The aim of this paper is to create a personalized computational model replicating the cardiorespiratory functionality and modulations of endurance athletes, and evaluate changes in the endurance metrics during dynamic running conditions. A wearable electrocardiogram (ECG) sensor alongside an accelerometer and GPS module within a mobile phone, were utilized to acquire data from marathon runners during weekly training runs. This data served as input for a personalized computational model, termed as 'cardiac digital twin', specifically developed for the runner's heart. Dynamic breathing rate (BR) was computed throughout the run. BR in conjunction with the model-generated cardiac parameters enabled the computation of several clinically relevant cardiorespiratory metrics linked to endurance. Information on intrinsic cardiorespiratory parameters like change in ventilation-perfusion, oxygen uptake efficiency slope, cardiac output, ejection fraction etc., during running could provide a holistic understanding of the cardiorespiratory health of the athlete. It could help runners better understand how their bodies perform under various conditions like high humidity, altitude variation, etc., identify potential health risks, and tailor their training accordingly.

Body surface potential (BSP) mapping (BSPM) from reduced lead sparse electrocardiogram (ECG) signals is of high clinical relevance. Cost-efficient and non-invasive cardiac activity localization of myocardial infarction scars and arrhythmic sources are a few of its potential applications. However, most BSP reconstruction algorithms’ stability suffers from the underlying ill-posed inverse problem and poor morphological fidelity. Hence, model-constrained regularization is generally employed to incorporate physiological knowledge about the spatio-temporal BSP dynamics. In this treatise, we leverage the recent generative adversarial networks (GAN) paradigm and propose a multi-head attention-based pix2pix GAN architecture with an integrated structural similarity metric for high-fidelity BSPM from sparse ECG sensing. The attention mechanism ensures morphological saliency, while the structural similarity-based loss function regularizes the ill-posed reconstruction during model training and preserves the reconstructed BSP’s intricate fiducial morphology, which is critical for subsequent cardiac activity localization. The proposed BSPM framework has been tested on measured and synthetically generated BSP data utilizing a forward electrophysiology pipeline. The morphologically preserved BSP generated from the proposed model can potentially lead to improved, cost-efficient, and non-invasive cardiac activity monitoring.

Recent progress in large-scale electrocardiogram (ECG) analysis has yielded cardiologist-level performance, albeit on uni-labeled datasets. However, in the real-world, ECG recordings often have markers of multiple labels like those in the PhysioNet Challenge 2020 dataset (PNC20DB). In the proposed classification strategy, we employ a novel class-distribution rebalancing approach, followed by a hybrid deep learning architecture to manage such multi-class multi-label (MCML) and class-imbalanced datasets. In the hybrid architecture, we pass 12-lead ECG data through a convolution neural network (CNN) and only Lead II ECG data through a residual network (ResNet). We also include domain features as a third processing unit. Finally, we employ k-means on the window-level predictions generated by the concatenation layer to obtain the final class-prediction. The proposed classification model is evaluated on the PNC20DB consisting of 27-class, 12-lead, MCML ECG recordings. The proposed architecture beats the leading entries of PhysioNet Challenge 2020 (PNC2020) and recent state-of-the-art techniques in a five-fold cross-validation method. It generates median AUROC and AUPRC of 94.1% and 56.2%, respectively. It also yields a median PNC2020 challenge metric of 60.4.

There is growing interest in developing non-invasive, widely accessible screening approaches for coronary artery disease (CAD) that are compatible with wearable technology. Prior studies have examined the association of CAD with abnormalities in the QRS-T and PR segments of the electrocardiogram (ECG), which require accurate identification of the onsets and offsets of P-QRS-T waves. This study proposes an alternative approach that extracts variability features from interval time series defined solely by ECG P-QRS-T wave peaks, thereby overcoming the persistent challenge of precise onset and offset detection. The proposed supervised hybrid feature selection approach identified an optimal feature combination that achieved$\mathbf{9 2 \%}$CAD/NonCAD classification accuracy on the validation dataset. It surpassed popular feature selection algorithms, including LASSO, mRMR, BBA, BCS, and BGW. On a blind test dataset, the selected features enabled the final trained ensemble classifier to achieve 88 % accuracy, correctly identifying 86 % of subjects with CAD and 92% of subjects without CAD-outperforming state-of-the-art methods evaluated on the same dataset. Furthermore, validation on a manually annotated QT database revealed notable correlations between proposed features extracted from peak based and clinically relevant interval time series, supporting their potential interchangeability when automated onset-offset detection is unreliable.

