UTAR Institutional Repository (Universiti Tunku Abdul Rahman)
Not a member yet
6132 research outputs found
Sort by
Acoustic signal identification in an audio track
Get PDFThis project focuses on the identification and transcription of acoustic signals within audio tracks, specifically targeting multi-speaker English audio files without background noise or overlapping speech. The primary objective is to develop a standalone, local software program using Python that can reliably identify different speakers and produce transcriptions that are credited to each one without the need for an internet connection. The system employs techniques for audio signal processing, speaker diarization for segmenting the audio stream based on speaker identity, and automatic speech recognition for transcribing the spoken content, all implemented using local models and libraries. The methodology involves processing the input audio locally, applying speaker diarization to detect speaker changes and segment the audio, and subsequently transcribing each segment while associating it with the corresponding speaker, ensuring full offline operation. This project contributes to the field of audio analysis by creating a self-contained, offline-capable tool for speaker-aware acoustic signal processing and transcription in controlled environments, demonstrating the practical application of Python-based audio processing and machine learning tools that function independently of cloud services. The final output is a functional offline Python application capable of identifying speakers and generating speaker-labelled transcriptions for the specified audio constraints
Universal infrared system using Raspberry Pi
Get PDFThis project focuses on the development of a Universal Infrared System using Raspberry Pi for academic research and practical implementation in smart home environments. The aim is to provide a clear methodology and hardware design framework that demonstrates how a single-board computer can serve as a centralized controller for multiple household appliances. The Raspberry Pi, equipped with GPIO (General Purpose Input/Output) pins, is used to interact with electronic components and explore Internet of Things (IoT) applications. By integrating the open-source Linux Infrared Remote Control (LIRC) software, the Raspberry Pi functions as both an infrared signal receiver and transmitter. In order to receive IR commands from conventional remote controls, an IR receiver module is connected to the GPIO pins, while IR LED transmitters are used to send commands to the target appliances. Infrared codes from various remotes such as those for lights, fans, and humidifiers are captured, recorded, and stored. These codes can then be retrieved and transmitted via the Raspberry Pi, allowing users to control multiple devices through a single, unified platform
Incorporate machine learning in analyze amazon sales datasets to improve operational strategy
Get PDFThis project is in the field of data analytics and machine learning, focusing on developing a short-term e-commerce sales forecasting system. The problem addressed is the difficulty for online retailers to predict sales trends due to seasonality, promotion-induced peaks, and irregular demand, and thereby leading to ineffective inventory planning and operations [2][3][4][13]. In order to overcome these challenges, three prediction models were used: Bidirectional Long Short-Term Memory (BiLSTM), Temporal Convolutional Network (TCN), and XGBoost. The study was carried out following the CRISP-DM methodology, beginning with data preprocessing and feature engineering from an openly accessible Amazon sales dataset (2017–2020) [28]. The data were condensed to daily sales figures, cleaned and converted, and subsequently modeled. BiLSTM modeled nonlinear temporal dependencies using a moving average, TCN learned long- and short-term patterns using causal convolutions, and XGBoost utilized lag features, rolling statistics, and calendar effects for interpretable tree-based forecasting. The models were evaluated using four metrics: R², RMSE, MAE, and MAPE. Results indicated that BiLSTM yielded the most balanced and accurate predictions (R² = 0.8481, MAPE = 12.91%), TCN had the highest explanatory power (R² = 0.9336, MAPE=24.35%) but overestimated peaks, whereas XGBoost performed poorly (R² = 0.6586, MAPE = 70.62%) despite being interpretable. To enhance practical adoption, an interactive Streamlit dashboard was developed, enabling users to upload sales data, select models, visualize forecasts, and receive AI-driven business insights. The novelty of this work lies in the combination of cutting-edge deep learning models and a decision-support dashboard that bridges the gap between predictive modeling and actionable strategy. In short, the system produces reliable short-term forecasts and interpretable recommendations, thereby forming an effective tool for operational and strategic planning for e-commerce
Careconnect:AI-powered companion for the elderly
Get PDFThis project presents the design and development of a mobile application aimed at supporting elderly users by enhancing safety, independence, and memory health. The system integrates several core features into a single platform, including medication management, AI-powered chatbot assistance, emergency alert and caregiver connectivity, and facial recognition for memory recall. The medication module provides timely reminders with user-friendly options, while the chatbot enables natural language interaction to add, find, and manage medical records. The emergency module ensures safety by triggering alerts through a countdown system and automatically notifying registered caregivers with location details if no response is received. In addition, the facial recognition module assists elderly users in identifying familiar faces and allows new samples to be added to improve accuracy.
