Assist Decision Makers Research Articles

An intention inference method for the space non-cooperative target based on BiGRU-Self Attention

Intention inference for space non-cooperative targets is the key to space situational awareness and assistant decision for collision avoidance. Given that the problem of target intention inference is essential to learn the dynamically changing time-series characteristics of space non-cooperative target intentions and infer their relative motion patterns for threat warning, this paper adopts a deep learning-based approach, introduces a bidirectional propagation mechanism and self-attention mechanism based on Gated Recurrent Unit (GRU) and proposes a bidirectional Gated Recurrent Unit (BiGRU)-Self Attention-based space non-cooperative target intention inference model. BiGRU is used to learn deep information in time-series characteristics of the space non-cooperative target, and self-attention mechanism is used to adaptively extract and assign weights to key characteristics to capture the internal correlations in time-series information, thus improving model performance. The line-of-sight measurements are used as the characteristics of target intention inference, and the typical target motion intentions are defined. Subsequently, the proposed model is trained and tested on the test set, with the accuracy reaching 97.1%. Besides, the effectiveness and advantages of the proposed model are verified by the simulation of a case study and comparison evaluations. The results demonstrate that our proposed model could significantly improve the accuracy, computational efficiency, and noise resistance for the space non-cooperative target intention inference compared with the existing intention inference models.

A resilient inventory management of pharmaceutical supply chains under demand disruption

Inspired by the global supply chain disruptions caused by the COVID-19 pandemic, we study optimal procurement and inventory decisions for a pharmaceutical supply chain over a finite planning horizon. To model disruption, we assume that the demand for medical drugs is uncertain and shows spatiotemporal variability. To address demand uncertainty, we propose a two-stage optimization framework, where in the first stage, the total cost of pre-positioning drugs at distribution centers and its associated risk is minimized, while the second stage minimizes the cost of recourse decisions (e.g., reallocation, inventory management). To allow for different risk preferences, we propose to capture the risk of demand uncertainty through the expectation and worst-case measures, leading to two different models, namely (risk-neutral) stochastic programming and (risk-averse) robust optimization. We consider a finite number of scenarios to represent the demand uncertainty, and to solve the resulting models efficiently, we propose L-shaped decomposition-based algorithms. Through extensive numerical experiments, we illustrate the impact of various parameters, such as travel time, product’s shelf life, and waste due to transportation and storage, on the supply chain resiliency and cost, under optimal risk-neutral and risk-averse policies. These insights can assist decision makers in making informed choices.

Oppression or Support? Social Policy in the Lives of Persons with Intellectual Disabilities

ABSTRACTIndividuals’ self-determination, in the sense of making one’s own decisions and controlling one’s own life, constitutes a fundamental human right. It is also pivotal to the realisation of other human rights, and has become a founding pillar of social policy. Through interviews with eight persons who have intellectual disabilities, this article looks at whether, how, and why the promise of self-determination stated in Norwegian guardianship and social-care policies impacts practice. As such it aims to give voice to perspectives that are largely underrepresented in human rights and social science research. The article finds that persons with intellectual disabilities commonly experience newly enacted polices as oppressive rather than supportive. Both social-care workers and guardians can easily obstruct the self-determination of persons who depend on their support, and Norwegian policies do not include efficient mechanisms for empowering these individuals. The article also provides some advice on how policies can better protect the rights of those who depend on decision-making assistance.

Agricultural Combine Remaining Value Forecasting Methodology and Model (and Derived Tool)

Harvesting is an integral component of the agricultural cycle, necessitating the use of high-performance grain harvester combines, which are utilized for a short period each year. Given the seasonality and significant cost involved, list prices ranging from a quarter to almost a million euros, a fact-based investment assessment decision-making process is essential. However, there is a paucity of research studies forecasting the remaining value of grain harvester combines in recent years. This study proposes a straightforward methodology based on public information that employs various parametric and non-parametric models to develop a robust and user-friendly model that can assist decision makers, such as farmers, contractors, sellers, and finance and insurance entities, in optimizing their harvesting operations. The model employs a power regression mode, with RMSE of 1.574 and RSqAdj of 0.8457 results, to provide accurate and reliable insights for informed decision-making. The robust model transparency enables us to easily create a mainstreamed spreadsheet-based dashboard tool.

