Journal of Computing Research and Innovation

Prediction of River Water Quality Based on Artificial Neural Network

2024-02-01T13:25:42+00:00

In machine learning, prediction is a method that is supported by historical data and is often used in various fields. It can be used to predict quality for water taken from river, which is a major source of life particularly for human. Water contamination may be a result of civilization and the rapid increment in economy. This research looks at how the Artificial Neural Network (ANN) algorithm predicts the Water Quality Index that will aid the environmental agencies and consumers. This study also aims to create an ANN-based water quality index prediction system that is effective at managing noisy data. Furthermore, the constructed system’s ability to accurately predict water quality is assessed. The water quality prediction method is based on the data taken from the three main rivers in Selangor, namely Sungai Buloh, Langat, and Kuala Selangor. The prediction takes into account variables such as Biological Oxygen Demand (BOD), dissolve oxygen (DO) and seven other water characteristics. The performance metric used in the study is the calculation of the accuracy for factors such as the number of neurons in the hidden layer, the epoch number, the split data ratio and the learning rate. The result has shown that the ANN model has produced good and acceptable performance with 88.44% accuracy. For future work, the ANN model can be improved by collecting more data for its training and the performance of the model can be compared with other prediction algorithms.

A Movie Recommendations: A Collaborative Filtering Approach Implemented in Python

2024-04-01T07:04:51+00:00

In-home entertainment, selecting the perfect movie is a pervasive challenge, amplified by many streaming platforms like Netflix and Amazon. This study introduces a groundbreaking Movie Recommendation System with Collaborative Filtering (MRS-CF), meticulously implemented in Python. Employing Item-Based Collaborative Filtering with Cosine Similarity, the system assesses inter-movie relationships based on user-submitted titles, explicitly focusing on genre distinctions. The core contribution of MRS-CF lies in its ability to expedite the movie selection process, swiftly presenting users with a curated list of ten recommended movies strategically organised by descending similarity. Augmented with individual similarity scores, this system is crafted to optimise the user’s movie-watching experience. Thirty participants were evaluated through the Perceived Ease of Use (PEOU). The PEOU results underscore the profound contribution of MRS-CF, revealing elevated user satisfaction across all dimensions. This research illuminates the potent impact of the MRS-CF, emphasising its role as a transformative tool for refining and enhancing personalised movie recommendations.

Innovative Time and Attendance System Software Selection for a Private Hospital: Leveraging the Entropy-TOPSIS Method

2024-01-31T11:52:42+00:00

Automated time and attendance systems offer the capability to track employee attendance, calculate working days, overtime hours, and late arrivals, and generate comprehensive attendance reports, thereby improving workforce productivity. Investing in suitable time and attendance system software is crucial for a company since many businesses are adopting digital time and attendance systems that automatically collect and analyse data to increase productivity and efficiency. This decision-making process considers numerous contradictory criteria. Thus, for this study, the Multi-Criteria Decision Making (MCDM) methods, namely Entropy and Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), were used to choose the best time and attendance system software for a private hospital. There were six (6) criteria used to evaluate the time and attendance system software. The criteria were categorised as cost ease of use being compatible with existing HR software and operating system reporting capabilities customer service and scheduling capabilities Meanwhile, the alternatives are labelled as The outcomes showed that the ranking order for the criteria is while the ranking order for the alternative is respectively. In conclusion, the Entropy-TOPSIS can be used to assess and rank the alternatives.

An AI Chatbot for Personalized Music Recommendations Based on User Emotions

2024-02-15T01:52:29+00:00

Most music recommendation systems use data from users' preferences to suggest songs. Popular songs, which have more data, are usually recommended more often, possibly leaving out newer or less popular music. Thus, this study aims to apply machine learning algorithms, such as Deep Learning and Natural Language Processing, to train an AI Chatbot to recommend personalized songs based on user emotions. Firstly, deep learning is employed to predict the mood of individual songs. Subsequently, a new dataset is created based on the predicted mood of each song, which can later be fed into the chatbot to enhance its ability to make song recommendations. Next, the chatbot's intents are defined and integrated into a feed-forward neural network. User messages are analyzed using IBM Watson's natural language analysis function, which returns a sentiment score indicating either a positive, negative, or neutral sentiment. Finally, the chatbot generates a song recommendation from the dataset based on the user's sentiment score and favorite music genre. In this study, two neural network models are developed: one for predicting song moods and the other for training the chatbot. The accuracy results demonstrate that both models achieve high accuracy, scoring 80.4% for predicting song moods and 90% for training the chatbot. These results show that the models are learning effectively and can successfully recommend music based on user emotions.

