Design Of Decision Support System Research Articles

Design of an efficient decision support system using evolutionary deep forward network model

With the vast advancements in the medical domain, earlier prediction of disease plays a substantial role in enhancing healthcare quality and making better decisions during tough times. This research concentrates on modelling and automated disease prediction model to offer an earlier prediction model for heart disease and the risk factors. This work considers a standard UCI machine learning-based benchmark dataset for model validation and extracts the risk factors related to the disease. The outliers and imbalanced datasets are pre-processed using data normalization to enhance the classification performance. Here, feature selection is performed using non-linear Particle Swarm Optimization (NL - PSO). Finally, classification is done with the Improved Deep Evolutionary model with Feed Forward Neural Networks (IDEBDFN). The algorithm’s learning nature is used to evaluate the nature of the hidden layers to produce the optimal results. The outcomes demonstrate that the anticipated model provides superior prediction accuracy. The simulation is carried out in a MATLAB environment, and metrics like accuracy, F-measure, precision, recall, and so on are evaluated. The accuracy (without features) of the evolutionary model in the UCI ML dataset is 97.65%, accuracy (with features) is 98.56%, specificity is 95%, specificity is 2% higher than both the datasets, F1-score is 40%, execution time (min) is 0.04 min, and the AUROC is 96.85% which is substantially higher than other datasets. The proposed model works efficiently compared to various prevailing standards and individual approaches.

Decision Support System Design for Informatics Student Final Projects Using C4.5 Algorithm

Academic consultation activities between students and academic supervisors are necessary to help students carry out academic activities. Based on the transcript of grades obtained, many students do not choose the appropriate final project/thesis specialization fields based on their academic abilities, resulting in a lot of inconsistencies between the course grades and the final project specialization fields. The purpose of this research is to minimize the subjectivity aspect of students in choosing their final project academic supervisors and minimize the inconsistencies between the course grades and the final project specialization fields. The method used in this research is classification data mining using the Decision Tree and C4.5 Algorithm methods, with the attributes involved being courses, course grades, and specialization courses. The C4.5 Decision Tree algorithm is used to transform data (tables) into a tree model and then convert the tree model into rules. The implementation of the C4.5 Decision Tree algorithm in the specialization field decision support system has been successfully carried out, with an accuracy rate of 70% from the total calculation data. The data used in this research is a sample data from several senior students in the Informatics program at Ubhara-Jaya. The results of the research decision support system can be used as a good recommendation for the Informatics program and senior students to direct their final project research. It is expected that further research will use more sample data so that the accuracy rate will be better and can be implemented in website or mobile-based applications.

TOWARDS INFORMED DESIGN DECISION SUPPORT OF ADDITIVE MANUFACTURING IN CONSTRUCTION - THE USE OF INTEGRATED KNOWLEDGE IN BIM-BASED ARCHITECTURAL DESIGN

Additive Manufacturing (AM) technologies have great potential to promote sustainable development in the architecture, engineering, and construction (AEC) domain. But the inherent complexity of AM and lack of domain knowledge hinder decisions about appropriate construction methods. With state-of-the-art Semantic Web technologies, a knowledge base regarding AM technologies can be formalized and integrated into the Building Information Modeling (BIM) methodology. To this end, this paper demonstrates how a Design Decision Support System (DDSS) utilizes formal knowledge to assist architects in choosing the appropriate AM method by assessing the manufacturability of individual building components. By following and refining the essential activities described, we aim to provide architects with informed decision support, thus facilitating the versatile use of AM technologies in the AEC domain.

Decision Support System Design and Development for Determine Graduate Phase of College Students with Naïve Bayes Algorithm Web-Based in Indonesia Institute of Business and Technology

In the course of the lecture period, each student is different, various factors can affect the mental and academic achievement of students which have an impact on their graduation period. This things also impact on the campus of the Indonesian Institute of Business and Technology, until now there is no system that can determine the graduation period of students at the campus, therefore it is necessary to build a decision support system to determine the graduation period of students, especially students in the Informatics Engineering Study Program and Program Study of Computer Systems at the Indonesian Institute of Business and Technology (INSTIKI) using the Naïve Bayes algorithm that utilizes parameters, namely student academic data consisting of work status, Semester Achievement Index (IPS) scores semesters one untill four, and Grade Point Average (IPK). The system designed by using the GaussianNB library in python and website based. From the results of this study, the accuracy of the model made on the system produces an accuracy value of 87.5% with a dataset rule of 800 data and the data is divided and used as test data by 20%, while the accuracy value of classifying 250 test data on the system is 80.8%.

