Technical University of Malaysia Malacca
Universiti Teknikal Malaysia Melaka (UTeM) RepositoryNot a member yet
10990 research outputs found
Sort by
Autism spectrum disorder screening using DSM-5 fulfillment and machine learning adaptation
Full text linkAutism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by persistent challenges in social communication, restricted interests, and repetitive behaviours. The prevalence of ASD has increased globally, prompting the need for more reliable, objective, and scalable screening and diagnostic methods. Traditional diagnostic tools, such as the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5), remain widely used in clinical settings. However, these tools are inherently dependent on subjective human judgment and clinician expertise, which can lead to inconsistencies in diagnosis and delayed interventions, particularly in early developmental stages. To address these limitations, this study explores a data-driven approach by integrating DSM-5 diagnostic criteria with advanced machine learning (ML) and deep learning (DL) models to enhance ASD detection and severity classification. Two datasets were employed in this research: the Autism Screening dataset, consisting of 1054 toddler data, 104 adolescence data, and 704 adult data samples, used for binary classification between ASD and non-ASD individuals; and the DSM-5 Diagnostic Dataset from Hospital Canselor Tuanku Muhriz UKM (HCTM), comprising 177 clinical samples after oversampling, used for multi-class classification of ASD severity (mild, moderate, and severe). Given the imbalance in class distribution, particularly in the severity-level dataset, oversampling techniques were implemented to improve model fairness and performance across all severity categories. The machine learning models evaluated in this study include Support Vector Machine (SVM), Decision Tree, and k-Nearest Neighbour (kNN). A Deep Neural Network (DNN) architecture was also designed and trained for comparative analysis. Model performance was assessed using standard classification metrics such as accuracy, precision, recall, and F1-score. The results demonstrate that the DNN model outperformed traditional ML models in both binary and severity-level classification tasks. Notably, the DNN achieved 100% accuracy in detecting ASD among younger children, reinforcing its potential as a tool for early screening. Furthermore, the severity classification results showed improved granularity and consistency compared to outcomes generated by manual assessments alone. This research highlights the value of integrating clinical standards with artificial intelligence to improve the speed, accuracy, and objectivity of ASD screening processes. The findings suggest that such hybrid approaches could support clinicians in making more informed decisions, reduce diagnostic delays, and enable timely interventions. Future research should explore larger and more diverse populations, refine model generalizability, address ethical considerations such as data privacy and bias, and assess real-world clinical deployment feasibility
Latent heat validation of phase change material using t-history method
Full text linkPhase change material (PCM) is a material that will absorb and release heat over a specified timeframe and it functions as a cooling technique to reduce temperature of the photovoltaic panels. The T-history method is a technique used to measure the thermal diffusivity of a material by subjecting a sample to a sudden temperature change. This project proposed PCM36 as a cooling method for PV temperature reduction and the expected result for this study is to meet the data from manufacturer with a small different percentage. T-history is introduced to validate the PCM36 latent heat capacity and melting point and thus compare it with the manufacturer data. The manufacturer data's latent heat capacity and melting point are 220 J/g and 36 ˚C, respectively. Based on the result obtained, the latent heat capacity from T-history is 217.891 J/g and is 0.9591% different compared with the manufacturer data. On the other hand, the melting point based on the T-history curve is in the range of 36 ˚C-38 ˚C, which is similar to the manufacturer data
Experimental analysis of color influence on optimized FDM parameters for PLA using the Taguchi method
Full text linkThis study examines the influence of filament color on optimizing FDM process parameters for PLA parts using the Taguchi method. Parameters such as layer thickness, print speed, and printing temperature were varied to identify optimal settings for white and black PLA filaments. The results demonstrate that the optimal parameters vary based on color: for white PLA, the best configuration involves a layer thickness of 0.35 mm, print speed of 50 mm/s, and a printing temperature of 210°C. For black PLA, the same layer thickness and print speed are optimal, but the printing temperature is lower at 200°C. Layer thickness was identified as the most significant factor affecting tensile strength across both filament types. However, the ideal printing temperature depended on the color of the filament. Notably, white PLA exhibited higher tensile strength than black PLA, with an increase ranging from 1.33% to 15.54%, attributed to the thermal properties of color pigments. These findings highlight the critical role of filament color in determining mechanical performance during FDM printing. Incorporating filament color into the optimization of FDM parameters can enhance the quality, strength, and reliability of 3D-printed components. This research provides valuable insights for improving additive manufacturing outcomes across a range of applications
Tribological effect of thermal energy on TIG arc surfacing techniques for surface modification of stainless steel
