Repository@USM

Welcome to closed access digital repository of Universiti Sains Malaysia (USM).

This repository contains multiple types of scholarly materials, especially USM theses and exam papers.

To access the full text, please log in with your USM email account.

Photo by @clarissemeyer

Research outputs

4170

Projects

People

Recent Additions

Fault detection of electrical motor based on thermal imaging and machine learning
(2023-08)
Yap, Jun Hong
Faults could occur on electrical motor due to various reasons, and an early motor fault detection system helps prevent interruption in service and financial losses. However, the current practice of manual fault inspection and preventive maintenance is time consuming, and it may not be effective. Thus, motor fault diagnosis using thermal imaging technique has been on the rise in recent years. To further improve the effectiveness and to automate fault detection using thermal imaging, artificial intelligence (AI) can be employed. Hence, in this project, an electrical motor fault detection system based on thermal imaging and machine learning (ML) technique was developed. Transfer learning (TL) approach using pre-trained convolutional neural networks (CNNs) was used. The CNN was trained to learn the features extracted from the thermal images of a faulty and a healthy motor and use them to diagnose the condition of the motor. Various hyperparameters were configured for network training to obtain the best results. Furthermore, performance analysis was conducted and discussed to evaluate the credibility and reliability of the trained network. A Graphical User Interface (GUI) was then created to ease the user in using the proposed fault detection system by just supplying the thermal images of a test motor to the GUI application for fault diagnosis. The evaluation results showed that GoogLeNet gives the best detection performance with both the mini-batch and the validation accuracy achieving a 100%, and both the losses were low as well, at 0.0015 and 0.0001 respectively. Thus, the final trained network based on GoogLeNet was used in the GUI for the implementation of the proposed motor fault detection system. In conclusion, the aim for implementing a fault detection system and GUI, through the use of thermal images and machine learning was achieved.
Explainable artificial intelligence for signature verification system
(2023-10)
Lee, Sze Yuan
In recent years, the use of personal identity, such as signatures, as a means of authentication has gained significant attention. There are some concerns arise due to the potential for signature forgery and leading to the development of signature verification systems to determine the authenticity of signatures. The lack of understanding behind the AI and DL can erode trust in the tools as incorrect or biased decisions made. The application of Explainable Artificial Intelligence (XAI) methods in signature verification systems can address these concerns by providing insights into the decision-making process and enhancing the trustworthiness and reliability of the system. This research aims to explore and evaluate various explanation models to improve the interpretability and performance of signature verification systems. Furthermore, this research seeks to identify the specific aspects that users and developers focus on when considering explanations generated by these models. Moreover, this research aims to develop a new explanation model by combining the strengths of two widely used methods, LIME and Grad-CAM. The experiment is conducted through MATLAB using package known as Deep Learning Toolbox. The explanation evaluates through the respond of 18 respondents in four aspects, understandability, interpretability, accuracy and usefulness. The survey is also used to identify the evaluation aspect that are focused by users and developers. In addition, a new explanation model is developed through the combination of “scoremap” of LIME and Grad-CAM. Preliminary findings indicate that the Grad-CAM method demonstrates better performance from the user's perspective, while developers tend to prefer the LIME method. By leveraging the strengths of both approaches, the new explanation model achieves an impressive increase in understandability, interpretability, accuracy, and usefulness.
Evaluation of isolated type multilevel inverter with different DC source selection scheme
(2023-07)
Ooi, Wei Tao
