Siti Mariyam Shamsuddin | Universiti Teknologi Malaysia - UTM (original) (raw)

Papers by Siti Mariyam Shamsuddin

The evolution of 3D scanning devices and innovation in computer processing power and storage capa... more The evolution of 3D scanning devices and innovation in computer processing power and storage capacity has sparked the revolution of producing big point-cloud datasets. This phenomenon has becoming an integral part of the sophisticated building design process especially in the era of 4 th Industrial Revolution. The big point-cloud datasets have caused complexity in handling surface reconstruction and visualization since existing algorithms are not so readily available. In this context, the surface reconstruction intelligent algorithms need to be revolutionized to deal with big point-cloud datasets in tandem with the advancement of hardware processing power and storage capacity. In this study, we propose GPUMLib – deep learning library for self-organizing map (SOM-DLLib) to solve problems involving big point-cloud datasets from 3D scanning devices. The SOM-DLLib consists of multiple layers for reducing and optimizing those big point cloud datasets. The findings show the final objects are successfully reconstructed with optimized neighborhood representation and the performance becomes better as the size of point clouds increases.

— The social network has in recent times gained much ground in the 21 st century generations of i... more — The social network has in recent times gained much ground in the 21 st century generations of internet users and this have made it an engaging communication means, most especially among university students. As a result of this, both social and academic activities and engagements among university students are rapidly carried out through social networking sites (SNSs) such as Twitter, Instagram, Facebook, LinkedIn, etc. All of these are usually used by students for various purposes. In recent times, the use of SNSs has become an integral and suitable part of day to day communication among university students. The use of SNSs has a major influence and effect on students in enormous ways, most especially on their social interactions and relationships. The aim of this study is to investigate the use of social network sites among university students and the impact it has on their social relationship. A structured questionnaire was designed and distributed among the sample of students who are considered to be active users of social networking sites. The results gotten shows that the SNSs that is mostly used among the university students is Facebook and Twitter and we also found out that the duration of time spent on SNSs per day is between 1-12 hours. Findings also shows that most students make use of SNSs majorly to keep in touch with relatives, family and friends, as this is most positive impacts that SNSs have on the students. However, the students expressed their concerns about the security and privacy issues of SNSs as a major negative effect on their interaction on the SNSs. Based on the research findings, the more active a student is on SNSs, and the more conspicuous will be the student's likelihood of keeping up a private profile. The result of this study gives a sign on how dynamic the students are on the social network sites. The review at long last present data that could be helpful for the educators about the overall activities of students. Through this review, instructors could translate the social structure of the systems gotten from the various activities carried out on the social network sites and in this manner gain knowledge on the forms of social interaction of students on social network. Therefore, it is recommended that students should explore the various activities and various security settings that are available on the SNSs as these will make them get well-groomed in the use of the privacy settings and options. The most grounded sources of social influence tend to be our direct associates, peers and colleagues and the more friends with private profiles a student has, the more important will be the student's likelihood of keeping up a private profile herself.

Knowledge-Based Systems, 2015

ABSTRACT Software requirements engineering is a critical discipline in the software development l... more ABSTRACT Software requirements engineering is a critical discipline in the software development life cycle. The major problem in software development is the selection and prioritization of the requirements in order to develop a system of high quality. This research analyzes the issues associated with existing software requirement prioritization techniques. One of the major issues in software requirement prioritization is that the existing techniques handle only toy projects or software projects with very few requirements. The current techniques are not suitable for the prioritization of a large number of requirements in projects where requirements may grow to the hundreds or even thousands. The research paper proposes an expert system, called the Priority Handler (PHandler), for requirement prioritization. PHandler is based on the value-based intelligent requirement prioritization technique, neural network and analytical hierarchical process in order to make the requirement prioritization process scalable. The back-propagation neural network is used to predict the value of a requirement in order to reduce the extent of expert biases and make the PHandler efficient. Moreover, the analytical hierarchy process is applied on prioritized groups of requirements in order to enhance the scalability of the requirement prioritization process.

The performance of the Harmony Search (HS) algorithm is highly dependent on the parameter setting... more The performance of the Harmony Search (HS) algorithm is highly dependent on the parameter settings and the initialization of the Harmony Memory (HM). To address these issues, this paper presents a new variant of the HS algorithm, which is called the DH/best algorithm, for the optimization of globally continuous problems. The proposed DH/best algorithm introduces a new improvisation method that differs from the conventional HS in two respects. First, the random initialization of the HM is replaced with a new method that effectively initializes the harmonies and reduces randomness. Second, the conventional pitch adjustment method is replaced by a new pitch adjustment method that is inspired by a Differential Evolution (DE) mutation strategy known as DE/best/1. Two sets of experiments are performed to evaluate the proposed algorithm. In the first experiment, the DH/best algorithm is compared with other variants of HS based on 12 optimization functions. In the second experiment, the complete CEC2014 problem set is used to compare the performance of the DH/best algorithm with six well-known optimization algorithms from different families. The experimental results demonstrate the superiority of the proposed algorithm in convergence, precision, and robustness.

