Hybrid manifold-deep convolutional neural network for sleep staging.

Analysis of electroencephalogram (EEG) is a crucial diagnostic criterion for many sleep disorders, of which sleep staging is an important component. Manual stage classification is a labor-intensive process and usually suffered from many subjective factors. Recently, more and more computer-aided techniques have been applied to this task, among which deep convolutional neural network has been performing well as an effective automatic classification model. Despite some comprehensive models have been developed to improve classification results, the accuracy for clinical applications has not been reached due to the lack of sufficient labeled data and the limitation of extracting latent discriminative EEG features. Therefore, we propose a novel hybrid manifold-deep convolutional neural network with hyperbolic attention. To overcome the shortage of labeled data, we update the semi-supervised training scheme as an optimal solution. In order to extract the latent feature representation, we introduce the manifold learning module and the hyperbolic module to extract more discriminative information. Eight subjects from the public dataset are utilized to evaluate our pipeline, and the model achieved 89% accuracy, 70% precision, 80% sensitivity, 72% f1-score and kappa coefficient of 78%, respectively. The proposed model demonstrates powerful ability in extracting feature representation and achieves promising results by using semi-supervised training scheme. Therefore, our approach shows strong potential for future clinical development.

Gait Rhythm Dynamics for Neuro-Degenerative Disease Classification via Persistence Landscape- Based Topological Representation.

Neuro-degenerative disease is a common progressive nervous system disorder that leads to serious clinical consequences. Gait rhythm dynamics analysis is essential for evaluating clinical states and improving quality of life for neuro-degenerative patients. The magnitude of stride-to-stride fluctuations and corresponding changes over time-gait dynamics-reflects the physiology of gait, in quantifying the pathologic alterations in the locomotor control system of health subjects and patients with neuro-degenerative diseases. Motivated by algebra topology theory, a topological data analysis-inspired nonlinear framework was adopted in the study of the gait dynamics. Meanwhile, the topological representation-persistence landscapes were used as input of classifiers in order to distinguish different neuro-degenerative disease type from healthy. In this work, stride-to-stride time series from healthy control (HC) subjects are compared with the gait dynamics from patients with amyotrophic lateral sclerosis (ALS), Huntington's disease (HD), and Parkinson's disease (PD). The obtained results show that the proposed methodology discriminates healthy subjects from subjects with other neuro-degenerative diseases with relatively high accuracy. In summary, our study is the first attempt to provide a topological representation-based method into the disease classification with gait rhythms measured from the stride intervals to visualize gait dynamics and classify neuro-degenerative diseases. The proposed method could be potentially used in earlier interventions and state monitoring.

Statistical and spectral analysis of ECG signal towards achieving non-invasive blood glucose monitoring.

BACKGROUND: Globally, the cases of diabetes mellitus (diabetes) have increased in the past three decades, and it is recorded as one of the leading cause of death. This epidemic is a metabolic condition where the body cannot regulate blood glucose, thereby leading to abnormally high blood sugar. Genetic condition plays a significant role to determine a person susceptibility to the condition, a sedentary lifestyle and an unhealthy diet are behaviour that supports the current global epidemic. The complication that arises from diabetes includes loss of vision, peripheral neuropathy, cardiovascular complications and so on. Victims of this condition require constant monitoring of blood glucose which is done by the pricking of the finger. This procedure is painful, inconvenient and can lead to disease infection. Therefore, it is important to find a way to measure blood glucose non-invasively to minimize or eliminate the disadvantages encountered with the usual monitoring of blood glucose. METHOD: In this paper, we performed two experiments on 16 participants while electrocardiogram (ECG) data was continuously captured. In the first experiment, participants are required to consume 75 g of anhydrous glucose solution (oral glucose tolerance test) and the second experiment, no glucose solution was taken. We explored statistical and spectral analysis on HRV, HR, R-H, P-H, PRQ, QRS, QT, QTC and ST segments derived from ECG signal to investigate which segments should be considered for the possibility of achieving non-invasive blood glucose monitoring. In the statistical analysis, we examined the pattern of the data with the boxplot technique to reveal the change in the statistical properties of the data. Power spectral density estimation was adopted for the spectral analysis to show the frequency distribution of the data. RESULTS: HRV segment obtained a statistical score of 81% for decreasing pattern and HR segment have the same statistical score for increasing pattern among the participants in the first quartile, median and mean properties. While ST segment has a statistical score of 81% for decreasing pattern in the third quartile, QT segment has 81% for increasing pattern for the median. From a total change score of 6, ST, QT, PRQ, P-H, HR and HRV obtained 4, 5, 4, 5 and 6 respectively. For spectral analysis, HRV and HR segment scored 81 and 75% respectively. ST, QT, PRQ have 75, 62 and 68% respectively. CONCLUSIONS: The results obtained demonstrate that HR, HRV, PRQ, QT and ST segments under a normal, healthy condition are affected by glucose and should be considered for modelling a system to achieve the possibility of non-invasive blood glucose measurement with ECG.