Design and Conceptual Proposal of an Intelligent Clinical Decision Support System for the Diagnosis of Suspicious Obstructive Sleep Apnea Patients from Health Profile

Obstructive Sleep Apnea (OSA) is a chronic sleep-related pathology characterized by recurrent episodes of total or partial obstruction of the upper airways during sleep. It entails a high impact on the health and quality of life of patients, affecting more than one thousand million people worldwide, which has resulted in an important public health concern in recent years. The usual diagnosis involves performing a sleep test, cardiorespiratory polygraphy, or polysomnography, which allows characterizing the pathology and assessing its severity. However, this procedure cannot be used on a massive scale in general screening studies of the population because of its execution and implementation costs; therefore, causing an increase in waiting lists which would negatively affect the health of the affected patients. Additionally, the symptoms shown by these patients are often unspecific, as well as appealing to the general population (excessive somnolence, snoring, etc.), causing many potential cases to be referred for a sleep study when in reality are not suffering from OSA. This paper proposes a novel intelligent clinical decision support system to be applied to the diagnosis of OSA that can be used in early outpatient stages, quickly, easily, and safely, when a suspicious OSA patient attends the consultation. Starting from information related to the patient's health profile (anthropometric data, habits, comorbidities, or medications taken), the system is capable of determining different alert levels of suffering from sleep apnea associated with different apnea-hypopnea index (AHI) levels to be studied. To that end, a series of automatic learning algorithms are deployed that, working concurrently, together with a corrective approach based on the use of an Adaptive Neuro-Based Fuzzy Inference System (ANFIS) and a specific heuristic algorithm, allow the calculation of a series of labels associated with the different levels of AHI previously indicated. For the initial software implementation, a data set with 4600 patients from the Álvaro Cunqueiro Hospital in Vigo was used. The results obtained after performing the proof tests determined ROC curves with AUC values in the range 0.8-0.9, and Matthews correlation coefficient values close to 0.6, with high success rates. This points to its potential use as a support tool for the diagnostic process, not only from the point of view of improving the quality of the services provided, but also from the best use of hospital resources and the consequent savings in terms of costs and time.

Optimization of Tree-Based Machine Learning Models to Predict the Length of Hospital Stay Using Genetic Algorithm.

The length of hospital stay (LOS) is a significant indicator of the quality of patient care, hospital efficiency, and operational resilience. Considering the importance of LOS in hospital resource management, this research aims to improve the accuracy of LOS prediction using hyperparameter optimization (HPO). Expert physicians and related studies were reviewed to determine the variables affecting LOS. The electronic medical records of 200 patients in the department of internal medicine of a hospital in Iran were collected randomly. As the performance of machine learning (ML) models can vary based on the characteristics of the features, several models were applied and evaluated in this study. In particular, k-nearest neighbors (KNN), multivariate regression, decision tree (DT), random forest (RF), artificial neural network (ANN), and XGBoost have been evaluated and improved. The genetic algorithm (GA) was applied to optimize the tree-based models. In addition, the dummy coding technique, sometimes called the One-Hot encoding, was used to encode categorical features to increase prediction accuracy. Compared with other algorithms, the XGBoost model optimized by GA (XGB_GA) achieved higher accuracy and better prediction performance. The mean and median of absolute errors in the test dataset for this model were 1.54 and 1.14 days, respectively. In other words, the XGB_GA model reduced the mean absolute error by 37%, which is beneficial in the reliable design of a clinical decision support system.

