Decision System Research Articles

Development of a stereo-EEG based seizure matching system for clinical decision making in epilepsy surgery.

Objective.The proportion of patients becoming seizure-free after epilepsy surgery has stagnated. Large multi-center stereo-electroencephalography (SEEG) datasets can allow comparing new patients to past similar cases and making clinical decisions with the knowledge of how cases were treated in the past. However, the complexity of these evaluations makes the manual search for similar patients impractical. We aim to develop an automated system that electrographically and anatomically matches seizures to those in a database. Additionally, since features that define seizure similarity are unknown, we evaluate the agreement and features among experts in classifying similarity.Approach.We utilized 320 SEEG seizures from 95 consecutive patients who underwent epilepsy surgery. Eight international experts evaluated seizure-pair similarity using a four-level similarity score. As our primary outcome, we developed and validated an automated seizure matching system by employing patient data marked by independent experts. Secondary outcomes included the inter-rater agreement (IRA) and features for classifying seizure similarity.Main results.The seizure matching system achieved a median area-under-the-curve of 0.76 (interquartile range, 0.1), indicating its feasibility. Six distinct seizure similarity features were identified and proved effective: onset region, onset pattern, propagation region, duration, extent of spread, and propagation speed. Among these features, the onset region showed the strongest correlation with expert scores (Spearman's rho = 0.75,p< 0.001). Additionally, the moderate IRA confirmed the practicality of our approach with an agreement of 73.9% (7%), and Gwet's kappa of 0.45 (0.16). Further, the interoperability of the system was validated on seizures from five centers.Significance.We demonstrated the feasibility and validity of a SEEG seizure matching system across patients, effectively mirroring the expertise of epileptologists. This novel system can identify patients with seizures similar to that of a patient being evaluated, thus optimizing the treatment plan by considering the results of treating similar patients in the past, potentially improving surgery outcome.

Counterfactual Explanations and Algorithmic Recourses for Machine Learning: A Review

Machine learning plays a role in many deployed decision systems, often in ways that are difficult or impossible to understand by human stakeholders. Explaining, in a human-understandable way, the relationship between the input and output of machine learning models is essential to the development of trustworthy machine learning based systems. A burgeoning body of research seeks to define the goals and methods of explainability in machine learning. In this article, we seek to review and categorize research on counterfactual explanations , a specific class of explanation that provides a link between what could have happened had input to a model been changed in a particular way. Modern approaches to counterfactual explainability in machine learning draw connections to the established legal doctrine in many countries, making them appealing to fielded systems in high-impact areas such as finance and healthcare. Thus, we design a rubric with desirable properties of counterfactual explanation algorithms and comprehensively evaluate all currently proposed algorithms against that rubric. Our rubric provides easy comparison and comprehension of the advantages and disadvantages of different approaches and serves as an introduction to major research themes in this field. We also identify gaps and discuss promising research directions in the space of counterfactual explainability.

Multiple fairness criteria in decision tree learning

The use of algorithmic decision-making systems based on machine learning models has led to a need for fair (unbiased) and explainable classification outcomes. In particular, machine learning algorithms can encode biases, which might result in discriminatory decisions for certain groups such as gender, race, or age. Although a number of works on decision tree learning have been proposed to decrease the chance of discrimination, they usually focus on the use of a single fairness metric. In general, creating a model based on a single fairness metric is not a sufficient way to mitigate discrimination since bias can originate from various sources—e.g., the data itself or the optimization process. In this paper, we propose a novel decision tree learning process that utilizes multiple fairness metrics to address both group and individual discrimination. This is achieved by extending the attribute selection procedure to consider not only information gain but also gain in fairness. Computational experiments on fourteen different datasets with various sensitive features demonstrate that the proposed Fair-C4.5 models improve fairness without a loss in predictive accuracy when compared to the well-known C4.5 and the fairness-aware FFTree algorithms.

