Low Complex CORDIC-based Hand Movement Recognition Design Methodology for Rehabilitation and Prosthetic Applications.

Hand movement recognition using Electromyography (EMG) signals have gained much significance lately and is extensively used for rehabilitation and prosthetic applications including stroke-driven disability and other neuromuscular disorders. Herein, quantitative analysis of EMG signals is very crucial. However, such applications are constrained by power consumption limitations due to the battery backup necessitating low-complex system design and the on-chip area requirement. Existing hand movement recognition methodologies using single-channel EMG signal involve computationally intensive stages, including Ensemble Empirical Mode Decomposition (EEMD), Fast Independent Component Analysis (FastICA), feature extraction, and Linear Discriminant Analysis (LDA) classification, which can not be mapped onto the low-complex architecture directly from the algorithmic level. The high computational complexity of LDA classification makes it difficult to be used for low-complex applications. In this paper, we introduce a low-complex CORDIC-based hand movement recognition design methodology targeting resource-constrained rehabilitation applications. This work explores replacing LDA classification with K-Means clustering due to its reduced complexity and efficient clustering algorithm. CORDIC-based K-Means clustering is used to further reduce the overall computational complexity of the system. The proposed low complex, K-Means clustering-based hand movement recognition for classifying seven hand movements using single-channel EMG data is found to be 99.77 % less complex and 1.28% more accurate than the conventional LDA-based classification.

Skyrmion based 3D low complex runtime reconfigurable architecture design methodology of universal logic gate.

In this study, we introduce the area efficient low complex runtime reconfigurable architecture design methodology based on Skyrmion logic for universal logic gate (ULG) i.e. NOR/NAND implementation using micromagnetic simulations. We have modelled the two input 3D device structure using bilayer ferromagnet/heavy metal where the magnetic tunnel junctions inject and detect the input and output skyrmions by exploiting the input reversal mechanism. The implementation of NOR and NAND is performed using this same device where it is reconfigured runtime with enhanced tunability by the ON and OFF state of current passing through a non magnetic metallic gate respectively. This gate acts as a barrier for skyrmion motion (additional control mechanism) to realize the required Skyrmion logic output states. To the best of authors's knowledge the boolean optimizations and the mapping logic have been presented for the first time to demonstrate the functionalities of the NOR/NAND implementation. This proposed architecture design methodology of ULG leads to reduced device footprint with regard to the number of thin film structures proposed, low complexity in terms of fabrication and also providing runtime reconfigurability to reduce the number of physical designs to achieve all truth table entries (∼75% device footprint reduction). The proposed 3D ULG architecture design benefits from the miniaturization resulting in opening up a new perspective for magneto-logic devices.

Hardware-Algorithm Codesign for Fast and Energy Efficient Approximate String Matching on FPGA for Computational Biology.

Myers bit-vector algorithm for approximate string matching (ASM) is a dynamic programming based approach that takes advantage of bit-parallel operations. It is one of the fastest algorithms to find the edit distance between two strings. In computational biology, ASM is used at various stages of the computational pipeline, including proteomics and genomics. The computationally intensive nature of the underlying algorithms for ASM operating on the large volume of data necessitates the acceleration of these algorithms. In this paper, we propose a novel ASM architecture based on Myers bit-vector algorithm for parallel searching of multiple query patterns in the biological databases. The proposed parallel architecture uses multiple processing engines and hardware/software codesign for an accelerated and energy-efficient design of ASM algorithm on hardware. In comparison with related literature, the proposed design achieves 22× better performance with a demonstrative energy efficiency of  âˆ¼ 500×109 cell updates per joule.

Personalized subcutaneous implantable cardioverter-defibrillator sensing vectors generated by mathematical rotation increase device eligibility whilst preserving device performance.

