Issue 1, Volume 1, 2007

Hierarchical frame and frameset components for visual programming of web applications
by Quan Liang Chen and Takao Shimomura

Abstract: By using the HTML frame facility, Web applications can display a lot of information on one Web page at a time and show it to users. This paper presents a methodology that makes it possible to visually design and program Web applications that use frame facilities. The BioPro system that implements this methodology newly provides Frameset page design windows with which we can design Web pages that represent a frameset consisting of several frames and other framesets. We design the contents of ordinary Web pages using Web page design windows. Each frame of a Frameset page design window has a link to the Web page that is displayed in the frame. The system generates Web application program code from these Frameset page design windows and the Web page design windows. Frameset page design windows provide several editing facilities such as adding, deleting, changing, and nesting of framesets to make it easier to develop Web applications that use frame facilities.
Keywords:
Automatic generation, HTML frames, HTML framesets, web application, web components
Full Paper, pp. 1-7



Initial Stage of Vapor Bubble Growth in Superheated Liquids
by D.Turlajs, V.Grivcovs, S.Yaundalders

Abstract: The given report deals with problems of nucleate pool boiling investigations of liquids with presence of solid heating surfaces. Problems of liquid to vapor phase change are actual both in theoretical and experimental investigations at least last 50-60 years due to extremely high importance of phenomena in different technical and scientific applications. A lot of researches are devoted to problems of vapor bubble growth dynamic, which is one of the most important parameters of total phenomena indexes. Dominating in special technical literature vapor bubble growth models are describing so called asymptotic stage of bubble radius versus time ()(lafR), where bubble growth speed is decreasing. Logically, bubble growth speed ddR/somewhere in initial stage of evolution have to be maximal. To find these correlations, we try to us
Full Paper, pp. 9-11

 

An Approach of Condition Monitoring of Induction Motor Using MCSA
by Neelam Mehla, Ratna Dahiya

Abstarct: With the industrial growth, it has become necessary to monitor the condition of the machine/system. Electrical machine being the most sensitive part has great importance for the researcher to monitor the faults diagnosis. Three phase squirrel cage motor is normally use for industrial purposes. Various techniques are used to control the speed such as DTC (Direct Torque Control), Vector Control, Close Loop Feedback Control etc. Small single phase Induction machine are used for home appliances hence the machine monitoring plays an important role for industrial as well as domestic appliances growth. Various fault detection method has been used in past two decades. Special attention is given to non-invasive methods which are capable to detect fault using major data without disassembly the machine. The Motor Current Signature Analysis (MCSA) is considered the most popular fault detection method now a day because it can easily detect the common machine fault such as turn to turn short ckt, cracked /broken rotor bars, bearing deterioration etc. The present paper discusses the fundamentals of Motor Current Signature Analysis (MCSA) plus condition monitoring of the induction motor using MCSA.
Keywords:
Condition Monitoring, Direct Torque Control, Control
Full Paper, pp. 13-17

 

Issue 3, Volume 1, 2007

Tropical Peat Swamp Forest Ecosystem and Floristic Diversity in Pahang, Malaysia
by Kamaruzaman Jusoff, Che Hashim Hassan and Khali Aziz Hamzah

Abstract: Peat swamp forests are highly significant globally, both for their diverse and threatened species and as representative unique ecosystems. Apart from its critical role in providing habitat for wildlife, the tropical peat swamp forest also acts as a gene bank that harbours potentially useful varieties of plant species. Malaysia’s peat swamp forests also provide crucial benefits and services for the sustainable development of human communities. The objective of the study is therefore to assess the status of the remaining peat swamp forest ecosystem and floristic biodiverstity in Pahang towards the efforts in establishing guidelines for its sustainable management and conservation. This collaborative study was undertaken by the Pahang Forestry Department, United Nation Development Programme/Global Environment Facility (UNDP/GEF)
Keywords:
Automatic generation, HTML frames, HTML framesets, web application, web components
Full Paper, pp. 41-44

 

Multi-Dimensional Features Reduction of PCA on SVM Classifier for Imaging Surveillance Application
by Tan Chue Poh, Nur Fateha Muhamad Lani, Lai Weng Kin

