International Journal of Information and Decision Sciences (56 papers in press)
Proposing a Model for Accepting Core Banking System in Iran Using Fuzzy DEMATEL Technique: A Case Study
by Ameneh Khadivar, Hamideh Nazarian, Sanaz Bodaghi
Abstract: Ever-increasing advancement and expansion of the information and communication technology in the recent decade has led to increased competition in organizations, especially financial organizations. Core banking system implementation project is a time consuming, cost-intensive, and complex task like other investments in information technology. As a result, plenty of core banking system projects have not been successful.
This research proposes a model for accepting the core banking system at Parsian Bank operating in Iran using the fuzzy DEMATEL technique. Using the fuzzy DEMATEL procedures, the involved criteria of a system are separated into the cause and effect groups for helping decision-makers focus on those criteria that provide great influence. Identified from the users' standpoint, factors affecting the acceptance of this system have been prioritized through the questionnaire.
The identified factors for accepting the core banking system in this research are: output quality of core banking system, experience of using the core banking system, voluntariness and motivation in employees to use the core banking system, perceived usefulness of core banking system by employees, perceived ease of use of the core banking system for employees, quality of core banking system, satisfaction with the core banking system, employee resistance to change and use of the new core banking system, and adequate training to employees to use core banking system.
The findings indicate that, three of the influencing factors are identified as critical ones; within the cause group, the criterion of the output quality of the core banking system is the most important factor for accepting the core banking system, whereas the quality of the core banking system has the best effect on the other criteria. By contrast, adequate training for employees to use the core banking system is the most easily improved of the effect group criteria.
Keywords: Core Banking System; Technology Acceptance; Accepting the Core Banking System; Fuzzy Dematel Technique.
A Synergy of Spatial Perspective based Non-Numeric ME-MCDM and Modified Dijkstra Algorithm for Optimal Distribution Route Selection
by Hartrisari Hardjomidjojo, Marimin Marimin, Suprihatin Suprihatin, Rindra Yusianto
Abstract: The optimal distribution routes selection is not only determined based on the shortest distance but needs to consider various alternatives and criteria that are complex and uncertain. Standard mathematical calculations cannot solve complex problems including geographic coordinates (X, Y) and spatial approaches. The contribution of this paper was a new method synergizing advanced non-numeric Multi-Expert Multi-Criteria Decision Making (ME-MCDM) and modified Dijkstra algorithm with spatial perspectives. The selected route was determined by multiplying Distance (D) in the classical Dijkstra algorithm with Alternative Values (AV) from non-numeric ME-MCDM using spatial perspective (S). We argued that spatial perspectives namely topography, road segments, multi-hazard zone indexes, and spatial-temporal congestion need to be considered. In this new method, we provided the ratio values (R) for each spatial variable. The most optimal route (Rs) was determined by calculating the Total Alternative Value (TAV) in each path that was considered conflicting multi-criteria. The smallest TAV value is selected as the most optimal route. The results showed the new method provides a more reasonable and meaningful solution compared with the classical Dijkstra algorithm results. Based on the verification and validation, this new method showed that the optimal route was not always the shortest. So, this new method can be used to determine the optimal distribution route selection which is more suitable for the agro-industrial sector. For further research, this method can be applied to optimize the supply and demand balance.
Keywords: distribution route selection; non-numeric ME-MCDM; modified Dijkstra algorithm; spatial perspectives.
Data Mining based analysis of the Human Activity in healthy subjects using smart phones
by Ankitha S, Sanjay H S
Abstract: Human-Activity-Recognition(HAR) approach provides a valuable insight about their interaction with the surrounding environment. The present work highlights an assessment of HAR using accelerometer and gyroscope sensors embedded in Samsung Galaxy-S2 smartphone to acquire 6 activities namely WAlking(WA), Walking-Upstairs(WU), Walking-Downstairs(WD), SItting(SI), STanding(ST) and Laying(LA) with data mining approaches. HAR data was pertaining to 30 healthy subjects of age 19-48 years, both males and females acquired with an informed consent. Linear Discriminant Analysis (LDA) was used for dimension reduction. Classification was performed with and without LDA using Support Vector Machine (SVM), Multiple Layer Perceptron (MLP), Decision Tree (DT), Extra Tree (ET), K Nearest Neighbor (KNN), Random Forest (RF) and Gradient Boosting Machine (GBM) approaches in python platform. The results showed an increase in accuracy with LDA based dimension reduction. SVM (with C=10, Gamma = 0.001 with RBF kernel) provided the highest accuracy for both the cases (SVM without LDA = SVM with LDA = 96%). However, the highest variation based on LDA was seen in case of DT approach (DT without LDA = 85% and DT-with LDA = 95%). Such predictions can help the subjects with limited locomotion in the field of rehabilitative engineering using Augmented as well as Virtual Reality.
Keywords: Human Activity recognition; Accelerometer; Gyroscope; Linear discriminant analysis; Rehabilitative engineering.
Multiple Criteria ABC Classification: An Accelerated Hybrid ELECTRE-PSO Method
by Ezzatollah Asgharizadeh, Amir Daneshvar, Ehsan Yadegari
Abstract: The objective of inventory management is to make decisions regarding the appropriate level of inventory. ABC classification analysis as the widely used inventory management approach, categorizes inventory items into predefined classes namely A, B and C. The limitation of the ABC management system is that only one criterion is considered, however, as generally emphasized in the literature, the inventory classification is a multi-criteria problem. So, this paper proposed a Multiple Criteria ABC Inventory Classification (MCIC) for the ABC inventory classification. Since, these models cannot handle the qualitative criteria and in many cases the classification problem isnt fully compensatory, this study integrates a non-compensative multi-criteria decision making technique (ELECTRE TRI) with a machine learning algorithm (PSO) to effectively conduct multi-criteria inventory analysis. Since, the application of ELECTRE TRI method requires to determine the preferences of decision makers (DMs) on some parameter values (e.g. prototypes pessimistic intervals and discrimination thresholds), the under consideration criteria and their related parameters are numerous and their interpretation is confusing, especially in large scale problems, the solution process is very complex and time-consuming. Tackling these difficulties, this paper proposed a method to infer all ELECTRE TRI parameters through a procedure using the previously classified inventory items determined by DMs. Then, a hybrid Particle Swarm Optimization (PSO) algorithm applied to induce parameters of ELECTRE TRI. Finally, for accelerating the PSO procedure to find the local and global optima and balance these points, the Variable Position (VP) model is proposed as an exploitation and variable exploration model with new velocity components. The findings indicate that the proposed model maximizes classification accuracy on each inventory dataset. In order to present the validity of the proposed method, it is applied to 6 inventory datasets and the results is also compared with some of the commonly used classification methods from the literature. The results also revealed high applicability of the proposed model to inventory classification problems.
Keywords: Inventory Classification; Outranking relations; PSO; ELECTRE TRI.
Inventory Policies under Fuzzy and Cloud Fuzzy Environment
by Nita Shah, Milan Patel, Pratik Shah
Abstract: This article is an attempt to extend the classical economic order quantity (EOQ) model for deteriorating items under fuzzy and cloud fuzzy environment. Inventory parameters such as holding cost, purchase cost, ordering cost, demand rate and deterioration rate are considered as triangular fuzzy numbers as well as cloud triangular fuzzy numbers to develop fuzzy and cloud fuzzy models respectively. Yagers ranking method and De and Begs ranking methods are used for defuzzification. A comparative study reveals the superiority of cloud fuzzy model over crisp and fuzzy model. Further, numerical example, graphical illustrations and sensitivity analysis are carried out for better understanding of the application of cloud fuzzy approach to inventory optimization problem.
Keywords: Inventory; EOQ; deterioration; cloud triangular fuzzy number.
