Decision Support System Model Research Articles

Models of context-aware decision support systems in dynamic structured domains

Some existing approaches to representation and organization of contexts in different information systems are analyzed. A two-level context management model for intelligent decision support in dynamic structured domains is proposed. A model for description of information resources of an open information environment is given. A technology model of context-aware decision support system is designed.

Bioeconomic Model of Decision Support System for Farm Management: Proposal of a Mathematical Model

The declining profitability of agriculture and livestock production, increasing climatic variations, and growing concern over the environmental impact of farming challenge farm management. In this context, we propose a generalized mathematical bioeconomic macro model for livestock production systems. This model resulted from a multidisciplinary effort to integrate major databases of climate, soil, plants, animals, and their economic aspects, searching for representing a livestock production similar to Brazilian systems of pasture-based beef cattle production. This work is divided into four submodels: (i) herd structure and animal characteristics; (ii) animal nutrient requirements; (iii) meteorological–soil–pasture–animal integration; and (iv) economic. We adopted the system dynamics modelling methodology, composed of differential and integral equations in structured iThink 9.1.4 software. The equations herein proposed were adapted from pre-existing studies, and we intend to include them into a macro model in the future and use them to build different scenarios based on real data. Copyright © 2014 John Wiley & Sons, Ltd.

Medical Decision Support Technology for Better Antenatal Care of the Mother, Under-Five Child Survival and Child Health in Rural India

Aim: To develop a decision support technology that can be used by the primary health care providers to take appropriate decisions while rendering health services to Mothers in antenatal Period, Mothers in Postnatal Period, Children below the age of 5 years. Materials and Methods: “Integrated Management of Childhood and Neonatal Illness” was chosen for prototyping for implementation as it was readily available. The developed software prototype was given to the protocol development unit and field trial unit for the initial feedback. We tested our decision support system (DSS) for maternal and childcare in two phases. The first phase involved live testing of the DSS in the urban hospital and in second phase it was given to Village Health workers (VHWs) in two rural Primary Health Centers. Result: We achieved nearly nil mismatches in the 0-2 months category and maternal care. The software for 2months-5years category found some mismatch in diagnosis. Apart from “acute severe malnutrition”; other disease classification found Kappa value to be above 0.9 Conclusion: Village Health worker together with clinical Decision Support System as one unit perform almost as good as a clinician in primary health care. The Decision Support System model may prove to be a highly replicable model.

Predictive assessment of autism using unsupervised machine learning models

The application of different artificial intelligence models in clinical decision support systems has been a research topic which mainly focuses on the diagnosis method. In this paper we describe the application of unsupervised machine learning models in decision supportive tools for predictive grading of autistic disorder. We used competitive learning networks and unsupervised data clustering methods to model the differential grading in childhood autistic rating scale CARS-based assessment. Modelling of conventional score-based assessment using unsupervised learning methods is the novelty in this work. Self-organisation feature map SOM with single input and four output units perform with a predictive ability of 100% during resubstitution testing.

Design of single user decision support system model based on fuzzy simple additive weighting algorithm to reduce consumer confusion problems in smartphone purchases

Design of single user decision support system model based on fuzzy simple additive weighting algorithm to reduce consumer confusion problems in smartphone purchases

A supply chain disturbance management fuzzy decision support system

This paper presents a supply chain disturbance management fuzzy decision support system model developed to support managers in their decision-making process of selecting the best operational policy (e.g., mitigation and/or contingency plans) to counter supply chain disturbances, thus improving supply chain resilience. The selection of such operational policies is based on the calculation of performance indexes that reflect the supply chain performance in different scenarios (e.g., normal operation, affected by disturbances, implementation of mitigation plans or implementation of contingency plans). The developed system lays on two pillars: first, on the use of fuzzy set theory to model the uncertainty associated with disturbances, their effects on the supply chain and the computation of the referred performance indexes; second, on the simulation of the supply chain under the effect of disturbances or operational policies, by coupling the system with a simulation software.