Abstract: This paper presents the application of multi dimensional feature reduction of Principal Component Analysis (PCA) and Support Vector Machine (SVM) classifier for imaging surveillance system. Recently, research in image processing has raised much interest in the security surveillance systems community. Weapon detection is one of the greatest challenges facing by the community recently. In order to overcome this issue, application of the popularly used SVM classifier is performed to focus on the need of detecting dangerous weapons. However, PCA is used to explore the usefulness of each feature and reduce the multi dimensional features to simplified features with no underlying hidden structure. In this paper, we take advantage of the simplified features and classifier to categorize images object with the hope to detect dangerous weapons effectively. In order to validate the effectiveness of the SVM classifier, several classifiers are used to compare the overall accuracy and computational speed of the system with the compliment from the features reduction of PCA. These classifiers include Neural Network, Decision Trees, Naïve Bayes and k-Nearest Neighbor methods. The final outcome of this research clearly indicates that SVM has the ability in improving the classification accuracy using the extracted features. Besides, it is also shown that PCA is able to speed-up the computational time with the reduced dimensionality of the features while maintaining the classification accuracy.
Keywords:
Support Vector Machine, Classification, Imaging surveillance
Full Paper, pp. 45-50

 

Crack growth prediction in a thick cylinder under fatigue loading – an FEA
by I. Salam, M. Abid, M.A. Malik

Abstract: This paper presents numerical study to predict crack growth rate under fatigue loading in a thick cylinder made of an aluminum alloy. Experimental fatigue crack growth data on middle tension (MT) samples available was applied to simulate and predict crack growth process using detailed 2-dimensional parametric finite element technique. The fatigue crack propagation was simulated based on linear elastic fracture mechanics and stress intensity factor determination. Finite element model provides results of crack growth analysis optimized for the stress levels of 40 to 25 % of the yield stress of the material. Results are plotted on SN curves and the disparity was explained in terms of crack growth rates near threshold stress intensity factor range.
Keywords:
Aluminum alloy, fatigue, crack growth, FEA, fracture mechanics.
Full Paper, pp. 51-55

 

Factors Decomposition of Energy Intensity: The case of Liaoning province in China
by He Yong-Xiu, Tao Wei-Jun, Zhang Song-Lei, Li Yan and Li Fu-Rong

Abstract: This paper introduces logarithmic mean Divisia index (LMDI) method on calculating factors contribution to energy intensity (EI) change and indicates that sector intensity contribution and efficiency contribution are different. Then this paper adopts LMDI to analyze the decrease of EI in Liaoning Province, the heavy industry base in northeast China. The results show that the sector intensity decline played a major role to the EI decline in Liaoning according to the division of three industries. When considering the product structure and product energy efficiency, the efficiency contribution share is 22.31%, and the product structure contribution share is 77.57% of the total EI decrease during 2000-2005. This revealed that structure change played a key role on the EI decline in Liaoning province. Finally, Reasonable proposals are given for Liaoning Province to achieve the energy-saving target in the 11th Five-Year Plan period.
Keywords:
Aluminum alloy, fatigue, crack growth, FEA, fracture mechanics.
Full Paper, pp. 56-61

 

Modeling and Design of Control System for Variable Speed Wind Turbine in All Operating Region
by Wu Dingguo and Wang Zhixin

Abstract: In order to get the maximum power from the wind, the variable-speed wind turbine should run at different speed when wind speed changes. In this paper a control system is introduced to get this purpose base on establishing the three-mass model of the wind turbine. The control system consists of two parts: one is a speed controller for generator control; the other is a PI controller for pitch control. Simulation results by using actual detailed parameters for wind turbine show the effectiveness and robustness of this control system.
Keywords:
three-mass model, feed-forward compensator, loop-shaping, speed controller, pitch controller, wind turbine, doubly-fed induction generator (DFIG).
Full Paper, pp. 62-68

 

“False Idol” Economy: The New Zealand Wine Industry
by Garry Clayton and Natalie Stevens

Abstract: The New Zealand Wine Industry is desperately attempting to portray itself as a major force of the national economy worth “idolising” for its stunning growth and success. It triumphs the fact that it produces over a billion glasses of wine per year and generates over a billion dollars in revenue. While it rightly highlights its successes the industry has unconsciously exposed the fact that it is a “false idol” with nearly 90% of its producers being uneconomic.The industry blames the burdens of excessive taxation and inflated exchange rate not business practises for poor performance and campaigns to change the regulatory and fiscal framework that the industry operates in. Seductive though the argument and reasoning appears, it is false. A critical review of the industry highlights that it lacks scale and poor utilizes capital investment. This paper carefully reviews the nature of the New Zealand wine industry, the perceptions of its success, the misdiagnosis of business challenges, and the identification of alternative options for sustainable business success.
Keywords:
Strategic Management, New Zealand, Wine Industry, Sustainability.
Full Paper, pp. 69-74

