International Journal of Information and Decision Sciences (35 papers in press)
Enhancing the performance of sentiment analysis task on product reviews by handling both local and global context
by Bagus Setya Rintyarna, Riyanarto Sarno, Chastine Fatichah
Abstract: Commonly, product review analysis includes extracting sentiment from product documents. The contextual aspect contained in a review document has potential to improve results obtained by the sentiment analysis task of product reviews. In this regard, this paper proposes an approach that takes into account both local and global context. The main contribution of this work is threefold. Firstly, local context is defined and the graph-based Word Sense Disambiguation (WSD) method is extended to deal with this contextual issue. The method is aimed at assigning the correct sense of a word in the context of a sentence, which means choosing the correct sentiment value of a word with respect to the context. Secondly, global context is defined for addressing contextual issues related to the specific domain of a review document, which can affect the sentiment value of the words contained in it. To address the global context issue, an improved SentiCircle-based method is used and a similarity-based technique is provided to select the pivot word. This method can be employed to assign sentiment value at sentence level. Thirdly, a weighted mean-based strategy to determine sentiment value at document level is presented. Several experiments were conducted to assess the proposed method and compare it with a baseline method. Overall, the proposed method outperformed the baseline method in almost all performance evaluation measures (precision, recall, F-measure and accuracy).
Keywords: sentiment analysis; local context; global context; word sense disambiguation; SentiCircle.
A new approach agent-based for distributing association rules by business to improve decision process in ERP systems
by Merouane Zoubeidi, Okba Kazar, Saber Benharzallah, Nadjib Mesbahi, Abdelhak Merizig, Djamil Rezki
Abstract: In the last decade, the distributed computing plays an important role in the Data Mining process, it helps to make systems scalable and it is important to develop mechanisms that distribute the workload among several sites in a flexible way also the acronym ERP stands for enterprise resource planning. It refers to the systems and software packages used by organizations to manage day-by-day business activities, ERP systems are designed for the defined data structure (schema) that usually has a common database. In addition, Data Mining is a technology that purposes to promote information and knowledge extraction from a large database. In this paper, we present a collaborative multi-agent based system for association rules mining from distributed databases. In our proposed approach
Keywords: Enterprise Resource Planning (ERP); Multi-Agents system (MAS); Data Mining associate rules; JADE; WEKA.
A rule-based approach for dynamic Analytic Hierarchy Process decision making
by Yun-ning Liu, Shiow-yang Wu
Abstract: The Analytic Hierarchy Process (AHP) is widely used in many multi-criteria decision-making problems and has been successfully applied to many practical cases. However, the AHP process is time-consuming and the decision model is not agile enough for fast changing environment. To overcome this weakness, we develop a rule-based approach for dynamic AHP decision-making in changing environment. We analyze critical factors in the AHP decision process under uncertainty and propose to encode expert knowledge for change handling using Event-Condition-Action rules. We propose a theorem and associated method to determine the change in ordering of decision alternatives based on Event-Condition-Action rule-induced weight updates. We demonstrate the effectiveness of our approach using a case study of the supplier selection decision making task of the steel and iron industry in Taiwan. The study shows that our mechanism can effectively reach the same level of decision quality as expert decision maker(s).
Keywords: Dynamic rule-based AHP; Two Criteria Update Impact Analysis; Steel and Iron Industry; Comparison Matrix.
Quality of Service based Service Selection in Smart Parking
by Shiksha Singh, Rohit Kumar Tiwari
Abstract: Smartness in the existing environment is required for overall growth of any country. Government is putting tremendous effort and a huge sum of money for making cities smart to achieve smartness. A very first asset that needs to be made smart is smart parking system to avoid the traffic congestion. There are many service providers which are offering smart parking services, but there is no Quality of Service (QoS) framework available so far. So, for a customer point of view it is very hard to select the best service provider and gain maximum satisfaction. So, in this paper, we have designed a QoS framework which consists of thirty-three metrics to evaluate a smart parking service. These parameters are identified from the user as well as vendors perspective and helps to select better service provider. We have also proposed multi criteria decision making (MCDM) approach TOPSIS to select best smart parking service provider based on identified QoS. We have demonstrated our approach with the help of case studies.
Keywords: Quality of Services; Smart City; Smart Parking System; Internet of Things; MCDM; TOPSIS.
A new framework using biform game for cost optimization of distribution networks
by Salma MOUATASSIM, Ahmed Haroun SABRY, Mustapha AHLAQQACH, Jamal BENHRA
Abstract: The present work focuses on the demand decision making problem for regional distribution centers sharing the same product families. Each center orders quantities to be distributed from production units. Our approach suggests a biform game to maximize the benefits of each center and minimize the end of cycle market induced supply to demand deviations. We start by an independent demand forecasting under uncertainty. Once the demand is met, the centers enter a collaboration phase where coalitions are created and products are exchanged, in order to achieve the core stability of the actual game. If not met, we try to achieve the same objectives using individual rationality through an adapted approach based on Shapley value analysis for each possible coalition.
Keywords: game theory; forecasting; Shapley value; collaboration; biform game; cost allocation; coalitions; core stability.
