Head Gesture Recognition Based on Capacitive Sensors Using Deep Learning Algorithms

Severin, Ionuţ-Cristian; Dobrea, Dan-Marius

doi:10.2478/bipie-2021-0018

Abstract

The current paper proposed and investigated the head motion recognition idea based on four capacitive sensors and deep learning models. The proposed system was designed to empower a tetraplegic person to control a remote device or an intelligent wheelchair. The capacitive sensors were placed around the neck using a necktie, which each volunteer who participated in this experiment was easy to use. The results show that the best-proposed deep learning model can determine each activity with a classification rate equal to 89.29% using capacitive raw data. During the experiments the deep learning models provided accuracy values in the range of 56.25% to 89.29%.

References

Aljarrah A., Ali A., Human Activity Recognition Using PCA and BiLSTM Recurrent Neural Networks, Proc. Internat. Conf. on Engineering Tech. and its Appl., IICETA 2019, 156-160.10.1109/IICETA47481.2019.9012979
Search in Google Scholar Back to article
Bashar S., Al Fahim A., Chon K., Smartphone Based Human Activity Recognition with Feature Selection and Dense Neural Network, Proc. Annual Internat. Conf. of IEEE EMBC Society, 2020, 5888-5891.10.1109/EMBC44109.2020.917623933019314
Search in Google Scholar Back to article
Chang W., Hsu C., Chen L., Su J., Chen M., A Wearable Devices-Based Home Sports Recording System for Health Management, Proc. IEEE Internat. Conf. on Consumer Electronics, ICCE-Taiwan 2020, 1-2.10.1109/ICCE-Taiwan49838.2020.9258028
Search in Google Scholar Back to article
Darvishzadeh A. et al., CNN-BLSTM-CRF Network for Semantic Labeling of Students’ Online Handwritten Assignments, Proc. Internat. Conf. on Document Analysis and Recognition, ICDAR 2019, 1035-1040.10.1109/ICDAR.2019.00169
Search in Google Scholar Back to article
Dobrea M., Dobrea D., Severin I., A New Wearable System for Head Gesture Recognition Designed to Control an Intelligent Wheelchair, Proc. E-Health and Bioeng. Conf., EHB 2019, 1-5.10.1109/EHB47216.2019.8969993
Search in Google Scholar Back to article
Dobrea D., Dobrea M., A Neuronal Model of the 3D Head Position Based on a Wearable System, Proc. Internat. Conf. and Exposition on Electrical and Power Eng., EPE 2018, 0341-0346.10.1109/ICEPE.2018.8559815
Search in Google Scholar Back to article
Du Y., Lim Y., Tan Y., Activity Prediction using LSTM in Smart Home, Proc. IEEE 8-th Global Conf. on Consumer Electronics, GCCE 2019, 918-919.10.1109/GCCE46687.2019.9015492
Search in Google Scholar Back to article
Kusumo B., Heryana A., Nugraheni E., Rozie A., Setiadi B., Recognizing Human Activities and Earthquake Vibration from Smartphone Accelerometers Using LSTM Algorithm, Proc. Internat. Conf. on Computer, Control, Informatics and its Applications, IC3INA 2018, Tangerang, Indonesia, 88-92.10.1109/IC3INA.2018.8629514
Search in Google Scholar Back to article
Mohmed G., Lotfi A., Pourabdollah A., Convolutional Neural Network Classifier with Fuzzy Feature Representation for Human Activity Modelling, Proc. IEEE Internat. Conf. on Fuzzy Systems, FUZZ-IEEE 2020, 1-7.10.1109/FUZZ48607.2020.9177851
Search in Google Scholar Back to article
Shiranthika C., Premakumara N., Chiu H.-L., Samani H., Shyalika C., Yang C.-Y., Human Activity Recognition Using CNN & LSTM, Proc. 5-th Internat. Conf. on Information Tech. Research, ICITR 2020, 1-6.10.1109/ICITR51448.2020.9310792
Search in Google Scholar Back to article
Severin I., Dobrea D., Head Gesture Recognition Based on 6DOF Inertial Sensor Using Artificial Neural Network, Proc. Internat. Symp. on Electronics and Telecomm., ISETC 2020, 1-4.10.1109/ISETC50328.2020.9301099
Search in Google Scholar Back to article
Severin I., Dobrea D., Dobrea M., Head Gesture Recognition using a 6DOF Inertial IMU, Internat. J. of Computers Comm. & Control, 15, (2020).10.15837/ijccc.2020.3.3856
Search in Google Scholar Back to article
Srinivasan A. et al., Elder Care System Using IoT and Machine Learning in AWS Cloud, Proc. IEEE 17-th Internat. Conf. on Smart Communities: Improving Quality of Life Using ICT, IoT and AI, HONET 2020, 92-98.10.1109/HONET50430.2020.9322834
Search in Google Scholar Back to article
Xia K., Huang J., Wang H., LSTM-CNN Architecture for Human Activity Recognition, IEEE Access, 8, 56855-56866 (2020).10.1109/ACCESS.2020.2982225
Search in Google Scholar Back to article
Yang S., Research on Network Behavior Anomaly Analysis Based on Bidirectional LSTM, Proc. IEEE 3-rd Inf. Tech., Networking, Electronic and Automation Control Conference, ITNEC 2019, Chengdu, China, 798-802.10.1109/ITNEC.2019.8729475
Search in Google Scholar Back to article

Head Gesture Recognition Based on Capacitive Sensors Using Deep Learning Algorithms

Abstract

Paradigm

My account