University of Technology Malaysia
Universiti Teknologi Malaysia Institutional RepositoryNot a member yet
70456 research outputs found
Sort by
Rainfall forecasting using the group method of data handling model: A case study of Sarawak, Malaysia
No full textTime series forecasting has led to the emergence of various forecasting models applied to arrays of time series problems, such as rainfall forecasting, dengue forecasting, tourism forecasting, and others. The Artificial Neural Network (ANN) is a popular Artificial Intelligence (AI) model extensively employed in much research for time series forecasting due to its nonlinear modeling ability. The group method of data handling (GMDH) is an AI model with the characteristics of heuristic self-organizing capability. This model has shown successful results in many areas. Nowadays, rainfall forecasting remains a vital interest and is still actively researched, where researchers use different soft computing techniques. The ANN has been popularly studied for rainfall forecasting because of its ability to efficiently train a large amount of data and completely detect complex connections between nonlinear dependent and independent variables. However, research on rainfall forecasting using the GMDH model is limited. Hence, this paper designates the GMDH model and its application to rainfall forecasting. The conventional GMDH model uses the polynomial transfer function. The sigmoid transfer function is proven to solve the multicollinearity issue caused by the quadratic polynomial of the GMDH model. Hence, this research tackled the multicollinearity issue of using different transfer functions in GMDH modeling and forecasting. The study compares the results of using polynomial and sigmoid transfer functions for the GMDH model development. This research uses the Malaysia rainfall dataset of the Sarawak regions from 2010 until 2019 as a case study to evaluate the effectiveness of the GMDH models in this research. The results exhibit that the polynomial transfer function is dominant in achieving the smallest RMSE and MSE values in all regions
The National Industry 4.0 Policy performance review based on Industry4WRD readiness assessment and intervention program
No full textIndustry growth has been accelerated by the discovery of emerging technology, from the early implementation of mechanical systems to support manufacturing processes to today’s highly automated assembly lines, in order to be flexible and adaptable to today’s changing consumer requirements and demands. As a result of the evolution of the industrial revolution, a variety of enabling technologies to have emerged. The manufacturing sector is vital to the development of smart and sustainable industries. As a result, Industry 4.0 aids in the shaping of smart future manufacturing through a variety of methods, one of which is the implementation of the Industry4WRD RA Program, which is influenced by the National Policy on Industry 4.0. The study depicts the performance of the National Industry 4.0 policy based on the SMEs Industry4WRD Readiness Assessment (RA) and intervention program. Analysis and discussion on the collective achievement of assessed Manufacturing and Manufacturing Related Services (MRS) companies for the year 2019 sorted primarily according to their respective Readiness Profiles will be presented in the following first application analysis before Readiness Profile achievement analysis, with suggestions to further improve the RA Program based on post assessment survey, and general observation and suggestions to assessed Manufacturing and MRS company
Three-dimensional (3D) reconstruction of a building from terrestrial laser scanning and photogrammetry dataset using Identical Point Picking (IPP) registration method
No full textBuilding is an immovable asset that requires accurate mapping and efficient documentation. Limitation of 2D- based data acquisition and insufficient semantic information on its geometry make the building documentation becomes less effective. Plus, even 3D- based data acquisition is used, it does not cover whole details optimally. The objectives of this research are to combine two geospatial surveying techniques; terrestrial laser scanning (TLS) and unmanned aerial vehicle (UAV) photogrammetry dataset into 3D modelling and to determine accuracy of the point clouds and the rendered 3D model. A geodetic laser scanner-2000 (GLS- 2000) terrestrial laser scanner was used to record existing details of Dewan Muafakat Johor, Taman Kobena, Tampoi, Johor Bahru, Johor. Meanwhile, UAV-photogrammetry was utilized to capture the rooftop and the aerial view of the building. Both pointcloud data from TLS and UAV-photogrammetry are integrated using Identical Point Picking (IPP) registration method until combined clouds called hybrid point cloud dataset are produced. A level of detail (LOD 3) of a three-dimensional (3D) model was developed using Sketchup and Undet For Sketchup (UFS) software based on the hybrid pointcloud. The root mean square error (RMSE) obtained shows that point cloud dataset is more accurate with 0.132m compared to higher RMSE, 0.455m of rendered 3D model dataset. As this study focuses on 3D data representation which significant for asset documentation, building monitoring and building information modelling (BIM) are the example of applications in the industry that suit with the purpose. Hence, the output from this study especially in terms of measurement and accuracy would be referable for decision making in building documentation
