Search

The fuzzy C-ordered-means clustering (FCOM) is a fuzzy clustering algorithm that enhances robustness and clustering accuracy through the ordered mechanism based on fuzzy C-means (FCM). However, despite these improvements, the FCOM algorithm’s effectiveness remains unsatisfactory due to the significant time cost incurred by its ordered operation. To address this problem, an investigation was conducted on the ordered weighted model of the FCOM algorithm leading to proposed enhancements by introducing the beta distribution weighted fuzzy C-ordered-means clustering (BDFCOM). The BDFCOM algorithm utilises the properties of the Beta distribution to weight sample features, thus not only circumventing the time cost problem of the traditional ordered mechanism but also reducing the influence of noise. Experiments were conducted on six UCI datasets to validate the effectiveness of the BDFCOM, comparing its performance against seven other clustering algorithms using six evaluation indices. The results show that compared to the average of the other seven algorithms, BDFCOM improves about 15 percent on F1-score, 11 percent on Rand Index, 13 percent on Adjusted Rand Index, 3 percent on Fowlkes-Mallows Index and 16 percent on Jaccard Index. For the other two ordered mechanism FCM algorithms, the time consumption was also reduced by 90.15 percent on average. The proposed algorithm, which designs a new way of feature weighting for ordered mechanisms, advances the field of ordered mechanisms. And, this paper provides a new method in the application field where there is a lot of noise in the dataset

Dengue is a virus that is spreading quickly and poses a severe threat in Malaysia. It is essential to have an accurate early detection system that can trigger prompt response, reducing deaths and morbidity. Nevertheless, uncertainties in the dengue outbreak dataset reduce the robustness of existing detection models, which require a training phase and thus fail to detect previously unseen outbreak patterns. Consequently, the model fails to detect newly discovered outbreak patterns. This outcome leads to inaccurate decision-making and delays in implementing prevention plans. Anomaly detection and other detection-based problems have already been widely implemented with some success using danger theory (DT), a variation of the artificial immune system and a nature-inspired computer technique. Therefore, this study employed DT to develop a novel outbreak detection model. A Malaysian dengue profile dataset was used for the experiment. The results revealed that the proposed DT model performed better than existing methods and significantly improved dengue outbreak detection. The findings demonstrated that the inclusion of a DT detection mechanism enhanced the dengue outbreak detection model’s accuracy. Even without a training phase, the proposed model consistently demonstrated high sensitivity, high specificity, high accuracy, and lower false alarm rate for distinguishing between outbreak and non-outbreak instances.

This article provides a brief yet comprehensive review of Conference Management Systems (CMS), showcasing widely-used platforms such as EasyChair, ConfBay, OpenConf, Microsoft CMT, COMS, and EDAS—tools commonly employed by conference organizers. The strengths and features of each platform are explored, with a focus on key aspects such as paper submission, the review process, registration, agenda and program management, virtual conference support, proceedings, and email communication. Through this comparative analysis, the diverse functionalities and distinctive contributions of each CMS become evident, offering valuable insights for conference organizers to make well-informed decisions tailored to their specific event requirements. For instance, EasyChair is recognized for its user-friendly interface and the inclusion of the Virtual Conference Support (VCS) feature, addressing the growing trend of virtual and hybrid events. ConfBay positions itself as a user-friendly CMS with customizable features, while OpenConf offers versatility through its Community, Plus, and Professional Editions. This review highlights the unique strengths of each CMS, empowering organizers with a deeper understanding of their capabilities. The adaptability of these systems to the evolving landscape of academic and scientific events is a central theme, underscoring their potential to significantly contribute to the success and efficiency of conferences globally. Ultimately, this analysis serves as a valuable resource for navigating the complex landscape of CMS platforms, guiding organizers toward optimal choices aligned with their unique event management needs.

This paper discusses a unique business model of eatery recommended system based on local knowledge using mobile platform. The business model is developed to define the business concept of the innovation which is a rural innovation involving multiple entities (locals, eatery owners and users who are searching for eatery). The innovation highlights on local knowledge crowd sourced from the participation of locals through ramification activities included in the mobile app. In achieving the aim, the design science methodology was adapted in this study which consists of 4 phases: (i) Awareness of Problem, (ii) Suggestion, (iii) Evaluation, and (iv) Conclusion. The proposed business model was developed through a few activities including literature review, comparative study and preliminary study. Then, the study continued with developing a prototype known as Makan@Local Chatok (M@LC) app and evaluated the app in terms of its usability aspects. Results from the usability testing concludes that the app is perceived as easy to use. It was also found that the proposed business model has been well-accepted by users. In conclusion, it is hoped that this study will not only demonstrate the potential and impact of mobile eatery recommendation system using local knowledge, but also provide a capstone on business research in the field of tourism industry.

