Zarita Zainuddin - Academia.edu (original) (raw)

Papers by Zarita Zainuddin

The learning phase of wavelet neural network entails the task of finding the optimal set of param... more The learning phase of wavelet neural network entails the task of finding the optimal set of parameter, which includes wavelet activation function, translation centers, dilation parameter, synaptic weight values, and bias terms. Apart from the traditional gradient descent-based approach, metaheuristic algorithms can also be used to determine these parameters. In this work, the harmony search algorithm is employed to find the optimal solution for both synaptic weight values and bias terms in the learning of wavelet neural network. The standard harmony search algorithm is modified accordingly in the aspect of initialization of harmony memory, as well as during the improvisation stage. The proposed harmony search-based learning algorithm is used in the task of epileptic seizure prediction. Simulation results show that the proposed algorithm outperforms other metaheuristic algorithms in terms of sensitivity

In today-s modern world, the number of vehicles is increasing on the road. This causes more peopl... more In today-s modern world, the number of vehicles is increasing on the road. This causes more people to choose walking instead of traveling using vehicles. Thus, proper planning of pedestrians- paths is important to ensure the safety of pedestrians in a walking area. Crowd dynamics study the pedestrians- behavior and modeling pedestrians- movement to ensure safety in their walking paths. To date, many models have been designed to ease pedestrians- movement. The Social Force Model is widely used among researchers as it is simpler and provides better simulation results. We will discuss the problem regarding the ritual of circumambulating the Ka-aba (Tawaf) where the entrances to this area are usually congested which worsens during the Hajj season. We will use the computer simulation model SimWalk which is based on the Social Force Model to simulate the movement of pilgrims in the Tawaf area. We will first discuss the effect of uni and bi-directional flows at the gates. We will then rest...

The social force model which belongs to the microscopic pedestrian studies has been considered as... more The social force model which belongs to the microscopic pedestrian studies has been considered as the supremacy by many researchers and due to the main feature of reproducing the self-organized phenomena resulted from pedestrian dynamic. The Preferred Force which is a measurement of pedestrian-s motivation to adapt his actual velocity to his desired velocity is an essential term on which the model was set up. This Force has gone through stages of development: first of all, Helbing and Molnar (1995) have modeled the original force for the normal situation. Second, Helbing and his co-workers (2000) have incorporated the panic situation into this force by incorporating the panic parameter to account for the panic situations. Third, Lakoba and Kaup (2005) have provided the pedestrians some kind of intelligence by incorporating aspects of the decision-making capability. In this paper, the authors analyze the most important incorporations into the model regarding the preferred force. They...

Advances in computer technology, coupled with the intention to utilize the limited resources to i... more Advances in computer technology, coupled with the intention to utilize the limited resources to its best possible way while conforming to the prescribed objective, has led to a wealth of different optimization approaches in engineering problems. Of particular note is the rise of using evolutionary algorithms in obtaining the optimal solutions in the engineering design problems. This paper sets out to compare the optimization performances of three recently developed evolutionary algorithms, namely, bat algorithm, cuckoo search algorithm, and flower pollination algorithm in constrained engineering optimization. Three infamous constrained real world problems, specifically, spring design, welded beam design, and pressure vessel design, are considered in this study. The promising optimization capabilities of all reviewed evolutionary algorithms are shown in the performance assessment.

Proceedings of The fourth International Conference on Information Science and Cloud Computing — PoS(ISCC2015), 2016

Artificial neural networks has been effectively applied to numerous applications because of their... more Artificial neural networks has been effectively applied to numerous applications because of their universal approximation property. This work is grounded on two frameworks. Firstly, it is concerned with solving universal approximation problem by a class of neural networks based on Hankel approximate identity which is embedded in the space of continuous functions on real positive numbers. Secondly, this problem solving will be investigated in the Lebesgue spaces on real positive numbers. The methods are constructed on the notions of Hankel convolution linear operators, Hankel approximate identity, and epsilon-net.

