Context-Driven Proactive Decision Support for Hybrid Teams

AI Magazine ◽  
2019 ◽  
Vol 40 (3) ◽  
pp. 41-57
Author(s):  
Manisha Mishra ◽  
Pujitha Mannaru ◽  
David Sidoti ◽  
Adam Bienkowski ◽  
Lingyi Zhang ◽  
...  
Keyword(s):  
Decision Support ◽  
Situational Awareness ◽  
Feature Space ◽  
Human Interaction ◽  
Superior Performance ◽  
Uncertain Environments ◽  
Cognitive States ◽  
Contextual Elements ◽  
Human Operators ◽  
Smart Machine

A synergy between AI and the Internet of Things (IoT) will significantly improve sense-making, situational awareness, proactivity, and collaboration. However, the key challenge is to identify the underlying context within which humans interact with smart machines. Knowledge of the context facilitates proactive allocation among members of a human–smart machine (agent) collective that balances auto­nomy with human interaction, without displacing humans from their supervisory role of ensuring that the system goals are achievable. In this article, we address four research questions as a means of advancing toward proactive autonomy: how to represent the interdependencies among the key elements of a hybrid team; how to rapidly identify and characterize critical contextual elements that require adaptation over time; how to allocate system tasks among machines and agents for superior performance; and how to enhance the performance of machine counterparts to provide intelligent and proactive courses of action while considering the cognitive states of human operators. The answers to these four questions help us to illustrate the integration of AI and IoT applied to the maritime domain, where we define context as an evolving multidimensional feature space for heterogeneous search, routing, and resource allocation in uncertain environments via proactive decision support systems.

scholarly journals Assessing a Decision Support Tool for SOC Analysts

2021 ◽  
Author(s):  
Jassim Happa ◽  
Ioannis Agrafiotis ◽  
Martin Helmhout ◽  
Thomas Bashford-Rogers ◽  
Michael Goldsmith ◽  
...  
Keyword(s):  
Decision Support ◽  
Mixed Method ◽  
User Study ◽  
Situational Awareness ◽  
Decision Support Tool ◽  
Lessons Learned ◽  
Visualization Tool ◽  
Support Tool ◽  
Response Strategies ◽  
Method Approach

In recent years, many tools have been developed to understand attacks that make use of visualization, but few examples aims to predict real-world consequences. We have developed a visualization tool that aims to improve decision support during attacks. Our tool visualizes propagation of risks from IDS and AV-alert data by relating sensor alerts to Business Process (BP) tasks and machine assets: an important capability gap present in many Security Operation Centres (SOCs) today. In this paper we present a user study in which we evaluate the tool's usability and ability to deliver situational awareness to the analyst. Ten analysts from seven SOCs performed carefully designed tasks related to understanding risks and prioritising recovery decisions. The study was conducted in laboratory conditions, with simulated attacks, and used a mixed-method approach to collect data from questionnaires, eyetracking and voice-recorded interviews. The findings suggest that providing analysts with situational awareness relating to business priorities can help them prioritise response strategies. Finally, we provide an in-depth discussion on the wider questions related to user studies in similar conditions as well as lessons learned from our user study and developing a visualization tool of this type.

Comparing Two Decision Support Modes Using the Cognitive Shadow Online Policy-Capturing System

2020 ◽  
Vol 64 (1) ◽  
pp. 1125-1129
Author(s):  
Katherine Labonté ◽  
Daniel Lafond ◽  
Aren Hunter ◽  
Heather F. Neyedli ◽  
Sébastien Tremblay
Keyword(s):  
Decision Making ◽  
Decision Support ◽  
Response Pattern ◽  
Policy Capturing ◽  
Model Accuracy ◽  
Prototype Tool ◽  
Human Operators ◽  
Support Decision Making ◽  
Threat Evaluation