 

 

 

Issue 2, Volume 1, 2007

Advanced Processing of UPM-APSB’s AISA Airborne Hyperspectral Images for Individual Timber Species Identification and Mapping
by Kamaruzaman Jusoff

Abstarct: UPM-APSB’s AISA airborne hyperspectral imaging offers the possibility of identifying and characterizing commercial and non-commercial individual timber species in the Malaysian tropical high mountain forests on the basis of the unique reflectance patterns that result from the interaction of solar energy with the molecular structure of the tree crowns. In this paper, a seminal view on recent advances in techniques for hyperspectral data processing was provided. It examines the performance of image processing techniques specifically developed for hyperspectral data in the context of individual timber species inventory mapping applications. The area chosen, located in Berangkat Forest Reserve, Kelantan near the locality of Kompleks Perkayuan Kelantan sawmill, had relatively virgin dense forest stand density at the time of imagery acquisition (dry month). The main focus is on the development of approaches able to naturally integrate the spatial and spectral information available from the hyperspectral data. Special attention is paid to techniques that circumvent the curse of dimensionality introduced by high-dimensional data spaces. Image processing was carried out in two steps, namely data conversion from radiance units to reflectance using a radiative transfer method and application of the mapping algorithm, specifically designed for identifying superficial materials based on similarities between image pixels and spectra from a spectral library of timber species. Experimental results, focused in this work on a specific case-study of individual timber species data analysis, demonstrate the success of the considered techniques. The results show that UPM-APSB’s AISA airborne hyperspectral imaging can identify 22 individual species in Block 53, Berangkat F.R and separated damar from non-damar group of species. Kelat constituted the highest count of species (1,402) mapped followed by Kedondong (1,185 trees), Medang (1,116 trees) and others out of the total 13,861 trees. It is therefore a valuable tool for mapping and quantification of individual tree in tropical dense virgin forested regions. This paper represents a first step towards the development of a quantitative and comparative assessment of advances in UPM-APSB’s AISA airborne hyperspectral data processing techniques.
Keywords: Fragile ecosystem, Arid mangroves, Community participation, Conservation.
Full Paper, pp. 21-27

 

Motor Current Signature Analysis and its Applications in Induction Motor Fault Diagnosis
by Neelam Mehla, Ratna Dahiya

Abstarct: The Motor Current Signature Analysis (MCSA) is considered the most popular fault detection method now a day because it can easily detect the common machine fault such as turn to turn short ckt, cracked /broken rotor bars, bearing deterioration etc. The present paper discusses the fundamentals of Motor Current Signature Analysis (MCSA) plus condition monitoring of the induction motor using MCSA. In addition, this paper presents four case studies of induction motor fault diagnosis. The results show that Motor current signature analysis (MCSA) can effectively detect abnormal operating conditions in induction motor applications.
Keywords:
Condition Monitoring, Direct Torque Control, Control, Fault Diagnosis
Full Paper, pp. 29-35

 

Issue 4, Volume 1, 2007

Mangrove Conservation through Community Participation in Pakistan: The Case of Sonmiani Bay
by Amjad, A. Shah and Kamaruzaman Jusoff

Abstract: Being fragile ecosystem, mangroves are under threats throughout the world. Various techniques and methodologies are under vogue in different countries for conservation of mangroves. Local communities as an important stakeholder can play effective role in mangroves conservation. As in the case of Pakistan, the Indus delta alone spread over 0.6 million ha and has mangroves over an area of 0.16 million ha along the coastline. The most significant characteristic of Indus delta is that it receives an average of only about 220 mm of rainfall per year, and sometime no rainfall at all. Sonmiani is the only place along the coast of Pakistan where three species of mangroves viz-a-viz Avicennia marina, Ceriops tagal and Rhizophora mucronata exist naturally. The mangrove forests are used for fuel wood, fodder for cattle and browsing areas for camels.Despite the area is subjected to grazing and fuel wood collection, different techniques were developed to restore the mangrove ecosystem through community participation with the assistance of WWF-Pakistan and local NGOs. Local community, whose main profession is fishing, has planted a considerable degraded area with mangroves, thus playing their role in protection and conservation of mangroves for future young Pakistani generations
Keywords:
Fragile ecosystem, Arid mangroves, Community participation, Conservation.
Full Paper, pp. 75-81

