Hierarchical Decision Models Research Articles

IoT-based generalized multi-granulation sequential three-way decisions

In the context of the Internet of Things (IoT), decision models and GRC (Governance, Risk, and Compliance) can be used for data processing and decision-making processes. The IoT involves a large number of sensors and devices, some of which enable “device-free” functionality, meaning that specific devices or sensors are not required to obtain the necessary information. This technology utilizes the signals present in the environment to determine the location of individuals without them carrying any specific devices. By incorporating “device-free” sensor data into decision models, we can process IoT data more efficiently and achieve accurate location positioning. The prevailing hierarchical sequential three-way decision models (STDM) follow a common pattern of constructing a hierarchical tree of conditional attributes to acquire knowledge. However, these models fail to meet the diverse needs of users when it comes to rule mining complex hierarchical data with multiple levels and views in real-world applications. Additionally, the pursuit of simplified rules remains a significant topic of interest. To address these challenges, we propose a novel approach that integrates multi-granularity, device-free localization, and STDM. By leveraging IoT and device-free localization, we collect data from various devices and sensors to accurately determine the positions of individuals. Using this data, we construct a generalized hierarchical decision table by creating a concept hierarchical tree with decision attributes. This framework offers a comprehensive solution for overcoming the challenges of device-free localization and IoT. Subsequently, we establish a granular structure by partitioning the complete set of attributes. In this paper, our proposed approach improves the efficiency and accuracy of data processing in machine learning models and enables users to better process and understand complex datasets. Finally, the performance is experimentally validated for the models in this paper. Such models greatly enrich the theoretical framework of three-way decision making. Overall, the abstract provides a concise and succinct overview, outlining the motivation behind the research and presenting the contributions made.

Inclusion Bayes factors for mixed hierarchical diffusion decision models.

Cognitive models provide a substantively meaningful quantitative description of latent cognitive processes. The quantitative formulation of these models supports cumulative theory building and enables strong empirical tests. However, the nonlinearity of these models and pervasive correlations among model parameters pose special challenges when applying cognitive models to data. Firstly, estimating cognitive models typically requires large hierarchical data sets that need to be accommodated by an appropriate statistical structure within the model. Secondly, statistical inference needs to appropriately account for model uncertainty to avoid overconfidence and biased parameter estimates. In the present work, we show how these challenges can be addressed through a combination of Bayesian hierarchical modeling and Bayesian model averaging. To illustrate these techniques, we apply the popular diffusion decision model to data from a collaborative selective influence study. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Generalized multigranulation sequential three-way decision models for hierarchical classification

Hierarchical classification is an important research hotspot in machine learning due to the widespread existence of data with hierarchical class structures. The existing sequential three-way decision models mainly constructed the hierarchical condition information granules via concept hierarchy tree to discuss the three probabilistic regions for flat classification. However, in real-world applications, one may face not only the tree-structured data with hierarchical condition attributes but also more often the multi-level data with hierarchical decision attribute (hierarchical class labels). How to obtain acceptable decisions under different levels of granularity is the most important issue within the multi-level and multi-view data. To this end, we construct a generalized hierarchical decision table and propose a generalized hierarchical multigranulation sequential three-way decision model by combining multi-granularity and sequential three-way decisions. Specifically, we first design a generalized hierarchical decision table using concept hierarchy trees of all conditional attributes and decision attribute, and explore some basic properties. Then we decompose and aggregate condition and decision granules under different levels of granularity, propose the optimistic and pessimistic generalized hierarchical multigranulation three-way decision models to update the three probabilistic regions for flat and hierarchical classification, and discuss the relationships between these two models. Finally, the experimental results demonstrate that the proposed models are more suitable for different applications. These models will provide a novel insight and enrich the development of multigranulation three-way decisions from the perspective of multi-level and multi-view.