Realization of Low Profile Leaky Wave Antennas Using the Bending Technique for Frequency Scanning and Sensor Applications.

This paper proposes an efficient transmission line modulation by using the bending technique to realize low profile leaky wave antennas in the Ku-band for frequency scanning and sensor applications. The paper focuses mainly on the bending effects of the transmission line in terms of the sharpness of edges. The right-hand/left-hand transmission line can be designed in the form of zig-zag pattern with sharp corners and only the right-hand transmission line in the form of sinusoidal patterns with smooth corners. In this presentation, we demonstrate that transmission lines of this kind can be used to realize highly efficient leaky wave antennas with broadband impedance matching and high gain characteristics in the Ku-band. Dispersion analysis and ladder network analysis have been performed for investigating the performance of the proposed designs. The sharpness of the bends periodically distributed along the body of the antenna has been used to our advantage for frequency scanning in the left-hand and right-hand quadrants at different frequencies. The proposed bending technique has been proven to be instrumental in achieving the desired characteristics of low profile leaky wave antennas.

Evaluation of Propagation Characteristics Using the Human Body as an Antenna.

In this paper, an inhomogeneous human body model was presented to investigate the propagation characteristics when the human body was used as an antenna to achieve signal transmission. Specifically, the channel gain of four scenarios, namely, (1) both TX electrode and RX electrode were placed in the air, (2) TX electrode was attached on the human body, and RX electrode was placed in the air, (3) TX electrode was placed in the air, and RX electrode was attached on the human body, (4) both the TX electrode and RX electrode were attached on the human body, were studied through numerical simulation in the frequency range 1 MHz to 90 MHz. Furthermore, the comparisons of input efficiency, accepted efficiency, total efficiency, absorption power of human body, and electric field distribution of different distances of four aforementioned scenarios were explored when the frequency was at 44 MHz. In addition, the influences of different human tissues, electrode position, and the distance between electrode and human body on the propagation characteristics were investigated respectively at 44 MHz. The results showed that the channel gain of Scenario 4 was the maximum when the frequency was from 1 MHz to 90 MHz. The propagation characteristics were almost independent of electrode position when the human body was using as an antenna. However, as the distance between TX electrode and human body increased, the channel gain decreased rapidly. The simulations were verified by experimental measurements. The results showed that the simulations were in agreement with the measurements.

An Approach to Biometric Verification Based on Human Body Communication in Wearable Devices.

In this paper, an approach to biometric verification based on human body communication (HBC) is presented for wearable devices. For this purpose, the transmission gain S21 of volunteer's forearm is measured by vector network analyzer (VNA). Specifically, in order to determine the chosen frequency for biometric verification, 1800 groups of data are acquired from 10 volunteers in the frequency range 0.3 MHz to 1500 MHz, and each group includes 1601 sample data. In addition, to achieve the rapid verification, 30 groups of data for each volunteer are acquired at the chosen frequency, and each group contains only 21 sample data. Furthermore, a threshold-adaptive template matching (TATM) algorithm based on weighted Euclidean distance is proposed for rapid verification in this work. The results indicate that the chosen frequency for biometric verification is from 650 MHz to 750 MHz. The false acceptance rate (FAR) and false rejection rate (FRR) based on TATM are approximately 5.79% and 6.74%, respectively. In contrast, the FAR and FRR were 4.17% and 37.5%, 3.37% and 33.33%, and 3.80% and 34.17% using K-nearest neighbor (KNN) classification, support vector machines (SVM), and naive Bayesian method (NBM) classification, respectively. In addition, the running time of TATM is 0.019 s, whereas the running times of KNN, SVM and NBM are 0.310 s, 0.0385 s, and 0.168 s, respectively. Therefore, TATM is suggested to be appropriate for rapid verification use in wearable devices.