Time series forecasting is a method of predicting the future based on previous observations. It depends on the values of the same variable, but at different time periods. To date, various models have been used in stock market time series forecasting, in particular using deep learning models. However, existing implementations of the models did not determine the suitable number of previous observations, that is the window length. Hence, this study investigates the impact of window length of long short-term memory model in forecasting stock market price. The forecasting is performed on S&P500 daily closing price data set. A different window length of 25-day, 50-day, and 100-day were tested on the same model and data set. The result of the experiment shows that different window length produced different forecasting accuracy. In the employed dataset, it is best to utilize 100 as the window length in forecasting the stock market price. Such a finding indicates the importance of determining the suitable window length for the problem in-hand as there is no One-Size-Fits-All model in time series forecasting.

—CSR UUMWiFi is a CSR project under Universiti Utara Malaysia (UUM) that provides unlimited free internet connection for the Changlun community launched in 2015, the service has accumulated a huge number of users with diverse background and interest. This paper aims to uncover interesting service users’ behavior by mining the usage data. To achieve that, the access log for 3 months with 24,000 online users were downloaded from the WiFi network server, pre-process and analyzed. The finding reveals that there were many loyal users who have been using this service on a daily basissince 2015 and the community spent 20-60 minutes per session. Besides that, the social media and leisure based application such YouTube, Facebook, Instagram, chatting applications, and miscellaneous web applications were among the top applications accessed by the Changlun community which contributes to huge data usage. It is also found that there were few users have used the CSR UUMWiFifor academicor business purposes. The identified patterns benefits the management team in providing a better quality service for community in future and setting up new policies for the service.

In dendrite cell algorithm (DCA), the abnormality of a data point is determined by comparing the multi-context antigen value (MCAV) with anomaly threshold. The limitation of the existing threshold is that the value needs to be determined before mining based on previous information and the existing MCAV is inefficient when exposed to extreme values. This causes the DCA fails to detect new data points if the pattern has distinct behavior from previous information and affects detection accuracy. This paper proposed an improved anomaly threshold solution for DCA using the statistical cumulative sum (CUSUM) with the aim to improve its detection capability. In the proposed approach, the MCAV were normalized with upper CUSUM and the new anomaly threshold was calculated during run time by considering the acceptance value and min MCAV. From the experiments towards 12 benchmark and two outbreak datasets, the improved DCA is proven to have a better detection result than its previous version in terms of sensitivity, specificity, false detection rate and accuracy.

This paper describes the design and development of data retrieval system using near field communication (NFC) protocol to read and transfer data from the device storage panel located at the recycle bin. In existing systems, data are manually collected from the storage device using the SD card and sent for upload to regional workstation of the data center, which is located at the central server. The device automatically establishes the NFC connection with the recycle bin panel and once the connection is established, data will automatically be transferred to the device and the current data storage in the recycle bin will be erased. Next, the collected data will be uploaded to the server through regional workstation

As a response to the government effort to bridge digital divide and democratising access to the Internet, particularly in rural area, Universiti Utara Malaysia (UUM) has taken a proactive step to provide free wireless internet connection for Sintok-Changlun community known as CSR UUMWiFi. It is the first local public university in Malaysia that provides such service as part of its corporate social responsibility.In this paper, an investigation towards CSR UUMWiFi was conducted with the aim to ascertain the level of awareness, satisfactions, and its importance to the community.To achieve that, a questionnaire survey (via printed and online) were conducted and distributed within the Sintok-Changlon areas.A total of 424 usable responses were collected through simple random sampling.Data from the questionnaire were analysed using several statistical analysis's such descriptive analysis, correlation test, and chi-square test.Findings from the study reveal that majority of the users are Changlun's local residents, particularly the young and well educated group.The service is rank highly in terms of its importance.Nevertheless, the level of satisfaction on the CSR UUMWiFi is still at a moderate level.Interestingly, the gender and level of education have significant relationship with internet browsing activity where female and those with bachelor degree and SPM have higher propensity to use the service.Some improvements and future works were proposed to ensure that the service is more reliable and can help to transform the socio-economic of the community.