The application was developed in Android Studio using Room Database for local data storage and OpenAI API for chatbot interaction, with emphasis on usability and accessibility through large buttons, intuitive navigation, and clear alerts. System evaluation confirmed that all modules functioned effectively, with alarms triggering reliably, chatbot responses processed correctly, emergency notifications reaching caregivers, and facial recognition performing with satisfactory accuracy. Overall, the project demonstrates the potential of integrating AI technologies into a user-centric mobile application to promote elderly safety, strengthen caregiver connectivity, and improve quality of life
Shaping user confidence towards online banking security and safety features in Malaysia
Get PDFThe rapid growth of online banking in Malaysia has transformed the way consumers access financial services, offering greater convenience and efficiency. However, concerns about security and confidence remain key barriers to wider adoption. This research aims to investigate the factors influence user confidence towards online banking security and safety features including system reliability, user knowledge, perceived data protection and technology infrastructure in Malaysia. The study utilises Protection Motivation Theory (PMT) to explain how user knowledge and technology infrastructure affects user confidence in online banking. Besides, Technology Acceptance Model (TAM) is used in this study to explain how user confidence is impacted by system reliability and perceived data protection. The data collection method used in this research is primary data using questionnaire and received a total of 384 responses. IBM Statistical Package for the Social Sciences tool (SPSS) was used to analyse and interpret the relevant data. The data was analysed by using descriptive analysis, reliability test, multicollinearity test, Pearson correlation, normality test and Multiple Linear Regression. The results show that system reliability and perceived data protection are significantly impact with the user confidence. The study provides valuable insight for banking industry and policymakers. This study also provides recommendations for future researchers to perform more precise and accurate studies regarding this area, therefore addressing the limitations of our work. Keywords: Online Banking; User Confidence; System Reliability; User Knowledge; Perceived Data Protection; Technology Infrastructure Subject Area: HG501 - 3550 Bankin
The role of central bank digital currency (CBDC) in financial development: Comparative analysis between BRICS and G7 countries
Get PDFThis study examines the impact of Central Bank Digital Currency on financial development by comparing emerging and developed economies, specifically BRICS and G7 countries, over the period from 2012 to 2023. The analysis uses the volume of electronic money payments as a proxy for Central Bank Digital Currency adoption and considers macroeconomic variables including interest rate, inflation, unemployment, and gross domestic product growth. Financial development is measured by domestic credit to the private sector as a percentage of gross domestic product. Panel data econometric techniques are employed, with model selection guided by statistical tests and robustness checks. The findings reveal that Central Bank Digital Currency adoption significantly enhances financial development in BRICS economies, likely due to improved access to digital financial services and inclusion. In contrast, the effect is statistically insignificant in G7 countries, where mature financial systems may reduce the marginal impact of digital currency innovations. This divergence highlights the varying developmental roles of digital currencies across economic structures. The results provide valuable insights for policymakers and central banks in designing digital currency systems tailored to their countries’ economic contexts. Recommendations include integrating digital currency initiatives with broader financial inclusion and employment strategies in emerging markets and enhancing regulatory and cybersecurity frameworks in developed nations. Keywords: Central Bank Digital Currency, Financial Development, Emerging Economies, Developed Economies, BRICS, G7
Subject Area: HG201-1496 Money
Subject Area: HG1501-3550 Banking
Subject Area: HB1-3840 Economic theory. Demograph
Factors influencing the intention to invest in Malaysia environmental, social, and governance (ESG) mutual funds
Get PDFEnvironmental, Social and Governance (ESG) investing is gaining global prominence as investors seek sustainable options that align with their values while generating returns, yet Malaysian investors remain hesitant toward ESG mutual funds despite growing environmental and governance concerns. This study examines factors influencing Malaysian investors' intention to invest in ESG mutual funds using the Theory of Planned Behaviour (TPB), collecting data from 407 Malaysian adults aged 18 and above through questionnaires. The study examined relationships between environmental and societal awareness, expected returns, social influence, personal values, investment experience, fund management reputation, and financial risk level with ESG investment intention. Results indicate that fund management reputation and financial risk level significantly and positively influence ESG investment intention, while environmental and societal awareness, expected returns, social influence, personal values, and investment experience showed no significant influence. The findings suggest that fund managers, financial institutions, and policymakers should focus on management reputation and risk communication when promoting ESG mutual fund adoption among Malaysian investors.