AIMS: Approximately 5.7% of potential subcutaneous implantable cardioverter-defibrillator (S-ICD) recipients are ineligible by virtue of their vector morphology, with higher rates of ineligibility observed in some at-risk groups. Mathematical vector rotation is a novel technique that can generate a personalized sensing vector, one with maximal R:T ratio, using electrocardiogram (ECG) signal recorded from the present S-ICD location. METHODS AND RESULTS: A cohort of S-ICD ineligible patients were identified through ECG screening of ICD patients with no ventricular pacing requirement and their personalized vectors were generated using ECG signal from a Holter monitor. Subcutaneous ICD eligibility in this cohort was then recalculated. In a separate cohort, episodes of arrhythmia were recorded in patients undergoing arrhythmia induction, and arrhythmia detection in standard S-ICD vectors was compared to rotated vectors using an S-ICD simulator. Ninety-two participants (mean age 64.9 ± 2.7 years) underwent screening and 5.4% were found to be S-ICD ineligible. Personalized vector generation increased the R:T ratio in these vectors from 2.21 to 7.21 (4.54-9.88, P < 0.001) increasing the cohort eligibility from 94.6% to 100%. Rotated S-ICD vectors also showed high ventricular fibrillation (VF) detection sensitivity (97.8%), low time to VF detection (6.1 s), and excellent tachycardia discrimination (sensitivity 96%, specificity 88%), with no significant differences between rotated and standard vectors. CONCLUSION: In S-ICD ineligible patients, mathematical vector rotation can generate a personalized vector that is associated with a significant increase in R:T ratio, resulting in universal device eligibility in our cohort. Ventricular fibrillation detection efficacy, time to VF detection, and tachycardia discrimination were not affected by vector rotation.

An FPGA Based Energy-Efficient Read Mapper With Parallel Filtering and In-Situ Verification.

In the assembly pipeline of Whole Genome Sequencing (WGS), read mapping is a widely used method to re-assemble the genome. It employs approximate string matching and dynamic programming-based algorithms on a large volume of data and associated structures, making it a computationally intensive process. Currently, the state-of-the-art data centers for genome sequencing incur substantial setup and energy costs for maintaining hardware, data storage and cooling systems. To enable low-cost genomics, we propose an energy-efficient architectural methodology for read mapping using a single system-on-chip (SoC) platform. The proposed methodology is based on the q-gram lemma and designed using a novel architecture for filtering and verification. The filtering algorithm is designed using a parallel sorted q-gram lemma based method for the first time, and it is complemented by an in-situ verification routine using parallel Myers bit-vector algorithm. We have implemented our design on the Zynq Ultrascale+ XCZU9EG MPSoC platform. It is then extensively validated using real genomic data to demonstrate up to 7.8× energy reduction and up to 13.3× less resource utilization when compared with the state-of-the-art software and hardware approaches.

Interlayer exchange couple based reliable and robust 3-input adder design methodology.

In this paper, a novel inter-layer exchange coupled (IEC) based 3-input full adder design methodology is proposed and subsequently the architecture has been implemented on the widely accepted micromagnetic OOMMF platform. The impact of temperature on the IEC coupled full-adder design has been analyzed up to Curie temperature. It was observed that even up to Curie temperature the IEC based adder design was able to operate at sub-50 nm as contrast to dipole coupled adder design which failed at 5 K for sub 50 nm. Simulation results obtained from OOMMF micromagnetic simulator shows, the IEC based adder design was at a lower energy state as compared to the dipole coupled adder indicating a more stable system and as the temperature of the design was increased, the total energy increased resulting in reduced stability. Potential explanation for the thermodynamic stability of IEC model lies in its energetically favored architecture, such that the total energy was lower than its dipole coupled counterparts. IEC architecture demonstrates supremacy in reliability and strength enabling NML to march towards beyond CMOS devices.

Deep neural network for automated simultaneous intervertebral disc (IVDs) identification and segmentation of multi-modal MR images.

BACKGROUND AND OBJECTIVE: Lower back pain in humans has become a major risk. Classical approaches follow a non-invasive imaging technique for the assessment of spinal intervertebral disc (IVDs) abnormalities, where identification and segmentation of discs are done separately, making it a time-consuming phenomenon. This necessitates designing a robust automated and simultaneous IVDs identification and segmentation of multi-modality MRI images. METHODS: We introduced a novel deep neural network architecture coined as 'RIMNet', a Region-to-Image Matching Network model, capable of performing an automated and simultaneous IVDs identification and segmentation of MRI images. The multi-modal input data is being fed to the network with a dropout strategy, by randomly disabling modalities in mini-batches. The performance accuracy as a function of the testing dataset was determined. The execution of the deep neural network model was evaluated by computing the IVDs Identification Accuracy, Dice coefficient, MDOC, Average Symmetric Surface Distance, Jaccard Coefficient, Hausdorff Distance and F1 Score. RESULTS: Proposed model has attained 94% identification accuracy, dice coefficient value of 91.7±1% in segmentation and MDOC 90.2±1%. Our model also achieved 0.87±0.02 for Jaccard Coefficient, 0.54±0.04 for ASD and 0.62±0.02 mm Hausdorff Distance. The results have been validated and compared with other methodologies on dataset of MICCAI IVD 2018 challenge. CONCLUSIONS: Our proposed deep-learning methodology is capable of performing simultaneous identification and segmentation on IVDs MRI images of the human spine with high accuracy.