Algebraic representations of the weighted mean

We introduce a general framework for the algebraic representation of the weighted mean in the case in which priorities and values refer to a common aggregation domain, for instance in hierarchical multicriteria decision models of the AHP type. The general framework proposed is based on the semifield structure of open interval domains and provides a natural algebraic description of weighted mean aggregation, including the essential mechanism of normalization which transforms priorities into weights. Such description necessarily involves two operations, addition (abelian semigroup) and multiplication (abelian group), which generalize the role of addition and multiplication in P=(0,∞). In this sense, the semifield framework extends recent work by Cavallo, D'Apuzzo, and Squillante on the multiplicative group structure on the basis of the representation of pairwise comparison matrices and their associated priority vectors. We consider open interval domains S⊆R whose semifield structures are generated by bijections ϕ:S⊆R→P. Continuous (thus strictly monotonic) bijections play a central role. In such case, continuous strict triangular conorms/norms and uninorms emerge naturally in the representation of the semifield structure and, in their weighted version, they also provide the representation of the weighted mean, in both the arithmetic and geometric forms.

A Hierarchical Decision Model Based on Pairwise Comparisons1

Pairwise comparisons (PC) method is an efficient technique a nd hierarchical analysis is a popular means coping with complex decision problems. Based on two proposed theorems, this pa- per shows that the PC-based hierarchical decision models stem from the weighted average methods (including the arithmetic form and the geometric form). Some issues (including the rank reversal, the criterion for acceptable consistency and the method for deriving priorities, etc) associated with the current PC-based hierarchical models (including the AHP, the multiplicative AHP and the FPR- AHP) are investigated. Another PC-based hierarchical decision model, which is different from the Saaty's AHP, is introduced for applications by virtue of its desirable traits (such as the rank preser- vation, the isomorphic correspondence, etc).

Perancangan Model Hirarki Keputusan dan Sistem Basis Data pada Sistem Informasi Sumber Daya Manusia Sub-Sistem Rekrutmen dengan Metode Berjenjang

Management of employees as a resource is essential to enhance the effectiveness of employee’s performance, and the process efficiency of for organizations or companies. Possible problems related to the management of human resources need to be diagnosed which one to be solved as a priority. The problem is how to design the decision making model to help the Human Resource Department in determining the criteria for recruitment which can be used to take decisions on recruitment of human resources. This research aims to design a model of decision making systems and databases to support accuracy of decision making in human resource information system to create high loyalty and productivity so that the productivity of the company can be further improved. The research is divided into two phases: collection as well as analysis of data and design model. Specifically target to be achieved in this research are to identify the critical success factors of the model of decision making system for recruitment and develop models of decision-making system. The results obtained from this research are hierarchical decision models using analytical hierarchy process and its database design for the recruitment sub-system of human resource.

Hair Removal Technology Selection

Cosmetic companies have long-noticed the demand for personal grooming, including hair removal, has been growing at a financially attractive rate. Hair removal has been one of the most sought after sectors within the cosmetic market to capitalize investment opportunities. The variety of existing and impending technologies has made investment decision-making complicated. Hierarchical decision models (HDM) are able to cope with the complexity of hair removal technology selection. To select hair removal technology based on a HDM model, the following steps were pursued: defining the problem, selecting the experts, building and verifying the HDM model, data gathering, data analysis, and sensitivity analysis. At the end, the model is implemented and the best technology is selected.

Understanding the influence of urban- or rural-living on cardiac patients’ decisions about diet and physical activity: Descriptive decision modeling

