MOTIVATION: Gene expression plays a crucial role in cell function, and enhancers can regulate gene expression precisely. Therefore, accurate prediction of enhancers is particularly critical. However, existing prediction methods have low accuracy or rely on fixed multiple epigenetic signals, which may not always be available. RESULTS: We propose a two-stage framework that accurately predicts enhancers by flexibly combining multiple epigenetic signals. In the first stage, we designed a Blending-KAN model, which integrates the results of various base classifiers and employs Kolmogorov-Arnold Networks (KAN) as a meta-classifier to predict enhancers based on flexible combinations of multiple epigenetic signals. In the second stage, we developed a Stacking-Auto model, which extracted sequence features using DNABERT-2 and located the enhancers based on the Stacking strategy and AutoGluon framework. The accuracy of the Blending-KAN model reached 99.69 ± 0.11% when five epigenetic signals were used. In cross-cell line prediction, the accuracy was more significant than or equal to 93.72%. With Gaussian noise, it still maintains an accuracy of 98.74 ± 0.03%. In the second stage, the accuracy of the Stacking-Auto model is 80.50%, which is better than the existing 17 methods. The results show that our models can be flexibly used to predict and locate enhancers utilizing a combination of multiple epigenetic signals. AVAILABILITY AND IMPLEMENTATION: The source code is available at https://github.com/emanlee/Hi-Enhancer and https://doi.org/10.6084/m9.figshare.29262158.v1.

Automated surgical workflow recognition is a key enabler for context-aware computer-assisted surgery. Due to the scarcity of labeled surgical videos, training models from scratch or fully fine-tuning large vision architectures is often resourceintensive and can lead to overfitting. To alleviate this bottleneck, we insert a lightweight spatiotemporal adapter module into an image-pretrained backbone to inject temporal reasoning capability into the backbone and fine-tune the entire network. This not only preserves the backbone's original strong spatial representation capability, but also enables the model to learn such issues as the characteristic long-range temporal dependencies in surgical scenarios and the fine-grained interactions between instruments and organs, thereby achieving robust transfer to surgical video understanding tasks. Specifically, we propose a parameter-efficient Gated Dual-Path Spatiotemporal Adapter (GDPA) for surgical workflow recognition. GDPA is a lightweight module inserted into a frozen image-pretrained backbone to enable parallel spatial and temporal modeling. Within each GDPA block, the spatial and temporal branches operate in parallel, and their outputs are fused by an adaptive gating mechanism. This gating mechanism adaptively allocates the contributions of the two branches according to phase-dependent requirements for fine-grained spatial semantics and long-range temporal cues. Compared with previous methods, GDPA requires only a small number of trainable parameters and low computational cost. By retaining the backbone's pretrained visual knowledge and training only lightweight adapters in an end-to-end manner, it achieves higher accuracy even in data-limited scenarios. We evaluate our method on the Cholec80 and AutoLaparo surgical video benchmarks. The results show that even with a parameter budget far below that of full fine-tuning, GDPA still achieves competitive or even superior performance.

Graph based models have significantly advanced skeleton-based action recognition, yet most methods rely on pairwise connections and struggle to capture higher order, rhythm consistent dependencies. We introduce the Spectral Adaptive Hypergraph Convolution Network (SA-HyperGCN), which constructs hyperedges in the frequency domain to model coordinated multi joint relations. By transforming joint trajectories into spectral representations and adaptively grouping joints via low-frequency similarity, SA-HyperGCN discovers actiondriven structures beyond spatial adjacency. The resulting spectral hypergraph is fused with the static skeleton topology through multi-head hypergraph convolution for expressive message passing. We further incorporate virtual joints into the hypergraph and apply a topology-aware regularization that discourages overly similar geometric configurations. This constraint helps maintain diversity among the learned virtual joint structures and stabilizes training. Extensive experiments on NTU RGB+D 60, NTU RGB+D 120 and NW-UCLA show that SA-HyperGCN consistently outperforms strong GCN and hypergraph baselines, validating the effectiveness of spectral modeling and topologyguided regularization.

Robot-assisted catheterization has garnered a good attention for its potentials in treating cardiovascular diseases. However, advancing surgeon-robot collaboration still requires further research, particularly on task-specific automation. For instance, automated tool segmentation can assist surgeons in visualizing and tracking endovascular tools during procedures. While learning-based models have demonstrated state-of-the-art segmentation performances, generating ground-truth labels for fully-supervised methods is laborintensive, time consuming, and costly. In this study, we developed a weakly-supervised learning method that is based on multi-lateral pseudo labeling for tool segmentation in cardiovascular angiogram datasets. The method utilizes a modified U-Net architecture featuring one encoder and multiple laterally branched decoders. The decoders generate diverse pseudo labels under different perturbations to augment the available partial annotation for model training. A mixed loss function with shared consistency was adapted for this purpose. The weakly-supervised model was trained end-to-end and validated using partially annotated angiogram data from three cardiovascular catheterization procedures. Validation results show that the weakly-supervised model could perform closer to fully-supervised models. Furthermore, the proposed multi-lateral approach outperforms three well known weakly-supervised learning methods, offering the highest segmentation performance across the three angiogram datasets. Numerous ablation studies confirmed the model's consistent performance under different settings. Finally, the model was applied for tool segmentation in a robot-assisted catheterization experiments. The model enhanced visualization with high connectivity indices for guidewire and catheter, and a mean segmentation time of 35.26±11.29 ms per frame. This study provides a fast, stable, and less expensive method for segmentation and visualization of endovascular tools in robot-assisted cardiac catheterization.