Human-robot collaborative decision method of hexapod robot based on prior knowledge and negotiation strategy

Against the unstructured terrain environment, human drivers often rely on remote operating patterns to accomplish tasks with robots. With the gradual improvement in robot intelligence, a key problem that urgently requires attention is how to bridge cognitive and perceptual differences between human and robot in collaborative decision-making processes. Particularly effective resolution of differences in decision outcomes is crucial. Therefore, this paper utilizes the decision logic process and prior knowledge model of human drivers to form a robot's decision framework, narrowing the cognitive differences between human and robot. Besides, embedding the human-robot-environment features that affect the decision-making process as prior knowledge into the robot's decision-making system can effectively reduce perceptual gaps. Under the same decision framework, a negotiation strategy is proposed for forming a unified decision outcome between human and robot by finding an optimal concession rate. This study utilizes a hexapod robot simulated driving platform to gather experimental data and develop prior knowledge for robots. It also leverages virtual reality equipment and visual augmentation technologies to establish a remote human-robot collaborative decision-making experimental system. The experimental results conducted in complex obstacle terrain demonstrate the effectiveness of adopting the negotiation strategy for human-robot collaborative decision-making. Compared with the individual human or robot decision, the human-robot collaborative decision method significantly enhances robot stability, reduces energy consumption, and minimizes collisions.

Environmental complexity modulates information processing and the balance between decision-making systems.

Behavior in naturalistic scenarios occurs in diverse environments. Adaptive strategies rely on multiple neural circuits and competing decision systems. However, past studies of rodent decision making have largely measured behavior in simple environments. To fill this gap, we recorded neural ensembles from hippocampus (HC), dorsolateral striatum (DLS), and dorsomedial prefrontal cortex (dmPFC) while rats foraged for food under changing rules in environments with varying topological complexity. Environmental complexity increased behavioral variability, lengthened HC nonlocal sequences, and modulated action caching. We found contrasting representations between DLS and HC, supporting a competition between decision systems. dmPFC activity was indicative of setting this balance, in particular predicting the extent of HC non-local coding. Inactivating mPFC impaired short-term behavioral adaptation and produced long-term deficits in balancing decision systems. Our findings reveal the dynamic nature of decision-making systems and how environmental complexity modulates their engagement with implications for behavior in naturalistic environments.

Environmental complexity and regularity shape the evolution of cognition.

The environmental complexity hypothesis suggests that cognition evolves to allow animals to negotiate a complex and changing environment. By contrast, signal detection theory suggests cognition exploits environmental regularities by containing biases (e.g. to avoid dangerous predators). Therefore, two significant bodies of theory on cognitive evolution may be in tension: one foregrounds environmental complexity, the other regularity. Difficulty in reconciling these theories stems from their focus on different aspects of cognition. The environmental complexity hypothesis focuses on the reliability of sensors in the origin of cognition, while signal detection theory focuses on decision making in cognitively sophisticated animals. Here, we extend the signal detection model to examine the joint evolution of mechanisms for detecting information (sensory systems) and those that process information to produce behaviour (decision-making systems). We find that the transition to cognition can only occur if processing compensates for unreliable sensors by trading-off errors. Further, we provide an explanation for why animals with sophisticated sensory systems nonetheless disregard the reliable information it provides, by having biases for particular behaviours. Our model suggests that there is greater nuance than has been previously appreciated, and that both complexity and regularity can promote cognition.

Software Architecture Design of ASV Rybitwa: Development of an Autonomous Surface Vehicle for Dynamic Navigation and Task Execution

Abstract This paper introduces the software design of an Autonomous Surface Vehicle (ASV) named ASV Rybitwa. It was designed as an easily transportable platform capable of autonomous navigation and performing tasks during the RoboBoat 2024 competition, with emphasis on its modularity, generality and extendibility. The paper presents a software architecture for a small autonomous surface vehicle using novel tools that provide easy system integration and expansion. To meet such requirements, a generic control box connecting an autopilot (PX4) and a onboard computer (NVIDIA Jetson Nano) was developed so as to host the Robot Operating System 2 (ROS2) and to interact with sensors and actuators. Computer vision from three Oak-D cameras, equipped with AI algorithm support (YOLOv8), was used for navigation and obstacle avoidance. The decision-making system was designed using behavioural trees and computer vision, allowing the vehicle’s capabilities to be adapted to the needs of the current tasks and mission. In addition, an Omni X propulsion system was proposed, providing full holonomy and enhancing dynamic positioning and navigation capabilities in complex navigational conditions. In addition this paper describes lessons learned from ASV Rybitwa’s real-world testing during the aforementioned competition.