E-commerce research in developing countries: A systematic review of research themes, frameworks, methods and future lines of research
by Frederick Pobee, Thuso Mphela
Abstract: AbstractrnThis paper presents a systematic review of e-commerce adoption research on developing countries with focus on the classification of literature and their associated themes, frameworks, research methodology over the period of ten years. A total of 151 articles from 35 peer reviewed journals from 2010-2019 were retrieved and used in the analysis. The findings reveal that majority of e-commerce adoption studies on developing countries tend to skew towards trust and satisfaction issues to the detriment of other under researched issue like attitude towards e-commerce adoption. Though there hasnt been a constant increase in e-commerce research on developing countries over the past 10 years, a significant number of published studies used qualitative approach as method of enquiry as compared to quantitative and mixed methodologies. Also, majority of e-commerce studies on developing countries have not been supported with theoretical frameworks and models. As contribution, this paper provides an in-depth analysis of e-commerce adoption in developing countries showing the trends of research themes, methodologies and frameworks. Implications for future research was discussed.rn
Keywords: Keywords: E-commerce; developing countries; research frameworks; methodologies; adoption.
Cybersecurity Antecedents of Trust: Toward OPS adoption in Jordan
by Yazan Alshboul, Nareman Al.Hamouri
Abstract: Online services such as online banking, particularly, the online payment system (OPS), plays an important role in modern life. In developing countries, there is a kind of resistance to adopting OPSs. Therefore, more focus is needed to understand the behavior toward OPS, especially in developing countries. This paper integrates the trust model and the theory of planned behavior and addresses the antecedents of the trust factor in the context of OPSs. Particularly, it focuses on the cybersecurity factors as antecedents to the trust model. We tested our model empirically using data gathered from 200 participants who use eFawateercom system, an online payment system used in Jordan. The results showed that cybersecurity factors like systems security, privacy, and reliability play an essential role in affecting users trust, which has a crucial impact on the attitude toward OPS adoption. This article concluded with implications for academia and practitioners.
Keywords: Online payment system; cybersecurity factors; trust; security; privacy; reliability.
A multi-view approach to multi-criteria decision making
by Francisco Santos, André Coelho
Abstract: Multi-view learning is a field of machine learning that deals specifically with data represented by distinct feature sets (known as views), possibly coming from multiple information sources. In this context, canonical correlation analysis (CCA) stands out as a representative technique, since it allows the automatic extraction of linear correlations among groups of data features in the form of canonical variables. In this paper, inspired by the great success of multi-view learning, we bring about a new perspective to multi-criteria decision making (MCDM), referred to as multi-view multi-criteria decision making (MV-MCDM), which is centered upon the application of CCA to distinct groups of judgement criteria (referred to as criteria views). By resorting to MV-MCDM, one can deal more naturally with multi-view multi-criteria problems than standard MCDM methods. Moreover, our approach enables the estimation of very reliable values for criteria weights via CCA. Another interesting advantage is that MV-MCDM entails the reduction of the dimensionality of the decision matrix by considering only one of the available views. In addition, we show that the MV-MCDM methodology permits the easy multi-view extension of well-known MCDM methods, such as SAW (simple additive weighting) and TOPSIS (technique for order of preferences by similarity to ideal solution). MV-MCDM is also generic enough to allow the adoption of different aggregation methods to generate the overall scores of the alternatives. In this regard, we show that the use of canonical variate correlation coefficients as fuzzy density measurements can make it possible the application of the Choquet integral. Besides, a new heuristic aggregation method based on radar charts is also considered. Finally, a numerical example focusing on the multi-view versions of SAW and TOPSIS demonstrates the applicability of the proposed approach.
Keywords: MCDM; Multi-view Canonical Correlation Analysis; TOPSIS; SAW; Choquet integral.
Discerning the traffic in Anonymous Communication Networks using Machine Learning: Concepts, Techniques and Future Trends
by Annapurna P. Patil, Lalitha Chinmayee MaheshKumar Hurali
Abstract: With the growing need for anonymity and privacy on the Internet, Anonymous Communication Networks (ACNs) such as Tor, I2P, JonDonym, and Freenet have risen to fame. Such anonymous networks aim to provide freedom of expression and protection against tracking to its users. Simultaneously, there is also a class of users involved in the illegal usage of these ACNs. An emerging research topic in the field of ACNs is network traffic classification, as it can improve the network security against illegal users as well as improve the Quality of Service for its legal users. In this study, we review the research works available in the literature relevant to traffic classification in ACNs based on Machine Learning and also present to the researchers the general concepts and techniques in this area. A discussion on future trends in this area is also provided to bring out the future enhancements required in ML-based network traffic classification in ACNs.
Keywords: Anonymous communication networks; Machine Learning; Traffic classification; Tor; Network security;.
Modelling Big Data Analysis Approach with Multi-agent System for Crop-yield Prediction
by Jaya Sinha, Shri Kant, Megha Saini
Abstract: Big data environment in current scenario is dealing with challenges in handling inherent complexity residing in the massive heterogeneous, multivariate and continuously evolving real time data along with offline statistics. The role of big data analytics to analyze such a highly diverse data also plays a significant role in estimating predictive performance of a system. This paper thus aims at proposing an intelligent agent based architecture that coordinates with big data analytics framework to model a system with an objective to improve the predictive performance of system by handling such diverse data. The paper also includes implementing predictive algorithm to predict crop yield in the agricultural domain. Various machine learning analytical tools have been used for data analysis to produce comprehensive and more accurate prediction using the proposed architecture.
Keywords: Multi-agent System (MAS); Big data; Data acquisition; Data analysis; Data storage; Machine learning; Intelligent agents.
The Art of Context Classification & Recognition of Text Conversation using CNN
by Sandeep Rathor, Sanket Agrawal
Abstract: This paper proposes a robust model for recognizing the context of a conversation by using CNN. Initially, preprocessing is performed on the input text conversation. It includes lowercase conversion followed by tokenization, padding, and word embedding. The embedding layer gives out a feature matrix. This feature matrix is passed to a multi-level Convolution Neural Network. The proposed model is designed in such a manner that each CNN reduces the input matrix to half of the input size. Thus, the output of the next CNN layer and the pass of the current CNN layer followed by average pooling can be added. This output is named a global pass and passed to another block of the same architecture. The output from the last CNN layer and global outputs are concatenated and finally, passed into two fully connected layers FC(512) & FC(8). The output from FC(8) gives the probability of conversation to belong to eight contexts. Finally, the context with the highest probability is taken.
Keywords: Context Recognition; Text Conversation; Text Mining; CNN; Machine learning.
In Search of Sustainable Electronic Human Resource Management in Public Organizations
by Reza Sepahvand, Khaled Nawaser, Mohammad Hossein Azadi, Ali Vafaei-Zadeh, Haniruzila Hanifah, Razieh Bagherzadeh Khodashahri
Abstract: Over the past two decades, issues such as environmental degradation, continued marginalization of large groups of people, growth of anti-globalization sentiments, and demand for innovation and creativity in public and private sectors have emerged as prominent global organizational problems. These developments have led to a growing interest in the concept of sustainability, which many Human Resource Management (HRM) researchers believe can enhance HRM capabilities and activities, leading to better organizational performance and competitive advantage. Given the significant impact of Information Technology (IT) on HRM, identification of factors affecting the implementation of sustainable Electronic Human Resource Management (SEHRM) in organizations can result in significant cost reduction and more principled organizational decision making. The present study aimed to identify and evaluate the factors affecting the implementation of sustainable EHRM in public organizations using type-2 fuzzy FMEA. After reviewing the research literature and surveying experts, 29 factors in three dimensions of social, environmental and economic were identified. After designing and distributing the questionnaire among experts, type-2 fuzzy AHP was used to determine the weight of risk factors of FMEA (occurrence probability, severity, and detectability). The identified factors were then ranked using type-2 fuzzy TOPSIS. The results showed that the social dimension is the most important dimension for the implementation of sustainable EHRM in the study area. The critical individual factors in order of significance for this implementation were found to be EHRM Reengineering, Green Performance Evaluation, IT Infrastructure, ECRM, Electronic Customer Satisfaction, Employee Safety, and Electronic Services.
Keywords: Sustainable Electronic Human Resources Management; FMEA; Type 2 Fuzzy TOPSIS; Type 2 Fuzzy AHP.