BackgroundIt is challenging to assist people to attend to risk factors for coronary artery disease (CAD). There is potential for cultural elements associated with place of residence (i.e., urban- or rural-living) to have an effect on peoples’ decision-making about managing CAD risk. AimTo better understand patient's decision-making processes regarding having a heart-healthy diet and engaging in regular physical activity (major CAD risk factors), and the potential influence of urban- or rural-living. MethodsBased on a previous series of qualitative interviews with 42 cardiac patients (21 urban-living, 21 rural-living), hierarchical decision-models regarding eating a heart-healthy diet and engaging in regular physical activity were developed, and a survey based on the decision-models generated. The models were then tested for ‘fit’ with another group of 42 cardiac patients, and were revised to make them more parsimonious. The final models were tested with a novel group of 647 CAD patients from Alberta, Canada (327 urban-living, 320 rural-living). The primary analysis was focused on determining the extent to which patients completing the survey fell in the correct behavioral group. Thereafter individual nodes were examined to determine decision-making constructs that were different between urban- and rural-living patients. ResultsWhen tested, the models had overall accuracy of 93.5% for diet and 97.5% for physical activity. The most salient model nodes that led to differing behavioral outcomes reflected these constructs: perception of control over health; time, effort, or competing priorities; receipt of appropriate information; and appeal of the activity. ConclusionsThis information is potentially useful to assist healthcare providers to: (1) understand patients’ decisions regarding their cardiac risk factor modification behavior, and (2) better direct conversations about risk factor modification and educational activities.

Is nuclear energy an alternative: a case of technology assessment in Oregon

This paper presents a technology assessment of the technology alternatives to meet Oregon's energy needs while meeting its goals for the environment and consumers. The analysis focused on comparing nuclear power with other sources of energy. Methodologies including Strengths, Weaknesses, Opportunities and Threats (SWOT) analysis, hierarchical decision models and expert interviews were used. This technology assessment found that nuclear technology was selected by a narrow margin over the alternate 'always on' sources of electrical power. Subsequently the results from the expert survey indicate that the Pressurised Water Reactor (PWR) is favoured in nuclear technology.

A hierarchical decision model for optimum design alternative selection

Head injury criterion test at Rockwell Collins Flight Dynamics is a requirement for many new government regulatory agency certifications of head-up display systems. A number of design alternatives are available which would meet the regulatory requirement, and a number of seemingly disparate considerations are taken into account when a decision is made regarding the optimum regulatory compliance strategy. No formal method has been used to quantify the decision parameters and integrate them into a decision method. This paper presents a methodology based on hierarchical decision models.

A sensitivity analysis algorithm for hierarchical decision models

In this paper, a comprehensive algorithm is developed to analyze the sensitivity of hierarchical decision models (HDM), including the analytic hierarchy process and its variants, to single and multiple changes in the local contribution matrices at any level of the decision hierarchy. The algorithm is applicable to all HDM that use an additive function to derive the overall contribution vector. It is independent of pairwise comparison scales, judgment quantification techniques and group opinion combining methods. The allowable range/region of perturbations, contribution tolerance, operating point sensitivity coefficient, total sensitivity coefficient and the most critical decision element at a certain level are identified in the HDM SA algorithm. An example is given to demonstrate the application of the algorithm and show that HDM SA can reveal information more significant and useful than simply knowing the rank order of the decision alternatives.

Contractor selection using the analytic network process

Contractor selection is one of the main activities of clients. Without a proper and accurate method for selecting the most appropriate contractor, the performance of the project will be affected. The multi‐criteria decision‐making (MCDM) is suggested to be a viable method for contractor selection. The analytic hierarchy process (AHP) has been used as a tool for MCDM. However, AHP can only be employed in hierarchical decision models. For complicated decision problems, the analytic network process (ANP) is highly recommended since ANP allows interdependent influences specified in the model. An example is demonstrated to illustrate how this method is conducted, including the formation of supermatrix and the limit matrix.

A function-decomposition method for development of hierarchical multi-attribute decision models

Function decomposition is a recent machine learning method that develops a hierarchical structure from class-labeled data by discovering new aggregate attributes and their descriptions. Each new aggregate attribute is described by an example set whose complexity is lower than the complexity of the initial set. We show that function decomposition can be used to develop a hierarchical multi-attribute decision model from a given unstructured set of decision examples. The method implemented in a system called HINT is experimentally evaluated on a real-world housing loans allocation problem and on the rediscovery of three hierarchical decision models. The experimentation demonstrates that the decomposition can discover meaningful and transparent decision models of high classification accuracy. We specifically study the effects of human interaction through either assistance or provision of background knowledge for function decomposition, and show that this has a positive effect on both the comprehensibility and classification accuracy.