The Development of an IoT-Based Air Quality Monitoring System Using the Blynk Application

2024-01-31T08:44:15+00:00

This paper discusses designing and developing an Arduino-based air quality monitoring system utilizing the Blynk application. The aim is to design an IoT-based air quality monitoring system that allows users to check current air quality precisely and promptly via their mobile phones in real-time. The construction of the application involves three phases: design, prototype development, and system testing. The design and development phases involved various setups and configurations of MQ135 gas sensor and microcontroller NodeMCU to assess air quality in parts per million (ppm) and allow data transmission via Wi-Fi to users’ mobile phones with the Blynk application. System testing has shown accurate results in the MQ135 gas sensor among five different gases, which led to the efficiency of the prototype system in detecting air quality based on air quality level (ppm). As a result, the Red LED illuminates, and the Buzzer emits a warning sound when the air pollution level exceeds 150ppm.

A Review Study of Microarray Data Classification with the Application of Dimension Reduction

2024-02-09T03:03:45+00:00

Background. The growth of gene expression or microarray data, mainly in cancer disease, has become a game changer for feature selection techniques in handling complex data. Hence, the advancement of Deoxyribonucleic acid (DNA) microarray technology has made it feasible to measure the expression level of thousands of genes with the ability to diagnose early detection. This extensive study is conducted to review and analyse literature related to applying various dimensionality reduction approaches to predict microarray data. This study is aimed for the Data Science and Medical Sciences disciplines with the goal of extending future research and broader interdisciplinary collaboration efforts.

Methods. The systematic review of this study is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines and reported in accordance with the PRISMA statement. Other than that, a systematic search is conducted using two search engines including, Scopus and Web of Science (WoS), from 2018 to 2022 by inputting the "feature extraction," "feature selection," "classification," and "microarray" as keywords. Based on the inclusion and exclusion criteria, the final articles available for review are 53 articles. Specifically, this study reports on the performance of feature selection approaches and the empirical comparisons of classification techniques used on the microarray dataset.

Results. According to the analysis, part of the included articles is mostly hybrid and novel approaches proposed for gene selection. Many novel and hybrid methods were developed to produce a good performance in terms of accuracy and computational efficiency. Moreover, the hybrid methods are proven effective in reducing dimensions and selecting relevant features. Besides, machine learning techniques are still the top interest among researchers for classification despite the emergence of deep learning approaches.

SafeSteps: A Persuasive Child Pedestrian Safety Learning Mobile Application

2024-02-01T17:03:42+00:00

This study focuses on the design, development, and evaluation of SafeSteps, a mobile application dedicated to child pedestrian safety. Employing multimedia elements, SafeSteps imparts knowledge on pedestrian safety to children, with an integrated quiz module enhancing learning activities. The project development adhered to the Waterfall Model Methodology, encompassing distinct stages of analysis, design, implementation, testing, and documentation. Guided by the principles of persuasive technology and multimedia, the application was developed using Android Studio as the Integrated Development Environment (IDE) tool. A User Experience Testing (UXT) involving 31 children aged six to twelve aimed to assess engagement, identify usability concerns, and discover areas for enhancement. Utilizing the User Experience Questionnaire (UEQ), the study gathered feedback, revealing a majority expressing a positive perception of SafeSteps in terms of attractiveness, efficiency, perspicuity, dependability, stimulation, and novelty. The UXT findings offer significant insights into user perceptions and interactions with SafeSteps. This information will be instrumental in identifying potential areas for improvement, implementing design modifications, and enhancing the overall user experience of the mobile application, emphasizing the importance of incorporating multimedia and interactive elements in child pedestrian safety interventions.

Web-Based Planner System: A User Centric Evaluation for University Community

2024-01-31T02:05:32+00:00

This study introduces a web-based planner system developed to enhance the planning and scheduling processes within the academic environment. It is due to universities grapple with manual and fragmented planning processes, leading to inefficiencies, miscommunication, and a lack of real-time updates. The Agile methodology was employed to foster adaptability and responsiveness to changing requirements throughout the development lifecycle. The research focuses on the User Acceptance Test (UAT) phase, a crucial element in ensuring the system's functionality aligns with end-user expectations. A total of 36 respondents, comprising academic staff, students, and administrative personnel from UiTM Perlis, participated in the UAT process. The study investigates user satisfaction, system usability, and overall acceptance of the web-based planner system through a series of targeted assessments and surveys. Results indicate a positive reception among users, highlighting the system's effectiveness in streamlining planning processes and improving overall user experience. The Agile methodology's iterative nature facilitated real-time adjustments based on user feedback, ensuring that the final product meets the dynamic needs of the academic community. The findings contribute valuable insights into the successful integration of Agile methodologies in web-based system development and underscore the importance of user involvement in shaping functional and user-friendly solutions. This research not only showcases the benefits of web-based but also emphasizes the significance of user acceptance testing as a critical step in delivering solutions that truly resonate with end-users.