Design, implementation, and evaluation of the computer-aided clinical decision support system based on learning-to-rank: collaboration between physicians and machine learning in the differential diagnosis process

BackgroundWe are researching, developing, and publishing the clinical decision support system based on learning-to-rank. The main objectives are (1) To support for differential diagnoses performed by internists and general practitioners and (2) To prevent diagnostic errors made by physicians. The main features are that “A physician inputs a patient's symptoms, findings, and test results to the system, and the system outputs a ranking list of possible diseases”.MethodThe software libraries for machine learning and artificial intelligence are TensorFlow and TensorFlow Ranking. The prediction algorithm is Learning-to-Rank with the listwise approach. The ranking metric is normalized discounted cumulative gain (NDCG). The loss functions are Approximate NDCG (A-NDCG). We evaluated the machine learning performance on k-fold cross-validation. We evaluated the differential diagnosis performance with validated cases.ResultsThe machine learning performance of our system was much higher than that of the conventional system. The differential diagnosis performance of our system was much higher than that of the conventional system. We have shown that the clinical decision support system prevents physicians' diagnostic errors due to confirmation bias.ConclusionsWe have demonstrated that the clinical decision support system is useful for supporting differential diagnoses and preventing diagnostic errors. We propose that differential diagnosis by physicians and learning-to-rank by machine has a high affinity. We found that information retrieval and clinical decision support systems have much in common (Target data, learning-to-rank, etc.). We propose that Clinical Decision Support Systems have the potential to support: (1) recall of rare diseases, (2) differential diagnoses for difficult-to-diagnoses cases, and (3) prevention of diagnostic errors. Our system can potentially evolve into an explainable clinical decision support system.

An Interactive Decision Support System for College Degree Planning

Many students in the Unites States enter college without having decided on a focus for their studies, and thus are faced with choosing from a large number of potential majors and associated very complex sets of degree requirements which can include many courses in other areas of study. Academic advisors use academic planning tools to help students make decisions about class schedules, selecting an academic major or minor, planning for graduation, and many other academic related activities. There is a dearth of decision support systems for degree planning, mainly due to the complexity of degree requirements, and thus many existing academic planning tools utilize static documents or PDF files for displaying information pertaining to degree requirements and course prerequisites. This work considers the complexity of degree requirements and presents the design and implementation of an efficient interactive decision support system that helps students explore degree completion paths. Keywords: degree planning, academic advising, academic decision making, decision support system, college degree planning

The Expert System Supporting Decision-Making in the Process of Vegetable Pests Extermination During Vegetation Period

Abstract The paper presents a computer system supporting the identification of vegetable pests during the vegetation period and the way in which it works on the example of red beet. The objective was to develop an expert system to facilitate the identification of pests and suggest an appropriate method of controlling them. Filling the database with the knowledge applying to one narrow area of knowledge turns the expert system framework into an expert system in this area of knowledge. The system consists of the expert system and the database in the form of text files, which contain additional explanations. The user of the expert system - “DSS – pest control” needs to answer the following questions: in the first stage the user selects the diagnosed vegetable, in the second stage, the user selects the symptom or symptoms on the above-ground vegetable part, in the third stage, the user selects the symptom or symptoms on the below-ground vegetable part. The designed decision support system (“DSS – pest control”) may be used by individual vegetable growers. It may also serve as an educational program, e.g. for students who want to find out more about the specific areas of knowledge as well as for scientists and researchers.

Design of intelligent decision support system for supply chain sustainability assessment

The objective of this research is to develop an intelligent decision support system (IDSS) that can aid decision-makers in enhancing the performance and sustainability of the sugarcane agroindustry's supply chain. A case study focusing on a sugarcane agroindustry supply chain was proposed. The IDSS was developed using the waterfall approach, which follows the system development life cycle (SDLC) and employed an object-oriented programming technique. The outcome of this study is a prototype of the IDSS, consisting of a database, model base, and knowledge-based management system configuration. To evaluate the sustainability of the supply chain, a fuzzy inference system and an adaptive fuzzy inference system algorithm were utilized. Through verification and validation, it was determined that the IDSS prototype has the potential to be implemented in real-world scenarios, as long as certain assumptions related to the model are taken into consideration.