A statistical frame based TDMA protocol for human body communication.

BACKGROUND: Human body communication (HBC) using the human body as the transmission medium, which has been regarded as one of the most promising short-range communications in wireless body area networks (WBAN). Compared to the traditional wireless networks, two challenges are existed in HBC based WBAN. (1) Its sensor nodes should be energy saving since it is inconvenient to replace or recharge the battery on these sensor nodes; (2) the coordinator should be able to react dynamically and rapidly to the burst traffic triggered by sensing events. Those burst traffic conditions include vital physical signal (electrocardiogram, electroencephalogram etc.) monitoring, human motion detection (fall detection, activity monitoring, gesture recognition, motion sensing etc.) and so on. To cope with aforementioned challenges, a statistical frame based TDMA (S-TDMA) protocol with multi-constrained (energy, delay, transmission efficiency and emergency management) service is proposed in this paper. METHODS: The scenarios where burst traffic is often triggered rapidly with low power consumption and low delay is handled in our proposed S-TDMA. A beacon frame with the contained synchronous and poll information is designed to reduce the possibility of collisions of request frames. A statistical frame which broadcasts the unified scheduling information is adopted to avoid packet collisions, idle listening and overhearing. Dynamic time slot allocation mechanism is presented to manage the burst traffic and reduce the active period in each beacon period. An emergency mechanism is proposed for vital signals to be transmitted. The theory analysis is proceed and the result is evaluated in the hardware platform. RESULTS: To verify its feasibility, S-TDMA was fully implemented on our independently-developed HBC platform where four sensor nodes and a coordinator are fastened on a human body. Experiment results show that S-TDMA costs 89.397 mJ every 20 s when the payload size is 122 bytes, 9.51% lower than Lightweight MAC (LMAC); the average data latency of S-TDMA is 6.3 ms, 7.02% lower than Preamble-based TDMA (PB-TDMA); the transmission efficiency of S-TDMA is 93.67%, 4.83% higher than IEEE 802.15.6 carrier sense multiple access/collision avoidance (CSMA/CA) protocol. CONCLUSIONS: With respect to the challenges of HBC based WBANs, a novel S-TDMA protocol was proposed in this paper. Compared to the traditional protocols, the results demonstrate that S-TDMA successfully meets the delay and transmission efficiency requirements of HBC while keeping a low energy consumption. We also believe that our S-TDMA protocol will promote development of HBC in wearable applications.

PPG based Noninvasive Blood Glucose Monitoring using Multi-view Attention and Cascaded BiLSTM Hierarchical Feature Fusion Approach.

Diabetes is a chronic disease with exponential growth and poses significant challenges to global healthcare. Regular blood glucose (BG) monitoring is key for avoiding diabetic complications. Traditional BG measurement techniques are invasive and minimally invasive, causing pain, discomfort, cost, and infection risks. To address these issues, we developed a noninvasive BG monitoring approach on photoplethysmography (PPG) signals using multi-view attention and cascaded BiLSTM hierarchical feature fusion approach. Firstly, we implemented a convolutional multi-view attention block to extract the temporal features through adaptive contextual information aggregation. Secondly, we built a cascaded BiLSTM network to efficiently extract the fine-grained features through bidirectional learning. Finally, we developed a hierarchical feature fusion with bilinear polling through cross-layer interaction to obtain higher-order features for BG monitoring. For validation, we conducted comprehensive experimentation on up to 6 days of PPG and BG data from 21 participants. The proposed approach showed competitive results compared to existing approaches by RMSE of 1.67 mmol/L and MARD of 17.88%. Additionally, the clinical accuracy using Clarke error grid (CEG) analysis showed 98.80% of BG values in Zone A+B. Therefore, the proposed approach offers a favorable solution in diabetes management by noninvasively monitoring the BG levels.