Learning-based Image Quality Assessment (IQA) models have obtained impressive performance with the help of reliable subjective quality labels, where Mean Opinion Score (MOS) is the most popular choice. However, in view of the subjective bias of individual annotators, the Labor-Abundant MOS (LA-MOS) typically requires large collections of opinion scores from multiple annotators for each image, which significantly increases the learning cost. In this paper, we aim to learn robust IQA models from Low-Cost MOS (LC-MOS), which only requires very few opinion scores or even a single opinion score for each image. More specifically, we consider the LC-MOS as the noisy observation of LA-MOS and enforce the IQA model learned from LC-MOS to approach the unbiased estimation of LA-MOS. Thus, we represent the subjective bias between LC-MOS and LA-MOS, and the model bias between IQA predictions learned from LC-MOS and LA-MOS (i.e., dual-bias) as two latent variables with unknown parameters. By means of the expectation-maximization-based alternating optimization, we can jointly estimate the parameters of the dual-bias, which suppresses the misleading of LC-MOS via a gated dual-bias calibration (GDBC) module. To the best of our knowledge, this is the first exploration of robust IQA model learning from noisy low-cost labels. Theoretical analysis and extensive experiments on four popular IQA datasets show that the proposed method is robust toward different bias rates and annotation numbers and significantly outperforms the other Learning-based IQA models when only LC-MOS is available. Furthermore, we also achieve comparable performance with respect to the other models learned with LA-MOS.

Human activity recognition is closely related to human health and is a hot research topic. With the continuous development of AI technology, large models have shown great potential in various training tasks. However, there is limited analysis of human sensor motion data. In this study, we fine-tuned large models on five motion datasets, designed an adaptation layer suitable for time series data to extract action representations fully, and proposed a novel HAR framework. We conducted action recognition experiments on five foundation models and compared them with ten classical algorithm models. The experimental results show that the accuracy of action recognition in small-parameter pre-trained large models can reach 98.8%, indicating significant research potential.

Robot-assisted catheterization offers a promising technique for cardiovascular interventions, addressing the limitations of manual interventional surgery, where precise tool manipulation is critical. In remote-control robotic systems, the lack of force feedback and imprecise navigation challenge cooperation between the surgeon and robot. This study proposes a manipulation-based evaluation framework to assess the cooperative performance between different operators and robot using kinesthetic, kinematic, and haptic data from multi-sensor technologies. The proposed evaluation framework achieves a recognition accuracy of 99.99% in assessing the cooperation between operator and robot. Additionally, the study investigates the impact of delay factors, considering no delay, constant delay, and variable delay, on cooperation characteristics. The findings suggest that variable delay contributes to improved cooperation performance between operator and robot in a primary-secondary isomorphic robotic system, compared to a constant delay factor. Furthermore, operators with experience in manual percutaneous coronary interventions exhibit significantly better cooperative manipulate on with the robot system than those without such experience, with respective synergy ratios of 89.66%, 90.28%, and 91.12% based on the three aspects of delay consideration. Moreover, the study explores interaction information, including distal force of tools-tissue and contact force of hand-control-ring, to understand how operators with different technical skills adjust their control strategy to prevent damage to the vascular vessel caused by excessive force while ensuring enough tension to navigate complex paths. The findings highlight the potential of variable delay to enhance cooperative control strategies in robotic catheterization systems, providing a basis for optimizing surgeon-robot collaboration in cardiovascular interventions.

change of blood glucose (BG) level stimulates the autonomic nervous system leading to variation in both human's electrocardiogram (ECG) and photoplethysmogram (PPG). In this article, we aimed to construct a novel multimodal framework based on ECG and PPG signal fusion to establish a universal BG monitoring model. This is proposed as a spatiotemporal decision fusion strategy that uses weight-based Choquet integral for BG monitoring. Specifically, the multimodal framework performs three-level fusion. First, ECG and PPG signals are collected and coupled into different pools. Second, the temporal statistical features and spatial morphological features in the ECG and PPG signals are extracted through numerical analysis and residual networks, respectively. Furthermore, the suitable temporal statistical features are determined with three feature selection techniques, and the spatial morphological features are compressed by deep neural networks (DNNs). Lastly, weight-based Choquet integral multimodel fusion is integrated for coupling different BG monitoring algorithms based on the temporal statistical features and spatial morphological features. To verify the feasibility of the model, a total of 103 days of ECG and PPG signals encompassing 21 participants were collected in this article. The BG levels of participants ranged between 2.2 and 21.8 mmol/L. The results obtained show that the proposed model has excellent BG monitoring performance with a root-mean-square error (RMSE) of 1.49 mmol/L, mean absolute relative difference (MARD) of 13.42%, and Zone A + B of 99.49% in tenfold cross-validation. Therefore, we conclude that the proposed fusion approach for BG monitoring has potentials in practical applications of diabetes management.

Hand gesture and movement analysis is a crucial learning task in Human-computer interaction (HCI) applications. Sensor-based HCI systems simultaneously capture the information with multiple locations to track the coordination of different regions of muscles. Based on the fact that there exists a temporal correlation between the regions, the connectivity analysis of sensor signals builds a network. The graph-based approach for analyzing the sensor network has provided novel insight into the learning in HCI, which has not been broadly investigated in hand gesture recognition tasks. This work proposes a topological representation learning scheme as a graph-based approach for sensor network analysis. Through investigation of the topological properties with persistent homology, the spatial-temporal characteristics are well described to build recognition models. Experiments on the NinaPro DB-2, DB-4, DB-5, and DB-7 datasets with sensor networks built with sEMG signal and IMU signal demonstrate exceptional performance of the proposed topological approach. The topological features are effective in graph representation learning with sensor networks used in hand gesture recognition. The proposed work provides a novel learning scheme in HCI systems and human-in-the-loop studies.