Role of Decision Support System for Renewable Energy Outreach

E is affected by various natural and manmade phenomena such as natural calamities, disasters, urbanization, and pollution. One such major issue is exhaustive usage of fossil energy and its adverse impact on our social, environmental and economical conditions.The study and the increase in awareness levels of ‘”energy resources and their environmental impact” is essential for the development of a sustainable society. Considering that the society consists of domain experts, policy makers and the general public, it is important for everyone to get familiarized with available renewable energy sources and how to exploit their benefits. Easy access to information on the availability of energy resources and their geographical distribution will help in better planning and determining potential energy investments, development strategies and also increase awareness among the public. In general, decision-making is the process of selecting the best viable option from a set of different options. Study on spatiotemporal characteristics of the energy sources will guide government, experts or even general public in agile decisionmaking. For a renewable energy project or for an individual, it is an important aspect to acquaint and select suitable optimized location considering all factors such as best available energy sources, climate, social and economical conditions. From an investment proposal to complex scientific analysis, decision-making is a key aspect in projects. Decision Support System (DSS) is being used to address various problems like carbon emissions and cost of product designs, impact of pollution on environment, etc. Specifically in the energy field, there are also diverse DSS models such as NREL, and IREL. Nevertheless, a systematic and holistic approach with detailed data structuring, intuitive reporting and integration of other heterogeneous models like demography and climate are missing for local insights and ground realities. DSS should be able to graphically represent the profile of energy sources that includes spatiotemporal patterns, demographics, topography, data history and characteristics of each energy source. This kind of DSS will aid in better planning and enable in finding the resources for governments and experts. As the data presented in an easy and understandable format, it will draw attention from the general public as well. Study on renewable energy requires understanding various data models and lot of broad and in-depth data analysis. The challenge is to extract the data from various sources, store, analyze, and present the information in an easy and intuitive format to all kinds of users. Different sections of users will have different requirements and different level of understanding about the data as shown in Figure 1. Importance and Maturity of DSS in terms of analytical capabilities and data (quality and quantity) varies from profession to profession and situational requirements. For example, from a common user’s perspective, “what is the annual average energy output that this energy source of fers?” an expert may wish to research, “why is there a decline in solar radiation in year 2012 when compared to2000; August versus January?” and governments may ask, “what could have been the change in energy output and savings if this particular energy source was used over the last f ive years?” Hence, DSS should be able to understand the user needs and present the information in engaging and understandable format. The challenges identified from a technical point of view are 2-fold: First, to do a spatiotemporal analysis it is important primarily to analyze huge historical data sets. Second, loading the data with minimal or no latency effects and communicating the processed information in a comprehensive format e.g. drill down chats for when and where analysis. Data warehouse (DW), extract, transfer and load (ETL), and business intelligence (BI) are successful business analytics’ technologies. They are designed to deal with huge, historical data sets by structuring data into multilevels for rapid exploration and analysis to aid decision-makers. Empowering scientific data with these technologies will assist scientists and government in making faster, productive and sustainable decisions. These technologies have the capability to handle and present the data ranging from global to local level scenarios.

A decision support system for public logistics information service management and optimization

Transportation optimization usually aims at minimizing the empty load ratios (ELRs) of vehicles. Most Chinese vehicles for logistics are owned by individual entrepreneurs. Because China is very large, transport distances are typically long, and thus the ELR is very high. The ELR is the primary reason for high transport costs, considerable pollution, and high energy consumption. Many Chinese local governments try to build public transport information services that decrease the ELR. This work proposes a decision support system (DSS) for public logistics information service management and optimization (PLISMO) for vehicle drivers and owners, logistics customers and related logistics service providers and management institutes. The dynamic and real-time matching model between goods and vehicles, and the enabling technologies are important issues for the DSS for PLISMO. Therefore, intelligent positioning technologies are employed to acquire and manage the vehicle status. A model matching vehicles with goods is developed based on an assessment model of transport capability and service priority criteria. A multi-objective real-time scheduling model is devised to minimize the ELR. Based on the concepts and decision-making models for PLISMO, a DSS is created and the architecture of the system is investigated. The effectiveness of the DSS and decision-making models is demonstrated by a case of finished vehicle logistics (FVL). Analytical results show that the proposed DSS can reduce the ELR and logistics cost. This system helps governments construct DSSs for general PLISMO.

Human Socio-cultural Behavior Modeling: A Soft-Computing Approach

Human behavioral and socio-cultural soft-computational modeling requires the ability to represent and manipulate imprecise perceptual and cognitive concepts. The research investigation into soft-computational models of human behavior and socio-cultural interactions, account for natural vagueness of human thought and communication, along with the dynamics, complexity, uncertainty, variability and unpredictability of actions and behavior. This paper covers selected soft-computational methods which were investigated for the Human Social Culture Behavior (HSCB) modeling program with the emphasis on the powerful computational benefits and usefulness of these methods to support forecasting social patterns and building socio-cultural decision support systems. The paper also introduces a novel social networking analysis model for the next generation decision sup-port systems.

Analysing urban resilience through alternative stormwater management options: application of the conceptual Spatial Decision Support System model at the neighbourhood scale

Recent changes in cities and their environments, caused by rapid urbanisation and climate change, have increased both flood probability and the severity of flooding. Consequently, there is a need for all cities to adapt to climate and socio-economic changes by developing new strategies for flood risk management. Following a risk paradigm shift from traditional to more integrated approaches, and considering the uncertainties of future urban development, one of the main emerging tasks for city managers becomes the development of resilient cities. However, the meaning of the resilience concept and its operability is still not clear. The goal of this research is to study how urban engineering and design disciplines can improve resilience to floods in urban neighbourhoods. This paper presents the conceptual Spatial Decision Support System (DS3) model which we consider a relevant tool to analyse and then implement resilience into neighbourhood design. Using this model, we analyse and discuss alternative stormwater management options at the neighbourhood scale in two specific areas: Rotterdam and New Orleans. The results obtained demonstrate that the DS3 model confirmed in its framework analysis that stormwater management systems can positively contribute to the improved flood resilience of a neighbourhood.

