Inspecting Hybrid Data Mining Approaches in Decision Support Systems for Humanities Texts Criticism

The majority of systems dealing with natural language processing (NLP) and artificial intelligence (AI) can assist in making automated and automatically-supported decisions. However, these systems may face challenges and difficulties or find it confusing to identify the required information (characterization) for eliciting a decision by extracting or summarizing relevant information from large text documents or colossal content. When obtaining these documents online, for instance from social networking or social media, these sites undergo a remarkable increase in the textual content. The main objective of the present study is to conduct a survey and show the latest developments about the implementation of text-mining techniques in humanities when summarizing and eliciting automated decisions. This process relies on technological advancement and considers (1) the automated-decision support-techniques commonly used in humanities, (2) the performance evolution and the use of the stylometric approach in text-mining, and (3) the comparisons of the results of chunking text by using different attributes in Burrows' Delta method. This study also provides an overview of the efficiency of applying some selected data-mining (DM) methods with various text-mining techniques to support the critics' decision in artistry ‒ one field of humanities. The automatic choice of criticism in this field was supported by a hybrid approach to these procedures.

Implementing an Enhanced Procurement Management System Using Decision Support Techniques

Modeling procurement management system is important for quality decision making regarding business capacity planning, supply and scheduling. In the Procurement Services Department (PSD), most commonly used indicators to measuring performance include supply period, products rating, ranking recommendations, resource scheduling and number of goods supplied and delivered. In this paper, a Decision Support Service (DSS) technique was proposed to optimize procurement services in business and public organization. First, a study of a typical public and private organization was conducted to gain insights into the operations of the procurement department and the contributions of important system parameters to procurement management. Second, a product and supplier collaborative filtering technique were investigated to obtain transformed data for model training and testing for implementation using Partial Correlation Coefficient (PCC). The Partial Correlation Coefficient (PCC) for a particular product or supplier was utilized for generating the outcomes with tuned values which were compared with actual observed outcomes. The residuals were evaluated in terms of linearity, normality, independence and constant variance. The visualized system plots indicate a good performance as the quality and accuracy of the decision support model was evaluated using some basic metrics. The overall system implementation and performance results demonstrated the importance of Decision Support Services in assessing the performance of procurement management systems. A robust tool for this assessment and a model for procurement and supply planning indicates that the system framework offered Quality of Service (QoS) provisioning.

Computer Support for Discussions in Spatial Planning

1. Introduction Spatial planning deals with the problem of distributing the limited resource "space" among different uses and users. It can be highly challenging to find a balanced land-use pattern, for example in urban agglomerations. Different interest groups such as residents, industry, and ecologists will claim different desirable land-uses for a given area. Spatial planning is also about locating unwanted land-use such as waste facilities. In this case, interest groups (e.g. city councils, neighbourhood organizations) and individuals will fight nearby locations. This situation is known as the NIMBY problem: “Not In My BackYard!” In democratic societies, decisions such as those in spatial planning are made by political representatives in cooperation with public administration and residents. The final decision will usually be based on a number of consecutive prior decisions, or choices, which are made by different groups of stakeholders. At any of these decision levels, there are two important methods to reach a conclusion: consensus finding, or voting. Both will be preceded by more or less intensive discussions and argumentation. The ultimate goal of discussions is to achieve sustainable development by integrating the objectives of diverse stakeholders. Thus, we argue that discussions are a crucial element of spatial planning procedures and are to be integrated with planning and decision support techniques. Discussions will have diverse formats in different planning projects. For example, the number of participants may vary from only two to hundreds and more; participants may get together or stay separated in space and/or time; discussion may be un-moderated, or moderated and structured. Nevertheless, discussion contributions (statements, messages, arguments, articles) in spatial planning will commonly contain a spatial reference. This does allow to link discussion support to spatially enabled decision support techniques as argued in this chapter. In section 2, we will review general theories on argumentation and introduce major concepts of computer-supported cooperative work. Next, geographically referenced discourse will be analysed in more detail leading to the argumentation map model (section 3). Section 4 develops use cases for GIS-based discussion support, and section 5 presents some existing applications. Finally, we will speculate about future developments in computer support for discussions in spatial planning (section 6).

