A unified model for context-based behavioural modelling and classification

Dabrowski, Joel Janek; Villiers, J. P. de

doi:10.1016/j.eswa.2015.04.061

Cited by 13 publications

(6 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One approach would be to include contextual information. This can be achieved in the SLDS using methods such as those described in [22,23,24]. Contextual information could include road signs, proximity to crossing areas, and traffic congestion levels.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction

Dabrowski¹,

Villiers²,

Rahman³

et al. 2019

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

The time it takes for a classifier to make an accurate prediction can be crucial in many behaviour recognition problems. For example, an autonomous vehicle should detect hazardous pedestrian behaviour early enough for it to take appropriate measures. In this context, we compare the switching linear dynamical system (SLDS) and a three-layered bi-directional long short-term memory (LSTM) neural network, which are applied to infer pedestrian behaviour from motion tracks. We show that, though the neural network model achieves an accuracy of 80%, it requires long sequences to achieve this (100 samples or more). The SLDS, has a lower accuracy of 74%, but it achieves this result with short sequences (10 samples). To our knowledge, such a comparison on sequence length has not been considered in the literature before. The results provide a key intuition of the suitability of the models in time-critical problems.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The SLDS has been extended in various ways, such as introducing variables representing behavioural context information. Such models have been applied to maritime piracy applications [22,23] and abalone poaching applications [24]. Linderman et.…”

Section: Switching Linear Dynamical Systemmentioning

confidence: 99%

Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction

Dabrowski¹,

Villiers²,

Rahman³

et al. 2019

Communications in Computer and Information Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Sentiment analysis move towards content, concept and context-based text analysis of natural language text [12], [13]. Context may be defined as any information that can be used to characterize the situation of an object or entity [14]. In textual form, context considers the environment of the selected term in a sentence.…”

Section: Overview Of Contextmentioning

confidence: 99%

A Review of Contextual Information for Context-Based Approach in Sentiment Analysis

Yusof

Mohamed²,

Abdul-Rahman³

2018

IJMLC

View full text Add to dashboard Cite

Online opinionated data has increased tremendously since the arrival of web 2.0. Users have the authority to generate online content expressing their sentiments or opinions regarding subjects of interest. Although these phenomena caused the problem of information overload, the opinionated data is valuable and beneficial to others. Looking at the prominent significance of this issue, many researchers grab this opportunity to further investigate sentiment analysis. The main task of sentiment analysis is to classify opinions into several orientations. However, the orientation of sentiment is highly dependent on the context of sentiment text. Thus, it is important to consider contextual information in order to correctly classify sentiments. This paper would like to facilitate researchers in capturing the contextual information of context-based approach in sentiment analysis; which includes sequence and collocation of words, negation handling, and ambiguity. Several recent studies that utilize the contextual information are also discussed. Besides, this paper presents the state of art of context based on the level, type, and representation of context. With the help of this review, researchers will be able to correctly classify sentiments based on context in improving the performance of sentiment analyzer.

show abstract

“…Lane et al [13] have employed Bayesian networks to detect threatening behaviours such as 'close approach' or 'unexpected activity' based on location, speed and heading of the suspicious boat. Dabrowski, et al [6] classify vessels as pirate vessels, fishing vessels or transport vessels based on the tracked trajectory of the vessel.…”

Section: Related Workmentioning

confidence: 99%

Loitering Behaviour Detection of Boats at Sea

Patino

Ferryman

2017

2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

View full text Add to dashboard Cite

We present in this paper a technique for Loitering detection based on the analysis of activity zones of the monitored area. Activity zones are learnt online employing a soft computing-based algorithm which takes as input the trajectory of object mobiles appearing on the scene. Statistical properties on zone occupancy and transition between zones makes it possible to discover abnormalities without the need to learn abnormal models beforehand. We have applied this approch to the PETS2017 IPATCH dataset and addressed the challenge on detecting skiff boats loitering around a protected ship, which eventually is attacked by the skiffs. Our results show that we can detect the suspicious behaviour on time to trigger an early warning.

show abstract

A unified model for context-based behavioural modelling and classification

Cited by 13 publications

References 105 publications

Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction

Deep Learning and Statistical Models for Time-Critical Pedestrian Behaviour Prediction

A Review of Contextual Information for Context-Based Approach in Sentiment Analysis

Loitering Behaviour Detection of Boats at Sea

Contact Info

Product

Resources

About