1
|
Guerra BMV, Torti E, Marenzi E, Schmid M, Ramat S, Leporati F, Danese G. Ambient assisted living for frail people through human activity recognition: state-of-the-art, challenges and future directions. Front Neurosci 2023; 17:1256682. [PMID: 37849892 PMCID: PMC10577184 DOI: 10.3389/fnins.2023.1256682] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2023] [Accepted: 09/18/2023] [Indexed: 10/19/2023] Open
Abstract
Ambient Assisted Living is a concept that focuses on using technology to support and enhance the quality of life and well-being of frail or elderly individuals in both indoor and outdoor environments. It aims at empowering individuals to maintain their independence and autonomy while ensuring their safety and providing assistance when needed. Human Activity Recognition is widely regarded as the most popular methodology within the field of Ambient Assisted Living. Human Activity Recognition involves automatically detecting and classifying the activities performed by individuals using sensor-based systems. Researchers have employed various methodologies, utilizing wearable and/or non-wearable sensors, and employing algorithms ranging from simple threshold-based techniques to more advanced deep learning approaches. In this review, literature from the past decade is critically examined, specifically exploring the technological aspects of Human Activity Recognition in Ambient Assisted Living. An exhaustive analysis of the methodologies adopted, highlighting their strengths and weaknesses is provided. Finally, challenges encountered in the field of Human Activity Recognition for Ambient Assisted Living are thoroughly discussed. These challenges encompass issues related to data collection, model training, real-time performance, generalizability, and user acceptance. Miniaturization, unobtrusiveness, energy harvesting and communication efficiency will be the crucial factors for new wearable solutions.
Collapse
Affiliation(s)
- Bruna Maria Vittoria Guerra
- Bioengineering Laboratory, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| | - Emanuele Torti
- Custom Computing and Programmable Systems Laboratory, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| | - Elisa Marenzi
- Custom Computing and Programmable Systems Laboratory, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| | - Micaela Schmid
- Bioengineering Laboratory, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| | - Stefano Ramat
- Bioengineering Laboratory, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| | - Francesco Leporati
- Custom Computing and Programmable Systems Laboratory, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| | - Giovanni Danese
- Custom Computing and Programmable Systems Laboratory, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy
| |
Collapse
|
2
|
Guerra BMV, Ramat S, Beltrami G, Schmid M. Recurrent Network Solutions for Human Posture Recognition Based on Kinect Skeletal Data. SENSORS (BASEL, SWITZERLAND) 2023; 23:s23115260. [PMID: 37299986 DOI: 10.3390/s23115260] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/04/2023] [Revised: 05/09/2023] [Accepted: 05/17/2023] [Indexed: 06/12/2023]
Abstract
Ambient Assisted Living (AAL) systems are designed to provide unobtrusive and user-friendly support in daily life and can be used for monitoring frail people based on various types of sensors, including wearables and cameras. Although cameras can be perceived as intrusive in terms of privacy, low-cost RGB-D devices (i.e., Kinect V2) that extract skeletal data can partially overcome these limits. In addition, deep learning-based algorithms, such as Recurrent Neural Networks (RNNs), can be trained on skeletal tracking data to automatically identify different human postures in the AAL domain. In this study, we investigate the performance of two RNN models (2BLSTM and 3BGRU) in identifying daily living postures and potentially dangerous situations in a home monitoring system, based on 3D skeletal data acquired with Kinect V2. We tested the RNN models with two different feature sets: one consisting of eight human-crafted kinematic features selected by a genetic algorithm, and another consisting of 52 ego-centric 3D coordinates of each considered skeleton joint, plus the subject's distance from the Kinect V2. To improve the generalization ability of the 3BGRU model, we also applied a data augmentation method to balance the training dataset. With this last solution we reached an accuracy of 88%, the best we achieved so far.
Collapse
Affiliation(s)
- Bruna Maria Vittoria Guerra
- Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy
| | - Stefano Ramat
- Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy
| | - Giorgio Beltrami
- Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy
| | - Micaela Schmid
- Laboratory of Bioengineering, Department of Electrical, Computer and Biomedical Engineering, University of Pavia, 27100 Pavia, Italy
| |
Collapse
|
3
|
Hartmann KV, Primc N, Rubeis G. Lost in translation? Conceptions of privacy and independence in the technical development of AI-based AAL. MEDICINE, HEALTH CARE, AND PHILOSOPHY 2023; 26:99-110. [PMID: 36348209 PMCID: PMC9984520 DOI: 10.1007/s11019-022-10126-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Accepted: 10/27/2022] [Indexed: 06/16/2023]
Abstract
AAL encompasses smart home technologies that are installed in the personal living environment in order to support older, disabled, as well as chronically ill people with the goal of delaying or reducing their need for nursing care in a care facility. Artificial intelligence (AI) is seen as an important tool for assisting the target group in their daily lives. A literature search and qualitative content analysis of 255 articles from computer science and engineering was conducted to explore the usage of ethical concepts. From an ethical point of view, the concept of independence and self-determination on the one hand and the possible loss of privacy on the other hand are widely discussed in the context of AAL. These concepts are adopted by the technical discourse in the sense that independence, self-determination and privacy are recognized as important values. Nevertheless, our research shows that these concepts have different usages and meanings in the ethical and the technical discourses. In the paper, we aim to map the different meanings of independence, self-determination and privacy as they can be found in the context of technological research on AI-based AAL systems. It investigates the interpretation of these ethical and social concepts which technicians try to build into AAL systems. In a second step, these interpretations are contextualized with concepts from the ethical discourse on AI-based assistive technologies.