A Multi-Criteria Decision Support System for the Assessment of Cities based on Air Quality Indicators
by Supriya Raheja, Rakesh Garg, Aakash Gupta, Geetika Munjal
Abstract: A deterministic decision support system is developed for the assessment and ranking of various cities based on the air quality indicators in this research. The present study models such assessment of cities as a multi-criteria decision making (MCDM) problem due to the involvement of multiple air quality indicators. Further, to solve the present assessment problem, a hybrid MCDM approach, namely, Entropy- Evaluation based on distance from average solution (EEDAS) is implemented by integrating two well-known approaches such as Shannon entropy and evaluation based on distance from average solution (EDAS). Shannon entropy approach is used to calculate the priority weights of the air quality indicators whereas the EDAS method is used to get the comprehensive ranking of the cities based on the identified air quality indicators.
Keywords: Air Pollution; Air quality indicators; Multi-Criteria decision making (MCDM); Entropy; EDAS; Decision support system.
Analyzing Impact of IT Investments on Banks Performance using Multi-Stage DEA
by Ankit Mehrotra, Reeti Agarwal
Abstract: The paper studies the impact of investments made in information technology (IT) on a firms performance. The paper makes use of multi-stage Data Envelopment Analysis (DEA) to find out the marginal impact of IT investment on firms performance. The paper uses a three-stage DEA approach by introducing a new variable i.e. communication expenses to study what bearing IT has on a firms efficiency attainment. The paper also extends existing literature related to the indirect influence of IT on a firms performance by making use of a non-parametric approach, DEA. To attain the aims of the study, data of a number of banks was considered for a period of five years. The study introduced IT variables at two stages of the analysis to analyze its marginal effect on efficiency outcome.
Keywords: Data Envelopment Analysis; DEA; performance; efficiency; information technology; bank; marginal effect.
Compromise ranking based on superiority, inferiority and Euclidean normalized similarity metrics: The ESIASP method
by Moufida Hidouri
Abstract: Xiaozhan Xu introduced in 2001 the superiority and inferiority ranking (SIR) methods called SIR.TOPSIS and SIR-SAW. The SIR.TOPSIS method has two quite different variants, which we call here SR.TOPSIS and IR.TOPSIS. What is noteworthy is that each variant gives attention only to one type of indexes rather than both types, which may result in questionable ranking results because both variants ignore available relevant indexes. In addition, the SIR.TOPSIS variants (ranking) indexes have been based on the TOPSIS relative closeness coefficient, which is inflexible in the sense of not being affected by the relative importance of separations of each alternative from positive ideal solution and negative ideal solution.
The SIR.SAW method ignores the relative significances of superiority flows (overall degrees of support for alternatives) and inferiority flows (overall degrees of support against alternatives).
It is therefore worthwhile to introduce a new ranking method to overcome the flaws seen in Xus SIR methods. The crisp method proposed in this paper, called the Evaluation based on Similarity to Ideal Augmented Superiority Profile (ESIASP) method, fully exploits all the available relevant indexes and takes account of their relative importance.
Finally, a supplier selection problem is given to demonstrate the proposed method. A comparison of rankings produced by the ESIASP method, SIR.TOPSIS and SIR.SAW variants shows that the suggested method is a relevant and implementable alternative to Xus SIR methods.
Keywords: crisp method; inferiority; SIR.SAW; SIR.TOPSIS; superiority; supplier selection.
Eliciting individual risk attitudes different procedures, different findings
by Sven Grüner, Norbert Hirschauer, Felix Krüger
Abstract: We compare three procedures for eliciting individual risk attitudes: Holt-and-Laury (2002), Eck-el-and-Grossman (2002), and the general willingness-to-take-risks question of the German socio-economic panel. Using a within-subject design, we carry out a classroom experiment with stu-dents who are enrolled in the degree programs Physics, Computer Sciences, Agricultural Scienc-es, Law, and History. We find that the risk attitudes as measured by the three procedures diverge substantially. This poses a serious challenge to the validity of these measurement instruments.
Keywords: Risk-attitude; Eckel-and-Grossman procedure; Holt-and-Laury procedure; self-reported willingness-to-take-risks; bounded rationality.
Evaluation and selection of a casting process using interval type-2 fuzzy analytical hierarchy process
by Devesh Sahu, Atul Chakrawarti
Abstract: Selection of a casting process is a kind of multi criteria decision making process, in which several factors like Cost, material utilization and flexibility, geometrical complexity and flexibility and dimensional accuracy and surface finish. As cost is considered as one of the prime criteria in decision making, so it is further sub categorised into three sub criteria i.e. tooling cost, equipment cost and labour cost. Past researchers have used multi criteria decision making technique like analytical hierarchy process along with type-1 fuzzy in the evaluation and selection of casting process, which is successful in handling the fuzziness of the system, but are unable to address the issue of uncertainty associated with decision making. So, in this paper interval type-2 fuzzy analytical hierarchy process is used to evaluate and select best casting process, which is capable of handling uncertainty associated with decision making. A numerical illustration is solved using the interval type-2 fuzzy analytical hierarchy process and it is found that investment casting is evaluated as best casting process for cam carrier and is ranked number one.
Keywords: Casting; MCDM; decision support system; type-2 fuzzy; AHP.
Combined Application of Condition Based Maintenance and Reliability Centred Maintenance using PFMEA and Lean Concepts A Case Study
by Claudia Carvalho De Oliveira, José Cristiano Pereira, Nélio Pizzolato
Abstract: Productivity is an essential element for competitiveness, helping companies to be better prepared for the future, given all of today's challenges. Such productivity needs to be clearly confirmed by operational results. This paper covers assets maintenance effectiveness, one of the productivity evaluation components increasingly gaining business attention. The proposed methodology helps the achievement of the required effectiveness on asset maintenance, by combining the concepts of Reliability Centered Maintenance and Condition Based Maintenance, also supported by PFMEA, a successful risk management strategy, and Lean Manufacturing practices. A case study was conducted in a high technology enterprise, combining those referred concepts. The implementation process used Minimum Viable Product strategy. The main concept is based on suitable equipment inspection and diagnosis practices which guides interventions and cleverer behaviour towards asset management. As a result, in the first year of implementation, 5 to 10% cost reduction was obtained together with a significant increase in equipment availability which has reached a level of 95%+.
Keywords: Reliability Centered Maintenance; RCM; Condition Based Maintenance; CBM; PFMEA; Lean Maintenance; asset Management; MVP.
Towards Building a Comprehensive Big Data Management Maturity Framework
by Mervat Helmy, Sherif Mazen, Amal Elgammal, M.Wagdy Youssef
Abstract: Profound insights are generated today from exploiting big data. However, organisations are still not recognising how mature their big data management capabilities are, and what improvements are needed. There is still no structured approach to assess the maturity of big data management capabilities. Existing solutions lack a consistent perception of big data management capabilities, a reliable assessment, and a rigid improvement scheme. So, the main contribution of this article is conducting an analytical study on existing key works in assessing and building big data management capabilities, and upon, the main requirements for building a comprehensive big data management maturity framework are proposed. Results of validating the developed framework proved that it enabled organisations to assess, build, and improve their current big data management capabilities.
Keywords: big data management maturity; big data management; big data management capabilities; big data capabilities; big data analytics capabilities; big data analytics capabilities construct; big data maturity; big data maturity model; big data maturity assessment; big data capabilities assessment.
Determining a Model for Eliminating Organizational Lying: A Grounded Theory Approach
by Mohammad Hakkak, Khaled Nawaser, Mohammad Jalali, Samaneh Ghahremani, Ali Vafaei-Zadeh, Haniruzila Hanifah
Abstract: The present study has been implemented to generate a theory in the field of organizational lying for better understanding and explaining the phenomenon in organizations. The research method is qualitative and based on the Grounded Theory. Semi-structured interviews were used for data collection and Strauss and Corbin Method and paradigmatic model were adopted for data analysis. Sampling was done using a theoretical sampling method and targeted (judgmental) and snowball (chain) techniques based on which 21 interviews were conducted with managers, employees and experts of the Imam Khomeini Relief Foundation (a charitable organization founded in 1979 to provide support for poor families and also known as IKRF) of Kurdistan Province in Iran who were familiar with the issue and context. The results of the analysis of the data obtained from the interviews during the open, axial and selective coding processes led to the formation of a grounded theory concerning the organizational lying based on which the purposeful lying, blind lying, and silent lying were introduced as the basic concepts of the Organizational Lying Model.