PEDOT:PSS-Based Wearable Flexible Temperature Sensor and Integrated Sensing Matrix for Human Body Monitoring.

Flexible temperature sensors have been widely used in electronic skins and health monitoring. Body temperature as one of the key physiological signals is crucial for detecting human body's abnormalities, which necessitates high sensitivity, quick responsiveness, and stable monitoring. In this paper, we reported a resistive temperature sensor designed as an ultrathin laminated structure with a serpentine pattern and a bioinspired adhesive layer, which was fabricated with a composite of poly(3,4-ethylenedioxythiophene)-poly(styrenesulfonate)/single-wall carbon nanotubes/reduced graphene oxide (PEDOT:PSS/SWCNTs/rGO) and polydimethylsiloxane (PDMS). The temperature sensor exhibited a high temperature sensitivity of 0.63% °C-1, coupled with outstanding linearity of 0.98 within 25-45 °C. Furthermore, it showed fast response and recovery speeds of 4.8 and 5.8 s, respectively, between 25 and 36 °C. It also demonstrated exceptional stability when subjected to stress and bending disturbances with the maximum bending interference deviation of 0.03%. Additionally, it displayed good cyclic stability over a broad temperature range from 25 to 85 °C, and the standard deviation at 25 °C is 0.14%. A series of experiments including blowing detection, respiratory monitoring with or without a mask, and during rest or sleep were conducted to show the potential of the flexible temperature sensors in human body monitoring. Furthermore, a 4 × 4 flexible temperature sensor matrix was integrated to detect and map objects such as wrenches and blood vessels through human hand skin. The results were consistent with those of infrared measurements. The flexible temperature sensor is capable of real-time temperature monitoring and has the potential in tracking human respiration, assessing sleep quality, and mapping the temperature of various objects.

Automatic Chinese Food recognition based on a stacking fusion model.

With commercialization of deep learning models, daily precision dietary record based on images from smartphones becomes possible. This study took advantage of Deep-learning techniques on visual recognition tasks and proposed a big-data-driven Deep-learning model regressing from food images. We established the largest data set of Chinese dishes to date, named CNFOOD-241. It contained more than 190,000 images with 241 categories, covering Staple food, meat, vegetarian diet, mixed meat and vegetables, soups, dessert category. This study also compares the prediction results of three popular deep learning models on this dataset, ResNeXt101_32x32d achieving up to 82.05% for top-1 accuracy and 97.13% for top-5 accuracy. Besides, this paper uses a multi-model fusion method based on stacking in the field of food recognition for the first time. We built a meta-learner after the base model to integrate the three base models of different architectures to improve robustness. The accuracy achieves 82.88% for top-1 accuracy.Clinical Relevance-This study proves that the application of artificial intelligence technology in the identification of Chinese dishes is feasible, which can play a positive role in people who need to control their diet, such as diabetes and obesity.

Continuous Glucose Monitoring Time Series Data Analysis: A Time Series Analysis Package for Continuous Glucose Monitoring Data.

The R package Continuous Glucose Monitoring Time Series Data Analysis (CGMTSA) was developed to facilitate investigations that examine the continuous glucose monitoring (CGM) data as a time series. Accordingly, novel time series functions were introduced to (1) enable more accurate missing data imputation and outlier identification; (2) calculate recommended CGM metrics as well as key time series parameters; (3) plot interactive and three-dimensional graphs that allow direct visualizations of temporal CGM data and time series model optimization. The software was designed to accommodate all popular CGM devices and support all common data processing steps. The program is available for Linux, Windows, and Mac at GitHub.

Noninvasive Blood Glucose Monitoring Using Spatiotemporal ECG and PPG Feature Fusion and Weight-Based Choquet Integral Multimodel Approach.

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.

Dynamic propagation channel characterization and modeling for human body communication.