Applied Soft Computing, 2019

Fossil fuels have been used widely for power generation. Emphasis should be given to the usage of... more Fossil fuels have been used widely for power generation. Emphasis should be given to the usage of renewable energy for power generation to reduce our dependence on primary fossil fuels. The burning of biomass with fossil fuels has a positive impact, both on the environment and the economics of power generation. Both coal and biomass are chosen because they have great potential to be developed in future for power generation in Malaysia. The aim of this study is to investigate the impacts of burning biomass with coal on the pollutant emissions and combustion performances of this cofiring. Type of biomass used is sawdust and simulation is done using CFD code FLUENT software. A good understanding of the combustion and pollutant generating processes in the combustor helps to reduce emissions of pollutants and improve boiler performances. CFD simulation is first performed on the combustion of coal solely. The results of simulation obtained are then compared to the actual data taken from the Tanjung Bin power plant for validation purpose. Once the data validation has been achieved, second simulation can be performed on the same model for cofiring. The validation indicates that finer grid of meshing produces more accurate results with small error of 6.9% and 7.9% for the validation of temperature and radiation respectively. The results obtained from simulation indicate that cofiring does lower the emissions of CO 2 significantly. This is shown by the concentration of CO 2 that dropped drastically when coal was cofired with biomass. It is very important to reduce the amount of CO 2 concentration in the air through the understanding of these gases formation as it would become a threat to the environment if the level is too high compared to other gases. A more intense combustion can also be achieved that can improve the combustion performance in terms of temperature and radiation. These parameters may indicate better combustion efficiency if the two fuels were burned together.

Cellulose, 2019

Rapid Prototyping (RP) technology is actively studied to be implemented in Investment Casting (IC... more Rapid Prototyping (RP) technology is actively studied to be implemented in Investment Casting (IC) process. Nowadays RP techniques were studied for the feasibility as IC master pattern, in terms of pattern collapsibility and drainage during burnout. The purpose of study is to determine the characteristic of Visijet® SR200 acrylate material during burnout process. Traditional IC patterns made from wax have properties that limit their application, in precision casting especially for parts with thin geometries that readily break or deform conventional when handled or dipped in the refractory slurry. Furthermore,it is not economical when producing small number of parts. Non wax pattern fabricated for IC process, revealed that ceramic shell cracking due to excessive thermal expansions, incomplete collapsibility of pattern during burnout, residual ash and poor surface finish. Thermogravimetric analysis (TGA) was used to measured the weight loss of acrylate material as the temperature was increased. TGA measured the change of material's mass as it is heated. It represents the decomposition temperature after being subjected to varying temperatures, as well as the amount of residual ash. In this experiment, the temperature range was from 20ºC to 700ºC with 5ºC increment. Experiment results shows the values of material's optimum reaction temperature and decomposing temperature of Visijet® SR200 acrylate. The percentages of remaining materials were also monitored throughout the process to obtain the amount of residual ash. All of the temperature value obtained is a resemblance for the actual burnout process and can be used as references.

The social force model which belongs to the microscopic pedestrian studies has been considered as... more The social force model which belongs to the microscopic pedestrian studies has been considered as the supreme model by many researchers and engineers due to the main feature of its capability in reproducing the self-organization phenomena resulting from pedestrian dynamics. Recently, some principles of this model have been modified by other researchers to overcome a shortcoming that the model could not reproduce experimental data in normal situations such as the fundamental diagram. In this article, we argue that these principles are not the reasons for this shortcoming. And we clarify that the actual reason for this shortcoming is due mainly to the misunderstanding of the role of the pedestrian's perception of the objects surrounding him. And then, we present a typical approach to find the relation between the pedestrian's perception and the local density which helps in reproducing the fundamental diagram which conforms to the empirical data while conserving the principles of the social force model.

2008 International Conference on Electronic Design, 2008

ABSTRACT Missing data is a problem that permeates much of the research bring done today. Some dat... more ABSTRACT Missing data is a problem that permeates much of the research bring done today. Some data frequently contain missing values such as gene expression data, which most of its down stream analyses for microarray experiments require complete data. In the literature many methods have been proposed to estimate missing values via information of the correlation patterns within the data matrix. In this report we describe an evaluation of top three current methods including a neural network method and two imputation methods on multiple types of data including microarray data, time series data such as air pollutant data and phytoplankton data. Based on the overall performance of the method, we then determine the most appropriate method that can be applied to various data sets. We found that the optimal method (local least square imputation (LLS) and Bayesian principle component analyses (BPCA)) are all highly competitive to each other in overall results. We tested with radial basis function (RBF) network method which is one of the neural network methods and found that, the overall performance of RBF network is lower than BPCA method and LLS method. According to the overall NRMSE of the three methods, the BPCA method provides the most accurate estimation for missing values.

