University of Technology Malaysia
Universiti Teknologi Malaysia Institutional RepositoryNot a member yet
70456 research outputs found
Sort by
Face mask detection for covid-19 standard operating procedure by using deep learning
Get PDFIn 2019, a new and highly infectious disease emerged in Wuhan, China, and quickly spread around the world. SARS-Cov 2 (also known as COVID-19) is the illness. The coronavirus COVID-19 pandemic is wreaking havoc on the world's health system, infecting over 180 million people, and killing over 3.8 million people. The virus transmission method was spread through respiratory droplets when an infected person coughs, sneezes or even speaks Even though a vaccine is available, there is still no effective treatment for this condition, and even if one is vaccinated, one can still be diagnosed. Therefore, the best approach to deal with it is to avoid it, and many medical experts have recommended wearing a face mask as one of the most effective ways to stop the virus from spreading. Aside from that, numerous countries throughout the world have enacted new laws or guidelines requiring individuals to wear face masks on a regular basis. However, some people continue to refuse to use a face mask when visiting public areas, especially in crowded places. As a result, stationing a security guard at the entry to monitor visitors appears to be the alternative. This approach, however, not only puts the guards in risk, but it also has the potential to cause overcrowding at the gate due to its inefficiency. Machine learning is undeniably the key to averting this downfall by minimizing direct human participation. Over the year, in field of image processing and computer vision, the spotlight was more focus on only face detection rather than face mask detection therefore the vulnerabilities of face mask detection technologies have not been properly addressed. Hence, the first objective of this paper is to implement the deep learning in image recognition for face mask detection. Next, the objective will be developing a system that able to detect whether a person is wearing a face mask or not by utilizing Convolutional Neural Network (CNN). In this project, the CNN architecture, MobileNetV2 is being utilised due to its low computational cost. A total of 3486 images of face masked and without face masked datasets are created from various online open-sourced datasets and fed to the model. Several optimizers, including SGD, RMSProp, and Adam, are evaluated to obtain the optimal network model. Finally, the Adam optimizer is chosen, and optimization techniques such as epoch size, batch size, and initial learning rate are gradually tuned and applied to the model. The validation accuracy could reach 99% throughout the tuning process, and the validation loss was decreased from 4.13 % to 2.86 %. The result model was then compared to another state-of-the-art CNN model, VGG-16, and the results reveal that the MobileNetV2 model did indeed utilise fewer computing resources, as it consumed 11% less memory, had a 5 times smaller result model, and took 5 times less time to train than that in VGG-16. When the model was put to the test with 50 real-life example images, the model able to achieve accuracy of 86% which the model able to detect the face in the image and correctly labelled it. In the end, the system able to detect face and distinguish the face with or without face mask and thus help in face mask detection to prevent the spread of COVID-19
Eco-friendly surface modification approach to develop thin film nanocomposite membrane with improved desalination and antifouling properties
No full textIntroduction: Nanomaterials aggregation within polyamide (PA) layer of thin film nanocomposite (TFN) membrane is found to be a common issue and can negatively affect membrane filtration performance. Thus, post-treatment on the surface of TFN membrane is one of the strategies to address the problem. Objective: In this study, an eco-friendly surface modification technique based on plasma enhanced chemical vapour deposition (PECVD) was used to deposit hydrophilic acrylic acid (AA) onto the PA surface of TFN membrane with the aims of simultaneously minimizing the PA surface defects caused by nanomaterials incorporation and improving the membrane surface hydrophilicity for reverse osmosis (RO) application. Methods: The TFN membrane was first synthesized by incorporating 0.05 wt% of functionalized titania nanotubes (TNTs) into its PA layer. It was then subjected to 15-s plasma deposition of AA monomer to establish extremely thin hydrophilic layer atop PA nanocomposite layer. PECVD is a promising surface modification method as it offers rapid and solvent-free functionalization for the membranes. Results: The findings clearly showed that the sodium chloride rejection of the plasma-modified TFN membrane was improved with salt passage reduced from 2.43% to 1.50% without significantly altering pure water flux. The AA-modified TFN membrane also exhibited a remarkable antifouling property with higher flux recovery rate (>95%, 5-h filtration using 1000 mg/L sodium alginate solution) compared to the unmodified TFN membrane (85.8%), which is mainly attributed to its enhanced hydrophilicity and smoother surface. Furthermore, the AA-modified TFN membrane also showed higher performance stability throughout 12-h filtration period. Conclusion: The deposition of hydrophilic material on the TFN membrane surface via eco-friendly method is potential to develop a defect-free TFN membrane with enhanced fouling resistance for improved desalination process
Artificial intelligence (AI) library services innovative conceptual framework for the digital transformation of university education