This paper presents the first characterization and modeling of dynamic propagation channels for human body communication (HBC). In-situ experiments were performed using customized transceivers in an anechoic chamber. Three HBC propagation channels, i.e., from right leg to left leg, from right hand to left hand and from right hand to left leg, were investigated under thirty-three motion scenarios. Snapshots of data (2,800,000) were acquired from five volunteers. Various path gains caused by different locations and movements were quantified and the statistical distributions were estimated. In general, for a given reference threshold è = -10 dB, the maximum average level crossing rate of the HBC was approximately 1.99 Hz, the maximum average fade time was 59.4 ms, and the percentage of bad channel duration time was less than 4.16%. The HBC exhibited a fade depth of -4 dB at 90% complementary cumulative probability. The statistical parameters were observed to be centered for each propagation channel. Subsequently a Fritchman model was implemented to estimate the burst characteristics of the on-body fading. It was concluded that the HBC is motion-insensitive, which is sufficient for reliable communication link during motions, and therefore it has great potential for body sensor/area networks.

Gradient variability coefficient: a novel method for assessing glycemic variability and risk of hypoglycemia.

OBJECTIVE: Despite the clinical importance of glycemic variability and hypoglycemia, thus far, there is no consensus on the optimum method for assessing glycemic variability and risk of hypoglycemia simultaneously. RESEARCH DESIGN AND METHODS: A novel metric, the gradient variability coefficient (GVC), was proposed for characterizing glycemic variability and risk of hypoglycemia. A total of 208 daily records of CGM encompassing 104 patients with T1DM and 2380 daily records from 1190 patients with T2DM were obtained in our study. Simulated CGM waveforms were used to assess the ability of GVC and other metrics to capture the amplitude and frequency of glucose fluctuations. In addition, the association between GVC and the risk of hypoglycemia was evaluated by receiver operating characteristic (ROC) curve. RESULTS: The results of simulated CGM waveforms indicated that, compared with the widely used metrics of glycemic variability including standard deviation of sensor glucose (SD), coefficient of variation (CV), and mean amplitude of glycemic excursion (MAGE), GVC could reflect both the amplitude and frequency of glucose oscillations. In addition, the area under the curve (AUC) of ROC was 0.827 in T1DM and 0.873 in T2DM, indicating good performance in predicting hypoglycemia. CONCLUSIONS: The proposed GVC might be a clinically useful tool in characterizing glycemic variability and the assessment of hypoglycemia risk in patients with diabetes.

Non-invasive Monitoring of Three Glucose Ranges Based On ECG By Using DBSCAN-CNN.

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.

Highly Sensitive Closed Loop Enclosed Split Ring Biosensor With High Field Confinement for Aqueous and Blood-Glucose Measurements.

This paper presents a highly sensitive closed loop enclosed split ring biosensor operating in microwave frequencies for measuring blood glucose levels in the human body. The proposed microwave glucose biosensor, working on the principle of high field confinement and concentrated energy, has been tested using both in-vitro and in-vivo methods. This principle allows the sensor to concentrate energy at the surface which results in improved accuracy of measurements. For in-vitro measurements, the biosensor has been tested using de-ionized water glucose solutions of different concentrations. The miniaturized micrometer scale biosensor is fabricated over a thin Si-substrate using photolithographic technique. The biosensor has been designed in a way to operate at desired microwave frequencies. Highly confined fields and concentrated energy inside the closed loop line containing the split ring resonators are responsible for the sensitivity enhancement. This new biosensor has obtained a high sensitivity of 82 MHz/mgmL-1 within the clinical diabetic range during in-vivo testing over the human body. In addition, the subjects (undergoing experiments) steady state has been continuously monitored throughout the experiment which helps in improving the accuracy of the results. The proposed biosensor has further obtained a low detection limit of <0.05 wt.% and can be useful for continuous non-invasive blood glucose monitoring.

Broadband Frequency Scanning Spoof Surface Plasmon Polariton Design with Highly Confined Endfire Radiations.

This paper proposes a compact broadband frequency scanning spoof surface plasmon polariton (SSPP) based design for efficient endfire radiations with high field confinement. Through the dispersion engineering, highly confined field distribution has been obtained in the operating frequency region. The proposed SSPP antenna has achieved a continuous through endfire scanning in the X-band at other operating frequencies which is in general difficult to obtain for SSPP based antennas. In the proposed design methodology, the swore-shaped surface plasmon antenna has both edges corrugated with an array of rectangular grooves which effectively confines the electromagnetic field into a slow travelling wave. The surface impedances along both edges were engineered to be different at operating frequencies as to force the surface current to preferentially flow along either edge of the antenna to a different extent. The design with overall dimensions of (55 × 30) mm2 has achieved a broadband of 4 GHz with high peak measured gain of 9.8 dBi and peak efficiency of about 95 percent in the X-band. The antenna has been further tested experimentally for scanning application of target location also.

