Indoor Activity Recognition by Using Recurrent Neural Networks

Zhao, Yu; Li, Qingjuan; Farha, Fadi; Zhu, Tao; Chen, Liming

doi:10.1007/978-981-15-1925-3_15

Cited by 5 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The studies using sensor data can be seen in Table 6. Sensor data for activities Touch sensor, Tilt sensor, Height sensor, Weight sensor, Reed switch, Infrared sensor [52] Multi-user activity data Occupancy sensor, Ambient sensor (temperature, brightness, Humidity, Sound), Screen sensor, Door sensor, Seat occupancy sensor [55] ADL data Ultrasonic Positioning System (Position), Bluetooth watt checker (power consumption), CT Sensor (power consumption), ECHONET (appliance status), Motion sensor (motion detect) [64] User authentication ShakeLogin data Smartphone internal sensors: accelerometer gyroscope, rotation vector [48] Figure 10 shows the analysis of the public datasets used in the studies using public datasets. In total, 47.5% of the studies used the CASAS project dataset.…”

Section: Rq3: How Is Dataset Collected Analyzed and Used By Each Study?mentioning

confidence: 99%

See 1 more Smart Citation

Deep Learning (CNN, RNN) Applications for Smart Homes: A Systematic Review

Jiménez

Villalba-Mora

2022

Computers

View full text Add to dashboard Cite

In recent years, research on convolutional neural networks (CNN) and recurrent neural networks (RNN) in deep learning has been actively conducted. In order to provide more personalized and advanced functions in smart home services, studies on deep learning applications are becoming more frequent, and deep learning is acknowledged as an efficient method for recognizing the voices and activities of users. In this context, this study aims to systematically review the smart home studies that apply CNN and RNN/LSTM as their main solution. Of the 632 studies retrieved from the Web of Science, Scopus, IEEE Explore, and PubMed databases, 43 studies were selected and analyzed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology. In this paper, we examine which smart home applications CNN and RNN/LSTM are applied to and compare how they were implemented and evaluated. The selected studies dealt with a total of 15 application areas for smart homes, where activity recognition was covered the most. This study provides essential data for all researchers who want to apply deep learning for smart homes, identifies the main trends, and can help to guide design and evaluation decisions for particular smart home services.

show abstract

Section: Rq3: How Is Dataset Collected Analyzed and Used By Each Study?mentioning

confidence: 99%

“…Zhao et al [52] directly collected sensor data for old age activity recognition and compared RNN, LSTM, and GRU models.…”

Section: Rq5: Ismentioning

confidence: 99%

Deep Learning (CNN, RNN) Applications for Smart Homes: A Systematic Review

Jiménez

Villalba-Mora

2022

Computers

View full text Add to dashboard Cite

show abstract

“…H UMAN activity recognition (HAR) based on the Internet of Things and wearable sensing (accelerometers and gyroscopes) had a crucial role in emerging user-centered smart applications, such as smart homes [1], [2] fall detection [3], [4] and healthcare rehabilitation [5], [6]. Recent applications of deep learning techniques [7], [8], [9], [10] have significantly improved activity recognition accuracy. However, deep learning methods usually require a large number of labeled data sets to train an activity recognition model.…”

Section: Introductionmentioning

confidence: 99%

Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition

Wang

Zhu

Chen

et al. 2023

IEEE Internet Things J.

Self Cite

View full text Add to dashboard Cite

“…Also, there was a study completed on various healthcare technologies in smart homes for older adults [ 19 ], as well as a survey on monitoring for the detection of abnormalities by recognizing the subject’s behavior [ 20 ]. In particular, with the development of deep learning technology, recognizing the behavior of older people, detecting falls, or predicting when actions will occur have been significantly advanced in the last 3–4 years [ 21 , 22 , 23 , 24 , 25 ].…”

Section: Introductionmentioning

confidence: 99%

Older Adult Segmentation According to Residentially-Based Lifestyles and Analysis of Their Needs for Smart Home Functions

Antonio

Villalba-Mora

2020

IJERPH

View full text Add to dashboard Cite

Globally, the percentage of older people in the general population is growing. Smart homes have the potential to help older adults to live independently and healthy, improving their quality of life, and relieving the pressure on the healthcare and social care systems. For that, we need to understand how older adults live and their needs. Thus, this study aims to analyze the residentially-based lifestyles (RBL) of older adults and segment them to compare and analyze the real needs of smart home functions for each group. To identify a person’s RBL, a questionnaire was designed to include questions about activities at home, social events, quality of life, etc. This study surveyed 271 older Koreans. As a result of the survey on RBL, five groups with different characteristics were clustered. Finally, each groups’ features and the differences in their needs for smart home functions were compared and analyzed. The priority of needed functions for each group was found to be significantly different. In a total of 26 smart home functions, there were meaningful differences in the needs for 16 functions among the groups. This study presents the results in South Korea, according to older adults’ RBL and their smart home needs.

show abstract

Indoor Activity Recognition by Using Recurrent Neural Networks

Cited by 5 publications

References 15 publications

Deep Learning (CNN, RNN) Applications for Smart Homes: A Systematic Review

Deep Learning (CNN, RNN) Applications for Smart Homes: A Systematic Review

Negative Selection by Clustering for Contrastive Learning in Human Activity Recognition

Older Adult Segmentation According to Residentially-Based Lifestyles and Analysis of Their Needs for Smart Home Functions

Contact Info

Product

Resources

About