IEEE International Conference on E-health Networking, Application & Services (IEEE Healthcom 2021)

Session OR-2: Opening Remarks
Session KN3: Keynote 3
Session VCB-3: Virtual Coffee Break Session VLB-2: Virtual Lunch Break Session VCB-4: Virtual Coffee Break Session VDB-2: Virtual Dinner Break
Session S4-R1: Medical, Biomedical, and Health Informatics Session S4-R2: E-Health Services and Applications Session S4-R3: Communications and Networking Session S5-R1: Medical, Biomedical, and Health Informatics Session S5-R2: E-Health Services and Applications Session S5-R3: Communications and Networking Session S6-R1: Medical, Biomedical, and Health Informatics Session S6-R2: Communications and Networking
Session T2: Tutorial: Transdisciplinary Methods For Interdisciplinary Research in IoT-Based Cyber-Physical Systems and Human-Machine Interfaces
Session D2-R1: Medical, Biomedical, and Health Informatics Session D2-R2: E-Health Services and Applications Session D2-R3: Communications and Networking

Session D2-R1

Medical, Biomedical, and Health Informatics

Conference
7:00 PM — 9:00 PM HKT
Local
Mar 2 Tue, 6:00 AM — 8:00 AM EST

Pharmacophore study using the HipHop for the screening novel potential BH3-mimetic compounds

Xin Wang (Lanzhou Universy, China)

0
Beclin-1 was bound to and inhibited by Bcl-2 or the Bcl-2 homolog Bcl-XL, this interaction involves a Bcl-2 homology 3 (BH3) domain in Beclin-1 and the BH3 binding groove of Bcl-2/Bcl-XL. In order to find a new BH3-mimetic compound to disrupt the combination of Beclin-1 and Bcl-2 and promote the autophagy mediated, we used the HipHop for screening novel potential BH3-mimetic compounds. The hit compounds were subjected to docking study to verify the correctness of screening and pick the optimization. Finally, two compounds were selected to carry out biology experiment, and both have a higher induction potency of autophagy in vitro.

Deep U-Net Network for identifying Covid 19 infection Using X Ray Images

Somasundaram Devaraj (Sri Shakthi Institute of Engineering and Technology Coimbatore, India); Nirmala Madian (Sri Shakthi Institute of Engineering and Technology, India)

0
The Novel coronavirus (COVID-19) detection is a challenging task for physicians and clinical people. Due the higher rate of affected people, the clinical tests take too much of time to provide the test results of the patients. The alternate screening is the X-ray and CT images to detect the infection in respiratory system. The classification is complex for visual examination in the X-ray, CT images due to COVID, Pneumonia and other respiratory problems. In this paper, a novel Unet is proposed for segmentation and classification of COVID with X-ray images to other diseased images. In this analysis 2000 COVID X-ray images, 2000 bacteria and 2000 normal images are used. Overall, 6000 test images are considered to train the network for classification. The proposed method provides the accuracy of 98.49 %.

VISKIT - Standardization of the Surveillance of Nosocomial Infections in Veterinary Medicine

Nicolas J. Lehmann, Laura Rohwedder, Adam Furmanczuk, Oliver Junk, Raphael Taxis, Yannick Röder, Agnès Voisard and Peter Böttcher (Freie Universität Berlin, Germany)

0
In veterinary medicine, as in human medicine, infections during a clinical visit are a critical risk factor that must be avoided. While the registration of infectious diseases in human medicine is already highly standardized today, there is still considerable need to catch up in veterinary medicine, especially in the area of hygiene. This paper presents a software system for the standardized registration, surveillance, and evaluation, including cause-of-effect research, of (nosocomial) infections in veterinary medicine, called VISKIT - Veterinary Infection Surveillance Kit.

PRECOSE - An Approach for Preserving Color Semantics in the Conversion of Colors to Grayscale in the Context of Medical Scoring Boards

Nicolas J. Lehmann and Agnès Voisard (Freie Universität Berlin, Germany); Joachim Fluhr (Charité - Universitätsmedizin Berlin, Germany); Felix Spielmann, Bianca George, Muhammed-Ugur Karagülle, Elen Niedermeyer and Semih Can Sancar (Freie Universität Berlin, Germany)

0
Medical visualization often contain colors that highlight important information. When printing medical scoring boards in grayscale, the semantic information of colors is lost. Hence, visualizations relies on text-based information for the reader to comprehend images in grayscale. Common grayscale mapping methods do not preserve the special semantics of colors. In medical scoring boards, colors that are used are red for critical, yellow for warning, green for harmless, and blue for without any concerns. To overcome problem of information loss, we present PRECOSE, a method for the color to grayscale conversion for medical scoring boards, which enables to PREserve COlor SEmantics in a grayscale color space. With PRECOSE medical scoring boards do not longer have the need for textual features. They can be printed in grayscale without the loss of colors' semantics.

