Template-Type: ReDIF-Article 1.0
Author-Name: Dhushy Thillaivasan
Author-X-Name-First: Dhushy
Author-X-Name-Last: Thillaivasan
Author-Name: C.N. Wickramasinghe
Author-X-Name-First: C.N.
Author-X-Name-Last: Wickramasinghe
Title: Reassessing privacy, fairness and governance in the age of algorithms and the impact on society and institutions
Abstract:
While algorithms will play a central role in the future of business and society, there is a lack of awareness of the grave implications to fundamental human values and to institutions that are built around these values. Algorithms have already rendered the present framework of law and governance outdated. While new technologies have historically roiled societies with the privacy conundrum at times of great change, the ability to gather, analyse, and combine vast quantities of data from different sources using powerful algorithms, impose a significant challenge to the traditional notion of privacy and fairness, as never seen before. This paper elucidates the concepts of data and algorithms along with our current notions of privacy and fairness. It explores the multi-dimensional algorithmic challenges to our present notion of privacy and fairness and to institutions to which privacy and fairness are at their core. It also deliberates on safeguards and remedial actions being considered at present.
Journal: Int. J. of Data Science
Pages: 121-141
Issue: 2
Volume: 7
Year: 2022
Keywords: privacy; fairness; governance; algorithm; AI; artificial intelligence; data.
File-URL: http://www.inderscience.com/link.php?id=126851
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:2:p:121-141

Template-Type: ReDIF-Article 1.0
Author-Name: Arabela Khan
Author-X-Name-First: Arabela
Author-X-Name-Last: Khan
Author-Name: Marcus Birkenkrahe
Author-X-Name-First: Marcus
Author-X-Name-Last: Birkenkrahe
Title: Development of a usability testing procedure for process mining tools
Abstract:
Process mining tools (PMTs) use event logs to enable things like process discovery, compliance checking, and bottleneck analysis. This study addresses the lack of transparency in the fast-growing PMT market. This study is the first usability study of selected PMTs. We focus on process discovery within the purchase-to-pay (P2P) process for first-time users of PMTs. We built and executed a usability test which resulted in valuable comparative insights. For this study, event logs from the P2P process were artificially generated. Ten participants worked on ten different tasks in the P2P process while their behaviour was documented in a structured form. Each use of a tool was followed by an interview as well as a questionnaire. The results chart effectiveness, learnability, efficiency, and satisfaction for each tool, and highlight those product features that contribute to a usable PMT. We provide a guideline to test the usability of PMTs.
Journal: Int. J. of Data Science
Pages: 142-163
Issue: 2
Volume: 7
Year: 2022
Keywords: PMT; process mining tools; usability testing; P2P; purchase-to-pay; procure-to-pay.
File-URL: http://www.inderscience.com/link.php?id=126852
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:2:p:142-163

Template-Type: ReDIF-Article 1.0
Author-Name: Wei Lu
Author-X-Name-First: Wei
Author-X-Name-Last: Lu
Author-Name: Ruben Xing
Author-X-Name-First: Ruben
Author-X-Name-Last: Xing
Author-Name: Pei Deng
Author-X-Name-First: Pei
Author-X-Name-Last: Deng
Author-Name: Zihan Shen
Author-X-Name-First: Zihan
Author-X-Name-Last: Shen
Title: User stickiness in mobile games
Abstract:
The continuous development of information technology in social needs has promoted the development of the mobile game industry, making games an important cultural and entertainment consumer product. The game industry became a huge dividend market. However, the booming game industry is highly competitive. How to maintain its competitiveness has become an urgent problem to be solved. This research aims at the related factors that affect users' game stickiness, such as user-perceived quality, switching cost, and perceived ease of use are focused as the primary concerns of this research. Combining the characteristics of games and users' behaviour, a structural equation model is constructed. Through the questionnaire survey and structural equation analysis, it is found that sociality, payment mechanism, user interface and plot have positive effects on game stickiness. Finally, based on the idea of behavioural design and the analysis results, this paper proposed some systematic improvement strategies for game stickiness.
Journal: Int. J. of Data Science
Pages: 95-120
Issue: 2
Volume: 7
Year: 2022
Keywords: mobile game; users stickiness; structural equation; technology acceptance model; users' behaviour theory; flow phenomenon.
File-URL: http://www.inderscience.com/link.php?id=126853
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:2:p:95-120