Failure recovery in distributed model composition with intelligent assistance

Composite models in Decision Support Systems (DSS) are combinations of model functions to solve complex decision problems. They must be executed successfully to obtain the desired results. Unfortunately, faults may happen during its execution due to the dynamic networks or the information asymmetry between developers and users. Therefore, designing effective failure recovery mechanism to ensure the reliability of the composite model execution is essential. Progress has been made in the web service composition field to obtain limited failure recovery capabilities, but not fully applicable to composite models since model services are informational services in essence which do not change the world conditions. This paper proposes a unified framework, integrated with a process ontology and multiple recovery strategies that can provide valuable failure recovery recommendations intelligently. The recovery strategies have been greatly enhanced in providing greater failure recovery capability. Feasibility and efficiency of this framework have been illustrated and tested.

Energy security for rural communities in the developing world

Purpose – The purpose of this paper is to demonstrate the viability of using bamboo hybrid fencing fertigated with grey water as a means of providing energy to rural communities in developing countries. Design/methodology/approach – The paper establishes such returns by developing a decision support system (DSS) model populated with parameters obtained from literature and field data. The DSS allows for a sensitivity analysis that examines the robustness of the hybrid bio-fencing under varying scenarios and the interactions among species, management, and technological variables. Findings – Critical variables identified include the technological efficiency, number of clumps per m2 planted and the influence of grey water on growth rates. Practical implications – In the developing countries, uncertainty abounds in rural “green” interventions. Such uncertainties can be quite problematic especially for marginal communities. This research provides developmental agents with the ability to derive specific economic...

Developing an Expertise Interaction Meta-Model for Group Decision Support System (GDSS)

Group Decision Support System (GDSS) provides a group electronic environment in which managers and teams can collectively make decisions and design solutions for unstructured and semi-structured problems. In this paper, we propose to model for group decision support system based on expertise interaction meta-model. In this paper we develop a specialized systems such as Management Information System (MIS), Decision Support Systems (DSS), and Executive Information Systems (EIS) to be talked about work with these systems and technologies for data mining and Online Analytical Processing (OLAP) and the role of knowledge-based DSS should be to allow experts to broaden and expand their expertise, not to narrow it down to focus on the specific decision needs of managers and employees. Expert System (ES) with knowledge base captured from numerous experts in the same subject area as well as from a variety of specialists in international financial management, international accounting, international tax areas, and so forth.

Development of an Object-Oriented Version of TOMGRO for a Web-based Decision Support System

The advantages of object-oriented programming for crop modeling are discussed. Contrarily to procedural languages such as Fortran77, object oriented programming yields a code that is intrinsically modular and whose architecture is close to that of the actual crop. This simplifies model merging and code re-use, which in turn tends to extend the model life-span and increases its chances of being adopted outside the research community. The tomato model TOMGRO is used as a case study and a new version of this model in C# is outlined. One of the advantages of C# is that it is fully integrated in the .Net framework and offers developers a powerful class library. Moreover, the inclusion of such a model in a web-based decision support system using Web services and ASP.NET would be straightforward.

Research of Decision Support System Based on Knowledge Management and Web Technology

This paper gives a new model of decision support system based on knowledge management and web technology. Firstly,we analysis the existing problem of the efficiency and expandability of the current system.Then, we study the knowledge management and the B/S model based on web technology.Based on this, a new model of decision support system is presented in this paper. The system is designed in four layers structure and on three library.Finally, the paper describes the structure of the system and gives the detailed steps of decision-making process.

Including social factors in an argumentative model for Group Decision Support Systems

In this paper we propose a Decision Support System for groups of people where each user delegates to an agent that represents her preferences and argues with other agents to obtain the best alternative for the whole group. The novelties of our approach are the inclusion of users' social factors, personality and trust, in the argumentation process and the negotiation system, plus a multi-agent architecture that represents the social connections within the group. Therefore, our model simulates the argumentations made by real users to agree on a concrete product in a very accurate way. As a case study, we have tested our theories in the movie recommendation domain with real social networks. We have concluded that distributed models and argumentation techniques including personality and social trust improve the satisfaction of users involved in a group decision making process.