Determining Optimal Replanting Rate in Palm Oil Industry, Malaysia: A System Dynamics Approach Optimal Policy Search in Oil Palm Plantation Feedback Loops using System Dynamics Optimization
by Mohd Zabid M Faeid, Norhaslinda Zainal Abidin, Shri Dewi Applanaidu
Abstract: One of the important factor that contribute to the stagnant growth of Malaysias crude palm oil production is the accumulation of ageing oil palm plantation area. Given the scarcity of new plantation area in Malaysia, it is very important that an optimal replanting rate has to be determined to decrease the accumulation of ageing area. The mature area of oil palm plantation has to be increased in order to obtain higher crude palm oil production. The main aim of this study is to determine an optimal replanting rate for oil palm industry in Malaysia.. This study compared the trend results of fresh fruit bunches yield using baserun system dynamics and system dynamics with optimization analysis.The findings indicate that the proposed optimal replanting rate based on system dynamics analysis revealed the maximum production in term of the fresh fruit bunch yield by year 2050 compared to baserun scenario analysis. Specifically, findings from optimization analysis recommended the replanting rate at 278,189 hectare annually. This practise will ensure the continuous supply of palm oil withoit significant distruption if high replanting rate has been implemented.. Findings from this study will be useful to the policy makers in palm oil industry and palm oil planters in assisting them to plan the appropriate planting strategy to maximize fresh fruit bunches yield.
Keywords: Fresh fruit bunches yield; Oil palm plantation; Optimal replanting rate; System dynamics optimization.
A SWITCHING HYBRID MOBILE RECOMMENDER SYSTEM FOR TOURISTS
by Bolanle Ojokoh, Idorenyin Amaunam
Abstract: Recommender systems are meant to give recommendations by receiving and analyzing feedbacks from users. These feedbacks could be obtained through ratings or likes. Nevertheless, a problem arises when there are no feedbacks. This can happen because: the system offering the recommendations is new (and has obtained no ratings), the user is new (and has not rated the system), or the items for recommendations are new (and have not been rated). This problem is termed the cold-start problem. Also, most recommender systems do not offer preferred recommendations to users. They rely mostly on the ratings of other users to give recommendations to the active user. These in most cases may not be the users choice. This paper thus, proposes a switching feature-based model that leverages the need of both new and existing users for recommendation of tourist locations. Recommendations to new users are implemented with Bayesian algorithm on supplied demographic data. For existing users, the system switches to the collaborative filtering subsystem, where the user inputs the location facility he/she wants. The user also has the privilege of changing location type. Recommendation results are produced through the appropriate algorithm and offered based on the items in the database. The model was validated with discounted cumulative gain, precision, and recall. A comparative analysis with some existing systems showed lower mean absolute error. Also, experimental results obtained through questionnaire distributed to general users, users from the computer science domain as well as experts in the tourism, showed the effectiveness of the proposed techniques.
Keywords: Bayesian algorithm; Conditional Probability Table (CPT); Cold-start; Mobile app; Recommender system.
Impact of Farmers Ownership of Seeds on Well-being of Farmers: Study of a Village in Odisha
by Sukanta Chandra Swain
Abstract: In order to achieve food security in the country, the government of India has introduced an initiative of new green revolution called as Bringing Green Revolution to Eastern India since 2010-11. After Indias green revolution in 1960s, the use of seed bio-technologies in agriculture, in which the ownership of seeds lies with organized private parties, have been in question. But prior to that, Indian farmers were going by using their harvested corps as seeds in future. The situation in eastern India, particularly in Odisha, was far behind as compared to the scenario at national level. Use of high yielding varieties (HYVs) seeds in Odisha agriculture came up at a very later stage although accessibility was not a problem. It was mostly due to ignorance and lack of acceptability of the HYV seeds. As time passed and the state entered into the phase of new green revolution, farmers in frontline got acclimatized to the seed bio-technology and succeeded in getting handful of harvests year after year. Small and Marginal farmers had also to follow the foot-print of the frontline farmers for two reasons; a) seeing the prosperity of the latter, the former got motivated to follow suit and b) good harvest with HYVs seeds by frontline farmers, leading to reduced average cost, drove the traditional seeds users away from the market on pricing ground. At present, while most of the farmers in Odisha are using seed bio-technology for more harvests, it is pertinent to unfold whether it has affected the well-being of the small farmers in rural Odisha. Keeping this in backdrop, this paper highlights the impact of ownership of seeds on small farmers well-being. For the purpose, a village called Kasarda of Odisha state (India) has been considered and the responses of 75 small farmers have been ascertained and analyzed.
Keywords: Seed Ownership; Seed Bio-technology; Small Farmers; Well-being; Kasarda; Odisha.