Full text linkTIG (tungsten inert gas) torch surface modification is a
unique process that can produce the surface alloying on a
work surface and effectively improve surface hardness
while altering the tribological behaviors. The significance
of this work is to examine the influence of thermal energy
on the surface characteristic of 2205 duplex stainless steel
samples. The thermal energy varied from 0.48 to 1.440
KJ/mm. The surface hardness and microstructure features
of the tribological properties of the materials were examined. Results indicate that, as thermal energy increases, the hardness value increases, thereby resulting in an increase of tribological properties. However, at higher thermal energy of 1.440 KJ/mm, the modified surface exhibits cracking in the melt layer. The microstructure transformed into different populations of dendritic structures. The best thermal energy obtained was 0.768 KJ/mm that resulted in the lowest wear rate of 3.0 x 10-4 mm3/Nm and friction coefficient of 0.43. High hardness of the surface modification and increased
tribological behavior were linked to higher levels of arc
energy during TIG melting process
Probing defect formation in sulfur-annealed graphene for TMDC integration
Full text linkThe integration of graphene with other 2D materials has been extensively studied over the past decade to realize high-performance devices unattainable with single materials. Graphene-transition metal dichalcogenides (TMDCs) such as MoS2, WS2, MoSe2, and WSe2 vertical heterostructures have demonstrated promise in numerous electronic and optoelectronic applications due to the wide bandgap range and strong light–matter interaction in TMDCs, and the ability to form electrostatically tunable junctions with graphene. However, conventional methods for TMDCs growth, including chemical vapor deposition (CVD), electrodeposition, and atomic layer deposition (ALD), require high temperatures, which can degrade graphene's electrical and structural properties. Here, we investigate the impact of sulfur annealing on graphene, revealing significant etching and electrical degradation. Density functional theory (DFT) calculations identify the divacancy defect with two sulfur adatoms (DV-2S) and C–S–C bonds as the dominant defect, differing from the previously reported monovacancy with one sulfur adatom (MV-1S). This defect induces p-doping in graphene, consistent with experimental observations. To address these challenges, we introduce a protective strategy utilizing self-assembled monolayers (SAMs) during annealing, enabling the growth of high-quality WS2 on graphene via electrodeposition. Our findings provide a foundation for integrating TMDCs with graphene while preserving its properties, advancing high-performance electronic and optoelectronic applications
Multi-modal biometric authentication system using score fusion techniques
Full text linkBiometric as an advanced access control method, however, the security can be enhanced through combination of more than one biometric element into one system. This study investigates the enhancement of security in access control systems by implementing a multi-modal biometric authentication system. It explores three biometric combinations: face and fingerprint, face and iris, and fingerprint and iris by using datasets from the CASIA database. The methodology includes biometric image preprocessing, feature extraction using DeepFace (for face), minutiae points (for fingerprints), and Gabor filters (for iris), followed by score-level fusion using weighted average techniques. Experimental analysis reveals that the face-fingerprint combination achieves the highest accuracy of 90.8%, followed by face-iris at 88.8%, outperforming unimodal systems. These results demonstrate the advantage of combining biometric traits for a more reliable and secure authentication system, contributing to the advancement of biometric security technologies
A digital signature on cubic Pell Cryptosystem CP256-1299
Full text linkElliptic curves have proven to be a suitable foundation for cryptosystems, with Elliptic Curve Cryptosystems (ECC) offering strong security with smaller key sizes. Recent advancements in ECC design aim to create more efficient and secure curves. In this paper, we introduce a new digital signature scheme, named CP256-1299. It is a 256-bit scheme based on a cubic Pell curve where the arithmetic operations are efficient and straightforward. In previous works, cubic Pell curves have been used to design public key cryptosystems. Our main motivation in proposing the new digital signature algorithm is to exploit the effectiveness of the arithmetic of cubic Pell curves, while maintaining reasonable keys and high security. We compare our new scheme to three widely-used digital signature algorithms based on ECC, namely ED25519, SECP256K1 and SECP256R1. It turns out that our cubic Pell curve based digital signature algorithm is designed to operate with a larger periodic order while maintaining at least similar computational requirements to most popular elliptic curve cryptosystems. Our new scheme is also suitable to support a central bank digital currency
Building power demand and energy consumption forecasting using a data-driven model: A case study in a student hostel