Development and Application of Drilling Intelligent Assistant Decision System

Abstract In order to systematically harness the substantial volume of data generated during the drilling process and achieve intelligent analysis and auxiliary decision-making for real-time risk monitoring and warnings during drilling, an intelligent drilling auxiliary decision-making system has been developed. This system integrates various technologies, including physical models, intelligent algorithms, and trend analysis. By analyzing the characteristics of logging data under different operating conditions, an intelligent algorithm capable of automatically distinguishing six types of drilling operating conditions has been established. Taking into account the impact of rock cuttings on the stress on the pipe string and annular pressure loss during the drilling process, coupled frictional torque and cyclic pressure loss calculation models were developed under coupled conditions. Building upon this foundation and considering the trend of deviation between predicted and measured parameters, a monitoring algorithm for detecting stuck drilling, wellbore leakage, and overflow incidents was formulated. The development of the drilling intelligent decision-making system was completed based on a C/S three-layer architecture and a data center. This system has been successfully applied in more than 50 exploration wells of various types, including shale oil and gas horizontal wells and deep wells. The static analysis results demonstrated a compliance rate of 91.5% with on-site monitoring, playing a crucial role in drilling parameter optimization and risk monitoring. The practicality and feasibility of the system have been verified, providing essential support for efficient and safe drilling production.

Development and Validation of a Clinical Prediction Model for Paclitaxel Hypersensitivity Reaction on the Basis of Real-World Data: Pac-HSR Score.

Paclitaxel is effective chemotherapy against various cancers but can cause hypersensitivity reaction (HSR). This study aimed to identify predictors associated with paclitaxel HSR and develop a clinical prediction model to guide clinical decisions. Data were collected from the medical records database of Rajavithi Hospital. Patients with cancer treated with paclitaxel from 2015 to 2022 were included, and a multivariable logistic regression analysis identified predictors associated with paclitaxel HSR. The scoring system was transformed and calibrated on the basis of diagnostic parameters. Discrimination and calibration performances were assessed. Internal validation was conducted using bootstrap resampling with 1,000 replications. This study involved 3,708 patients with cancer, with an incidence of paclitaxel HSR of 10.11%. An 11-predictor-based Pac-HSR scoring system was developed, involving the following factors: younger age; poor Eastern Cooperative Oncology Group performance status; previous history of paclitaxel HSR; medication allergy history; chronic obstructive airway disease; lung and cervical cancers; high actual dose of paclitaxel; no diphenhydramine premedication; low hemoglobin level; high WBC count; and high absolute lymphocyte count. The C-statistics was 0.73 (95% CI, 0.70 to 0.76), indicating acceptable discrimination. The P value of the Hosmer-Lemeshow goodness-of-fit test was 0.751. The ratio of observed and expected values was 1.00, indicating good calibration. At a cutoff point of 8, specificity was 75.28% and sensitivity was 57.07%. Internal validation indicated good performance with minimal bias, and decision curve analysis demonstrated improved prediction with the use of this scoring system in clinical decision making. This study developed the 11-predictor-based Pac-HSR scoring system for predicting paclitaxel HSR in patients with cancer. High-risk patients identified by this score should be prioritized for close monitoring and early treatment prophylaxis.