User-centred design of a clinical decision support system for palliative care: Insights from healthcare professionals.

Although clinical decision support systems (CDSS) have many benefits for clinical practice, they also have several barriers to their acceptance by professionals. Our objective in this study was to design and validate The Aleph palliative care (PC) CDSS through a user-centred method, considering the predictions of the artificial intelligence (AI) core, usability and user experience (UX). We performed two rounds of individual evaluation sessions with potential users. Each session included a model evaluation, a task test and a usability and UX assessment. The machine learning (ML) predictive models outperformed the participants in the three predictive tasks. System Usability Scale (SUS) reported 62.7 ± 14.1 and 65 ± 26.2 on a 100-point rating scale for both rounds, respectively, while User Experience Questionnaire - Short Version (UEQ-S) scores were 1.42 and 1.5 on the -3 to 3 scale. The think-aloud method and including the UX dimension helped us to identify most of the workflow implementation issues. The system has good UX hedonic qualities; participants were interested in the tool and responded positively to it. Performance regarding usability was modest but acceptable.

Communication architecture for real-time decision support systems in railway nodes

Rail transport nodes are complex systems providing transport for goods and people. The dispatcher providing operational control is essential for the proper functioning of these nodes. His role mainly consists of decision-making connected with the allocation of limited resources such as tracks or personnel. These decisions are complicated because of many unexpected influences, e.g., train delays. Recognizing the importance of decision support for the dispatcher's decision-making process, we had designed a real-time decision support system with a simulation model at its core. Such a system requires a high-quality information source for its operation, that needs to be efficiently acquired, processed, and used. In this paper, therefore, we address the possibilities of obtaining up-to-date information about the railway system. Moreover, we designed a communication architecture that allows the distribution of information to the designed decision support system with a simulation model in the core.

Spatial Data Warehouse Modeling at the Watershed Scale. Part 1: Design Aspects

Gathering, analyzing and synthesizing large and complex sets of hydraulic, terrestrial, atmospheric, biological and socio-economic data are critical for any decision making process in the water sector. This paper aims to propose a practical approach for increasing the effectiveness of sustainable management of water resources within Integrated Water Resources Management (IWRM) framework and climate change context. The article advocates that the designed Decision Support System (DSS) is a prerequisite in proper IWRM. In fact, it offers a dedicated management system, to assist decision makers and policy makers of water in providing timely, well informed and reproducible answers to important questions, as well as transforming data into knowledge and understandable results through innovative techniques. However, to provide a Decision Support System allowing both access to geographic data needed for IWRM and steering business processes through reliable indicators, it is imperative that the system must be able to combine the geographic information system technology with Business Intelligence, so called Geo-BI (Geo-Business Intelligence). To this end, this paper presents a study that revolves around the concept of Geo-BI and aims to model a Multidimensional Decision Support System, which is a part of an extensive process of spatial data warehouse construction.

Особенности предоставления финансовой поддержки субъектам малого бизнеса рыбной отрасли с использованием продукционной модели базы знаний

The article highlights the procedure of selecting applications for state financial support for small businesses in the fishing industry. Criteria for expert evaluation of applications have been defined taking into account industry specifics and including the following blocks: “Compliance with formal requirements”, “Type of activity”, “Justification of the requested funding”, “Socio-economic contribution to the region”. The principles of developing the evaluation criteria are generalized. The examination procedure algorithm taking into account the observance of formal requirements at the first stage of the expertise has been worked out. The algorithm provides for the functionality of clarifying the type of activity and conducting assessment according to the relevant criteria. Aggregated indicators of expert assessments reduced to a linguistic description “high”, “medium”, “low” are obtained. The system of trapezoidal membership functions on the 01-carrier (five-factor 01-classifier) is illustrated. The applicability of fuzzy logic tools for the tasks of multi-criteria assessment and management decision-making is substantiated. A base of rules for fuzzy production has been developed, consisting of 9 rules and a set of management decisions on financial support. The implementation of the decision-making procedure as a fuzzy production model built on using FuzzyLogicToolbox is shown. The conclusion about the possibility of using the results in the design of intelligent decision support systems in the field of financing small and medium-sized businesses in the fishing industry is made. It has been stated that the fuzzy production system and the expert evaluation algorithm can be projected onto other branches of the national economy as a result of the configuration of the constituent elements.