Human ECG sensing signals can be regarded as the observed variables of the human heart’s nonlinear dynamic system, which can effectively reflect the state changes of the heart system. They can be used for heart health monitoring and related disease identification. Due to the robust chaos, nonlinearity, and complexity of ECG signals, it is challenging to express them by standard features. Therefore, this paper proposes a nonlinear topological data analysis method to model ECG signals and extract nonlinear features for ECG anomaly detection. Firstly, we use the time delay embedding approach to map the ECG time series to the topological space for phase space reconstruction to form the ECG point cloud. Then, based on the point cloud information in space, the persistent homology method was used to construct the topological imprint of ECG data. Finally, the persistence landscape in the topological impression was extracted as the topological feature of the ECG signal for ECG anomaly detection. With only 20% of the total training dataset, it achieves a 100% accuracy for normal heartbeats, 98.75% for ventricular beats, 95.88% for supra-ventricular moments, and 91.97% for fusion beats. Thus the method can be trained for a single individual, allowing for personalized analysis systems. With the present study, TDA could be a valuable tool for biomedical signal analysis, with potential application in customized data processing.

Robot-assisted intravascular interventions have evolved as unique treatments approach for cardiovascular diseases. However, the technology currently has low potentials for catheterization skill evaluation, slow learning curve, and inability to transfer experience gained from manual interventions. This study proposes a new weighting-based deep ensemble model for recognizing interventionalists' hand motions in manual and robotic intravascular catheterization. The model has a module of neural layers for extracting features in electromyography data, and an ensemble of machine learning methods for classifying interventionalists' hand gestures as one of the six hand motions used during catheterization. A soft-weighting technique is applied to guide the contributions of each base learners. The model is validated with electromyography data recorded duringin-vitroandin-vivotrials and labeled asmany-to-onesequences. Results obtained show the proposed model could achieve 97.52% and 47.80% recognition performances on test samples in thein-vitroandin-vivodata, respectively. For the latter, transfer learning was applied to update weights from thein-vitrodata, and the retrained model was used for recognizing the hand motions in thein-vivodata. The weighting-based ensemble was evaluated against the base learners and the results obtained shows it has a more stable performance across the six hand motion classes. Also, the proposed model was compared with four existing methods used for hand motion recognition in intravascular catheterization. The results obtained show our model has the best recognition performances for both thein-vitroandin-vivocatheterization datasets. This study is developed toward increasing interventionalists' skills in robot-assisted catheterization.

This work presents a topological nonlinear analysis approach for dynamical system measurements, frequently appearing in sensor-based inference tasks in human physical activity analysis. Traditional approaches to dynamical modeling included linear and nonlinear methods with specific representational abilities and some drawbacks. A novel approach we investigate is using topological descriptors of the shape of the dynamical attractor to represent the nature of dynamics. The proposed framework has three essential advantages compared to previous approaches: 1) with nonlinear phase space reconstruction, the dynamics descriptor is derived from the observation time series without any statistical assumption; 2) with the topological data analysis technique, the phase space topological properties are described in an intrinsic multiresolution analytical way, which brings novel information compared to traditional phase-space modeling techniques; 3) with different types of measurement sensing signals, the proposed approach shows stability in activities state inference. We illustrate our idea with the physical activity recognition tasks with wearable sensors, where the topological characteristics of reconstructed phase state space show strong representational ability for activity type inference.

Recently, flexible robotic systems are developed to enhance minimally invasive interventions on internal organs located in confined areas of human body. These surgical devices are designed to navigate anatomical pathways via single-port access, such as natural orifices or minimal incisions and intraluminal interventions. With improved precision, spatial flexibility and dexterity, the robotic technology can enhance surgery such that minimally invasive flexible access would become a faster, safer, and more convenient method for intra-body interventions without multiple or wide incisions. However, a lot of works are still required for global acceptance of existing flexible robotic surgical platforms. This review provides extended insights on the design details of two types of flexible robotic systems used for endoscopic and endovascular procedures. As of today, several prototypes of both platforms have been proposed; however, their global acceptability and applicability remains very low. To address these, we present an extensive review on design constraints and control methods which are vital for safer, faster, and better operation of the flexible robotic systems in minimally invasive surgery (MIS). Finally, research trends of flexible robotic systems and their clinical application status in MIS are discussed along with some of the technical and technological challenges hindering their prominence.

The growing world population is facing challenges such as increased chronic diseases and medical expenses. Integrate the latest modern technology into healthcare system can diminish these issues. Internet of medical things (IoMT) is the vision to provide the better healthcare system. The IoMT comprises of different sensor nodes connected together. The IoMT system incorporated with medical devices (sensors) for given the healthcare facilities to the patient and physician can have capability to monitor the patients very efficiently. The main challenge for IoMT is the energy consumption, battery charge consumption and limited battery lifetime in sensor based medical devices. During charging the charges that are stored in battery and these charges are not fully utilized due to non-linearity of discharging process. The short time period needed to restore these unused charges is referred as recovery effect. An algorithm exploiting recovery effect to extend the battery lifetime that leads to low consumption of energy. This paper provides the proposed adaptive Energy efficient (EEA) algorithm that adopts this effect for enhancing energy efficiency, battery lifetime and throughput. The results have been simulated on MATLAB by considering the Li-ion battery. The proposed adaptive Energy efficient (EEA) algorithm is also compared with other state of the art existing method named, BRLE. The Proposed algorithm increased the lifetime of battery, energy consumption and provides the improved performance as compared to BRLE algorithm. It consumes low energy and supports continuous connectivity of devices without any loss/ interruptions.

Body Sensor Networks (BSNs) is the emerging driver to revolutionize the entire landscape of the medical field. However, sensor-based handheld devices suffer from high power drain and limited battery life, due to their resource-constrained nature. Hybridization of different energy control methods and protocol layers is a best approach to enhance the performance perimeters for smart and connected healthcare. Thus, this paper mainly contributes in two ways. First, adaptive duty-cycle optimization algorithm (ADO), is proposed which optimizes the active time by considering the specific power level which leads to more energy saving instead of increasing the sleep period unlike the traditional methods. Second, joint Green and sustainable healthcare framework is proposed. Extensive theoretical and experimental analysis is performed by adopting real-time data sets with Monte Carlo simulation in MATLAB, and it is revealed that proposed algorithm enhance reliability and energy saving by 24.43%, 36.54%, respectively. Thus it can be said that proposed algorithm have more potential for energy constrained sensor devices in smart and connected healthcare platform.