No full textPurpose: Artificial intelligence (AI) is one of the latest digital transformation (DT) technological trends the university library can use to provide library users with alternative educational services. AI can foster intelligent decisions for retrieving and sharing information for learning and research. However, extant literature confirms a low adoption rate by the university libraries in using AI to provide innovative alternative services, as this is missing in their strategic plan. The research develops (AI-LSICF) an artificial intelligence library services innovative conceptual framework to provide new insight into how AI technology can be used to deliver value-added innovative library services to achieve digital transformation. It will also encourage library and information professionals to adopt AI to complement effective service delivery. Design/methodology/approach: This study adopts a qualitative content analysis to investigate extant literature on how AI adoption fosters innovative services in various organisations. The study also used content analysis to generate possible solutions to aid AI service innovation and delivery in university libraries. Findings: This study uses its findings to develop an Artificial Intelligence Library Services Innovative Conceptual Framework (AI-LSICF) by integrating AI applications and functions into the digital transformation framework elements and discussed using a service innovation framework. Research limitations/implications: In research, AI-LSICF helps increase an understanding of AI by presenting new insights into how the university library can leverage technology to actualise innovation in service provision to foster DT. This trail will be valuable to scholars and academics interested in addressing the application pathways of AI library service innovation, which is still under-explored in digital transformation. Practical implications: In practice, AI-LSICF could reform the information industry from its traditional brands into a more applied and resolutely customer-driven organisation. This reformation will awaken awareness of how librarians and information professionals can leverage technology to catch up with digital transformation in this age of the fourth industrial revolution. Social implications: The enlightenment of AI-LSICF will motivate library professionals to take advantage of AI's potential to enhance their current business model and achieve a unique competitive advantage within their community. Originality/value: AI-LSICF development serves as a revelation, motivating university libraries and information professionals to consider AI in their strategic plan to enable technology to support university education. This act will enable alternative service delivery in the face of unforeseen circumstances like technological disruption and the present global COVID-19 pandemic that requires non-physical interaction
Performance comparison of grid connected photovoltaic system with energy storage system under malaysia renewable energy programs
No full textThe purpose of this study is to analyse the feasible solution of grid-connected PV system with and without battery for a typical residential load under Malaysia renewable energy (RE) programs. To date, net-energy-metering 3.0 (NEM3.0) scheme was launched in 2021 by Malaysia government. After the end of NEM 3.0 program, it will be replaced by self-consumption (SELCO) scheme, which new former NEM 3.0 users have to find a way to address the excess PV energy. The PV project may not economically viable under combination of NEM 3.0 and SELCO scheme. So, in this project, Homer Pro software was used to simulate the study. Due to some limitation of the features in Homer Pro software, the grid-connected PV system under NEM and SELCO was simulated separately. By combining the nominal cash flow data computed by Homer under NEM and SELCO respectively, the economic assessment was performed on the data to determine the feasibility of the solution. There is a total of six types of solution proposed in this study. Unfortunately, the battery that available in 2021 market was uneconomically viable to integrate into grid-connected PV system under combination of NEM and SELCO scheme. By using the forecasted inputs from a professional and international agency, the PV system with battery under NEM and SELCO are able to achieve lower net present cost than grid-only system. Other than that, the study proposed two solutions, which keep the initial sizing without battery or resized the RE system for aiming day time load consumption during SELCO scheme. These two solutions are able to achieve lower NPC than grid-only system and the resized configuration had a slightly lower NPC than initial RE system with battery under SELCO. So, if the forecasted results become realistic in future, grid-connected PV system with battery would be the recommended option. Because it is not only achieved lower NPC than grid-only system, the CO2 emission by generating the energy was also greatly reduced. And if the forecasted results could not become realistic, resized configuration without battery may be the best option. This study may help to establish a more attractive financial return of RE program in future for promoting RE in residential sector
Flow structure characteristics of the simplified compact car exposed to crosswind effects using CFD
No full textAerodynamic characteristics of a car are important in reducing car accidents caused by wind loading and in lowering fuel economy, continuing to be a major topic of interest. The restrictions of wind tunnel tests and the rising trend of numerical methods have been complied with by past researchers to investigate vehicle aerodynamics computationally. This research aims to analyze comprehensively the effect of crosswinds on a moving vehicle in terms of aerodynamic loadings and flow structures using commercial fluid dynamic software ANSYS FLUENT. This paper will focus on the CFD-based simplified compact car body developed in CATIA V5 by neglecting the external parts such as side mirrors and underbody. The implementation of Standard k − Ɛ model with the inlet velocity, v is setup to 30.56 m/s and Reynolds number equal to 8.89 × 105 by using numerical analysis for this research. The generic compact car which represents car geometries are expected to influence the aerodynamic characteristics whereas the crosswind angles are increased, it will cause high values for the coefficient of side forces and rolling moments in terms of aerodynamic loads due to the existence of the vortices at the leeward region. At Ψ = 0°, the coefficient of side force (Cs) is close to zero and this is predicted because the flow to the body is aligned to the inlet velocity, v
Thermal and mechanical properties of thermoplastic cassava starch/beeswax reinforced with cogon grass fiber
