Svetlana Yanushkevich

Dr. Svetlana Yanushkevich

orcid

Research Focus & Metrics

Academic Career Length

24Years (2003-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 July 2023 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MMMansooreh Montazerin
Mansooreh Montazerin
ERElahe Rahimian
Elahe Rahimian
FNFarnoosh Naderkhani
Farnoosh Naderkhani
SAS. Farokh Atashzar
S. Farokh Atashzar
SYSvetlana Yanushkevich
Svetlana Yanushkevich
AMArash Mohammadi
Arash Mohammadi
Designing efficient and labor-saving prosthetic hands requires powerful hand gesture recognition algorithms that can achieve high accuracy with limited complexity and latency. In this context, the paper proposes a Compact Transformer-based Hand Gesture Recognition framework referred to as $$\text {CT-HGR}$$ CT-HGR , which employs a vision transformer network to conduct hand gesture recognition using high-density surface EMG (HD-sEMG) signals. Taking advantage of the attention mechanism, which is incorporated into the transformer architectures, our proposed $$\text {CT-HGR}$$ CT-HGR framework overcomes major constraints associated with most of the existing deep learning models such as model complexity; requiring feature engineering; inability to consider both temporal and spatial information of HD-sEMG signals, and requiring a large number of training samples. The attention mechanism in the proposed model identifies similarities among different data segments with a greater capacity for parallel computations and addresses the memory limitation problems while dealing with inputs of large sequence lengths. $$\text {CT-HGR}$$ CT-HGR can be trained from scratch without any need for transfer learning and can simultaneously extract both temporal and spatial features of HD-sEMG data. Additionally, the $$\text {CT-HGR}$$ CT-HGR framework can perform instantaneous recognition using sEMG image spatially composed from HD-sEMG signals. A variant of the $$\text {CT-HGR}$$ CT-HGR is also designed to incorporate microscopic neural drive information in the form of Motor Unit Spike Trains (MUSTs) extracted from HD-sEMG signals using Blind Source Separation (BSS). This variant is combined with its baseline version via a hybrid architecture to evaluate potentials of fusing macroscopic and microscopic neural drive information. The utilized HD-sEMG dataset involves 128 electrodes that collect the signals related to 65 isometric hand gestures of 20 subjects. The proposed $$\text {CT-HGR}$$ CT-HGR framework is applied to 31.25, 62.5, 125, 250 ms window sizes of the above-mentioned dataset utilizing 32, 64, 128 electrode channels. Our results are obtained via 5-fold cross-validation by first applying the proposed framework on the dataset of each subject separately and then, averaging the accuracies among all the subjects. The average accuracy over all the participants using 32 electrodes and a window size of 31.25 ms is 86.23%, which gradually increases till reaching 91.98% for 128 electrodes and a window size of 250 ms. The $$\text {CT-HGR}$$ CT-HGR achieves accuracy of 89.13% for instantaneous recognition based on a single frame of HD-sEMG image. The proposed model is statistically compared with a 3D Convolutional Neural Network (CNN) and two different variants of Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) models. The accuracy results for each of the above-mentioned models are paired with their precision, recall, F1 score, required memory, and train/test times. The results corroborate effectiveness of the proposed $$\text {CT-HGR}$$ CT-HGR framework compared to its counterparts.

5 February 2021 in IEEE Access
Verified
Journal Article
Open access
KLKenneth Lai
Kenneth Lai
SYSvetlana Yanushkevich
Svetlana Yanushkevich
VSVlad P. Shmerko
Vlad P. Shmerko
This paper describes a prototype of an intelligent Stress Monitoring Assistant (SMA), - the next generation of stress detectors. The SMA is intended for the first responders and professionals coping with exposure to extreme physical and psychological stressors, e.g. firefighters, combat military personnel, explosive ordnance disposal operatives, law enforcement officers, emergency medical technicians, and paramedics. Stress impacts human behavior and decision-making, which can be propagated between the team members. The SMA is an integral part of the Decision Support System, it is a component of the decision support perception-action cycle. We model this cycle as a cognitive dynamic system. The intelligent part of the SMA is designed using a) a residual-temporal convolution network for learning data from sensors and detection of stress features, and b) a reasoning mechanism based on a causal network for fusion at various levels. The SMA prototype has been tested using a multi-factor physiological dataset WEarable Stress and Affect Detection (WESAD). In both modes, the stress recognition and stress detection, the SMA achieves an accuracy of 86% and 98% for the WESAD dataset, respectively. This performance is superior to the known results in satisfying the requirements of reliable decision support.