An effective farmer-centred mobile intelligence solution using lightweight deep learning for integrated wheat pest management

Integrated Pest Management (IPM) techniques have been widely used in agriculture to manage pest damage in the most economical way and to minimise harm to people, property and the environment. However, current research and products on the market cannot consolidate this process. Most existing solutions either require experts to visually identify pests or cannot automatically assess pest levels and make decisions based on detection results. To make the process from pest identification to pest management decision making more automated and intelligent, we propose an end-to-end integrated pest management solution that uses deep learning for semi-automated pest detection and an expert system for pest management decision making. Specifically, a low computational cost sampling point generation algorithm is proposed to enable mobile devices to generate uniformly distributed sampling points in irregularly shaped fields. We build a pest detection model based on YoloX and use Pytorch Mobile to deploy it on mobile phones, allowing users to detect pests offline. We develop a standardised sampling specification and a mobile application to guide users to take photos that allow pest population density to be calculated. A rule-based expert system is established to derive pest management thresholds from prior agricultural knowledge and make decisions based on pest detection results. We also propose a human-in-the-loop algorithm to continuously track and update the validity of the thresholds in the expert system. The mean average precision of the pest detection model is 58.17% for 97 classes, 75.29% for 2 classes, and 57.33% for 11 classes on three pest datasets, respectively. The usability of the pest management system is assessed by the User Experience Surveys and achieves a System Usability Scale (SUS) score of 76. The usability of the proposed solution is validated by qualitative field experiments.

The Cognitive Reflection Test and Investment Decision

The Cognitive Reflection Test (CRT), a measure of cognitive reflection, assesses people's capacity and, accordingly, investors' ability to override immediate, reflexive responses in favour of rational answers and decisions. The test is significant in behavioural finance as its questions reveal biases and heuristics, which affect rational investment decisions and choices. The present research employs a sample of Accounting and Finance students, who represent potential future investors and participants in financial markets, to examine the extent to which the respondents engage in rational thinking when answering the test questions. CRT approach aims to evaluate their ability to avoid impulsive actions and rely less on intuitive decision-making (System 1).

Decoding decision delegation to artificial intelligence: A mixed-methods study on the preferences of decision-makers and decision-affected in surrogate decision contexts

Organizations are increasingly opting to use decision-making systems based on artificial intelligence (AI) to increase decision quality and speed and free up resources. However, delegating decisions to AI is challenging, especially in contexts that go beyond classical optimization problems. Current research has so far largely neglected to include the viewpoints of the decision-affected and of surrogate decision-makers in the discussion. To address these gaps, in this study we rely on two experimental designs and complement our findings with qualitative interview data to shed light on both sides: the perspective of those affected by the decision and that of the decision maker in surrogate and ethically complex decision contexts. Findings reveal that the individual decision-making perspective may lead to opposing perceptions. Whereas the willingness to delegate an ethically challenging decision to AI in a surrogate decision context is lower than that in a non-surrogate context (decision-maker perspective), people affected by the decision do not generally prefer humans to AI (decision-affected perspective). By these findings, we contribute to the literature on AI-enabled decision-making and decision delegation to non-human entities.

Landscape Planning Aided by Reinforcement Learning Decision System in Environmental Design

Landscape Planning Aided by Reinforcement Learning Decision System in Environmental Design

Decision-making method of managed pressure drilling based on real-time calculation and analysis models

Abstract As petroleum exploration and development extend towards marginal, deep, and unconventional resources, drilling challenges such as narrow density windows and high wellbore control risks become increasingly prominent. Managed pressure drilling (MPD) proves effective in reducing drilling operational difficulties and well control risks in narrow safe-density window formations. However, existing MPD systems have limited capabilities for real-time calculation and analysis in the absence of downhole pressure measurement data, hindering accurate guidance for real-time calculation, analysis, and control decision recommendations in both conventional and precise MPD operations.Therefore, based on on-site engineering logging, real-time data from MPD operations, a branch decision tree was established to automatically determine the operational conditions of MPD. This achieved real-time identification of 11 drilling conditions. Starting from the characteristics of two-phase fluid flow in the annulus, coupling wellbore pressure and formation fluid invasion, a predictive model for annular pressure distribution during MPD was established. This model facilitated the calculation, determination, and recommendation of the pre-control value for wellhead backpressure. Building upon theoretical research, a MPD calculation, analysis, and control decision system was developed. Field testing and validation indicated that the system could simulate and analyze wellbore pressure and wellhead backpressure values, automatically identify drilling conditions and downhole complexities. The average error between the calculated and measured values of the standpipe pressure was 1.88%. The accuracy of the predicted wellhead backpressure values based on safe operating conditions compared to the actual controlled values reached 89.8%. This system achieved real-time calculation, analysis, and control decision-making based on real-time engineering parameters, enhancing the reliability and timeliness of wellhead backpressure control in MPD operations. It effectively guided conventional MPD operations and improved the capabilities and intelligence level of precision MPD operations after process optimization.

