Aniruddha Sinha

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.

UbiHeld: ubiquitous healthcare monitoring system for elderly and chronic patients

Once the persons identity is established, the most important aspects of ubiquitous healthcare monitoring of elderly and chronic patients are location, activity, physiological and psychological parameters. Since smartphones have become the most pervasive computing platform today, it is only a logical extension to use the same in healthcare domain for bringing ubiquity. Besides smartphone, skeleton based activity detection and localization using depth sensor like Kinect make ubiquitous monitoring effective without compromising privacy to a large extent. Finally sensing mental condition is made possible by analysis of the subjects social network feed. This paper presents an end-to-end healthcare monitoring system code named UbiHeld (Ubiquitous Healthcare for Elderly) using the techniques mentioned above and an IoT (Internet of Things) based back-end platform.

Noise cleaning and Gaussian modeling of smart phone photoplethysmogram to improve blood pressure estimation

Photoplethysmography (PPG) signals, captured using smart phones are generally noisy in nature. Although they have been successfully used to determine heart rate from frequency domain analysis, further indirect markers like blood pressure (BP) require time domain analysis for which the signal needs to be substantially cleaned. In this paper we propose a methodology to clean such noisy PPG signals. Apart from filtering, the proposed approach reduces the baseline drift of PPG signal to near zero. Furthermore it models each cycle of PPG signal as a sum of 2 Gaussian functions which is a novel contribution of the method. We show that, the noise cleaning effect produces better accuracy and consistency in estimating BP, compared to the state of the art method that uses the 2-element Windkessel model on features derived from raw PPG signal, captured from an Android phone.

Pose Based Person Identification Using Kinect

The importance of automatic person identification using non-intrusive biometric modality has created enormous interest in computer vision society over the last few years. For this, gait based person recognition is receiving much more attention in different applications like visual surveillance, security control, people counting. In this paper, we have presented a gait based person identification system using 3D human pose modeling for any arbitrary walking pattern in any unrestricted indoor environment, using Microsoft Kinect sensor. Instead of estimating gait cycle, we have modeled the gait pattern with a spatiotemporal set of key poses and sub-poses which occur periodically in different gait cycles. The robustness of the solution is increased by outlier detection to handle noisy skeleton data obtained from Kinect. The performance of the proposed system is also assessed with rotating Kinect setup to increase the field of view of single Kinect. We have done the average and worst case performance evaluation of the system with respect to the existing Kinect based approaches. It needs to be mentioned that our proposed person identification system is able to achieve a frame level F-score of more than 90% for 20 subjects with fixed Kinect setup.

Estimating blood pressure using Windkessel model on Photoplethysmogram.

Simple and non-invasive methods to estimate vital signs are very important for preventive healthcare. In this paper, we present a methodology to estimate Blood Pressure (BP) using Photoplethysmography (PPG). Instead of directly relating systolic and diastolic BP values with PPG features, our proposed methodology initially maps PPG features with some person specific intermediate latent parameters and later derives BP values from them. The 2-Element Windkessel model has been considered in the current context to estimate total peripheral resistance and arterial compliance of a person using PPG features, followed by linear regression for simulating arterial blood pressure. Experimental results, performed on a standard hospital dataset yielded absolute errors of 0.78±13.1 mmHg and 0.59 ± 10.23 mmHg for systolic and diastolic BP values respectively. Results also indicate that the methodology is more robust than the standard methodologies that directly estimate BP values from PPG signal.

Evaluation of Different Onscreen Keyboard Layouts Using EEG Signals

The paper aims at evaluation of different onscreen keyboard layouts based on the biological responses of the users. The signal used for the said purpose is Electroencephalogram acquired by low cost neuro-headset from Emotiv. We propose to use human cognition as the fundamental feature to discriminate between user-friendly vs. cumbersome onscreen layout designs. To validate our observations we compared our results with bench marked data based on user study and KLM-GOMS model. A classifier is first trained for high and low cognition tasks based on well-established cognitive tests (e.g. Stroop test) and then this classifier is used to report the cognition class for a particular onscreen layout. A high cognition load class indicates complexity in the layout design whereas a low cognition output indicates the layout to be user friendly. Present evaluation methods like user study or KLM-GOMS based model, serves as an indirect measure of goodness of layout designs. In contrast, our approach has a unique advantage as this is a direct measure of humans biological response subjected to stimuli (in our case onscreen keyboard layouts) hence more reliable.

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.

Recognition of trademarks from sports videos for channel hyperlinking in consumer end

In this paper authors have proposed a system to automatically recognize the Trademarks from sports video for channel hyperlinking in client end. In this method we have used the output of Set Top Box (STB) video stream in YUV 4:2:2 formats as input to our application. In this work we have first localized the text regions using some characteristic of text and then recognized the trademark using the shape invariant features and color features from the restricted trademark database. Experimental results show that the proposed approach can work in real time in any commercially available DSP platform and can mark the trademarks in the video successfully. The system on different type of sports videos gives a recall rate of 86.6% and a precision rate of 85.42%.

Pattern based robust digital watermarking scheme for images

Digital Watermarking is an effective and popular technique to discourage illegal copying and distribution of copyrighted digital image information. The important attributes are the picture quality of the watermarked image (similarity to the original) and robustness to attacks such as cropping. We propose a transform-domain robust digital watermarking technique which uses a pattern-based compression of the watermark image, an intelligent dynamic embedding of the signature bits and a post-watermarking content-based visual masking technique to deliver high image quality and robustness in retaining watermark content against attacks (cropping).

Feature selection by Differential Evolution algorithm - A case study in personnel identification

Feature selection is an important area of research as it has a tremendous effect on the accuracy and performance of classification algorithms. In this paper we propose an objective function for feature selection, which combines the intra class feature variation and inter class feature distance using a Lagrangian multiplier. The inter class distance is measured using the sum of absolute difference of the ratio of mean and standard deviation for respective classes. The objective function is minimized using Differential Evolutionary (DE) Algorithm where the population vector is encoded using Binary Encoded Decimal to avoid the float number optimization problem. An automatic clustering of the possible values of the Lagrangian multiplier provides a detailed insight of the selected features during the proposed DE based optimization process. The classification accuracy of Support Vector Machine (SVM) is used to measure the performance of the selected features. The proposed algorithm outperforms the existing DE based approaches when tested on IRIS, Wine, Wisconsin Breast Cancer, Sonar and Ionosphere datasets. The same algorithm when applied on gait based people identification, using skeleton datapoints obtained from Microsoft Kinect sensor, exceeds the previously reported accuracies.