sensors-logo

Journal Browser

Journal Browser

Context and Activity Modelling and Recognition

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Physical Sensors".

Deadline for manuscript submissions: closed (31 August 2018) | Viewed by 21585

Special Issue Editors

Data and Web Science Group, University of Mannheim, 68159 Mannheim, Germany
Interests: artificial intelligence; activity recognition
Institute for Parallel and Distributed Systems, University of Stuttgart, Stuttgart, Germany
Interests: Internet of Things; Industry 4.0; Context recognition
Institute for Parallel and Distributed Systems, University of Stuttgart, Stuttgart, Germany
Interests: Internet of Things; Context recognition; Data flow processing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The 14th Workshop on Context and Activity Modeling and Recognition (CoMoRea'18) will be held in Athens, Greece, 19–23 March, 2018.

This workshop’s aim is to advance the state-of-the-art in context modeling and reasoning and discuss fundamental issues in context processing and management. The goal is to identify concepts, theories and methods applicable to context modeling and context reasoning, as well as system-oriented issues related to the design and implementation of context-aware systems. In particular, the following topics are of interest to this workshop:

  • Context modeling techniques and domain-specific context models
  • Ontology-based approaches to context modeling and reasoning
  • Ontologies of Activities and Context
  • Hybrid context models and advanced issues in context modeling, including issues of information quality, ambiguity, and provenance
  • Context reasoning algorithms, their complexity and accuracy
  • Discovery, reuse, privacy, security and trust of context information
  • Distributed and scalable context management
  • Tool support for context modeling and development of context model-based applications
  • Machine learning and reasoning techniques for context and activity recognition
  • High Level Activity Recognition from Sensor Data
  • Machine Learning and Computer Vision for Context and Activity Recognition
  • Reference Datasets and Benchmarks for Activity Recognition and Context Reasoning

We invite investigators to contribute original research articles, as well as review articles, to this Special Issue.

Prof. Dr. Heiner Stuckenschmidt
Dr. Matthias Wieland
Dipl.-Inf. Pascal Hirmer
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (5 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

27 pages, 2006 KiB  
Article
Semantic-Enhanced Multi-Dimensional Markov Chains on Semantic Trajectories for Predicting Future Locations
by Antonios Karatzoglou, Dominik Köhler and Michael Beigl
Sensors 2018, 18(10), 3582; https://doi.org/10.3390/s18103582 - 22 Oct 2018
Cited by 12 | Viewed by 5563
Abstract
In this work, we investigate the performance of Markov Chains with respect to modelling semantic trajectories and predicting future locations. In the first part, we examine whether and to what degree the semantic level of semantic trajectories affects the predictive performance of a [...] Read more.
In this work, we investigate the performance of Markov Chains with respect to modelling semantic trajectories and predicting future locations. In the first part, we examine whether and to what degree the semantic level of semantic trajectories affects the predictive performance of a spatial Markov model. It can be shown that the choice of the semantic level when describing trajectories has a significant impact on the accuracy of the models. High-level descriptions lead to better results than low-level ones. The second part introduces a multi-dimensional Markov Chain construct that considers, besides locations, additional context information, such as time, day and the users’ activity. While the respective approach is able to outperform our baseline, we could also identify some limitations. These are mainly attributed to its sensitivity towards small-sized training datasets. We attempt to overcome this issue, among others, by adding a semantic similarity analysis component to our model that takes the varying role of locations due each time to the respective purpose of visiting the particular location explicitly into consideration. To capture the aforementioned dynamics, we define an entity, which we refer to as Purpose-of-Visit-Dependent Frame (PoVDF). In the third part of this work, we describe in detail the PoVDF-based approach and we evaluate it against the multi-dimensional Markov Chain model as well as with a semantic trajectory mining and prefix tree based model. Our evaluation shows that the PoVDF-based approach outperforms its competition and lays a solid foundation for further investigation. Full article
(This article belongs to the Special Issue Context and Activity Modelling and Recognition)
Show Figures

Figure 1

19 pages, 991 KiB  
Article
Classifier for Activities with Variations
by Rabih Younes, Mark Jones and Thomas L. Martin
Sensors 2018, 18(10), 3529; https://doi.org/10.3390/s18103529 - 18 Oct 2018
Cited by 5 | Viewed by 2351
Abstract
Most activity classifiers focus on recognizing application-specific activities that are mostly performed in a scripted manner, where there is very little room for variation within the activity. These classifiers are mainly good at recognizing short scripted activities that are performed in a specific [...] Read more.
Most activity classifiers focus on recognizing application-specific activities that are mostly performed in a scripted manner, where there is very little room for variation within the activity. These classifiers are mainly good at recognizing short scripted activities that are performed in a specific way. In reality, especially when considering daily activities, humans perform complex activities in a variety of ways. In this work, we aim to make activity recognition more practical by proposing a novel approach to recognize complex heterogeneous activities that could be performed in a wide variety of ways. We collect data from 15 subjects performing eight complex activities and test our approach while analyzing it from different aspects. The results show the validity of our approach. They also show how it performs better than the state-of-the-art approaches that tried to recognize the same activities in a more controlled environment. Full article
(This article belongs to the Special Issue Context and Activity Modelling and Recognition)
Show Figures