No full textThe aim of this paper is to investigate the effect of cogon grass fiber (CGF) on the thermal and mechanical properties of thermoplastic cassava starch (TPCS)/beeswax matrix. The alteration of TPCS/beeswax reinforced with cogon grass fiber was performed by incorporating various amount of CGF (0,10,20,30,40 wt.%) into the polymer matrix. The samples were then evaluated using thermogravimetric analysis and tensile test. The findings showed that the thermal properties of the composite were slightly improved as the CGF content increase. The mechanical test showed that the tensile strength and tensile modulus increased with the addition of the CGF. However, the elongation at break showed a decreased pattern following the increasing content of CGF compared to the 0% of fiber content. In general, the findings from this study have shown that the TPCS/beeswax reinforced with the CGF composite has improved the functional properties of the composites compared to the TPCS matrix
A modified UTAUT model for hospital information systems geared towards motivating patient loyalty
No full textHealthcare service institutions (HSIs) have sought ways to motivate patient loyalty in response to surging rates of medical tourism. Previous research indicates that Hospital Information System (HIS) is essential for HSIs to gather, measure, and analyze the massive amounts of data required to generate patient loyalty. There is currently no consensus on the factors that comprise HIS specifically geared towards motivating patient loyalty (HISPL). Furthermore, HIS requires full adoption by HSI staff to be effective. Thus, to reduce wastage of HSI resources, it is necessary to predict whether a given HIS specifically geared towards motivating patient loyalty is likely to be adopted. The purpose of this study is to reveal the factors that comprise HISPL and to modify the Unified Theory of Acceptance and Use of Technology (UTAUT) model to help predict the likelihood of an HISPL to be fully adopted by HSI staff. The results revealed that pertinent HISPL factors are capability, configurability, ease of use/help desk availability and competence (EU), and accessibility/shareability (AS). Using these factors, the UTAUT model was modified to fit the specific needs of HISPL. The modifications are theoretical and will have to be validated in future empirical studies
Gain scaling tuning of fuzzy logic Sugeno controller type for ride comfort suspension system using firefly algorithm
No full textA control system based on fuzzy logic (FL) is one of the effective controllers which operates using an inference mechanism rule base that requires a knowledge database. The system itself can remotely able to produce good linguistic variables depending types of output required. Nevertheless, the FL controller design still has a drawback that requires an improvement to give a very high capability in controlling a dynamic ride comfort of the vehicle suspension system. This study aims to improve the FL controller design by adding a gain scaling value for each input and output of the FL system. A metaheuristic-based firefly algorithm (FA) is used to optimize the value of each input and output of the FL system. Taking an acceleration of the suspension system response as an objective function, the FA strategy is an attempt to find and search for an optimum value of the gains that able to be as a sort of contact information for improving the targeted value obtained from the FL controller. In this work, an external disturbance in the form of sinusoidal waves is applied to the system to verify the sensitivity and durability of the proposed control schemes. Consequently, a comparative assessment between FL controller without having gain scaling and with the gain scaling tuned by FL strategy is investigated an analysis in the form of the amplitude reduction for both body displacement and acceleration responses. Simulation results indicated that the FL with gain scaling shows a good response compared to the FL without gain and its performance is improved by up to 52.1% compared to others
Neural network based self-tuning PID controller for automatic voltage regulator of hydropower plant
Get PDFHydropower plant is a renewable resource with low operating, maintenance expenses and low environmental effects. Due to the constant load change as a result of changing consumers demand, terminal voltage from the generator is fluctuating for certain period before it settle to the desired level. The amount of fluctuation is negatively influencing the power quality and performance of power system. Automatic voltage regulator (AVR) is playing vital role for maintaining the terminal voltage within desired level. The proportional-integral-derivative (PID) controller's is popularly deployed in AVR system due to its ease structure and straightforward design with almost no computational cost. However, traditional methods of PID tuning in some industrial applications does not meet the required response due to severe load fluctuations. In this work, in order to meet the optimum PID-AVR performance; a three types of neural networks namely: feed forward neural network (FFNN), cascade back propagation neural network (CBPNN), and convolutional neural network (CNN) were used to design three self-tuning PID controllers (NNs-PIDF) for AVR system. These artificial intelligence based controller are proven stunning performance over traditional PID controllers also over those controller made using particle swarm optimization (PSO) and fuzzy logic. The outcomes of this work revealed that FFNN-PIDF based AVR system was able to produce best results e.g. settling time, overshoot, and rise time. The proposed controllers has provided consistence performance in controller stability and robustness tests
Cyberattack feature selection using correlation-based feature selection method in an intrusion detection system
No full textAn intrusion detection system (IDS) is software or hardware that works as a monitoring and defense system against cyberattacks. This system monitors computer systems or network activities that have the potential to violate security policies. In general, there are two techniques used by an IDS in its cyberattack detection system: signature-based and anomaly-based. However, these techniques still face some problems, such as false alarm warnings, low accuracy and precision rates, high-dimensional data, complex data structures, and long computational times. IDS performance can be improved by implementing feature selection, which can reduce the amount of data to be processed on the IDS detection engine. This research used correlation-based feature selection (CFS). Experimental results on CIC-IDS2018 dataset show optimal IDS performance. The proposed CFS-based IDS achieves an accuracy of 99.9995%, recall of 100%, specificity of 99.9985%, precision of 99.9992, F1-score of 99.9996%, true positive rate of 99.9992%, and true negative rate of 100%