Suitable Decision Research Articles

An IoT enabled smart healthcare system using deep reinforcement learning

AbstractSmart healthcare systems do exist with a variety of architectures. However, the hunt for better smart healthcare systems is more predominant. The cutting‐edge field of IoT (internet of things) and technological developments provide better solutions for smart healthcare systems using Sensor–Body Area Networks. Thus, the patient's sensor data can be collected, stored, analyzed, and suitable treatments can be offered, over the inter‐network, anytime, anywhere. The most complex part in such systems is the physician analysis of the huge volume of patient's data, to handle and prepare suitable diagnose and treatment for humanity. This article reveals a methodology of Deep Reinforcement Learning for smart healthcare decisions in an IoT interfaced Smart Healthcare–intelligent monitoring system. The system incorporates four layers, patient data collection, Edge computing, patient data transmission and Cloud computing. IoT is employed for automatic collection of Patient's data and for transmission of data, to data centers. Artificial intelligence techniques are used to analyze these data to provide suitable decisions, diagnosis, and treatment for those patients and humanity. Deep Reinforcement Learning provides the platform for smart decisions, diagnosis, and treatment. The investigation was experimented with synthetic simulated data of various BAN sensors. We developed a data set of size 286, which contains 21 different health parameters. After pre‐processing, these data were stored in the Amazon web services (AWS) cloud server using (message queue telemetry and transport) MQTT–IoT protocol. Initially, the Deep Q‐Network (DQN) was imposed to the training algorithm. The methodology was examined in PyTorch using a single GTX 1080 Ti X GPU with the training data sizes from 27 to 1536. The training time was about 10,000 to 90,000 s for training 500 epochs. In the high dimensional action space environment, the algorithm responded slowly to analyze, explore, and determine effective healthcare strategies. The systems convergence response of estimated hidden health state (g') and the actual health state (g) for the 21 different health parameters were estimated, whose values range from 0 to 1. The system responded with smart decisive interventions, which were good and close to that of a Physician's decision. The proposed methodology is definitely a promising solution for a smart and economic telemedicine.

Public Health Decision Making in the Case of the Use of a Nuclear Weapon.

The current geopolitical situation and the war on Ukraine’s territory generate questions about the possible use of a nuclear weapon and create the need to refresh emergency protective plans for the population. Ensuring the protection of public health is a national responsibility, but the problem is of international size and global scale. Radiological or nuclear disasters need suitable decision making at the right time, which determine large effective radiation protection activities to ensure public health is protected, reduce fatalities, radiation disease, and other effects. In this study, a simulation of a single nuclear weapon detonation with an explosion yield of 0.3 and 1 Mt was applied for a hypothetical location, to indicate the required decision making and the need to trigger protocols for the protection of the population. The simulated explosion was located in a city center, in a European country, for the estimation of the size of the effects of the explosion and its consequences for public health. Based on the simulation results and knowledge obtained from historical nuclear events, practical suggestions, discussion, a review of the recommendations was conducted, exacerbated by the time constraints of a public health emergency. Making science-based decisions should encompass clear procedures with specific activities triggered immediately based on confirmed information, acquired from active or/and passive warning systems and radiometric specific analysis provided by authorized laboratories. This study has the potential to support the preparedness of decision makers in the event of a disaster or crisis-related emergency for population health management and summarizes the strengths and weaknesses of the current ability to respond.

How to adopt mass customization strategy: Understanding the role of consumers’ perceived brand value

How to make a suitable decision by balancing the benefits and costs of Mass customization (MC) has been widely discussed by scholars. While with the development of information and production technology, some traditional factors that affect firms’ MC decisions have significantly changed. Meanwhile, consumers’ brand recognition is playing an increasingly important role in consumers’ purchase decisions. Motivated by the new conditions, we develop an analytical model to investigate how a firm’s MC decisions are affected by consumers’ perceived brand value and customization cost. The solution of the benchmark model shows that (i) if brand loss outweighs maximal travel cost, the firm generally abandons MC even if MC is costless; (ii) the firm is more likely to adopt MC when the impact of MC on perceived brand value is positive; (iii) a higher customization level may not imply a higher price, but the firm always obtains higher profit with the increase of customization level, and (iv) the implementation of MC may derive an economically inefficient situation. As an extension, we consider a scenario where consumers have heterogeneous attitudes toward the impact of MC on brand value and find that: (i) the main conclusions in the benchmark model are still valid; and (ii) consumers’ heterogeneous attitudes toward brand value can benefit themselves.