Computer Support for Discussions in Spatial Planning

1. Introduction Spatial planning deals with the problem of distributing the limited resource "space" among different uses and users. It can be highly challenging to find a balanced land-use pattern, for example in urban agglomerations. Different interest groups such as residents, industry, and ecologists will claim different desirable land-uses for a given area. Spatial planning is also about locating unwanted land-use such as waste facilities. In this case, interest groups (e.g. city councils, neighbourhood organizations) and individuals will fight nearby locations. This situation is known as the NIMBY problem: “Not In My BackYard!” In democratic societies, decisions such as those in spatial planning are made by political representatives in cooperation with public administration and residents. The final decision will usually be based on a number of consecutive prior decisions, or choices, which are made by different groups of stakeholders. At any of these decision levels, there are two important methods to reach a conclusion: consensus finding, or voting. Both will be preceded by more or less intensive discussions and argumentation. The ultimate goal of discussions is to achieve sustainable development by integrating the objectives of diverse stakeholders. Thus, we argue that discussions are a crucial element of spatial planning procedures and are to be integrated with planning and decision support techniques. Discussions will have diverse formats in different planning projects. For example, the number of participants may vary from only two to hundreds and more; participants may get together or stay separated in space and/or time; discussion may be un-moderated, or moderated and structured. Nevertheless, discussion contributions (statements, messages, arguments, articles) in spatial planning will commonly contain a spatial reference. This does allow to link discussion support to spatially enabled decision support techniques as argued in this chapter. In section 2, we will review general theories on argumentation and introduce major concepts of computer-supported cooperative work. Next, geographically referenced discourse will be analysed in more detail leading to the argumentation map model (section 3). Section 4 develops use cases for GIS-based discussion support, and section 5 presents some existing applications. Finally, we will speculate about future developments in computer support for discussions in spatial planning (section 6).

Roadkill-Data-Based Identification and Ranking of Mammal Habitats

Wildlife–vehicle collisions, as well as environmental factors that affect collisions and mitigation measures, are usually modelled and analysed in the vicinity of or within roads, while habitat attractiveness to wildlife along with risk to drivers remain mostly underestimated. The main goal of this study was the identification, characterisation, and ranking of mammalian habitats in Lithuania in relation to 2002–2017 roadkill data. We identified habitat patches as areas (varying from 1 to 1488 square kilometres) isolated by neighbouring roads characterised by at least one wildlife–vehicle collision hotspot. We ranked all identified habitats on the basis of land cover, the presence of an ecological corridor, a mammalian pathway, and roadkill hotspot data. A ranking scenario describing both habitat attractiveness to wildlife and the risk to drivers was defined and applied. Ranks for each habitat were calculated using multiple criteria spatial decision support techniques. Multiple regression analyses were used to identify the relationship between habitat ranks, species richness, and land cover classes. Strong relationships were identified and are discussed between the habitat patch ranks in five (out of 28) land cover classes and in eight (out of 28) species (97% of all mammal road kills). We conclude that, along with conventional roadkill hotspot identification, roadkill-based habitat identification and characterisation as well as species richness analysis should be used in road safety infrastructure planning.