The Effect of Social Capital on the Effectiveness of Community Development Programmes in Malaysia
by Amir Imran Zainoddin, Azlan Amran, Mohd Rizaimy Shaharudin
Abstract: This study aims to determine the influence of social capital on the effectiveness of the farmers development programme established by a MNC in Malaysia for business - community relations as part of the companys CSR endeavours. The sampling technique employed in this study was census sampling with all of the 400 respondents being included in the study. The results unveiled that the relational and cognitive dimensions were positively and significantly related to the effectiveness of the community development programme. Nevertheless, the structural dimension failed to follow similar inclinations. The finding has contributed to the social capital theory by supporting the relational and cognitive dimensions as the factors that influence the success of the community development programmes. Future study is suggested to measure the effectiveness of community development programmes using financial or non-financial aspects, utilise the stakeholder theory perspectives, as well as validate the inconsistencies in the outcomes of the past studies.
Keywords: Corporate Social Responsibility; Social Capital; Effectiveness; Community Development Programmes; Farmers.
Impact of Knowledge Flows on Supply Chain Performance: An Experiment on Four Indian Luggage Manufacturing Firms
by Vishal Bhosale, Ravi Kant, Ravi Kant, Mark Goh, Mark Goh
Abstract: This paper seeks to investigate the role and impact of Supply Chain Knowledge Flow Enablers (SCKFEs) in improving the supply chain performance of four luggage manufacturing firms. The paper applies fuzzy Analytic Hierarchy Process (AHP) to obtain the weights of the SCKFEs, and fuzzy Multi-Objective Optimization by the Ratio Analysis (MOORA) to rank the firms practicing knowledge flows. A case study of four Indian luggage manufacturers suggests that the better the implementation of the SCKFEs, the better the knowledge flows and hence better supply chain performance. This study reveals how firms practicing knowledge flows influence their supply chain performance.
Keywords: Knowledge flow; Supply chain performance; MCDM; AHP; MOORA.
Decision Tree Classifier: A Detailed Survey
Abstract: Decision Tree Classifier (DTC) is one of the well-known and important methods for data classification. The most significant features of decision tree classifier(DTC) is its ability to change the complicated decision making problems into a simple decision making processes, thus finding a solution which is understandable and easier to interpret. DTCs can be used in many disciplines such as remote sensing, Character Recognition, Medical Diagnosis, Expert Systems, Speech Recognition, and Radar Signal Classification etc. This Paper provides a brief but self-explanatory review on various algorithms developed in literature for constructing and representing decision trees, different splitting criteria for selecting best attribute and various pruning methods. In addition to these, some enhancements made in DTCs time to time are also discussed which would be beneficial for beginners. After reading this paper, the readers will be able to understand why decision trees are more popular among all other methods of classification, what are their uses, limitations and applications in different diverse areas. They will also come to know about many decision tree induction algorithms like ID3, CART, C4.5, SPRINT, BOAT, SLIQ, their uses and variants, different splitting criteria and various pruning methods, concepts of ensemble methods, fuzzy decision trees and hybridization of decision trees with other classification methods or meta-heuristics. Therefore, one can conclude that inclusion of these concepts in decision trees provide ample opportunities to solve complex datasets with less computation in very short time period while achieving high accuracy.
Keywords: Decision Tree Hybridization; Classification; ID3; CART; ensembles; splitting criteria; pruning methods.
Context Vector Convergence (CVC) of Computational Behavior and Cultural Traits for Team Selection
by Hrishikesh Kulkarni, Manisha Marathe
Abstract: Selection of Team for match, mission or project is always challenging since every mission is different, every match brings new uncertainties and every project has its own complexities. Your best resource may not be the right choice for given task. It is the context of task, behaviors of individuals and above all constitution of the team in that scenario contribute to outcome. The proposed technique is based on convergence of multiple context vectors representing computational behaviors. Learning based on these vectors helps us to select the optimal combination. The Context Vector Convergence (CVC) of Behavioral Vectors helps in deriving the actual effect of two vectors in overall team performance. The personality vector is used to derive behavioral context while mission vector is used to derive the scenario context. These two vectors are graphically associated in convergence to identify and recommend the best team combinations. The multiple combinations are ranked with reference to scenario to select the most appropriate one. While formulating the vector cultural aspects and behaviors are captured through expressions and interactions. Top three combinations are compared to validate hypotheses. The promising results reinforce the premise to establish further research directions.
Keywords: Behavioral Psychology; Machine Learning; Artificial Intelligence; Cognitive Sciences; Computational Psychology; Context; Cultural Computing.
Strategic Decision Making to maximize the efficiency of water usage in Steel Manufacturing Process via Analytic Hierarchy Process (AHP) and Bayesian Belief Networks (BBN): A Case Study.
by Jose Pereira, Geane Fayer
Abstract: This study proposes a method for strategic decision making, considering the identification and prioritization of the potential risks that could stop production in the steel production processes in a water crisis scenario. This method combines AHP and BBN to assess risks arising from the water crisis scenario in steel manufacturing industries. The objective is to guarantee the availability of water resources necessary to ensure a safe operation. As a methodological approach experts and professionals from a group of steel manufacturing companies were interviewed do identify risk factors considering a water crisis scenario and the risk probabilities were elicited accordingly. AHP and BBN were combined to obtain the global risk matrix and prioritization of risks. Even though water is a natural resource renewed by physical processes of hydrological cycle, its scarcity is making it no longer a free, abundant and available to all. Water is recognized worldwide as a limited resource to which particular attention should be given. In terms of impact, the World Economic Forum held in 2017 ranked the so-called Water Crisis risk in third place, second only to weapons of mass destruction and climate change. No previous work dealing with risk analysis to prioritize risks arising from the water crisis scenario in steel manufacturing processes could be found. As a result of this study, a global risk matrix is proposed. It shows the risks that could stop production processes and are considered intolerable. The result completes a gap in the literature and provides a source of information and a method to be used by professionals, engineers and decision makers in the identification of risk factors that could impact the operation of steel manufacturing companies.
