Parama Sridevi

The paper presents the model of a sign language interpreter that can verbalize American Sign Language (ASL). This robust model is based on creating a human-computer interface (HCI) using the user’s hand gesture only. The combination of Hardware and software interfaces-webcam and MATLAB 2016a-performs the feature extraction process from the image captured from real-time video of hand signs. These features are compared with the features of the database images and after some image processing techniques in MATLAB, the system generates outputs depending on the prediction of highest resemblance. As the model is free from any other apparatus or accessories, it is solely practical and easy to use. This model provided satisfactory accuracy in our tests without any need of any constant or unicolor background. The proposed technique, together with a vast source database, will definitely be highly beneficial for mitigating the communication gap between the people with speaking and hearing abilities and those without them.

The paper presents the design methodology and implementation of a low-cost spirometer prototype that can detect pulmonary diseases. By sensing the pressure difference of the expiratory air passing through the 3D printed venturi tube, the system calculates forced vital capacity (FVC). Through free campaigns, the performance and efficiency of this venturi tube spirometer were tested in different locations and the accuracy rate was highly promising. With this great efficiency and accuracy, this model diagnoses chronic obstructive pulmonary disease (COPD). Apart from measuring FVC, the model also measures forced expiratory volume in one second (FEV1) and from their ratio, it identifies COPD. In underprivileged areas, each and every hospital cannot afford spirometers available in the market because of their high price. This low-cost spirometer model ensures proper detection of pulmonary diseases in those underprivileged areas and it is definitely going to add a new dimension to the diagnosis of COPD.

Chronic Kidney Disease, Diabetes, Hypertension, and Anemia are affecting more people these days and causing serious deterioration in health conditions, which can cause death if left undiagnosed and untreated. Machine learning models can play an indispensable role in precisely predicting diseases at an early stage which can help doctors start the disease-management plan early and reduce the suffering of patients and the death rates. In this study, we propose machine learning based Chronic Kidney Disease, Diabetes, Hypertension, and Anemia Prediction. We analyzed Chronic_Kidney_Disease Data Set from the UCI repository. After data-prepossessing, we created four new datasets from the initial dataset for predicting the four diseases. We applied Feature Engineering on every dataset to identify the best features. We developed five machine learning based models and compared the models’ performance before and after Feature Engineering for every dataset. The Random Forest model performs best for chronic kidney disease prediction with an accuracy of 99.5%, validation score of 99.0%, and ROC-AUC score of 1.0. The Logistic Regression model gives the highest accuracy of 88.8%, validation score of 82.0%, and ROC-AUC score of 0.94 for predicting diabetes. For hypertension prediction, XGBoost outperforms other models with an accuracy of 88.8%, validation score of 83.2%, and ROCAUC score of 0.95. XGboost model best-predicted anemia with an accuracy of 88.8%, validation score of 91%, and ROC-AUC score of 0.91. Since the developed models can accurately perform these diseases’ predictions, we believe this study will be beneficial for the diagnosis and management of these diseases.

Patients with several incompletely diagnosed and understood chronic diseases suffer from symptoms that limit their functional capacity. In particular, chronic fatigue syndrome/myalgic encephalomyelitis (CFS/ME) and long covid syndromes lead to variable fatigue, malaise, poor and unrefreshing sleep, delayed sleep, and post-exertional exacerbation. There are no specific tests for these patients to diagnose their diseases properly. This paper presents a foot-insole sensor system for detecting and measuring physical leg activity, a wrist and arm motion sensor system for dominant arm and hand activity, and a cell phone system for measuring social interaction and noise exposure.

Monitoring blood pressure (BP) is an essential component of evaluating cardiovascular health, aiding in the early detection and management of hypertension-related complications. Traditional methods of BP measurement often involve invasive or cumbersome devices, leading to discomfort and reduced compliance. We propose a framework to monitor BP non-invasively, analyzing the face video captured by a webcam or smartphone camera leveraging the relationship of image-based Pulse Transit Time (iPTT) and Heart Rate Variability (HRV) with BP. We have built a dataset of 90 sets of collected videos using a mobile phone front camera and BP data from a standard digital BP monitor from 12 individuals from an approved Institutional Review Board (IRB) to evaluate our system. We have got a Mean Absolute Error (MAE) of 10.35+/−2.5 mmHg for systolic BP (SBP) and 7.8+/−1.5 mmHg for diastolic BP (DBP) while using the HRV representation RMSSD. On the other hand, an MAE of 8.25+/−3.5 mmHg for SBP and 7.7+/−2.5 mmHg for DBP while using the HRV representation SDRR. Finally, we have developed a framework and built a real-time system to monitor BP as a mobile and web-based application that can facilitate early detection of trends and anomalies, allowing healthcare providers to intervene promptly and personalize treatment plans.

In this manuscript, we describe the architecture and development of a non-invasive prototype- KidneyCare that captures the ten-second fingertip video using the smartphone camera and NIR LED. Then this fingertip video will be analyzed to estimate the creatinine, GFR, and CrCl levels by using ML models. KidneyCare acts as a regular, remote, self-monitoring, and noninvasive point-of-care by providing information about the user’s kidney condition. KidneyCare provides data visualization features and conducts as a data management platform for practitioners which promotes early diagnosis and initiation of an early treatment plan. With all the above-mentioned features, KidneyCare will be a powerful mHealth-based system for monitoring kidney conditions by estimating Creatinine, GFR, and CrCl levels non-invasively.

This work aims to explain leveled sampling period quantization by monitoring the instantaneous derivatives of the signal. Signal derivatives have been calculated and engaged in sensing signal summits. A differential sharpness or tip detection algorithm consists of one fixed level has been employed here. The detector compares each derivative value with the level to define sampling time into 2 individual time intervals for sharp and soft regions accordingly, then quantizes those and does 1-bit time encoding. Both signal and time codes are combined finally in a semi-synchronous style. The proposal is compatible with any pulse code modulations. Promising reconstructed signals are obtained by this method, in contrast with reconstructed shape and data compression. This paper also includes simulations and comparative discussions.

Current solar cells, under research and development, primarily utilize single band-gap absorber layer which limits the photon absorption capabilities. In pursuance of developing next-generation solar cells, research is moving towards an effective photon harvesting method. Recently, metal halide perovskites have drawn the attention of the research community considering its low cost and optoelectronic characteristics. In this paper, one-dimensional modeling of planar heterojunction perovskite solar cells is implemented. A linearly graded band-gap design in the intrinsic layer of an inverted p-i-n perovskite solar cell is studied. We demonstrate that the graded band-gap cells have power conversion efficiencies of 22.7%. An analysis of the simulation model yields high fill factors of 85% and high short-circuit current densities up to 25.18m Acm-2.