Keywords: Organizational Lying; Antecedents of Lying; Consequences of Lying; Grounded Theory.
EOQ model for time dependent demand with deterioration, inflation, shortages and trade credits
by R.P. Tripathi
Abstract: The Inflation acts an important role for each area of life in the world. Inflation varies rapidly for high tech commodities with passing over time. This study develops an EOQ model with time sensitive demand rate for deteriorating products and shortages with inflation over a predetermined planning horizon. Mathematical formulations are prepared under two cases (i) time for positive inventory (T1) is greater than credit period M and (ii) T1 is less than or equal to credit period M, to gain optimal number of replenishment and cycle time. An algorithm is presented to find most favorable cycle time so that total annual relevant profit is maximized. We then demonstrate the total profit is concave with respect to number of replenishments. Numerical examples are offered to display the model. Sensitivity investigation for variation of a number of key parameters is also discussed. Mathematica 7.0 software is used to calculate numerical results and optimality conditions.
Keywords: Cash flow; inflation; non- increasing demand; credit period; shortages.
Investigation of the rank reversal problem in some novel objective weight based MADM methods
by Ravindra Singh Saluja, Varinder Singh
Abstract: Objective weight based multi-attribute decision making (OWMADM) methods are applied in decision situations where the weight values are not sought from decision makers and are rather obtained based on the range or spread of attribute data. The present study develops three novel OWMADM methods namely Preference Selection Index Proximity indexed value Method (PSIPIVM), Standard Deviation Proximity indexed value Method (SDPIVM) and Entropy Proximity indexed value Method (EPIVM), by combining the objective weights obtained through three different methods with recently developed proximity indexed value method (PIVM), which is known to promote minimization of the rank reversal problem. Two established criteria are adopted to evaluate the occurrence of rank reversal, one by removing the least preferred alternative from consideration while another involved splitting the considered alternatives into two sets and testing for the transitive property. The paper also attempts to identify suitable normalization techniques for the proposed OWMADM methods to yield robust ranking orders, which may enhance the reliability of decision outcome.
Keywords: Multi-attribute decision making; Objective weight; PSI; SD; Entropy; PIVM; Rank reversal; Decision analysis.
A Bi Objective Optimization Technique for Scheduling Repetitive Projects
by JEENO MATHEW, BRIJESH PAUL
Abstract: Repetitive projects are projects in which the same type of works/activities get repeated in different locations or sites. For each of this type of projects, different crew options are available for each activity and selecting the best option corresponding to each activity is a difficult task. Project managers in these projects are often faced with the task of finding out the best schedule corresponding to the optimum project duration and expenditure which will satisfy different constraints like due time in which each activity to be completed, movement of crew from one location/unit to other, precedence relationship among different activities etc. In this case, the decision maker wants to get a solution that simultaneously optimizes the two conflicting and diverse objectives of duration and expenditure while obtaining an acceptable trade off amongst the objectives. Therefore, development of a suitable solution method, which gives near optimal solutions while considering single objectives like minimization of project duration or project expenditure and also for bi objective optimization considering minimization of the combined effect of duration and cost, is very important. Since the computational complexity is very high in these type of projects, an ABC algorithm based heuristic methodology is developed in this study which can give good solutions for satisfying the above mentioned objectives with respect to different constraints. The proposed methodologys performance is analyzed with exact solutions and the results show that an ABC algorithm based methodology gives significantly good quality solutions.
Keywords: ABC Algorithm; Repetitive projects; Optimization.
Availability and Mean Time to Failure for Repairable k-out-N: G Systems with Identical Components
by Mohammed Hajeeh
Abstract: This study presents Markov models for assessing the availability and the mean time to failure (MTTF) of a k-out-of n: G system with exponentially distributed time between failures and repair times. Generalized analytical expressions for the steady-state availability and MTTF are derived. Furthermore, numerical results are provided to illustrate the performance of several models along with the cost of adopting different configurations.
Keywords: k-out-of n: G system; Availability; Mean time to failure; Cost.
NoSQL based approach in data warehousing and OLAP cube computation
by Abdelhak Khalil, Mustapha Belaissaoui
Abstract: Over the last few years, Not only SQL (NoSQL) databases are gaining increasingly significant ground and are considered as the future of data storage. In this paper we are interested in implementing NoSQL-OLAP systems by defining mapping rules from the multidimensional conceptual level to logical key-value model, and providing a set of online analysis operators. We consider two different approaches in order to implement a big data warehouse within key value stores. The first one uses SQL-like table structure layered on top of the key-value schema, the second one uses a simple key-value pair structure. Then we provide aggregation operators (Map-Reduce Cube and Bit-Encoded Cube) for key value models in order to perform OLAP cube computation. We implemented OLAP operator using Oracle NoSQL database and LevelDB, and we conducted experiments on a fictional data warehouse produced by an existing benchmark that considers NoSQL models. Thus, results showed clearly the performance of OLAP implementations under NoSQL key value stores in terms of efficiency and scalability.
Keywords: OLAP; Data Warehouse; NoSQL; Big Data; Cube Model.
SOFT SKILLS FUZZY TOPSIS RANKED MULTICRITERIA TO SELECT PROJECT MANAGER
by Luciano Ferreira Da Silva, Paulo Oliveira, Gustavo Grander, Renato Penha, Flavio Bizarrias
Abstract: This study aims to use fuzzy logic to select a project manager based on soft skills. In the first phase, a focus group interview was applied to establish the weights according to the soft skills list selected. In the second phase, the Fuzzy Topsis logic was applied. According to the concept of the Fuzzy Topsis, a closeness coefficient is defined to determine the ranking order of all alternatives. The results allowed the construction of the framework here called Fuzzy Topsis Ranked Multicriteria for selecting the best candidate according to the profile and criteria adopted. The contribution of this study is to allow the attribution of values to soft skills that, in essence, are subjectivity. This framework is friendly, the investment required is low, and it is adaptable to different contexts.
Keywords: Fuzzy Topsis; Multicriteria Decision; Project Manager Selection; Soft Skill.
A GIS-Based Framework For Flood Hazard Vulnerability Evaluation In Thudawa Area, Sri Lanka
by MALLIYAWADU RASHINI NUWANKA, NEEL CHAMINDA WITHANAGE
Abstract: At present flash floods became as one of the most devastating natural disasters all over the world especially in tropical areas including Sri Lanka. Considering the increase of flood events in recent years, accurate flood risk assessment is an essential component of flood mitigation in highly populated urban areas. The objectives of our research were to identifying and classifying flood risk areas into different classes in Thudawa area, Sri Lanka, and developing a Geographical Information System (GIS) model to identify flood vulnerability areas accurately in Thudawa area. Through this, it was expected to proposing preventive guidelines of flood hazard vulnerability using geo-informatics. As located near the Nilvala River mouth Thudawa is having a high risk for flash flood events over the recent period. Therefore, it was very important to conducting a Geo informatics-based risk assessment in the area. The methodological procedure is extremely important in this type of research thus, the spatial Multi-Criteria Decision Analysis (MCDA) procedure was used. Multi-criteria analysis has been widely applied to solve decision-making problems related to the environment, and natural resource management. For this research Analytical Hierarchy Process (AHP) was used for the criterion weighting. To run the GIS model in ARC GIS environment AHP calculations run upon the results of experts' judgment as proposed by the Satty incorporating pair-wise comparison method. The results of this study attempt to analyze the existing flash flood risk levels using the GIS-based multi-criteria analysis technique which allowed ranking of risk areas since it is important in the decision-making process to mitigate the flood risk in the study area. And also, the results of the research will be more useful to identify future risk areas for flood hazards in disaster management and land use planning as well as, on the other hand, it can provide valuable support for a range of decisions such as land use master planning, design of infrastructure, and emergency response preparation in the area. This study can be taken as a reference for researchers who engage with similar studies in the same or other areas using Geo-informatics tools after integrating other methods and tools such as fuzzy AHP method, fuzzy multiple-attribute decision-making method, fuzzy TOPSIS, and Pythagorean fuzzy AHP.
