A Prototype Agent Based Model and Machine Learning Hybrid System for Healthcare Decision Support

2011 ◽  
Vol 2 (4) ◽  
pp. 67-90 ◽  
Author(s):  
Marek Laskowski
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Patient Flow ◽  
Policy Decision ◽  
Healthcare Policy ◽  
Agent Based Modeling ◽  
Learning System ◽  
Agent Based Model ◽  
Agent Based ◽  
Markov Decision

Science is on the verge of practical agent based modeling decision support systems capable of machine learning for healthcare policy decision support. The details of integrating an agent based model of a hospital emergency department with a genetic programming machine learning system are presented in this paper. A novel GP heuristic or extension is introduced to better represent the Markov Decision Process that underlies agent decision making in an unknown environment. The capabilities of the resulting prototype for automated hypothesis generation within the context of healthcare policy decision support are demonstrated by automatically generating patient flow and infection spread prevention policies. Finally, some observations are made regarding moving forward from the prototype stage.

A Prototype Agent Based Model and Machine Learning Hybrid System for Healthcare Decision Support

2012 ◽  
pp. 230-253 ◽  
Author(s):  
Marek Laskowski
Keyword(s):  
Machine Learning ◽  
Decision Support ◽  
Decision Process ◽  
Patient Flow ◽  
Policy Decision ◽  
Healthcare Policy ◽  
Learning System ◽  
Agent Based Model ◽  
Agent Based ◽  
Markov Decision

Science is on the verge of practical agent based modeling decision support systems capable of machine learning for healthcare policy decision support. The details of integrating an agent based model of a hospital emergency department with a genetic programming machine learning system are presented in this paper. A novel GP heuristic or extension is introduced to better represent the Markov Decision Process that underlies agent decision making in an unknown environment. The capabilities of the resulting prototype for automated hypothesis generation within the context of healthcare policy decision support are demonstrated by automatically generating patient flow and infection spread prevention policies. Finally, some observations are made regarding moving forward from the prototype stage.

scholarly journals Toward a better understanding of team decision processes: combining laboratory experiments with agent-based modeling

2021 ◽  
Author(s):  
Iris Lorscheid ◽  
Matthias Meyer
Keyword(s):  
Laboratory Experiment ◽  
Mixed Method ◽  
Agent Based Modeling ◽  
Decision Processes ◽  
Mixed Method Research ◽  
Team Cognition ◽  
Agent Based Model ◽  
Agent Based ◽  
Individual Level ◽  
Team Decision

AbstractDespite advances in the field, we still know little about the socio-cognitive processes of team decisions, particularly their emergence from an individual level and transition to a team level. This study investigates team decision processes by using an agent-based model to conceptualize team decisions as an emergent property. It uses a mixed-method research design with a laboratory experiment providing qualitative and quantitative input for the model’s construction, as well as data for an output validation of the model. First, the laboratory experiment generates data about individual and team cognition structures. Then, the agent-based model is used as a computational testbed to contrast several processes of team decision making, representing potential, simplified mechanisms of how a team decision emerges. The increasing overall fit of the simulation and empirical results indicates that the modeled decision processes can at least partly explain the observed team decisions. Overall, we contribute to the current literature by presenting an innovative mixed-method approach that opens and exposes the black box of team decision processes beyond well-known static attributes.

scholarly journals Streaming Video Classification Using Machine Learning

2020 ◽  
Vol 17 (4A) ◽  
pp. 677-682
Author(s):  
Adnan Shaout ◽  
Brennan Crispin
Keyword(s):  
Machine Learning ◽  
Decision Process ◽  
Data Stream ◽  
Streaming Video ◽  
Learning System ◽  
Network Interface ◽  
Video Classification ◽  
Design And Implementation ◽  
Markov Decision ◽  
Streaming Services

This paper presents a method using neural networks and Markov Decision Process (MDP) to identify the source and class of video streaming services. The paper presents the design and implementation of an end-to-end pipeline for training and classifying a machine learning system that can take in packets collected over a network interface and classify the data stream as belonging to one of five streaming video services: You Tube, You Tube TV, Netflix, Amazon Prime, or HBO

Use of a sonification system for science learning by people who are blind

2016 ◽  
Vol 10 (4) ◽  
pp. 187-198 ◽  
Author(s):  
Orly Lahav ◽  
Nuha Chagab ◽  
Vadim Talis
Keyword(s):  
Complex Systems ◽  
Conceptual Knowledge ◽  
Science Curriculum ◽  
Low Cost ◽  
Agent Based Modeling ◽  
Learning System ◽  
Learning Ability ◽  
Content Type ◽  
Agent Based ◽  
K 12

Purpose The purpose of this paper is to examine a central need of students who are blind: the ability to access science curriculum content. Design/methodology/approach Agent-based modeling is a relatively new computational modeling paradigm that models complex dynamic systems. NetLogo is a widely used agent-based modeling language that enables exploration and construction of models of complex systems by programming and running the rules and behaviors. Sonification of variables and events in an agent-based NetLogo computer model of gas in a container is used to convey phenomena information. This study examined mainly two research topics: the scientific conceptual knowledge and systems reasoning that were learned as a result of interaction with the listen-to-complexity (L2C) environment as appeared in answers to the pre- and post-tests and the learning topics of kinetic molecular theory of gas in chemistry that was learned as a result of interaction with the L2C environment. The case study research focused on A., a woman who is adventitiously blind, for eight sessions. Findings The participant successfully completed all curricular assignments; her scientific conceptual knowledge and systems reasoning became more specific and aligned with scientific knowledge. Practical implications A practical implication of further studies is that they are likely to have an impact on the accessibility of learning materials, especially in science education for students who are blind, as equal access to low-cost learning environments that are equivalent to those used by sighted users would support their inclusion in the K-12 academic curriculum. Originality/value The innovative and low-cost learning system that is used in this research is based on transmittal of visual information of dynamic and complex systems, providing perceptual compensation by harnessing auditory feedback. For the first time the L2C system is based on sound that represents a dynamic rather than a static array. In this study, the authors explore how a combination of several auditory representations may affect cognitive learning ability.

