Application of a Group Decision Support System in the Reform of Study Programmes

This paper presents the process and impact of the application of a group decision support system (GDSS) in the reform of post-Bologna graduate and postgraduate study programmes in two higher education institutions in Slovenia. Four experiments with four groups including both students and staff were performed. We have used the GDSS tool TeamWorks to organize, moderate and document meetings intended to develop possible answers to the question "How can we improve the content and execution of the study programmes?" The obtained results are to be used in the design of new study courses. Analysis of the idea gathering process dynamics represents important information for researchers in the field of group decision-making process dynamics. In addition to the experimental work the structure of a group decision support process is described and guidelines for the further development of tools and methodologies are presented.

Mining Primary Care Electronic Health Records for Automatic Disease Phenotyping: A Transparent Machine Learning Framework

(1) Background: We aimed to develop a transparent machine-learning (ML) framework to automatically identify patients with a condition from electronic health records (EHRs) via a parsimonious set of features. (2) Methods: We linked multiple sources of EHRs, including 917,496,869 primary care records and 40,656,805 secondary care records and 694,954 records from specialist surgeries between 2002 and 2012, to generate a unique dataset. Then, we treated patient identification as a problem of text classification and proposed a transparent disease-phenotyping framework. This framework comprises a generation of patient representation, feature selection, and optimal phenotyping algorithm development to tackle the imbalanced nature of the data. This framework was extensively evaluated by identifying rheumatoid arthritis (RA) and ankylosing spondylitis (AS). (3) Results: Being applied to the linked dataset of 9657 patients with 1484 cases of rheumatoid arthritis (RA) and 204 cases of ankylosing spondylitis (AS), this framework achieved accuracy and positive predictive values of 86.19% and 88.46%, respectively, for RA and 99.23% and 97.75% for AS, comparable with expert knowledge-driven methods. (4) Conclusions: This framework could potentially be used as an efficient tool for identifying patients with a condition of interest from EHRs, helping clinicians in clinical decision-support process.

A conceptual framework for an agile asset performance management process

PurposeDisturbances in terms of major crises such as pandemics, fluctuations in demand and oil price, energy consumption and supply chain can significantly impair the maintenance programs effectiveness and efficiency. Hence, there is an urgent need for an agile asset performance management (AAPM) framework.Design/methodology/approachThis paper's main objective is to design a comprehensive framework for an AAPM system that sustains the desired asset performance by reacting efficiently, quickly and intelligently to the changes in the operating context parameters and asset health conditions. Such a framework is adaptive to changes in scenarios and aims to systematise the decision support process, considering different objectives.FindingsThe development of the proposed framework has led to identifying an innovative way of seamless integration between crucial reliability and asset management tools. Also, the methodology implementation is expected to promote the practical use of its reliability tools and enable asset stakeholders to break silo working for clear communication around asset performance.Originality/valueThe implementation of the AAPM framework follows a new approach developed during this research and coined by the authors as the “8S approach.”

Strategic decision support for long-term conservation management planning.

Forward thinking conservation-planning can benefit from modeling future landscapes that result from multiple alternative management scenarios. However, long-term landscape modeling and downstream analyses of modeling results can lead to massive amounts of data that are difficult to assemble, analyze, and to report findings in a way that is easily accessible to decision makers. In this study, we developed a decision support process to evaluate modeled forest conditions resulting from five management scenarios, modeled across 100 years in California's Lake Tahoe basin; to this end we drew upon a large and complex hierarchical dataset intended to evaluate landscape resilience. Trajectories of landscape characteristics used to inform an analysis of landscape resilience in the Lake Tahoe basin were modeled with the spatially explicit LANDIS-II vegetation simulator. Downstream modeling outputs of additional landscape characteristics were derived from the LANDIS-II outputs (e.g., wildlife conditions, water quality, effects of fire). The later modeling processes resulted in the generation of massive data sets with high dimensionality of landscape characteristics at both high spatial and temporal resolution. Ultimately, our analysis distilled hundreds of data inputs into trajectories of the performance of the five management scenarios over the 100-year time horizon of the modeling. We then evaluated each management scenario based on inter-year variability, and absolute and relative performance. We found that the management scenario that relied on prescribed fire, outperformed the other four management approaches. Both these results, and the process that led to them, provided decision makers with easy-to-understand results based on a rational, transparent, and repeatable decision support process.