Keywords: AHP; Flood Hazard; GIS; MCDA; Modelling.
D4SP Decision Support System based on the use of the AHP method for Science Park Selection
by Bruno Moura, Ivo Santos, Nelson Barros, Fernando Luis Almeida
Abstract: The literature reveals that science parks offer numerous benefits and support services to the activity of a technological startup. However, the decision of choosing the best science park for the startup tends to be an informal process, technically not very rigorous and planning, arising essentially by affinities with the research center and university. In this study, a decision support system is presented to support entrepreneurs in the process of selecting a science park for the implementation of their startup. The AHP method is used to compare the importance of the criteria for selecting a science park, which includes factors such as location, activity sector, infrastructure, cost, and size. The findings reveal that the use of this decision support system helps entrepreneurs to find a science park that is suitable for the needs of their startup and allows them to comparatively identify the most relevant criteria when choosing a science park.
Keywords: entrepreneurship; decision science; AHP; startups; new venture; science park.
Artificial Neural Networks in the Development of Business Analytics Projects
by Juan Bernardo Quintero, David Villanueva-Valdés, Bell Manrique-Losada
Abstract: The accelerated evolution of information and communication technologies, with an ever-growing increase in their access and availability, has become the foundation for the current big data age. Business Analytics (BA) has helped different organizations leverage the large volumes of information available today. In fact, Artificial Neural Networks (ANNs) provide deep data-mining facilities to organizations for identifying patterns, predict future states, and fully benefit from predictions/forecasts. This article describes three ANNs application scenarios for developing BA projects, by using network learning: i) for executing accounting processes, ii) for time series forecasts, and iii) for regression-based predictions. We validate scenarios by implementing an application-case using actual data, thus demonstrating the full extent of the capabilities of this technique. The main findings exhibit the expressive power of the programming languages used in data analytics, the wide range of tools/techniques available, and the impact these factors may have on the BA development projects.
Keywords: Artificial Neural Networks; Business Analytics; Data Analytics; Big Data; Deep data mining; Network learning process; Time series forecast; Regression-based prediction; Activity Based Costing; Supervised learning; Decision making.
Designing a decision support system for integrated production and distribution planning in shrimp agro-industry
by Lely Herlina, Machfud Machfud, Elisa Anggraeni, Sukardi Sukardi
Abstract: The integration of production and distribution planning is essential for the efficiency and responsiveness of the shrimp agro-industry. Due to the large number of actors involved in the supply chain and intense competition from similar industries, the integration needed. Besides, uncertainties in the supply of perishable raw materials, annual growth and harvest, various sizes and yields, and voluminous are challenges for the shrimp agro-industry. To overcome this, the integration production and distribution planning needed a decision support system (DSS). This study aims to develop a prototype of a decision support system that integrates production and distribution planning in shrimp agro-industry. To test the designed system, a multi-objective Evolutionary Algorithm (MOEA) framework used resulting in that DSS-shrimp can provide a validated mechanism for decision making in an integrated production and distribution planning in shrimp agro-industry.
Keywords: decision support system; production planning; distribution; supply chain; agro-industry; multi-objective Evolutionary Algorithm;.
How young consumers are influenced by the valence of positive and negative frames: a cross-cultural perspective
by Theodore Tarnanidis, Kofi Osei-Frimpong, Jason Papathanasiou, Nana Owusu-Frimpong
Abstract: The specific study examines the use and the impact of three types of framing effects in different mental activities and everyday situations in consumers lives, namely: attribute, goal, and risky choice framing. Although, many studies across the globe have proposed empirical framing models that differ each other due to context discrepancies and other implicitly information. Yet, framing effects in the international cross-cultural perspective remain a pervasive issue. Having that purpose in mind this study aims to contribute to the examination of the literatures on framing effects between two diverse contexts with dissimilar environments, i.e. Greece and Ghana. The first one has a strong democratic culture over the last 2.500 years, whereas the other is characterized by long periods of military rule. Thus, cultural variations make people to make decisions differently. To that extent, data was collected in two stages from 590 young consumers (i.e. students) from Greece and Ghana. The different framing types were examined by using a within subjects design that provided participants the positive and negative conditions of each framing task. The results suggest a partial inter-correlation between the three categories of framing effects. In the attribute framing examinations, gain-framed messages make people to focus on the positive outcomes, whereas loss-framed messages have negative evaluations. Likewise, in the goal framing case, the majority of the subjects from both countries preferred the positive condition. And when decisions involve a risky option, Greeks in the positively framed condition were split between risk avoid and risk seeking behaviour, whereas Ghanaians have only a risk-seeking behaviour. In contrast, in the negatively framed condition all study subjects showed a risk seeking attitude. The findings provide unique technical insights into the consumer framing arena for future evaluations.
Keywords: decision framing; framing effects; cognition; prospect theory; Greece; Ghana.
An Intelligent Decision Support System Modelling for Improving Agroindustrys Supply Chain Performance: A Case Study
by Muhammad Asrol, Marimin Marimin, Machfud Machfud, Moh. Yani
Abstract: Decision-making has an important role to improve agroindustrys business process performance. This research comprises 4 important aspects to determine agroindustrys performance, namely supply chain performance, risk management, green productivity performance and agroindustrys business promising. This paper proposed an Intelligent Decision Support System (IDSS) which was organized of main performance models to improve agroindustrys competitiveness. Supply chain performance modeling was organized by Supply Chain Operation Reference (SCOR) framework, agroindustrys risks assessment using Fuzzy House of Risk, green productivity evaluation using Green Productivity Index (GPI) and Fuzzy Inference System (FIS) while agroindustrys business promising and feasibility assessment which was modelled with FIS. Overall supply chain performance was developed by Single Input Single Output Fuzzy model to realize the final agroindustrys supply chain performance. An IDSS was comprised database, model-base and knowledge base to be periodically simulated the supply chain performance measurement of agroindustry. The proposed IDSS was validated under real condition of a sugarcane agroindustry and found that the supply chain business performance was moderate, it had high risk threat, normal green productivity performance and moderate feasible of business promising performance. The overall supply chain performance validations showed that sugarcane agroindustry -as a case study- performance was moderate. For further research, this paper requires experienced expert verification to formulate the supply chain performance improvement strategy and verify the IDSS model to be implemented for the real world.
Keywords: Agro-industry; Fuzzy system; Green productivity; Intelligent decision support system; Risk management; Supply chain.
A CASE STUDY TO PREPARE THE FRAMEWORK SOLUTION FOR OPERATIONAL EXCELLENCE DURING THE RECESSION AT MANUFACTURING INDUSTRY
by Rohit Kenge
Abstract: Since December 2019, the world is facing COVID 19 pandemic and its impact on the economy. As the product demand is shrinking, the product supply with the pre-installed capacities is facing major issues like job cuts, high unsold material inventory, and the running of companies at lower capacities. To answer these operational issues, we prepared the research hypothesis framework integrating the twelve operational excellence factors into an operational excellence model consisting of people, process, and flow approach. We evaluated this hypothesis through a set of 36 questionnaires for a survey based on the Likert scale and received 402 complete responses. We performed the analysis of survey response data by testing the reliability, correlation, validity, and structural equation modelling and found out that organizational performance has a significant positive impact on our proposed operational excellence model. Also, organizational performance has a significant positive impact on our proposed operational excellence model.
Keywords: Operational Excellence; Recession; Organizational Performance; COVID-19; Demand-Supply Cycle.
Designing a method to model the socio-technical systems
by Mohammad Mirkazemi Mood, Ali Mohaghar, Yaser Nesari
Abstract: To capture the complexity and diversity of systems with both technical and social features, modeling methods are needed that similarly provide various tools and concepts. Study of developed methods shows that despite all of their advantages and strengths, there is a need for a method that with a holistic approach integrates perspectives, strengths and tools of the developed methods and models with different aspects of socio-technical systems. The main aim of the current study is to design a method for modeling complex socio-technical systems. To achieve this goal, it is necessary to design a method that is based on creativity and existing knowledge base. Therefore, Design science research is used as a research strategy to design proposed method. For the first time, design science research in the field of operations research has been used to design a modeling method. This study also presents new tools and concepts for modeling socio-technical systems.