CORAL: Verification-Aware OpenCL Based Read Mapper for Heterogeneous Systems.

Genomics has the potential to transform medicine from reactive to a personalized, predictive, preventive, and participatory (P4) form. Being a Big Data application with continuously increasing rate of data production, the computational costs of genomics have become a daunting challenge. Most modern computing systems are heterogeneous consisting of various combinations of computing resources, such as CPUs, GPUs, and FPGAs. They require platform-specific software and languages to program making their simultaneous operation challenging. Existing read mappers and analysis tools in the whole genome sequencing (WGS) pipeline do not scale for such heterogeneity. Additionally, the computational cost of mapping reads is high due to expensive dynamic programming based verification, where optimized implementations are already available. Thus, improvement in filtration techniques is needed to reduce verification overhead. To address the aforementioned limitations with regards to the mapping element of the WGS pipeline, we propose a Cross-platfOrm Read mApper using opencL (CORAL). CORAL is capable of executing on heterogeneous devices/platforms, simultaneously. It can reduce computational time by suitably distributing the workload without any additional programming effort. We showcase this on a quadcore Intel CPU along with two Nvidia GTX 590 GPUs, distributing the workload judiciously to achieve up to 2× speedup compared to when, only, the CPUs are used. To reduce the verification overhead, CORAL dynamically adapts k-mer length during filtration. We demonstrate competitive timings in comparison with other mappers using real and simulated reads. CORAL is available at: https://github.com/nclaes/CORAL.

A novel and reliable interlayer exchange coupled nanomagnetic universal logic gate design.

In this paper, we propose an interlayer exchange coupling (IEC) based 3D universal NAND/NOR gate design methodology for the reliable and robust implementation of nanomagnetic logic design as compared to the state-of-the art architectures. Owing to stronger coupling scheme as compared to the conventional dipole coupling, the random flip of the states of the nanomagnets (i.e. the soft error) is reduced resulting in greater scalability and better data retention at the deep sub-micron level. Results obtained from Object Oriented Micromagnetic Framework micromagnetic simulation show even at a Curie temperature of the nanomagnets coupled through IEC, the logic function works properly as opposed to dipole coupled nanomagnets which fails at 5 K when scaled down to sub 50 nm. Contemplating the fabrication challenges, the robustness of the IEC design was studied for structural defects, positional misalignment, shape, and size variations. This proposed 3D universal gate design methodology benefits from the miniaturization of nanomagnets as well as reduces the effect of thermally induced errors resulting in opening up a new perspective for nanomagnet based design in magneto-logic devices.

Locomo-Net: A Low -Complex Deep Learning Framework for sEMG-Based Hand Movement Recognition for Prosthetic Control.

Background: The enhancement in the performance of the myoelectric pattern recognition techniques based on deep learning algorithm possess computationally expensive and exhibit extensive memory behavior. Therefore, in this paper we report a deep learning framework named 'Low-Complex Movement recognition-Net' (LoCoMo-Net) built with convolution neural network (CNN) for recognition of wrist and finger flexion movements; grasping and functional movements; and force pattern from single channel surface electromyography (sEMG) recording. The network consists of a two-stage pipeline: 1) input data compression; 2) data-driven weight sharing. Methods: The proposed framework was validated on two different datasets- our own dataset (DS1) and publicly available NinaPro dataset (DS2) for 16 movements and 50 movements respectively. Further, we have prototyped the proposed LoCoMo-Net on Virtex-7 Xilinx field-programmable gate array (FPGA) platform and validated for 15 movements from DS1 to demonstrate its feasibility for real-time execution. Results: The effectiveness of the proposed LoCoMo-Net was verified by a comparative analysis against the benchmarked models using the same datasets wherein our proposed model outperformed Twin- Support Vector Machine (SVM) and existing CNN based model by an average classification accuracy of 8.5 % and 16.0 % respectively. In addition, hardware complexity analysis is done to reveal the advantages of the two-stage pipeline where approximately 27 %, 49 %, 50 %, 23 %, and 43 % savings achieved in lookup tables (LUT's), registers, memory, power consumption and computational time respectively. Conclusion: The clinical significance of such sEMG based accurate and low-complex movement recognition system can be favorable for the potential improvement in quality of life of an amputated persons.