Case-based reasoning for shipwreck emergency salvage scheme assisted decision

Shipwrecks that adversely affect the marine ecological environment and the passage of vessels should be recovered urgently. The formulation of emergency salvage plans is still based on experts’ judgment. Therefore, this paper proposes an assisted decision model for the emergency salvage plan for wrecks based on case reasoning. This paper uses the Improved Game Theory (IGT) method to calculate the combined weight of multiple subjective and objective methods to overcome the one-sidedness of a single method to determine the weight. To further improve the sensitivity of the interval similarity calculation, this paper improves the method of interval similarity calculation in shipwreck cases. Based on the comparison and analysis of multiple methods based on the real shipwreck salvage case, the standard deviation of the case similarity obtained by the model method in this paper is 0.134, which is the highest compared with the classical algorithm, which shows that the similarity calculation results of this paper are reasonable and have a higher degree of discrimination. This method can provide decision support for the formulation of a marine emergency salvage plan for shipwrecks.

Urban Expressway Renewal Strategy Based on Knowledge Graphs

As an important element of urban infrastructure renewal, urban expressway renewal is of great significance to improve the commuting efficiency of cities (especially metropolitan cities), strengthen the service capacity of urban road facilities, and enhance the quality of cities. Considering the advantages of a knowledge graph in the integration of multi-source data and assisted decision-making based on knowledge reasoning, this paper provides assisted decision support for urban expressway renewal with the help of a knowledge graph. In this paper, we sorted out the concepts related to road renewal from road maintenance standards, designed an ontology concept matching algorithm to extract relevant concepts in existing ontologies, constructed concept models, and built a knowledge graph of expressway renewal with ontology as the carrier. Then, based on road maintenance standards and road properties, this work proposes a knowledge reasoning rule combined with case similarity for an expressway renewal strategy. The final experimental results verified the feasibility of the expressway renewal strategy based on the knowledge graph.

Post-Disaster Recovery Challenges of Public Housing Residents: Lumberton, North Carolina After Hurricane Matthew

The floods caused by Hurricane Matthew in 2016 affected Lumberton, a socioeconomically diverse city in North Carolina with 729 public housing units. Public housing residents face unique challenges in accessing resources and post-disaster temporary accommodations, further delaying their recovery compared to other survivors. This paper investigates the obstacles to public housing recovery and the residents’ recovery challenges using descriptive statistics, mapping, and qualitative analysis in Lumberton. Findings show the dependency of public housing units’ recovery on assistance policies and decisions of various organizations, including local housing authorities. Multiple changes in recovery plans and limited, uncertain, delayed funding and bureaucratic obstacles to funding allocation slow the units’ recovery and prolong the residents’ displacement, adversely affecting their recovery. Hence, pre-disaster resilience initiatives should address these vulnerabilities and the recovery policy's limitations to support public housing units and residents’ recovery. Moreover, affordable housing recovery must become a priority in national housing recovery policies.

Enhancing Green Supply Chain Efficiency Through Linear Diophantine Fuzzy Soft-Max Aggregation Operators

Improving the effectiveness of green supply chains is a critical step towards minimizing waste, optimizing resource use, and reducing the environmental impact of business operations. Sustainable practices should be implemented throughout the entire supply chain, from product design and procurement to production and transportation, in order to achieve these goals. By doing so, businesses can not only improve their environmental performance but also reduce costs, increase customer satisfaction, and gain a competitive advantage in the market. However, due to the existence of competing characteristics, imprecise information, and a lack of knowledge, selecting the appropriate green provider is a complex and unpredictable decision-making issue. The primary objective of a linear-diophantine fuzzy (LiDF) framework is to assist decision makers in selecting the optimal course of action. This paper introduces several novel aggregation operators (AOs), namely the linear Diophantine fuzzy soft-max average (LiDFSMA) and the linear Diophantine fuzzy soft-max geometric (LiDFSMG) operators. The proposed method is then demonstrated through a simple example of a green supplier optimization technique containing linear Diophantine fuzzy content, showing the utility and applicability of the approach. Overall, the proposed LiDF framework and AOs can aid decision makers in selecting the most suitable green provider, thereby enhancing the efficiency of green supply chains.