The user has requested enhancement of the downloaded file. All in-text references underlined in b... more The user has requested enhancement of the downloaded file. All in-text references underlined in blue are added to the original document and are linked to publications on ResearchGate, letting you access and read them immediately.

We present a study of using fuzzy-based parameters for solving public bus routing problem where d... more We present a study of using fuzzy-based parameters for solving public bus routing problem where demand is uncertain. The fuzzy-based parameters are designed to provide data required by the route selection procedure. The uncertain data are represented as linguistic values which are fully dependent on the user's preference. This paper focuses on the selection of the Defuzzification method to discover the most appropriate method for obtaining crisp values which represent uncertain data. We also present a step by step evaluation showing that the fuzzy-based parameters are capable to represent uncertain data replacing the use of exact data which common route selection algorithms usually use.

2015 3rd International Conference on Information and Communication Technology (ICoICT), 2015

Moving object segmentation is crucial in many computer vision applications such as video surveill... more Moving object segmentation is crucial in many computer vision applications such as video surveillance, automated inspection, and many others. The goal of moving object segmentation is to classify pixels as foreground or background; the foreground pixels forming the moving objects. A good segmentation method should be able to do segmentation when the scene is complex as well as adaptable to changes in the environment. Many methods have been proposed for segmentation; statistical methods are the most popular ones. These methods model the background based on statistical information extracted from incoming frames. In this study, we estimate the background with the concept of vector quantization. The motion mask is created by subtracting incoming frames from estimated background under various conditions especially when the color variation between background and foreground objects is high. We measure the performance by some metrics such as similarity and error-rate. The results have shown...

Procedia - Social and Behavioral Sciences, 2013

Industrialised Building System (IBS) is world wide responding to sustainable construction. In ord... more Industrialised Building System (IBS) is world wide responding to sustainable construction. In order to be competitive in this current trend, local construction players have to take this advantages and shift their paradigm from conventional construction to IBS. This paper therefore, aimed to determine the economic attributes related to the sustainability of Malaysian construction. The main tool used for data collection is questionnaire survey collected from 50 respondents. The results showed that there are many momentous economical attributes identified related with sustainable and IBS, which are IBS offers long term monitoring mechanism by using Life Cycle Costing in cost development, the thoughts of environmental-related products are always involved a huge financial burden up-front and in term of financial investment, IBS offers more speed Return-on-Investment of a project. Based on information gained strategies to strengthen and promotes broader adoption of sustainability in IBS construction, in Malaysia was suggested.

JOURNAL OF JAPAN SOCIETY OF HYDROLOGY & WATER RESOURCES, 2004

… , Japan, from 30 June to 11 …, 2003

... J. Geophys. Res. (in press). Tani, M., Abdul Rahim, N., Ohtani, Y., Yasuda, Y., Mohd, Md S., ... more ... J. Geophys. Res. (in press). Tani, M., Abdul Rahim, N., Ohtani, Y., Yasuda, Y., Mohd, Md S., Baharuddin, K., Takanashi, S., Noguchi, S., Zulkifli, Y. & Watanabe, T. (2003) Characteristics of energy exchange and surface conductance of a tropical rain forest in Peninsular Malaysia. ...

Aboul Ella Hassanien Aiping Jiang Albert Zomaya Andre CPLF De Carvalho Antonia Azzini Bei-Bei Liu... more Aboul Ella Hassanien Aiping Jiang Albert Zomaya Andre CPLF De Carvalho Antonia Azzini Bei-Bei Liu Benoit Otjacques Bing-Hong Liu Chao-Ho Chen Cheng-Min Lin Chih-Yuan Lien Chiu-Chiao Chung Chuang Lin Chuan-Yu Chang Deng-Yuan Huang Fa-Xin Yu Gabriel Gianini Guoqiang Wang Hao Luo Hao Wen Lin Hao-Tian Wu Hao-Xian Wang Hong Chen Hongbin Ma Hong-Chi Shih Huang-Nan Huang Hui-Cheng Zheng JC Wei James Peters. Janusz Kacprzyk Javier Bajo Jiangzhong Cao Ji-Xin Liu Jun Lang Jun-Bao Li KE Parsopoulos Katarzyna ...