Temperature and Size Effect on the Electrical Properties of Monolayer Graphene based Interconnects for Next Generation MQCA based Nanoelectronics.

Graphene interconnects have been projected to out-perform Copper interconnects in the next generation Magnetic Quantum-dot Cellular Automata (MQCA) based nano-electronic applications. In this paper a simple two-step lithography process for patterning CVD monolayer graphene on SiO2/Si substrate has been used that resulted in the current density of one order higher magnitude as compared to the state-of-the-art graphene-based interconnects. Electrical performances of the fabricated graphene interconnects were evaluated, and the impact of temperature and size on the current density and reliability was investigated. The maximum current density of 1.18 ×108 A/cm2 was observed for 0.3 µm graphene interconnect on SiO2/Si substrate, which is about two orders and one order higher than that of conventionally used copper interconnects and CVD grown graphene respectively, thus demonstrating huge potential in outperforming copper wires for on-chip clocking. The drop in current at 473 K as compared to room temperature was found to be nearly 30%, indicating a positive temperature coefficient of resistivity (TCR). TCR for all cases were studied and it was found that with decrease in width, the sensitivity of temperature also reduces. The effect of resistivity on the breakdown current density was analysed on the experimental data using Matlab and found to follow the power-law equations. The breakdown current density was found to have a reciprocal relationship to graphene interconnect resistivity suggesting Joule heating as the likely mechanism of breakdown.

MyoNet: A Transfer-Learning-Based LRCN for Lower Limb Movement Recognition and Knee Joint Angle Prediction for Remote Monitoring of Rehabilitation Progress From sEMG.

The clinical assessment technology such as remote monitoring of rehabilitation progress for lower limb related ailments rely on the automatic evaluation of movement performed along with an estimation of joint angle information. In this paper, we introduce a transfer-learning based Long-term Recurrent Convolution Network (LRCN) named as 'MyoNet' for the classification of lower limb movements, along with the prediction of the corresponding knee joint angle. The model consists of three blocks- (i) feature extractor block, (ii) joint angle prediction block, and (iii) movement classification block. Initially, the model is end-to-end trained for knee joint angle prediction followed by transferring the knowledge of a trained model to the movement classification through transfer-learning approach making a memory and computationally efficient design. The proposed MyoNet was evaluated on publicly available University of California (UC) Irvine machine learning repository dataset of the lower limb for 11 healthy subjects and 11 subjects with knee pathology for three movements type-walking, standing with knee flexion movements and sitting with knee extension movements. The average mean absolute error (MAE) resulted in the prediction of joint angle for healthy subjects and subjects with knee pathology are 8.1 % and 9.2 % respectively. Subsequently, an average classification accuracy of 98.1 % and 92.4 % were achieved for healthy subjects and subjects with knee pathology, respectively. Interestingly, the significance of this study in itself is promising with substantial improvement in the performance compared to state-of-the-art methodologies. The clinical significance of such surface electromyography signals (sEMG) based movement recognition and prediction of corresponding joint angle system could be beneficial for remote monitoring of rehabilitation progress by the physiotherapist using wearables.

Nanomagnetic logic based runtime Reconfigurable area efficient and high speed adder design methodology.

In this study, we present a runtime reconfigurable nanomagnetic (RRN) adder design offering significant area efficiency and high speed operations. Subsequently, it is implemented using a micromagnetic simulation tool, by exploiting the reversal magnetization and energy minimization nature of the nanomagnets. We compute the carry and sum of the 1-bit full adder using only two majority gates comprising a total of 7 nanomagnets and single design layout. Consequently, the on-chip clocking schematic for the proposed RRN adder implementation for both horizontal and vertical layouts are introduced. The quantitative analysis of the required resources for higher bit adder architecture using the proposed design is performed and compared with state-of-the art. The proposed design methodology leads to ∼86%, ∼83% and ∼93% reduction in the number of nanomagnets, majority gates and clock cycles respectively resulting in an area efficient and high speed RRN adder architecture.