IMPLEMENTATION OF THE MULTIFACTOR EVALUATION PROCESS METHOD FOR THE ELIGIBILITY OF PROVIDING ADVANCED TEACHER PROFESSIONAL ALLOWANCES AT THE EDUCATION OFFICE OF ASAHAN REGENCY

The teacher certification program is a way to improve the quality of teachers so that the quality of education is increasing. Where the performance appraisal process for each certification teacher is carried out every six months, namely by providing a report that is assessed by the teacher certification/standardization worker team, where the teacher performance appraisal report is still carried out in file collection and archived so as to allow for inaccuracies in the data and values ​​given so that it This will affect the selection of teacher certification eligibility. The method used in this research is the MFEP method which is one of the methods of decision support systems. This method was chosen because it is more efficient than other methods included in the completion of Multi Attribute Decision Making (MADM). Utilization of MFEP requires a relatively shorter calculation time. Based on this, in selecting the feasibility of providing teacher professional allowances or teacher certification, it is necessary to build a decision support system design for the feasibility of providing advanced teacher professional allowances at the Asahan District Education Office. The results obtained are the highest preference score of 4,435 named Siti Khairani Butar-Butar and the results of the system implementation can help performance in the selection of certification teachers. So it can be concluded that this system can provide convenience in obtaining assessment results effectively on a decision support system for the feasibility of providing advanced teacher professional allowances at the Asahan District Education Office.

Sistem Pendukung Keputusan Penilaian Kinerja Guru Dengan Metode Saw Pada Man 2 Tebo

MAN 2 Tebo is a high school under the auspices of the Ministry of Religion which is engaged in the field of Religion and Education. The development of a madrasa is determined by the number of students who register at the madrasa, of course with this increase it requires teachers who are competent and perform well in teaching. To improve good performance, of course, through teacher performance assessment, it is a very important thing in an educational institution. In this case, the process of assessing teacher performance is only limited to an assessment system for periodic salary and rank increases and there is no appreciation in terms of teacher performance appraisal. This is what causes the teacher to be a little unmotivated in performance. Therefore, based on these conditions, a teacher performance appraisal decision support system is needed that helps the head of madrasah in assessing teacher performance based on existing criteria. So the final result of this research is the design of a teacher performance appraisal decision support system with the SAW method which aims to facilitate decision making in determining teacher performance accurately and consistently.

A Decision Support System Based on Neural Network and Genetic Algorithm: Case Study of Breast Cancer

Introduction: Artificial intelligence has been changing the way healthcare has been provided in many high-risk environments or areas with poor healthcare facilities. The emergence of epidemics and new diseases, as well as the crucial role of early diagnosis in prevention and the adoption of more effective treatments have highlighted the need for accurate design and self-organization of Clinical Decision Support Systems (CDSSs).Material and Methods: In this study, a CDSS based on a neural networks (NN) and genetic algorithm is proposed. Since, on the one hand, the performance of the neural network (NN) is highly dependent on its parameters, and on the other hand, there is a constant need for optimization experts to fine-tune the parameters in the use of new data, a new chromosomal structure is proposed to automatically extract the optimal NN architecture, the number of layers and neurons. The goal is to increase the reusability of the model and ease of use by health experts.Results: To evaluate the performance of the model, two standard breast cancer (BC) datasets, WBC and WDBC, were used. The model uses 70% of the data set for training and the remaining equally used for evaluation and testing. The test accuracy of the proposed model on WBC and WDBC datasets was 98.51 and 97.55%, respectively. The optimal NN architecture on WBC consisted a three-hidden layers with 18, 15 and 19 neurons in each layers, and on WDBC consisted one hidden layer with a single neuron.Conclusion: The proposed chromosomal structure is able to derive optimal NN architecture. In according to the high classification accuracy of the model in the diagnosis of BC and providing the different architectures in accordance with the hardware implementation considerations, the proposed model can be used effectively in the diagnosis of other diseases.