The convergence of artificial intelligence (AI) and the Internet of Things (IoT) promotes energy-efficient communication in smart homes. Quality-of-Service (QoS) optimization during video streaming through wireless micro medical devices (WMMDs) in smart healthcare homes is the main purpose of this research. This article contributes in four distinct ways. First, to propose a novel lazy video transmission algorithm (LVTA). Second, a novel video transmission rate control algorithm (VTRCA) is proposed. Third, a novel cloud-based video transmission framework is developed. Fourth, the relationship between buffer size and performance indicators, i.e., peak-to-mean ratio (PMR), energy (i.e., encoding and transmission), and standard deviation, is investigated while comparing LVTA, VTRCA, and baseline approaches. The experimental results demonstrate that the reduction in encoding (32% and 35.4%) and transmission (37% and 39%) energy drains, PMR (5 and 4), and standard deviation (3 and 4 dB) for VTRCA and LVTA, respectively, is greater than that obtained by baseline during video streaming through WMMD.

Machine learning (ML) techniques in association to emerging sixth generation (6G) technologies, i.e., massive Internet of Things (IoT), big data analytics have caught too much attention from academia to the business world since last few years due to their high and fast computing capabilities. The role of ML-based 6G techniques is to reshape the imaginary idea into physical world for resolving the challenging issues of energy, quality of service (QoS), and quality of experience (QoE). Besides, ML techniques with better association to 6G reshapes the industrial network in box (NIB) platform. In the mean-time rapidly increasing market of the IoT devices to deliver multimedia content has caught the attention of various fields such as, industrial, and healthcare. The challenging issue that end-users are facing is the unsatisfactory and annoyed performance of portable devices while surfing the video, and image to/from desired entity, i.e., low QoE. To resolve these issues this research first, proposes a novel ML-driven mobility management method for the efficient communication in industrial NIB applications. Second, a novel architecture of 6G-based intelligent QoE and QoS optimization in industrial NIB is proposed. Third, a 6G-based NIB framework is proposed in association to the long-term evolution. Forth, use-case for 6G-empowered industrial NIB is recommended for an energy efficient communication. Experimental results are extracted with high energy efficiency, better QoE, and QoS in 6G-based industrial NIB.

Autonomic nervous system (ANS) can maintain homeostasis through the coordination of different organs including heart. The change of blood glucose (BG) level can stimulate the ANS, which will lead to the variation of Electrocardiogram (ECG). Considering that the monitoring of different BG ranges is significant for diabetes care, in this paper, an ECG-based technique was proposed to achieve non-invasive monitoring with three BG ranges: low glucose level, moderate glucose level, and high glucose level. For this purpose, multiple experiments that included fasting tests and oral glucose tolerance tests were conducted, and the ECG signals from 21 adults were recorded continuously. Furthermore, an approach of fusing density-based spatial clustering of applications with noise and convolution neural networks (DBSCAN-CNN) was presented for ECG preprocessing of outliers and classification of BG ranges based ECG. Also, ECG's important information, which was related to different BG ranges, was graphically visualized. The result showed that the percentages of accurate classification were 87.94% in low glucose level, 69.36% in moderate glucose level, and 86.39% in high glucose level. Moreover, the visualization results revealed that the highlights of ECG for the different BG ranges were different. In addition, the sensitivity of prediabetes/diabetes screening based on ECG was up to 98.48%, and the specificity was 76.75%. Therefore, we conclude that the proposed approach for BG range monitoring and prediabetes/diabetes screening has potentials in practical applications.

Fifth generation (5G) technologies have become the center of attention in managing and monitoring high-speed transportation system effectively with the intelligent and self-adaptive sensing capabilities. Besides, the boom in portable devices has witnessed a huge breakthrough in the data driven vehicular platform. However, sensor-based Internet of Things (IoT) devices are playing the major role as edge nodes in the intelligent transportation system (ITS). Thus, due to high mobility/speed of vehicles and resource-constrained nature of edge nodes more data packets will be lost with high power drain and shorter battery life. Thus, this research significantly contributes in three ways. First, 5G-based self-adaptive green (i.e., energy efficient) algorithm is proposed. Second, a novel 5G-driven reliable algorithm is proposed. Proposed joint energy efficient and reliable approach contains four layers, i.e., application, physical, networks, and medium access control. Third, a novel joint energy efficient and reliable framework is proposed for ITS. Moreover, the energy and reliability in terms of received signal strength (RSSI) and hence packet loss ratio (PLR) optimization is performed under the constraint that all transmitted packets must utilize minimum transmission power with high reliability under particular active time slot. Experimental results reveal that the proposed approach (with Cross Layer) significantly obtains the green (55%) and reliable (41%) ITS platform unlike the Baseline (without Cross Layer) for aging society.

Application of intravascular catheterization, a vital task used in minimally invasive vascular surgery, has been hindered by lack of distal force sensor with miniaturized size and millinewton sensing capability. Thus, development of distal sensor for evaluating tool-vessel force interactions during robot-assisted intravascular interventions remains a research area in minimally invasive surgery. In this study, a millinewton force sensor is developed by integrating optical fibers with bragg grating in an isotonic 3D-printed flexure. The miniaturized sensor is calibrated in an experiment for 1D distal force sensing application in PCI procedures, and performance of the sensor is evaluated against that of direct FBG-pasting method. Results from the study shows that the designed sensor shows a higher repeatability and stability with a millinewton resolution in the flexure compartment. Thus, it can be suitably used for distal catheter-tip force sensing during intravascular catheterization.