Template-Type: ReDIF-Article 1.0
Author-Name: Jun-Qi Yang
Author-X-Name-First: Jun-Qi
Author-X-Name-Last: Yang
Author-Name: Hai-Zhong Liu
Author-X-Name-First: Hai-Zhong
Author-X-Name-Last: Liu
Title: Application of EMD-Adaboost in wind speed prediction
Abstract:
Wind speed in advance can provide decision support for a wind farm operation. This paper attempts to propose an improved artificial neural network algorithm based on empirical mode decomposition combined with the ensemble learning model Adaboost to improve and optimise the wind speed prediction method. In the prediction process, a new hidden layer node selection method is proposed. After using empirical mode decomposition to obtain new input data, considering the relationship between each component and output after decomposition, a single hidden layer node method is adopted, which is confirmed by experiments. The root mean square error (RMSE) of the final forecasting model under two different volatility conditions (unstable volatility and stable volatility) reached 0.46 and 0.2809, and the R-squared was 0.84 and 0.96. These indicators are the optimal level in a comparison model, and are statistically significant (R-squared at the 0.05 significance level).
Journal: Int. J. of Data Science
Pages: 164-180
Issue: 2
Volume: 7
Year: 2022
Keywords: new energy; wind prediction; machine learning; nonlinear prediction; empirical mode decomposition; ensemble learning; hidden layer; Adaboost; artificial neural networks; root mean square error.
File-URL: http://www.inderscience.com/link.php?id=126854
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:2:p:164-180

Template-Type: ReDIF-Article 1.0
Author-Name: Xiaomin Xu
Author-X-Name-First: Xiaomin
Author-X-Name-Last: Xu
Author-Name: Kewei Wu
Author-X-Name-First: Kewei
Author-X-Name-Last: Wu
Title: Statistical analysis of iron concentrate quality data
Abstract:
China's steel industry is gradually converging with the international one and is becoming an important force in the international steel industry. However, there exists a big gap between the quality of China's iron concentrate and the world standard. This paper takes the iron concentrate of a mining company as the object of quality analysis and improvement. Firstly, the toxic element sulphur in iron concentrate was found, which affects the quality of smelting steel. Secondly, the multiple linear regression method was used to analyse the indexes of influencing factors, in order to find out the key factors affecting the sulphur content. Finally, the effect of sulphur content in iron concentrate was verified by a hypothesis test, and improved results were achieved.
Journal: Int. J. of Data Science
Pages: 181-196
Issue: 2
Volume: 7
Year: 2022
Keywords: data of iron concentrate; statistical analysis; quality analysis; quality improvement; software analysis; multiple regression analysis; hypothesis testing.
File-URL: http://www.inderscience.com/link.php?id=126857
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:2:p:181-196

Template-Type: ReDIF-Article 1.0
Author-Name: Ardavan Asef-Vaziri
Author-X-Name-First: Ardavan
Author-X-Name-Last: Asef-Vaziri
Author-Name: Ahmad Vessal
Author-X-Name-First: Ahmad
Author-X-Name-Last: Vessal
Author-Name: Amir Gharehgozli
Author-X-Name-First: Amir
Author-X-Name-Last: Gharehgozli
Title: Scheduling faculty for lunch and dinner meetings with candidates during campus visits
Abstract:
Hiring talented faculty is key to student success. A crucial step in hiring faculty during the campus visits is to give both faculty and candidates to meet. To achieve this, hiring departments prepare a schedule for one-to-one meetings. Furthermore, there are meetings over lunch and dinner. We propose a model to schedule faculty for lunch and dinner. Throughout a case study, we investigate the impact of several constraints. The problem is implemented in MS Excel®, which is straightforward and can be used by search and screen committees. Furthermore, it can be embedded in the teaching materials of a Prescriptive Analytics course to discuss how a model is gradually developed.
Journal: Int. J. of Data Science
Pages: 44-59
Issue: 1
Volume: 7
Year: 2022
Keywords: campus visit; scheduling faculty; lunch and dinner; excel implementation; teaching case.
File-URL: http://www.inderscience.com/link.php?id=124353
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:1:p:44-59