Evaluating a novel or enhanced algorithm is compulsory in data mining studies in order to measure it has superior performance than its previous version. In practice, most of studies apply a straightforward approach for evaluation where appropriate performance metrics such as classification accuracy is selected, computes the mean and its variance over several repetitive experiments, and then compares it with the base algorithm or other comparative approach. However, there are limitations using this approach because dataset from different domain tend to produce different error rate thus make their average meaningless as well as susceptible to the outlier. This study demonstrates the mechanism of evaluating an enhanced algorithm using performance metrics and validated it using statistical analysis. In this study, we evaluated the performance of the enhanced algorithm called dendrite cell algorithm using sensitivity, specificity, false positive rate, and accuracy and validated the result using parametric and non parametric statistical significant tests. From the evaluation, the new version of dendrite cell algorithm was statistically proven to have improvement with a significant difference compared to its previous versions in all performance metrics.

The dendrite cell algorithm (DCA) relies on the multi-context antigen value (MCAV) to determine the abnormality of a record by comparing it with anomaly threshold.In practice, the threshold is pre-determined before mining based on previous information and the existing MCAV is inefficient when expose to extreme values.This causes the DCA fails to detect unlabeled data if the new pattern distinct from previous information and reduces the detection accuracy.This paper proposed an adaptive anomaly threshold for DCA using the statistical cumulative sum (CUSUM) with the aim to improve its detection capability.In the proposed approach, the MCAV were normalized with upper CUSUM and the new anomaly threshold was calculated during run time by considering the acceptance value and min MCAV.From the experiments towards 12 datasets, the new version of DCA generated a better detection result than its previous version in term of sensitivity, specificity, false detection rate, and accuracy.

The characteristics of early outbreak signal which are weak and behaved under uncertainties has brought to the development of outbreak detection model based on dendrite cell algorithm.Although the algorithm is proven can improve detection performance, it relies on several parameters which need to be defined before mining.In this study, the most appropriate parameter setting for outbreak detection using dendrite cell algorithm is examined.The experiment includes four parameters; the number of cell cycle update, the number of dendrite cell allowed to be in population, weight, and migration threshold value. To achieve that, an anthrax disease outbreak is chosen as a case study.Two artificial anthrax datasets known as WSARE7 and WSARE58 are taken as experiment data.The experiment is measured based on five metrics; detection rate, specificity, false alarm rate, accuracy, and time taken to produce result. Besides that, a comparison is made with Cumulative Sum, Exponentially-weighted Moving Average, and Multi Layer Perceptron.From the experiment, the best parameter setting for anthrax outbreak using dendrite cell algorithm is identified whereby it proven can helps the model to produce a good detection result between detection rate and false alarm rate.Since each outbreak disease carries different outbreak characteristic, the parameter setting for different outbreak might be different.

Dendrite cell algorithm needs appropriates feature to represents its specific input signals. Although there are many feature selection algorithms have been used in identifying appropriate features for dendrite cell signals, there are algorithms that never been investigated and limited work to compare performance among them. In this study, six feature selection algorithms namely Information Gain, Gain Ratio, Symmetrical Uncertainties, Chi Square, Support Vector Machine, and Rough Set with Genetic Algorithm Reduct are examined and their effectiveness to represent dendrite cell signal are evaluated. Eight universal datasets are chosen and assessing their performance according to sensitivity, specificity, and accuracy. From the experiment, the Rough Set Genetic Algorithm reduct is found to be the most effect feature selection for dendrite cell algorithm when it generates a consistent result for all evaluation metrics. In single evaluation metrics, the chi square technique has the best competence in term of sensitiveness while the rough set genetic algorithm reduct is good at specificity and accuracy. In the next step, further analysis will be conducted on complex dataset such as time series data set.

This paper proposed an intelligent model that is aimed at facilitating key workers select suitable trainees for a training program.The proposed model is initiated because it has been found that many motivational training programs fail to meet their objectives because there is a mismatch between the needs of training programs and the integrity levels of trainees.The proposed model consists of three modules namely personality characteristics identification, training program requirements identification, and trainee selection agent.A dataset for the study called Trainees Integrity Dataset (TID) is mined using association rule to discover important personality characteristics. TID is obtained from Langkawi District Education Office (LDEO) and it has 1500 respondents which represents secondary school teachers in Pulau Langkawi, Kedah, Malaysia who attended a training program organized by LDEO in 2009.The proposed model is intended to produce an efficient selection process and suitable trainees.

Conference management system (CMS) is designed to help the conference committee manages a conference well.The CMS which is available in market nowadays provides a well managed pre-conference function such as paper reviewing, paper submission, and participant registration system.However, payment module is not given priority by the existing CMS. This study argues that the payment management is importance ant to simplify the payment process, avoiding the unpaid paper being published in the proceeding. Also the conference committee can easily calculate the conference profit when the event ends. However, CMS is inflexible handling certain cases such as in case authors are unable to pay the fee before the conference day but need to submit the camera ready.Hence, this paper attempts to explain the design of a flexible conference management system (f-CMS).f-CMS is developed using RAD approach. It also includes the registration module during conference day.This paper presents the review of literatures and the early stages of the development of f-CMS.