The Cognitive Shadow is a prototype tool intended to support decision making by autonomously modeling human operators’ response pattern and providing online notifications to the operators about the decision they are expected to make in new situations. Since the system can be configured either in a reactive “shadowing” or a proactive “recommendation” mode, this study aimed to determine its most effective mode in terms of human and model accuracy, workload, and trust. Subjects participated in an aircraft threat evaluation simulation without decision support or while using either mode of the Cognitive Shadow. Whereas the recommendation mode had no advantage over the control condition, the shadowing mode led to higher human and model accuracy. These benefits were maintained even when the tool was unexpectedly removed. Neither mode influenced workload, and the initial lower trust rating in the shadowing mode faded quickly, making it the best overall configuration for the cognitive assistant.

scholarly journals Online Multilingual Hate Speech Detection: Experimenting with Hindi and English Social Media

2020 ◽  
Author(s):  
Neeraj Vashistha ◽  
Arkaitz Zubiaga
Keyword(s):  
Social Media ◽  
Hate Speech ◽  
Model Performance ◽  
Academic Community ◽  
Human Interaction ◽  
Superior Performance ◽  
Competitive Performance ◽  
Speech Detection ◽  
Improve Model ◽  
Use Of The Internet

The exponential increase in the use of the Internet and social media over the last two decades has changed human interaction. This has led to many positive outcomes, but at the same time it has brought risks and harms. While the volume of harmful content online, such as hate speech, is not manageable by humans, interest in the academic community to investigate automated means for hate speech detection has increased. In this study, we analyse six publicly available datasets by combining them into a single homogeneous dataset and classify them into three classes, abusive, hateful or neither. We create a baseline model and we improve model performance scores using various optimisation techniques. After attaining a competitive performance score, we create a tool which identifies and scores a page with effective metric in near-real time and uses the same as feedback to re-train our model. We prove the competitive performance of our multilingual model on two langauges, English and Hindi, leading to comparable or superior performance to most monolingual models.

Computational Methods and Tools for Decision Support in Biomedicine

2009 ◽  
pp. 1-17
Author(s):  
Ioannis Dimou ◽  
Michalis Zervakis ◽  
David Lowe ◽  
Manolis Tsiknakis
Keyword(s):  
Decision Making ◽  
Decision Support ◽  
Computational Methods ◽  
Pattern Analysis ◽  
State Of The Art ◽  
Biomedical Informatics ◽  
Feature Space ◽  
Diagnostic Tools ◽  
Methodological Issues ◽  
Medical Problems

The automation of diagnostic tools and the increasing availability of extensive medical datasets in the last decade have triggered the development of new analytical methodologies in the context of biomedical informatics. The aim is always to explore a problem’s feature space, extract useful information and support clinicians in their time, volume, and accuracy demanding decision making tasks. From simple summarizing statistics to state-of-the-art pattern analysis algorithms, the underlying principles that drive most medical problems show trends that can be identified and taken into account to improve the usefulness of computerized medicine to the field-clinicians and ultimately to the patient. This chapter presents a thorough review of this field and highlights the achievements and shortcomings of each family of methods. The authors’ effort has been focused on methodological issues as to generalize useful conclusions based on the large number of notable, yet case-specific developments presented in the field.

A Cross-Domain Approach to Designing an Unobtrusive System to Assess Human State and Predict Upcoming Performance Deficits

2016 ◽  
Vol 60 (1) ◽  
pp. 707-711 ◽  
Author(s):  
Bethany Bracken ◽  
Noa Palmon ◽  
Lee Kellogg ◽  
Seth Elkin-Frankston ◽  
Michael Farry
Keyword(s):  
Situational Awareness ◽  
Work Environments ◽  
Cognitive Workload ◽  
Performance Deficits ◽  
Cognitive Readiness ◽  
Cross Domain ◽  
Mission Success ◽  
Working Together ◽  
Human Operators ◽  
And Performance