No full textAccurate forecasting of building power demand and energy consumption is essential for optimizing energy usage, improving efficiency, reducing costs, and ensuring sustainability. However, this prediction process is challenging due to factors such as variable occupancy, unpredictable occupant behavior, seasonal weather changes, data limitations, complex system interactions, and other external influences. This study develops a data-driven model based on historical electrical power data to predict the power demand and energy consumption of a student hostel. The historical data, recorded at five-minute intervals, was collected by logging the main incoming power supply using a power quality analyzer at the main switch block. Based on the power profile, the model was developed for four distinct time frames: falling, baseload, rising, and peak-load periods. Two key independent variables - minutes past midnight and type of day (weekday or weekend)—were considered as primary influences on power demand. Unlike previous models, this study employed MATLAB programming to optimize correlation modeling using the statistical approach of the power-law function. Results indicate that eighth- to ninth-degree polynomial fits provide the best power forecasting, achieving R² values as high as 0.9989. However, the prediction of power demand and energy consumption during peak-load periods on weekends was more complex, with a power correlation R² value of just 0.6100. Model accuracy assessments across different time frames and days showed that the developed model could predict power demand and energy consumption with a deviation of less than 5% compared to actual measurements. These findings demonstrate that a predictive model using only two independent variables, a power-law function, and polynomial fits up to the eighth and ninth degrees can effectively forecast power demand and energy consumption of the hostel. This model is expected to be valuable for future demand response (DR) programs, supporting the analysis of DR initiatives and the optimization of energy efficiency strategies. Future research could explore the integration of additional significant parameters alongside machine learning techniques to further enhance model accuracy. Factors such as outdoor air temperature, examination days, and a more detailed occupancy rate could be investigated and incorporated into future model development. This would allow for a more comprehensive evaluation of various energy consumption scenarios and their potential impact
Halal principle and operational performance of MSMEs industries: Mediating role of lean six sigma and sustainability
No full textImproving operational performance in MSMEs within Indonesia’s poultry industry is crucial, given the sector’s significant contribution to the national economy. However, it continues to face challenges related to Halal Principles (HP), process inefficiencies, quality issues, low product innovation, and adverse environmental and social impacts that may hinder economic growth. This study investigates the influence of HP on Operational Performance (OP), with Lean Six Sigma (LSS) and Sustainability (S) as mediating variables, in the context of Indonesia's poultry industry. Data from 249 randomly selected respondents were analyzed using Structural Equation Modelling (SEM) with IBM SPSS AMOS version 24.0. The results reveal that HP significantly affects both OP and S. LSS was found to have a direct impact on OP and partially mediates the relationship between HP and OP. Similarly, S directly influences OP and acts as a partial mediator between HP and OP, as well as between LSS and OP. The novelty of this study lies in the development of an inductive model, termed the Halal Lean Six Sigma Model (HLSSM), which theoretically connects HP, LSS, S, and OP. The findings confirm that HP, along with LSS and S, are key influencers of OP. These insights can guide MSME management in Indonesia’s poultry sector to strategically address the interrelationships among HP, LSS, and S to enhance operational performance
Regulator insight on the establishment of socialbased healthcare institutions in Malaysia
Full text linkSocial innovation is gaining significant recognition in research and policy domains, including within the healthcare sector. Institutions based on trade and business principles have accumulated social capital to pursue social objectives. However, the sustainability of these social-based healthcare institutions remains uncertain. Regulatory insights are essential for the development and maintenance of these institutions in the future. This qualitative study aims to explore and understand the perspective of the Division of Medical Practice and Private Services (CKAPS) on the establishment and sustainability of social-based healthcare institutions. Consequently, primary data were collected through interviews with officers at the CKPAS, while secondary data were obtained from documentary analysis of Act 586 and related documents. The transcripts were analyzed inductively using NVivo software, with codes and themes developed based on a preestablished conceptual framework. The
findings reveal no definitional distinction between social-based and profit-based private healthcare providers.
Both types of institutions are governed by Act 586 and its subsidiary regulations regarding establishment, maintenance, and licensing. Practically, social-based healthcare can be identified through 1) self-declaration, 2) documents such as tax exemption letter from LHDN or the National Audit Department, and 3) information from the public. To ensure sustainability, social-based healthcare institutions must adhere to the principles outlined in Act 586, which emphasize comprehensive planning and robust proposals. Healthcare quality is the top priority and should not be forgotten to reduce the cost of healthcare in an attempt to serve the poor. Thus, these institutions need to be financially, socially, and environmentally sustainable, managed by qualified and
experienced leadership teams. The key critical contribution of this study is that it presents new evidence regarding the impacts of government policies towards the establishment and sustainability of social-based healthcare institutions