Polycystic Ovary Syndrome (PCOS) Prediction System Using PSO-SVM

2024-02-09T02:44:54+00:00

A prevalent and complicated gynaecological condition that affects women’s reproductive health is PCOS. However, delayed diagnosis and treatment are frequently caused by a lack of understanding of its signs and symptoms. To help users and specialized physicians identify and anticipate ovarian cysts early, a PCOS prediction system integrating PSO-SVM was created to solve this issue. This study explores the application of data mining techniques, using PSO-SVM, to predict PCOS in the field of gynaecology. The dataset was taken from the Kaggle benchmark dataset, owned by Karnika Kapoor. There are 42 selected features and attributes of the PCOS dataset. The system used Python-based data preprocessing, data splitting, and PSO-SVM optimization for predicting PCOS disease. The evaluation showed that PSO-SVM with 20 particles and 100 iterations achieved the best accuracy for feature selection with an accuracy of 90.18%. The system exhibited promising predictive abilities. To enhance accuracy and user experience, future work should focus on longitudinal data integration, expert decision support, and collaboration with medical experts. The developed PSO-SVM-based PCOS prediction system significantly improves risk assessment and early identification, aiding patients, and medical practitioners. It serves as a valuable decision support tool for doctors, enabling quick and accurate diagnosis for early intervention and specialized treatment plans.

Extraction of Interaction and Physical Design Principles as Guidelines in Designing Wearable Technology for Individual with Autism

2024-02-09T06:02:45+00:00

Autism Spectrum Disorder is a neurodevelopmental condition characterized by challenges in social interaction, communication, and behavior, with each individual exhibiting unique characteristics due to the diverse symptoms and varying severity levels across the spectrum. Individuals with autism often face difficulties in behavior, communication, and interaction, occasionally leading to stress and tantrums due to their limited verbal expression of emotions. Traditional methods such as therapy and medication have not been enough to fully help individual with autism. Nowadays, technology, especially wearable technology offers promising opportunities for autism intervention. Recognizing their unique characteristics, this study aims to explore the wearable technology design principles that will cater their needs. Two common concepts which are the interaction and physical design components have been identified as essential in the designing the wearable technology for individual with autism. The extraction of the elements and design principles for both components have been done through an extensive process involving literature reviews and focus group discussions. After the validation process through an expert review survey, four key elements for each component, along with their respective design principles, are proposed by the study. The interaction design component includes navigation tools, feedback, direct manipulation, and multimedia elements, while the physical design component comprises material, screen display, safety, and portability. The proposed components, elements, and design principles outlined in this paper will serve as a valuable guideline in designing wearable technology to effectively meet the distinctive needs of individuals with autism.

Review of the Lazada application on Google Play Store: Sentiment Analysis

2024-01-29T02:27:23+00:00

Sentiment analysis is a technique for gaining meaningful insight from unstructured and unorganized textual content from multiple platforms. It is a Natural Language Processing (NLP) method that may categorize data or reviews as positive, negative, or neutral. Analyzing reviews on the internet could yield helpful, actionable insights that could be economically beneficial to vendors or other interested parties. There are various online shopping platforms due to customer demand and rely on reviews and ratings while selecting choices. However, it could be difficult to tell whether the reviews are positive, negative, or both. The objective of this research is to classify the reviews on Lazada which is one of the online shopping platforms as positive, neutral or negative sentiments and to examine the words used most frequently in Lazada users’ reviews on the Google Play Store. This research used data from 7267 reviews that were extracted from the Google Play Store between 2019 and 2022 using the Google-play-scraper Python script. The reviews have been analyzed using the Valence Aware Dictionary and Sentiment Reasoner (VADER)’s to determine whether they are positive, neutral, or negative. The results indicate that 4229 reviews are positive. There are about 2857 negative sentiments and 181 neutral sentiments. It demonstrates that more people are happy using the Lazada app between 2019 and 2022. The results also demonstrate that sentiment analysis is an effective tool for categorising and evaluating other people's reviews and feedback.