Keywords: Design science research; Soft operations research; Problem structuring methods; System thinking; Meta-synthesis; Modeling methods.
Examination Gym Centers Design Criteria using multicriteria decision analysis methodologies
by Cansu Ergun, Sumeyra Elif Erdogan, Gokhan Aldemir, Ferhan Cebi
Abstract: Designing a gym and selecting its atmospheric elements are time-consuming and difficult to change. Therefore, the aim of our study is to provide a beneficial and different perspective for operators who are considering designing a gym. Our study starts with a participatory observation in order to examine consumer behavior in the natural state after the studies in the literature are examined. An interview and a survey study are conducted to define the crucial criteria for the consumer in the gym. A hierarchy is created, and a paired comparison is made to illustrate the importance levels. Accordingly, analytical hierarchy process (AHP) is applied and the criteria are sorted according to their importance. Different concepts are formed by giving different values to the criteria. The concepts with the highest score are determined by the concept selection matrix and their architectural designs are made by programs. The most optimal design is determined by the concept test.
Keywords: multicriteria decision making; gym design; AHP; consumer behavior.
A data mining model to predict the debts with risk of non-payment in tax administration.
by Maria Hallo, José Ordoñez Placencia, Sergio Luján-Mora
Abstract: One of the main tasks in tax administration is debt management. The main goal of this function is tax due collection. Statements are processed in order to select strategies to use in the debt management process to optimize the debt collection process.
This work proposes to carry out a data mining process to predict debts of taxpayers with high probability of non-payment. The data mining process identifies high-risk debts using a survival analysis on a dataset from a tax administration.
Three groups of tax debtors with similar payment behavior were identified and a success rate of up to 90% was reached in estimating the payment time of taxpayers. The concordance index (C-index) was used to determine the performance of the constructed model. The highest prediction rate reached was 90.37% corresponding to the third group.
Keywords: Data mining; debt management analysis; machine learning; taxpayer behaviour patterns; survival analysis.
Dimensions of anti-citizenship behaviors incidence in organizations: A Meta-analysis
by Fatemeh Gheitarani, Khaled Nawaser, Haniruzila Hanifah, Ali Vafaei-Zadeh
Abstract: Research growth in organizational behavior research, has increased the importance of paying attention to anti-citizenship behaviors. The current research with the aim of quantitative combination, has examined the results of research in effect of underlying factors of organizational anti-citizenship behaviors using meta-analysis method and CMA2 software and 55 articles during the time period of 2000-2020. The results showed a positive significant link between underlying factors of organizational anti-citizenship behaviors and occurrence of these behaviors and this influence was 0.389, 0.338, 0514 and 0.498 (structural, organizational, managerial, employment and professional and socio-economic and cultural factors). The level of connection found relating to each 4 occurrences are 68 links, 49 links, 93 links and 71 links. Findings indicate that minute attention has been paid to organizational anti-citizenship behaviors, especially to job and professional factors in research works. Research should be conducted to control and manage these behaviors more purposefully in organizations.
Keywords: Organizational Behaviors; Anti-citizenship behaviors; Meta-Analysis; Organizational Factor; Personal Factor.
Hybrid of Machine Learning-Based Multiple Criteria Decision Making and Mass Balance Analysis in The New Coconut Agro-industry Product Development
by Siti Wardah, Moh Yani, Taufik Djatna, Marimin Marimin
Abstract: Product innovation has become a crucial part of the sustainability of the coconut agro-industry in Indonesia, covering upstream and downstream sides. To overcome this challenge, it is necessary to create several model stages using a hybrid method that combines machine learning based on multiple criteria decision making and mass balance analysis. The research case study was conducted in Tembilahan District, Riau Province, Indonesia, one of the primary coconut producers in Indonesia. The analysis results showed that potential products for domestic customers included coconut milk, coconut cooking oil, coconut chips, coconut jelly, coconut sugar, and virgin coconut oil. Furthermore, considering the experts, the most potential product to be developed was coconut sugar with a weight of 0.26. Prediction of coconut sugar demand reached 13,996,607 tons/year, requiring coconut sap as a raw material up to 97,976,249.
Keywords: Coconut Agro-industry; hybrid of machine learning; mass balance analysis; multiple criteria.
A Novel approach of psychometric interaction and principal component for analyzing factors affecting e-wallet usage
by Gurpreet Singh Matharou, Simran Kaur
Abstract: The Republic of India has witnessed an enormous leap in financial transactions after a sudden demonetization in 2016. The study represents an in-depth analysis of the factors influencing e-wallets usage post-COVID situation covering the National Capital Region. The scientifically collected data were subjected to Pearsons correlation to recognize the correlation amongst the selected e-wallets. The usage of e-wallets is observed mainly during recharge, UPI payments, and utility payments. Through psychometric response and interaction analysis, six factors were selected and examined for data distribution and stable observation using standard deviation and variance coefficient. The coefficient of variance for six factors was observed ? 1. The weight of the factors noted to be secured way (0.184), to take advantage of cashback (0.182), low risk of theft (0.169), fast service (0.1689), ease to use (0.156), and saves time (0.139) using principal component eigenvectors analysis. Freecharge and Tez wallets reveal a maximum 99.2% correlation.
Keywords: Wallets; Correlation; Payment; P-value; Technology.
Discovering Interesting Relationships in the Factors Relating to the Elderly Living Alone in Thailand Using Association Analysis
by Nichnan Kittiphattanabawon
Abstract: Many countries are facing an aging society situation. The problem of the elderly living alone happens often, even in Thailand. This research aimed to discover the factors that reflect the elderly living alone. Association analysis techniques were employed to unearth all possible factor combinations. The measures, called support and confidence, were utilized to determine the strength of the discovered factors. Association rules have also been mined to reveal the relationship between the factors affecting the elderly living alone. The study sample consisted of 36,574 elderly living alone and was received from the National Statistical Office of Thailand. The study showed that the elderly living alone often do not need a caregiver if they have supportive family members, have public healthcare benefits, earn a living from a social security fund, and have amenities in the house. The primary discovery was that they can carry out a routine without assistance. Furthermore, most importantly, they are in good health.
Keywords: elderly; aloneness; Thailand; association analysis; association rules; interesting relationships.
A Novel SMS Spam Dataset and Bi-directional Transformer based Short-Text Representations for SMS Spam Detection
by Srishti Maheshwari, Shubhangi Aggarwal, Rishabh Kaushal
Abstract: Short Message Service (SMS) is a form of exchanging short messages over mobile phones without the Internet. Unfortunately, the SMS services popularity is exploited to send irrelevant and malicious messages to entrap users into scams and frauds. In this work, we investigate the performance of state-of-the-art Bi-directional encoder representations from transformers for short-text messages in SMS data. For evaluation, we curate a novel augmented SMS spam dataset by extending a classical SMS spam dataset to further categorize spam SMS messages into four fine-grained categories, namely, indecent, malicious, promotional, and updates. We perform experiments on the standard benchmark SMS dataset of spam & non-spam and on our curated multi-class SMS spam dataset. We find that BERT based short-text representations outperform the baseline traditional approach of using handcrafted text-based features by 15-30% for different machine learning algorithms in terms of accuracy on multi-class SMS spam dataset.
Keywords: Spam Classification;Machine Learning;Word Embedding;Representation Learning;.