An approximate dynamic programming approach for solving aircraft fleet engine maintenance problem: Methodology and a case study

We consider a long-term engine maintenance planning problem for an aircraft fleet. The objective is to guarantee sufficient on-wing engines to reach service levels while effectively organizing shop visits for engines. However, complexity arises from intricate maintenance policies and uncertainty in engine deterioration. To address this problem, we propose a graph-based approach representing high-dimensional engine statuses and transitions. We then formulate the problem as a multi-stage stochastic integer program with endogenous uncertainty. We develop an approximate dynamic programming algorithm enhanced by dynamic graph generation and policy-sifting techniques so as to reduce the computational overhead in large problems. We demonstrate the efficacy of our method, compared with other popular methods, in terms of running time and solution quality. In the case study, we present an implementation in a real-world decision system in China Southern Airlines, in which the proposed method works seamlessly with other supporting modules and significantly improves the efficiency of engine maintenance management.

Інформаційно-комп’ютерна технологія підтримки психічного здоров’я людини з урахуванням її характерологічних властивостей

Introduction. The current stage of the development of society is characterized by an avalanche-like increase in information, which, due to the continuous and rapidly growing pace, has acquired the character of the information industry. Currently, the problem of developing and using information systems in those areas of activity that are related to human health, especially in the areas of psychosocial status of a person who was under the negative influence of stressogenic factors caused by the state of war, is gaining relevance. Therefore, the development of information technology, which includes methods of operative diagnosis of the psychological state of a person, methods of qualifying corrective and rehabilitation measures with the involvement of the willpower of the victims, taking into account their characterological properties and the strength of the personal "I", are of great importance. Providing psychological support to persons who have been under the negative influence of psychogenic factors is an urgent and rather complex problem. We consider it expedient to involve the means of modern computer technologies in its solution. The purpose of the paper is to develop a computer decision-making support system for the rehabilitation of the psychosocial state of health of a person who was under the negative influence of psychogenic factors, taking into account personal character traits. Results. A hierarchical structure of health assessment technology was developed, taking into account personal characterological properties. On the basis of a hierarchical approach, an information-technological structure of classification and evaluation of human character properties has been developed. A program algorithm for the application of rehabilitation measures depending on the strength of manifestation of characterological properties of the individual has been synthesized. A computer system was developed to support rehabilitation decision-making by a person with psychological problems, taking into account his personal character traits. Conclusions. The developed classification of the working information array, which is carried out using a hierarchical approach, systematizes and transforms a huge amount of unordered data related to the psychological component, taking into account the character, into an information product convenient for further computer-technological transformations. The developed information technology, implemented in a computer decision support system, is a constructive tool for increasing the accessibility and efficiency of providing the necessary specific information to the user when choosing rehabilitation measures, taking into account the personal characteristics of his character. Taking into account the characterological components of mental status in the developed computer support system for making rehabilitation decisions by persons who were under the influence of psychological overstrain in connection with martial law increases the purposefulness of recommendations in the case of independent selection of health measures. Keywords: human character, hierarchical modeling, negative psychogenic factors, mental health, computer decision support system.