Keywords: Risk Analysis; Water shortage; AHP; BBN; Steel Industry.
Hierarchical Two-pathway Autoencoders Neural Networks for Skyline Context Conceptualization
by Ameni Sassi, Wael Ouarda, Chokri Ben Amar, Serge Miguet
Abstract: In this paper, we proposed a novel hierarchical two-pathway autoencoders architecture to transform a local information based on skyline scene representation, into non-linear space. The first pathway is intended for the transformation of the geometric features extracted from the horizon line. The second pathway is applied after the first one to joint the color information under the skyline to the transformed geometric features, and to get the landscape context conceptualization. To evaluate our suggested system, we constructed the SKYLINEScene database containing 2000 images of rural and urban landscapes, with a high degree of diversity. In order to investigate the performance of our HTANN-Skyline, many experiments were carried out using this new database. Our approach shows its robustness in Skyline context conceptualization and enhances the classification rates by 1% compared to the AlexNet architecture; and by more than 10% compared to the hand-crafted approaches based on global and local features.
Keywords: Deep Neural Network; Autoencoder; Scene Categorization; Skyline; Curvature Scale Space; Features Transformation; Classification; horizon line.
Family members as an External Source of Travel information
by Zahra Shekarchizade, Bahram Ranjbarian, Vahid Ghasemi
Abstract: The aim of this work is to investigate the effect of family structure, duration of family life and family members acquaintance with travel destination on information search behavior of heads of families to buy a package tour. A sample of 70 Isfahani heads of families who had bought an outbound package tour in January-September 2017 was selected by employing the Convenient Sampling method. A questionnaire was used in order to collect data. The results indicate that family structure and duration of family life have important impacts on the perceived value of seeking information among family members. In other words, in families that have different value structures and in various stages of family life cycle, the perceived value of seeking information among family members is different; however, perceived value of seeking information among family members was not significantly effective in the level of seeking information among family members. As a matter of fact, family members acquaintance with travel destination has a significant impact on the level of seeking information among family members by using perceived value of seeking information among family members. While family members are acquainted with the travel destination, seeking information from inside the family is of great value. In this way, the desire for seeking information among family members will be increased.
Keywords: Family Members; External Source of Information; Travel Information; Familiarity; Family Structure; Duration of Family Life; Information Search Behavior; Perceived Value; Familial Factors; Iran.
CREDIT CARDS IN A DEVELOPING ECONOMY: A DATA MINING APPROACH
by Ankit Mehrotra, Reeti Agarwal
Abstract: Usage of credit cards has been witnessing an increase in recent years in India. The study was undertaken to comprehend the effect of the different demographic characteristics of the respondents on credit cards owned by them. Findings indicate that friends/family members are most influential in affecting customers knowledge of credit card. It was seen that for pitching more than one credit card, the group of customers that should be targeted are those with low income and in the age group 46-60 years.
Keywords: C&RT; credit cards; Data mining; demographic variables; feature selection; gender; income; Indian customers; influencing medium; target group.
Query optimization in real-time spatial Big Data
by Sana Hamdi
Abstract: Nowadays, real-time spatial applications have become more and more\r\nimportant. Such applications result dynamic environments where data as well as queries are continuously moving. As a result, there is a tremendous amount of real-time spatial data generated every day. The growth of the data volume seems to outspeed the advance of databases and data warehouses, especially that users expect to receive the results of each query within a short time period without holding into account the load of the system. To solve this problem, several optimization techniques are used. Thus, we propose, as a ﬁrst contribution, a novel data partitioning approach for real-time spatial Big data named VPA-RTSBD (Vertical Partitioning Approach for Real-Time Spatial Big data). This contribution is an implementation of the Matching algorithm for traditional vertical partitioning. Then, as a second contribution, we propose a new frequent itemset mining approach which relaxes the notion of window size and proposes a new algorithm named PrePost*-RTSBD. Thereafter, a simulation study is shown to prove that our contributions can achieve a signiﬁcant performance improvement.
Keywords: Real-Time spatial Data; Transaction; Stream data; Feedback Control\r\nScheduling; Quality of Service; Data partitioning; Frequent itemset mining;\r\nSimulation.