Recently, applications of robotic device is showing greater advances in surgery. While robotic catheterization has been embraced to reduce the operational challenges (radiation and orthopedic hazards) inherent with percutaneous coronary interventions (PCIs), robot-based cardiac interventions are still limited to very few clinical centers in the world. In this paper, the development and application of a robotic PCI system for intravascular catheterization is presented. The robotic system is setup with underactuated master-and-slave devices and a direct control model designed based on mapping unit scales of the master displacement to trigger the slave robot for intravascular catheterization. To validate the robotic system, in-vitro trials are observed in a human-like silicone-based vascular pathway with aortic stenosis. The master-slave robotic system was successfully used to cannulate the stenotic vascular pathway with guidewire and catheter. Thus, it can be suitably adapted for intravascular catheterization during PCI and related cardiac interventions.

The pervasive and smart healthcare is important for elderly patients which has revolutionized the medical world and caught the attention from industry and academia with the help of portable sensor-enabled devices. Tiny size and resource-constrained nature restricts them to perform several tasks at a time. Thus, energy drain, limited battery lifetime, and high packet loss ratio (PLR) are the key challenges to be tackled carefully for ubiquitous healthcare. Energy efficiency, reliability and longer battery cycle are the vital ingredients for wearable devices to empower cost-effective and pervasive medical environment. Thus, this research work has three key contributions. First, a novel transmission power control driven energy efficient algorithm (EEA) is proposed to enhance energy, battery lifetime and reliability while monitoring the health status of elderly patients. Proposed EEA and conventional constant transmission power control (TPC) are evaluated by adopting real-time datasets of static (i.e., wheelchair sitting) and dynamic (i.e., wheelchair moving) body postures of elderly patients. Second, smart healthcare framework is proposed. Third, performance metrics such as, energy drain, battery lifetime and reliability are introduced and calculated by considering average and threshold RSSI and TPC values. Finally, it is observed through experimental analysis that the proposed EEA enhances energy efficiency with acceptable PLR than the constant TPC during data transmission.

Fourth industrial revolution ally for elderly patients. As QoS is not the appropriate entity to express the feelings and expectations of the end-users i.e., elderly patients. Therefore, the quality of experience in medical media (QoEMM) services is quite important. This research optimizes the medical media service such as, electrocardiogram (ECG) for the elderly patients by adopting wearable devices with large screen. Due to small size, and resource-constrained nature of those handheld devices it is hard to satisfy the end user's perception while monitoring the elderly emergency patients. Besides, how the elderly patient's QoE during medical media ECG data transmission can be captured, for this purpose first, framework of QoEMM is developed by adopting acquisition time. Second, the relationship between subjective test score (i.e. surveyed data) and objective performance metrics (i.e., energy consumption and entropy) with acquisition time and actual time of ECG service is established. It is revealed through extensive real-time subjective data sets in experimental setup that QoEMM is optimized through portable devices, and correlated with QoS parameters during medical media ECG service to improve the satisfaction level of end-users.

Continuous blood glucose (BG) monitoring is necessary to avoid the deadly health complications from diabetes mellitus. The conventional method of measuring and monitoring BG is by pricking the finger which causes pain and discomfort to patients. To tackle this issue, there are research focusing on physiological signals, such as an electrocardiogram (ECG) to create a model capable of continuous glucose measurement. However, there are ECG segments that have not been considered that have the possibility of improving the performance for non-invasive BG monitoring. In this paper, we perform an oral glucose tolerance test (OGTT) on thirteen adults while continuously recording the ECG signal. A control experiment was also performed without the consumption of glucose. We captured continuous ECG signals and extracted 9 ECG segments. Boxplot and correlation coefficient analysis was performed on the extracted segments to observe the changes for BG. The result reveals a consistent pattern among QT, ST, QTC segments from each participant. HR and RR-I segments have dominant inverse behavior with a 92% correlation with the QT segment. While PRQ and QRS segments can also be included due to 85% and 77% correlation respectively with QTC segments. Whereas R-H and P-H segments have weak results with most of their values below 50%.

Despite the important role played by muscle co-contraction in stabilizing and stiffening the spine during daily activities, the effects of multi-movement models on the lumbar co-contraction are yet to be explored. This study explores the co-contraction features of lumbar muscle in subjects with and without low back pain while they perform four different movements namely forward, backward, left flexion and right flexion lumbar actions. Surface electromyography (EMG) signals of three paired lumbar muscles were measured from a total number of 60 subjects while they performed specified movement models. Co-contraction ratio (CCR), defined as ratio of normalized integration of antagonist EMG activities to the total muscle activities, were accessed, and questionnaires about pain intensity were collected with visual analogue scale (VAS). The results showed that the CCR of LBP at forward (p = 0.007) and right flexion (p = 0.011) models was significantly greater than that of healthy controls, respectively. Also, CCR was significantly different among forward, backward, left flexion and right flexion models (p<;0.05). Finally, co-contraction patterns from LBP subjects reveal disordered neuromuscular control in regulating the stiffness of lumbar spine.

Freehand three-dimensional (3D) ultrasound imaging is an attractive research area because it is capable of providing large field of view and high in-plane resolution image to allow better illustration of complex anatomy structures. However, reconstructed image is corrupted with speckle noise and artifacts in the conventional reconstructed volume data. In this paper, we propose a simple but effective adaptive kernel regression method for volume reconstruction from freehand swept B-scan images. By creating a linear model for estimating the homogeneous region of the B-scan image and learning the parameters of the model with a supervised learning method, the statistical characteristic of speckle can be well recovered. With the learned linear model of speckle, we can easily estimate the homogenous region and reconstruct image with speckle reduction and edge preservation via the adaptive turning of the smoothing parameters of the kernel regression. Our algorithm lends itself to parallel processing, and yields a 288× speedup on a graphics processing unit (GPU). Experiments on the simulated data, ultrasonic abdominal phantom and in-vivo liver of human subject and comparisons with some classical and recent algorithms are used to demonstrate its improvements in both volume reconstruction accuracy and efficiency.