Cardiac computational models that replicate cardiac functionalities like a ‘digital twin’, can play important roles in serving clinical and research requirements, ranging from presurgical planning to predictive analysis. Personalization of such digital twins are non-trivial and computationally exhaustive due to the uncertainties of fitting mechanistic models to clinical measurements for individual patients. In this paper, we propose a method to personalize the hemodynamics functionality of a cardiac digital twin using a particle swarm optimization (PSO) framework that tunes the cardiac chamber properties based on subject-specific echocardiogram (Echo) and electrocardiogram (ECG) data. Parameters derived from ECG like information related to time instances of pumping action in cardiac chambers and Echo parameters like left ventricle end systolic and diastolic diameters and volumes are used to personalize the cardiac chamber parameters of an existing lumped cardiac hemodynamics model. Using this strategy, personalized hemodynamics parameters are generated for a healthy and two diseased subjects, suffering from cardiac Amyloidosis and Grade I Diastolic dysfunction. The proposed method of non-invasive modality-based (Echo and ECG) personalizing cardiac functionality can play a critical role in facilitating the circulatory hemodynamics model for clinical settings and aid in enabling precision medicine applications.

Patients surviving a brain stroke often experience an impaired neuro-motor coordination and cognitive capability. Rehabilitation assisted by therapists can help them regain much of this coordination. In recent past, gamified activities have proved to be effective in this regard with enhanced patient engagement. But, they may require special hardware and certain usage restrictions regarding patient's positioning etc. for operating effectively. We have set out to develop a suite of games using a smartwatch to sense arm's motion to eliminate such challenges, supporting customized scoring for different post-stroke mobility stages and focusing on state-of-the-art 3D graphics offering a high realism aimed at better patient engagement and adherence. In this demonstration, we present two of these games. First is a 'Forest Stroll' game where the patient controls heading of an in-game character moving on a forest path, with scoring based on how closely the path is followed, with a few additional arm gestures which can be activated by the therapist optionally. Second is a 'Drumming' game, where the patient controls a virtual drumstick and tries to play a customizable pre-saved pattern involving multiple ranges of motion, scored on how closely the pattern is played, testing both motor and cognitive capabilities.

Freezing of Gait (FoG) is one of the incapacitating motor symptoms that appear in patients with Parkinson’s Disease (PD). FoG manifests gait impairments and imposes unforeseen difficulties in commencing the locomotion. Frequent episodes of FoG often lead to fall-related injuries and impart dreadful health repercussions. Prediction of FoG before the occurrence could potentially increase the opportunities for pre-emptive cueing to mitigate or abate the episode of FoG. This paper presents a novel algorithm to predict the onset of FoG using a single ankle accelerometer sensor. Principally, we have focused on designing a lightweight algorithm to facilitate the real-time prediction of FoG in resource-limited hardware. A novel Genetic Algorithm (GA) is introduced as a feature selection method to enhance the algorithm’s performance. We have adapted the patient-invariant model which is a more viable approach in practical deployment. The algorithm is evaluated using the Daphnet dataset and achieved 88% FoG prediction accuracy with 1 second prediction time.