Predicting Future Utilization Using Self-Reported Health and Health Conditions in a Longitudinal Cohort Study: Implications for Health Insurance Decision Support

Decision support techniques and online algorithms aim to help individuals predict costs and facilitate their choice of health insurance coverage. Self-reported health status (SHS), whereby patients rate their own health, could improve cost-prediction estimates without requiring individuals to share personal health information or know about undiagnosed conditions. We compared the predictive accuracy of several models: (1) SHS only, (2) a “basic” model adding health-related variables, and (3) a “full” model adding measures of healthcare access. The Medical Expenditure Panel Survey was used to predict 2015 health expenditures from 2014 data. Relative performance was assessed by comparing adjusted-R2 values and by reporting the predictive accuracy of the models for a new cohort (2015–2016 data). In the SHS-only model, those with better SHS were less likely to incur expenditures. However, after accounting for health variables, those with better SHS were more likely to incur expenses. In the full model, SHS was no longer predictive of incurring expenses. Variables indicating better access to care were associated with higher likelihood of spending and higher spending. The full model ( R2 = 0.290) performed slightly better than the basic model ( R2 = 0.240), but neither performed well at the upper tail of the cost distribution. While our SHS-based models perform well in the aggregate, predicting population-level risk well, they are not sufficiently accurate to guide individuals’ insurance shopping decisions in all cases. Policies that rely heavily on health insurance consumers making individually optimal choices cannot assume that decision tools can accurately anticipate high costs.

Energy Supply Preferences as Multicriteria Decision Problems: Developing a System of Criteria from Survey Data

Decision support techniques have a key role in investment and strategic decisions in the energy sector. As complex decision-making problems involve the simultaneous consideration of an extensive set of different factors, it is an essential part of the methodology to define, structure, and integrate the criteria. The main purpose of the study was to develop a system of criteria and weights that are suitable for general application in the energy sector and can best describe the decision-making mechanisms present in society and various social groups. When developing the system of criteria, we moved away from the hierarchical approach related to the three pillars of sustainability; therefore, a wide range of notions were assessed based on a population representative survey data collected in Hungary. We used algebraic methods to explore the internal structure of the set of criteria that had been previously defined by means of social sciences, while the importance weights were specified by applying the method of analytic network process. Furthermore, the ranking of heating and electricity generation alternatives were determined.

Decision Support Techniques for Dermatology Using Case-Based Reasoning

Identification of skin disease has become a challenging task with the origination of various skin diseases. This paper presents a case-based reasoning (CBR) decision support system to enhance dermatological diagnosis for rural and remote communities. In this proposed work, an automated way is introduced to deal with the inconsistency problem in CBRs. This new hybrid architecture is to support the diagnosis in multiple skin diseases. The architecture used case-based reasoning terminology facilitates the medical diagnosis. Case based reasoning system retrieves the data which contains symptoms and treatment plan of the disease from the data repository by the way of matching visual contents of the image, such as shape, texture, and color descriptors. The extracted feature vector is fed into a framework to retrieve the data. The results proved using ROC curve that the proposed architecture yields high contribution to the computer-aided diagnosis of skin lesions. In experimental analysis, the system yields a specificity of 95.25% and a sensitivity of 86.77%. Our empirical evaluation has a superior retrieval and diagnosis performance when compared to the performance of other works.

Precision Medicine in the Context of Artificial Intelligence

Similar to all fields of study, growth occurs with breakthrough or developmental research spanning to the progress and intimate utility of technology. Dilemmas of various sectors have been favorably resolved by adopting artificial intelligence (AI) algorithms. Applying Precision Medicine profoundly depends on AI algorithms to work Precision Medicine queries like; predicting or detecting, diagnosing the disease properly, and optimizing therapy, hence, the selection of the algorithm is affected by its capacity and practicality. Nevertheless, it is yet in its initial step and fronts some hurdles crucial to the flourishing deployment of precision medicine like research, adoption values, and authority controls. Notwithstanding, Precision Medicine also pretends some difficulties like; modifying the health discipline and profession to the fact that automata and algorithms could displace most of the healthcare professional tasks they act now. Ultimately, effective employment of precision medicine would rescue countless lives and improve the health profession. This review examines the present state of AI applications in precision medicine and future opportunities. It discusses major AI systems like IBM Watson, examining moral accountability and legal obligations when applying it in clinical decision-making, advantages and boundaries of employing Watson and different AI clinical decision support techniques, and considerations before consulting AI systems.