Search

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Current suicide risk assessments for predicting suicide attempts are time consuming, of low predictive value and have inadequate reliability. This paper aims to develop a predictive model for suicide attempts among patients with depression using machine learning algorithms as well as presents a comparative study on single predictive models with ensemble predictive models for differentiating depressed patients with suicide attempts from non-suicide attempters. We applied and trained eight different machine learning algorithms using a dataset that consists of 75 patients diagnosed with a depressive disorder. A recursive feature elimination was used to reduce the features via three-fold cross validation. An ensemble predictive models outperformed the single predictive models. Voting and bagging revealed the highest accuracy of 92% compared to other machine learning algorithms. Our findings indicate that history of suicide attempt, religion, race, suicide ideation and severity of clinical depression are useful factors for prediction of suicide attempts. [ABSTRACT FROM AUTHOR]

Purpose - Personal bankruptcy is on the rise in Malaysia. The Insolvency Department of Malaysia reported that personal bankruptcy has increased since 2007, and the total accumulated personal bankruptcy cases stood at 131,282 in 2014. This is indeed an alarming issue because the increasing number of personal bankruptcy cases will have a negative impact on the Malaysian economy, as well as on the society. From the aspect of individual's personal economy, bankruptcy minimizes their chances of securing a job. Apart from that, their account will be frozen, lost control on their assets and properties and not allowed to start any business nor be a part of any company's management. Bankrupts also will be denied from any loan application, restricted from travelling overseas and cannot act as a guarantor. This paper aims to investigate this problem by developing the personal bankruptcy prediction model using the decision tree technique. Design/methodology/approach - In this paper, bankrupt is defined as terminated members who failed to settle their loans. The sample comprised of 24,546 cases with 17 per cent settled cases and 83 per cent terminated cases. The data included a dependent variable, i.e. bankruptcy status (Y = 1(bankrupt), Y = 0 (non-bankrupt)) and 12 predictors. SAS Enterprise Miner 14.1 software was used to develop the decision tree model. Findings - Upon completion, this study succeeds to come out with the profiles of bankrupts, reliable personal bankruptcy scoring model and significant variables of personal bankruptcy. Practical implications - This decision tree model is possible for patent and income generation. Financial institutions are able to use this model for potential borrowers to predict their tendency toward personal bankruptcy. Originality/value - This decision tree model is able to facilitate and assist financial institutions in evaluating and assessing their potential borrower. It helps to identify potential defaulting borrowers. It also can assist financial institutions in implementing the right strategies to avoid defaulting borrowers. [ABSTRACT FROM AUTHOR]

A customer trouble ticketing system (CTT) is an organization's tool to track the detection, reporting, and resolution of tickets submitted by customers. It also comprises a summary of the issue reported, the status of the ticket, the incident information, and the approach that was previously utilized to resolve the problems. The technician's skill set and experience rely solely on completing the task without the right direction on which area to focus on first. As a result of this manual classification of a trouble ticket, it will be necessary to build methodologies for predicting future resolution codes. The research for this report is mainly focused on one of the telco companies in Malaysia. This study result assists the telco engineer, and the specialists resolve each issue in a very short amount of time. Additionally, the classification of the trouble ticket resolution code method used in this study will indicate the characteristics of each issue that is being investigated. The relationship between events is feasible to discover by exploring the root cause. It is critical to establish a link between recent events and events in the previous. Because of current data mining limitations, the study needs to be more comprehensive. Data processing methods are being implemented within big data platforms to overcome the limitation of data scalability, enhance classification accuracy, and increase computation speed. The research work will continue to progress in the direction of big data centricity. Some of the most effective approaches for big data integration and machine learning will be discussed in this paper. Throughout the experiment, any problems will be explained, as well as the solutions to each situation. A wide range of research subjects will be discussed, including construction classification models for trouble tickets. To achieve reasonable accuracy, a few customized transformations are required. The data set's custom parameter optimization process will further increase the classification trouble ticket's efficiency. However, greater processing capacity is necessitated to use multiple parallel classifiers such as Bayes, Decision-Tree, and Rule-Based with help of bigdata framewrks such as Spark. According to the study, an increase of 8% classification performance substantially influences service recovery time, customer satisfaction, and preventative maintenance expenses in the telco industry. [ABSTRACT FROM AUTHOR]

Purpose — This paper aims assess to the perceived importance (PI) and actual implementation (Al) of five preliminary knowledge management (KM) success factors, i.e. business strategy, organizational structure, knowledge team, knowledge audit, and knowledge map in the Malaysian telecommunication industry. Design/methodology/approach — A questionnaire survey was conducted on telecommunication organizations located in the capital of Malaysia. Data were analyzed using indices and parametric statistics. Findings — The results show that the organizations are aware of the importance of all the KM factors but fall short of implementation. The implemented factors consist of business strategy, organizational structure, and knowledge team. Knowledge audit and knowledge map are perceived as important but are the least implemented factors. Research limitations/implications — This study was conducted in only one industry in Malaysia. Furthermore, it focuses on the preliminary success factors of KM implementation rather than on learning and knowledge utilization. Practical implications — Telecommunication organizations have to overcome resources problems and enhance implementation level in order to narrow the gaps for effective, full scale KM implementation in the later stage. Such viable practice will significantly help the industry not only to compete more effectively within Malaysia, but also to position itself as a global player in the world. Originality/value — This study is perhaps one of the first to address the preliminary steps to be dealt with prior to KM implementation. Moreover, it attempts to compare the PI and AT of the five proposed success factors, which has received very little attention to date. [ABSTRACT FROM AUTHOR]