An integer programming mathematical model with line balancing and scheduling for standard work optimization: A realistic application to aircraft engines assembly lines

Aircraft Engine Maintenance Repair and Overhaul (MRO) companies face intense global competition that requires effective management of maintenance costs, TAT (turnaround time), and accurate job standards. These indicators can be improved through methodologies such as line balancing and scheduling of assembly tasks. The main objective of this article is to propose models for standard work definition that can optimize companies’ indicators – TAT, the number of operators, training costs, and load balancing – considering the specificities of the aircraft engine assembly lines. First, a literature review identified features of line balancing and scheduling integrated problems relevant to aircraft engine assembly and highlighted the integer programming mathematical models already proposed. Second, four new MILP models were developed in order to combine some of the features identified during the literature review and include new relevant ones: the multi-skilled operators can work in more than one engine per takt time, and each task may start in one takt time, and finish in the next. Lastly, the models were implemented in the AIMMS system and hierarchically solved by the CPLEX on data of two different assembly lines from a Brazilian MRO company. The results were considerably better than those obtained empirically by the firm. They include a 14.3% reduction in TAT for one assembly line and a 15.4% reduction in the number of operators for another, confirming a suitable decision support tool for the company, which can also help other firms.

Mathematical modeling and AI based decision making for COVID-19 suspects backed by novel distance and similarity measures on plithogenic hypersoft sets

It goes without saying that coronavirus (COVID-19) is an infectious disease and many countries are coping with its different variants. Owing to the limited medical facilities, vaccine and medical experts, need of the hour is to intelligently tackle its spread by making artificial intelligence (AI) based smart decisions for COVID-19 suspects who develop different symptoms and they are kept under observation and monitored to see the severity of the symptoms. The target of this study is to analyze COVID-19 suspects data and detect whether a suspect is a COVID-19 patient or not, and if yes, then to what extent, so that a suitable decision can be made. The decision can be categorized such that an infected person can be isolated or quarantined at home or at a facilitation center or the person can be sent to the hospital for the treatment. This target is achieved by designing a mathematical model of COVID-19 suspects in the form of a multi-criteria decision making (MCDM) model and a novel AI based technique is devised and implemented with the help of newly developed plithogenic distance and similarity measures in fuzzy environment. All findings are depicted graphically for a clear understanding and to provide an insight of the necessity and effectiveness of the proposed method. The concept and results of the proposed technique make it suitable for implementation in machine learning, deep learning, pattern recognition etc.

A data-driven approach for the optimization of future two-level hydrogen supply network design with stochastic demand under carbon regulations

Reducing emission of conventional vehicle exhaust has many benefits for developing low-carbon cities. The transition from on-road conventional passenger cars to Hydrogen Fuel Cell Vehicles (HFCVs) may enhance air quality and health significantly. Aiming at constructing low-cost and environmentally friendly hydrogen supply networks (HSNs) in urban areas, a basic model that considers hydrogen plant and refueling station decisions is presented for the Two-level Hydrogen Supply Network Design (THSND) with stochastic demand. By coupling the basic model and carbon regulations, four extended models are established to evaluate carbon reduction on total cost of HSNs. A data-driven approach that does not require the full information of target areas is developed to solve the models. It introduces a data acquisition method of Points of Interests (POIs), a clustering-based method to select alternative refueling stations, a trip simulation method to determine demand uncertainty, and the application of solvers. The developed data-driven approach is shown to be robust and effective in terms of applicability and generalizability according to the simulations. Meanwhile, the best suitable decision result on plants and stations is both cost-effective and environmentally successful under the model considering carbon cap and trade. The internal relationship between the models indicates that the hybrid carbon emission policy is superior to naive carbon regulations.

