Browsing by Author "Gupta, Ankit"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
- Availability and performance of face based non-contact methods for heart rate and oxygen saturation estimations: a systematic reviewPublication . Gupta, Ankit; Ravelo-García, Antonio G.; Dias, Fernando Morgado; Gupta, Ankit; Ravelo-García, Antonio G.; Morgado-Dias, FernandoBackground: Consumer-level cameras have provided an advantage of designing cost-effective, non-contact physiological parameters estimation approaches which is not possible with gold standard estimation tech niques. This encourages the development of non-contact estimation methods using camera technology. Therefore, this work aims to present a systematic review summarizing the currently existing face-based non-contact methods along with their performance. Methods: This review includes all heart rate (HR) and oxygen saturation (SpO2) studies published in journals and a few reputed conferences, which have compared the proposed estimation methods with one or more standard reference devices. The articles were collected from the following research databases: In stitute of Electrical and Electronics Engineers (IEEE), PubMed, Web of Science (WoS), Science Direct, and Association of Computer Machinery (ACM) digital library. All database searches were completed on May 20, 2021. Each study was assessed using a finite set of identified factors for reporting bias. Results: Out of 332 identified studies, 32 studies were selected for the final review. Additionally, 18 studies were included by thoroughly checking these studies. 3 out of 50 (6%) studies were performed in clinical conditions, while the remaining studies were carried out on a healthy population. 42 out of 50 (84%) studies have estimated HR, while 5/50 (10%) studies have measured SpO2 only. The remaining three stud ies have estimated both parameters. The majority of the studies have used 1–3 min videos for estimation. Among the estimation methods, Deep Learning and Independent component analysis (ICA) were used by 11/42 (26.19%) and 9/42 (21.42%) studies, respectively. According to the Bland-Altman analysis, only 8/45 (17.77%) HR studies achieved the clinically accepted error limits whereas, for SpO2, 4/5 (80%) studies have matched the industry standards (±3%). Discussion: Deep Learning and ICA have been predominantly used for HR estimations. Among deep learn ing estimation methods, convolutional neural networks have been employed till date due to their good generalization ability. Most non-contact HR estimation methods need significant improvements to im plement these methods in a clinical environment. Furthermore, these methods need to be tested on the subjects suffering from any related disease. SpO2 estimation studies are challenging and need to be tested by conducting hypoxemic events. The authors would encourage reporting the detailed information about the study population, the use of longer videos, and appropriate performance metrics and testing under abnormal HR and SpO2 ranges for future estimation studies.
- Facial video based physiological variables estimation in dark environmentsPublication . Gupta, Ankit; Dias, Fernando Manuel Rosmaninho Morgado Ferrão; Ravelo García, Antonio GabrielAs estimativas de parâmetros fisiológicos desempenham um papel relevante na de terminação do estado de saúde de um indivíduo. Entre esses parâmetros, a fre quência cardíaca e a saturação de oxigénio têm sido amplamente utilizadas para monitorização da saúde durante exames médicos, cirurgias, diagnóstico de distúr bios do sono e em unidades de cuidados intensivos. As técnicas de referência para estimar esses parâmetros são a eletrocardiografia e a fotopletismografia. Ambas são técnicas baseadas em contacto e, portanto, podem causar desconforto ao paciente em cenários como monitorização prolongada e pele sensível ou queimada. Assim, a fotopletismografia remota foi introduzida como uma variante sem contacto da foto pletismografia. Esta técnica extrai o sinal de pulso do volume sanguíneo das sequên cias espaço-temporais da região de interesse, seguida pela estimativa da frequência cardíaca. Por outro lado, as estimativas da saturação de oxigénio são realizadas us ando o método de razão de razões usando os canais vermelho e azul. Os métodos existentes sem contacto foram projetados para condições de luz ambiente. Alguns métodos desenvolvidos para ambientes escuros usaram câmaras infravermelhas, que são caras, e os espectros resultantes têm força pulsátil inferior aos espectros visíveis. Portanto, esta tese investiga o potencial dos espectros visíveis para medidas fisiológ icas em ambientes escuros (iluminância 1,0 lux). Especificamente, esta tese tem três contribuições principais: primeiro, um novo método de estimativa da frequência cardíaca baseado na análise de componentes independentes subcompleta, que foi de senvolvido e testado sob diferentes condições em tempo real, e segundo, um conjunto de dados "Dark-Video" abrangendo participantes de diferentes etnias e, finalmente, uma nova arquitetura de aprendizagem profunda para aprimoramento de imagens escuras que também foi proposta para facilitar medições fisiológicas nos ambientes escuros mencionados acima (ou seja, métodos de estimativa em cascata pelo apri moramento de imagens). Diversas experiências foram conduzidas para a análise de desempenho usando métricas de desempenho selecionadas criticamente provaram a superioridade dos métodos desenvolvidos e também exibiram o seu potencial de serem clinicamente viáveis. A direção futura desta trabalho visa implementar esses métodos para cenários como monitorização do sono sem contacto ou monitorização durante a condução noturna.