The Application of Strategic Alignment in a Fuzzy Environment: A Case Study in Banking
by Ayfer Basar
Abstract: As a natural consequence of rapid changes and high competition, companies have to determine right business and information technology (IT) strategies consistently to accomplish business value and IT flexibility. They also need to align their strategies and develop an appropriate roadmap in todays competitive environment. The lack of strategic alignment induces many problems in terms of profitability, efficiency, quality, and performance. In fact, there are many studies about strategic alignment in the literature. However, there is not an accepted method to align business and IT strategies and establish a suitable roadmap based on these strategies especially in the fuzzy environment. This study presents a new methodology to meet banks strategic alignment problem which can be defined by hierarchically and solved in a top-down structure. For this aim, a method of aligning first business and IT strategies; then IT strategies and domains is proposed depending on the customer expectations and technological improvements. Expert judgments are collected in pairwise comparison with Hesitant Fuzzy Linguistic Term Sets (HFLTS) for aligning and relatively weighting strategies and service domains. The importance weights obtained by HFLTS are also used to find the most appropriate investment rate for each service area. Proposed methodology is applied in a technology company of a big Turkish national bank to take investment decisions. The results are approved by experts working as strategic managers in banks and technology companies.
Keywords: Strategic alignment; banking; information technology; pairwise comparison; HFLTS.
Unorganized Entrepreneurship and Employment Generation in India
by Dhyanadipta Panda
Abstract: Considering Indias population growth and paucity of job opportunities, entrepreneurship is the only key to come out of the juncture of unemployment. Entrepreneurship may be in the organized or unorganized form. So far as engagement of workforce is concerned, unorganized sector in India outweighs the organized sector. But the unorganized sector fails to win the confidence of the stakeholders owing to its unsystematic approach and unavailability of regulatory framework. Due to this the stakeholders of this sector dont boast about their affiliation. This paper unfolds how unorganized sector in India easily accommodate heavy workforce but with many gray areas. Case study method and in-depth interview method are followed to highlight the problem and focus group discussion is conducted to design a framework for win-win situation.
Keywords: Unorganized sector; entrepreneur; self-employment; contribution; challenges.
SWARA Approach for Ranking of Agricultural Supply Chain Risks of Odisha in India
by Debesh Mishra, Suchismita Satapathy
Abstract: Disruptions in supply chain process could have negative effects on firms performance and if the highly influential risks factors involved in disruptions of the supply chain are ranked and mitigated properly based on their importance, then those disruptions could be well managed. In order to assist the decision makers and other managers to take appropriate decision, this study provides the ranking of the risks in agricultural supply chain of Odisha in India using the SWARA (Step-wise Weight Assessment Ratio Analysis) method based on the four main categories in agricultural sector such as crops, livestock, fishing and forestry & logging. In addition to the above, this study also ranks the risks based on agricultural supply chain related risk considering the important risk variables involved in the supply chain.
Keywords: Agricultural sector; Supply chain; Risks; Ranking; SWARA; Odisha.
Comparative Study of MCDM Methods under Different Levels of Uncertainty
by Akshay Hinduja, Manju Pandey
Abstract: Often, data in MCDM problems are imprecise and changeable due to the mandatory participation of human judgment, which is often unclear and vague. Hence the selection of an appropriate MCDM method is crucial to the optimal decision making. All the MCDM methods are heavily affected by individual or group preferences and therefore even a small change in the data can cause rank-reversal. With the regular proliferation of such methods and their modifications, it is important to carry out a comparative study that provides comprehensive insight into their performances under uncertain conditions. In this paper, we use the Monte Carlo simulation approach to empirically compare the results of five well-known and widely applied MCDM methods, WSM, WPM, TOPSIS, GRA, and MULTIMOORA under different levels of uncertainty. The findings of this paper will assist decision makers in the selection of most robust and reliable MCDM methods for different decision scenarios. The results of this research are significant additions to the current repository of knowledge in the Multi-Criteria Decision Analysis as well as the literature pertaining to the Information Systems. It also provides insights for many managerial applications of these MCDM methods.
Keywords: Multi-Criteria Decision Making; Comparative analysis of MCDM Methods; Monte-Carlo Simulation; Uncertainty.
Integrating Statistical Correlation with Discrete Multi-Criteria Decision Making
by Malik Haddad, David Sanders, Giles Tewkesbury, Nils Bausch
Abstract: This paper analyses two hypotheses that considers a correlation between the number of alternatives and the number of criteria considered in a Multiple Criteria Decision Making (MCDM) problem with the minimum percentage change required in the lowest criterion weight to change the outcome of a method. Two MCDM methods are considered, The Analytical Hierarchy Process (AHP) and The Preference Ranking Organization METHod for Enrichment of Evaluations II (PROMETHEE II) were applied to the same sets of criteria weights and performance measures. More than two thousand randomly generated sets of criteria weights and performance measures are considered. The minimum percentage change in the lowest criterion weight required to change the outcome of a method is calculated. Pearsons r parametric test is used to test the hypotheses. Results from parametric test were statistically significant and shows a weak negative correlation for hypothesis one and weak positive correlation for hypothesis two.
Keywords: Multiple Criteria Decision Making; AHP; PROMETHEE II; Correlation; Criteria; Pearson’s r parametric test.