Multilevel inverters (MLI) play a major role in various power applications in converting direct current to alternating current for a power system. The ideal output voltage waveform should be a perfect sine wave. In practical, a real inverter will produce output voltage waveform which contains harmonics that are not acceptable for high power applications. Harmonics cause current and voltage waveforms to be distorted, resulting in power system degradation. To date, reducing the total harmonics distortion (THD) is always the main objective to conduct the research regarding the multilevel inverters, especially when the inverters are applied in renewable energy application. Therefore, the simulation testing of this project will focus on the total harmonic distortion value of the system. The proposed multilevel inverter in this research is asymmetrical multilevel inverter with trinary sequence. The targeted number of output levels are 5-L, 7-L and 9-L. This research is aimed to analyze the proposed topologies from the aspects of inverter power ratio, total harmonic distortion level and power contribution of DC voltage source in different DC source scheme. The switching signals are generated using a low frequency modulation technique where the switching angles are pre-calculated using derived mathematical equations. To evaluate the performance of the topology, linear load tests are conducted to ensure proper operation of the proposed topology in reference to theoretical analysis with MATLAB Simulink software. Based on simulation result, the THD values of the 5-L waveforms are the highest, followed by the 7-L waveforms and the lowest THD are measured on the 9-L waveforms. Under RL loads, the current waveforms show much lower THD readings since they are filtered by the inductive loads. The RL filtering effect causes the current waveforms to lost the stepped pattern which explains their smoother waveforms. The results show the high power ratio is averagely achieving 95% and above, indicating the reliability of the system. From DC source power contribution aspect, it is concluded that high power source is required to produce higher number of levels in MLI inverter. In short, the research outcome shows the topology with different DC source configuration is capable of generating high number of output levels with low number of total components. The individual current harmonics are also in accordance to the IEC/EN 61000-3-2 standard. Hence, this topology has great potential to be developed for real applications since the production cost is expected to be lower than the other topologies.
Evaluation of conventional and modified hill climbing mppt algorithms
(2023-08)
Siti Khadijah binti Shamsulkamal
The conventional perturb and observe (P&O) algorithm, one of the methods of Hill Climbing maximum power point tracking (MPPT), is well-liked due to its simplicity of implementation. Nonetheless, conventional P&O has limitations because of power oscillations in the steady state and poor tracking of MPP with inadequate choices of perturbation step size and tracking time. Additionally, even after achieving a steady state, continual perturbations still result in wasteful power oscillations. On the other hand, a significant study has been conducted on the P&O MPPT methods for enhancing the overall effectiveness of solar photovoltaic (PV) systems. In this paper, an evaluation of the conventional and the recently published modified P&O hill climbing MPPT algorithm approaches is proposed to solve these drawbacks of the conventional P&O algorithm. By modelling the three algorithms in MATLAB Simulink and comparing their performance to that of the conventional P&O algorithm, the effectiveness of the three-enhanced method has been confirmed. It can be seen that the Modified 1 P&O method surpasses the Modified 2 and 3 P&O MPPT methods as well as conventional P&O. The Modified 1 P&O algorithm is the most effective way to lower steady-state oscillation since it has a low average input power ripple (0.19336%) and the lowest average output voltage ripple (0.05602%). In comparison to other approaches, it also offers the fastest simulation time, the shortest tracking time, and the highest MPPT efficiency (99.97%).
Enabling data visualization through an iot and cloud-based monitoring platform
(2023-08)
Muhammad Danial bin Mahamad Farizan
IoT represents the integration of multiple technologies, such as cybersecurity, cloud computing, big data, and artificial intelligence. The IoT enables connection between each device and sensors. The implementation of IoT technologies can lead to increase productivity and efficiency. This project aims to explore the use of IoT technologies with the development of a cloud-based IoT platform for data visualization. The cloud-based platform is designed to improve the efficiency of the IoT technologies at an affordable cost. The platform will allow the user to monitor data and receive a notification based on the data received from the device

Most viewed

Growth Of Single-Walled Carbon Nanotubes Through Pengethanol Colloidal Solution
(2011-10)
Seah, Choon Ming
Since the discovery of carbon nanotubes (CNTs), powder form catalyst support becomes the dominant in this field. But powder form catalyst support possesses some shortcoming such as difficulty in catalyst size monitoring and required subsequent purification. In this study, CNTs were grown over iron nanoparticles prepared by spin coated iron nitrate that diluted in colloidal solution of absolute ethanol and polyethylene glycol (PEG). The colloidal solution was later spin coated on silicon wafer and through catalytic chemical vapor deposition (CCVD) to grow CNTs. This approach competently overcomes the shortcomings aforementioned. In order to understand the effects of various process parameters on the topography of iron nanoparticles obtained and morphology of the as-grown CNTs, all the process parameters were studied separately. The parametric study was done in three stages, representing colloidal solution (composition of colloidal solution and concentration of iron nitrate), spin coating (spin speed, angular acceleration and spin period) and CCVD (reaction temperature, methane partial pressure and reaction period) study. Iron nitrate with concentration of 40mmol/L diluted in colloidal solution at a ratio 1:1 (v/v) of absolute ethanol to PEG-400, spin coated on silicon wafer at 8000 rpm for 30 seconds and under angular acceleration of 300rpm/sec was the best parameter to distribute iron nanoparticles evenly and in small size. This catalyst sample could grow single-walled CNTs (SWCNTs) with the highest selectivity and uniformity in diameter. Piranha solution was found useful to render the hyrophobicity of silicon oxide by introducing –OH group on the wafer. The –OH group was found could form a weak bond with PEG, providing force to reduce the surface tension. This led to the formation of catalyst nanoparticles of more uniform distribution. In CCVD, the best operating parameter to growth SWCNTs with highest uniformity and selectivity was at 850ºC under methane partial pressure of 0.333atm for 30 minutes. All three parameters were crucial to synthesize SWCNTs with high selectivity and crystallinity. The ratio of pre-growth catalyst size to the SWCNTs diameter was 2.3, while the ratio decreased to 1.38 for post growth catalyst used for comparison. Bigger the average size of catalyst nanoparticle resulted CNTs with wider distribution of diameter and also higher the ratio between the average catalyst nanoprticles to CNTs diameter. Finally, the crystallographic structure of the catalyst was also demonstrated as well. The iron nanoparticle was found to be converted to iron carbide after the growth of CNTs. The crystal structure was uniform throughout the whole catalyst particles. The decomposition of carbon sources on the surface of the iron and the dissolved carbon might diffuse to the center of the catalyst to achieve supersaturation and started the nucleation of CNTs. This work has successfully demonstrated a simple, novel and cost effective route to synthesize SWCNTs with high quality.
Equivalent diagonal strut coupled with hybrid plasticity approach for seismic response macro-modelling of clay brick wall infilled frames
(2020-11-01)
Van, Tze Che
Interaction between reinforced concrete frames and masonry infills under seismic load in Malaysia is often being overlooked by engineers and experts due to the low occurrence and magnitude of earthquake and scarcity of established research studies in the related area. Moreover, no guidance is given by Eurocode 6 and Eurocode 8 on macro-modelling approach of the seismic response of infilled frame. This study aims to provide an in-depth understanding on the seismic behaviour of masonry infilled reinforced concrete frames in Malaysia and to propose macro-modelling for masonry infilled frame through equivalent diagonal strut coupled with hybrid plasticity approach. Under the experimental testing, six half scale single-storey single-bay reinforced concrete frames with and without unreinforced clay brick infills were subjected to lateral monotonic and cyclic loadings. The seismic behaviour of the frame system improved in terms of strength, initial stiffness, energy dissipation and also delay in cracks formation in frame due to the presence of infill. However, the adopted masonry wall system is considered strong, thus induces shear failure in columns. It