- Non-Destructive Banana Ripeness Detection Using Shallow and Deep Learning: A Systematic ReviewPublication . Baglat, Preety; Hayat, Ahatsham; Mendonça, Fábio; Gupta, Ankit; Mostafa, Sheikh Shanawaz; Dias, Fernando MorgadoThe ripeness of bananas is the most significant factor affecting nutrient composition and demand. Conventionally, cutting and ripeness analysis requires expert knowledge and substantial human intervention, and different studies have been conducted to automate and substantially reduce human effort. Using the Preferred Reporting Items for the Systematic Reviews approach, 1548 studies were extracted from journals and conferences, using different research databases, and 35 were included in the final review for key parameters. These studies suggest the dominance of banana fingers as input data, a sensor camera as the preferred capturing device, and appropriate features, such as color, that can provide better detection. Among six stages of ripeness, the studies employing the four mentioned stages performed better in terms of accuracy and coefficient of determination value. Among all the works for detecting ripeness stages prediction, convolutional neural networks were found to perform sufficiently well with large datasets, whereas conventional artificial neural networks and support vector machines attained better performance for sensor-related data. However, insufficient information on the dataset and capturing device, limited data availability, and exploitation of data augmentation techniques are limitations in existing studies. Thus, effectively addressing these shortcomings and close collaboration with experts to predict the ripeness stages should be pursued.
- Visual Explanations of Deep Learning Architectures in Predicting Cyclic Alternating Patterns Using Wavelet TransformsPublication . Gupta, Ankit; Mendonça, Fabio; Mostafa, Sheikh Shanawaz; Ravelo-García, Antonio G.; Dias, Fernando Morgado: Cyclic Alternating Pattern (CAP) is a sleep instability marker defined based on the ampli tude and frequency of the electroencephalogram signal. Because of the time and intensive process of labeling the data, different machine learning and automatic approaches are proposed. However, due to the low accuracy of the traditional approach and the black box approach of the machine learning approach, the proposed systems remain untrusted by the physician. This study contributes to accurately estimating CAP in a Frequency-Time domain by A-phase and its subtypes prediction by transforming the monopolar deviated electroencephalogram signals into corresponding scalograms. Subsequently, various computer vision classifiers were tested for the A-phase using scalogram images. It was found that MobileNetV2 outperformed all other tested classifiers by achieving the average accuracy, sensitivity, and specificity values of 0.80, 0.75, and 0.81, respectively. The MobileNetV2 trained model was further fine-tuned for A-phase subtypes prediction. To further verify the visual ability of the trained models, Gradcam++ was employed to identify the targeted regions by the trained network. It was verified that the areas identified by the model match the regions focused on by the sleep experts for A-phase predictions, thereby proving its clinical viability and robustness. This motivates the development of novel deep learning based methods for CAP patterns predictions.