Influence of strategies and heuristics on farmers’ response to change under uncertainty

Hierarchical Decision Models of woolproducers’ decisions provide unique insights into the impact of major price changes. Producers’ lagged response in some contexts appear to be due to the ambiguous decision environment they face, their strategic goals and responses to that environment apart from lags caused by factors such as attitude to risk, expectations adjustment, adjustment costs and learning costs. Much of the response to major price changes comes from strategic decisions to change enterprises rather than marginal changes to existing enterprises. In ambiguous environments, methods may need to be found that incorporate simplifying behavioural rules and strategies.

Applications of qualitative multi-attribute decision models in health care

Hierarchical decision models are a general decision support methodology aimed at the classification or evaluation of options that occur in decision-making processes. They are also important for the analysis, simulation and explanation of options. Decision models are typically developed through the decomposition of complex decision problems into smaller and less complex subproblems; the result of such decomposition is a hierarchical structure that consists of attributes and utility functions. This article presents an approach to the development and application of qualitative hierarchical decision models that is based on DEX, an expert system shell for multi-attribute decision support. The distinguishing characteristics of DEX are the use of qualitative (symbolic) attributes, and ‘if-then’ decision rules. Also, DEX provides a number of methods for the analysis of models and options, such as selective explanation and what-if analysis. We demonstrate the applicability and flexibility of the approach presenting four real-life applications of DEX in health care: assessment of breast cancer risk, assessment of basic living activities in community nursing, risk assessment in diabetic foot care, and technical analysis of radiogram errors. In particular, we highlight and justify the importance of knowledge presentation and option analysis methods for practical decision-making. We further show that, using a recently developed data mining method called HINT, such hierarchical decision models can be discovered from retrospective patient data.

Modelling farmer behaviour: a personal construct theory interpretation of hierarchical decision models

Hierarchical decision models based on a two-stage decision process (Gladwin, 1977, 1989) have proved useful for describing and predicting individual decisions with a minimum of theoretical bias. The model has two weaknesses. First, it does not incorporate an explanation of the underlying motivation for behaviour. Second, the empirical techniques for building the decision models are based on ethnographic approaches that are time consuming and difficult to implement when multiple visits are a problem. In this article it is shown personal construct psychology (Kelly, 1955), which assumes people behave as ‘scientists’, can overcome these weaknesses. The combination provides a theory and an empirical model of behaviour that explains the motivation and reasons for behaviour, allows for learning, and describes and predicts individual decisions. In addition, it has associated interviewing techniques that complement the ethnographic techniques and overcome some of their limitations.

On fuzzy ratio comparisons in hierarchical decision models

This article develops a method for the interactive analysis of fuzzy pairwise comparisons in hierarchical weighting models. In the proposed method, fuzzy ratios of relative importance are employed as constraints on the membership values of local priorities so that fuzzy weights for the alternatives can be computed through linear programming. Moreover, graph displays of fuzzy relations are used as a means of illustrating the dominance implications of the specified statements.

Is Gardening an Adaptive Strategy for Florida Family Farmers?

The climatic and economic situation of the last five years has been disastrous for many of Florida's full-time farmers. As a result, more and more full-time farmers are being forced to cut back or stop farming commercially and get a higher-paying off-farm job. For these part-time farmers it makes more economic sense to secure a stable income from off-farm work and guarantee more than half the family's food supply through gardening and livestock production, than take the risk of full-time farming. Although gardening is not often considered to be as important as commercial farming, the results presented here of a gardening survey in four Florida counties show that gardening today is a key survival strategy for Florida farmers. How it became an adaptive strategy is the theoretical point of this paper. We propose that originally survival strategies are processed by the individual as sets of decision rules, which can be modeled using hierarchical decision models (HDMs). Over time, the decisions are made so frequently and routinely that they become part of a preattentive plan or script. The more successful plans or scripts diffuse from farmer to farmer and endure over generations, and thus become adaptive strategies.