Energy–Accuracy Aware Finger Gesture Recognition for Wearable IoT Devices
Wearable Internet of Things (IoT) devices can be used efficiently for gesture recognition applications. The nature of these applications requires high recognition accuracy with low energy consumption, which is not easy to solve at the same time. In this paper, we design a finger gesture recognition...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/13/4801 |
| _version_ | 1797441999409774592 |
|---|---|
| author | Woosoon Jung Hyung Gyu Lee |
| author_facet | Woosoon Jung Hyung Gyu Lee |
| author_sort | Woosoon Jung |
| collection | DOAJ |
| description | Wearable Internet of Things (IoT) devices can be used efficiently for gesture recognition applications. The nature of these applications requires high recognition accuracy with low energy consumption, which is not easy to solve at the same time. In this paper, we design a finger gesture recognition system using a wearable IoT device. The proposed recognition system uses a light-weight multi-layer perceptron (MLP) classifier which can be implemented even on a low-end micro controller unit (MCU), with a 2-axes flex sensor. To achieve high recognition accuracy with low energy consumption, we first design a framework for the finger gesture recognition system including its components, followed by system-level performance and energy models. Then, we analyze system-level accuracy and energy optimization issues, and explore the numerous design choices to finally achieve energy–accuracy aware finger gesture recognition, targeting four commonly used low-end MCUs. Our extensive simulation and measurements using prototypes demonstrate that the proposed design achieves up to 95.5% recognition accuracy with energy consumption under 2.74 mJ per gesture on a low-end embedded wearable IoT device. We also provide the Pareto-optimal designs among a total of 159 design choices to achieve energy–accuracy aware design points under given energy or accuracy constraints. |
| first_indexed | 2024-03-09T12:35:26Z |
| format | Article |
| id | doaj.art-f1490fa6ffd14db7b276268e6c96b09c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T12:35:26Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-f1490fa6ffd14db7b276268e6c96b09c2023-11-30T22:25:16ZengMDPI AGSensors1424-82202022-06-012213480110.3390/s22134801Energy–Accuracy Aware Finger Gesture Recognition for Wearable IoT DevicesWoosoon Jung0Hyung Gyu Lee1Department of Computer and Information Engineering, Daegu University, Gyeongsan-si 38453, KoreaDepartment of Software, Duksung Women’s University, Seoul 01369, KoreaWearable Internet of Things (IoT) devices can be used efficiently for gesture recognition applications. The nature of these applications requires high recognition accuracy with low energy consumption, which is not easy to solve at the same time. In this paper, we design a finger gesture recognition system using a wearable IoT device. The proposed recognition system uses a light-weight multi-layer perceptron (MLP) classifier which can be implemented even on a low-end micro controller unit (MCU), with a 2-axes flex sensor. To achieve high recognition accuracy with low energy consumption, we first design a framework for the finger gesture recognition system including its components, followed by system-level performance and energy models. Then, we analyze system-level accuracy and energy optimization issues, and explore the numerous design choices to finally achieve energy–accuracy aware finger gesture recognition, targeting four commonly used low-end MCUs. Our extensive simulation and measurements using prototypes demonstrate that the proposed design achieves up to 95.5% recognition accuracy with energy consumption under 2.74 mJ per gesture on a low-end embedded wearable IoT device. We also provide the Pareto-optimal designs among a total of 159 design choices to achieve energy–accuracy aware design points under given energy or accuracy constraints.https://www.mdpi.com/1424-8220/22/13/4801MLPgesture recognitionflex sensormodel searchneural network |
| spellingShingle | Woosoon Jung Hyung Gyu Lee Energy–Accuracy Aware Finger Gesture Recognition for Wearable IoT Devices Sensors MLP gesture recognition flex sensor model search neural network |
| title | Energy–Accuracy Aware Finger Gesture Recognition for Wearable IoT Devices |
| title_full | Energy–Accuracy Aware Finger Gesture Recognition for Wearable IoT Devices |
| title_fullStr | Energy–Accuracy Aware Finger Gesture Recognition for Wearable IoT Devices |
| title_full_unstemmed | Energy–Accuracy Aware Finger Gesture Recognition for Wearable IoT Devices |
| title_short | Energy–Accuracy Aware Finger Gesture Recognition for Wearable IoT Devices |
| title_sort | energy accuracy aware finger gesture recognition for wearable iot devices |
| topic | MLP gesture recognition flex sensor model search neural network |
| url | https://www.mdpi.com/1424-8220/22/13/4801 |
| work_keys_str_mv | AT woosoonjung energyaccuracyawarefingergesturerecognitionforwearableiotdevices AT hyunggyulee energyaccuracyawarefingergesturerecognitionforwearableiotdevices |