Towards an Ontology for Impact Projection of Complex Decisions

Complex decisions are an unusual process, composed of actions. An impact is a measure of the tangible and intangible consequences of one thing on another. Impacts are interdependent, and the environment in which they are measured generates constant change for decision making. This paper proposes the impact projection’s conceptualization, organized into a meta-ontology called OntoImpact. It comprises concepts that are crucial in supporting the understanding and representation of impact projections for complex decisions. The main contribution of OntoImpact is to support decision-makers in their work tasks, besides providing bases to support the development of a complex decision system. This paper was evaluated in a case study of an emergency domain. The results show that OntoImpact provides elements that can support complex decision analysis and project impacts in a collaborative way.

Sistem Informasi Pengambilan Keputusan Penerima Rehab Rumah Menggunakan Metode Weighted Sum Model (WSM) Pada Desa Bira Lhok Kecamatan Montasik

The house renovation program provided by the Aceh Besar regional government, especially in Gampong Bira Lhok, Montasik District, is an assistance program for the welfare of villagers whose housing conditions are far from livable. The problem faced by the Gampong government in the decision system for recipients of house renovation assistance at this time is that it still uses the decision system of deliberations between the Gampong apparatus and the Village Head so that it takes time to make decisions. Therefore, it is necessary to have a Decision Support System (SPK) to determine the acceptance of the house rehab program for residents with livable housing conditions based on computer information systems. This final project research aims to build a decision-making information system for home rehabilitation recipients using the Weighted Sum Model (WSM) method in Bira Lhok Village, Montasik District. The system development method used is the SDLC (Software Development Life Cycle) method using PHP and MySQL programming. The final project research resulted in a decision making information system for home rehabilitation recipients using the web-based Weighted Sum Model (WSM) with a factor weighting form interface, a form for prospective beneficiaries, a form for income criteria, assets, food and buildings, as well as a report on the assessment list of prospective recipients of rehabilitation assistance. House. Based on the results of the system that was built, the presence of an information system for decision making for home rehabilitation recipients using the Weighted Sum Model (WSM) method has made it easier for the Gampong Bira Lhok government to make decisions for recipients of home rehabilitation assistance quickly.

A Decision-Making Model for Self-Driving Vehicles Based on Overtaking Frequency

The driving state of a self-driving vehicle represents an important component in the self-driving decision system. To ensure the safe and efficient driving state of a self-driving vehicle, the driving state of the self-driving vehicle needs to be evaluated quantitatively. In this paper, a driving state assessment method for the decision system of self-driving vehicles is proposed. First, a self-driving vehicle and surrounding vehicles are compared in terms of the overtaking frequency (OTF), and an OTF-based driving state evaluation algorithm is proposed considering the future driving efficiency. Next, a decision model based on the deep deterministic policy gradient (DDPG) algorithm and the proposed method is designed, and the driving state assessment method is integrated with the existing time-to-collision (TTC) and minimum safe distance. In addition, the reward function and multiple driving scenarios are designed so that the most efficient driving strategy at the current moment can be determined by optimal search under the condition of ensuring safety. Finally, the proposed decision model is verified by simulations in four three-lane highway scenarios. The simulation results show that the proposed decision model that integrates the self-driving vehicle driving state assessment method can help self-driving vehicles to drive safely and to maintain good maneuverability.

Health-Related Parameters for Evaluation Methodologies of Human Operators in Industry: A Systematic Literature Review

Human factors have always been an important part of research in industry, but more recently the idea of sustainable development has attracted considerable interest for manufacturing companies and management practitioners. Incorporating human factors into a decision system is a difficult challenge for manufacturing companies because the data related to human factors are difficult to sense and integrate into the decision-making processes. Our objectives with this review are to propose an overview of the different methods to measure human factors, of the solutions to reduce the occupational strain for workers and of the technical solutions to integrate these measures and solutions into a complex industrial decision system. The Scopus database was systematically searched for works from 2014 to 2021 that describe some aspects of human factors in industry. We categorized these works into three different classes, representing the specificity of the studied human factor. This review aims to show the main differences between the approaches of short-term fatigue, long-term physical strain and psychosocial risks. Long-term physical strain is the subject that concentrates the most research efforts, mainly with physical and simulation techniques to highlight physical constraints at work. Short-term fatigue and psychosocial constraints have become a growing concern in industry due to new technologies that increase the requirements of cognitive activities of workers. Human factors are taking an important place in the sustainable development of industry, in order to ameliorate working conditions. However, vigilance is required because health-related data creation and exploitation are sensible for the integrity and privacy of workers.