Analyzing the Influences of Passive Investment Strategies on Financial Markets via Agent-Based Modeling

2008 ◽  
pp. 224-238 ◽  
Author(s):  
Hiroshi Takahashi ◽  
Satoru Takahashi ◽  
Takao Terano
Keyword(s):  
Asset Pricing ◽  
Financial Markets ◽  
Financial Market ◽  
Investment Strategy ◽  
Agent Based Modeling ◽  
Investment Strategies ◽  
Agent Based Model ◽  
Efficient Market ◽  
Agent Based ◽  
Price Fluctuations

This chapter develops an agent-based model to analyze microscopic and macroscopic links between investor behaviors and price fluctuations in a financial market. This analysis focuses on the effects of Passive Investment Strategy in a financial market. From the extensive analyses, we have found that (1) Passive Investment Strategy is valid in a realistic efficient market, however, it could have bad influences such as instability of market and inadequate asset pricing deviations, and (2) under certain assumptions, Passive Investment Strategy and Active Investment Strategy could coexist in a Financial Market.

scholarly journals Investigating the Exits’ Symmetry Impact on the Evacuation Process of Classrooms and Lecture Halls: An Agent-Based Modeling Approach

Symmetry ◽  
2020 ◽  
Vol 12 (4) ◽  
pp. 627 ◽  
Author(s):  
Camelia Delcea ◽  
Liviu-Adrian Cotfas ◽  
Ioana-Alexandra Bradea ◽  
Marcel-Ioan Boloș ◽  
Gabriella Ferruzzi
Keyword(s):  
Agent Based Modeling ◽  
Agent Based Model ◽  
Evacuation Time ◽  
High Importance ◽  
Agent Based ◽  
Modeling Approach ◽  
Size Number ◽  
The Doors

As the evacuation problem has attracted and continues to attract a series of researchers due to its high importance both for saving human lives and for reducing the material losses in such situations, the present paper analyses whether the evacuation doors configuration in the case of classrooms and lecture halls matters in reducing the evacuation time. For this aim, eighteen possible doors configurations have been considered along with five possible placements of desks and chairs. The doors configurations have been divided into symmetrical and asymmetrical clusters based on the two doors positions within the room. An agent-based model has been created in NetLogo which allows a fast configuration of the classrooms and lecture halls in terms of size, number of desks and chairs, desks and chair configuration, exits’ size, the presence of fallen objects, type of evacuees and their speed. The model has been used for performing and analyzing various scenarios. Based on these results, it has been observed that, in most cases, the symmetrical doors configurations provide good/optimal results, while only some of the asymmetrical doors configurations provide comparable/better results. The model is configurable and can be used in various scenarios.

Agent-Based Modeling and Simulation as a Tool for Decision Support for Managing Patient Falls in a Dynamic Hospital Setting

2010 ◽  
pp. 149-162 ◽  
Author(s):  
Gokul Bhandari ◽  
Ziad Kobti ◽  
Anne W. Snowdon ◽  
Ashish Nakhwal ◽  
Shamual Rahaman ◽  
...  
Keyword(s):  
Decision Support ◽  
Modeling And Simulation ◽  
Hospital Setting ◽  
Agent Based Modeling ◽  
Agent Based ◽  
Patient Falls

scholarly journals Implementation of modified SARSA learning technique in EMCAP

2017 ◽  
Vol 7 (1.5) ◽  
pp. 274
Author(s):  
D. Ganesha ◽  
Vijayakumar Maragal Venkatamuni
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Decision Process ◽  
Learning Algorithm ◽  
Research Work ◽  
Learning System ◽  
State Action ◽  
Learning Technique ◽  
Markov Decision ◽  
Experiment Analysis

This research work presents analysis of Modified Sarsa learning algorithm. Modified Sarsa algorithm.  State-Action-Reward-State-Action (SARSA) is an technique for learning a Markov decision process (MDP) strategy, used in for reinforcement learning int the field of artificial intelligence (AI) and machine learning (ML). The Modified SARSA Algorithm makes better actions to get better rewards.  Experiment are conducted to evaluate the performace for each agent individually. For result comparison among different agent, the same statistics were collected. This work considered varied kind of agents in different level of architecture for experiment analysis. The Fungus world testbed has been considered for experiment which is has been implemented using SwI-Prolog 5.4.6. The fixed obstructs tend to be more versatile, to make a location that is specific to Fungus world testbed environment. The various parameters are introduced in an environment to test a agent’s performance. This modified   SARSA learning algorithm can   be more suitable in EMCAP architecture.  The experiments are conducted the modified   SARSA Learning system gets   more rewards compare to existing  SARSA algorithm.

Drivers of Late Pleistocene human survival and dispersal: an agent-based modeling and machine learning approach

2019 ◽  
Vol 221 ◽  
pp. 105867 ◽  
Author(s):  
Ali R. Vahdati ◽  
John David Weissmann ◽  
Axel Timmermann ◽  
Marcia S. Ponce de León ◽  
Christoph P.E. Zollikofer
Keyword(s):  
Machine Learning ◽  
Late Pleistocene ◽  
Agent Based Modeling ◽  
Learning Approach ◽  
Agent Based ◽  
Human Survival ◽  
Machine Learning Approach
Sign in / Sign up

Export Citation Format

Share Document