Dipole coupled magnetic quantum-dot cellular automata-based efficient approximate nanomagnetic subtractor and adder design approach.

In this paper, we propose a dipole coupled magnetic quantum-dot cellular automata-based approximate nanomagnetic (APN) architectural design approach for subtractor and adder. In addition, we also introduce an APN architecture which offers runtime reconfigurability using a single design layout comprising only four nanomagnets. Subsequently, we propose the APN add/sub architecture by exploiting shape anisotropy and ferromagnetically coupled fixed input majority gate. The proposed APN architecture designs have been implemented using a micromagnetic simulation tool and performance has been compared with the state-of-the-art approach resulting in a ∼50%-80% reduction in the number of nanomagnets and clock cycles without degradation in the accuracy leading to area and energy efficiency.

Hardware-Software Codesign Based Accelerated and Reconfigurable Methodology for String Matching in Computational Bioinformatics Applications.

Research for new technologies and methods in computational bioinformatics has resulted in many folds biological data generation. To cope with the ever increasing growth of biological data, there is a need for accelerated solutions in various domains of computational bioinformatics. In these domains, string matching is a most versatile operation performed at various stages of the computational pipeline. For search patterns that are updated with time, there is a need for accelerated and reconfigurable string matching to perform faster searching in the ever-growing biological databases. In this paper, we have proposed an accelerated and real-time reconfigurable methodology for string matching using hardware-software codesign. Using state of the art field programmable gate arrays, we have proposed a complete system-on-chip solution for applications that require accelerated as well as real-time reconfigurable string matching. The proposed methodology is the first of its kind novel approach for high-speed string matching that also supports quick reconfiguration by patterns changing with time. It is verified at the string matching stage of protein identification. Experimental results show that the architectures designed using our proposed methodology are 4X faster than state-of-the-art software implementation running on a workstation and 1.5X-4X faster than hardware accelerators available in the literature.

Phase Space Reconstruction Based CVD Classifier Using Localized Features.

This paper proposes a generalized Phase Space Reconstruction (PSR) based Cardiovascular Diseases (CVD) classification methodology by exploiting the localized features of the ECG. The proposed methodology first extracts the ECG localized features including PR interval, QRS complex, and QT interval from the continuous ECG waveform using features extraction logic, then the PSR technique is applied to get the phase portraits of all the localized features. Based on the cleanliness and contour of the phase portraits CVD classification will be done. This is first of its kind approach where the localized features of ECG are being taken into considerations unlike the state-of-art approaches, where the entire ECG beats have been considered. The proposed methodology is generic and can be extended to most of the CVD cases. It is verified on the PTBDB and IAFDB databases by taking the CVD including Atrial Fibrillation, Myocardial Infarction, Bundle Branch Block, Cardiomyopathy, Dysrhythmia, and Hypertrophy. The methodology has been tested on 65 patients' data for the classification of abnormalities in PR interval, QRS complex, and QT interval. Based on the obtained statistical results, to detect the abnormality in PR interval, QRS complex and QT interval the Coefficient Variation (CV) should be greater than or equal to 0.1012, 0.083, 0.082 respectively with individual accuracy levels of 95.3%, 96.9%, and 98.5% respectively. To justify the clinical significance of the proposed methodology, the Confidence Interval (CI), the p-value using ANOVA have been computed. The p-value obtained is less than 0.05, and greater F-statistic values reveal the robust classification of CVD using localized features.

Nanomagnetic logic design approach for area and speed efficient adder using ferromagnetically coupled fixed input majority gate.

In this letter, we introduce the magnetic quantum-dot cellular automata (MQCA) based area and speed efficient design approach for nanomagnetic full adder implementation. We exploited the physical properties of three input MQCA majority gate (MG), where the fixed input of the MG is coupled ferromagnetically to one of the primary input operands. Subsequently we propose a design methodology, mapping logic and micromagnetic software implementation, validation of the binary full adder architecture built using two-three inputs MQCA MGs. In addition, we also analyzed our proposed design for switching errors to ensure bit stability and reliability. Our proposed design leads to ∼36%-69% reduction in the number of nanomagnets, ∼50%-75% reduction in the number of clock cycles and ∼33%-50% reduction in the number of MG operations required for the binary full adder implementation compared to the state of art designs.