Multi-Attribute Decision-Making Application Based on Pythagorean Fuzzy Soft Expert Set
by Muhammad Ihsan, Muhammad Saeed, Atiqe Ur Rahman
Abstract: The Pythagorean fuzzy soft expert set (PFSE-set) is a parameterized
family and one of the appropriate extensions of the Pythagorean fuzzy sets. It
is also a generalization of intuitionistic fuzzy soft expert set, used to accurately
assess deficiencies, uncertainties, and anxiety in evaluation. The most important
advantage of over existing sets is that the Pythagorean fuzzy soft expert set is
considered a parametric tool. The PFSE-set can accommodate more uncertainty
comparative to the intuitionistic fuzzy soft expert set, this is the most important
strategy to explain fuzzy information in the decision-making process. The main
objective of the present research is to establish the new structure of PFSE-set
along with its corresponding fundamental properties in a Pythagorean fuzzy soft
expert environment. In this article, we introduce Pythagorean fuzzy soft expert
set and discuss their desirable characteristics (i.e. subset, not set and equal set),
results (i.e. commutative, associative, distributive and De Morgans Laws) and
set-theoretic operations (i.e. complement, union intersection AND, and OR )
are explained. An algorithm is proposed to solve decision-making problem. A
comparative analysis with the advantages,effectiveness,flexibility,and numerous
existing studies demonstrates the effectiveness of this method.
Keywords: Soft Expert Set;Pythagorean Fuzzy Soft Set;Pythagorean Fuzzy Soft Expert Set.
A game theoretic approach on the investment in economic sectors by multiplier analysis: case study of Irans economy
by Atieh Namazi, Mohammad Khodabakhshi, Vahid Reza Salamat
Abstract: There is a debate on how the amount of capital should be invested in economic sectors to achieve the most prosperity in the economy. According to the balanced growth theory, some economists believe that large investment in different economic sectors increases productivity and the production size. However, other economists cling to the belief that limiting investment in key economic sectors results in increasing production. In this article, the game theory approach is utilized by using multiplier analysis and the matrix derived from the input-output table. This method is the middle ground between the balanced and unbalanced growth theories and benefits from them. The results obtained from applying the new approach in the economy of Iran indicate that it is more profitable to invest in different economic sectors; however, the investment should be in accordance with the contribution of the economic sectors in the production process.
Keywords: Game theory; Multi-criteria analysis; Data envelopment analysis; Input-output analysis.
The Importance-Performance Analysis of Lean Human Resource Management Themes
by Mohammad Hossein Azadi, Mohammad Hakkak, Reza Sepahvand, Seyed Najmodin Mousavi
Abstract: Lean management to human resources (HR) talks about a technique that makes different organization departments, particularly the HR management (HRM) which adhere to a set of executive policies and processes. This descriptive research of applied type was conducted on a statistical population including 23 senior managers working at the Social Security Organization (SSO) in Fars Province, Iran, In the qualitative phase of the study, semi-structured interviews were employed to collect the data, whose validity and reliability were endorsed using content validity ratio (CVR) and Cohens kappa coefficient (?), respectively. To analyze the qualitative findings, thematic analysis was also exercised. Upon examining the existing literature and the expert opinions, seven global themes, as well as 27 and 85 organizing and basic themes were respectively identified. In the quantitative phase, a questionnaire was administered to collect the data, Afterwards, the themes obtained were investigated using the importance-performance analysis (IPA).
Keywords: Human Resource Management; Importance-Performance Analysis; Fuzzy Numbers; Lean Human Resources; Thematic Analysisrn.
Social media and decision making: A data science lifecycle for opinion mining of public reactions to the 2020 international booker prize in twitter
by Zhe Chyuan Yeap, Pantea Keikhosrokiani, Moussa Pourya Asl
Abstract: The emergence of social media platforms has altered patterns of interaction between individuals and decision-makers. To explore the impact of such changes, this study conducts an opinion mining of public reactions in Twitter to the 2020 International Booker Prize shortlist. Over 13,000 tweets were collected and analysed to examine whether publics emotions and responses to a list of nominees are akin to or influence the judges decisions about the winning novelist. A data science lifecycle for Sentiment Analysis and Topic Modelling is proposed to classify tweet sentiments and identify the dominant topics in relation to the six shortlisted literary works both before and after the announcement of the winner. The findings show a marked discrepancy between readers preference and the judges decision as the prize was granted to one of the least heeded nominees. This difference reinforces the suspicion that the literary prizes are filtered through judges personal views. The proposed digital model in this study can assist critics, book club judges, literary prize-givers, and publishing industries in better decision making.
Keywords: Decision Making; Opinion Mining; Natural Language Processing; Sentiment Analysis; Topic Modelling; International Booker Prize.
Estimating regulatory governance gaps for adoption of augmented reality in automobile sector: the application of analytical hierarchy approach
by BRAJESH MISHRA, Fateh Bahadur Singh
Abstract: This study aims to estimate regulatory gaps that AR applications may encounter in the automobile sector. The theoretical framework of this study is inspired by regulatory commons dynamics approach. The document analysis and thematic analysis of semi-structure interview transcript helped propose an estimation framework of regulatory gaps in the context of AR adoption in Indian automobile sector. Next, the importance of various regulatory gaps domains and sub-domains have been assessed using fuzzy analytical hierarchy process technique. The automobile market regulatory gaps emerged as the most important regulatory gap domains, while the violation liability, market distortion, smart road infrastructure, customer interest, and safety have been globally ranked as the top five important regulatory gap sub-domains. Policymakers and regulators face a big challenge to match market dynamics created by rapidly advancing technologies. Market regulatory gaps and technical regulatory gaps need to be addressed separately for clarity and focus.
Keywords: Multiple criteria analysis; regulatory gaps; augmented reality; Indian automobile sector; fuzzy AHP; smart road infrastructure.
A Novel Hybrid Meta-heuristic-enabled Ensemble Learning Model with Deep Feature Extraction for Crop Yield Prediction with Heuristic Ensemble Yield
by S. Vijaya Bharathi, Manikandan A
Abstract: The fundamental goal of this study is to build and use heuristic-based ensemble learning for improved agricultural production prediction. The Squirrel Tunicate Swarm Algorithm (STSA), a hybrid Squirrel Search Algorithm (SSA) and Tunicate Swarm Algorithm (TSA), extracts deep features using the Optimized Convolutional Neural Network (O-CNN). The datasets for agricultural production prediction are obtained from public sources, and deep features are extracted using an Optimized Convolutional Neural Network (O-CNN). Following that, the optimum deep features are exposed to Heuristic-based Ensemble learning using three distinct classifiers: Linear Regression (LR), Support Vector Regression (SVR), and Long-Short-Term-Memory Regression (LSTM). The suggested STSA is utilized to calibrate the ensemble learning's three classifiers. When comparing the predicted performance of the developed model to that of other procedures, the proposed Heuristic ensemble yield framework beats previous techniques.
Keywords: Novel Crop Yield Prediction; Deep Feature Extraction; Optimized Convolutional Neural Network; Heuristic-based Ensemble Learning; Squirrel Tunicate Swarm Algorithm.
MVRO-based DRNN: Multi-Verse Rider Optimization-based Deep Recurrent Neural Network for intrusion detection in Latency constrained Cyber physical systems
by Arvind Kamble, Virendra S. Malemath
Abstract: The cyber attacks on cyber physical system leads to actuation and sensing behaviour, safety risks, and rigorous damages to the physical object. Therefore, in this paper, Multi-Verse Rider Optimization (MVRO)-based Deep Recurrent Neural Network (DRNN) is devised for identifying intrusions in latency-constrained cyber physical systems. In the latency-constrained cyber physical system, the process is carried out using three layers, end point layer, cloud layer, and fog layer. Here, the feature extraction process is performed using the Water Wave-based Improved Rider Optimization Algorithm (WWIROA) for the classification process. The MVRO approach is the combination of the Rider Optimization Algorithm (ROA), and Multi-Verse Optimizer (MVO). The DRNN classifier is utilized for the intrusion detection process. In addition, the DRNN classifier is trained using the introduced MVRO technique for better performance. Furthermore, the MVRO-based DRNN technique achieves low latency of 19.23s, high specificity, sensitivity, and accuracy of 0.929, 0.974, and 0.956, respectively.
Keywords: Intrusion detection; Cyber physical system; cloud layer; Deep Recurrent Neural Network; Multi-Verse Optimizer; Rider Optimization Algorithm.