Daylighting performance with courtyard design variant on occupant wellbeing in a tropical climate
No full textIn a tropical climate, the abundance of natural daylighting can illuminate an internal space, and it is an effective passive design strategy that provides energy savings for buildings. natural daylighting was widely used in all building settings before the innovation of artificial lighting, due to this innovation most buildings have transitioned and adopted artificial lighting to illuminate the interior of the building. due to this, high dependency on artificial lighting causes a poor indoor environment for user health and an increase in energy consumption in the building. a courtyard is a universal design element that has been practised for thousands of years globally. its design has become an area of interest in the tropical climate, which improves daylighting performance in buildings. courtyards with a proper design are key in providing sufficient daylighting for the indoor environment, as well as major energy savings in electric lighting. this research aims to explore the daylighting performance with courtyard design variant on occupant wellbeing. the objective is to identify and evaluate the courtyard design variant and the impact of the daylighting performance done toward occupant wellbeing. the methodology used in this research is the comparative analysis method which analyses the simulation data result that produces the recommended courtyard design, which is optimum for the occupant wellbeing in daylighting performance. the daylighting performance studies are done using sketchup and velux daylight visualizer software. the result from the findings will provide the optimum courtyard design variant and daylighting performance for occupant wellbeing. the result of the finding will contribute as a guideline for courtyard implementation in a tropical climate for occupant wellbeing
Comparative study of service-based sentiment analysis of social networking sites fanatical contents
No full textThe proliferation of mobile web services (MWS) for sentiment analysis makes it hard to identify the best MWS for sentiment analysis of social networking sites’ fanatical contents. This paper carries out a comparative study of service-based sentiment analysis of social networking sites’ fanatical contents. This is achieved by cleaning, transformation, and reduction of fanatical contents from the publicly available social media dataset, and multiple MWS are selected for comparison using the application programming interface (API) key of the MWS. To evaluate the service-based sentiment analysis, standard measures such as accuracy, precision, recall, and f-measures of sentiment result for each MWS are used. The result shows that Dandelion SA performs better in terms of accuracy (72.5%) and recall (76.9%), while Wingify SA performs better in terms of precision (88.6%) and f-measure (75.5%), though AlchemyAPI offers the most crucial elements in analyzing sentiments such as emotion, relevance score, and sentiment type. The outcomes of this paper will benefit the sentiment analysis service developers, sentiment analysis service requesters as well as other researchers in the social media fanatical content domain
Flexible housing application of scaffolding system as a tools in sustainable design
No full textThe residents of high-rise housing have rigid indoor layout that fail to respond to the user change. Thus, the unique identity of residents needs to be addressed through a flexible space and housing layout scheme that can adapt to the user needs and culture. The research aim is to study flexible housing that use scaffolding system as a tool for sustainable living which adapt to the user needs and growth. The flexibility of scaffolding as a tool in house units has been explored during the research. Scaffolding is the most common reusable material, having standardised components, a wide range of forms, and a very simple assembly technique. Case studies have been analysed as methodology for this paper that are based on flexible house and scaffolding structure for interior space flexibility. The author argues through the use of examples, that the adaptability and flexibility of living space to the changing demands of people is a decisive element in the period we live in. Flexibility enables consumers to select the best solution from a multitude of possibilities and simply or inexpensively modify it, which is also part of the notion of sustainable development
Vertical neighborhood the empowerment of greenery towards healthy living for M40 group of Johorean