Neurocomputing, 2011

The main purpose of this study is to state conditions that guarantee an interval type-2 triangula... more The main purpose of this study is to state conditions that guarantee an interval type-2 triangular fuzzy (IT2TF) neural network can approximate continuous IT2TF functions. To make a more efficient calculation with IT2TF numbers, the sum and the product of two IT2TF numbers are constructed. These concepts are used in the definition of IT2TF polynomials. Moreover, the present study provides a mathematical framework to show that IT2TF polynomials are a compact Hausdroff space. Based on this concept we establish an interval type-2 fuzzy neural networks version of the Stone-Weierstrass theorem which enables approximation by a special class of IT2TF neural networks on the set of all monotonic and continuous IT2TF functions. Finally, a numerical example is given to illustrate the results.

Neural Computing and Applications, 2013

Neural Computation, 1999

This article focuses on gradient-based backpropagation algorithms that use either a common adapti... more This article focuses on gradient-based backpropagation algorithms that use either a common adaptive learning rate for all weights or an individual adaptive learning rate for each weight and apply the Goldstein/Armijo line search. The learning-rate adaptation is based on descent techniques and estimates of the local Lipschitz constant that are obtained without additional error function and gradient evaluations. The proposed algorithms improve the backpropagation training in terms of both convergence rate and convergence characteristics, such as stable learning and robustness to oscillations. Simulations are conducted to compare and evaluate the convergence behavior of these gradient-based training algorithms with several popular training methods.

International Journal of Remote Sensing, 2003

This paper deals with the problem of retrieving optically active parameters of the water from mul... more This paper deals with the problem of retrieving optically active parameters of the water from multispectral remotely sensed data. We analyse the neural networks approach applied to the estimation of chlorophyll concentration in coastal waters (Case II Waters) and discuss the use of two types of networks: the Radial Basis Function neural network and Multilayer Perceptron. We present a brief summary concerning their architectures and training methods. For proving the concept we analyse the procedures and the performances on a simulated data set reproducing the data acquired from the MERIS (Medium Resolution Imaging Spectrometer), the multispectral sensor on board the ENVISAT satellite. The multispectral subsurface reflectance data have been generated by means of a three component ocean colour direct model and statistically reproduce the case II waters. The neural networks performances have been analysed in terms of MSE (Mean Square Error), correlation coefficient and relative error. We provide a detailed discussion and comparison of the two types of networks and the obtained results confirm the effectiveness of the neural approach in such an application.

International Journal of Computer Mathematics, 1997

Standard backpropagation, as with many gradient based optimization methods converges slowly as ne... more Standard backpropagation, as with many gradient based optimization methods converges slowly as neural networks training problems become larger and more complex. In this paper, we present a new algorithm, dynamic adaptation of the learning rate to accelerate steepest descent. The underlying idea is to partition the iteration number domain into n intervals and a suitable value for the learning rate

Industrial Crops and Products, 2013

Expert Systems with Applications, 2011

Provided by UTHM Institutional Repository pelajar-pelajar yang sedang berada ditahun akhir pengaj... more Provided by UTHM Institutional Repository pelajar-pelajar yang sedang berada ditahun akhir pengajian mereka di Kolej Antarabangsa IKIP (IKIP), Kuantan, Pahang. Seramai 127 orang sampel daripada 191 orang jumlah populasi telah dipilih. Data yang diperolehi dianalisis menggunakan Perisian SPSS bagi mendapatkan analisis deskriptif skor min serta analisis statistik inferensi Ujian-t dan Ujian ANOVA. Hasil dapatan kajian menunjukkan bahawa tahap penguasaan ketiga-tiga kemahiran insaniah tersebut bagi pelajar di IKIP adalah berada ditahap yang tinggi manakala kaedah pengajaran dan pembelajaran yang berkesan untuk menerapkan ketiga-tiga kemahiran insaniah tersebut adalah sesi perbincangan secara bersemuka dengan pensyarah, sesi sumbangsaran (brainstorming) dan sesi membuat kajian kes. Kajian ini juga mendapati bahawa tidak terdapat perbezaan yang signifikan dari segi penguasaan kemahiran insaniah tersebut merentasi bidang pengajian dan jantina. Implikasi kajian ini akan dapat memberikan gambaran tentang kepentingan untuk menguasai kemahiran insaniah ini bagi pelajar, pusat pengajian dan para pensyarah.