The government has arranged many programs for teacher development however the training is organized to fit yearly calendar without considering the right teacher for the right training.The selection of teacher to attend training is done randomly, by rotation and not based on their work performance.This paper investigate the weakest integrity trait of teacher using association rule technique with the aim can assists the school management to organize training related to teachers integrity performance and avoid sending a wrong teacher for a training.A dataset of Trainees Integrity Dataset (TID) representing 1500 secondary school teachers in Langkawi Island, Malaysia in the year 2009 were pre-processed and mined using apriori. The knowledge from the mining was analyzed based on demographic and integrity trait of teacher.The finding indicates that adaptability and stability are the weakest integrity trait among teachers.Besides that, the analysis also unable to prove that demographic factor such as the age and gender of teachers reflect their low integrity performance.The finding can be a guideline for school management to propose a suitable training program for teacher to improve integrity mainly at the adaptability and stability trait.

A limited number of factors in critical areas are necessary to identify the sustainability of companies [30].It was found that three factors were commonly used [2] and a maximum of seven factors was recommended [2].In order to identify the optimal factors, we propose a method based on rough set theory that consisted of five main steps.These were data cleansing and preparation, dimensional reduction, ranking selected factors, optimal factor extraction, and rules generation and evaluation. Dimensional reduction was conducted using rough set theory where the set of factors were identified from the set of reducts that produce highest classification accuracy.These factors were first ranked through computation of its occurrences in reduct sets and then selected based on highest occurrences.The major contribution of this work is the reduced factors shows competitive results in classifying new cases and therefore keeping the quality of knowledge.

This paper presents a new way of online communications through mobile to web that helps students and lecturers to be always aware of appointments no matter where they are. It contributes to the teaching and learning process, in which communication is made easy using short messaging system (SMS) technology which is called Web-based Student Appointment System with GSM Network (WAS-GN).It starts with examples of previous success stories of the implementation of SMS in many areas.The objectives of the paper are to discuss about the hardware and software requirement, and integrate them to be measured in terms of functionality. The research method is outlined next, and some discussions over current outcomes of the research are addressed.The prototype of WAS-GN is successfully implemented using SMS technology.Briefly, results show that WAS-GN is able to solve the appointment-making problem.

Face recognition is one of the most interesting applications in the image processing field.To build a model to recognize the face of different people, we need to do several processes on the image to obtain the most efficient features.In this research a face recognition model is developed.The dataset used is of different face images. Neural Networks technique, specifically Multilayer Perceptron (MLP) model with Back-Propagation learning algorithm and Template Matching approach are implemented in model developed.The face recognition model developed is then applied on a remote database backup system.Template matching approach is found to give a higher percentage of matching accuracy and a faster result can be obtained compared to MLP as no learning process is required

Training programs for teacher’s development in Malaysia are organized ever year. The selection of teachers to attend trainings is currently done randomly, by rotation and not based on their work performance.This poses a problem in selecting the right teacher to attend the right course.Up until now, there is no intelligent model to assist the school management to determine the integrity level of teacher and assign them to the right training program. Thus, this study investigates the integrity traits of teacher using association rule technique with an aim, which can assist the school management to organize a training related to teachers’ integrity performance and to avoid sending the wrong teacher for the training.A dataset of Trainees Integrity Dataset representing 1500 secondary school teachers in Langkawi Island, Malaysia in the year 2009 were pre-processed and mined using apriori. Mining knowledge was analyzed based on demographic and integrity trait of teacher.The finding indicates that adaptability and stability are the weakest integrity trait among teachers. Teachers from the age group of 26 - 30 years are found to have lower integrity performance.However, other demographic factor such as gender, race, and grade position of teachers were not able to reflect their low integrity level in this study.Findings from this study can be used as guideline for school management to propose suitable training programs for teacher to improve their integrity mainly on adaptability and stability traits.