Figure 1

19 pages, 6501 KiB  
Article
A Robotic Context Query-Processing Framework Based on Spatio-Temporal Context Ontology
by Seokjun Lee and Incheol Kim
Sensors 2018, 18(10), 3336; https://doi.org/10.3390/s18103336 - 05 Oct 2018
Cited by 7 | Viewed by 3657
Abstract
Service robots operating in indoor environments should recognize dynamic changes from sensors, such as RGB-depth (RGB-D) cameras, and recall the past context. Therefore, we propose a context query-processing framework, comprising spatio-temporal robotic context query language (ST-RCQL) and a spatio-temporal robotic context query-processing system [...] Read more.
Service robots operating in indoor environments should recognize dynamic changes from sensors, such as RGB-depth (RGB-D) cameras, and recall the past context. Therefore, we propose a context query-processing framework, comprising spatio-temporal robotic context query language (ST-RCQL) and a spatio-temporal robotic context query-processing system (ST-RCQP), for service robots. We designed them based on spatio-temporal context ontology. ST-RCQL can query not only the current context knowledge, but also the past. In addition, ST-RCQL includes a variety of time operators and time constants; thus, queries can be written very efficiently. The ST-RCQP is a query-processing system equipped with a perception handler, working memory, and backward reasoner for real-time query-processing. Moreover, ST-RCQP accelerates query-processing speed by building a spatio-temporal index in the working memory, where percepts are stored. Through various qualitative and quantitative experiments, we demonstrate the high efficiency and performance of the proposed context query-processing framework. Full article
(This article belongs to the Special Issue Context and Activity Modelling and Recognition)
Show Figures

Figure 1

19 pages, 5259 KiB  
Article
An Automatic User Activity Analysis Method for Discovering Latent Requirements: Usability Issue Detection on Mobile Applications
by Soojin Park, Sungyong Park and Kyeongwook Ma
Sensors 2018, 18(9), 2963; https://doi.org/10.3390/s18092963 - 05 Sep 2018
Cited by 2 | Viewed by 3254
Abstract
Starting with the Internet of Things (IoT), new forms of system operation concepts have emerged to provide creative services through collaborations among autonomic devices. Following these paradigmatic changes, the ability of each participating system to automatically diagnose the degree of quality it is [...] Read more.
Starting with the Internet of Things (IoT), new forms of system operation concepts have emerged to provide creative services through collaborations among autonomic devices. Following these paradigmatic changes, the ability of each participating system to automatically diagnose the degree of quality it is providing is inevitable. This paper proposed a method to automatically detect symptoms that hinder certain quality attributes. The method consisted of three steps: (1) extracting information from real usage logs and automatically generating an activity model from the captured information; (2) merging multiple user activity models into a single, representative model; and (3) detecting differences between the representative user activity model, and an expected activity model. The proposed method was implemented in a domain-independent framework, workable on the Android platform. Unlike other related works, we used quantitative evaluation results to show the benefits of applying the proposed method to five Android-based, open-source mobile applications. The evaluation results showed that the average precision rate for the automatic detection of symptoms was 70%, and the success rate for user implementation of usage scenarios demonstrated an improvement of around 21%, when the automatically detected symptoms were resolved. Full article
(This article belongs to the Special Issue Context and Activity Modelling and Recognition)
Show Figures

Figure 1

18 pages, 2965 KiB  
Article
Action Recognition by an Attention-Aware Temporal Weighted Convolutional Neural Network
by Le Wang, Jinliang Zang, Qilin Zhang, Zhenxing Niu, Gang Hua and Nanning Zheng
Sensors 2018, 18(7), 1979; https://doi.org/10.3390/s18071979 - 21 Jun 2018
Cited by 32 | Viewed by 6134
Abstract
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs). However, effective and efficient methods for incorporation of temporal information into CNNs are still being actively explored in the recent literature. [...] Read more.
Research in human action recognition has accelerated significantly since the introduction of powerful machine learning tools such as Convolutional Neural Networks (CNNs). However, effective and efficient methods for incorporation of temporal information into CNNs are still being actively explored in the recent literature. Motivated by the popular recurrent attention models in the research area of natural language processing, we propose the Attention-aware Temporal Weighted CNN (ATW CNN) for action recognition in videos, which embeds a visual attention model into a temporal weighted multi-stream CNN. This attention model is simply implemented as temporal weighting yet it effectively boosts the recognition performance of video representations. Besides, each stream in the proposed ATW CNN framework is capable of end-to-end training, with both network parameters and temporal weights optimized by stochastic gradient descent (SGD) with back-propagation. Our experimental results on the UCF-101 and HMDB-51 datasets showed that the proposed attention mechanism contributes substantially to the performance gains with the more discriminative snippets by focusing on more relevant video segments. Full article
(This article belongs to the Special Issue Context and Activity Modelling and Recognition)
Show Figures

Figure 1

Back to TopTop