Bioresource Technology, 2011

Sasaran kerajaan untuk menerima 36 juta ketibaan pelancong pada tahun 2020 memerlukan kira-kira 4... more Sasaran kerajaan untuk menerima 36 juta ketibaan pelancong pada tahun 2020 memerlukan kira-kira 497,000 tenaga kerja dalam sektor pelancongan. Dalam jumlah itu, 65 peratus daripada tenaga kerja memerlukan mereka yang berkelayakan sijil. Kementerian Pengajian Tinggi Malaysia telah memperkenalkan progam Sijil Kemahiran Khas Politeknik dalam Pengurusan Hotel & Katering pada tahun 2002. Kajian berbentuk deskriptif ini mengkaji kebolehpasaran graduan bermasalah pendengaran dalam industri hospitaliti di Malaysia dengan mengkaji impak pendidikan kemahiran khas terhadap kerjaya graduan bermasalah pendengaran dalam industri hospitaliti, tahap minat mereka dan juga mengkaji halangan yang menghadkan peluang graduan ini untuk bekerja dalam industri hospitaliti. Kajian ini melibatkan 70 orang responden yang merupakan graduan bermasalah pendengaran program Kemahiran Khas Pengurusan Hotel dan Katering di PIS dan juga 30 orang pengurus sumber manusia dari industri hospitaliti. Menggunakan soal selidik dan temu bual sebagai instrumen kajian, data dianalisa dengan menggunakan Statistical Packages for Social Sciences (SPSS) Version 17.0 bagi mendapatkan nilai peratusan, kekerapan dan purata skor min. Hasil dapatan menunjukkan impak pendidikan yang positif terhadap kerjaya graduan bermasalah pendengaran (Min=4.09). Tahap minat graduan juga berada pada tahap yang tinggi (Min=4.12). Halangan dan kekangan terdiri daripada masalah komunikasi, perasaan rendah diri, kekurangupayaan mereka dan layanan industri berada pada tahap yang tinggi (Min= 3.89). Dapatan ini juga disokong dengan dapatan dari temubual yang dijalankan. Secara keseluruhannya, walaupun pendidikan kemahiran khas membantu graduan meningkatkan kemahiran dan pengetahuan serta mempunyai minat untuk bekerja dalam industri, halangan dan kekangan yang ada menyebabkan tidak semua graduan berpeluang bekerja dalam industri hospitaliti. Majikan dalam industri hospitaliti diharapkan dapat mengubah persepsi terhadap golongan ini kerana mereka mempunyai kelayakan dan mampu bekerja dalam industri hospitaliti sekiranya diberi peluang. vi ABSTRACT Government's target to receive 36 million tourist arrivals by 2020 will require about 497,000 workers in the tourism sector. In total, 65 per cent of their workforce requires a qualified certificate. The Ministry of Higher Education has introduced a Special Skills Polytechnic Certificate program in Hotel Management & Catering in 2002. This descriptive study reviewed the hearing impaired employability of graduates in the hospitality industry in Malaysia to assess the impact of special skills education for hearing impaired graduate's career in the hospitality industry, the level of their interest and to study the barriers that limit opportunities for these graduates to work in the hospitality industry. The study involved 70 respondents who are hearing impaired graduates of Special Skills program in Hotel Management and Catering in the PIS and the 30 human resource managers from the hospitality industry. Using questionnaires and interviews as a research instrument, data were analysed using the Statistical Packages for Social Sciences (SPSS) Version 17.0 for the percentage, frequency and the average score. The findings show a positive impact on hearing impaired graduate's career in hospitality industry (Mean = 4:09). Graduate level of interest was also at a high level (Mean = 4.12). Obstacles and constraints includes communication problems, low self-esteem, their disability and hospitality industry acceptance at a high level (Mean = 3.89). This result is also supported by findings from interviews carried out. Overall, although the education of special skills to help graduates improve their skills and knowledge and they have a passion for working in the industry, but because of the barriers and constraints resulted not all graduates get the opportunity to work in the hospitality industry. Employers in the hospitality industry are expected to change the perception of these groups because they have the qualifications and ability to work in the hospitality industry if given the chance.