 

Use of Ferrofluids for Bushing Cooling and On-Line Monitoring
by S.D. Nedelcut, V. Proca, D.M. Purcaru

Abstract: This paper reviews all the advantages of the on-line monitoring and presents an equipment for on-line monitoring of bushings, which is the own contribution of specialists who are the authors of this paper. The paper presents a study of the temperature field, using the finite element method. For carrying out this study, the 3D modelling of the above mentioned bushing was performed. The analysis study is done taking into account the extreme thermal stresses, focusing at the level of the first cooling wing section of the ceramic insulator. This fact enables to justify the tan variation in time, depending on the transformer loading and the environmental conditions. With a view to reducing the variation of dielectric losses in bushing insulation, the use of ferrofuids instead of mineral oils is proposed.
Keywords:
monitoring, dielectric losses, ferrofluids, bushing
Full Paper, pp. 82-90

 

New Methods for Reliability Prediction at Nuclear Complex System (NCS)
by Vasile Anghel

Abstract: The reliability level for a nuclear installation is given in generally by the technological process quality of operation and maintenance and in particular by a lot of technical, technological, economic and human factors. The maintenance role is fundamental for a nuclear installation. In the maintenance activity as in any dynamic area, appear continuously new elements which, sometimes, require new methods of approach, thus for considered installation that is a Nuclear Detritiation Plant (NDP) existent as part of National Research and Development Institute for Cryogenics and Isotopic Technologies – ICSI, Rm.Valcea, for assurance the reliability level in operation is proposed for predictive maintenance the theory fuzzy, entropy theory and software LabVIEW. The final aim is to achieve the best practices for maintenance of Plant that process tritium.
Keywords:
LabVIEW, nuclear, reliability, simulation
Full Paper, pp. 91-99

 

Production yield improvement in a series system by a multithreshold CBM model
by Mosè Gallo, Guido Guizzi, Pasquale Zoppoli

Abstract: In many manufacturing environments, equipment condition has a significant impact on product quality, or yield. In this work it has been studied the case of a series of Pick and Place machines, characterized by a high value of basic components. So, in this kind of process it’s necessary to rework all refused units caused by defective assembling. The approach we used in this work consider a condition based maintenance (CBM) model which is able to determine when it is economically convenient to make a preventive maintenance intervention on the machine in function of the number of refused units per unit of time produced by the process. We used the defection rate (number of refused units per unit of time produced by the process) as a parameter to decide when it’s convenient to stop the machines, wich are in a series: so, every time one is stopped, it’s neeeded to stop them all. We modeled the cost of the system and its productive behavior by an event driven simulator. The cost optimization consists in determining, by simulation, at what value the threshold (defection rate) should be fixed to minimize the overall maintenance and rework cost. The proposed model has clearly demostrated to improve the efficience of the process respect the nowaday, experienced based, management, but also respect a model based on the optimizing of the processes yield present in scientific literature.
Keywords:
LabVIEW, nuclear, reliability, simulation
Full Paper, pp. 100-111

 

Data Driven Simulation in the Health and Hospital Field: a Model for the “G. Gaslini” Clinical Pathology Laboratory Workout
by Roberto Revetria, Pietro Giribone, Francesca Oliva, Maurizio Schenone

Abstract: The use of IT tools and simulation in the health and hospital field is growing up to improve the efficiency and reduce the costs. The concepts used in the simulation of hospitals are more or less the same of those used in the industrial system’s one, but in the first there are more variability connected to the high presence of human intervention. This leads to the use of logic-type models, with the simulator built up according to the Data Driven Simulator approach. In this paper an applicative case will be analysed regarding the building of a simulation model of the Clinical Pathology Laboratory of the “G. Gaslini” Paediatric Institute, and .
Keywords:
ANOVA, Clinical Laboratory, Data Driven Simulation, Lagrange philosophy, Montecarlo.
Full Paper, pp. 112-119

 

An experiment of Life-support network for elderly people living in a rural area
by Jun Sasaki, Keizo Yamada, Michiru Tanaka and Yutaka Funyu