Lagos’ Vulnerability to Flood’s Changes Mapping Adopting Analytical Hierarchy Process Using Geographical Information System

Flood disaster is considered a major natural hazard plaguing Lagosains due to its devastating effect on affected communities. Analytical Hierarchy Process (AHP) was adopted using Geographical Information System (GIS) to determine areas vulnerable to flood in Lagos for 1984 and 2013. This research considers the contribution of rainfall, elevation, land use, slope and soil to flood. AHP method was applied to these factors by means of ranking and pairwise comparison. This products a relative weight of 34.45% for slope, 19.58% for rainfall, 18.79% for land use, 18.61% for elevation, and 8.57% for soil. The consistency value was found to be reasonable with a consistency index of 0.0738 with a consistency ratio of 7%, these aids in flood vulnerability mapping. This reveals that the impact of flood is high for residential and socio-economic activities in Lagos, thus, this will assist decision makers on the menace posed by the disaster and mitigation measures to adopt.

Learning Methods and Predictive Modeling to Identify Failure by Human Factors in the Aviation Industry

This paper proposes a model capable of predicting fatal occurrences in aviation events such as accidents and incidents, using as inputs the human factors that contributed to each incident, together with information about the flight. This is important because aviation demands have increased over the years; while safety standards are very rigorous, managing risk and preventing failures due to human factors, thereby further increasing safety, requires models capable of predicting potential failures or risky situations. The database for this paper’s model was provided by the Aviation Safety Network (ASN). Correlations between leading causes of incident and the human element are proposed, using the Human Factors Analysis Classification System (HFACS). A classification model system is proposed, with the database preprocessed for the use of machine learning techniques. For modeling, two supervised learning algorithms, Random Forest (RF) and Artificial Neural Networks (ANN), and the semi-supervised Active Learning (AL) are considered. Their respective structures are optimized applying hyperparameter analysis to improve the model. The best predictive model, obtained with RF, was able to achieve an accuracy of 90%, macro F1 of 87%, and a recall of 86%, outperforming ANN models, with a lower ability to predict fatal accidents. These performances are expected to assist decision makers in planning actions to avoid human factors that may cause aviation incidents, and to direct efforts to the more important areas.

Rating pressure factors affecting logistics systems during the pandemic and the ideal logistic decision selection under the Pythagorean fuzzy environment

PurposeDue to the current pandemic, the importance of logistics functions and decisions is well understood both at the level of companies and users. Logistics systems and related decisions are of vital importance in making supply chains effective, efficient and without disruption. Logistic pressure factors may emerge at different points along the logistics process, and given the role of logistics decisions as one of the important indicators of competitiveness, the determination of the logistics pressures that are likely to increase the costs of business, and their causative factors are a vital aspect of the logistics decision-making process. The study aims to provide assistance in the selection of the most ideal logistics decision by ranking the pressure factors affecting the logistics system, especially during the pandemic period for logistics enterprises operating in Ordu and Giresun provinces and which have a corporate identity.Design/methodology/approachIn this study, it is aimed to make the most ideal logistics decision selection by ranking the pressure factors affecting the logistics system, especially during the pandemic period for the logistics enterprises operating in Ordu and Giresun provinces and having a corporate identity. For that purpose interval-valued Pythagorean fuzzy (IVPF)–analytic hierarchy process (AHP) based combinative distance-based assessment (CODAS) methodology was used. Additionally sensitivity and comparison analysis were discussed.FindingsCompetitive pressure was found as the most important pressure factor affecting the logistics system during the pandemic period. Change in regulatory rules was the pressure factor found to have the least effect on the logistics system. Using the weights of logistics pressure factors, “Operational Decisions” was found to be the most ideal logistics decision selection.Research limitations/implicationsThe findings provide support for the evaluation of logistical pressures and decision options by presenting a decision model capable of processing ambiguous information. During a pandemic or similar period, the study assists decision makers in determining a new route. The findings will also call business managers' attention to logistical pressure factors and lead them toward more realistic and feasible practices in the logistics decision-making process.Originality/valueThis study provided an effective and applicable solution to a decision-making problem in the logistics sector including logistics pressure factors and the selection of logistics decisions. In this context, a methodology was presented that will allow businesses to self-evaluate their own logistics pressure factors and the selection of optimal solutions.