Template-Type: ReDIF-Article 1.0
Author-Name: Matthias Lederer
Author-X-Name-First: Matthias
Author-X-Name-Last: Lederer
Author-Name: Elias Jakob
Author-X-Name-First: Elias
Author-X-Name-Last: Jakob
Author-Name: Peter Rathnow
Author-X-Name-First: Peter
Author-X-Name-Last: Rathnow
Title: State-of-the-art and possible fields of application for the integrated support of merger and acquisition processes by means of artificial intelligence
Abstract:
Artificial intelligence has the potential to fundamentally change many industries, including the finance industry. By now, there has been no radical evolution in the way Mergers and Acquisitions (M%A) processes are conducted for decades. The aim of this research is to analyse if and how artificial intelligence (AI) can be used to increase efficiency and effectiveness in M%A transactions. The work is based on the one hand on the respective literature on AI and on M%A and on the other hand on a survey of experts from the financial services industry. The results show that respondents see the greatest opportunities for AI in the M%A process in increasing efficiency and precision. Limitations of the application arise regarding data conformity, data protection and the technical reproducibility of emotional intelligence. Overall, this paper shows which realistic approaches exist for AI in the M%A process and how this technology can lead to an increase in effectiveness and efficiency.
Journal: Int. J. of Data Science
Pages: 22-43
Issue: 1
Volume: 7
Year: 2022
Keywords: artificial intelligence; mergers and acquisitions; M%A process; due diligence.
File-URL: http://www.inderscience.com/link.php?id=124354
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:1:p:22-43

Template-Type: ReDIF-Article 1.0
Author-Name: Roger Poch Alonso
Author-X-Name-First: Roger Poch
Author-X-Name-Last: Alonso
Author-Name: Marina Bagić Babac
Author-X-Name-First: Marina Bagić
Author-X-Name-Last: Babac
Title: Machine learning approach to predicting a basketball game outcome
Abstract:
The outcome of a basketball match depends on many factors, such as the morale of a team or a player, skills, coaching strategy, and many others. Thus, it is a challenging task to predict the exact results of individual matches. This paper shows how to learn from historical data about previous basketball games, including both individual and team features, to predict future matches. It outlines the advantages and disadvantages of existing machine learning systems and tries to apply the best practices focusing on a case study of the National Basketball Association (NBA). In addition, a comparison between different machine learning algorithms in search of the most accurate prediction is provided.
Journal: Int. J. of Data Science
Pages: 60-77
Issue: 1
Volume: 7
Year: 2022
Keywords: machine learning; supervised learning; prediction; KNN; k-nearest neighbours; decision trees; Naive Bayes classifier; basketball; NBA.
File-URL: http://www.inderscience.com/link.php?id=124356
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:1:p:60-77

Template-Type: ReDIF-Article 1.0
Author-Name: Abdelghani Hmich
Author-X-Name-First: Abdelghani
Author-X-Name-Last: Hmich
Author-Name: Abdelmajid Badri
Author-X-Name-First: Abdelmajid
Author-X-Name-Last: Badri
Author-Name: Aicha Sahel
Author-X-Name-First: Aicha
Author-X-Name-Last: Sahel
Title: Group student profiling in massive open online courses using educational data mining
Abstract:
Student profiling is one of the great accomplishments in the field of educational data mining (EDM). Student profile can mainly offer the most exact description of students in order to be able to offer students the most appropriate personalisation and recommendation. In this paper, we use a demarche for discovering group Massive Open Online Course (MOOC) student profile in relation to their quiz performance. This demarche is based on the combination of hierarchical density-based spatial clustering of applications with noise (HDBSCAN) and apriori algorithm, first the groups of students with similar learning characteristic are extracted by using the clustering algorithm HDBSCAN, then the extracted groups were analysed by using apriori algorithm in order to characterise the distinct profiles of group of students using data collected from a MOOC in Moodle platform. The results show that there are three groups of students organised by quiz performance and learning behaviours. First group is characterised by the low quiz performance, the second group is characterised by the good quiz performance and the third group is characterised by the excellent quiz performance.
Journal: Int. J. of Data Science
Pages: 78-94
Issue: 1
Volume: 7
Year: 2022
Keywords: student profiling; EDM; educational data mining; E-learning; MOOCs; Massive Open Online Courses; clustering; HDBSCAN; association rules mining.
File-URL: http://www.inderscience.com/link.php?id=124358
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:1:p:78-94