is discovered that effect of aspect ratio of infilled frame is significant in energy dissipation. Macro-Modelling of masonry infilled reinforced concrete frames using equivalent diagonal strut coupled with hybrid plasticity approach and an improved constitutive backbone law shows good correspondence with experimental result. Under the investigation of reliability of seven equivalent diagonal strut width models using the improved constitutive backbone law, it is discovered that models with similar strut width trends over aspect ratio produce similar responses. All the strut models are able to produce response with reasonable accuracy except Mainstone (1974) model. Seismic performance of a five-storey non-ductile masonry infilled reinforced concrete frames typically found in Malaysia was assessed using incremental dynamic analysis (IDA) with ten ground motion records. The collapse capacity at 16%, 50% and 84% fractiles of IDA curves are 1.0, 1.53 and 2.03, respectively. The maximum drift ratio where dynamic instability is reached ranges between 0.1% to 0.26%. This study has provided a practical elucidation of the interaction between infill and frame for the development of more realistic seismic-resistant design for Malaysia.
The Effects Of Bacillus And Lactobacillus As Probiotics On Mud Crab Scylla Paramamosain (Estampador, 1949) Zoea Larval Culture Performance
(Universiti Sains Malaysia, 2016-03)
Kwong, Kok Onn
Mud crabs (Scylla spp.) are commercially important crustaceans. One of the major obstacles to the growth of Scylla aquaculture is the low supply of hatchery produced seed due to bacterial diseases and high rates of mortalities. Currently, antibiotics are used extensively in Scylla larval culture to improve survival, but its use poses numerous risks including the development of resistance in bacteria to antibiotics, higher levels of virulence, and detection of restricted chemicals in the flesh of farmed animals. The aim of this study was to determine the culture performance of Scylla paramamosain larvae with the use of three different types of probiotics, namely a multispecies Bacillus, Lactobacillus casei (Shirota), and Lactobacillus plantarum, at various concentrations. There were higher average larval survivals in treatments with a multispecies Bacillus probiotics added compared with the control, especially at concentrations of 5.00 × 108 (12.33 - 18.33 ± 1.76 - 3.76 % compared to 1.67 - 3.67 ± 1.67 - 1.76 %; P < 0.05) and 1.00 × 109 cfu/ml. The best concentration of the multispecies Bacillus probiotic that gave lower Vibrio parahaemolyticus counts in this study was at a concentration of 1.00 × 109 cfu/ml. This was significantly lower than the control (1.33 ± 1.33 cfu/ml compared to 32.67 ± 11.05 cfu/ml) during the later days post hatching (DPH). Vibrio parahaemolyticus is known to be pathogenic to Scylla larvae, thus lower numbers are desirable in culture. On average, there were no obvious differences in water qualities and Larval Stage Indexes (LSIs) between the multispecies Bacillus treatments and controls, although larvae appeared healthier in the multispecies Bacillus treatments. Water qualities were within tolerable ranges for Scylla larvae. The fastest larval developmental stage was seen in the multispecies Bacillus treatment at 1.00 × 109 cfu/ml. Lactobacillus casei treatments at concentrations of 1.88 × 108 and 3.75 × 108 cfu/ml gave significantly higher survival rates compared to the control during the early to mid DPHs (49.70 - 99.30 ± 11.90 - 29.20 and 70.70 ± 13.03 % compared to 2.30 - 5.70 ± 1.20 - 5.70 %, respectively; P = 0.022 and 0.029). There were significantly higher survival rates in the Lactobacillus plantarum treatments compared to the control during the early DPH (74.33 - 90.67 ± 7.26 - 6.57 % compared to 47.67 ± 2.19 %; P = 0.040 and 0.005), at concentrations of 1.00 × 102 and 5.00 × 102 cfu/ml in the culture water. In terms of water qualities and LSIs, there were no obvious differences between the Lactobacillus treatments and controls, and this could be due to the relatively low concentration of Lactobacillus added. Based on the concentrations used in this study, the multispecies Bacillus probiotic was more effective than single species Lactobacillus for improving the survival rate and lowering V. parahaemolyticus counts of S. paramamosain larvae. The recommended concentration of the multispecies Bacillus to be added into S. paramamosain larvae was therefore 5.00 × 108 and 1.00 × 109 cfu/ml, and for Lactobacillus it was 3.75 × 108 cfu/ml. The use of Bacillus and Lactobacillus as probiotics is an ideal alternative to antibiotics in Scylla hatcheries to provide a consistent, commercially feasible production of seedlings.