Computer programming is one of the most essential skills which each graduate has to acquire.However, there are reports that they are unable to write a program well. Researches indicated there are many factors can affect student programming performance.Thus, the aim of this study is to investigate the significant factors that may influence students programming performance based information from previous student performance using data mining technique. Data mining is a data analysis technique that able to discover hidden knowledge in database. The programming dataset used in this study comprises information on the performance profile of Universiti Utara Malaysia students from 4 different bachelor programs that were Bachelor in Information Technology , Bachelor in Multimedia, Bachelor in Decision Science and Bachelor in Education specializing in IT of the November session year 2004/2005. They were required to enroll introductory programming subject as requirement to graduate . The dataset consisting of 4 19 records with 70 attributes were pre-processed and then mined using directed association rule mining algorithm namely Apriori. The result indicated that the student who has been exposed to programming prior to entering university and scored well in Mathematics and English subject during secondary Malaysian School Certificate examination were among strong indicators that contributes to good programming grades. This finding can be a guideline to the faculty to plan a teaching and learning program for new registered student.

This paper describes an ongoing project for recording examination attendance using Radio Frequency Identification (RFID).The project is carried out to test in a university, where the system which is named Portable Examination Attendance System (PEAS) is integrated with the existing system for record extraction.The use of RFID technology enables the university management to avoid attendance forms from damages such as tear, lost, and misplaced. This paper describes about the design and development of PEAS in terms of hardware technology and software. In addition, some related works are reviewed and addressed to support this project.As a conclusion, this paper states some future works of this project.

Case-based reasoning (CBR) considers previous experience in form of cases to overcome new problems. It requires many solved cases in case base in order to produce a quality decision. Since today, database technology has allowed CBR to use a huge case storage therefore the case retrieval process also reflects the final decision in CBR. Traditionally, sequential indexing method has been applied to search for possible cases in case base. This technique is worked fast when the number of cases is small but it consumes more time to retrieve when the number of data grows in case base.To overcome the weakness, this study researches the non-sequential indexing called hashing as an alternative to mine large cases and faster the retrieval time in CBR. Hashing indexing searches a record by determines the index using only an entry's search key without traveling to all records. This paper presents the review of a literature and early stages of the integration hashing indexing method in CBR. The concept of hashing indexing in case retrieving process, the model development, and the preliminary algorithm testing result will be discussed in this paper.

This paper presents an ongoing research that helps students and lecturers to be always aware of the appointment no matter where they are.It contributes to the teaching and learning process, in which communication is made easy using short messaging system (SMS) technology.It starts with examples of previous success stories of the implementation of SMS in many areas.The objectives of the paper are to discuss about the hardware and software requirement, and integrate them to be measured in terms functional. The research method is outlined next, and some discussions on current outcome of the research are addressed.The research is planned to be continued with full implementation of the proposed system that is called Student Appointment System using SMS technology.

Computer programming is taught as a core subject in Information Technology related studies.It is one of the most essential skills which each student has to acquire.However, there is still a small number of students who are unable to write a program well. Several researches indicated that there are many factors which can affect student programming performance.Thus, the objective of this paper is to investigate the significant factors that may influence students programming performance using information from previous student performance.Since data mining data analysis able to discover hidden knowledge in database, a programming dataset which comprises information about performance profile of Bachelor of Information Technology students of Faculty of IT, Universiti Utara Malaysia in the year 2004-2005 were explored using data mining technique.The dataset consists of 421 records with 70 mixture type of attributes were pre-processed and then mined using directed association rule (AR) mining algorithm namely apriori.The result indicated that the student who has a programming experience in advanced before starts learn programming in university and scored well in Mathematics and English subject during SPM were among the factor that contributes to a good programming grades.

Web log file analysis began as a way for IT administrators to ensure adequate bandwidth and server capacity on their organizations website. Log file data can offer valuable insight into web site usage.It reflects actual usage in natural working condition, compared to the artificial setting of a usability lab.It represents the activity of many users, over potentially long period of time, compared to a limited number of users for an hour or two each.This paper describes the pre-processing techniques on IIS Web Server Logs ranging from the raw log file until before mining process can be performed. Since the pre-processing is tedious process, it depending on the algorithm and purposes of the applications.

This paper presents a comparative study of two rule based classifier; rough set (Rc) and decision tree (DTc).Both techniques apply different approach to perform classification but produce same structure of output with comparable result. Theoretically, different classifiers will generate different sets of rules via knowledge even though they are implemented to the same classification problem.Hence, the aim of this paper is to investigate the quality of knowledge produced by Rc and DTc when similar problems are presented to them.In this case, four important performance metrics are used as comparison, the accuracy of classification, rules quantity, rules length and rules coverage.Five dataset from UCI Machine Learning are chosen and then mined using Rc toolkit namely ROSETTA while C4.5 algorithm in WEKA application is chosen as DTc rule generator. The experimental result shows that Rc and DTc own capability to generate quality knowledge since most of the results are comparable. Rc outperform as an accurate classifier, produce shorter and simpler rule with higher coverage. Meanwhile, DTc obviously generates fewer numbers of rules with significant difference.