RiCSO-based RiDeep LSTM: Rider Competitive Swarm Optimizer enabled Rider Deep LSTM for air quality prediction
by Deepika Dadasaheb Patil, Thanuja T C, Bhuvaneshwari C. Melinamath
Abstract: This paper is for air quality prediction. Here, the time-series data is considered for
the effective prediction of air quality. Moreover, missing value imputation is applied in this model to perform pre-processing. The technical indicators are extracted as features for the effectual prediction of air quality. The Rider Deep Long Short-Term Memory (LSTM) is also
included for predicting air quality, trained by a developed RCSO algorithm. Moreover, the
developed Rider competitive swarm optimization (RCSO) approach is newly devised by
incorporating Rider Optimization Algorithm (ROA) and Competitive Swarm optimizer
(CSO). The performance of the developed air quality prediction model is evaluated using
several error metrics. The introduced air quality prediction system obtained a minimum Mean
Square Error (MSE) of 0.10, a Root Mean Square Error (RMSE) of 0.31, a Mean absolute
Percentage Error (MAPE) of 8.34%, and Mean absolute Scaled Error (MASE) of 0.30. The
results demonstrated that the developed RCSO-based Rider Deep LSTM model attained
better performance than other techniques.
Keywords: Air quality prediction; Competitive Swarm Optimizer; Rider Optimization Algorithm; Rider deep LSTM; Triple Exponential Moving Average.rnrn.
A survey on various Alzheimer classification techniques using 3D MRI images: A challenging overview
by NEETHU M., ROOPA JAYASINGH J
Abstract: This survey presents 50 research papers focussed on various techniques in Alzheimer classification techniques using 3D MRI images, and the categorization of the techniques is made based on the fusion-based, Convolutional Neural Network (CNN)-based, Random forest (RF)-based and Support vector Machine (SVM)-based approaches. Finally, the analysis is to be promoted in the survey based on the research technique, publication year, employed tools, utilized dataset, performance measures and achievement of the research methodologies towards Alzheimer classification techniques using 3D MRI images. At the end, the research gaps and issues of the techniques for Alzheimer classification techniques using 3D MRI images is to be revealed.
Keywords: Alzheimer classification; Convolutional Neural Network; Random forest; Support vector Machine; Fusion.
A Consumer Behavior Assessment using Dimension Reduction and Deep Learning Classification
by Pragya Pandey, Kailash Chandra Bandhu
Abstract: Consumer behavior assessment is extremely important for online communities to finding out mindset of customer and change their views about specific products and services. Customers share their experiences with particular goods, and services on channels and social media, empowered by artificial intelligence for consumer knowledge sharing and acquire new information. In this proposed work, a deep learning model has been developed for statistical tests, statistical analysis using correlation and association testing are performed. The ordinary dimension reduction with principal component analysis and module eigenvalues, followed by a second normalization phase that maximizes the coefficient's size using possible values. The keras library was used on the third layer of the deep learning classification hierarchy with the rectified linear unit and sigmoid activation functions. The average F1 score was 98 % accurate and according to the statistics, the proposed strategy had an accuracy of 84% and a recall of 100%.
Keywords: Consumer Behavior; Artificial Intelligence; Consumer Knowledge-Sharing; Principal Component Analysis; Deep Learning Classification.
The Influence of Information Sources on Process and Content Confidence when Making Ill-structured Managerial Decisions
by David McLain, Jinpei Wu
Abstract: Although information is an important influence on decision confidence, disparate views exist about that influence. Engineering-derived psychological theory associates information non-negatively with confidence whereas the overconfidence literature suggests information has a non-positive influence on confidence. Previous research, however, has used information sources lacking ecological validity and almost exclusively studied well-structured decisions and single facets of confidence. Drawing on research and practice in management, decision making, and the neurosciences, the influences of technology-sourced (web) information and performance feedback information were studied as influences on confidence when making ill-structured decisions. Clear distinctions were made between judgment leading up to a decision, called process confidence, and evaluation of the final decision, called content confidence. Process-integrated web use only weakly increased either confidence while feedback significantly reduced content confidence and left process confidence little changed. This effect was amplified when the feedback clarified others decision expectations. Within subjects, the relationship between quantified feedback and confidence, especially process confidence, was positive and increased with each decision. These findings suggest that an information resource when making ill-structured decisions has little effect on confidence but that credible, post-decision performance information can affect content confidence while process confidence remains resilient.
Keywords: confidence; information; decision-making; ambiguity; ill-structured decisions; meta-cognition; feedback; web; Internet.
SALES ORDER BOOKING PROCESS LEAD TIME REDUCTION BY DEPLOYMENT OF THE LEAN PRINCIPLE
by Rohit Kenge
Abstract: Changing environmental conditions, government imbalances, and COVID 19 disease are resulting in the more product delivery time. We studied the current sales order booking process in the literature survey, found some gaps, and proposed a hypothesis to reduce the lead time of the sales order booking process. We executed a survey of buyers and salespersons with a set of 39 questionnaires for the period of December 2020 to March 2021 on a convenience sampling basis for the 500 samples by circulating the Google form. 479 responses are received and we considered 402 valid responses after rejecting 77 wrongly ?lled answers. Hence, we got 80.33% correct responses. We performed the analysis of survey response data by testing the reliability, validity, correlation matrix, and structural equation modelling and concluded that our proposed model is the best fit and improved the overall lead time for the sales order booking process.
Keywords: Sales management; Lean; Lead time reduction; Sales Operation excellence; and Sales order booking process.
A Comparison of Statistical and Machine Learning Models for Stock Price Prediction
by Saurab Iyer, Vraj Patel, Joy Mehta, Jai Prakash Verma, Ankit Sharma
Abstract: A huge proportion of money around the world is held by the stock markets. It is one of the most pivotal aspects of the financial institutions and experts. Predicting the movements of stock markets can improve decision making for traders. In this paper, data science techniques are employed to predict the
Keywords: deep learning; machine learning; stock price prediction; statistical modelling.
Special Issue on: ICALT 2020 Decision Analytics for Logistics and Supply Chain Management New Perspectives
An Improved Hybrid Genetic Algorithm to solve the multi-vehicle covering tour problem with restriction on the number of vertices
by Manel Kammoun
Abstract: In this paper, we address the multi-vehicle covering tour problem (m-
CTP) that is a generalization of the well know vehicle routing problem (VRP)
in which we dont need to visit all customers. The objective of the m-CTP is
to minimize the total routing cost and fulfill the demand of all customers such
that each customer which is not included in any route must be covered. In this
work, we deal with a particular case of the m-CTP where we consider only
the restriction on the number of vertices in each route and the constraint on
the length of the route was relaxed. This special case of the problem called m-
CTP-p where each covered vertex must be within a given distance of at least a
visited vertex and the number of vertices on a route does not exceed a predefined
number p. We propose two approaches to solve this variant. First, we develop a
Genetic Algorithm (GA) using an iterative improvement mechanism. Then, an
effective Hybrid Genetic Algorithm (HGA) is developed in addition to a local
search heuristic based on Variable Neighborhood Descent method to improve the
solution. Extensive computational results based on benchmark instances on the
m-CTP-p problem show the performance of our methods.
Keywords: Covering; Genetic Algorithm; Variable Neighborhood Descent ;Hybrid approach.
Hybrid Multi Agent Framework for Green Supply Chain Management
by Mohamed Dif El Idrissi, Abdelkabir Charkaoui, Abdelouahed Echchatbi
Abstract: Environmental customer collaboration has recently attracted a big attention from researchers and industrial professionals. Many studies show that companies may reach high performance level by considering customer collaboration and environmental regulations. However, literature in the Green Supply Chain Management (GSCM) suggests having more structured collaboration and information exchange processes between Supply Chain partners based on new technologies. For this reason, this work proposes a hybrid solution based on Multi agent systems (MAS) and Mixed integer linear programming (MILP) to automate and facilitate the environmental customer collaboration process. The study demonstrates how MAS can be used in the GSCM context to improve communication and reduce complexity. An industrial study case in the automotive spare parts sector is used to demonstrate the applicability of the established MAS model.
Keywords: green supply chain management; multi agent systems; supply chain management; customer collaboration; environmental regulation.