Neural Network World, Nov 1, 2007

In business, industry and government agencies, anticipating future behavior that involves many cr... more In business, industry and government agencies, anticipating future behavior that involves many critical variables for nation wealth creation is vitally important, thus the necessity to make precise decision by the policy makers is really essential. Consequently, an accurate and reliable forecast system is needed to compose such predictions. Accordingly, the aim of this research is to develop a new hybrid model by combining a linear and nonlinear model for forecasting time series data. The proposed model (GRANN ARIMA) integrates nonlinear Grey Relational Artificial Neural Network (GRANN) and linear ARIMA model, combining new features such as multivariate time series data as well as grey relational analysis to select the appropriate inputs and hybridization succession. To validate the performance of the proposed model, small and large scale data sets are used. The forecasting performance was compared with several models, and these include: individual models (ARIMA, Multiple Regression, Grey Relational Artificial Neural Network), several hybrid models (MARMA, MR ANN, ARIMA ANN), and Artificial Neural Network (ANN) trained using Levenberg Marquardt algorithm. The experiments have shown that the proposed model has outperformed other models with 99.5% forecasting accuracy for small-scale data and 99.84% for large-scale data. The empirical results obtained have proved that the GRANN ARIMA model can provide a better alternative for time series forecasting due to its promising performance and capability in handling time series data for both small and large scale data.

Http Dx Doi Org 10 1080 08839510902879384, Apr 28, 2009

In business, industry and government agencies, anticipating future behavior that involves many cr... more In business, industry and government agencies, anticipating future behavior that involves many critical variables for nation wealth creation is vitally important, thus the necessity to make precise decision by the policy makers is really essential. Consequently, an accurate and reliable forecast system is needed to compose such predictions. Accordingly, the aim of this research is to develop a new hybrid model by combining a linear and nonlinear model for forecasting time series data. The proposed model (GRANN_ARIMA) integrates nonlinear Grey Relational Artificial Neural Network (GRANN) and linear ARIMA model, combining new features such as multivariate time series data as well as grey relational analysis to select the appropriate inputs and hybridization succession. To validate the performance of the proposed model, small and large scale data sets are used. The forecasting performance was compared with several models, and these include: individual models (ARIMA, Multiple Regression, Grey Relational Artificial Neural Network), several hybrid models (MARMA, MR_ANN, ARIMA_ANN), and Artificial Neural Network (ANN) trained using Levenberg Marquardt algorithm. The experiments have shown that the proposed model has outperformed other models with 99.5% forecasting accuracy for small-scale data and 99.84% for large-scale data. The empirical results obtained have proved that the GRANN_ARIMA model can provide a better alternative for time series forecasting due to its promising performance and capability in handling time series data for both small and large scale data.

Knowledge-Based Systems, 2015

2015 3rd International Conference on Information and Communication Technology (ICoICT), 2015

Procedia - Social and Behavioral Sciences, 2013

JOURNAL OF JAPAN SOCIETY OF HYDROLOGY & WATER RESOURCES, 2004

… , Japan, from 30 June to 11 …, 2003

Neural Network World, Nov 1, 2007

Http Dx Doi Org 10 1080 08839510902879384, Apr 28, 2009

In business, industry and government agencies, anticipating future behavior that involves many cr... more In business, industry and government agencies, anticipating future behavior that involves many critical variables for nation wealth creation is vitally important, thus the necessity to make precise decision by the policy makers is really essential. Consequently, an accurate and reliable forecast system is needed to compose such predictions. Accordingly, the aim of this research is to develop a new hybrid model by combining a linear and nonlinear model for forecasting time series data. The proposed model (GRANN_ARIMA) integrates nonlinear Grey Relational Artificial Neural Network (GRANN) and linear ARIMA model, combining new features such as multivariate time series data as well as grey relational analysis to select the appropriate inputs and hybridization succession. To validate the performance of the proposed model, small and large scale data sets are used. The forecasting performance was compared with several models, and these include: individual models (ARIMA, Multiple Regression, Grey Relational Artificial Neural Network), several hybrid models (MARMA, MR_ANN, ARIMA_ANN), and Artificial Neural Network (ANN) trained using Levenberg Marquardt algorithm. The experiments have shown that the proposed model has outperformed other models with 99.5% forecasting accuracy for small-scale data and 99.84% for large-scale data. The empirical results obtained have proved that the GRANN_ARIMA model can provide a better alternative for time series forecasting due to its promising performance and capability in handling time series data for both small and large scale data.