Impact Of Traditional Prognostic Factor And Chemotherapy Schedule Modification On Breast Cancer Patients: A 5 Year Retrospective Study In A District Specialist Hospital In The State Of Perak
(Universiti Sains Malaysia, 2021-10)
Gobi Hariyanayagam A/l Gunasekaran
Chemotherapy schedule modifications are done in clinical practice due to treatment complications or the patients preference. Multiple clinical studies have established the negative prognostic impact of dose delay on survival rates. This study aims to investigate the prevalence and reason for chemotherapy schedule modification with the impact of schedule modification on the Overall Survival (OS) of the breast cancer patient. This retrospective cohort study was done among breast cancer patients receiving chemotherapy from 2013 to 2017 and was followed until 31 Dec 2018. Medical records of patients with cancer were reviewed. Inclusion criteria involved the female patients over eighteen years old, primary carcinoma of the breast, received Anthracycline or Taxane based chemotherapy regimen and completed more than two cycles of chemotherapy. Patients were categorised into three categories of no schedule modification, with schedule modification, and incomplete schedule. The Kaplan-Meier were used to test for survival differences in the univariate setting, and the Cox regression model was used in the multivariate setting. This study aims to measure the prevalence, OS rates, and Hazard Risk (HR) of these three treatment categories. Among 171 patients receiving chemotherapy, 28 (16.4%) had no schedule modification, 118 (69.0%) had schedule modification, and the remaining 25 (14.6%) had an incomplete schedule with OS of 75.0%, 59.3%, and 52.0%, respectively
Synthesis and properties of novel poly(alkyd-urethane)s derived from various types of vegetable oils
(2014)
Jem Shan, Ling
Triglyceride of oil palm (Elaeis guineensis), soy (Glycine max) and sunflower (Helianthus annuus) were used to produce novel alkyd diols and poly(alkydurethane) s with chemical structure specifically designed for better coating performances. The vegetable oils were first converted to monoglycerides by glycerolysis process. The monoglycerides derived from the different oils were reacted with phthalic anhydride at 2:1 monoglyceride-to-phthalic anhydride ratio to obtain novel polyols called alkyd diols. The polyols were then reacted with 4,4`- methylenediphenyldiisocyanate (MDI) to produce five novel poly(alkyd-urethane)s (PAU), namely palm oil based poly(alkyd-urethane) (POPAU), soy oil based poly(alkyd-urethane) (SOPAU), sunflower oil based poly(alkyd-urethane) (SFPAU), palm-soy oils based poly(alkyd-urethane) (POSOPAU) and palm-sunflower oils based poly(alkyd-urethane) (POSFPAU). The successful synthesis of the monoglycerides, alkyd diols and poly(alkyd-urethane)s were confirmed by FTIR, 1H NMR, 13C NMR spectroscopy and their morphology were evaluated by scanning electron microscopy (SEM). The obtained varieties of poly(alkyd-urethane) were applied onto substrates to study their physical and mechanical properties. Further analyses prior to application included viscosity, solubility, iodine number testing, gel content, drying time test while thermogravimetric analysis (TGA), crosshatch adhesion tests, impact strength, pencil hardness, chemical and water resistance were employed after the films were cured. The films showed good homogeneity and impressive thermal stability with palm oil poly(alkyd-urethane) showing only 5% weight loss temperature in N2 at 270oC. Overall, sunflower oil poly(alkyd-urethane) exhibited relatively better mechanical and thermal properties among all due to the highest percentage of cross linked fraction portrayed by its higher iodine value and gel content. Coating performance of poly(alkyd-urethane) based on palm oil was enhanced after blending with sunflower oil or soy oil based alkyd-diols. The adopted technique in the novel chemical design of poly(alkyd-urethane)s created a potential alternative reaction schemes to be applied in the industry for surface coating, binder for composites and other applications, aiding the effort to replace or minimize the use of non-sustainable petroleum-based raw material.