ASSIGNMENT PROBLEM AS A DECISION SUPPORT PROCESS TOOLKIT IN THE LOGISTIC FIRM TURNOVER

The features of the decision-making at a logistics enterprise are shown. The assignment problem solution on the example of a specific commodity item made it possible to determine the directions of increasing the efficiency of the warehouse complex functioning, to propose the distribution of goods by cells, to find the optimal option for storing goods in the warehouse of a specific logistics enterprise.

Knowledge Acquisition and Representation for High-Performance Building Design: A Review for Defining Requirements for Developing a Design Expert System

New functions and requirements of high performance building (HPB) being added and several regulations and certification conditions being reinforced steadily make it harder for designers to decide HPB designs alone. Although many designers wish to rely on HPB consultants for advice, not all projects can afford consultants. We expect that, in the near future, computer aids such as design expert systems can help designers by providing the role of HPB consultants. The effectiveness and success or failure of the solution offered by the expert system must be affected by the quality, systemic structure, resilience, and applicability of expert knowledge. This study aims to set the problem definition and category required for existing HPB designs, and to find the knowledge acquisition and representation methods that are the most suitable to the design expert system based on the literature review. The HPB design literature from the past 10 years revealed that the greatest features of knowledge acquisition and representation are the increasing proportion of computer-based data analytics using machine learning algorithms, whereas rules, frames, and cognitive maps that are derived from heuristics are conventional representation formalisms of traditional expert systems. Moreover, data analytics are applied to not only literally raw data from observations and measurement, but also discrete processed data as the results of simulations or composite rules in order to derive latent rule, hidden pattern, and trends. Furthermore, there is a clear trend that designers prefer the method that decision support tools propose a solution directly as optimizer does. This is due to the lack of resources and time for designers to execute performance evaluation and analysis of alternatives by themselves, even if they have sufficient experience on the HPB. However, because the risk and responsibility for the final design should be taken by designers solely, they are afraid of convenient black box decision making provided by machines. If the process of using the primary knowledge in which frame to reach the solution and how the solution is derived are transparently open to the designers, the solution made by the design expert system will be able to obtain more trust from designers. This transparent decision support process would comply with the requirement specified in a recent design study that designers prefer flexible design environments that give more creative control and freedom over design options, when compared to an automated optimization approach.

Assessment of wind damage risk in forest areas: application with GIS and Fuzzy-AHP MATLAB graphical user interface tool

<p>In the current situation, the forest degradation areas caused by severe wind-breaking has steadily risen. This research proposes an efficient decision support tool to reduce wind damage risk and monitor forest zones. This study provides an outcome of the role of the combination of geographical information system (GIS) and Fuzzy-AHP MATLAB graphical user interface (GUI) for forest managers and environmental consultants. The user-friendly application shows how the research work ensures forest spatial planning and monitoring on ecological and forest management purposes on a regional and national worldwide scale. A representative Czech case study was chosen regarding different parameter characteristics to test our approach. The study also used map surfaces from field survey sampling results and compared the ground truth values at specific locations with data from the new model. The GIS and Fuzzy-AHP GUI are helpful for various consultants in optimizing the decision-support process in many fields.</p>