Performance Evaluation in a Two-stage Network-DEA with Intermediate Products
by Hoda Golshani, Mohammad Khoveyni, Hadi Bagherzadeh Valami, Robabeh Eslami
Abstract: A main difference between conventional data envelopment analysis (DEA) and network DEA (NDEA) is considering the internal structure of a decision making unit (DMU). The existing NDEA methodologies neglect to address the issue of incorporating the influenced of intermediate directly in objective function. To overcome this shortcoming, we are setting an NSBM model for evaluating the overall efficiency score by using two steps in a generic two-stage structure. Hence, we solve an additive model for finding the amount of optimal value of intermediate measures, firstly. Then, our modified NSBM model have incorporated optimal value of objective function is introduced. So, our sole contribution will be introducing a model for finding overall efficiency and calculating unique value for stage efficiencies, input, intermediate and output oriented efficiency that is an important issue in network research area. Finally, an empirical example is provided for verifying our proposed approach.
Keywords: Data envelopment analysis (DEA); Intermediate products; Slack-based measure (SBM); Efficiency; Network-DEA (NDEA); Two-stage; Intermediate-oriented efficiency.
Surveying forecasting: a review and directions for future research
by Shari De Baets
Abstract: How is forecasting doing in todays world? Its a question researchers have been asking for a long time. For half a century, we have been surveying practitioners, conference attendees, other academics, managers and high-level executives. From the introduction of forecasting in organisations onward, we have questioned technique use and familiarity, accuracy and evaluation methods, the place of forecasting within organisations and the hurdles and barriers that prevent forecasting from evolving as fast in practice as it does in academia. This paper summarizes these findings and concludes with a number of recommendations for future surveys, as we will need to continue tracking the state of the art of forecasting practice. Recommendations includes surveying the analysts rather than the forecasting managers, using an international sample, focusing on process-oriented performance measures and looking into the barriers that prevent a more widespread adoption of sophisticated forecasting techniques.
Keywords: forecasting survey; practitioners; forecast improvement.
An ontology-based approach for automatic goal requirements engineering in data warehouse design
by Fahmi Bargui, Hanene Ben-abdallah
Abstract: Goal-oriented approaches in data warehouse development projects still face two main issues. First, analysts often lack domain knowledge required during goal decomposition. This may lead to identifying erroneous requirements that most likely propagate to the remaining project phases, potentially leading to the project failure. Second, the identification of the data warehouse content from requirements is done manually by the designers in an error-prone process. In this paper, we address these two issues. We propose an ontology that formalizes and automates the reasoning about decision-making knowledge, which allows analysts to compensate their lack of domain knowledge during goal decomposition. In addition, to demonstrate the feasibility of our proposal we present a semi-automatic process that assists the construction of the ontology. Furthermore, the proposed ontology ensures the traceability between both decision-making and data warehouse knowledge. Thanks to this traceability, we propose a set of rules that automatically derive a data warehouse schema from requirements specification.
Keywords: Decision Support Systems; Data Warehouse; Data Mart; Multidimensional modeling; Requirements elicitation; Goal-oriented Requirements Engineering; Automatic Reasoning; Ontology.
The Impact of Agricultural Technology Adoption on Income Inequality: A Propensity Score Matching Analysis for Rural Ethiopia
by Aynalem Shita, Nand Kumar, Seema Singh
Abstract: This study analyzes the impact of agricultural technology adoption on income inequality. Primary data have been collected from 400 sample households in Awi zone of Ethiopia through household survey during agricultural season of 2017/18. The collected data were analyzed by using propensity score matching method. The estimated results revealed that adoption of agricultural technologies such as chemical fertilizer and improved seeds significantly increase total household income but worsen income distribution. After adoption of agricultural technologies, income inequality measured by Gini coefficient increased ranged from 0.047 to 0.087. Hence, the government and other concerned authorities should exert more efforts in order to enhance technology adoption status of the poor households by increasing their accessibility for extension and credit services.
Keywords: Technology adoption; Income inequality; propensity score matching; Ethiopia.
Rough Set based Quality of Service Optimization Guidelines with Stack Parameter in MANET
by PRATHVIRAJ NAGARAJA
Abstract: In Mobile Ad-hoc NETwork(MANET),providing a guaranteed service for packet delivery has to pass through several hurdles. Providing guaranteed service should address multiple Quality of Service (QoS) parameters under uncertain network conditions. The QoS parameters should be prioritized in consideration of MANET constraints and applications running on MANET. Decision making from imprecise information will solve NP-complete problem of providing multi constrained QoS routing. The QoS aspects of MANET are impacted by the multi layer stack parameters. An analysis has been conducted to identify the trade off point for configuring the stack parameters to achieve better QoS in packet delivery. The outcome of analysis is discussed in terms of packet error rate, energy efﬁciency, goodput and delay with the support of Rough Set Theory(RST).The multi-objective analysis capabilities of RST make it suitable for taking dynamic decision to prioritize QoS parameter,which provide the guaranteed service in packet delivery. The Rough Set Exploration System (RSES) is used for extensive analysis of QoS in data delivery. The different stages of RSES like data exploration, discretization, reduction and decision rules are applied on QoS values of available routes. The rough set decision rules are filtered out based on probabilistic properties like strength, certainty and coverage of the decision rules. The positive dependency between conditions and decisions of selected decision rules are confirmed with certainty and coverage of relationships.
