Browsing Proceeding Papers by Title
Now showing items 1-20 of 22
-
An Adaptive Learning Algorithm for Supervised Neural Network with Contour Preserving Classification
(2009-11)
A study of noise tolerance characteristics of an adaptive learning algorithm for supervised neural network is presented in this paper. The algorithm allows the existing knowledge to age out in slow rate as a supervised neural network is gradually retrained with consecutive sets of new samples, resembling the change of application locality under a consistent environment. The algorithm utilizes the contour preserving classification algorithm to pre-process the training data to improve the classification and the noise tolerance. The experimental ... -
AIDE-adaptive instructional design model for E-learning
(2009-11)
Today, the new teaching and learning environment are changing because of an active usage of information technology. However, no matter how much technology becomes the essential element in learning, instructional designer has to consider the most appropriate methods to support an effective learning. The primary goal of instructional design is to guarantee the quality of online learning services by using technology-based instruction. In other words, the instructional design should be able to promote, facilitate, inspire deep learning and promote ... -
Applying logistic regression analysis: a study of the influential factors on consumers' purchasing decision toward mobile service provider in Bangkok, Thailand
(2009-10)
Logistic regression analysis is one of multivariate analysis where the outcome of dependent variable is categorical variable and the independents are quantitative variables, categorical variables, or both. The objective of this study was to propose the application of logistic regression analysis in order to identify the influential factors on consumers' purchasing decision among top three mobile service providers in Thailand: Advanced Info Service Public Col, Ltd (AIS), Total Access communication Public Col, Ltd (DTAC), and True Corporation ... -
Attitudes toward Student-Customer Concept: Educational Level, Institution Status and Interdisciplinary Studies
(2010-04)
The study explores student attitudes toward treating students as customers in fundamental and higher educations based on three units of analysis−educational levels (undergrad vs. graduate), institution status (public vs. private), and interdisciplinary (technology, engineering, and business). It also examines students’ opinions toward using the student-customer concept in higher education. Quantitative and qualitative data were analyzed to answer the research questions. The quantitative analysis results indicate that, in overall, students disagree ... -
Attitudes toward Using Communication Technologies in Education: A Comparative Study of Email and SMS
(2009-12)
Educational institutions deploy email and short message service (SMS) to maintain efficient communication with their students. This research examines factors influencing students' attitudes toward using SMS and email, and compares the differences in the proposed factors between email and SMS. The results show that information richness and mobility affect students' perceived utility of email and SMS while information privacy and perceived utility affect the students' attitudes toward using email and SMS. Social pressure has found no impact on ... -
Clustering Analysis on Alumni Data Using Abandoned and Reborn Particle Swarm Optimization
(2016-02)
Alumni data is one of the most important data that university management uses for developing the learning process decisions. This paper applies the idea of Abandoned and Reborn PSO (AR-PSO) to convert a clustering problem into the optimization form with an objective function to minimize the ugliness of the desired clusters. This algorithm of Clustering using AR-PSO (CAR-PSO) is slightly adapted to the cluster problem domain. The generated clusters need to be examined to decide if they are acceptable. There are three evaluations; the closeness, ... -
Clustering approach to examination scheduling
(2010-05)
The difficulty in examination scheduling is to draw an examination timetable by taking a number of different constraints into account. This paper attempts to optimize two major constraints-to minimize the examination time conflicts and the number of consecutive examinations for a student in a day. Clustering method is applied by analyzing exam enrollments and then groups students into clusters so that students within a cluster are having more similar subject combination to each others than those in another clusters. The purpose of clustering ... -
Diagnosing prostate cancer using backpropagation neural network and greedy decision procedure
(2010-05)
A novel procedure for diagnosing prostate cancer (PC) based on Back propagation Neural Network (BPNN) is proposed. Elderly men with symptoms such as urinary retention, urinary hesitancy, urinary dribbling, burning urination, hematuria, etc. are considered as primary attributes. Prostate-specific antigen (PSA) level and Gleason score are the secondary attributes. Initial dataset is generated based on the clinical database. The BPNN assigns symptom levels of a set of patients based on their primary attributes. A greedy decision procedure ... -
Dimension Independent Cosine Similarity for Collaborative Filtering using MapReduce
(2016-02)
DIMSUM, an efficient and accurate all-pair similarity algorithm for real-world large scale dataset, tackles shuffle size problem of several similarity measures using MapReduce. The algorithm uses a sampling technique to reduce `power items' and preserves similarities. This paper presents an improved algorithm DIMSUM+ with a complex sampling technique to enhance DIMSUM so that it is able to further reduce `power users'. The algorithm generates k-nearest-neighbor matrix that are used in collaborative based Recommender systems. The evaluations of ... -
Distance measurement with smartphone using acceleration model of hand movement
(2016-02)
This paper proposes a novel method to obtain the displacement of a smartphone movement. The method utilizes genetic algorithm to synthesize a mathematical model of acceleration based on behavior of a person's hand movement from the raw acceleration data. Then, double integration is performed on the synthesized acceleration model, which is significantly less affected by the noise accumulation. The raw acceleration of the hand's movement is calibrated initially using acceleration-time graph analysis and a modified version of peak detection based ... -