Rehab-Net: Deep Learning Framework for Arm Movement Classification Using Wearable Sensors for Stroke Rehabilitation.

In this paper, we present a deep learning framework "Rehab-Net" for effectively classifying three upper limb movements of the human arm, involving extension, flexion, and rotation of the forearm, which, over the time, could provide a measure of rehabilitation progress. The proposed framework, Rehab-Net is formulated with a personalized, light weight and low-complex, customized convolutional neural network (CNN) model, using two-layers of CNN, interleaved with pooling layers, followed by a fully connected layer that classifies the three movements from tri-axial acceleration input data collected from the wrist. The proposed Rehab-Net framework was validated on sensor data collected in two situations: 1) semi-naturalistic environment involving an archetypal activity of "making-tea" with four stroke survivors and 2) natural environment, where ten stroke survivors were free to perform any desired arm movement for the duration of 120 min. We achieved an overall accuracy of 97.89% on semi-naturalistic data and 88.87% on naturalistic data which exceeded state-of-the-art learning algorithms namely, linear discriminant analysis, support vector machines, and k-means clustering with an average accuracy of 48.89%, 44.14%, and 27.64%. Subsequently, a computational complexity analysis of the proposed model has been discussed with an eye toward hardware implementation. The clinical significance of this study is to accurately monitor the clinical progress of the rehabilitated subjects under the ambulatory settings.

CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment.

Advancements in wireless sensor network technologies have enabled the proliferation of miniaturized body-worn sensors, capable of long-term pervasive biomedical signal monitoring. Remote cardiovascular monitoring has been one of the beneficiaries of this development, resulting in non-invasive, photoplethysmography (PPG) sensors being used in ambulatory settings. Wrist-worn PPG, although a popular alternative to electrocardiogram, suffers from motion artifacts inherent in daily life. Hence, in this paper, we present a novel deep learning framework (CorNET) to efficiently estimate heart rate (HR) information and perform biometric identification (BId) using only a wrist-worn, single-channel PPG signal collected in ambulant environment. We have formulated a completely personalized data-driven approach, using a four-layer deep neural network. Two convolution neural network layers are used in conjunction with two long short-term memory layers, followed by a dense output layer for modeling the temporal sequence inherent within the pulsatile signal representative of cardiac activity. The final dense layer is customized with respect to the application, functioning as: regression layer-having a single neuron to predict HR; classification layer-two neurons that identify a subject among a group. The proposed network was evaluated on the TROIKA dataset having 22 PPG records collected during various physical activities. We achieve a mean absolute error of 1.47 ± 3.37 beats per minute for HR estimation and an average accuracy of 96% for BId on 20 subjects. CorNET was further evaluated successfully in an ambulant use-case scenario with custom sensors for two subjects.

Tunable intrinsic magnetic phase transition in pristine single-layer graphene nanoribbons.

In this paper, we report on the interesting phenomenon of magnetic phase transitions (MPTs) observed under the combined influence of an electric field (E) and temperature (T) leading to a thermo-electromagnetic effect on the pristine single-layer zigzag graphene nanoribbon (szGNR). Density functional theory-based first principles calculations have been deployed for this study on the intrinsic magnetic properties of graphene. Interestingly, by tuning electric field (E) and temperature (T), three distinct magnetic phase behaviors, para-, ferro- and antiferromagnetic are exhibited in pristine szGNR. We have investigated the unrivaled positional parameters of these MPTs. MPT occurring in the system also follows a positional trend and the change in these positional parameters with regard to the size of the szGNR along with the varied E and T is studied. We propose a bow-tie schematic to induce the intrinsic magnetism in graphene and present the envisaged model of the processor application with the reported intrinsic MPT in szGNR. This fundamental insight into the intrinsic MPTs in graphene is an essential step towards developing graphene-based spin-transfer torque magnetoresistive random access memory, quantum computing devices, magnonics and spintronic memory application.