Health and Economic Impacts of Lockdown Policies in the Early Stage of COVID-19 in the United States

Lockdown policies, such as stay-at-home orders, are known to be effective in controlling the spread of the novel coronavirus disease 2019. However, concerns over economic burdens of these policies rapidly propelled U.S. states to move toward reopening in the early stage of the pandemic. Decision making in most states has been challenging, especially because of a dearth of quantitative evidence on health gains versus economic burdens of different policies. To assist decision makers, we study the health and economic impacts of various lockdown policies across U.S. states and shed light on policies that are most effective. To this end, we make use of detailed data from 50 U.S. states plus the District of Columbia on various factors, including number of tests, positive and negative results, hospitalizations, ICU beds and ventilators used, residents’ mobility obtained from cellphone data, and deaths. Our analyses allow quantifying the total cost versus the total quality-adjusted life year (QALY) associated with various lockdown policies. We utilize a compartmental model with Markov chain Monte Carlo simulation to estimate the spread of disease. To calibrate our model separately for each U.S. state, we make use of empirical data on the intensity of intervention policies, age, ratio of Black/Hispanic populations, per capita income, residents’ mobility, and number of daily tests and feed them to a longitudinal mixed-effect model. Finally, we utilize a microsimulation model to estimate the total cost and total QALY for each state and perform cost-effectiveness analysis to identify policies that would have worked best. Our results show that, compared with no intervention during March–June 2020, the policies undertaken across the United States saved, on average, about 41,284.51 years’ worth of QALY (per 100K capita), incurring $164.01 million (per 100K capita). Had the states undertaken more strict policies during the same time frame than those they adopted, these values would be 44,909.41 years and $117.28 million, respectively. By quantifying the impact of various lockdown policies separately for each state, our results allow federal and state authorities to avoid following a “one size fits all” strategy and instead enact policies that are better suited for each state. Specifically, by studying the trade-offs between health gains and economic impacts, we identify the particular states that would have benefited from implementing more restrictive policies. Finally, in addition to shedding light on the impact of lockdown policies during our study period (March–June 2020), our results have important implications on curbing future fast-spreading variants of the coronavirus or other related potential epidemics.Supplemental Material: The online appendix is available at https://doi.org/10.1287/serv.2023.0321 .

DETECTION OF NAIL DISEASES USING ENSEMBLE MODEL BASED ON MAJORITY VOTING

Nail diseases are disorders that can have serious effects on human quality of life. With the developing computational methods and technology, anomalies on the nail may be detected quickly and in a non-invasive way. This study proposes a model that provides better performance by combining the results of different deep learning networks with the ensemble learning method. The performance of 7 different deep learning architectures was examined using a database containing 17 disease classes. The proposed method achieved 75 % accuracy, resulting in significant increases in precision and recall metrics compared to individual deep-learning architectures. Thanks to a mobile application that will be developed, the proposed model for large-scale screening may be used as an assistive decision support system for medical professionals. When the results are observed, we predict that early detection of nail diseases (in a remote way) on the hand, which is one of our most used limbs, can reduce hospital visits and costs. In addition, the proposed method can be integrated into dermatoscopy devices used for skin diseases and mole analysis.