Applied Soft Computing, 2011

European Journal of …, 2009

The study of pedestrian flow is important to simulate pedestrian path which would help in the des... more The study of pedestrian flow is important to simulate pedestrian path which would help in the design of proper walking facilities to avoid disasters during panic and evacuation situations. To date, many models have been introduced which includes the Benefit Cost Cellular Model, Cellular Automata Model, Magnetic Force Model and the Social Force Model(SFM). The SFM is the most recent form of pedestrian model and is widely used in computer simulation software as the model is more realistic which is characterised by repulsion and attractive forces. The equations of pedestrian models are based on second order differential equations which can be solved using standard numerical techniques. This work uses the pedestrian simulation computer software, SimWalk, to study the simulation of pedestrian flow. This software can design pedestrian walking areas and simulate the movement of pedestrians in a crowd. SimWalk uses the SFM as its basic equation to find the pedestrian's path. The basic algorithm to design the pedestrian walking path in this software is the shortest-path algorithm where the pedestrian finds the shortest route to reach his/her destination after avoiding all the obstacles. The study of circumambulation of the Ka'aba is taken as an illustrative example, where performing Tawaf is one of the rituals when performing Hajj. The process of Tawaf involves circumambulating the Ka'aba seven times in a counter clockwise direction. The pilgrims face two main problems in this situation. The first is the overflowing of the pilgrims during the Hajj season. The large number of pedestrians will cause crowd congestion and may cause disasters as pedestrians push into each other. Elderly pilgrims and women face difficulties in completing the seven rounds. Secondly, entry into the Tawaf area is unlimited which causes pilgrims to flow in from various directions at the same time. This study suggests various mitigation measures to alleviate the problems associated to circumambulation of the Ka'aba. The entries into the Tawaf area are directed and limited and simulations are done using SimWalk to compare the differences of the time taken to complete the seven rounds. Simulating the Circumambulation of the Ka'aba using SimWalk 455

Bull. Malays. Math. Sci. …, 2002

Abstract. The past three decades has seen many mathematics departments adopting plans for the app... more Abstract. The past three decades has seen many mathematics departments adopting plans for the appropriate use of instructional technology tools in the learning and teaching of mathematics, and in the assessment of mathematics learning. A device that can be ...

Proceedings of The fourth International Conference on Information Science and Cloud Computing — PoS(ISCC2015), 2016

Applied Soft Computing, 2019

Cellulose, 2019

The social force model which belongs to the microscopic pedestrian studies has been considered as... more The social force model which belongs to the microscopic pedestrian studies has been considered as the supreme model by many researchers and engineers due to the main feature of its capability in reproducing the self-organization phenomena resulting from pedestrian dynamics. Recently, some principles of this model have been modified by other researchers to overcome a shortcoming that the model could not reproduce experimental data in normal situations such as the fundamental diagram. In this article, we argue that these principles are not the reasons for this shortcoming. And we clarify that the actual reason for this shortcoming is due mainly to the misunderstanding of the role of the pedestrian's perception of the objects surrounding him. And then, we present a typical approach to find the relation between the pedestrian's perception and the local density which helps in reproducing the fundamental diagram which conforms to the empirical data while conserving the principles of the social force model.

2008 International Conference on Electronic Design, 2008

Neurocomputing, 2011

Neural Computing and Applications, 2013

Neural Computation, 1999

International Journal of Remote Sensing, 2003

International Journal of Computer Mathematics, 1997

Industrial Crops and Products, 2013

Expert Systems with Applications, 2011

Bioresource Technology, 2011

Applied Soft Computing, 2011

European Journal of …, 2009

Bull. Malays. Math. Sci. …, 2002