Integrated framework of knowledge-based decision support system for user-centered residential design

A user-oriented residential environment is considered essential to providing occupants with a comfortable living experience while meeting their demands. However, design assessment in the early stage of residential design is a complex problem due to multifactor coupling, the diversity in user needs, and the incompleteness of design knowledge. This study proposes an integrated framework of knowledge-based decision support system (KBDSS) to mitigate such problems. In this framework, the user segmentation is performed in accordance with people’s particular requirements priority and, thus, enables design decisions that create better satisfaction among a wider audience. Meanwhile, the quality function deployment approach, decision support system, and fuzzy set theory are used to translate user requirements into quantifiable design specifications, thereby making the design a multicriteria decision-making problem. To illustrate and validate the proposed framework, a case study of a KBDSS for a multiunit residential building kitchen design is demonstrated to explore a user-centered residential design with such decision support. This proposed framework provides naive design practitioners with specific knowledge about decision problems and assists them in consistently making user-centered design decisions. The research results represent a further step toward a systematic methodology of user-centered built environment design.

Dark cities or cities of light? – sunlight amenity preservation at whole-city scale using a spatio-temporal decision support approach

Public open spaces are fundamentally important for the health and well-being of citizens in densely populated cities. If not carefully planned, high-density urban development can overshadow adjacent open spaces, resulting in poor quality, dark and oppressive winter conditions. Current planning control approaches for protecting light amenity in cities are often limited to simple overshadowing impact diagrams (e.g. shadows cast on the equinox at 9 a.m., 12 p.m. and 3 p.m.). In cities transitioning from low to higher density, comprising more complex urban forms and more extreme seasonal light amenity dynamics, these static approaches are insufficient. This paper outlines the development of a spatio-temporal design decision support system for analysing and protecting the light amenity of public open spaces, applied to a capital city in Australia. The system described has two parts: Firstly, to assess the overshadowing of existing public open spaces and identify those in need of protection (Part A), and secondly to generate planning restrictions to protect designated open spaces from future deprivation of light (Part B). For Part A, we use a graphics processing unit accelerated aggregate-shadow (15 minute increments) calculation applied to a detailed city-wide 3D model generated from billions of points of aerial survey (LiDAR) data. For Part B, we use a reversed solar ray casting approach we call the ‘Subtracto-Sun’ which allows a user to specify a time range (e.g. 9 a.m.–4 p.m.) for multiple days of the year and subsequent generation of 3D maximum building height development envelopes. The output of this system was used by the local government to inform a proposed planning policy amendment for the City of Melbourne. The findings illustrate the potential for urban professionals to use the system to rapidly assess shadow impacts for existing and proposed, contextually accurate, large, complex urban environments with high levels of geometric and temporal details. The presented results are significant in that we develop and apply our spatio-temporal decision-support approach to a local government area, successfully informing planning height restriction decisions to protect daylight amenity of public open spaces in need of protection. Our method for setting development height restrictions allows for higher density to be achieved, while not increasing the overshadowing of critical open space infrastructure during designated times.

Усовершенствование ситуационной методологии разработки систем поддержки принятия решений для предприятий

The article proposes a technique for the development of a situational methodology for the development of decision support systems for organizational systems, taking into account the influence of the time factor. In the existing methodologies, insufficient attention is paid to the links between the organizational part of the model and the parametric method, with the help of which the choice of an acceptable solution is made, the assessment of the consequences of the decisions made is often ignored, and the application of these methodologies to solving practical problems is difficult. The main purpose of the article is to summarize the existing approaches to decision making based on an improved methodology for developing decision support systems, which is aimed at eliminating the identified problems. To achieve the goal, systemic and situational approaches, ontological engineering, structural analysis of systems, and methods for classifying complex objects were used. As a result, proposals were formed to improve the situational approach to creating decision support systems, including the definition of a hierarchy of decision-making process components, descriptions of transition methods between decision-making levels, with an emphasis on the level of choice of a parametric method for transforming a set of decision options into effective solution. The article concludes that the proposed methodology will simplify the process of designing decision support systems for enterprises.