No full textGrowing plants on the vertical surfaces is called vertical greenery systems. These systems have been recognized to mitigate some problems such as air, water and noise pollutions, urban heat island, and consequently global warming. Vertical greenery systems are divided into two categories, i.e., green facades and living walls. In this study, the aim is to design a lively and functionally quality environment vertical neighbourhood through the application of vertical green in the living context. The study leads to understand architecture as a tool for empowering greenery in the living environment. The objectives in this study are to provide environmentally friendly service apartments for M40 group of Johorean, integrating the green element in relation to creating green communities and improving green design strategy that provide sense of place in living context. Hence, the data collected from various source is analysed and synthesised in order to complement the objectives. This study believes that greenery can cultivate a sense of healing in the living environment by implementing the design initiative and achieving a conducive vertical neighbourhood for M40 group of Johorean
Quantitative heuristic approach for eye tracker availability: How focus ability enhances the students’ learning process
No full textEye tracking is a popular indicator to measure student' attention and ability to focus based on eye movement and eye position. In this era of Education 4.0, interface design, user experience and privacy issues prevent people from using wearable devices, which make it difficult to measure paper visual behavior and fine eye movement for several different eye tracking device types. Therefore, this paper present results on study to investigate the importance of eye tracker availability for student learning processes. Integrated Structural Equation Modeling and Analysis of MOment Structures (SEM-AMOS) model used for presenting the results. Excel, Statistical Package for the Social Sciences (SPSS) and AMOS software employed in implementing the simulation and factors of quantitative heuristic approach (QHA) used to analyze the model performance. The results show that there is a positive and significant relationship between the eye trackers availability and its importance. The findings of the QHA paper support the hypothesis
The influence of tourism on commercial gentrification in Jonker Street, Melaka
No full textThis research explores the effect of tourism that led to the commercial gentrification in Jonker Street, Malacca. The commercial gentrification process brings positive and negative impacts to the residents in their communities. In Jonker Street, the revitalization of the economies can be seen from the emergences of business activities by the multinational company and local company entry with emergence of cafe, multi chain retail, hotel and restaurant. Residential displacement driven by this process of tourism activity has been noted by several authors. The commercial gentrification process seems as the important part into changing the places into more friendly for both visitor and resident as it improves the quality of the facilities and quality of life. Furthermore, this research also summarizes the effect of commercial gentrification and the policies that have been implements. This research is a qualitative where in depth interview, observation and Instagram survey are use and also secondary data to develop the themes for the findings. The total of five themes have been identified to answer the objectives one and two. Moreover, there are policies that have been review after the Control of Rent (Repeal) Act 1997. In conclusion of the analysis, the development of the city as renown tourism attraction arouses the indirect displacement pressures whereby the exclusion constrains the quality of life that in long term make them seek migration into other places
A near infrared image of forearm subcutaneous vein extraction using U-Net
No full textMachine learning is in demand for acquiring important perceptions from big data or producing advanced revolutionary technologies and helps most the human tasks effortlessly. Healthcare is one of the industries that receive benefits from it. In the medical industry, venipuncture is one of the most crucial procedures, and locating the patient’s vein is the challenge faced by clinicians. The difficulty leads to multiple trials of venipuncture and causing harm such as bleeding, bruising, damaging surrounding cells, and other effects on the patient. If the case is worst, the patient might have to go to central venous access. Near-Infrared (NIR) has some strong properties such as non-invasive technique, low cost, and small size for the implementation locating the forearm subcutaneous vein; thus, it is a popular method among researchers. The technique has a weakness in that it requires image processing for the enhancement and the vein is more visible and located. This paper is approaching Deep Learning to automatically extract the forearm subcutaneous vein from the NIR image using two architectures: the standard convolutional neural network (CNN) with U-Net architecture and Residual U-Net architecture. The purpose of using two types of architecture is to compare the result and will use the highest accuracy method for the forearm subcutaneous vein extraction. The research found that the U-Net architecture with common CNN has results dice score of 0.6995 while deep residual architecture results 0.7599. It proves that the deep residual architecture has a better extraction than the common CNN block. This project is expected to expand to extract the live video of the forearm subcutaneous vein in future