assist authorities in making operational, management, and strategic decisions to keep the quality of water supply monitored under specific criteria. Taking advantage of the good performance of long short-term memory (LSTM) deep neural networks in time-series prediction, the purpose of this paper is to develop and train a Long-Short Term Memory (LSTM) Neural Network to predict water quality parameters in the Selangor River. The primary goal of this study is to predict five (5) water quality parameters in the Selangor River, namely Biochemical Oxygen Demand (BOD), Ammonia Nitrogen (NH3-N), Chemical Oxygen Demand (COD), pH, and Dissolved Oxygen (DO), using secondary data from different monitoring stations along the river basin. The accuracy of this method was then measured using RMSE as the forecast measure. The results show that by using the Power of Hydrogen (pH), the dataset yielded the lowest RMSE value, with a minimum of 0.2106 at station 004 and a maximum of 1.2587 at station 001. The results of the study indicate that the predicted values of the model and the actual values were in good agreement and revealed the future developing trend of water quality parameters, showing the feasibility and effectiveness of using LSTM deep neural networks to predict the quality of water parameters.

SafeSearch: Obfuscated VPN Server using Raspberry Pi for Secure Network

Virtual Private Network (VPN) is a private network that uses public network to tunnel the connection from the users’ end to the VPN server. VPN allows users to create a secure connection to another network over the public Internet. VPNs can be used to shield users’ browsing activity and encrypts data transmitted over the network to prevent sniffing attack. Nowadays, users can either pay a premium price for a good VPN service or risk their privacy using free browser-based VPN. Thus, SafeSearch is developed to address these issues in mind. With SafeSearch, users will not need to fork out a lot of money for premium VPN subscription services or expose themselves to targeted advertising when utilising free browser-based VPN. In this study, open VPN protocol was used to create the VPN server on a microcomputer called Raspberry Pi. The software used was mostly open-source except for the VPN client. Obfuscation technique was used to hide VPN traffic by disguising it as just another normal Internet traffic against Deep Packet Inspection when passing through firewall. After the VPN server was established, tests were carried out to evaluate the functionality and reliability of the VPN server in “real-world” environment. The tests conducted were network restriction penetration assessment, network performance and user acceptance test. Penetration assessment result showed that SafeSearch is capable of bypassing web filtering and deep packet inspection. Network performance during SafeSearch connection has slight latency and bandwidth decline, although it is not overly affected. The outcome of the user acceptance test was positive as the majority of participants of the study were confident that SafeSearch can secure their connection and protect their privacy when browsing the web. To conclude, both objectives of this project were fully achieved and the scope of study was followed thoroughly.

Comparison of Fuzzy Time Series and ARIMA to Forecast Tourist Arrivals to Homestay in Pahang

Predictions of future events must be incorporated into the decision-making process. For tourism demand, forecasting is very important to help directors and investors to make decisions in operational, tactical, and strategic decisions. This study focuses on forecasting performance between Fuzzy Time Series and ARIMA to forecast the tourist arrivals in homestays in Pahang. The main objective of this study is to compare and identify the best method between Fuzzy Time Series and Autoregressive Integrated Moving Average (ARIMA) in forecasting the arrival of tourists based on the secondary data of tourist arrivals to homestay in Pahang from January 2015 to December 2018. ARIMA models are flexible and widely used in time-series analysis and Fuzzy Time Series which do not need large samples and long past time series. These two methods have been compared by using the mean square error (MSE) and mean absolute percentage error (MAPE) as the forecast measures of accuracy. The results show that Fuzzy Time Series outperforms the ARIMA. The lowest value of MSE and MAPE was obtained from using the Fuzzy Time Series method at values 2192305.89 and 11.92256, respectively.

“Wiraku Suci”: A Children’s App for Learning Hygiene Practices

Hygiene care is a basic human need, but very essential practice that must be taught since childhood. Personal hygiene involves making sure body parts are clean to avoid from health issues caused by poor cleanliness. Parents ultimately bear the responsibility to teach their children about cleanliness, and normally this is done by showing and practising hygiene care themselves. Nevertheless, it is not that easy to educate personal hygiene care to them, especially in the ages of four to six years old, because they are actively playing and exploring their environments. To aid parents, mobile learning app could be employed because hygiene habits can be shown via more engaging ways such as through pictures and video clips of personal hygiene care, simple drag and drop games, and pictorial quiz. In this study, a mobile learning app with game-based approach has been developed by following the software development life cycle Spiral model. During evaluation phase, a heuristic evaluation with five Computer Science lecturers was conducted to examine the usability of the app. Results from the evaluation were used as guidance to refine and improvise the app so that they will be usable and enjoyable for children.

Network Automation using Ansible for EIGRP Network

Network automation has evolved into a solution that emphasizes efficiency in all areas. Furthermore, communication and computer networks rely on a platform that provides the necessary technological infrastructure for packet transfer through the Internet using routing protocols. The Enhanced Interior Gateway Routing Protocol (EIGRP) is a hybrid routing protocol that combines the properties of both distance-vector and link-state routing methods. The traditional technique to configure EIGRP is inefficient and requires repeated processes compared to the network automation concept. Network automation helps to assist network administrators in automating and verifying the EIGRP configuration using scripting. This paper implemented network automation using Ansible to configure EIGRP routing and advanced configuration in the GNS3 environment. This study is focused on automated scripting to configure IP Addresses to the interfaces, EIGRP routing protocol, a default static route and advanced EIGRP configurations. Ansible ran the scripting on Network Automation Docker and pushed the configurations to the routers. The network automation docker communicated with other routers via SSH. In the testing phase, the running configuration between the traditional approach and automation scripting in the Ansible playbook was compared to verify EIGRP configurations' accuracy. The findings show that Ansible has successfully deployed the configuration to the routers with no errors. Ansible can help network administrators minimized human mistakes, reduce time-consuming and enable device visibility across the network environment. Implementing EIGRP authentication and hardening process can enhance the network security level for future study.

