Improving the Performance and Explainability of Indoor Human Activity Recognition in the Internet of Things Environment

Cengiz, Ayse Betul; Birant, Kökten Ulaş; Cengiz, Mehmet; Birant, Derya; Baysari, Kemal

doi:10.3390/sym14102022

Cited by 10 publications

(7 citation statements)

References 74 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address the challenge of identifying symmetric and asymmetric human activities, we embarked on a study focusing on activity taxonomies [17,18]. We systematically categorized human activities into two primary classes: symmetry and asymmetry.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Deep Residual Network with a CBAM Mechanism for the Recognition of Symmetric and Asymmetric Human Activity Using Wearable Sensors

Mekruksavanich,

Jitpattanakul

2024

Symmetry

View full text Add to dashboard Cite

Wearable devices are paramount in health monitoring applications since they provide contextual information to identify and recognize human activities. Although sensor-based human activity recognition (HAR) has been thoroughly examined, prior studies have yet to definitively differentiate between symmetric and asymmetric motions. Determining these movement patterns might provide a more profound understanding of assessing physical activity. The main objective of this research is to investigate the use of wearable motion sensors and deep convolutional neural networks in the analysis of symmetric and asymmetric activities. This study provides a new approach for classifying symmetric and asymmetric motions using a deep residual network incorporating channel and spatial convolutional block attention modules (CBAMs). Two publicly accessible benchmark HAR datasets, which consist of inertial measurements obtained from wrist-worn sensors, are used to assess the model’s efficacy. The model we have presented is subjected to thorough examination and demonstrates exceptional accuracy on both datasets. The ablation experiment examination also demonstrates noteworthy contributions from the residual mappings and CBAMs. The significance of recognizing basic movement symmetries in increasing sensor-based activity identification utilizing wearable devices is shown by the enhanced accuracy and F1-score, especially in asymmetric activities. The technique under consideration can provide activity monitoring with enhanced accuracy and detail, offering prospective advantages in diverse domains like customized healthcare, fitness tracking, and rehabilitation progress evaluation.

show abstract

Section: Methodsmentioning

confidence: 99%

“…The concept of symmetry has received limited attention in studies on HAR, as evidenced by [17,18]. Furthermore, it can also be explored concerning indoor activity recognition.…”

Section: Sensor-based Harmentioning

confidence: 99%

Deep Residual Network with a CBAM Mechanism for the Recognition of Symmetric and Asymmetric Human Activity Using Wearable Sensors

Mekruksavanich,

Jitpattanakul

2024

Symmetry

View full text Add to dashboard Cite

show abstract

“…Augmented reality refers to a medium in which digital information is added or superimposed onto the real world in accordance with the world itself and shown to a user depending on their position and perspective [ 40 ]. In an interactive simulation, human behavior is used as the basis for interaction, rather than deliberate interaction, allowing users to further integrate into the experience and enhance the immersion of the interaction through a variety of different behaviors, as well as by performing system functions in a wearable manner [ 41 , 42 , 43 , 44 , 45 ].…”

Section: Related Researchmentioning

confidence: 99%

SENS+: A Co-Existing Fabrication System for a Smart DFA Environment Based on Energy Fusion Information

Chang

Huang

Hong

et al. 2023

Sensors

View full text Add to dashboard Cite

In factories, energy conservation is a crucial issue. The co-fabrication space is a modern-day equivalent of a new factory type, and it makes use of Internet of Things (IoT) devices, such as sensors, software, and online connectivity, to keep track of various building features, analyze data, and produce reports on usage patterns and trends that can be used to improve building operations and the environment. The co-fabrication user requires dynamic and flexible space, which is different from the conventional user’s usage. Because the user composition in a co-fabrication space is dynamic and unstable, we cannot use the conventional approach to assess their usage and rentals. Prototyping necessitates a specifically designed energy-saving strategy. The research uses a “seeing–moving–seeing” design thinking framework, which enables designers to more easily convey their ideas to others through direct observation of the outcomes of their intuitive designs and the representation of their works through design media. The three components of human behavior, physical manufacture, and digital interaction are primarily the focus of this work. The computing system that connects the physical machine is created through communication between the designer and the digital interface, giving the designer control over the physical machine. It is an interactive fabrication process formed by behavior. The Sensible Energy System+ is an interactive fabrication process of virtual and real coexistence created by combining the already-existing technology, the prototype fabrication machine, and SENS. This process analyzes each step of the fabrication process and energy, fits it into the computing system mode to control the prototype fabrication machine, and reduces the problem between virtual and physical fabrication and energy consumption.

show abstract

“…A significant method of representing data is Human Activity Recognition on Signal Images (HARSI). As described in [22], this method is very efficient and the research describes the method as converting the raw data into an understandable image. The images were generated by plotting the raw data from an accelerometer.…”

Section: Related Workmentioning

confidence: 99%

“…This dataset was chosen as it is one of the most important and used datasets for human activity recognition based on wearable devices, as also mentioned in [22]. Since it was used in multiple studies, it is a perfect candidate to be used to compare different approaches and to analyze the obtained accuracy rates across multiple different implementations.…”

Section: Wisdm Biometrics Datasetmentioning

confidence: 99%

Real-Time Machine Learning for Human Activities Recognition Based on Wrist-Worn Wearable Devices

Alexan,

Oniga

2023

Applied Sciences

View full text Add to dashboard Cite

Wearable technologies have slowly invaded our lives and can easily help with our day-to-day tasks. One area where wearable devices can shine is in human activity recognition, as they can gather sensor data in a non-intrusive way. We describe a real-time activity recognition system based on a common wearable device: a smartwatch. This is one of the most inconspicuous devices suitable for activity recognition as it is very common and worn for extensive periods of time. We propose a human activity recognition system that is extensible, due to the wide range of sensing devices that can be integrated, and that provides a flexible deployment system. The machine learning component recognizes activity based on plot images generated from raw sensor data. This service is exposed as a Web API that can be deployed locally or directly in the cloud. The proposed system aims to simplify the human activity recognition process by exposing such capabilities via a web API. This web API can be consumed by small-network-enabled wearable devices, even with basic processing capabilities, by leveraging a simple data contract interface and using raw data. The system replaces extensive pre-processing by leveraging high performance image recognition based on plot images generated from raw sensor data. We have managed to obtain an activity recognition rate of 94.89% and to implement a fully functional real-time human activity recognition system.

show abstract

Improving the Performance and Explainability of Indoor Human Activity Recognition in the Internet of Things Environment

Cited by 10 publications

References 74 publications

Deep Residual Network with a CBAM Mechanism for the Recognition of Symmetric and Asymmetric Human Activity Using Wearable Sensors

Deep Residual Network with a CBAM Mechanism for the Recognition of Symmetric and Asymmetric Human Activity Using Wearable Sensors

SENS+: A Co-Existing Fabrication System for a Smart DFA Environment Based on Energy Fusion Information

Real-Time Machine Learning for Human Activities Recognition Based on Wrist-Worn Wearable Devices

Contact Info

Product

Resources

About