Keywords: MANET; Quality of Service; Rough Set Theory; Rough Set Exploration System.
Academic Students' Performance Prediction Model: An Oman Case Study
by P. Vijaya, Satish Chander, Gupta S.L
Abstract: Education system in Oman attains a fast growth and it requires effective standards to increase the number of graduates with quality education and with effective skills and knowledge. The Higher Education Institutions (HEIs) in Oman is increasing in number and it poses the need for graduates with world-level competing tendencies. Keeping this in mind, the proposed methodology proposes a novel method of predicting the academic performance of the students enrolled in the universities of Oman. For predicting the academic performance of the students, the Dragonfly Optimization-based Deep Belief Network (DrDBN) is employed. The data is collected using the proper questionnaire session and the best feature is selected based on the fuzzy-based entropy function. The training algorithm determines the optimal weight to the Deep Belief Network (DBN) for predicting the best solution. The proposed method predicts the performance of the student in the semester exams and adopts a proper teaching standard to equally benefit the students of all grades and in addition, the prediction strategy contributes a lot to the students to utilize their full potentials in the process of learning. The effectiveness of the proposed DrDBN is checked depending on the MSE and the RMSE metric values and is evaluated to be the best when compared to other existing techniques with low MSE value as 0.532, and low RMSE value as 0.026, respectively.
Keywords: Student performance prediction; Dragonfly algorithm; fuzzy entropy; Deep Belief Network; MSE.
Health Information Exchange Adoption: Influences of Public Insurance Programs
by Hsun-Ming Lee, Ju Long, Mayur Mehta, Peiqin Zhang
Abstract: For many years, the U.S. government has pushed the adoption of Health Information Exchange (HIE), which is a key to spur large-scale innovation in the healthcare delivery. As funding has diminished, healthcare managers need to assess the adoption incentivized by government programs. This study helps to get a better understanding of how the adoption is influenced by the factors associated with the policies regulated by public insurance programs: Medicare and Medicaid. Using the technology-organization-environment (TOE) framework, we evaluate the Health Information Exchange (HIE) adoption factors associate with policy implications. Based on a dataset integrated from data reported to the Healthcare Cost Report Information System and Hospital Comparison data, we conducted a logistic regression analysis to model the probability of HIE adoption as a function of TOE factors. Besides factors that affect hospitals technology adoption, such as hospital sizes and geographic locations, our research also revealed three significant HIE adoption factors not thoroughly examined before, including imaging efficiency, scale of outpatient departments, and payer mix. Our research could provide insights for practitioners and healthcare managers when examining the strategies associated with HIE adoption.
Keywords: Health information exchange; Healthcare; Technology adoption; TOE framework; Public insurance.
Technical Debt Reduction using Epsilon-Nash equilibrium for the Perturbed Software Refactor Game Model
by Vimaladevi Madhivanan, Zayaraz Godandapani
Abstract: Introduction of various software development processes and methodologies are aimed at building a quality software product. Irrespective of the existence of such techniques, there is a constant requirement to achieve a better and improved quality of the software products. Refactoring is a well known and vital technique for quality improvement that is applied to all types of software systems, which helps in the improvement of the internal structure of the code, without modifying the externally visible properties. Technical Debt (TD) is a metaphor that is one of the reasons for software to become obsolete. TD occurs whenever the required uncompleted changes exist in software due to constraints such as deadline management. The process of refactoring can be effectively applied to reduce the Technical Debt and the improvement of other vital quality attributes such as Abstraction, Inheritance, and coupling. This paper discusses a refactoring model that can be applied for an object oriented software system for improved quality by applying the concepts of Game Theory. A Multi-Player Perturbed Software Refactor Game Model is developed, that models Inheritance, Abstraction, Coupling and the Technical Debt, as multiple players of the game. An optimal strategy for refactoring the source code is arrived by calculating the ?-Nash equilibrium of the perturbed game. The results attained are compared against the popular Genetic Algorithm (GA), Artificial Bee Colony (ABC) and Simulated Annealing (SA) optimization algorithms, taking three open source java project samples. The results show that the proposed Game-Theoretic approach outperforms the other compared optimization algorithms with significant improvement in terms of the quality gain for Technical Debt and Coupling functions.
Keywords: Refactoring; Quality attributes; Technical debt; Game Theory; Epsilon-Nash equilibrium; Multiplayer Software Game; Trembling Hand Perfection.