Healthy Management of Menopause: Exploring Issues and User Requirements for Mobile Intervention

Designing and developing a mobile health intervention that focuses on menopausal symptom management and emotional support for women should be grounded by some knowledge about their problems and needs. Therefore, to gather information about the issues surrounding women in their menopausal phase, review of literatures pertaining to the topic was conducted, followed by a brief preliminary investigation (PI) using online survey method which was administered to Malaysian women for two weeks. The purpose of PI was to examine their awareness about menopause, namely its phases and symptoms management, as well as methods of information searching on menopause. Respondents were also inquired about their requirements from mobile app to support management of menopause. A total of 30 respondents answered the survey, with majority of them were between the ages of 40 and 59 years old. It was discovered that menopausal women had experienced variety of symptoms, some could be intense more often than the others, and they use diary or book to record these symptoms, which is deemed ineffective. It is imperative to help Malaysian women to manage this unavoidable phase of their lives in a more convenient approach. Therefore, a mobile app that supports symptoms management, and provides educational and motivational tips in Malay language is proposed.

Mathematical Modelling of Diet Planning Problem for Hypertension Patients

Hypertension or high blood pressure is also called a “silent killer” that may lead to serious damage to the heart and kidney. The worst case can result in sudden death. Unbalanced diets are one of the risk factors for hypertension. Previous studies have proven that diet plays a significant role in influencing hypertension patient condition. Proper planning on the selection of diets needs to be done to control food intake for this cardiovascular disease patient. This study aims to formulate a mathematical model of diet planning for hypertension patients. Specifically, this study attempts to determine the amount of nutrients need by hypertension patients, to find the cost of the food combination, and to identify the best model between linear programming and integer programming. The research model included 10 types of food groups with 200 variables based on Malaysian recipes and developed a mathematical model using two programming techniques; linear programming and integer programming. The finding showed that the solution provided by the entire programming method has met the constraints and requirements of the food group. The results from the integer programming approach would offer optimal and efficient alternatives to diet planning for patients with hypertension. It can serve as a guideline for hypertension patients on type of food to eat and the correct amount of serving to complete their nutritional plan.

Role of Effective Communication in Enhancing Leadership Skills Among Students of Bachelor of Management Mathematics in UiTM Perlis

Communication is the most important key factor for a student to lead effectively because it helps them to express their opinion. Some students are struggling to socialise with other students due to a lack of communication skills. It is important for students to have effective communication because it helps them develop their leadership skills and can also improvise their self-confidence. The purpose of this study was to identify the level of effective listening, performing tasks completely and effectively, clarity of thought and expression, and leadership skills, to assess the significant difference of demographic variables (gender, age, and semester) on effective listening, performing tasks completely and effectively, clarity of thought and expression and leadership skills, to determine the relationship between effective listening, performing tasks completely and effectively, clarity of thought and expression and leadership skills, and lastly to examine whether effective listening, performing tasks completely and effectively, clarity of thought and expression relate toward leadership skills. The random sample of 155 respondents is from the Faculty of Computer and Mathematical Science (FSKM) at UiTM Perlis. To achieve all the objectives, the researcher has chosen to apply the frequency test, the independent t-Test, the one-way ANOVA, the correlation, and regression performed by the Statistical Package for Social Sciences Version 20.0. (SPSS). Based on the findings, there is a positive relationship between the role of effective communication and leadership skills, but a great deal of determination is still needed to establish leadership criteria among undergraduates, as a few students have not been aware of the importance of leadership skills in their future careers. Moreover, the analysis shows that clarity of thought and expression are the most important roles that contribute to leadership skills. The role of effective communication in enhancing leadership skills among university students must be properly studied so that students can develop their ability to soon become major leaders.

Green Inventory Routing Problem using Hybrid Genetic Algorithm

Carbon dioxide (CO2) is known as one of the largest sources of global warming. One of the ways to curb CO2 emissions is by considering the environmental aspect in the supply chain management. This paper analyses the influence of carbon emissions on the Inventory Routing Problem (IRP). The IRP network consists of a depot, an assembly plant and multiple suppliers. The deterministic demands vary and are determined by the assembly plant. Fixed transportation cost, fuel consumption cost and inventory holding cost are used to evaluate the system’s total cost in which fuel consumption cost is determined by fuel consumption rate, distance, and fuel price. Backordering and split pick-up are not allowed. The main purpose of this study is to analyze the distribution network especially the overall costs of the supply chain by considering the CO2 emissions as well. The problem is known as Green Inventory Routing Problem (GIRP). The mixed-integer linear programming of this problem is adopted from Cheng et al. wherein this study a different Hybrid Genetic Algorithm is proposed at mutation operator. As predicted, GIRP has a higher total cost as it considered fuel consumption cost together with the transportation and inventory costs. The results showed the algorithm led to different sequences of routings considering the carbon dioxide emission in the objective function.