Prediction of Nurses Allotment to Patient in Hospital through Game Theory

Allotment of nurses to patients is a critical task in terms of better treatment. Nurses should be appointed according to a patient's health condition, type of disease, and financial condition. Again, understaffing of nurses may hamper patient health and condition. Similarly, overstaffing of nurses is a waste of manpower. Adequate staffing of nurses is crucial. The authors propose a technique using game theory to meet overstaffing and understaffing of nurses. Game theory plays a vital role to meet the exact requirement. Nash equilibrium can be used for taking all possible decisions, like appointment of nurses in different categories for smooth treatment of patients. However, the final and most suitable decision can be taken using perfect Nash equilibrium. This technique is a perfect technique to implement in case of vital and critical decision points.

Economic Adaptation of Refugees in Algeria: A Comparative Study of Syrian and Malian Emigrants’

This study aims to compare the economic adaptations of Malian and Syrian emigrants living outside of government shelters in Algeria, and its association with their personal and occupational characteristics. Data were collected using Semi-directed interviews with 127 emigrants living in urban areas for a period of nine months (from April to December 2016). In addition, the analysis is based on the Montgomery model, which includes monthly income, best monthly pay, average hours of work per month, average monthly work per year and the number of appliances they own at home.The results show that emigrants from Syria have higher net wages and incomes, work longer days, and hold more appliances than Malian emigrants. Meanwhile, the number of working months is similar for both. Moreover, the findings indicate that Syrian men are more preferred than Malians at work. In addition, findings reveal that there is no significant difference between genders to obtain a job. According to evidences, Syrian emigrants with low education and self-employment are expected to face difficult economic adaptation. The results should help policy makers to make suitable decisions that push to raise the emigrants’ economic adaptation levels in Algeria.

A Comparative Study: Bank Loan V/S Trade Credit, a Panel Data Approach

Abstract. Non-financial firms have a unique behavior towards trade credit, where they have complicated constraints on bank loans for a developing economy. There is a huge trading governed by the way of trade credit in this ever emerging trade era. Trade credit is a short-term business financing based on purchases between the buyer and the supplier. In almost every field technology has driven trading to the smart, sophisticated ways of businesses. The current study is concerned with some of these factors especially the trade credit system which is beneficial for the small industries of the country. This is helpful in suitable decision making for business schemes, to overcome those factors which causes obstacles in revenue generation in case of lack of availability of funds from banks and other financial institutions. The demand for trade credit serves the best means of short term financing to the financial distressed firms. Financial sectors including banks require the collateral as guarantee however, customer is usually unable to provide any security and suffers from financial discomfort. The interest rates and documentation keeps the burden on the small investors so they move towards other easy sources of funding as trade credit is suitable for same business dealers. Whereas, trade credit serves the short term loan at easy requirements. This facility is helpful for the customer in flexible way as product price and profit is returned after a short time span. Trade credit regulates the business in a smooth way. The method adopted to pursue the research is by using the panel data of Pakistan non-financial SMEs from 2009–2019, it has been analyzed that although the investments of SMEs are restricted by banks, trade credit can maintain the sustainability of enterprises. Private enterprises are more reliant on trade credit, which can be intensified during periods of monetary tightening. The data is also helpful for SME’s having lack of financial support. Due to the long-term nature and information asymmetry, SMEs experience serious financial constraints that affect their business. The methodology used is Generalized Method of Moments (GMM) formalized by Lars Peter Hansen in 1982. GMM is helpful for the problem raised because of the correlation among the independent variables and the error term known as endogeneity as well as the heterogeneity of firms. The results enlighten that trade credit is the simplest and most demanding method to generate finance for the financially distressed firms as compared to the bank loans and other financial sectors. The conclusion states that the short term financing as trade credit is suitable for small investors as compared to the bank loan and other financial institutions

Control Techniques for Safe, Ergonomic, and Efficient Human-Robot Collaboration in the Digital Industry: A Survey