Template-Type: ReDIF-Article 1.0
Author-Name: Xin Li
Author-X-Name-First: Xin
Author-X-Name-Last: Li
Author-Name: Ning Wang
Author-X-Name-First: Ning
Author-X-Name-Last: Wang
Author-Name: Kunlin Song
Author-X-Name-First: Kunlin
Author-X-Name-Last: Song
Author-Name: Kun Xu
Author-X-Name-First: Kun
Author-X-Name-Last: Xu
Author-Name: Jiancheng Huang
Author-X-Name-First: Jiancheng
Author-X-Name-Last: Huang
Title: Point cloud and image 3D visualisation platform based on web
Abstract:
Nowadays, the point cloud data collected by light detection and ranging (LiDAR) and image data collected by camera are increasing. How to effectively manage and visualise such massive data has always been a research hotspot for scholars. Meanwhile, the development of web technology provides a new and efficient way for the visualisation of these data. Therefore, we propose a web-based 3D visualisation method of point cloud and images. In this platform, least squares is used to achieve accurate matching of the feature of heterogeneous data. The Potree and Django framework is applied to realise 3D visualisation of web endpoint cloud images, as well as basic measurement, annotation, file output, etc. This platform can realise the online quick browsing of point cloud and image data. The visualisation smoothness of point cloud and images on the web end has been significantly improved.
Journal: Int. J. of Data Science
Pages: 229-241
Issue: 3
Volume: 7
Year: 2022
Keywords: 3D visualisation; point cloud; image; web; Potree.
File-URL: http://www.inderscience.com/link.php?id=127692
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:3:p:229-241

Template-Type: ReDIF-Article 1.0
Author-Name: Ting Zhang
Author-X-Name-First: Ting
Author-X-Name-Last: Zhang
Author-Name: Xiaojun Zhu
Author-X-Name-First: Xiaojun
Author-X-Name-Last: Zhu
Author-Name: Dejun Xie
Author-X-Name-First: Dejun
Author-X-Name-Last: Xie
Author-Name: Feng Su
Author-X-Name-First: Feng
Author-X-Name-Last: Su
Author-Name: Narayanaswamy Balakrishnan
Author-X-Name-First: Narayanaswamy
Author-X-Name-Last: Balakrishnan
Title: Test of equality of proportional hazard models with jointly censored data
Abstract:
This paper addresses the problem of and solutions to the equality of two samples following the same class of nonlinear models. The test statistic used is based on the partial likelihood estimate from two independent samples with proportional hazard under complete and censored samples. By assuming that the hazard function is time-dependent, we develop exact inference for the partial likelihood estimate of the ratio of two hazard rates. The results obtained are important for testing the equality of sampling distributions and evaluating parameters for the hazard models. We propose a new sequential test based on the partial likelihood estimate, followed by an efficient computational methodology for exact inferential statistics. Examples are provided to demonstrate the implementation of our statistical testing procedure.
Journal: Int. J. of Data Science
Pages: 1-21
Issue: 1
Volume: 7
Year: 2022
Keywords: exact inference; partial likelihood estimator; proportional hazard; sequential test; maximum likelihood; complete sampling; censored sample; critical region; power test; test efficiency.
File-URL: http://www.inderscience.com/link.php?id=124365
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:1:p:1-21

Template-Type: ReDIF-Article 1.0
Author-Name: S.M. Deepa
Author-X-Name-First: S.M.
Author-X-Name-Last: Deepa
Title: The mediation effects of job characteristics between interpersonal justice, informational justice and job engagement
Abstract:
The present study examined the role of interactional justice (interpersonal and informational) on job engagement and the mediation role of job characteristics between interactional justice and job engagement (physical, cognitive and emotional). Using a sample of 252 employees from information technology firms based in South India, the current study analysed the hypothesised mediation model by employing partial least squares-structural equation modelling (PLS-SEM). Results revealed that interpersonal justice and informational justice have positive impacts on job characteristics, and job characteristics partially mediate between interactional justice and job engagement. The findings of the study emphasise that (a) interactional justice has a positive relationship with job characteristics which is scarcely found in the literature; and (b) job characteristics act as a mediator between interactional justice and job engagement, which is a new perspective. All three energies of job engagement are examined individually.
Journal: Int. J. of Data Science
Pages: 242-269
Issue: 3
Volume: 7
Year: 2022
Keywords: interpersonal justice; informational justice; job characteristics; job engagement; physical; cognitive; emotional; PLS-SEM; partial least squares-structural equation modelling; information technology sector.
File-URL: http://www.inderscience.com/link.php?id=127694
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:3:p:242-269

