Journal Browser

Journal Browser

Special Issue "Multisensor and Multimodal Datasets in Intelligent Home for Context-Awareness, Human Home Interaction and Dialogue"

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

Deadline for manuscript submissions: closed (31 March 2021) | Viewed by 3799

Special Issue Editors

Laboratoire d'informatique de Grenoble (LIG), Domaine Universitaire de Saint Martin d'Hères, FRANCE
Interests: Multisource Context-Aware Activity and Situation Recognition; Knowledge-based Decision Support System; Natural Language Generation; Multisource Automatic Speech Recognition
Institute of Computer Science, University of Rostock, 18051 Rostock, Germany
Interests: activity and intention recognition; human behavior models; knowledge elicitation; natural language processing; automatic extraction of behavior models from textual sources
Special Issues, Collections and Topics in MDPI journals
Nara Institute of Science and Technology (NAIST), 8916-5, Takayama-machi, Ikoma, Nara, Japan
Interests: Ubiquitous computing system; Social information system
Department of Electrical & Electronic Engineering, University of Bristol, Bristol, UK
Interests: activity recognition; data visualisation; social and physical sensors
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Intelligent home systems rely on sensor information and models of the underlying user behaviour to reason about the needs of the users and assist them in their everyday activities. With the continued shift from knowledge-based approaches to methods relying on machine learning techniques, the need of large-scale datasets of high quality increases. Datasets are essential both in designing and training the system to recognise and reason about the situation, either through the definition of a suitable situation model in knowledge-driven applications or through the preparation of training data for learning tasks in data-driven models. Hence, the quality of datasets can have a significant impact on the performance of the derived systems. Datasets are also vital for validating and quantifying the performance of applications. Furthermore, well documented datasets with reliable annotation ensure the reproducibility of research results. While datasets and the process of collecting and annotating them are highly developed in some fields, such as natural language processing (NLP) or computer vision, in smart homes, this data collection process is less systematic. This is due to several reasons:

  • There is a large diversity of sensors and applications (highly variable input/output);
  • The smart home domain is still a developing research field as opposed to some mature tasks such as in NLP;
  • It is difficult to acquire ground truth in smart homes without jeopardizing the ecological aspect of the data being collected;
  • There are no established roadmaps and standards for annotating data for smart homes, which results in datasets with different annotation granularity and structure, making them difficult to re-use in other applications/environments.

This call encourages submissions reporting methodological or experimental studies about ground truth labelled multisensor corpus collections. In particular, ecological corpus including several modalities (home automation sensors, wearable sensors, microphones, video cameras) and several dwellers are very welcome. All submissions should contain a section about the ethical positioning of the study/project. Further, when relevant, authors reporting a corpus collection are encouraged to make it available to the community and register it through a DOI. We also look forward to submissions which provide guidelines for sensor data collection and annotation or which empirically analyse existing or novel sensor datasets especially in the context of transfer learning.

The topics of interest include but are not limited to:

  • Methods and intelligent tools for ecological corpus collection in intelligent or the general houses;
  • Multimodal corpora (microphones, video cameras and any other sensors) made publicly available to the community;
  • Processes of and best practices in collecting ecological user data;
  • Improving and evaluating the quality of annotations;
  • Ethical and privacy issues in data collection in home;
  • Overview of currently available corpora in smart home;
  • Synthetic data generation for improving models learning;
  • Machine learning techniques to re-use mismatched data.

Dr. François Portet
Dr. Kristina Yordanova
Dr. Hirohiko Suwa
Dr. Emma Tonkin
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at 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 (1 paper)

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


SALON: Simplified Sensing System for Activity of Daily Living in Ordinary Home
Sensors 2020, 20(17), 4895; - 29 Aug 2020
Cited by 12 | Viewed by 3170
As aging populations continue to grow, primarily in developed countries, there are increasing demands for the system that monitors the activities of elderly people while continuing to allow them to pursue their individual, healthy, and independent lifestyles. Therefore, it is required to develop [...] Read more.
As aging populations continue to grow, primarily in developed countries, there are increasing demands for the system that monitors the activities of elderly people while continuing to allow them to pursue their individual, healthy, and independent lifestyles. Therefore, it is required to develop the activity of daily living (ADL) sensing systems that are based on high-performance sensors and information technologies. However, most of the systems that have been proposed to date have only been investigated and/or evaluated in experimental environments. When considering the spread of such systems to typical homes inhabited by elderly people, it is clear that such sensing systems will need to meet the following five requirements: (1) be inexpensive; (2) provide robustness; (3) protect privacy; (4) be maintenance-free; and, (5) work with a simple user interface. In this paper, we propose a novel senior-friendly ADL sensing system that can fulfill these requirements. More specifically, we achieve an easy collection of ADL data from elderly people while using a proposed system that consists of a small number of inexpensive energy harvesting sensors and simple annotation buttons, without the need for privacy-invasive cameras or microphones. In order to evaluate the practicality of our proposed system, we installed it in ten typical homes with elderly residents and collected the ADL data over a two-month period. We then visualized the collected data and performed activity recognition using a long short-term memory (LSTM) model. From the collected results, we confirmed that our proposed system, which is inexpensive and non-invasive, can correctly collect resident ADL data and could recognize activities from the collected data with a high recall rate of 72.3% on average. This result shows a high potential of our proposed system for application to services for elderly people. Full article
Show Figures

Figure 1

Back to TopTop