Exploring human behaviour models through causal summaries and machine learning

2013 ◽  
Author(s):  
M. Kvassay ◽  
L. Hluchy ◽  
P. Krammer ◽  
B. Schneider
Keyword(s):  
Machine Learning ◽  
Human Behaviour ◽  
Behaviour Models

A Driver's Mind

2019 ◽  
pp. 429-454
Author(s):  
Marco Lützenberger
Keyword(s):  
Point Of View ◽  
Human Behaviour ◽  
Infrastructure Management ◽  
Driver Behaviour ◽  
Human Driver ◽  
Psychological Point ◽  
Factors Of Influence ◽  
Traffic Systems ◽  
Behaviour Models ◽  
Traffic Simulations

Over the last decade, traffic simulation frameworks have advanced into an indispensible tool for traffic planning and infrastructure management. For these simulations, sophisticated models are used to “mimic” traffic systems in a lifelike fashion. In most cases, these models focus on a rather technical scope. Human factors, such as drivers' behaviours are either neglected or “estimated” without any proven connection to reality. This chapter presents an analysis of psychological driver models in order to establish such a connection. In order to do so, human driver behaviour is introduced from a psychological point of view, and state-of-the-art conceptualisations are analysed to identify factors that determine human traffic behaviour. These factors are explained in more detail, and their appliances in human behaviour models for traffic simulations are discussed. This chapter does not provide a comprehensive mapping from simulation requirements to particular characteristics of human driver behaviour but clarifies the assembly of human traffic behaviour, identifies relevant factors of influence, and thus, serves as a guideline for the development of human behaviour models for traffic simulations.

scholarly journals Organisational plasticity: can we really model human–agent behaviours?

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Dale Richards
Keyword(s):  
Sudden Change ◽  
Computational Modelling ◽  
Human Behaviour ◽  
Complex Nature ◽  
Key Factors ◽  
Content Type ◽  
Agent Based ◽  
Human Agent ◽  
External Pressures ◽  
Behaviour Models

PurposeThe ability for an organisation to adapt and respond to external pressures is a beneficial activity towards optimising efficiency and increasing the likelihood of achieving set goals. It can also be suggested that this very ability to adapt to one's surroundings is one of the key factors of resilience. The nature of dynamically responding to sudden change and then to return to a state that is efficient may be termed as possessing the characteristic of plasticity. Uses of agent-based systems in assisting in organisational processes may have a hand in facilitating an organisations' plasticity, and computational modelling has often been used to try and predict both agent and human behaviour. Such models also promise the ability to examine the dynamics of organisational plasticity through the direct manipulation of key factors. This paper discusses the use of such models in application to organisational plasticity and in particular the relevance to human behaviour and perception of agent-based modelling. The uses of analogies for explaining organisational plasticity is also discussed, with particular discussion around the use of modelling. When the authors consider the means by which the authors can adopt theories to explain this type of behaviour, models tend to focus on aspects of predictability. This in turn loses a degree of realism when we consider the complex nature of human behaviour, and more so that of human–agent behaviour.Design/methodology/approachThe methodology and approach used for this paper is reflected in the review of the literature and research.FindingsThe use of human–agent behaviour models in organisational plasticity is discussed in this paper.Originality/valueThe originality of this paper is based on the importance of considering the human–agent-based models. When compared to agent-based model approaches, analogy is used as a narrative in this paper.

Illicit Bitcoin transactions: challenges in getting to the who, what, when and where

2018 ◽  
Vol 21 (3) ◽  
pp. 297-313 ◽  
Author(s):  
Angela S.M. Irwin ◽  
Adam B. Turner
Keyword(s):  
Machine Learning ◽  
Law Enforcement ◽  
Cyber Security ◽  
Optimal Solution ◽  
Law Enforcement Agencies ◽  
Content Type ◽  
Predictive Policing ◽  
External Data ◽  
Functional Software ◽  
Behaviour Models

Purpose The purpose of this paper is to highlight the intelligence and investigatory challenges experienced by law enforcement agencies in discovering the identity of illicit Bitcoin users and the transactions that they perform. This paper proposes solutions to assist law enforcement agencies in piecing together the disparate and complex technical, behavioural and criminological elements that make up cybercriminal offending. Design/methodology/approach A literature review was conducted to highlight the main law enforcement challenges and discussions and examine current discourse in the areas of anonymity and attribution. The paper also looked at other research and projects that aim to identify illicit transactions involving cryptocurrencies and the darknet. Findings An optimal solution would be one which has a predictive capability and a machine learning architecture which automatically collects and analyses data from the Bitcoin blockchain and other external data sources and applies search criteria matching, indexing and clustering to identify suspicious behaviours. The implementation of a machine learning architecture would help improve results over time and would be less manpower intensive. Cyber investigators would also receive intelligence in a format and language that they understand and it would allow for intelligence-led and predictive policing rather than reactive policing. The optimal solution would be one which allows for intelligence-led, predictive policing and enables and encourages information sharing between multiple stakeholders from the law enforcement, financial intelligence units, cyber security organisations and fintech industry. This would enable the creation of red flags and behaviour models and the provision of up-to-date intelligence on the threat landscape to form a viable intelligence product for law enforcement agencies so that they can more easily get to the who, what, when and where. Originality/value The development of a functional software architecture that, in theory, could be used to detected suspicious illicit transactions on the Bitcoin network.

A Driver’s Mind

2014 ◽  
pp. 182-205 ◽  
Author(s):  
Marco Lützenberger
Keyword(s):  
Point Of View ◽  
Human Behaviour ◽  
Infrastructure Management ◽  
Driver Behaviour ◽  
Human Driver ◽  
Psychological Point ◽  
Factors Of Influence ◽  
Traffic Systems ◽  
Behaviour Models ◽  
Traffic Simulations

Over the last decade, traffic simulation frameworks have advanced into an indispensible tool for traffic planning and infrastructure management. For these simulations, sophisticated models are used to “mimic” traffic systems in a lifelike fashion. In most cases, these models focus on a rather technical scope. Human factors, such as drivers’ behaviours are either neglected or “estimated” without any proven connection to reality. This chapter presents an analysis of psychological driver models in order to establish such a connection. In order to do so, human driver behaviour is introduced from a psychological point of view, and state-of-the-art conceptualisations are analysed to identify factors that determine human traffic behaviour. These factors are explained in more detail, and their appliances in human behaviour models for traffic simulations are discussed. This chapter does not provide a comprehensive mapping from simulation requirements to particular characteristics of human driver behaviour but clarifies the assembly of human traffic behaviour, identifies relevant factors of influence, and thus, serves as a guideline for the development of human behaviour models for traffic simulations.

Sign in / Sign up

Export Citation Format

Share Document