Smart Homes as Enablers for Depression Pre-Diagnosis Using PHQ-9 on HMI through Fuzzy Logic Decision System

Depression is a common mental illness characterized by sadness, lack of interest, or pleasure. According to the DSM-5, there are nine symptoms, from which an individual must present 4 or 5 in the last two weeks to fulfill the diagnosis criteria of depression. Nevertheless, the common methods that health care professionals use to assess and monitor depression symptoms are face-to-face questionnaires leading to time-consuming or expensive methods. On the other hand, smart homes can monitor householders’ health through smart devices such as smartphones, wearables, cameras, or voice assistants connected to the home. Although the depression disorders at smart homes are commonly oriented to the senior sector, depression affects all of us. Therefore, even though an expert needs to diagnose the depression disorder, questionnaires as the PHQ-9 help spot any depressive symptomatology as a pre-diagnosis. Thus, this paper proposes a three-step framework; the first step assesses the nine questions to the end-user through ALEXA or a gamified HMI. Then, a fuzzy logic decision system considers three actions based on the nine responses. Finally, the last step considers these three actions: continue monitoring through Alexa and the HMI, suggest specialist referral, and mandatory specialist referral.

Optimal Combination of Multivariate Filter Feature Selection and Classifier for Speech-Based Depression Detection

In this paper, we have focused to improve the performance of a speech-based uni-modal depression detection system, which is non-invasive, involves low cost and computation time in comparison to multi-modal systems. The performance of a decision system mainly depends on the choice of feature selection method and the classifier. We have investigated the combination of four well-known multivariate filter methods (minimum Redundancy Maximum Relevance, Scatter Ratio, Mahalanobis Distance, Fast Correlation Based feature selection) and four well-known classifiers (k-Nearest Neighbour, Linear Discriminant classifier, Decision Tree, Support Vector Machine) to obtain a minimal set of relevant and non-redundant features to improve the performance. This will speed up the acquisition of features from speech and build the decision system with low cost and complexity. Experimental results on the high and low-level features of recent work on the DAICWOZ dataset demonstrate the superior performance of the combination of Scatter Ratio and LDC as well as that of Mahalanobis Distance and LDC, in comparison to other combinations and existing speech-based depression results, for both gender independent and gender-based studies. Further, these combinations have also outperformed a few multimodal systems. It was noted that low-level features are more discriminatory and provide a better f1 score.

Covering Rough Set Based Incremental Feature Selection for Mixed Decision System

Covering rough sets conceptualize different types of features with their respective generated coverings. By integrating these coverings into a single covering, covering rough set based feature selection finds valuable features from a mixed decision system with symbolic, real-valued, missing-valued, and set-valued features. Existing approaches to covering rough set based feature selection, however, are intractable to handle large mixed data. Therefore, an efficient strategy of incremental feature selection is proposed by presenting a mixed data set in sample subsets one after another. Once a new sample subset comes in, the relative discernible relation of each feature is updated to disclose incremental feature selection scheme that decides the strategies of increasing informative features and removing redundant features. The incremental scheme is applied to establish two incremental feature selection algorithms from large or dynamic mixed datasets. The first algorithm updates the feature subset upon the sequent arrival of sample subsets, and returns the reduct when no further sample subsets are obtained. The second one merely updates the relative discernible relations, and finds the reduct when no subsets are obtained. Extensive experiments demonstrate that the two proposed incremental algorithms, especially the second one speeds up covering rough set based feature selection without sacrificing too much classification performance.