The purpose of this study was to explore the characteristic of trunk angle and flexibility of spine in lumbar disc herniation (LDH) patients, non-specific low back pain (LBP) patients and healthy subjects during bending exercises. 35 patients with LDH, 32 patients with non-specific LBP and 24 healthy controls participated in this experiment, volunteered to stand, then bend forward as far as possible, stay fully flexed, and return to stand with performing five cycles. As an indirect measure of spine performance, the trunk angle captured using motion sensors. We estimated the degree of spine activity by comparing the trunk angle between LDH, LBP and healthy controls in roll, pitch and yaw planes, respectively. As results, the significant differences between LDH, LBP and healthy controls in the female group of volunteers was found for trunk angle of three planes (p<; 0.05). Between female and male had differences of trunk angle in LDH, LBP and healthy controls, respectively. Combined the most frequently used visual analog scale (VAS) for the pain of clinical research to explore the characteristic of subjective response of the patient on trunk angle by objective measurement, which might be a useful tool to reflect the abnormal degree of the spine in the diagnosis of spine and rehabilitation. In summary, these results advised LDH and LBP patients to do strength training reasonably to restore lumbar muscle function and assist in stabilizing the spine.

The aim of this study was to analyse quantitatively spine angle changes of subjects suffering from low back pain (LBP) during dynamic exercises. We explored the differences in the range of spine angle based on gender, disability severity, the correlation between the spine angle range and the visual analogue scale (VAS) scores, as well as the differences in standard deviations between the healthy and LBP subjects. We recruited thirty-nine LBP subjects and thirty-seven healthy people. They were asked to perform several movements from a standing position first and then from a sitting position. The motions were forward and backward bending, left and right lateral bending, as well as left and right axial rotation, respectively. Results show that for the most movements, the means of the spine angle changes in the females were larger than those in the males. In the LBP group, we observed much smaller spine angle values than those in the healthy subjects during exercise. With the increase of VAS score, a declining trend of the spine angle change was observed. There were significant differences in the spine angle range between standing and sitting positions when performing left and right axial rotation (p=0.000, p=0.002, respectively). We observed high correlations (with a max. result of r=0.804) for most movements, executed both from a standing and sitting position. We also found a wider range of standard deviation in the LBP subjects compared to healthy subjects. These results indicate that quantitative analysis of the spine angle range could provide an objective reference of the disability level, and allow for the progress assessment during the rehabilitation of low back pain patients.

Human body communication (HBC) is a short-range, wireless communication in the vicinity of, or inside a human body. In this paper, biometric authentication based on capacitive coupled HBC is presented for the wearable devices. In-situ experiments were conducted with 20 volunteers to investigate the feasibility. The S21 parameters of the HBC channel from one palm to the other within the frequency range of 300 KHz-50 MHz were measured. A total of 2,561,600 data are acquired. The data are analyzed by the support vector machines (SVM) including C-SVM and nu-SVM, where 2,241,400 data are used to train the SVM model and 320,200 data are used to estimate the authentication rate. Linear, polynomial, and radial basis function (RBF) are adopted as the kernel functions, respectively. In addition, to verify whether the features in low frequency band will affect the performance of HBC authentication, the features in four frequency bands, i.e., from 300 KHz to 50 MHz, from 3.4 MHz to 50 MHz, from 5.6 MHz to 50 MHz, and from 9.6 MHz to 50 MHz are used as the biometric trait, respectively. The experiment results show that, in biometric identification mode, identification rate of 98% is achieved, and in biometric verification mode, the equal error rate (EER) is 0.24%, the average area under the curve (AUC) of receiver operating characteristic (ROC) reaches 0.9993.

An restricted Boltzmann machine learning algorithm were proposed in the two-lead heart beat classification problem. ECG classification is a complex pattern recognition problem. The unsupervised learning algorithm of restricted Boltzmann machine is ideal in mining the massive unlabelled ECG wave beats collected in the heart healthcare monitoring applications. A restricted Boltzmann machine (RBM) is a generative stochastic artificial neural network that can learn a probability distribution over its set of inputs. In this paper a deep belief network was constructed and the RBM based algorithm was used in the classification problem. Under the recommended twelve classes by the ANSI/AAMI EC57: 1998/(R)2008 standard as the waveform labels, the algorithm was evaluated on the two-lead ECG dataset of MIT-BIH and gets the performance with accuracy of 98.829%. The proposed algorithm performed well in the two-lead ECG classification problem, which could be generalized to multi-lead unsupervised ECG classification or detection problems.

This paper presents the design and simulation results of a silicon cochlea system that has closely similar behavior as the real cochlea. A cochlea filter-bank based on the improved three-stage filter cascade structure is used to model the frequency decomposition function of the basilar membrane; a filter tuning block is designed to model the adaptive response of the cochlea; besides, an asynchronous event-triggered spike codec is employed as the system interface with bank-end spiking neural networks. As shown in the simulation results, the system has biologically faithful frequency response, impulse response, and active adaptation behavior; also the system outputs multiple band-pass channels of spikes from which the original sound input can be recovered. The proposed silicon cochlea is feasible for analog VLSI implementation so that it not only emulates the way that sounds are preprocessed in human ears but also is able match the compact physical size of a real cochlea.