The fourth industrial revolution, also known as Industry 4.0, is reshaping the way individuals live and work while providing a substantial influence on the manufacturing scenario. The key enabling technology that has made Industry 4.0 a concrete reality is without doubt <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">collaborative robotics</i> , which is also evolving as a fundamental pillar of the next revolution, the so-called Industry 5.0. The improvement of employees’ safety and well-being, together with the increase of profitability and productivity, are indeed the main goals of human-robot collaboration (HRC) in the industrial setting. The robotic controller design and the analysis of existing decision and control techniques are crucially needed to develop innovative models and state-of-the-art methodologies for a safe, ergonomic, and efficient HRC. To this aim, this paper presents an accurate review of the most recent and relevant contributions to the related literature, focusing on the control perspective. All the surveyed works are carefully selected and categorized by target (i.e., safety, ergonomics, and efficiency), and then by problem and type of control, in presence or absence of optimization. Finally, the discussion of the achieved results and the analysis of the emerging challenges in this research field are reported, highlighting the identified gaps and the promising future developments in the context of the digital evolution. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Note to Practitioners</i> —The design and development of manufacturing systems are experiencing substantial changes towards full automation. This ongoing challenge is being tackled by academia and industrial practitioners with the adoption of collaborative robots, where the skills and peculiarities of humans (e.g., intelligence, creativity, adaptability, etc.) and robots (e.g., flexibility, pinpoint accuracy, tirelessness, etc.) are combined to better perform a variety of tasks. Nevertheless, due to their different characteristics, there is an emerging need for designing suitable decision and control techniques to ensure a safe and ergonomic HRC, while keeping the highest level of productivity. Against this background, the aim of this paper is to provide researchers and practitioners with a reference source in the related field, which can help them designing and developing suitable solutions to control problems in safe, ergonomic, and efficient collaborative robotics.

조건부 자율주행에서 제어권 전환 시 운전자의 뇌 활성도에 관한 예비연구

Conditional autonomous vehicles should hand over control to the driver according on driving situations. However, if the driver is immersed in a non-driving task, the driver may not be able to make suitable decisions. Previous studies have confirmed that the cues enhance take-over performance with a directional information on driving. However, studies on the effect of take-over cues on the driver

Solar Based Smart Corridor System

Abstract: This paper presents a Solar Based Smart Corridor System. The system provides an automated lighting system and charging circuit. This detection is based on the motion sensor. The whole system is automated by ESP32 microcontroller. Admin can control the lighting system remotely as the controller has a wi-fi module. The goal of a microcontroller is to interface with sub-systemsand provide suitable decisions for efficient working of the system. The system will use solar energy from solar panels to perform its work. In the absence or failure of it, the system will work on a battery which is charged with the help of solar power. In failure of these both the system will work on traditional state electricity supply. This system is made to work on hybrid mode of power supply. To get this system to work efficiently, we have prepared a set of rules. So that entire system will work according to the algorithm developed. So this system uses eco-friendly energy sources with good efficiency. Also, as the system is robust, scaling of the system based on the need of energy required is relatively easy

Estimation of fault probability in medium voltage feeders through calibration techniques in classification models

Machine Learning is currently a well-suited approach widely adopted for solving data-driven problems in predictive maintenance. Data-driven approaches can be used as the main building block in risk-based assessment and analysis tools for Transmission and Distribution System Operators in modern Smart Grids. For this purpose, a suitable Decision Support System should be able of providing not only early warnings, such as the detection of faults in real time, but even an accurate probability estimate of outages and failures. In other words, the performance of classification systems, at least in these cases, needs to be assessed even in terms of reliable outputting posterior probabilities, a really important feature that, in general, classifiers very often do not offer. In this paper are compared several state-of-the-art calibration techniques along with a set of simple new proposed techniques, with the aim of calibrating fuzzy scoring values of a custom-made evolutionary-cluster-based hybrid classifier trained on a set of a real-world dataset of faults collected within the power grid that feeds the city of Rome, Italy. Comparison results show that in real-world cases calibration techniques need to be assessed carefully depending on the scores distribution and the proposed techniques are a valid alternative to the ones existing in the technical literature in terms of calibration performance, computational efficiency and flexibility.

