An Intelligent System for Aggression De-Escalation Training

2010 IEEE International Conference on Systems, Man and Cybernetics, 2010

This paper presents work addressing the challenges of video analysis for automatic detection of aggression in a train. Using data from surveillance cameras, the system assists human operators in their work. It is unobtrusive and respects the privacy of passengers. We used existing algorithms to recognize and classify human behavior. While evaluating the algorithms we paid special attention to their ability to cope with environment specific issues, such as varying lighting conditions and (self)occlusions. A passenger behavior model was developed based on many hours of observing and studying professional operators as they analyze and respond to surveillance data. Experiments were conducted in a real train to evaluate the detection system.

2007 IEEE Conference on Advanced Video and Signal Based Surveillance, 2007

The paper presents a knowledge-based system designed to detect evidence of aggression by means of audio analysis. The detection is based on the way sounds are analyzed and how they attract attention in the human auditory system. The performance achieved is comparable to human performance in complex social environments. The SIgard system has been deployed in a number of different real-life situations and was tested extensively in the inner city of Groningen. Experienced police observers have annotated ~1400 recordings with various degrees of shouting, which were used for optimization. All essential events and a small number of nonessential aggressive events were detected. The system produces only a few false alarms (non-shouts) per microphone per year and misses no incidents. This makes it the first successful detection system for a non-trivial target in an unconstrained environment.

2004

The Navy is shifting its training and education from traditional methods, such as on-site instruction, texts, and observing students uring drills, to computer-supported learning such as web-based nstruction and computer simulations in lieu of live drills. This transition presents the challenge of keeping the best parts of traditional methods of instruction while obtaining the advantages that computers afford. The challenge is more difficult because to maximize savings in manpower, money and time, computer-based learning must be able to teach, evaluate and give feedback to students without any instructor in the loop. A valuable aspect of traditional training methods, in which computers currently fall short, is the 'mentor/student' relationship: an experienced person discussing a novice's performance with him or her. The mentor gives the student direct, personalized feedback in a setting where the student can ask questions and discuss issues. Most computer simulations are lacking in this type of interaction. We propose that giving computers the ability to debrief and discuss a student's actions using natural language will more closely simulate this relationship and greatly improve the effectiveness of computer-based learning. To assess this hypothesis, we are utilizing natural language technology to (1) allow students to use a damage control trainer for surface ships by speaking with the simulation system, and (2) to support a subsequent spoken discussion with an intelligent tutoring system that provides an after action review of the student's performance. The combined system performs a mentoring function, helping students learn correct actions and avoid 'practicing mistakes'. We are studying the usefulness of this mentoring system for students under training in damage control, and will present results about differences in rate of learning with and without mentoring. An additional benefit of natural language interaction with the computer systems is that students train as they will actually perform on duty.

Lecture Notes in Computer Science, 2008

Opponent Modeling is one of the most attractive and practical arenas in Multi Agent System (MAS) for predicting and identifying the future behaviors of opponent. This paper introduces a novel approach using rule based expert system towards opponent modeling in RoboCup Soccer Coach Simulation. In this scene, an autonomous coach agent is able to identify the patterns of the opponent by analyzing the opponent's past games and advising own players. For this purpose, the main goal of our research comprises two complementary parts: (a) developing a 3-tier learning architecture for classifying opponent behaviors. To achieve this objective, sequential events of the game are identified using environmental data. Then the patterns of the opponent are predicted using statistical calculations. Eventually, by comparing the opponent patterns with the rest of team's behavior, a model of the opponent is constructed. (b) designing a rule based expert system containing provocation strategies to expedite detection of opponent patterns. These items mentioned are used by coach, to model the opponent and generate an appropriate strategy to play against the opponent. This structure is tested in RoboCup Soccer Coach Simulation and MRLCoach was the champion at RoboCup 2006 in Germany.

2006

Using empathic virtual agents for Personal and Social Education is a powerful and immersive way to sensitise students for the problems and dangers related to persistent aggressive behaviour among students, also known as bullying. The work reported here relates to the evaluation of applying such agents in schools in the UK, Portugal, and Germany as well as to consequences that can be drawn from these evaluation results. The Bullying Problem The problem of bullying is well-known to educators and parents across Europe. Among others, the enduring victimisation of one student by one or more other students may cause health problems, depression, truancy, and even suicide in the victim. It has been defined as “repeated action that occurs regularly over time, and usually involves an imbalance in strength, either real or perceived” (Olweus, 1999). Bullying means various types of aggressive behaviour including punching, kicking, hitting (direct physical bullying), teasing and cruel name-callin...

2018

Simulator-based training platforms have become increasingly popular on the grounds of their potential to facilitate skill acquisition within safe and controlled environments. However, current technology is limited in its ability to adapt to individual trainees. Tailoring is in fact typically based on recorded simulation inputs and outputs, or relies on costly and time-consuming trainer-driven interventions, as opposed to direct monitoring of trainee state. This research explores whether automated detection of trainee emotional state can be used to drive real-time changes to the simulator control. The present paper reports on preliminary work to establish the technical viability of such an intervention using current emotion detection technology within a state-of-the-art fixed-base driving simulator environment. Data on the accuracy of the emotion detection software supports the feasibility of the approach, thereby suggesting the possibility of implementing emotion-driven training trajectories bespoke to the needs of individual trainees.

2009

In this chapter, we give an overview of the FearNot! virtual drama system constructed for use in education against bullying. The motivation for the system is discussed and the chapter considers issues relating to believability. It describes the emotionally driven architecture used for characters as well as the management of the overall story and finally considers issues relating to evaluation of systems like this.

HCI 2018

Across multiple sectors training programmes aim to help learners improve their communication skills. It is well recognised that non-verbal 'social signals' play an important role in communication effectiveness. Previous research in the social signalling domain meticulously observed hours of videos and conducted observational studies to identify these social signals. This resulted in subjective inferences about human emotions. The aim of the current research is to investigate whether social signals can be detected and trained using automated technology in a person-toperson training context in three stages; exploratory stage, feedback design stage and an experimental stage. This research will allow trainers to provide objective feedback to trainees about their performance with a clear criterion. This research will also explore the best way to feedback signals detected and whether this is effective and actionable. Further long-term benefits of this research might contribute to the eventual development of a training avatar.

The Race to Brand De-escalation Training for Law Enforcement, 2019

Abstract This project began with the goal of producing a definitive decision-making tool for local, suburban Police Chiefs that would help them decide which de-escalation training programs made sense for addressing their unique needs. Creating a tool that could quickly and uniformly apply proved unrealistic because de-escalation training for law enforcement is an emerging field with emerging standards of practice. Instead, first-hand experience with five trainings resulted in creating tools that introduce readers to the complexities of comparing for choosing de-escalation training programs. Theories of conflict resolution were applied to the most common training content, methods and terminology used by the trainers of these five programs. Theoretical comparisons revealed important parallels and differences between the use and application of terminology and skills development in areas such as active listening, naming, framing, rapport, empathy, and influencing behavioral change. The place for empathy in de-escalation emerged as both a key overlap and disconnect between the professional literature. This report provides a theoretical comparison made visually palpable through real-life stories of police de-escalation, followed by a brief comparative review of five de-escalation training programs and trainer profiles. A new look at a commonly used stairway model is offered and explained. Finally, the paper concludes with a general discussion about the need and opportunities for additional research on the topic of de-escalation training for law enforcement. Ultimately, this paper lays the framework for creating cross-disciplinary standards. Keywords: De-escalation Training, Active Listening, Rapport, Empathy, Law Enforcement Training, Conflict Resolution, Police Training, Training Requirements