Improving Group Decision Support Systems using Rough Set

In this paper, a proposed Group Decision Support Systems model based on Rough Set is presented. The model improves decision making process by using rough set as a tool for knowledge discovery on decision support system, where the same feature may evaluate by one decision maker as good and by another one as medium, in this case inconsistent will appear in decision problem. To cope with this problem, the model will be used to reduce inconsistent after computing lower and upper approximations. Moreover, the classification accuracy of the rough set with a single classifier and multiple classifiers was compared. These results indicate that, the model improve the classification accuracy for data sets, rather than using single and multiple classifiers.

HANDLING IMPRECISION IN QUALITATIVE DATA WAREHOUSE: URBAN BUILDING SITES ANNOYANCE ANALYSIS USE CASE

Abstract. Data warehouse means a decision support database allowing integration, organization, historisation, and management of data from heterogeneous sources, with the aim of exploiting them for decision-making. Data warehouses are essentially based on multidimensional model. This model organizes data into facts (subjects of analysis) and dimensions (axes of analysis). In classical data warehouses, facts are composed of numerical measures and dimensions which characterize it. Dimensions are organized into hierarchical levels of detail. Based on the navigation and aggregation mechanisms offered by OLAP (On-Line Analytical Processing) tools, facts can be analyzed according to the desired level of detail. In real world applications, facts are not always numerical, and can be of qualitative nature. In addition, sometimes a human expert or learned model such as a decision tree provides a qualitative evaluation of phenomenon based on its different parameters i.e. dimensions. Conventional data warehouses are thus not adapted to qualitative reasoning and have not the ability to deal with qualitative data. In previous work, we have proposed an original approach of qualitative data warehouse modeling, which permits integrating qualitative measures. Based on computing with words methodology, we have extended classical multidimensional data model to allow the aggregation and analysis of qualitative data in OLAP environment. We have implemented this model in a Spatial Decision Support System to help managers of public spaces to reduce annoyances and improve the quality of life of the citizens. In this paper, we will focus our study on the representation and management of imprecision in annoyance analysis process. The main objective of this process consists in determining the least harmful scenario of urban building sites, particularly in dense urban environments.

English

Phosphorus is a critical nutrient for crop production. The soil phosphorus deficit in sub-Saharan Africa is one of the most important constraints on crop productions. Resulting from the high phosphorus fixation capacities of highly weathered acidic soil coupled with the relatively low total phosphorus, the impact of this deficit is particularly pronounced in the case of rice cultivation. Phosphate rock is a promising alternative to water-soluble phosphorus fertilizers, but its low solubility has so far prevented its widespread adoption in the region. This study examined the results of a direct application effect of phosphate rock produced in Burkina Faso phosphate rock (BPR) on rice yields in on-farm trials conducted in the Guinea savannah and Equatorial forest zones, and on a phosphate rock decision support system (PRDSS) model. We initially hypothesized that BPR direct application will show little effect on rice yield due to its low solubility as same as previous studies. However, our study found that direct application of BPR has an effect on rice grain yield comparable to that of chemical water-soluble phosphate fertilizer, although according to PRDSS simulations, direct application of BPR had little effect compared to the effect of water-soluble phosphate fertilizers. The recognition of BPR effect on rice yield can enhance rice cultivation along with the aspect of usage of indigenous phosphorus resource in sub Saharan Africa (SSA).   Key words: Phosphate rock, direct application, phosphate rock decision support system (PRDSS), lowland rice, Ghana.

Development, uncertainty and sensitivity analysis of the simple SALUS crop model in DSSAT

Simplified approaches to modeling crop growth and development have recently received more attention due to increased interest in applying crop models at large scales for various agricultural assessments. In this study, we integrated the simple version of SALUS (System Approach to Land Use Sustainability) crop model in the widely-used Decision Support System for Agrotechnology Transfer (DSSAT) to enhance the capability of DSSAT to simulate additional crops without requiring detailed parameterization. An uncertainty and sensitivity analysis was conducted using the integrated DSSAT-simple SALUS model to assess the variability in model outputs and crop parameter ranking in response to uncertainties associated with crop parameters required by the model. The influence of year, production level, and location on the effect of crop parameter uncertainty was also investigated.Parameter uncertainty resulted in a high variability in modeled outputs. Simulated potential aboveground biomass ranged from 1.2tha−1 to 38tha−1 for maize and 4tha−1 to 26.5tha−1 for peanut and cotton, all locations and years considered. The degree of variability was dependent upon the production level, the location, the year, and the crop. Ranking of crop parameters was not significantly affected by the year of study but was strongly related to the production level, location, and crop. The model was not sensitive to parameters related to prediction of the timing of germination and emergence. The most influential parameters were related to leaf area index growth, crop duration, and thermal time accumulation. Findings from this study contributed to understanding the effects of crop parameter uncertainty on the model's outputs under different environmental conditions.