Readability, Understandability, and Actionability of Online Limb Preservation Patient Education Materials

With countless sites detailing disease management, treatment, and prognosis, patients often turn to the internet for medical decision-making assistance. While such sites provide ample patient education material, little is known about the reading level, understandability, and actionability of information on these sites. In a limb preservation population, assessing what information patients are interpreting becomes vital to ensure care is not compromised. Internet searches of the terms “Charcot foot, diabetic foot ulcer, foot ulcer, critical limb ischemia, gangrene, osteomyelitis, lymphedema, DVT, pulmonary thrombosis, and amputation” were performed. The Flesch Kincaid readability score from the text from the first 10 links with patient education information were calculated. Understandability and actionability of each resource were then graded by 2 reviewers. Across the 100 accessed websites, 10% maintained patient education materials with at least one readability score at or below the recommended sixth grade reading level. Seventy-three percent of the materials revealed an understanding greater than the recommended 70%. Ninety-nine percent of materials maintained patient education materials with actionability less than 70%. The Spearman Rho correlation revealed a statistically significant relationship between understandability score and the order of each keyword's respective website search position (Rho = −0.01; p = .002). Overall, many online limb preservation patient education materials are written well above the recommended sixth grade reading level with varying understandability and actionability scores. Online resources, as well as physician offices, should examine their patient education materials to ensure they are of an appropriate reading level and provide actions to be taken in case of emergencies.

Спектральная плотность стохастических процессов в прогностических навигационно-управляющих задачах движения судна на курсе

When controlling a modern vessel while moving on a course and under the condition of an integrated bridge satu-rated with instruments, the skipper does not pay enough attention to the analysis of a complex navigational situa-tion, which leads to a chaotic and unpredictable passage of the route. The method of estimating the spectral densi-ty of stochastic processes in the problems of identification, filtering and forecasting of ship management when solving issues of assistance in decision-making by the boat master in navigation and control actions and route op-timization is investigated. The prediction of a stochastic process in real time is investigated on the basis of the ob-tained spectral density estimate, the results of modeling on a ship computer, the convergence rate and the accura-cy of the solution of the problem. The paper also substantiates the need for the formation of stochastic thinking at the future navigator, which allows, based on intuitive and logical thinking, to abandon at the initial stage of solving a problem from deliberately false options for the development of the process in order to ensure the safety of navi-gation.

Audio Feedback with the Use of a Smartphone in Sailing Training among Windsurfers

The open-water training conditions in sailing sports limit the coach’s ability to provide instructions. Auditory feedback provided using a smartphone application in real-time seems to be a promising tool in the training process. The aim of the study was to assess the usefulness of a smartphone application created to support tactical decisions via an auditory display. Thirteen successful windsurfers competing in RS:X class took part in the study. The results, collected with the use of a questionnaire, related to the technical and aesthetic aspects of the functions as well as decision-making assistance of the application during upwind sailing races. Most of the competitors positively evaluated application function (54–85%). Real-time information about the deviation from the set course and information about potential tack change due to a changed wind direction were statistically significantly more helpful for less experienced windsurfers (rho = −0.68 and rho = −0.78, respectively) and those with lower sports level (rho = −0.63 and rho = −0.65, respectively). It can be concluded that the use of sound feedback in the conditions of training on-water in sailing has potential, primarily for younger and less experienced competitors. Quantitative evaluations of the sailing performance should be considered in further research on the functionality of the application.