Evaluation of Risk Causing Factors for the Incidence of Neck and Shoulder Pain in Adolescents using Fuzzy Analytic Hierarchy Process
by T. Padma, S.P. Shantharajah
Abstract: The incidence of neck and shoulder pain is recurrent in adolescents, and numerous factors causes for the occurrence of such a risk. Neck and shoulder pain in adolescents constitutes a large socioeconomic challenge and is responsible for substantial personal impacts and societal costs; thus requires intensive and systematic research to identify the potential causes and their precedence in pain occurrence. This study intent to explore the prevalence of neck and shoulder pain among the adolescents and to examine the array of risk factors associated with the hazard of the pain. Through background study and knowledge engineering process the potential risk factors identified are physical-, psychological-, psychosocial-, behavioural-, emotional- and sedentary-related. A set of domain experts comprising of an orthopedic surgeon, a neurologist, a psychoanalyst, a public health physician and a physiotherapist were involved in building a knowledge base. A Fuzzy analytic hierarchy process method exploiting indeterminate human knowledge and experience is applied to prioritize the derived risk factors and determines the precedence of risk level in neck and shoulder pain incidence among the adolescents which are categorized based on their ages as early-, middle- and late- adolescence group (age between 10-17, 18-21 and 22-24 respectively). The arrived results indicate that the middle adolescence category have a significantly greater chance for pain occurrence followed by early adolescence category; and then by late adolescence category. The outcomes of this research will support physicians, parents, policy makers and social workers in decision making and planning for the welfare of youths.
Keywords: Adolescent health; Neck and shoulder pain; Knowledge Engineering; Domain experts; Fuzzy Analytic Hierarchy Process.
Has globalisation reaped rewards? A fresh perspective from India.
by Shikha Gupta, Nand Kumar
Abstract: Using annual time series data from 1980-2015, the study aims to estimate the empirical relationship between Indias trade, globalisation, and GDP growth. For this, ADF along with PP and KPSS techniques are used to establish stationarity. As there is evidence of co-integration, Vector Error Correction Model and DOLS estimations are used to adjudge the adjustment of variables. Wald test and Toda-Yamamoto Granger causality follow in analysis to investigate the short-run and the long-run causality, respectively. In order to assess the response path, variance decomposition and impulse response functions are created. Globalization has a negative effect and trade bears a positive effect on economic growth. However, contrary to the perception of New Growth Theory, increasing trade and globalisation do not have an impact on the long-run economic growth. The novelty of the study lies in using an augmented version of KoF Index to avoid the problem of collinearity and more robust approach.
Keywords: Trade; Globalisation; Growth; Openness; KoF Globalisation Index.
Special Issue on: ICDSST - PROMETHEE DAYS 2018 Decision Support for Transport Methodologies, Tools and Applications
Decision Making on Sea; An Expert System for Risk Assessment in Maritime using Data Mining
by Dimitrios Kokotos, Alkiviadis Kyriakakis
Abstract: This work proposes the prototyping implementation of a dynamic expert system. The essence of the paper is the proposal of prediction of ship accidents. The database used consists of data collected from official investigation reports of the Coast Guard and the validation process of the proposed expert system was based on this data. The real-world data are noisy and have many missing attribute values. A classifier based on C5 algorithm is able to work even in presence of these limitations thus is used for building decision trees. The models are described through the provision of Predictive Model Markup Language. The decision tree models are used in the knowledge acquisition and its representation.
The optimal decision rules estimated the dependency of the most important predictor upon the target variable "Source of accidents". The comparison between two periods shows that accidents due to human error were reduced; this result is in line with the International Maritime Organisation report.
The resulting patterns can be used to gain insight into aspects of shipping safety and to predict outcomes for future situations as an aid to decision-making. The proposed expert system is an essential reference for sea and coastal operations since it is expected to provide valuable decisions for shipping safety.
The optimal decision rules estimated the dependency of the most important predictor upon the target variable "Source of accidents". The comparison between two periods shows that accidents due to human error were reduced; this result is in line with the International Maritime Organisation report.
Keywords: Classification algorithms; Prediction; Ship accident; Maritime Safety; Decision Trees; Data Mining; Off-shore.
Sustainable Development and Morphological Analysis: A Multi-Level Strategic Planning for the Transport Sector
by Maria De Fátima Teles, Jorge Freire De Sousa
Abstract: Societies face complex challenges, which require a harmonious transition to future patterns. A strategic response to reconfigure society should assure the provision of critical resources and the resilience of the socio-technical systems in the long-term. The implementation of a new dominant technology and paradigm in the transport context is a complex process: it is multidimensional, requires seamless integration of various features and entails trade-offs in the decision-making process. The authors use General Morphological Analysis (GMA) as a theoretical framework that supports decision-making in the transition management of transport to a new powertrain technology. This example is just an illustration of a broader representation of all the possible solutions of a large-scale problem as it is the case of any multi-level process of governance, leading to the pursuit of new paradigms. The originality of the paper lies on using a GMA that addresses sustainable challenges in a transport system from a multi-level perspective.
Keywords: sustainable development; multi-level process; integrated decision-making; general morphological analysis; transport.
Multi-criteria location of multi-modal terminals in integrated public transport systems
by Jairo R. Montoya-Torres, Johanna Camargo-Perez
Abstract: A global trend worldwide in people transportation in urban areas is to integrate different transportation modes into the same network so the needs of several stakeholders are considered. This paper proposes a methodology for the location of multimodal terminals in integrated public transport systems considering multiple decision-making criteria for large-sized cities. To validate the methodology, the case of the city of Bogot
Keywords: people transportation; urban; location; multi-criteria decision-making; case study.