Keywords: ESG, Mutual Fund, Investment intentions, Sustainable investing, Malaysia Subject Area: HG4530 Investment companies, Investment trusts, Mutual Fund
Investigating the intention to adopt financial robo-advisors in Malaysia
Get PDFFinancial robo-advisors (FRA) have begun to attract attention in Malaysia’s financial industry, offering users customised investment portfolios without human intervention and requiring only a minimal investment amount. However, their adoption in Malaysia has been slower compared to regional counterparts such as Singapore and Hong Kong. Therefore, this study examines the factors influencing the intention to adopt FRA in Malaysia, using the Unified Theory of Acceptance and Use of Technology (UTAUT) as the underlying research framework. The independent variables drawn from UTAUT are performance expectancy, effort expectancy, social influence, and facilitating conditions, with an additional factor of financial knowledge incorporated into the model. The study targeted individuals aged 18 to 30 across all regions of Malaysia. Data were collected via an online questionnaire and analysed using Partial Least Squares Structural Equation Modelling (PLS-SEM) with SmartPLS software. The results indicate that performance expectancy, effort expectancy, social influence, and financial knowledge significantly influence the intention to adopt FRA, whereas facilitating conditions have no significant effect. These findings provide valuable insights into the adoption intentions of young Malaysians and offer theoretical and practical implications for researchers, financial institutions, and policymakers seeking to promote the development of robo-advisors in Malaysia. Keywords: UTAUT, financial knowledge, robo-advisors, PLS-SEM, technology adoption Subject Area: HG 4621 Stockbrokers. Security dealers. Investment advisers
Bearish fears and bullish confidence: Financial awareness and technology growth reshape investment strategies in Malaysia
Get PDFWith online trading emerging as a prevailing norm, investors have gained unprecedented accessibility to investment opportunities and wealth management avenues. Malaysia’s accelerated technological development combined with the financial awareness of its population has significantly broadened the investor base, underscoring the necessity to evaluate whether these drivers have resulted in heterogeneous strategic adaptations among investors. Given that existing investors already possess established investment strategies, this study investigates how Malaysia’s technology growth and financial awareness on reshaping Malaysia’s investors’ strategies and further analyses the moderating role of market sentiment within this dynamic. This study employed purposive sampling to survey 395 existing investors which were randomly selected from three states including Selangor, Johor, and Penang. Guided by the Unified Theory of Acceptance and Use of Technology 3 (UTAUT3) and Behavioural Finance Theory, this research aims to investigate investor behaviour by examining factors such as herding effect, habit, performance expectancy, and personal innovativeness in Information Technology. Additionally, the study explores the moderating effect of market sentiment on these factors among existing investors in Malaysia. The results indicate that all four independent variables have significant direct relationships with the reshaping of investment strategies and market sentiment only significantly moderate interaction with personal innovativeness in IT. Consequently, this findings expected to provide valuable insights into behavioural patterns which may contribute and affect to more effective strategies for engaging investors within the Malaysian financial market. Keywords: Reshape investment strategies; technology growth; financial awareness; market sentiment; UTAUT3; Behavioural Finance Theory; Malaysia Subject Area: HG4001-4285 Finance management. Business finance. Corporation finance Subject Area: HM1176-1281 Social influence. Social pressure Subject Area: T58.5-58.64 Information technolog
AI-driven journalism: Examining the impact on news credibility and public trust in The Star
Get PDFThis study explores the impact of Artificial Intelligence (AI) on news credibility and public trust in The Star, a prominent Malaysian news outlet. As AI tools are increasingly employed in journalism for content creation, data analysis, and audience engagement, this research investigates their influence on the reliability of news. Employing content analysis, surveys, and interviews, the study compares AI-generated articles with human-written content to evaluate accuracy, tone, and transparency. Findings reveal that while AI enhances efficiency, public perceptions of credibility hinge on transparency and editorial oversight. Ethical concerns, such as algorithmic bias and accountability, also significantly affect trust. By addressing these challenges, the research underscores the need for responsible AI integration and clear communication strategies in journalism to maintain public confidence. This study contributes to the discourse on AI ethics in media, offering insights for news organizations and policymakers navigating this evolving landscape