This paper presents a novel approach of generating synthetic Photoplethysmogram (PPG) data using a physical model of the cardiovascular system to improve classifier performance with a combination of synthetic and real data. The physical model is an in-silico cardiac computational model, consisting of a four-chambered heart with electrophysiology, hemodynamic, and blood pressure auto-regulation functionality. Starting with a small number of measured PPG data, the cardiac model is used to synthesize healthy as well as PPG time-series pertaining to coronary artery disease (CAD) by varying pathophysiological parameters. A Variational Autoencoder (VAE) structure is proposed to derive a statistical feature space for CAD classification. Results are presented in two perspectives namely, (i) using artificially reduced real disease data and (ii) using all the real disease data. In both cases, by augmenting with the synthetic data for training, the performance (sensitivity, specificity) of the classifier changes from (i) (0.65, 1) to (1, 0.9) and (ii) (1, 0.95) to (1, 1). The proposed hybrid approach of combining physical modelling and statistical feature space selection generates realistic PPG data with pathophysiological interpretation and can outperform a baseline Generative Adversarial Network (GAN) architecture with a relatively small amount of real data for training. This proposed method could aid as a substitution technique for handling the problem of bulk data required for training machine learning algorithms for cardiac health-care applications.

Freezing of Gait (FoG) is a paroxysmal and devitalizing symptom associated with Parkinson’s disease (PD). Episodes of FoG impedes gait and augments fall propensity, often leading to serious fall-injury. In this paper, we present a method for online detection of FoG using a wearable motion sensor. The novelty lies in utilizing the Empirical Wavelet Transform for signal denoising and incorporating the two new features to ameliorate the accuracy of the algorithm. Fundamentally, we have focused on a patient-independent model and leveraged a single ankle sensor which makes it a more feasible approach in terms of usability. Our model is evaluated on Daphnet dataset and achieved the average Sensitivity of.95 and Specificity of.70 with only a single sensor, demonstrating its immense potential.

Synthetic data generation has recently emerged as a substitution technique for handling the problem of bulk data needed in training machine learning algorithms. Healthcare, primarily cardiovascular domain is a major area where synthetic physiological data can be used improve accuracy of machine learning algorithm. This paper presents a novel approach of generating synthetic Photoplethysmogram (PPG) data using statistical explosion. Synthetic data is subsequently used to classify Coronary Artery Disease (CAD) using a two stage cascaded classifier. Proposed classifier along with synthetic data removes class bias and provides better accuracy compared to state of art. The proposed data generation and cascaded classifier is generic enough to be used to improve machine learning algorithm on any time series signal.

Electrooculography (EOG) signals acquire different types of eye movements, which can be employed for human-machine interfaces (HMI) and also for diagnostic purposes. In realistic circumstances, EOG signals tend to be contaminated with noise due to unconstrained head movements. This noise degrades the signal quality as well as increases the misclassification rate of eye movement detection. General filtering and preprocessing techniques are unable to remove this noise. This paper presents a novel approach of head-movement noise removal from EOG signals by employing a biorthogonal wavelet transform to extract the level-4 approximation coefficients, which are also exploited as features classified by k- nearest neighbor (kNN) classifier. This approach enhances the classification performance remarkably. Even when this wavelet based technique is applied as denoising technique and features to the prior arts, it improves the performance of those existing techniques too. Moreover, the proposed technique is suitable for real time applications.

The increasing importance of Kinect as a tool for clinical assessment and rehabilitation is due to its affordability, portability and being a markerless system for human motion capture. However, it is inefficient in terms of accuracy in measuring 3-D body joint locations when compared to marker-based motion capture systems. The measured length of the physically connected joints (bone length) vary with time, along with joint fluctuations during static pose. In this paper, we propose a novel approach to filter the noise of the Kinect 3-D joint coordinates while minimizing the variation in bone length. Kalman is used to filter the data and track the motion, while differential evolutionary (DE) optimization is used to minimize the fluctuations in bone length. A feedback loop is introduced between the Kalman and DE for exchanging the parameters. The algorithm is tested on the data obtained from 26 healthy subjects performing Range of Motion, Single Limb Stance (SLS) exercises and 10 stroke survivors performing SLS. Experimental results show average 41% and 40% improvement in deviation of bone length, which are under motion, for the healthy subjects and stroke patients respectively, outperforming Kalman filter and other existing algorithms like low pass filter, exponential, double exponential filter.

Microsoft Kinect has the huge potential to be used in home-based rehabilitation and clinical assessments for patients suffering from stroke or other neurological disorder, due to its affordability and unobtrusiveness in analysing joint kinematics. However, skeleton data obtained from Kinect Xbox 360 (Kinect 1) or Kinect Xbox One (Kinect 2) are usually noisy which affects accuracy of estimation of three dimensional joint locations. The noise profile varies for both stationary and dynamic postures and it affects anthropometric measurements of the body segments connecting any two joints. We propose a novel approach to constrain a standard Kalman filter, based on the dynamics of individual joints, in order to keep the distance between any two physically connected joints (namely bone length) constant over time. Our constrained Kalman filter method not only tracks the joints accurately but also reduces the variation in bone lengths by 92% and 94% for Kinect 2 and 1 respectively.

Cognitive load corresponds to the amount of working memory demanded while performing a certain task. Estimation of cognitive load is crucial to many domains and the usage of pupil size dilation to accomplish this is widely researched. However, existing approaches suffer severely as they are largely based on the raw pupil size. In this study, we aim to use the frequency domain analysis of the pupil size variations to get an insight of the load imposed. We propose a cognitive load metric based on the power and frequency relations at the mean frequency of the variation in pupil size. The stimulus used is a mental addition task which is designed in a manner to induce low and high cognitive loads on the participants. Results show good separation in the metric for the tasks inducing low and high mental workloads in contrast to the state of the art methods.

During an examination, the performance of a student not only depends on the preparation but also depends on cognitive and psychological factors. The present study aims at analysing the dynamics of the mental workload or stress and its impact on students' performance during an examination process. The experiment is designed using a set of multiple choice questions (MCQs) in one of the subject area namely data-structure. The MCQs are selected in three levels of complexity, which are rated by subject matter experts. A total of 13 right-handed graduate students in the specialization of Masters in Computer Application participated in the experiment. In order to get rid of any bias related to the intelligent quotient (IQ), students are taken such that the IQ varies from low to high. Experimental tasks are designed as interleaved sequences of the MCQs of varying complexity levels. During the tasks, Galvanic skin response (GSR) and pulse-oximeter (SPO2) signals are captured to estimate the stress of an individual from electro-dermal changes and heart rate variability (HRV). Apart from the tonic and phasic power of the GSR, fluctuation analysis is performed on the raw GSR signals. The standard deviation of normal-to-normal interval (SDNN) is computed to measure the HRV using the Photoplethysmogram (PPG) signal obtained from the SPO2 device. An estimation of the stress level is done using a score computed by the fluctuation analysis of the GSR signal. Out of the 13 students, the GSR sensor data for the 6 students are found to erroneous and hence only 7 data are analyzed. The methodology used to reject the erroneous data is also presented. Results indicate that there is a strong statistical correlation between the complexity of the MCQs and the GSR signals. Results of HRV analysis provide new insights to guess work during an assessment process.

This paper presents a novel single limb body balance analysis system which will aid medical practitioners to analyze crucial factor for fall risk minimization, injury prevention, fitness and rehabilitation programs. We use skeleton data obtained from Microsoft Kinect which captures full human body as well as ensures user's privacy. A new eigen vector based curvature analysis algorithm is developed to compute single limb stance (SLS) duration on the skeleton data. Two parameters vibration-jitter and force per unit mass (FPUM) are derived for each body part to assess postural stability during SLS. Experimental results show the efficacy of our system to apply it in medical domain.

Non-invasive cuff-less Blood Pressure (BP) estimation from Photoplethysmogram (PPG) is a well known challenge in the field of affordable healthcare. This paper presents a set of improvements over an existing method that estimates BP using 2-element Windkessel model from PPG signal. A noisy PPG corpus is collected using fingertip pulse oximeter, from two different locations in India. Exhaustive pre-processing techniques, such as filtering, baseline and topline correction are performed on the noisy PPG signals, followed by the selection of consistent cycles. Subsequently, the most relevant PPG features and demographic features are selected through Maximal Information Coefficient (MIC) score for learning the latent parameters controlling BP. Experimental results reveal that overall error in estimating BP lies within 10% of a commercially available digital BP monitoring device. Also, use of alternative latent parameters that incorporate the variation in cardiac output, shows a better trend following for abnormally low and high BP.

Extraction of desirable information from electroencephalogram signals require same level of active involvement from the participants throughout the entire duration of the task. However, this is hard to attain due to environmental, personal and internal factors including thought processes. This poses a major challenge in realizing accurate evaluation of mental workload. This study is aimed at detection of the inactive mental states of the participant during an experimental task. Conventionally cognitive load is computed with respect to the baseline period. Here a novel approach is adopted based on the detection of most inactive mental state during the rest period. It is observed that alpha rhythms (8 - 12 Hz) are dominant than theta rhythms (4 - 7 Hz) during the rest state and this information is used in determining the most inactive mental states. Galvanic skin response (GSR) is also analyzed for the same purpose to validate the decoded mental state from the brain signals. Results indicate that the proposed approach of inactivity detection, improves the overall accuracy of detection of cognitive load by 15.57 %.

Heart rate variability (HRV) measures the instantaneous change in heart rate and is an important marker for checking physical condition as well as mental stress of a person. In this paper, we propose a methodology to calculate HRV of a person using smart phone audio. Heart sound is captured in the inbuilt microphone of a smart phone, by placing the device on the chest of the person. We propose a process flow to make the phone captured noisy audio signal clean and audible. Furthermore, we propose a novel peak detection algorithm for accurately locating the peaks corresponding to heart sound in the noisy audio signal. The algorithm is also capable of rejecting the noisy peaks present in the captured audio that resembles heart sound pattern. Results show that the proposed methodology yields significant improvement in estimating HRV parameters compared to a clinical pulse-oximeter device, that works on the principle of photoplethysmogram (PPG) technique.

It is very challenging to provide a learning experience which is meaningful, motivated and at the same time enjoyable in nature. This often affects the students who cannot learn or do not want to learn due to lack of engagement and guidance. The same scenario is also true for working professionals in industries. Cognitive flow, defined as the mental state in which a subject is fully concentrating with a feeling of full involvement and enjoyment, is reported to play a key role in this. There are different questionnaire based indirect methods for measuring ones' flow state. However, in our present work we attempt to measure the flow state more directly using Electroencephalogram and multi-modal physiological signals including heart rate variability and galvanic skin response. Twenty right-handed engineers from our research lab played a video game to induce conditions of boredom and flow. A modified colour based Tetris (similar to Stroop test) game is used for the said purpose. A comparative study is done between the offline questionnaire based and the physiological signal based flow measurements. From the results it is clear that flow/boredom state can be derived from brain signals, which is modeled using Markov chain, as well as from other physiological signals. Hence can be used as an important feedback in various applications for maintaining a steady flow state for a longer period. Finally, the flow-boredom model generated from brain signals has been used in Web Based Learning to automatically measure the learning experience.

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.

Sensor nodes are embodiment of IoT systems in microscopic level. As the volume of sensor data increases exponentially, data compression is essential for storage, transmission and in-network processing. The compression performance to realize significant gain in processing high volume sensor data cannot be attained by conventional lossy compression methods. In this paper, we propose ASDC (Adaptive Sensor Data Compression), an adaptive compression scheme that caters various sensor applications and achieve high performance gain. Our approach is to exhaustively analyze the sensor data and adapt the parameters of compression scheme to maximize compression gain while optimizing information loss. We apply robust statistics and information theoretic techniques to establish the adaptivity criteria. We experiment with large sets of heterogeneous sensor datasets to prove the efficacy. Nonlinear lossy compression (Chebyshev) is extensively considered as the standard technique as well as experimental result with frequency domain compression like Discrete Fourier Transform (DFT) is shown as future scope of further improvement.

Electroencephalogram (EEG) signals are of very low amplitude and are easily contaminated by different types of noises like environmental and of non-cerebral in nature. Thus signal pre-processing is a major challenge while dealing with applications involving EEG signals. The scenario becomes much more complex while using commercially available, low resolution devices as they have fewer electrodes. In this paper, we have applied some of the widely used signal processing techniques to get rid of eye blink and noise related artifacts from EEG signals recorded using a low cost wireless device from Emotiv. Investigations reveal that clustering based eye blink detection method and the skewness based noise detection method give the best detection accuracy. As an example use-case, we show how selective filtering of the EEG signals in the blink regions and removal of noisy windows can help in improving the discrimination power between the two types of color Stroop stimulus based cognitive load analysis. Thus with appropriate signal pre-processing techniques, these low resolution devices can be successfully used to differentiate between different levels of mental workload, which in turn makes these devices useful for non-medical Brain Computer Interface (BCI) applications requiring mass deployment.

Measurement of cognitive load using brain signalsis an important area of research in human behavior and psychology. Recently, there have been attempts to use low cost, commercially available Electroencephalogram (EEG) devices for the analysis of the cognitive load. Due to the reduced number of leads, these low resolution devices pose major challenges in signal processing as well as in feature extraction. In this paper, we investigate the significant leads or channels that are useful for the analysis of the cognitive load. We use a standard matching test and n-back memory test imparting low and high cognitive loads respectively. The investigation is based on the analysis of variance (ANOVA) of Alpha and Theta frequency band signals for various combinations of leads. Comparisons have been done between the previously reported leads and those obtained using a few feature selection algorithms. Results indicate that for a given stimulus, though the significant leads are very much dependent on the subjects, the leads corresponding to the left frontal lobe and right parieto-occipital lobe are in general most significant across majority of subjects for analysis of the cognitive load.

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.

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 user's 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.

In this paper authors have proposed a person identification method independent of his position with respect to the input sensor. The proposed method works for various postures or states namely, standing, sitting, walking. This method initially identifies the person's state and separate SVM based models are used for person identification (PI) for each of these three above mentioned states.

Regular ECG check up is a good practice for cardiac patients as well as elderly people. In this paper we propose a low cost methodology to coarsely estimate the range of some important parameters of ECG using Photoplethysmography (PPG). PPG is easy to measure (even with a smart phone) and strongly related to human cardio-vascular system. The proposed methodology extracts a set of time domain features from PPG signal. A statistical analysis is performed to select the most relevant set of PPG features for the ECG parameters. Training model for the ECG parameters are created based on those selected features. Both artificial neural network and support vector machine based supervised learning approach is used for performance comparison. Experimental results, performed on benchmark dataset shows that good accuracy in the estimation of ECG parameters can be achieved in our proposed methodology. Results also show that the overall performance improves in using feature selection technique rather than using all the PPG features for classification.

Individuals exhibit different levels of cognitive load for a given mental task. Measurement of cognitive load can enable real-time personalized content generation for distant learning, usability testing of applications on mobile devices and other areas related to human interactions. Electroencephalogram (EEG) signals can be used to analyze the brain-signals and measure the cognitive load. We have used a low cost and commercially available neuro-headset as the EEG device. A universal model, generated by supervised learning algorithms, for different levels of cognitive load cannot work for all individuals due to the issue of normalization. In this paper, we propose an unsupervised approach for measuring the level of cognitive load on an individual for a given stimulus. Results indicate that the unsupervised approach is comparable and sometimes better than supervised (e.g. support vector machine) method. Further, in the unsupervised domain, the Component based Fuzzy c-Means (CFCM) outperforms the traditional Fuzzy c-Means (FCM) in terms of the measurement accuracy of the cognitive load.

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.

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.

This paper proposes an extension of the traditional Fuzzy c-Means algorithm by allowing each component of the datapoints to independently contribute in the decision-making process of determining the cluster membership of the point. The above extension results in an improved accuracy in clustering. The second interesting issue undertaken here is to determine the optimum fuzziness control parameter for stabilization of the cluster centers. Lastly, the proposed extension helps in identifying the important dimensions in characterization of the datapoints. Experimental runs indicate an improvement in accuracy of clustering by the proposed algorithm in comparison to the traditional Fuzzy c-Means, with respect to the measure Fmeasureparameter by 26, 15 and 6 percentage on Colon cancer, Wine and Wisconsin Diagnostic Breast Cancer (WDBC) datasets respectively.

Unobtrusive people identification based on gait recognition is steadily growing attention in modern video surveillance systems. In this paper we propose a two tier architecture for gait based people identification. The proposed architecture employs multiple Kinects working together as an integrated system to broaden the coverage area of surveillance. An intelligent triggering mechanism is presented for switching on and off the infrared (IR) cameras of different Kinects for optimum resource utilization. For efficient utilization of network bandwidth, the skeleton data from all the Kinects' edge devices (controllers) are compressed and sent to a backend server for people identification. Experimental results show that the triggering mechanism is capable of reducing the average power consumption of the Kinect controllers by more than 40 percent. Results also indicate that the person recognition accuracy does not degrade with the usage of the data compression, which reduces the data rate by 4 to 6 times while preserving their statistical properties.

In this paper, we explore features related to spectral and time domain for classification of crowd noise. Spectral information is represented by mel-frequency cepstral coefficients (MFCC) and spectral flatness measure (SFM), whereas time domain information is represented by short-time energy (STE) and zero-cross rate (ZCR). For carrying out these studies, crowd noise data collected from railway stations and book fairs have been used. In this study, two categories of crowd noise, namely, no crowd and crowd, are used. Support Vector Machines (SVM) are used to capture the discriminative information between the above mentioned noise categories, from the spectral and time domain features. The SVM models are developed separately using spectral and time domain features. The classification performance of the developed SVM models using spectral and time domain features is observed to be 91.35% and 84.65%, respectively. In this work, we have also examined the performance of the crowd noise classification system by combining the spectral and time domain information at feature and score levels. The classification performance using feature and score level fusion is observed to be 93.10% and 96.25% respectively.

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.

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.

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 human's biological response subjected to stimuli (in our case onscreen keyboard layouts) hence more reliable.

A lot of research is now going on to extract the context of the show to provide additional information related to the TV show. One major method to extract the context from TV is to recognize the texts from the videos which is also known as video Optical Character Recognition (VOCR). The problem of VOCR from the TV shows of a multiligual country like India is more difficult. In India still more than 90% TV viewers are using RF Cable as input to TV and nearly 90% channels have multilingual texts in the TV shows. Thus the video quality is poor in compare to the modern digital TV signals as well as different text scripts are present in a single video frame. These made the problem of Indian TV context recognition more challenging. So this paper is concerned about the construction of a video corpus of text rich Indian TV shows. The proposed database contains more than 100 videos each of nearly 10 min duration containing text in the video frame. A statistical analysis of the corpus is also presented in the paper which can be used to identify the genre of TV show. The analysis also revealed that distribution of numerals, special characters, uppercase and lower case character can be used to classify a news video frame. This corpus is useful for a wide variety of research problems namely, (i) localization of the text regions from a video frame, (ii) recognition of texts from a video frame, (iii) extraction of context from video, and (iv) performance evaluation of a video OCR system.

We propose a fast video transcoding technique based on region-of-interest (ROI) determination. The ROIs are identified using the properties of the human visual system (HVS), applied in the compressed domain. We use the edge, motion and spatial frequency content of the video frame as the parameters in identifying perceptually important regions in the compressed domain (Agarwal, G. et al., 2003). The TM5 rate-control of the video transcoder is modified to assign relatively more bits to the ROIs, thereby providing better quality to the areas that are likely to attract the viewer's attention. The ROI determination in the compressed domain has been modified to give more robust results. Our algorithm achieves a speed-up of 15-20 times as compared to similar algorithms in the pixel domain, while giving comparable results. This computation is only around 8% of the total transcoder complexity.

We propose a fast, yet simple algorithm to find the region of interest (ROI) from a compressed MPEG video bitstream, with partial decoding. We have used the properties of the human visual system (HVS), applied in the DCT domain, to extract the ROIs. Though a lot of work has been done to obtain ROIs in images based on the HVS, all these systems work in the pixel domain. However, finding the ROIs in the compressed domain has wide applications such as emphasizing perceptually important regions while transrating, defining descriptors for encoded video (MPEG-7), changing image size to adapt to heterogeneous client displays, etc.

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).