A Novel CGM Metric-Gradient and Combining Mean Sensor Glucose Enable to Improve the Prediction of Nocturnal Hypoglycemic Events in Patients with Diabetes.

Nocturnal hypoglycemia is a serious complication of insulin-treated diabetes, and it is often asymptomatic. A novel CGM metric-gradient was proposed in this paper, and a method of combining mean sensor glucose (MSG) and gradient was presented for the prediction of nocturnal hypoglycemia. For this purpose, the data from continuous glucose monitoring (CGM) encompassing 1,921 patients with diabetes were analyzed, and a total of 302 nocturnal hypoglycemic events were recorded. The MSG and gradient values were calculated, respectively, and then combined as a new metric (i.e., MSG+gradient). In addition, the prediction was conducted by four algorithms, namely, logistic regression, support vector machine, random forest, and long short-term memory. The results revealed that the gradient of CGM showed a downward trend before hypoglycemic events happened. Additionally, the results indicated that the specificity and sensitivity based on the proposed method were better than the conventional metrics of low blood glucose index (LBGI), coefficient of variation (CV), mean absolute glucose (MAG), lability index (LI), etc., and the complex metrics of MSG+LBGI, MSG+CV, MSG+MAG, and MSG+LI, etc. Specifically, the specificity and sensitivity were greater than 96.07% and 96.03% at the prediction horizon of 15 minutes and greater than 87.79% and 90.07% at the prediction horizon of 30 minutes when the proposed method was adopted to predict nocturnal hypoglycemic events in the aforementioned four algorithms. Therefore, the proposed method of combining MSG and gradient may enable to improve the prediction of nocturnal hypoglycemic events. Future studies are warranted to confirm the validity of this metric.

Deep Learning Intervention for Health Care Challenges: Some Biomedical Domain Considerations.

The use of deep learning (DL) for the analysis and diagnosis of biomedical and health care problems has received unprecedented attention in the last decade. The technique has recorded a number of achievements for unearthing meaningful features and accomplishing tasks that were hitherto difficult to solve by other methods and human experts. Currently, biological and medical devices, treatment, and applications are capable of generating large volumes of data in the form of images, sounds, text, graphs, and signals creating the concept of big data. The innovation of DL is a developing trend in the wake of big data for data representation and analysis. DL is a type of machine learning algorithm that has deeper (or more) hidden layers of similar function cascaded into the network and has the capability to make meaning from medical big data. Current transformation drivers to achieve personalized health care delivery will be possible with the use of mobile health (mHealth). DL can provide the analysis for the deluge of data generated from mHealth apps. This paper reviews the fundamentals of DL methods and presents a general view of the trends in DL by capturing literature from PubMed and the Institute of Electrical and Electronics Engineers database publications that implement different variants of DL. We highlight the implementation of DL in health care, which we categorize into biological system, electronic health record, medical image, and physiological signals. In addition, we discuss some inherent challenges of DL affecting biomedical and health domain, as well as prospective research directions that focus on improving health management by promoting the application of physiological signals and modern internet technology.

Statistical characterization of the dynamic human body communication channel at 45 MHz.

The dynamic human body communication (HBC) propagation channel at 45 MHz was statistical characterized in this paper. A large amount of measurement data has been gathered in practical environment with real activities -treadmill running at different speeds in a lab room. The received power between two lower legs was acquired from three volunteers, with more than 60,000 snap shot of data in total. The statistical analyses confirmed that the HBC propagation channel at 45 MHz followed the Gamma and Lognormal distributions at the slower (2 km/h and 4 km/h) and faster (6 km/h and 8 km/h) running activities, respectively. The channel is insensitive to body motion with the maximum average fade duration is 0.0413 s and the most averaging bad channel duration time being less than 60 ms with the percentage of the bad channel duration time being less than 4.35%.