Cooking Activity Recognition with Varying Sampling Rates Using Deep Convolutional GRU Framework

Siraj, Md. Sadman; Shahid, Omar; Ahad, Md. Atiqur Rahman

doi:10.1007/978-981-15-8269-1_10

Cited by 4 publications

(2 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It used an artificial neural network-based approach that could detect four eating states-chewing, swallowing, talking, and idle. Siraj et al [18] developed a framework to recognize small activities, such as cooking, that are performed with other complex activities during a day. The authors used multiple machine learning models including those of deep learning, convolutional neural network, and gated recurrent unit to train their framework for the recognition of tasks and actions associated with the activity of cooking.…”

Section: Literature Reviewmentioning

confidence: 99%

“…For instance, in [17], the work focused on eating activity recognition and analysis; in [13], the activity analysis was done to detect enter and exit motions only in a given IoT-based space. In [18], the methodology focused on the detection of simple and less complicated activities, such an cooking, and [22] presented a system that could remind its users to take their routine medications. The analysis of such small tasks and actions are important, but the challenge in this context is the fact that these systems are specific to such tasks and cannot be deployed or implemented in the context of other activities.…”

mentioning

confidence: 99%

See 1 more Smart Citation

An Ambient Intelligence-Based Human Behavior Monitoring Framework for Ubiquitous Environments

Thakur

Han

2021

Information

View full text Add to dashboard Cite

This framework for human behavior monitoring aims to take a holistic approach to study, track, monitor, and analyze human behavior during activities of daily living (ADLs). The framework consists of two novel functionalities. First, it can perform the semantic analysis of user interactions on the diverse contextual parameters during ADLs to identify a list of distinct behavioral patterns associated with different complex activities. Second, it consists of an intelligent decision-making algorithm that can analyze these behavioral patterns and their relationships with the dynamic contextual and spatial features of the environment to detect any anomalies in user behavior that could constitute an emergency. These functionalities of this interdisciplinary framework were developed by integrating the latest advancements and technologies in human–computer interaction, machine learning, Internet of Things, pattern recognition, and ubiquitous computing. The framework was evaluated on a dataset of ADLs, and the performance accuracies of these two functionalities were found to be 76.71% and 83.87%, respectively. The presented and discussed results uphold the relevance and immense potential of this framework to contribute towards improving the quality of life and assisted living of the aging population in the future of Internet of Things (IoT)-based ubiquitous living environments, e.g., smart homes.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

mentioning

confidence: 99%