Fuzzy TOPSIS Application in Motorcycle Brand Rankings: A Preliminary Study

2024-02-02T02:45:39+00:00

Due to rapid economic growth, the demand for transportation has escalated, with cars and motorcycles being the most common personal vehicles. However, motorcycles have gained favor as a mode of transportation due to their ease of maneuvering through traffic, cost-effectiveness, and lower fuel consumption. Presently, there is a multitude of motorcycle manufacturers offering a diverse array of options. This study is focused on ascertaining the top motorcycle brand based on well-defined criteria, employing the fuzzy Technique for Order Preference by Similarity to Ideal Situation (fuzzy TOPSIS). Three expert decision makers were provided with a questionnaire to rank three motorcycle brands commonly used in Malaysia based on specific criteria: price, safety, efficiency, design, performance, and durability. Computational analyses were conducted, revealing Yamaha as the top-ranked brand with a closeness coefficient (CC) value of 0.2869, closely trailed by Honda with a CC of 0.2852. Modenas, on the other hand, ranked the lowest among the brands analyzed, with a CC of 0.1447. The marginal difference of 0.017 in CC between Yamaha and Honda suggests the highly competitive scenario between these two brands. By providing a comprehensive assessment of motorcycle brands, this study seeks to layout information of consumer preferences in decision making for motorcycle purchases. The preliminary results served as aid for manufacturers or retailers of the motorcycle market.

Topic modelling analysis of depression text message therapy: A preliminary study

2024-02-01T13:47:04+00:00

The coronavirus disease 2019 (COVID-19) that has plagued the world since 2019 has initiated several issues and challenges in the mental health services field. World Health Organisation (WHO) recommended implementing remote mental health services such as telehealth to reach out to patients. One of telehealth services is text messaging therapy. Despite the challenges in treating depression via text messaging, the text messages for depression therapy that were built with different content renders this situation as a captivating subject for study. Nonetheless, the topics included in depression mobile therapy are scarce, particularly from the short text perspective. Fortunately, a machine learning technique known as topic modelling (TM) can be used to extracts topics from a set of documents without manually reading individual documents. It is very useful in searching for topics contained in short texts. This study aims to determine the topics in the text messages sent by mental health practitioners for depression therapy. In this study, three topic modelling techniques, i.e., Biterm Topic Model (BTM), Word Network Topic Model (WNTM), and Latent Feature Dirichlet Multinomial Mixture (LFDMM), were evaluated on 258 text messages of depression therapy. The performance of the TM techniques was evaluated using classification accuracy, clustering, and coherence scores. The findings indicate that the set of text messages comprises five topics. BTM performed better than the other techniques in classification accuracy and clustering in some cases based on the performance measures. Consequently, not much significant difference was found in the coherence score between the three topic modelling.

Enhancing IoT in Education: A Comprehensive Analysis of CS110 Students’ Perceptions Towards Do-It-Yourself (DIY) Workshops at UiTM Sarawak Branch

2024-01-31T02:08:20+00:00

The Internet of Things (IoT) revolutionizes by connecting everyday things to the Internet. Its growing use in diverse sectors has spurred innovative teaching methods and tools in education. Recently, a new topic called “Basic IoT” has been added to the Digital Electronics course offered in the Diploma in Computer Science (CS110) at UiTM. Before the topic was introduced, the students rarely worked directly with hardware components and knew little about IoT. Conventional teaching methods may fall short of providing students with hands-on experience. Therefore, five (5) DIY workshop sessions were conducted to expose the students to IoT. This research aims to determine the level of students' perceptions towards the DIY IoT workshop, evaluate the difficulty level for all modules throughout the DIY IoT workshop, and assess the effectiveness of DIY workshops in learning IoT. There were 21 students who participated in the workshop, where the students were introduced to the fundamentals of the Internet of Things, the ESP32 microcontroller and the installation of Arduino IDE software, the method of lighting LEDs using ESP32, the method of connecting ESP32 to a Wi-Fi network, as well as the method of reading data from sensors and sending data to Google Sheets. Online questionnaires were disseminated at the end of the workshop, and a short interview was conducted to gain the students’ perceptions of the workshop. Data analysis was conducted in three primary phases: descriptive statistics, mean scores, and t-tests using the Statistical Package for the Social Sciences (SPSS). This study's outcome indicates that students have positive perceptions towards the DIY workshop in learning IoT (t = -9.34, p-value (0.000) < 0.05), contributing to SDG 4 (Quality Education). Hence, it offers invaluable insights into the role of experiential learning in IoT education and provides actionable recommendations for optimizing the workshop.