Web search results processing in an information support system for decision-making processes

Objectives. The problem of the web search results processing in an information support system for decision[1]making is solved in order to create and correct a meaningful description of a problem situation. An approach to solving this problem is proposed based on the use of thematic text corpora (collections of texts on a specific topic) as knowledge about the subject area, as well as a knowledge representation model based on verbal associations. When solving problems of the web search results processing in a decision-making information support system, five main goals are pursued: the formation of an extended description of a problem situation, the synthesis of a search prescription, an Internet search for information about decisions made, the synthesis of a retelling of the information found, and an assessment of the quality of the found analogues of the decisions made.Methods. Methods of set theory, graph theory and mathematical linguistics are used.Results. A mathematical model has been developed for the web search results processing in an information support system for decision making. The concepts of verbal association of words and texts, as well as pragmatically complete lexical structure, are formalized. The proven properties of such structures provide algorithmization of information processes in the model under consideration.Conclusion. The approach to modeling is based on the formalization of the concepts of the informativeness of words, sentences, texts and the informativeness of verbal associations between them. As an implementation of the model proposed in the article, algorithms have been developed for creating a dictionary of pragmatically complete lexical structures, creating structural-lexical templates for sentences, texts and subject areas, synthesizing a brief retelling of the information found, and assessing the quality of the found analogues of the decisions made.

The use of situational modeling in the development of decision-making systems for complex organizational systems

The use of situational modeling in the development of decision-making systems for complex organizational systems

뉴욕경찰청의 알고리즘 예측치안 전략의 논쟁점

The purpose of this study is to examine the controversies surrounding the algorithmic predictive policing strategy adopted by the New York Police Department. NYPD is very active in pursuing algorithmic predictive policing strategies, but it is facing a variety of criticisms, including: First, personal information collection activities for predictive security violate the ideology of the Fourth Amendment to the U.S. Constitution, which prohibits invasion of privacy. Second, as the police rely on instructions generated by algorithmic predictions, police operations are becoming dehumanized. Third, the police exercise their police authority intensively against dangerous people or dangerous areas, and there is a risk that these people will eventually be negatively stigmatized and become criminals. Fourth, the police unilaterally exercise police power based on algorithmic predictions, rather than a two-way police service that reflects the needs of citizens or the community. Fifth, the efficiency of algorithmic predictive policing has not been verified, and the problem of contamination of used big data is being raised. Sixth, it is impossible to confirm whether the data provided by the police to private companies is opaque and secure. Seventh, there is the irrationality of Police power being replaced by private companies' for-profit businesses. Eighth, the New York Police Department is subject to monitoring of algorithmic predictive policing through the Local Law in Relation to Automated Decision Systems Used by Agencies and Public Oversight of Surveillance Technology(POST) Act, but the problems remain unresolved. Ninth, the New York Police Department continues to engage in legal disputes with human rights watchdog groups such as the Brennen Center over the non-disclosure of algorithmic predictive security information, losing most cases, raising questions about the legality of big data collection and management.

Clinical Decision Support and Natural Language Processing in Medicine: Systematic Literature Review.

Ensuring access to accurate and verified information is essential for effective patient treatment and diagnosis. Although health workers rely on the internet for clinical data, there is a need for a more streamlined approach. This systematic review aims to assess the current state of artificial intelligence (AI) and natural language processing (NLP) techniques in health care to identify their potential use in electronic health records and automated information searches. A search was conducted in the PubMed, Embase, ScienceDirect, Scopus, and Web of Science online databases for articles published between January 2000 and April 2023. The only inclusion criteria were (1) original research articles and studies on the application of AI-based medical clinical decision support using NLP techniques and (2) publications in English. A Critical Appraisal Skills Programme tool was used to assess the quality of the studies. The search yielded 707 articles, from which 26 studies were included (24 original articles and 2 systematic reviews). Of the evaluated articles, 21 (81%) explained the use of NLP as a source of data collection, 18 (69%) used electronic health records as a data source, and a further 8 (31%) were based on clinical data. Only 5 (19%) of the articles showed the use of combined strategies for NLP to obtain clinical data. In total, 16 (62%) articles presented stand-alone data review algorithms. Other studies (n=9, 35%) showed that the clinical decision support system alternative was also a way of displaying the information obtained for immediate clinical use. The use of NLP engines can effectively improve clinical decision systems' accuracy, while biphasic tools combining AI algorithms and human criteria may optimize clinical diagnosis and treatment flows. PROSPERO CRD42022373386; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=373386.