With the development of digital multimedia technologies, image matting has gained increasing interests from both academic and industrial communities. The purpose of image matting is to precisely extract the foreground objects with arbitrary shapes from an image or a video frame for further editing. It is generally known that image matting is inherently an ill-posed problem because we need to output three images out of only one input image. In this paper, we provide a comprehensive survey of the existing image matting algorithms and evaluate their performance. In addition to the blue screen matting, we systematically divide all existing natural image matting methods into four categories: 1) color sampling-based; 2) propagation-based; 3) combination of sampling-based and propagation-based; and 4) learning-based approaches. Sampling-based methods assume that the foreground and background colors of an unknown pixel can be explicitly estimated by examining nearby pixels. Propagation-based methods are instead based on the assumption that foreground and background colors are locally smooth. Learning-based methods treat the matting process as a supervised or semisupervised learning problem. Via the learning process, users can construct a linear or nonlinear model between the alpha mattes and the image colors using a training set to estimate the alpha matte of an unknown pixel without any assumption about the characteristics of the testing image. With three benchmark data sets, the various matting algorithms are evaluated and compared using several metrics to demonstrate the strengths and weaknesses of each method both quantitatively and qualitatively. Finally, we conclude this paper by outlining the research trends and suggesting a number of promising directions for future development.

Bad weather (eg., fog and haze) significantly degrades the quality of outdoor images taken by camera, leading to the fact that most automatic systems, which strongly depends on the definition of the input images, fail to work normally. Thus, the improvement of the dehazing technology is highly desired. To overcome the disadvantages of traditional dark channel priorbased algorithm, we propose a more efficient dehazing algorithm combining dark channel prior and mean shift segmentation. Firstly, we take the operation of white balance on the input haze image to reduce the negative influence of color cast. Secondly, we use the mean shift segmentation algorithm to separate the sky regions from the foreground in the transmission map, which is obtained with the dark channel prior-based approach. Thirdly, we enhance the brightness of the sky regions in the transmission map independently and use guided image filtering to smooth the map. Finally, we restore the image with the re-refined transmission map. The experimental results demonstrate that the proposed approach is better able to handle the sky regions and solve the problem of color cast compared with the typical dehazing algorithms.

As a direct determinant parameter to quantify muscle activity, the muscle thickness (MT) has been investigated in many aspects and for various purposes. Ultrasonography (US) is a promising modality to detect muscle morphological changes during contractions since it is portable, noninvasive, and real time. However, there are few reports on sensitive and efficient estimation of changes of MT in a cross-sectional plane. In this feasibility investigation, we proposed a coarse-to-fine method based on a compressive-tracking algorithm for estimation of MT changes during an example task of isometric knee extension using ultrasound images. The sensitivity and efficiency are evaluated with 1920 US images from quadriceps muscle (QM) in eight subjects. The detection results were compared with those obtained from both traditional manual measurement and the well known normalized cross-correlation method, and the effect of the size of tracking window on detection performance was evaluated as well. It is demonstrated that the proposed method agrees well with the manual measurement. Meanwhile, it is not only sensitive to relatively small changes of MT but also computationally efficient.

This paper presents first several steps towards an FPGA-based electronic system for remote pulse rate (PR) measurement. The system uses a low-cost digital camera as an image sensor, which operates at up to 30 frames per second (fps) in WXGA (1200×800 pixels) resolution. A novel algorithm for PR measurement was implemented using an FPGA development board. A commercially-available photoplethysmography module (TP-TSD200A from BIOPAC) was used as a golden standard to verify the performance of the suggested system. Ten male subjects were simultaneously examined using both the suggested system and the golden standard, and the results were compared. The proposed system leads to a potential means for providing mobile healthcare using smart phones and other mobile consumer products.

This paper proposes a fast GrowCut (FGC) algorithm and applies the new algorithm in three-dimensional (3D) kidney segmentation from computed tomography (CT) volume data. Users could mark the object of interest with different labels in CT slices. FGC propagates the labels using monotonically decreasing function and gray features to derive an optimal cut for a given data in space. The gray features play a great role in comparing with neighborhood cells. The experimental results clearly demonstrate nie superiority of FGC in accuracy and speed.

In wireless body sensor networks (WBSN) and wireless body area networks (WBAN), sensor nodes have different bandwidth requirements, therefore, heterogeneous traffic is created. In this paper, we propose a statistical medium access control (MAC) protocol with periodic synchronization for use in heterogeneous traffic networks based on human body communication (HBC). The MAC protocol is designated to ensure energy efficiency by means of flexible time slot allocation and a statistical frame. The statistical frame is intended to increase the sleep time and keep low duty cycles in each beacon period. The MAC protocol was fully implemented on our HBC platform. The experimental results proved that the proposed MAC protocol is compact and energy-efficient.

Current image matting approaches are often implemented based upon color samples under various local assumptions. In this letter, a novel image matting algorithm is investigated by treating the alpha matting as a regression problem. Specifically, we learn spatially-varying relations between pixel features and alpha values using support vector regression. Via the learning-based approach, limitations caused by local image assumptions can be greatly relieved. In addition, the computed confidence terms in learning phase can be conveniently integrated with other matting approaches for the matting accuracy improvement. Qualitative and quantitative evaluations are implemented with a public matting benchmark. And the results are compared with some recent matting algorithms to show its advantages in both efficiency and accuracy.

Muscle thickness measurement in ultrasonography was traditionally conducted by a trained operator, and the manual detecting process is time consuming and subjective. In this paper, we proposed an automatic tracking strategy to achieve the continuous and quantitative measurement for gastrocnemius muscle thickness in ultrasound images. The method involved three steps: tracking of seed points, contours extraction of aponeuroses, and muscle thickness estimation. In an ultrasound image sequence, we first selected two seed points in the first frame manually for the superficial and deep aponeuroses, respectively. Seed points in all following frames were then tracked by registering to their respective previous frames. Second, we adopted the local and global intensity fitting model to extract the contours of aponeuroses. At last, the muscle thickness was achieved by calculating the distance between the contours of superficial and deep aponeuroses. The performance of the algorithm was evaluated using 500 frames of ultrasound images. It was demonstrated in the experiments that the proposed methods could be used for objective tracking of aponeuroses and estimation of muscle thickness in musculoskeletal ultrasound images.