Energy Efficient Topology Control in Multi-hop Wireless Networks based on One-hop and Two-hop Neighbor Information
(2016-07)
Topology control in multi-hop wireless networks is a technique used to control nodes' activities to construct a topology with an acceptable level of network connectivity while minimizing energy consumption. It can be broadly classified into two main paradigms which are State Scheduling and Transmission Power Control. Both of them have received lots of attention from many researchers for decades. According to Transmission Power Control technique, most of them take into account only one-hop neighbor information to optimize transmission power ... -
Exploring the Effects of Openness to Experience and Theory of Consumption Values on Online Learning Adoption
(2016-04)
Personality traits and perceived product values are increasingly used to explain how people adopt innovative technologies. However, their relationships and effects on online learning adoption are ill-defined. This study investigates one of the common personality trait - openness to experience - and the value dimensions of theory of consumption values - functional (quality and monetary) value, social value, emotional value, epistemic value, and conditional value - to understand students’ intentions to adopt online learning. The study used a ... -
The impact of maketing communiation factors on consumers' purchasing decision of discout stores in Thailand
(2009-12)
The objective of this study is to investigate the marketing communication factors that impact on consumers' purchasing decision on discount store in Thailand. The multinomial logistic regression analysis was used and the attitude survey was conducted from 450 consumers have shopped among top three discount store operators: Tesco Lotus, Big C, and Carrefour. The results of this study show that the marketing communication factors in order to increase the customer base and make more market share in this segmentation. Tesco lotus should maintain ... -
An incremental learning algorithm for supervised neural network with contour preserving Classification
(2009-05)
This paper presents an alternative algorithm for integrating the existing knowledge of a supervised learning neural network with the new training data. The algorithm allows the existing knowledge to age out in slow rate as a neural network is gradually retrained with consecutive sets of new samples, resembling the change of application locality under a consistent environment. The algorithm also utilizes the contour preserving classification algorithm to increase the accuracy of classification. The experiment is performed on 2-dimension partition ... -
IT Design Skills Selection for Professional Development
(2016-02)
IT professionals in these days need to obtain multidisciplinary skill sets in order to succeed in their career. Design skill is considered as one of important characteristic for IT professionals. Many researches addressed design skill sets differently. This results in an increasing numbers of design skill items, in which some of those items have their meaning slightly different from each other. These long lists of design skill items can cause to long range of questionnaire. This study evaluates three techniques used for items selection which help ... -
Motion vector recovery for error concealment based on angular similarity
(2009-07)
This paper presents a motion vector (MV) recovery using the similarity of the angle of the corresponding surrounded MVs. The approach is based on the assumption that a group of macroblocks (MBs) which belongs to the same object and resides in the same region likely to move in the same direction. hence, those corresponded MVs that move in the same direction likely to have similar angle. As a result a lost motion vector can be estimated using a set of candidate MVs selected from the neighbouring MVs on the left, top-left, top, top-right, right, ... -
Multi-class contour preserving classification
(2012-08)
The original contour preserving classification technique was proposed to improve the robustness and weight fault tolerance of a neu- ral network applied with a two-class linearly separable problem. It was recently found to be improving the level of accuracy of two-class classi- fication. This paper presents an augmentation of the original technique to improve the level of accuracy of multi-class classification by better preservation of the shape or distribution model of a multi-class problem. The test results on six real world multi-class ... -
A Novel Adaptive Topology Control in Mobile Ad Hoc Networks based on Connectivity Index
(2015-11)
Mobile ad hoc networks or MANETs are infrastructureless wireless networks where each node can freely move and directly connect to the other nodes located within its transmission range to form the topology in any arbitrary pattern. Hence, to ensure network connectivity, each node tends to use the maximum transmission power to extend its transmission range. However, this maximized transmission range typically consumes more energy and consequently drains battery faster on mobile devices in these networks. Topology control is an effective technique ... -
Performance evaluation on multimedia traffic for DVB-RCS over satellite links
(2009-12)
Adaptive Rate Control (ARC) is a successful algorithm to increase the throughput to The Digital View Broadcasting Return Channel via Satellite (DVB-RCS) but the throughput and dropped traffic did not meet the Quality of Service (QoS) for multimedia traffic standard [ETSI EN 300 421 v.1.1.2]. This paper will present the modified ARC algorithm to overcome the QoS problem for multimedia traffic by prioritize dropped traffic to retransmit as voice, video, and data through the system. This modified mechanism will guarantee a certain level of QoS to ... -
A Self-Growing and Self-Organizing Batch Map with Automatic Stopping Condition
(2013)
This paper proposes a model of self-growing and self-organizing feature map designed to alleviate the difficulty of predetermining an appropriate size and shape of the feature map suitable for the input data in the applications of the Self-Organizing Map. The proposed model progressively builds a feature map by incremental growing of the network in a way that maintains two-dimensional regular grid structure and gradual adaptation of the reference vectors by coordinated competitive learning dynamics of the Batch Map algorithm. Experimental results ...