Aishwarya Visvanathan

A robust heart rate detection using smart-phone video

In this paper, the authors have presented a smartphone based robust heart rate measurement system. The system requires the user to place the tip of his/her index finger on the lens of a smart phone camera, while the flash is on. The captured video signal often contains noise generated due to (i) improper finger placement, (ii) imparting excessive pressure, which subsequently blocks normal blood circulation and (iii) movement of the fingertip. To mitigate the above issues, a two stage approach has been proposed. Firstly, the onset of good video signal is detected by formulating a finite state machine, which employs multiple window short time fast fourier transform. Only upon receiving sufficient acceptable video signal, the heart rate is computed. Results indicate that the proposed method has successfully identified and rejected noisy video signal, resulting in avoidance of erroneous output.

Estimation of blood pressure levels from reflective Photoplethysmograph using smart phones

As part of preventive healthcare, there is a need to regularly monitor blood pressure (BP) of cardiac patients and elderly people. Mobile Healthcare, measuring human vitals like heart rate, Spo2 and blood pressure with smart phones using the Photoplethysmography technique is becoming widely popular. But, for estimating the BP, multiple smart phone sensors or additional hardware is required, which causes uneasiness for patients to use it, individually. In this paper, we present a methodology to estimate the systolic and diastolic BP levels by only using PPG signals captured with smart phones, which adds to the affordability, usability and portability of the system. Initially, a training model (Linear Regression Model or SVM Model) for various known levels of BP is created using a set of PPG features. This model is later used to estimate the BP levels from the features of the newly captured PPG signals. Experiments are performed on benchmark hospital dataset and data captured from smart phones in our lab. Results indicate that by additionally adding information of height, weight and age play a vital role in increasing the accuracy of the estimation of BP levels.

PhotoECG: Photoplethysmographyto estimate ECG parameters

This paper presents a simple method to indirectly estimate the range of certain important electrocardiogram (ECG) parameters using photoplethysmography (PPG). The proposed method, termed as PhotoECG, extracts a set of time and frequency domain features from fingertip PPG signal. A feature selection algorithm utilizing the concept of Maximal Information Coefficient (MIC) is presented to rank the PPG features according to their relevance to create training models for different ECG parameters. The proposed method yields above 90% accuracy in estimating ECG parameters on a benchmark hospital dataset having clean PPG signal. The same method results an average of 80% accuracy on noisy PPG signal captured by iPhone, indicating its feasibility to create phone applications for preventive ECG monitoring at home.

Smart phone based blood pressure indicator

In this paper, we propose a methodology to estimate the range of human blood pressure (BP) using Photoplethysmography (PPG). 12 time domain features and 7 frequency domain features are pointed out and extracted from the PPG signal. A feature selection algorithm based on Maximal Information Coefficient (MIC) is presented to reduce the dimensionality of the feature set to effective ones, thereby cutting down resource requirements. Support Vector Machine (SVM) is used to classify the BP values into separate bins. The proposed methodology is validated and tested on a standard benchmark clean dataset as well as phone captured noisy dataset to justify its robustness and efficiency. Apart from a commending performance improvement, BP estimation is achieved with minimal features and processing, making the algorithm light weight for porting on smart phones.

HeartSense: smart phones to estimate blood pressure from photoplethysmography

In this paper we propose to demonstrate a smart phone application, that estimates human blood pressure (BP) values from photoplethysmography (PPG) signal using Windkessel model. PPG signal is extracted from a video sequence of a users index fingertip, acquired using smart phone camera. A set of time domain PPG features are used to estimate different lumped parameters of Windkessel model to simulate arterial BP. Under most of the cases, the application estimates systolic and diastolic BP values, within a range of ±10% of clinical measurement.

Enhancement of camera captured text images with specular reflection

Specular reflection of light degrades the quality of scene images. Whenever specular reflection affects the text portion of such an image, its readability is reduced significantly. Consequently, it becomes difficult for an OCR software to detect and recognize similar texts. In the present work, we propose a novel but simple technique to enhance the region of the image with specular reflection. The pixels with specular reflection were identified in YUV color plane. In the next step, it enhances the region by interpolating possible pixel values in YUV space. The proposed method has been compared against a few existing general purpose image enhancement techniques which include (i) histogram equalization, (ii) gamma correction and (iii) Laplacian filter based enhancement method. The proposed approach has been tested on some images from ICDAR 2003 Robust Reading Competition image database. We computed a Mean Opinion Score based measure to show that the proposed method outperforms the existing enhancement techniques for enhancement of readability of texts in images affected by specular reflection.

HeartSense: Estimating Heart Rate from Smartphone Photoplethysmogram Using Adaptive Filter and Interpolation

In recent days, physiological sensing using smartphones is gaining attention everywhere for preventive health-care. In this paper, we propose a 2-stage approach for robust heart rate (HR) calculation from photoplethysmogram (PPG) signal, captured using smartphones. Firstly, Normalized Least Mean Square (NLMS) based adaptive filter is used to clean up the noisy PPG signal. Then, heart rate is calculated from the frequency spectrum, which is further fine-tuned using different interpolation techniques. Experimental results, show that the overall HR calculation improves significantly due to the proposed 2-stage approach.

Improved heart rate detection using smart phone

Smart Phone based health care is a very recent topic and various methods for detection of heart rate are available. Reflective photoplethysmography (PPG) is used to measure heart rate of a person while placing the finger on the camera of a smart phone. In this paper, authors have proposed the usage of certain signal processing components to enhance the performance while retaining low complexity. Overlapping window based approach improves the accuracy of the solution. Post processing components are implemented in both time and frequency domain to detect the erroneous signals and remove false positives. Results indicate that, by additionally employing the above components, more than 50% improvement in heart rate detection accuracy is achieved as compared to a standard spectral based approach.

HeartSense: estimating blood pressure and ECG from photoplethysmograph using smart phones

Regular monitoring of certain vital parameters like heart-rate (HR), blood pressure (BP), Electrocardiogram (ECG) are the basic needs for elderly people and patients with chronic diseases residing at home. In this demo, authors would like to demonstrate the possibility of estimating BP levels and certain ECG parameters using the PPG signals captured from smart phones. The work includes mainly three components -- (i) robust PPG signal acquisition, (ii) estimation of BP levels (low, medium, high) from PPG signals and (iii) estimation of PR, RR, QRS and QT intervals of ECG parameters from PPG signals. Initially certain time domain features are extracted from PPG, which are used to create training models for various BP levels and ECG parameters. The approach is tested on two benchmark hospital datasets from (i) University of Queensland and (ii) Capnobase TBME RR dataset and one dataset captured from smart phones. Results indicate that the estimation accuracy is above 75% and sometimes above 95% if the height, weight and age information are considered.

Car number plate recognition for smart building management

The traditional OCR based approach for number plate recognition does not work for the variations in painting style of the number plates. In this paper authors have presented an image retrieval based method to recognize the car number plate captured using a smart phone to facilitate the Car management system of a Smart office premise. In the proposed method a smart phone is used to capture the images and extract features of the car number plate. These features are matched against predefined set of same car number plate images in the database. The character images are matched in an efficient manner to make it a real time solution. The proposed method recognizes the car with almost 93.75% accuracy and is already deployed in our office premise.