A Tri-Model Prediction Approach for COVID-19 ICU Bed Occupancy: A Case Study

The impact of COVID-19 and the pressure it exerts on health systems worldwide motivated this study, which focuses on the case of Greece. We aim to assist decision makers as well as health professionals, by estimating the short to medium term needs in Intensive Care Unit (ICU) beds. We analyse time series of confirmed cases, hospitalised patients, ICU bed occupancy, recovered patients and deaths. We employ state-of-the-art forecasting algorithms, such as ARTXP, ARIMA, SARIMAX, and Multivariate Regression models. We combine these into three forecasting models culminating to a tri-model approach in time series analysis and compare them. The results of this study show that the combination of ARIMA with SARIMAX is more accurate for the majority of the investigated regions in short term 1-week ahead predictions, while Multivariate Regression outperforms the other two models for 2-weeks ahead predictions. Finally, for the medium term 3-weeks ahead predictions the Multivariate Regression and ARIMA with SARIMAX show the best results. We report on Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), R-squared (R2), and Mean Absolute Error (MAE) values, for one-week, two-week and three-week ahead predictions for ICU bed requirements. Such timely insights offer new capabilities for efficient management of healthcare resources.

Mapping of the digital climate nudges in Nordic online grocery stores

This paper explores how 21 Nordic online food retailers nudge their customers towards more climate-friendly food choices. We use a choice architecture taxonomy dividing the nudges into decision information, decision structure, and decision assistance. We find that most retailers use several types of climate nudges. Most of these are decision information type nudges, such as personalized carbon footprint apps and climate labels. Wide use of non-salient nudges, often presenting the climate impact after the customers have made their purchase, limits the potential impact of information on consumers' environmental footprints. Furthermore, the use of broad climate categories and aggregated CO2 measures reflect the challenges in calculating the footprints of individual products. The lack of industry-wide standards for emission data and climate labels makes the current situation challenging for customers wanting to compare emissions across stores. Our results also show that few stores have any form of decision structure or decision assistance nudges, even though these are often found to be the most effective types in the literature on nudges. We end with discussing promising digital climate nudging opportunities for retailers seeking to reduce the environmental footprint of their customers.

Opportunities for the United States hotel industry to recover from COVID-19: a multi-period DEA analysis of key efficiency determinants

PurposeThis study examines empirically the development of efficiency levels in the hotel industry and its key drivers, by juxtaposing pre- and post-COVID-19 results in the four most important cities in the United States in terms of international arrivals.Design/methodology/approachA two-step approach was employed by first utilising the data envelopment analysis method to characterise the efficiency of United States hotels. A multiple linear regression analysis was performed to compare hotel performance in the two years prior to the COVID-19 outbreak with the first two years after the outbreak.FindingsThe results indicated the positive effect of size and the economy hotel category on efficiency, while increasing property age, urban location and a lack of brand affiliation showed a negative effect. During the pandemic, size and the economy category remained significant and positive, whereas urban location continued to represent a negative effect.Practical implicationsThis study assists decision makers regarding prospective investments, supports existing and future portfolio analyses, contributes to observations on competition, and offers a wider perspective of the industry.Originality/valueFirst, this study investigated the evolution of factors that influenced efficiency before and after the outbreak of the COVID-19 pandemic. Second, the results offer insights into the impact of the pandemic on hotels' efficiency levels. Third, the study proposes directions for the restoration of hotel efficiency to pre-COVID-19 levels.

Automation irrigation system using arduino for smart crop field productivity

Agriculture is essential to the prosperity of agricultural countries like India. Thus, the suggested strategy is to use automation and internet of thing (IoT) technology to make agriculture smart. Applications enabled by the IoTs include irrigation decision assistance, crop growth monitoring and selection, and more. an Arduino-powered technology that boosts agricultural productivity. This study's main goal is to find the least quantity of water necessary to grow crops. Most farmers squander a lot of time on the fields rather than concentrating on the water that plants have access to at the right moment. The suggested system determines the required amount of water based on the data obtained from the sensors. Two sensors provide data on the soil's temperature, humidity, amount of sunlight each day, and soil temperature to the base station. The suggested systems must determine the amount of water required for irrigation based on these criteria. The system's main benefit is the use of precision agriculture (PA) in conjunction with cloud computing, which will maximise the use of water fertilisers while maximising crop yields and also assist in determining field weather conditions.