Improving Dynamic Hand Gesture Recognition based IR-UWB using Offline Data Augmentation and Deep Learning

Korti, Djazila Souhila; Slimane, Zohra

doi:10.1109/iicaiet55139.2022.9936862

Cited by 1 publication

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Note that the model for all experiments is trained from scratch for 100 epochs with a batch size of 16 using the Adam optimizer with a learning rate set to 0.001. All the default configurations of the are left intact as mentioned in [26]. Except for the LSTM layer, the number of units is changed to 300.…”

Section: Methodsmentioning

confidence: 99%

“…For the SVM classifier, the number of binary classifiers is set to 11 corresponding to the number of class activities. We use the same SVM hyperparameters as mentioned in [26]. By keeping hyperparameters constant over all datasets for all experiments, we can demonstrate that the mitigation of overfitting is attributed to data augmentation rather than hyperparameter tuning.…”

Section: Methodsmentioning

confidence: 99%

“…For the preprocessing phase, we adopt the proposed approach in [26]. This method is designed to improve the image content in order to extract and learn discriminative features.…”

Section: Preprocessingmentioning

confidence: 99%

“…The latter uses two directional filters to convolute the input image, respectively, to obtain Dx, Dy and Dxy. More details about the data preprocessing can be found in [26].…”

Section: Preprocessingmentioning

confidence: 99%

“…This approach makes it possible to enhance human motion characteristics to improve the accuracy of the final classifier without adding prior knowledge or re-acquiring data. The second objective is to extend our previous work [26] based on Hand Gesture Recognition (HGR) to the HAR application. Our previous contribution consisted of extending a single sample to three representations by extracting low-level feature images using the Sobel filter.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Advanced Human Activity Recognition through Data Augmentation and Feature Concatenation of Micro-Doppler Signatures

Souhila Korti,

Slimane

2023

Int. j. electr. comput. eng. syst. (Online)

View full text Add to dashboard Cite

Developing accurate classification models for radar-based Human Activity Recognition (HAR), capable of solving real-world problems, depends heavily on the amount of available data. In this paper, we propose a simple, effective, and generalizable data augmentation strategy along with preprocessing for micro-Doppler signatures to enhance recognition performance. By leveraging the decomposition properties of the Discrete Wavelet Transform (DWT), new samples are generated with distinct characteristics that do not overlap with those of the original samples. The micro-Doppler signatures are projected onto the DWT space for the decomposition process using the Haar wavelet. The returned decomposition components are used in different configurations to generate new data. Three new samples are obtained from a single spectrogram, which increases the amount of training data without creating duplicates. Next, the augmented samples are processed using the Sobel filter. This step allows each sample to be expanded into three representations, including the gradient in the x-direction (Dx), y-direction (Dy), and both x- and y-directions (Dxy). These representations are used as input for training a three-input convolutional neural network-long short-term memory support vector machine (CNN-LSTM-SVM) model. We have assessed the feasibility of our solution by evaluating it on three datasets containing micro-Doppler signatures of human activities, including Frequency Modulated Continuous Wave (FMCW) 77 GHz, FMCW 24 GHz, and Impulse Radio Ultra-Wide Band (IR-UWB) 10 GHz datasets. Several experiments have been carried out to evaluate the model's performance with the inclusion of additional samples. The model was trained from scratch only on the augmented samples and tested on the original samples. Our augmentation approach has been thoroughly evaluated using various metrics, including accuracy, precision, recall, and F1-score. The results demonstrate a substantial improvement in the recognition rate and effectively alleviate the overfitting effect. Accuracies of 96.47%, 94.27%, and 98.18% are obtained for the FMCW 77 GHz, FMCW 24 GHz, and IR- UWB 10 GHz datasets, respectively. The findings of the study demonstrate the utility of DWT to enrich micro-Doppler training samples to improve HAR performance. Furthermore, the processing step was found to be efficient in enhancing the classification accuracy, achieving 96.78%, 96.32%, and 100% for the FMCW 77 GHz, FMCW 24 GHz, and IR-UWB 10 GHz datasets, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

“…For the preprocessing phase, we adopt the proposed approach in [26]. This method is designed to improve the image content in order to extract and learn discriminative features.…”

Section: Preprocessingmentioning

confidence: 99%

“…The latter uses two directional filters to convolute the input image, respectively, to obtain Dx, Dy and Dxy. More details about the data preprocessing can be found in [26].…”

Section: Preprocessingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations