Dwaipayan Biswas

A Low-Complexity ECG Feature Extraction Algorithm for Mobile Healthcare Applications

This paper introduces a low-complexity algorithm for the extraction of the fiducial points from the electrocardiogram (ECG). The application area we consider is that of remote cardiovascular monitoring, where continuous sensing and processing takes place in low-power, computationally constrained devices, thus the power consumption and complexity of the processing algorithms should remain at a minimum level. Under this context, we choose to employ the discrete wavelet transform (DWT) with the Haar function being the mother wavelet, as our principal analysis method. From the modulus-maxima analysis on the DWT coefficients, an approximation of the ECG fiducial points is extracted. These initial findings are complimented with a refinement stage, based on the time-domain morphological properties of the ECG, which alleviates the decreased temporal resolution of the DWT. The resulting algorithm is a hybrid scheme of time- and frequency-domain signal processing. Feature extraction results from 27 ECG signals from QTDB were tested against manual annotations and used to compare our approach against the state-of-the art ECG delineators. In addition, 450 signals from the 15-lead PTBDB are used to evaluate the obtained performance against the CSE tolerance limits. Our findings indicate that all but one CSE limits are satisfied. This level of performance combined with a complexity analysis, where the upper bound of the proposed algorithm, in terms of arithmetic operations, is calculated as 2.423N+214 additions and 1.093N+12 multiplications for N ≤ 861 or 2.553N+102 additions and 1.093N+10 multiplications for N > 861 (N being the number of input samples), reveals that the proposed method achieves an ideal tradeoff between computational complexity and performance, a key requirement in remote cardiovascular disease monitoring systems.

Detecting Elementary Arm Movements by Tracking Upper Limb Joint Angles With MARG Sensors

This paper reports an algorithm for the detection of three elementary upper limb movements, i.e., reach and retrieve, bend the arm at the elbow and rotation of the arm about the long axis. We employ two MARG sensors, attached at the elbow and wrist, from which the kinematic properties (joint angles, position) of the upper arm and forearm are calculated through data fusion using a quaternion-based gradient-descent method and a two-link model of the upper limb. By studying the kinematic patterns of the three movements on a small dataset, we derive discriminative features that are indicative of each movement; these are then used to formulate the proposed detection algorithm. Our novel approach of employing the joint angles and position to discriminate the three fundamental movements was evaluated in a series of experiments with 22 volunteers who participated in the study: 18 healthy subjects and four stroke survivors. In a controlled experiment, each volunteer was instructed to perform each movement a number of times. This was complimented by a seminaturalistic experiment where the volunteers performed the same movements as subtasks of an activity that emulated the preparation of a cup of tea. In the stroke survivors group, the overall detection accuracy for all three movements was 93.75% and 83.00%, for the controlled and seminaturalistic experiment, respectively. The performance was higher in the healthy group where 96.85% of the tasks in the controlled experiment and 89.69% in the seminaturalistic were detected correctly. Finally, the detection ratio remains close (±6%) to the average value, for different task durations further attesting to the algorithms robustness.

Classifying human emotional states using wireless EEG based ERP and functional connectivity measures

In this paper we present a systematic exploration to determine several EEG based features for classifying three emotional states (happy, fearful and neutral) pertaining to face perception. EEG data were acquired through a 19-channel wireless system from eight adults under two conditions - in a constrained position and involving head-body movements. The movement EEG data was pre-processed using an artifact reduction algorithm and both datasets were processed to extract neurophysiological features - ERP components and from functional connectivity measures. The functional connectivity measures were processed using a brain connectivity toolbox and gray level co-occurrence matrices to generate a total of 463 features. The feature set was split into: training dataset comprising of constrained and movement EEG data and test dataset comprising of only movement EEG data. A retrospective cross-validation approach was run on the training dataset in conjunction with two classifiers (LDA and SVM) and the ranked feature set, to select the best features using a sequential forward selection algorithm. The best features were further used to prospectively classify the three emotions in the test dataset. Our results show that we can successfully classify the emotions using LDA with an accuracy of 89% and using top 17 ranked features.

ECG compression for remote healthcare systems using selective thresholding based on energy compaction

This paper presents a wavelet-based low-complexity Electrocardiogram (ECG) compression algorithm for mobile healthcare systems, in the backdrop of real clinical requirements. The proposed method aims at achieving good trade-off between the compression ratio (CR) and the fidelity of the reconstructed signal, to preserve the clinically diagnostic features. Keeping the computational complexity at a minimal level is paramount since the application area we consider is that of remote cardiovascular monitoring, where continuous sensing and processing takes place in low-power, computationally constrained devices. The proposed compression methodology is based on the Discrete Wavelet Transform (DWT). The energy packing efficiency of the DWT coefficients at different resolution levels is analysed and a thresholding policy is applied to select only those coefficients which have significant contribution to the original signal total energy. The proposed methodology is evaluated on normal and abnormal ECG signals extracted from the MIT-BIH database and achieves an average compression ratio of 16.5:1, an average percent root mean square difference of 0.75 and an average cross correlation value of 0.98.

Telemedicine system for game-based rehabilitation of stroke patients in the FP7-“StrokeBack” project

Stroke is a disease with very high socio-economic impact. In average, the healthcare expenditure cost for Strokes across different countries in Europe and USA exceeds 3% of their entire healthcare expenditure, including inpatient treatments, outpatient hospital visits and long-term rehabilitation and care1 Therefore, there is an urgent need for devising an effective long-term care and rehabilitation strategy for stroke patients, which would actively involve patients in the rehabilitation process while minimizing costly human support. This paper reports on the results of the FP7-StrokeBack project where game-based training system has been proposed allowing physicians to supervise the rehabilitation of patents at home. The proposed approach empowers the patients and their caretakers for effective application of rehabilitation protocols in their home settings, while leading physicians are enabled to supervise the progress of the rehabilitation (and intervene if needed) through the use of Personal Health Record (PHR) system. The increased rehabilitation speed and ability to perform training at home directly improves quality of life of patients.

Shape memory alloy smart knee spacer to enhance knee functionality: Model design and finite element analysis

In this paper we introduce Shape Memory Alloy (SMA) for designing the tibial part of Total Knee Arthroplasty (TKA) by exploiting the shape-memory and pseudo-elasticity property of the SMA (e.g. NiTi). This would eliminate the drawbacks of the state-of-the art PMMA based knee-spacer including fracture, sustainability, dislocation, tilting, translation and subluxation for tackling the Osteoarthritis especially for the aged people of 45-plus or the athletes. In this paper a Computer Aided Design (CAD) model using SolidWorks for the knee-spacer is presented based on the proposed SMA adopting the state-of-the art industry-standard geometry that is used in the PMMA based spacer design. Subsequently Ansys based Finite Element Analysis is carried out to measure and compare the performance between the proposed SMA based model with the state-of-the art PMMA ones. 81% more bending is noticed in the PMMA based spacer compared to the proposed SMA that would eventually cause fracture and tilting or translation of spacer. Permanent shape deformation of approximately 58.75% in PMMA based spacer is observed compared to recoverable 11% deformation in SMA when same load is applied on both separately.In this paper we introduce Shape Memory Alloy (SMA) for designing the tibial part of Total Knee Arthroplasty (TKA) by exploiting the shape-memory and pseudo-elasticity property of the SMA (e.g. NiTi). This would eliminate the drawbacks of the state-of-the art PMMA based knee-spacer including fracture, sustainability, dislocation, tilting, translation and subluxation for tackling the Osteoarthritis especially for the aged people of 45-plus or the athletes. In this paper a Computer Aided Design (CAD) model using SolidWorks for the knee-spacer is presented based on the proposed SMA adopting the state-of-the art industry-standard geometry that is used in the PMMA based spacer design. Subsequently Ansys based Finite Element Analysis is carried out to measure and compare the performance between the proposed SMA based model with the state-of-the art PMMA ones. 81% more bending is noticed in the PMMA based spacer compared to the proposed SMA that would eventually cause fracture and tilting or translation of spacer. Permanent shape deformation of approximately 58.75% in PMMA based spacer is observed compared to recoverable 11% deformation in SMA when same load is applied on both separately.

Low Complexity Single Channel ICA Architecture Design Methodology for Pervasive Healthcare Applications

In this paper, we propose a low-complexity architecture design methodology for the Single Channel Independent Component Analysis (SCICA) algorithm targeting pervasive personalized healthcare. SCICA, unlike the conventional ICA, separates the signal from multiple sources using only a single sensor that has tremendous potential for reducing the number of body-worn sensors. However, such applications are constrained by power consumption limitation due to the battery backup necessitating low-complexity system design and the on-chip area requirement. On the other hand, SCICA, involving computationally intensive stages including ICA, Fast Fourier Transform (FFT), Eigen Value Decomposition (EVD) and k-means clustering, is not possible to be mapped onto the low-complexity architecture directly from the algorithmic level. Hence, in this paper, adopting algorithm-architecture holistic approach, we introduce the Coordinate Rotation Digital Computer (CORDIC) based low-complexity SCICA architecture design methodology suitable for such resource constrained applications. K-means architecture used for low-complex SCICA based on the proposed methodology consumes core silicon area of 0.28mm2 and power of 0.25mW at 1.2 V, 1-MHz frequency using 0.13μm standard cell technology library (TSMC) that is about 50% less than that of the state-of-the art approaches. The functionality has been compared favorably with the conventional SCICA and hardware analysis has also cross-verified the low complexity nature of the proposed methodology.

Body Area Sensing Networks for Remote Health Monitoring

This chapter explores the field of remote sensor systems using wearable technologies that play a significant role in monitoring activities of patients in home and community settings. The focus is on body area sensing networks incorporating the primary enabling technologies: sensors for capturing the physiological and kinematic data, and data analysis techniques for extracting the clinically relevant information. With respect to the StrokeBack project, the majority of this chapter is dedicated towards physical activity monitoring—a key component in stroke rehabilitation. In particular, the domain of upper limb rehabilitation is examined since reduction of upper limb motor function is a common effect of stroke and significantly impairs the performance of patients as they engage in activities of daily life. As an example, a case study is presented where different arm movements are recognized in real time using data from inertial sensors attached to the arm. Tracking the occurrences of specific arm movements (e.g. prescribed exercises) over time can give an indication of rehabilitation progress since the frequency of these movements is expected to increase as motor functionality improves.

On the sensor choice and data analysis for classification of elementary upper limb movements

In this paper we present a systematic exploration for determining the appropriate type of inertial sensor and the associated data processing techniques for classifying four fundamental movements of the upper limb. Our motivation was to explore classification techniques that are of low computational complexity enabling low power processing on body-worn sensor nodes for unhindered operation over a prolonged time. Kinematic data was collected from 18 healthy subjects, repeating 20 trials of each movement, using tri-axial accelerometers and tri-axial rate gyroscopes located near the wrist. Ten time-domain features extracted from data from individual sensor streams, their modulus and specific fused signals, were used to train classifiers based on three learning algorithms: LDA, QDA and SVM. Each classifier was evaluated using a leave-one-subject-out strategy. Our results show that we can correctly identify the four arm movements, with sensitivities in the range of 83-96%, using data from just a tri-axial gyroscope located near the wrist, and requiring only 12 features in combination with the lower complexity LDA learning algorithm.

Inter-Cluster Thread-to-Core Mapping and DVFS on Heterogeneous Multi-Cores

Heterogeneous multi-core platforms that contain different types of cores, organized as clusters, are emerging, e.g., ARM’s big.LITTLE architecture. These platforms often need to deal with multiple applications, having different performance requirements, executing concurrently. This leads to the generation of varying and mixed workloads (e.g., compute and memory intensive) due to resource sharing. Run-time management is required for adapting to such performance requirements and workload variabilities and to achieve energy efficiency. Moreover, the management becomes challenging when the applications are multi-threaded and the heterogeneity needs to be exploited. The existing run-time management approaches do not efficiently exploit cores situated in different clusters simultaneously (referred to as inter-cluster exploitation) and DVFS potential of cores, which is the aim of this paper. Such exploitation might help to satisfy the performance requirement while achieving energy savings at the same time. Therefore, in this paper, we propose a run-time management approach that first selects thread-to-core mapping based on the performance requirements and resource availability. Then, it applies online adaptation by adjusting the voltage-frequency (V-f) levels to achieve energy optimization, without trading-off application performance. For thread-to-core mapping, offline profiled results are used, which contain performance and energy characteristics of applications when executed on the heterogeneous platform by using different types of cores in various possible combinations. For an application, thread-to-core mapping process defines the number of used cores and their type, which are situated in different clusters. The online adaptation process classifies the inherent workload characteristics of concurrently executing applications, incurring a lower overhead than existing learning-based approaches as demonstrated in this paper. The classification of workload is performed using the metric Memory Reads Per Instruction (MRPI). The adaptation process pro-actively selects an appropriate V-f pair for a predicted workload. Subsequently, it monitors the workload prediction error and performance loss, quantified by instructions per second (IPS), and adjusts the chosen V-f to compensate. We validate the proposed run-time management approach on a hardware platform, the Odroid-XU3, with various combinations of multi-threaded applications from PARSEC and SPLASH benchmarks. Results show an average improvement in energy efficiency up to 33 percent compared to existing approaches while meeting the performance requirements.