This paper describes a new method to implement ultra-low frequency analog filters for electrophysiological signal acquisitions. Unlike the traditional pseudo-resistor or trans conductor-capacitor architectures, the proposed continues time filters employed current steering integrators which help decrease the capacitor area and reducing the total harmonic distorting (THD) simultaneously. Three basic structures (high pass, notch and low pass filters) were designed by proposing this technique and were implemented by 0.18 μm CMOS technology. Measurement results showed that the-3 dB of the low pass and high pass filters were 220 Hz and 0.05 Hz and notch frequency center of notch filter 50 Hz. Besides, the three filters' THD were measured to be-76 dB, -76 dB and -80 dB which are the lowest values with the comparison with other state-of-the-arts.

Segmentation of video with dynamic background is an important research topic in image analysis and computer vision domains. In this paper, we present a novel recursive Bayesian learning-based method for the efficient and accurate segmentation of video with dynamic background. In the algorithm, each frame pixel is represented as the layered normal distributions which correspond to different background contents in the scene. The layers are associated with a confident term and only the layers satisfy the given confidence which will be updated via the recursive Bayesian estimation. This makes learning of background motion trajectories more accurate and efficient. To improve the segmentation quality, the coarse foreground is obtained via simple background subtraction first. Then, a local texture correlation operator is introduced to fill the vacancies and remove the fractional false foreground regions. Extensive experiments on a variety of public video datasets and comparisons with some classical and recent algorithms are used to demonstrate its improvements in both segmentation accuracy and efficiency.

Human Body Communication (HBC) is regarded as a burgeoning transmission technology for short-range body sensor network applications. However, there are currently few full-scale on-body measurements describing the principle of body channel propagation characteristics upon capacitive coupling. This paper focuses on the comprehensive experiments on different body parts to investigate body channel characteristics. Using capacitive coupling technique, the body channel characteristics were measured both in frequency domain and in time domain. Based on the whole body measurement results, it was found that the body maintained stable attenuation characteristics: the lowest attenuation is approximate -15dB at 28MHz. Arthrosis such as elbow, knee and wrist affected channel attenuation characteristic by about 2dB. Furthermore, the experiment results illustrate that the fat content in body also affects channel characteristic by 4dB.

This paper evaluates the feasibility of a proposed ultrasound-based surgical navigation system for percutaneous renal intervention via in vivo measurements and in vitro assessment. The system integrates preoperative computer tomography (CT) planning with intraoperative ultrasonography (US) by means of a proposed semi-automatic US to CT rigid registration. The interventional procedure is performed with a visualized guidance interface. The navigation system is evaluated at two levels. Level I evaluation comprises measurements of the accuracy, precision, and processing time of our registration method on in vivo data provided by volunteers. For Level II, expert urologists are asked to rate the perceptual quality of the system via in vitro tests on a kidney phantom. Both objective and subjective evaluations validate the proposed surgical navigation system.

This paper proposes a multi-hop synchronization protocol for multiple physiological information transmission over the body sensor network (BSN). A packet reconstitution mechanism was designed to achieve synchronous transmission. The experimental results validated the efficiency of the protocol on continuous real-time monitoring of multiple physiological parameters over multi-hop BSNs.

Personalized insole design is a novel approach for better quality of daily life. In this study we developed a low-cost foot pressure measurement system elaborated for primary care and community hospitals, subsequently the feature extraction and pattern recognition were carried out in order to assist the clubfoot diagnosis. The original data were obtained from 20 adults with normal feet and 30 patients with diagnosed clubfeet. Features such as peak pressure and regional contact area were deduced from 10 anatomically significant areas. It was indicated that, comparing with normal feet, flat feet exhibited larger contact area in midfoot (p<;0.001), and hollow feet showed smaller contact area (p<;0.001) in midfoot. During walking, the highest peak pressure (p<;0.001) and the second highest pressure (p<;0.05) of pollex valgus were found beneath hallux and middle forefoot, respectively, and overall the highest peak pressure of hollow feet was found beneath forefoot. Furthermore, the highest peak pressure (p<;0.001) and the second highest peak pressure (p<;0.05) of pollex valgus for standing were found underneath hallux and lateral forefoot. Our study represented the first steps towards a fully-automated personalized insole design.

Human movement pattern can be a valuable information for rehabilitation therapy, sport medicine and elderly people monitoring, but acquisition of them through multi-cite accelerormeters would result in uncomfortable wearing and complex data processing. In this paper, method of using a single waist-fixed accelerometer to detect human movement pattern was investigated and evaluated. 10 subjects were asked to run or walk on a treadmill in a regular way. A 5th order Butterworth low pass filter with cutoff frequency 20Hz was designed to filter the acceleration data and denoise the sample. By collecting the velocity from treadmill as label data and the individual's waist acceleration data, training data set was established. A Bayesian network classifier trained by EM learning algorithm was developed for human movement pattern assessing. Experiment showed that the method could predict the human walking and running state with a considerable accuracy more than 90%. Such accuracy could also be achieved even with a single superior-inferior acceleration feature. The classification of fast speed walking and normal speed one also achieved satisfying result. This indicated that in some application in which walking and running state were only needed to classify could employ the low power, low computational complexity uniaxial accelerometer as the human movement detector.

Recent years have seen the rapid development of microsensor technology, system on chip design, wireless technology and ubiquitous computing. When assembled into a complex microsystem the technologies become powerful tools in medical diagnostics, environmental monitoring and personal connectivity. In this paper we describe the demonstration of a silicon chip that has all the attributes required of a microsystem for use in these applications. The design methodology we have employed is a variant of the system on chip approach whereby many intellectual property blocks are integrated at a high level in the design flow. Our intellectual property blocks include the analogue sensor instrumentation for temperature and pH, a data multiplexing and conversion module, a digital platform based around an 8-bit microcontroller, data encoding for spread-spectrum wireless transmission and a RF section requiring very few off-chip components. The chip has been fully evaluated and tested by connection to external sensors. Each block has well defined interfaces so that they can be easily reused in future designs targeted to different applications