23 May 2023 in Epidemiology and Infection
Verified
Journal Article
Open access
PDF file
MBMarina Banuet-Martinez
Marina Banuet-Martinez
YYYang Yang
Yang Yang
BJBehnaz Jafari
Behnaz Jafari
AKAvneet Kaur
Avneet Kaur
Zahid ButtZahid Butt
Zahid Butt
CKChapin S. Korosec
Chapin S. Korosec
Human monkeypox (mpox) virus is a viral zoonosis that belongs to the Orthopoxvirus genus of the Poxviridae family, which presents with similar symptoms as those seen in human smallpox patients. Mpox is an increasing concern globally, with over 80,000 cases in non-endemic countries as of December 2022. In this review, we provide a brief history and ecology of mpox, its basic virology, and the key differences in mpox viral fitness traits before and after 2022. We summarize and critique current knowledge from epidemiological mathematical models, within-host models, and between-host transmission models using the One Health approach, where we distinguish between models that focus on immunity from vaccination, geography, climatic variables, as well as animal models. We report various epidemiological parameters, such as the reproduction number,R0, in a condensed format to facilitate comparison between studies. We focus on how mathematical modelling studies have led to novel mechanistic insight into mpox transmission and pathogenesis. As mpox is predicted to lead to further infection peaks in many historically non-endemic countries, mathematical modelling studies of mpox can provide rapid actionable insights into viral dynamics to guide public health measures and mitigation strategies.

1 July 2019
Verified
Conference Paper
Closed access
TTThomas Truong
Thomas Truong
SYSvetlana Yanushkevich
Svetlana Yanushkevich
A major obstacle in ultra-wideband radar based approaches for object detection concealed on human body is the difficulty in collecting high quality radar signal data. Generative adversarial networks (GAN) have shown promise in synthesizing data for image and audio processing. This paper proposes the design of a GAN for application in radar signal generation. Data collected using the Finite-Difference Time-Domain (FDTD) method on three concealed object classes (no object, large object, and small object) are used as training data. A GAN is trained to generate radar signal samples for each class. The proposed GAN is capable of synthesizing the radar signal data which is indistinguishable from the training data by qualitative analysis performed by human observers.

21 March 2022 in IEEE Access
Verified
Journal Article
Open access
GHGee-Sern Jison Hsu
Gee-Sern Jison Hsu
HWHung-Yi Wu
Hung-Yi Wu
CTChun-Hung Tsai
Chun-Hung Tsai
SYSvetlana Yanushkevich
Svetlana Yanushkevich
MGMarina L. Gavrilova
Marina L. Gavrilova
As we have been seriously hit by the COVID-19 pandemic, wearing a facial mask is a crucial action that we can take for our protection. This paper reports a comprehensive study on the recognition of masked faces. By using facial landmarks, we synthesize the facial mask for each face in several benchmark databases with different challenging factors. The IJB-B and IJB-C databases are selected for evaluating the performance against the variation across pose, illumination and expression (PIE). The FG-Net database is selected for evaluating the performance across age. The SCface is chosen for evaluating the performance on low-resolution images. The MS-1MV2 is exploited as the base training set. We use the ResNet-100 as the feature embedding network connected to state-of-the-art loss functions designed for tackling face recognition. The loss functions considered include the Center Loss, the Marginal Loss, the Angular Softmax Loss, the Large Margin Cosine Loss and the Additive Angular Margin Loss. Both verification and identification are conducted in our evaluation. The performances for recognizing faces with and without the synthetic masks are all evaluated for a complete comparison. The network with the best loss function for recognizing synthetic masked faces is then assessed on a real masked face database, the cleaned RMFRD (c-RMFRD) dataset. Compared with a human user test on the c-RMFRD, the network trained on the synthetic masked faces outperforms human vision for a large gap. Our contributions are fourfold. The first is a comprehensive study for tackling masked face recognition by using state-of-the-art loss functions against various compounding factors. For comparison purpose, the second is another comprehensive study on the recognition of faces without masks by using the same loss functions against the same challenging factors. The third is the verification of the network trained on synthetic masked faces for tackling the real masked face recognition with performance better than human inspectors. The fourth is the highlight on the challenges of masked face recognition and the directions for future research. Our code, trained models and dataset are available via the project GitHub site.

1 July 2019
Verified
Conference Paper
Closed access
KLKenneth Lai
Kenneth Lai
XTXinyuan Tu
Xinyuan Tu
SYSvetlana Yanushkevich
Svetlana Yanushkevich
This paper addresses the problem of biometric identification of animals, specifically dogs. We apply advanced machine learning models such as deep neural network on the photographs of pets in order to determine the pet identity. In this paper, we explore the possibility of using different types of "soft" biometrics, such as breed, height, or gender, in fusion with "hard" biometrics such as photographs of the pet’s face. We apply the principle of transfer learning on different Convolutional Neural Networks, in order to create a network designed specifically for breed classification. The proposed network is able to achieve an accuracy of 90.80% and 91.29% when differentiating between the two dog breeds, for two different datasets. Without the use of "soft" biometrics, the identification rate of dogs is 78.09% but by using a decision network to incorporate "soft" biometrics, the identification rate can achieve an accuracy of 84.94%.