Knowledge-based decision support for BIM adoption by small and medium-sized enterprises in developing economies

BIM is often considered to be unsuitable and there are no systematic approaches to guiding suitability decisions in construction SMEs, especially in developing economies. Thus, this paper evaluated key decision-making factors (DMFs) for BIM-based projects in SMEs. Data was collected through interviews, a Delphi survey and analysed with Fuzzy Synthetic Evaluation (FSE). The result revealed that contractual factors, client requirements and project features are the most important DMF categories. Suitability Decision Support Index (SDSI) was computed, and action plans were compiled. These serve as a decision support engine and a knowledge base in developing a Knowledge-Based Decision Support System (KBDSS). The KBDSS validation showed that it is a useful tool for providing reliable decision support for SMEs. The findings provide solid empirical support for the evaluation of BIM in SMEs from a decision-making perspective. It has significant implications for policy and research and provides ground for technology suitability theory.

Quality of life profile of methadone maintenance treatment patients in Ho Chi Minh City, Vietnam

ABSTRACT Aim To determine the health-related quality of life (HRQoL) of methadone maintenance treatment patients in Ho Chi Minh City, Vietnam. Subject and Methods A cross-sectional study was conducted in 967 patients being treated at two methadone clinics in Ho Chi Minh City, in 2018. Patient’s HRQoL was estimated using the EQ-5D-5L and Visual analogue scale (VAS). Tobit regressions were used to identify factors related to patient’s HRQoL. Results Overall, the mean EQ-5D-5L utility and EQ-VAS indexes were 0.96 (SD = 0.12) and 75.8 (SD=15.5), respectively. Higher EQ-5D-5L score were found in single patients, and have a higher monthly income, while patients aged under 30 years old, have full-time employment, and have higher education were associated with a higher EQ-VAS score. HIV was associated with lower scores of both EQ-5D-5L and EQ-VAS (□ = -0.07 (95%CI: -0.13; -0.01), and □ = -7.10 (95%CI: -9.23; -4.98), respectively). Conclusion HRQoL measurement provides valuable information for the policymaker to adopt suitable decisions on opioid dependence treatment. The finding shows education, employment, and socioeconomic status are the related elements with higher HRQoL, which suggested that the policymakers and physicians should pay more attention to these aspects while working on treatment plans for drug users.

Effect of dividend policy on stock price volatility of companies listed on the stock market of Vietnam

The decision on dividend policy is considered an important decision in financial management and dividend policy is always an issue attracting the attention of investors. The purpose of this research is to identify the impact of dividend policy on the stock price volatility of companies in the stock market of Vietnam. Understanding this matter helps companies to choose an appropriate dividend policy and at the same time helps investors have an overview to make the most suitable and optimal investment decisions. The research has built a regression model to assess the impact of dividend policy on stock price volatility of companies listed on the stock market in Vietnam. The strength of this research is to use the E-view software in quantitative analysis to build a panel data regression model. At the same time, the researchers used the Hausman test to select the appropriate model compared to other research. Research data is collected using a sample size of 100 companies in all industries (except companies in the banking and finance industry) listed on two stock exchanges HOSE and HNX from 2015 to 2020. With the application of E-view software in quantitative analysis to build table data regression models, the article has built a regression model to determine the relationship and level of impact of dividend policy on the stock price volatility of companies. The research results show that the variables of dividend policy have no impact on stock price volatility, which is totally in contrast to previous studies in Vietnam.

Optimal resilient operation of hub energy system considering uncertain parameters

The high potential of hub energy in power systems has considerable profits to improve resiliency and sustainability of system. Variable energy sources embedded in multi-carrier energy systems could be used to propose a robust operation model for improve resiliency of multi-carrier systems during high risk time intervals such as extreme weather condition. Thermal energy sector could be rescheduled for storing heat generated by combined heat and power (CHP) units and boilers in certain periods to coordinate with electrical sector when required. Such cooperation increase operator’s capability to manage electrical grid during time intervals with high uncertainty of outages due to extreme weather condition. Accordingly, in this paper an information gap decision theory (IGDT) method is used to model uncertainty of power outages in optimal system operation. By applying the IGDT method, distribution network operator is able to employ an appropriate methodology to have a robust optimal operation. Also, such methodology leads to make suitable decisions during high risk time intervals such as extreme weather condition. The simulation results proved that proposed model improves the performance and resilience of system by cooperation between thermal and electrical sectors. Also, the chance of electrical grid for successful islanding process increased by reduction in power imbalance during high risk time intervals.

Geospatial Approach to Solving Traffic Congestion Problems In Mushin Local Government Area of Lagos State

The variation in road conditions in relation to traffic congestion overtime enhances the need for proper development of a geospatial platform by comprehensively building and relating the attributes information of the entire road network with respect to various road segments. This is better executed through the concept of dynamic road segmentation. The aim of this study is to carry out geospatial data structure of dynamic road segmentation in Mushin local government area of Lagos State showing the road segment (spatial data) and its topological information.The selected roads within Mushin Local Government were extracted from a street map of Mushin Local Government Area gotten from the office of the Surveyor General of Lagos state. The selected roads were digitized to obtain the spatial information required for the road segmentation. The road vectorization or digitization was carried out in ArcGIS 10.2 software. It was created as a separate shapefile and added as a layer within the GIS environment.The information acquired from the field survey describing the road network as well as the segments i.e. the attribute information, formed a database developed in a GIS platform using ArcGIS 10.2 software. This relational database contains information such as name of road, segment ID, nature of roads, nature of segments, presence of pot holes, presence of crime scenes, presence of congestion, causes of congestion, local inhabitants of segment, length of segments, adjoining land use (to the left and right), mode of transportation along the segment, the traffic condition of the roads and the number of lanes of the road.These large amount of attribute information for all the segment were geospatially referenced with respect to the positions of all the segments and this is the basis of every GIS operation; providing an environment for relating the spatial locations of features with the attribute information describing the spatial feature (which in this case the roads and the road segments represents the spatial feature)Spatial query by attribute as well as location can easily be carried out to select road segments of interest based on predefined criteria using a specific Structural Query Language (SQL) within the GIS environment.Dynamic road segmentation provides a platform for planning and controlling changes on road network. Since the roads are broken down into segments, temporal changes of the road structure as well as the traffic conditions of the roads can be analysed and suitable decisions as well as policies for proper road maintenance can easily be taken and the policies implemented with respect to the segmentation of the roads. It also aids the security organization implementing platform within a GIS environment to monitor the crime scenes with respect to affected segment and would aid in the deployment of security agents at the appropriate locations in case of emergency.In the control of traffic, dynamic road segmentation aid in deciding the alternative conditions to follow since the entire road network have being spatially segmented and the conditions of all the segments built into the GIS database.

Environmental No Impact Factor for Decision Making on Pollutants

The decision making process based on environmental impacts of pollutants can be mathematically expressed. It will be helpful for taking right decisions on discharge of water pollutants and emissions of air pollutants in the environmental recipient components. No effect release can be made possible by reducing the pollutants with suitable decision making for which the indicators for potential impacts from the produced pollutant release has to be developed as Environmental No Impact Factor (ENIF). With the development of suitable mathematical models, NEIF can be applied to different pollutant releases in order to select the best option for reducing the potential impacts from the released/discharged pollutants. The present paper describes the scientific aspects in brief for such model applicable for discharge of water pollutants, emission of air pollutants and release of soil pollutants by which decision making becomes easier.

Geometric Average Weakening Buffer GM(1,1) and its Application in Prediction of Employment Rate of College Graduates

Prediction of the employment rate of college graduates is very important not only for education department to make suitable decision but also for university to adjust its teaching plan. However, it is a difficult task to accurately predict the employment rate of college graduates because it is affected by many factors, making the original data fluctuant. In this paper, a simple and effective prediction approach is proposed to predict employment rate of college graduates using GM (1,1). To attenuate effect of data fluctuation and improve prediction accuracy of GM (1,1) model, the geometric average weakening buffer operator (GAWBO) is first applied to original employment rate data, and then GM (1,1) model is used to predict employment rate. The prediction experiment of Yanshan university employment rate from 2010 to 2019 is performed using the proposed method. Results show that the proposed method can obtain more accurate prediction result than GM (1,1). © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.