Basic positions of support of decision making in management of fire departments

Introduction. The article is devoted to the study of the features of managerial decision-making in complex socio-economic systems in the context of fire and rescue units management. The article deals with the decomposition of the decision-making process into the main elements and provides a thematic analysis of each of them. The author's classification of decision-makers on the fire from among the main positions and non-regular officials of the garrison is presented. The tasks of the research are to analyze the current state of the basic conceptual apparatus of the theory of decision support in the management of fire protection units and to formulate the most general approach to the definition of the decision support process. Methods. The analysis of Russian- and English-language literary, normative and statistical sources of information on the topic under consideration is carried out. The result of the decomposition and synthesis of the analyzed information is tables, figures and diagrams, as well as explanations to them. The author also compares the approaches to decision-making from the Russian-language management theory with the results of empirical studies conducted abroad. Results and discussion. A theoretical review of the basic provisions of the theory of decision support with an appeal to the features inherent in the process of managing fire protection units is carried out. The author presents the results of a retrospective analysis of the development of approaches to the definition of the concepts of "decision support system" and "management support", as well as the definition of the term "support of decision making". Conclusions. Based on the results of the study, a hypothesis is formulated that at the stage of development of specialized decision support systems for decision makers, a synthesis between different approaches will remain. Keywords: decision support systems, management support, decision support, fire department management, complex socio-economic systems

Methodology for the Study of Near-Future Changes of Fire Weather Patterns with Emphasis on Archaeological and Protected Touristic Areas in Greece

This work introduces a methodology for assessing near-future fire weather pattern changes based on the Canadian Fire Weather Index system components (Fire Weather Index (FWI), Initial Spread Index (ISI), Fire Severity Rating (FSR)), applied in touristic areas in Greece. Four series of daily raster-based datasets for the fire seasons (May–October), concerning a historic (2006 to 2015) and a future climatology period (2036–2045), were created for the areas under consideration, based on high-resolution climate modelling with the Representative Concentration Pathway (RCP), PCR 4.5 and RCP 8.5 scenarios. The climate model data were obtained from the European Coordinated Downscaling Experiment (EURO-CORDEX) climate database and consisted of atmospheric variables as required by the FWI system, at 12.5 km spatial resolution. The final datasets of the abovementioned variables used for the study were processed at 5 km spatial resolution for the domain of interest after applying regridding based on the nearest neighbour interpolating process. Geographic Information Systems (GIS) spatial operations, including spatial statistics and zonal analyses, were applied on the series of the derived daily raster maps in order to provide a number of output thematic layers. Moreover, historic FWI percentile values, which were estimated for Greece in the frame of a past research study of the Environmental Research Laboratory (EREL), were used as reference data for further evaluation of future fire weather changes. The straightforward methodology for the assessment of the evolution of spatial and temporal distribution of Fire weather Danger due to climate change presented herewith is an essential tool for enhancing the knowledge for the decision support process for forest fire prevention, planning and management policies in areas where the fire risk both in terms of fire hazard likelihood and expected impact is quite important due to human presence and cultural prestige, such as archaeological and tourist protected areas.

Decision Support System for Direct Target Cash Recipients Using the AHP and K-Means Method

<strong><em>In the Covid-19 pandemic situation, the government organized a Direct Cash Assistance as known as BLT for the people who were affected by Covid-19. The nominal amount of BLT received by the public is Rp. 600,000 per month. But in fact, the amount of BLT quota is not proportional to the list of BLT recipients submitted by regional officials, in this case, RT (Rukun Tetangga). So, to find out who is really suitable or appropriate, a decision-making system is needed so that the deposit of the BLT from the government can be right on target in accordance with the criteria set by the government. Stages of the study began with clustering of weights. After that, it is entered into the system to do a decision support process with AHP (Analytical Hierarchy Process). The target of this research is the application that can be used to assist the government in distributing BLT to be right on target. Based on the functional testing of the system, the functions in the system have been succeeded according to plan. This system has successfully applied the K-Means and AHP methods for decision making, to receive direct cash assistance from the government. This system has a 100% accuracy rate. Where the most important criteria in this system are income with a weight of 0.394142515, ownership of a house with a weight of 0.231035138, number of dependents with a weight of 0.190359096, age with a weight of 0.081077616, employment with a weight of 0.058111736, and weight with a weight of 0, 045273898</em></strong>