Introduction: The use of electronic cigarette and vape (ECV) among adults has been rapidly in Malaysia. Objectives: The primary objective of this paper is to understand the characteristics of ECV users in Malaysia by assessing the perceptions and demographic variables. The influence of perceptions and demographic variables were assessed on the current status of ECV use. Several predictor variables included in this study were: seven demographics variables (i.e., age, gender, race, residence, marital, occupation and education) and twenty variables on the perception of ECV use. An Induction Decision Tree (ID3) algorithm, one of the renowned data mining technique, was used in this study. Materials and Methods: A number of simulations was carried out on the dataset which was extracted from the National Electronic Cigarette Survey (NECS) 2016. Results: The result of this study shows that the most critical variable identified in this study was gender, hence indicates decision for ECV uses significantly differs among male and female. Conclusion: The findings of this study would contribute towards strategizing public health campaign on smoking cessation. [ABSTRACT FROM AUTHOR]

Abstract: This paper investigates the effect of organizational demographic variables on successful knowledge management (KM) implementation which insofar has not been thoroughly reported in the KM literature. For meaningful results to be generated, four organizational demographic variables, namely functional areas, years of KM involvement, KM development stage, and degree of knowledge intensity were moderated against a comprehensive set of KM activities, which comprise of KM preliminary success factors, KM strategies and KM processes, with organizational performance. The respondents comprised of middle managers working in the telecommunication industry in Malaysia. Based on the data collected from 289 respondents using a set of structured questionnaire, the results reveal that all the four demographic characteristics interacted with the degree of implementation of the KM activities, while three of the characteristics, with exception of functional areas, show significant relationships with organizational performance. The contributions of the paper, along with the implications of the results are discussed and interpreted to provide guidance to organizations for improved business performance through KM implementation success. [Copyright &y& Elsevier]

Air is the most crucial element for the survival of life on Earth. The air we breathe has a profound effect on our ecosystem biodiversity. Consequently, it is always prudent to monitor the air quality in our environment. There are few ways can be done in predicting the air pollution index (API) like data mining. Therefore, this study aimed to evaluate three types of support vector regression (linear, SVR, libSVR) in predicting the air pollutant concentration and identify the best model. This study also would like to calculate the API by using the proposed model. The secondary daily data is used in this study from year 2002 to 2020 from the Department of Environment (DoE) Malaysia which located at Petaling Jaya monitoring station. There are six major pollutants that have been focusing in this work like PM10, PM2.5, SO2, NO2, CO, and O3. The root means square error (RMSE), mean absolute error (MAE) and relative error (RE) were used to evaluate the performance of the regression models. Experimental results showed that the best model is linear SVR with average of RMSE = 5.548, MAE = 3.490, and RE = 27.98% because had the lowest total rank value of RMSE, MAE, and RE for five air pollutants (PM10, PM2.5, SO2, CO, O3) in this study. Unlikely for NO2, the best model is support vector regression (SVR) with RMSE = 0.007, MAE = 0.006, and RE = 20.75% in predicting the air pollutant concentration. This work also illustrates that combining data mining with air pollutants prediction is an efficient and convenient way to solve some related environment problems. The best model has the potential to be applied as an early warning system to inform local authorities about the air quality and can reliably predict the daily air pollution events over three consecutive days. Besides, good air quality plays a significant role in supporting biodiversity and maintaning healthy ecosystems. [ABSTRACT FROM AUTHOR]

This study explored radiology procedure' cost across available units in the Radiology's Department UKMMC (University Kebangsaan Malaysia Medical Centre). In 2011, the total number of radiology procedures carried out in this department was 121,221. Nevertheless, the estimating expenses of offering these procedures are not known. An economic evaluation study was employed and cost centric data mining based on costing activity method was used to determine the charge of the procedure in every centre. Information on seven cost parameters was collected for each procedure: human resources, consumables, equipment, reagents, administration, maintenance and utilities. The results of the study show that the highest percentage of cost parameter for the human resource was Radiology (Mobile) 57.5%, the highest percentage of cost parameter for consumables and reagent was EIR (Endovascular International Radiology) Unit 75.8% and Medical Nuclear Unit 68.1% was the highest percentage of cost parameter for reagent. The MRI (Magnetic Resonance Imaging) Unit 81.4% was the highest cost parameter for equipment. The most top mean cost procedures were EIR MYR4330 and it was revealed that procedures with the highest difference ratio were procedures in EIR (18.50). Finding of this study is very useful to UKMMC management since it helps to enhance the efficiency of services and reduce unnecessary radiology procedures in patients' management. [ABSTRACT FROM AUTHOR]