Many work environments are fraught with highly variable demands on cognitive workload, fluctuating between periods of high operational demand to the point of cognitive overload, to long periods of low workload bordering on boredom. When cognitive workload is not in an optimal range at either end of the spectrum, it can be detrimental to situational awareness and operational readiness, resulting in impaired cognitive functioning (Yerkes and Dodson, 1908). An unobtrusive system to assess the state of the human operator (e.g., stress, cognitive workload) and predict upcoming performance deficits could warn operators when steps should be taken to augment cognitive readiness. This system would also be useful during testing and evaluation (T&E) when new tools and systems are being evaluated for operational use. T&E researchers could accurately evaluate the cognitive and physical demands of these new tools and systems, and the effects they will have on task performance and accuracy. In this paper, we describe an approach to designing such a system that is applicable across environments. First, a suite of sensors is used to perform real-time synchronous data collection in a robust and unobtrusive fashion, and provide a holistic assessment of operators. Second, the best combination of indicators of operator state is extracted, fused, and interpreted. Third, performance deficits are comprehensively predicted, optimizing the likelihood of mission success. Finally, the data are displayed in such a way that supports the information requirements of any user. The approach described here is one we have successfully used in several projects, including modeling cognitive workload in the context of high-tempo, physically demanding environments, and modeling individual and team workload, stress, engagement, and performance while working together on a computerized task. We believe this approach is widely applicable and useful across domains to dramatically improve the mission readiness of human operators, and will improve the design and development of tools available to assist the operator in carrying out mission objectives. A system designed using this approach could enable crew to be aware of impending deficits to aid in augmenting mission performance, and will enable more effective T&E by measuring workload in response to new tools and systems while they are being designed and developed, rather than once they are deployed.

scholarly journals Enhanced Situational Awareness through a Decision Support Service for Optimal Allocation of Resources and Response Capacity

2017 ◽  
Vol 32 (S1) ◽  
pp. S229
Author(s):  
Irene Christodoulou ◽  
George M. Milis ◽  
Panayiotis Kolios ◽  
Christos Panayiotou ◽  
Marios Polycarpou ◽  
...  
Keyword(s):  
Decision Support ◽  
Optimal Allocation ◽  
Situational Awareness ◽  
Support Service ◽  
Allocation Of Resources ◽  
Response Capacity

scholarly journals Bayesian generalized biclustering analysis via adaptive structured shrinkage

Biostatistics ◽  
2018 ◽  
Vol 21 (3) ◽  
pp. 610-624
Author(s):  
Ziyi Li ◽  
Changgee Chang ◽  
Suprateek Kundu ◽  
Qi Long
Keyword(s):  
Negative Binomial ◽  
Feature Space ◽  
Biological Information ◽  
Superior Performance ◽  
Data Matrix ◽  
Data Types ◽  
Binomial Data ◽  
Multiple Data ◽  
Local Patterns ◽  
Shrinkage Prior

Summary Biclustering techniques can identify local patterns of a data matrix by clustering feature space and sample space at the same time. Various biclustering methods have been proposed and successfully applied to analysis of gene expression data. While existing biclustering methods have many desirable features, most of them are developed for continuous data and few of them can efficiently handle -omics data of various types, for example, binomial data as in single nucleotide polymorphism data or negative binomial data as in RNA-seq data. In addition, none of existing methods can utilize biological information such as those from functional genomics or proteomics. Recent work has shown that incorporating biological information can improve variable selection and prediction performance in analyses such as linear regression and multivariate analysis. In this article, we propose a novel Bayesian biclustering method that can handle multiple data types including Gaussian, Binomial, and Negative Binomial. In addition, our method uses a Bayesian adaptive structured shrinkage prior that enables feature selection guided by existing biological information. Our simulation studies and application to multi-omics datasets demonstrate robust and superior performance of the proposed method, compared to other existing biclustering methods.

Sign in / Sign up

Export Citation Format

Share Document