Abstract: In order to provide comfortable and safety life for every people in the world, information technologies will be useful in a rural area as well as in a metropolitan area. This paper proposes a new concept of Life Support Network (LSN) for elderly people living in a rural area. The network is a type of Intranet, which incorporates a safety confirmation system, a remote healthcare system, an emergency information system and other useful daily network services in the closed life area. We developed a part of the experimental LSN system and carried out a field experiment in a typical rural town “Shiwa” in the Iwate Prefecture in Japan. The system has two sub-systems of the safety confirmation system and the remote healthcare system. We clarified that the experimental LSN gave the feeling of safety to the elderly people living in the rural area.
Keywords:
Information System, Healthcare System, Welfare System, Telemedicine
Full Paper, pp. 120-124

 

An integrated approach to locate and allocate production and distribution sites by using simulation models
by Elpidio Romano, Liberatina C. Santillo, Pasquale Zoppoli

Abstract: In spite of an increasing development of applied mathematics to the theory of location, just a few applications have been done about support to decision regarding the location of production and/or selling sites. This paper aims at localization of a firm, that will produce controlled leavening baking products, and its kiosks (selling points), displaced on a municipality area. To make the choice, it’s been considered the double function of the kiosk: it is a restocking point and it will be necessary to study the optimal path from the production point, that is considered known, to the kiosk itself; it is also a selling point, so it has to be located where it’s mostly perceived by the customers. The two choice dimensions, regarding an unique location, need the creation of a model able to represent the scenarios dynamism of reality. As the location of production points has been supposed known, it’s been studied the problem of kiosks location, by the optimization of attracting capacity and by minimizing the restocking cost from the production point. So, it’ been simulated a quantitative model to represent the choice behaviour of different categories customers to move in the urban area. The simulation model output gives the traffic flows on the network, where the production system (manufacturing and selling points) has been located. These results give also the inputs for a second model used to define the optimal paths on the same network. In this way, the choice model for the best path from production to selling point is able to consider the network loads. The interaction between the two models will also be useful to define the localization of the whole production system, estimating the dimension of each production and selling point.
Keywords:
logistic network, location routing, vehicle routing, simulation.
Full Paper, pp. 125-136

 

An integrated approach to develop a simulation model in manufacturing processes
by M. Gallo, G. Guizzi, V. Zoppoli

Abstract: The present paper faces the problem of simplifying simulation tools management in their industrial applications. An approach to implement efficiently and effectively simulation models in manufacturing systems, as decision support system, is deployed. The framework proposed is very flexible and easy to use because of the building block architecture and the automatic model generation. This model is focused on operational decisions as those concerning with scheduling problems.
Keywords:
Event-driven simulation, Quick modeling, Manufacturing process, Scheduling
Full Paper, pp. 137-145

 

A heuristic algorithm for the constrained location - routing problem
by L. Guerra, T. Murino and E. Romano

Abstract: The logistics system of a firm deals with purchasing materials (acquisition logistics), controls work in process in each production phase (production logistics system), through the distribution management, it controls the flow of the products delivered to the customer (distributive logistics), defines the backtracking of a discarded, disused or damaged product, to reemploy its parts or materials (reverse logistics). The structures displaced within the logistics network must guarantee an opportune level of service and the cutback of logistics costs. Transport system performance are, therefore, of primary importance, as well as the location of the distribution centers and products distribution issues. In literature they are present accurate mathematical models and effective solution techniques to face location, allocation and distribution problems. The topic is still of extreme interest because of the increasing structural complexity of the models due to the constraints imposed by the “real systems” representation. Integrated location routing models are used to solve the facility location problem (FLP) and the vehicle routing problem (VRP) simultaneously so to reflect the interactions between the two decisions. In this paper, particularly, a possible approach (the TSPVRP heuristic) will be proposed to optimize the routing phase in a Location-Routing Problem (LRP). Results are compared with those obtainable turning to other commonly adopted procedures.
Keywords:
Distributive Logistics, Location-Routing Problem, Traveling Salesman Problem, Vehicle Routing Problem.
Full Paper, pp. 146-154

 

An Agent-based System for Sales and Operations Planning in Manufacturing Supply Chains
by Massimo Paolucci, Roberto Revetria, Flavio Tonelli