Collapse
Affiliation(s)
- Kris Vera Hartmann
- Institute for History and Ethics of Medicine, Faculty of Medicine, Ruprecht-Karls-Universität Heidelberg, Heidelberg, Germany.
| | - Nadia Primc
- Institute for History and Ethics of Medicine, Faculty of Medicine, Ruprecht-Karls-Universität Heidelberg, Heidelberg, Germany
| | - Giovanni Rubeis
- Department of General Health Studies, Division Biomedical and Public Health Ethics, Karl Landsteiner Private University for Health Sciences, Krems, Austria
| |
Collapse
|
4
|
Neural Networks for Automatic Posture Recognition in Ambient-Assisted Living. SENSORS 2022; 22:s22072609. [PMID: 35408224 PMCID: PMC9003043 DOI: 10.3390/s22072609] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 02/15/2022] [Revised: 03/25/2022] [Accepted: 03/27/2022] [Indexed: 12/29/2022]
Abstract
Human Action Recognition (HAR) is a rapidly evolving field impacting numerous domains, among which is Ambient Assisted Living (AAL). In such a context, the aim of HAR is meeting the needs of frail individuals, whether elderly and/or disabled and promoting autonomous, safe and secure living. To this goal, we propose a monitoring system detecting dangerous situations by classifying human postures through Artificial Intelligence (AI) solutions. The developed algorithm works on a set of features computed from the skeleton data provided by four Kinect One systems simultaneously recording the scene from different angles and identifying the posture of the subject in an ecological context within each recorded frame. Here, we compare the recognition abilities of Multi-Layer Perceptron (MLP) and Long-Short Term Memory (LSTM) Sequence networks. Starting from the set of previously selected features we performed a further feature selection based on an SVM algorithm for the optimization of the MLP network and used a genetic algorithm for selecting the features for the LSTM sequence model. We then optimized the architecture and hyperparameters of both models before comparing their performances. The best MLP model (3 hidden layers and a Softmax output layer) achieved 78.4%, while the best LSTM (2 bidirectional LSTM layers, 2 dropout and a fully connected layer) reached 85.7%. The analysis of the performances on individual classes highlights the better suitability of the LSTM approach.
Collapse
|
5
|
Jovanovic M, Mitrov G, Zdravevski E, Lameski P, Colantonio S, Kampel M, Tellioglu H, Florez-Revuelta F. Ambient Assisted Living: A Scoping Review of Artificial Intelligence Models, Domains, Technology and Concerns (Preprint). J Med Internet Res 2022; 24:e36553. [DOI: 10.2196/36553] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/17/2022] [Revised: 08/15/2022] [Accepted: 09/23/2022] [Indexed: 11/13/2022] Open
|
6
|
Liu J, Wang Y, Liu Y, Xiang S, Pan C. 3D PostureNet: A unified framework for skeleton-based posture recognition. Pattern Recognit Lett 2020. [DOI: 10.1016/j.patrec.2020.09.029] [Citation(s) in RCA: 9] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/28/2022]
|
7
|
Guerra BMV, Ramat S, Gandolfi R, Beltrami G, Schmid M. Skeleton data pre-processing for human pose recognition using Neural Network. ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY. ANNUAL INTERNATIONAL CONFERENCE 2020; 2020:4265-4268. [PMID: 33018938 DOI: 10.1109/embc44109.2020.9175588] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/08/2022]
Abstract
Automatic monitoring of daily living activities can greatly improve the possibility of living autonomously for frail individuals. Pose recognition based on skeleton tracking data is promising for identifying dangerous situations and trigger external intervention or other alarms, while avoiding privacy issues and the need for patient compliance. Here we present the benefits of pre-processing Kinect-recorded skeleton data to limit the several errors produced by the system when the subject is not in ideal tracking conditions. The accuracy of our two hidden layers MLP classifier improved from about 82% to over 92% in recognizing actors in four different poses: standing, sitting, lying and dangerous sitting.
Collapse
|