Template-Type: ReDIF-Article 1.0
Author-Name: Xiaoliang Jiang
Author-X-Name-First: Xiaoliang
Author-X-Name-Last: Jiang
Author-Name: Jinyun Jiang
Author-X-Name-First: Jinyun
Author-X-Name-Last: Jiang
Title: Localised active contour method via local similarity measure for image segmentation
Abstract:
The accuracy of active contour methods is not always exact since there are many uncertainty factors, e.g., abundant noise, lack of clear boundaries, intensity inhomogeneity. To tackle these issues, a localised region-based segmentation framework is presented in this paper. In our method, a new adaptive local similarity measure is built in local regions as the spatial constraint to guarantee noise suppression and outlier resistance. Second, we construct an objective equation by integrating the local similarity measure into an active contour algorithm based on the local region. Furthermore, we design the local mean difference energy as a control constraint to enhance the efficiency and smoothness of the profile curve. Experimental data demonstrate that our algorithm, when compared with other classical region-based models, can achieve higher accuracy and has stronger robustness for images with higher noise levels.
Journal: Int. J. of Data Science
Pages: 197-209
Issue: 3
Volume: 7
Year: 2022
Keywords: segmentation; active contour; local similarity measure; local mean difference; C-V; level set; region-based; initial contour; noise.
File-URL: http://www.inderscience.com/link.php?id=127701
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:3:p:197-209

Template-Type: ReDIF-Article 1.0
Author-Name: Asish Satpathy
Author-X-Name-First: Asish
Author-X-Name-Last: Satpathy
Author-Name: Satyajit Behari
Author-X-Name-First: Satyajit
Author-X-Name-Last: Behari
Title: Machine learning prediction of chronic diabetes based on a person's demography and lifestyle information
Abstract:
Chronic diseases such as diabetes are prevalent globally and responsible for many deaths yearly. In addition, treatments for such chronic diseases account for a high healthcare cost. However, research has shown that diabetes can be proactively managed and prevented while lowering healthcare costs. We have mined a sample of ten million customers' 360° insight that includes behavioural, demographic, and lifestyle information, representing the state of Texas, USA, with attributes current as of late 2018. The sample, obtained from a market research data vendor, has over 1000 customer attributes consisting of behavioural, demographic, lifestyle, and, in some cases, self-reported chronic conditions such as diabetes or hypertension. In this study, we have developed a classification model to predict chronic diabetes with an accuracy of 80%. In addition, we demonstrate a use case where a large volume of customers' 360° data can be helpful to predict and hence proactively prevent and manage a person's chronic diabetes. Customer and person are both used interchangeably throughout the paper.
Journal: Int. J. of Data Science
Pages: 210-228
Issue: 3
Volume: 7
Year: 2022
Keywords: data mining in health care; classification analysis with lifestyle and demographic data; customers' 360° insights; data mining for predicting diabetes.
File-URL: http://www.inderscience.com/link.php?id=127705
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:3:p:210-228

Template-Type: ReDIF-Article 1.0
Author-Name: Weiying Zheng
Author-X-Name-First: Weiying
Author-X-Name-Last: Zheng
Author-Name: Zhiyi Zhao
Author-X-Name-First: Zhiyi
Author-X-Name-Last: Zhao
Title: On the integration path between reading promotion activities and traditional culture in the university library
Abstract:
This paper gives the meaning of reading promotion, determines the characteristics of reading promotion activities in university libraries, analyses the practical significance of reading promotion activities in university libraries, and analyses the feasibility of carrying out reading promotion activities in university libraries. According to the above basis, the selection of reading promotion evaluation indicators is realised, the analytic hierarchy process is used to construct the discrimination matrix, and the AHP method is used to calculate the weight of reading promotion indicators, so as to realise the integration of reading promotion activities of the university library and traditional culture. Through the verification of integration satisfaction, the integration satisfaction of reading promotion activities and traditional culture of this method can reach 97.5%, which shows that this method can realise the integration of reading promotion activities and traditional culture of university libraries.
Journal: Int. J. of Data Science
Pages: 270-291
Issue: 3
Volume: 7
Year: 2022
Keywords: AHP; analytic hierarchy process; square root method; index weight; discriminant matrix; reading promotion; integration of traditional culture.
File-URL: http://www.inderscience.com/link.php?id=127707
File-Format: text/html
File-Restriction: Access to full text is restricted to subscribers.
Handle: RePEc:ids:ijdsci:v:7:y:2022:i:3:p:270-291