Abstract: A major problem faced by manufacturing organizations is providing efficient and cost-effective responses to the unpredictable changes taking place in global markets and in supply chains. Sales and Operations Planning helps giving better customer service, lower inventory, shorten customer lead times, stabilized production rates providing top management with a handle on the business and supporting a company to get and keep demand and supply in balance over time. This paper proposes a multi-agent based system that would enable small and medium-size manufacturing organizations to dynamically achieve cost-effective aggregate sales and operations plans in supply chain contexts. In supply chain operations planning, the simulation of the agent’s interactions supports planners, ,providing multiple scenarios with respect to the balance between supply and demand. This paper presents the main features of the proposed system and it finally discusses the benefits and limitations highlighted by its application in real industrial contexts.
Keywords:
Supply Chain Operations Planning, Decision Support System, Scenario Based Analysis, Multi-Agent System.
Full Paper, pp. 155-163

 

An Agent-based System for Sales and Operations Planning in Manufacturing Supply Chains
by Massimo Paolucci, Roberto Revetria, Flavio Tonelli

Abstract: A major problem faced by manufacturing organizations is providing efficient and cost-effective responses to the unpredictable changes taking place in global markets and in supply chains. Sales and Operations Planning helps giving better customer service, lower inventory, shorten customer lead times, stabilized production rates providing top management with a handle on the business and supporting a company to get and keep demand and supply in balance over time. This paper proposes a multi-agent based system that would enable small and medium-size manufacturing organizations to dynamically achieve cost-effective aggregate sales and operations plans in supply chain contexts. In supply chain operations planning, the simulation of the agent’s interactions supports planners, ,providing multiple scenarios with respect to the balance between supply and demand. This paper presents the main features of the proposed system and it finally discusses the benefits and limitations highlighted by its application in real industrial contexts.
Keywords:
Supply Chain Operations Planning, Decision Support System, Scenario Based Analysis, Multi-Agent System.
Full Paper, pp. 155-163

 

Appraisal of Course Learning Outcomes of Course Learning Outcomes Using Rasch Measurement: A Case Study in Information Technology Education
by Azrilah AbdulAziz, Azlinah Mohamed, NoorHabibah Arshad, Sohaimi Zakaria and MohdSaidfudin Masodi

Abstract: The development of Rasch measurement model in social science educational measurement has rapidly expanded to other areas of education including technical and engineering fields. This paper is an attempt of a paradigm shift in testing and evaluation in it education towards bio-based Rasch model. It is believed compatibility exist with the fundamental measurement currently used based on Kuhn’s explanation on the role of measurement; in particular, Learning Performance Measurement System (LPMS). These cannot be gleaned from textbooks in engineering science or statistics. Taking the paradigm shift, faculty A, in one of Malaysian Institution of Higher Learning has embarked on the application of Rasch model to measure the achievement of it’s Course Learning Outcomes (CLO) -Decision Support System, as a pre-requisite stipulated in the newly enacted Malaysia Qualification Framework, 2005 (MQF). Rasch model tabulates the students; i.e. Person and Items on a distribution map (PIDM) which gives a precise overview of the student’s achievement on a linear scale for measurement. Comparative analysis against the traditional histogram tabulation and simple mean shows that Rasch measurement was found to give a better exploratory depth in understanding problems in information technology education. Despite the small sample size, the students were clearly categorized according to the respective cognitive skills hence; CLO’s which was structured based on Bloom’s taxonomy. Subsequently, it is possible to extend this approach in assessment of generic skills in students or professionals. This leads to a new paradigm in assessing competency of individuals using Rasch model.
Keywords:
Rasch Model, Course Learning Outcomes, Kuhn paradigm, continuous improvement, quality education.
Full Paper, pp. 164-172

 

Function Approximation Using Artificial Neural Networks
by Zarita Zainuddin and Ong Pauline

Abstract: Function approximation, which finds the underlying relationship from a given finite input-output data is the fundamental problem in a vast majority of real world applications, such as prediction, pattern recognition, data mining and classification. Various methods have been developed to address this problem, where one of them is by using artificial neural networks. In this paper, the radial basis function network and the wavelet neural network are applied in estimating periodic, exponential and piecewise continuous functions. Different types of basis functions are used as the activation function in the hidden nodes of the radial basis function network and the wavelet neural network. The performance is compared by using the normalized square root mean square error function as the indicator of the accuracy of these neural network models.
Keywords:
function approximation, artificial neural network, radial basis function network, wavelet neural network
Full Paper, pp. 173-178