Highly conformal, ultrathin, robust Au@AgNWs/PVDF epidermal electrodes for electrophysiological signals recording

Lin Jin, Tang Wenjie, Zhou Yuxuan and Hu Benhui (Nanjing Medical University, China)

0
Non-invasive epidermal electrodes have emerged as a smart health monitoring apparatus to record the electrophysiological signals. However, previously reported conformal epidermal electrodes are generally unresilient to oxidization, thus limiting their application in long-term wearable healthcare electronics. Here, by in-situ growth of Au on Ag-nanowires, we produce Au@AgNWs/PVDF epidermal electrodes. Owing to the protection of Au, our epidermal electrode exhibits higher robustness than AgNWs/PVDF electrode. Besides, the PVDF matrix with high dielectric constant and good biocompatibility effectively reduced contact impedance and skin irritation. Using this Au@AgNWs/PVDF electrode, we successfully monitored high quality electroencephalographic signals, demonstrating its ability in recording high quality electrophysiological signals.

Deep Learning for a Low-data Drug Design System

Yuchen Qian (Baylor University, USA); Yuan Xing (University of Wisconsin-Stout, USA); Liang Dong (Baylor University, USA)

0
Molecule design is the process of discovering potential compound candidates for drug discovery. Deep learning technique shows significant advantages in data mining and can be used for molecule design. However, most drug discovery projects are limited to low-data situations, and it is difficult to train deep learning neural networks. This paper proposes a novel drug design system that is based on deep learning. It adopts one-shot learning and reinforcement learning, and it can operate under low-data conditions. Once trained, the system can generate new molecules with the desired properties.

Session D2-R2

E-Health Services and Applications

Conference
7:00 PM — 9:00 PM HKT
Local
Mar 2 Tue, 6:00 AM — 8:00 AM EST

High Sensitive Ultrathin Wearable Sensor for Physiological Signal Monitoring

Dianpeng Qi and Yan Liu (Harbin Institute of Technology, China)

0
The high thickness of the wearable device restricts its conformal adhesion to the human skin, which results in low sensitive and unstable detection to the physiological signals. Here, an ultrathin wearable sensor with conformal skin adhesion was developed. It showed high sensitivity and good stability in physiological signal monitoring (e. g., human pulse)

mHealthAtlas - An Approach for the Multidisciplinary Evaluation of mHealth Applications

Nicolas J. Lehmann (Freie Universität Berlin, Germany); Joachim Fluhr (Charité - Universitätsmedizin Berlin, Germany); Agnès Voisard, Oliver Junk, Laura Mielke, Daniel Kmiotek, Muhammed-Ugur Karagülle, Linus Ververs, Bianca George and Felix Spielmann (Freie Universität Berlin, Germany)

0
In Germany, mHealth applications can be prescribed to patients since December 19, 2019. A meaningful taxonomy for the selection of a suitable mHealth application is not available in current mobile application stores. Additionally, the stores lack reliable content and quality controls. An adequate approach to determine the quality of mHealth applications has been missing since then. Presently, these facts prevent physicians from determining which mHealth applications are suitable for prescribing them to their patients. Following that, the question arises how existing technical approaches and regulations can be conjoined to provide a quality assured and low-distortion approach for the evaluation of mHealth applications. In this paper, we present mHealthAtlas, a multidisciplinary expert-based approach for the evaluation of the quality of mHealth applications, based on \cite{b02}. First, mHealthAtlas addresses the problems of undifferentiated mHealth taxonomies and proposes a solution for the differentiated classification of mHealth applications. Second, a score is proposed for a comparable quality assessment of mHealth applications. Third, the mHealthAtlas system and its mode of operation is presented.

Au/PDMS Composite Film for High-Sensitivity Stretchable Strain Sensors

Shaowu Pan (Donghua University, China)

0
Stretchable strain sensors play significant application in human activity capturing, health monitoring and soft robotics. To obtain reliable information, a high-sensitivity strain sensor should be designed. Herein, (3-mercaptopropyl)trimethoxysilane is used as a "bridge molecule" to bond gold naofilm with polydimethylsiloxane, forming a stable and flexible composite film. This film shows a high sensitivity (average gauge factor: 183.2) in stretchable strain sensors.

A Behaviour Patterns Extraction Method for Recognizing Generalized Anxiety Disorder

Minqiang Yang, Jingsheng Tang and Yushan Wu (Lanzhou University, China); Zhenyu Liu (Lanzhou Univerisity, China); Xiping Hu and Bin Hu (Lanzhou University, China)

0
Generalized anxiety disorder (GAD), as one of the most common chronic anxiety disorders, it facing difficulty to be clinically diagnosed. With the rapid development and wide application on smartphones in recent years, its application prospects in the field of mental disease monitoring and diagnosis have been fully proven. Based on the WeChat applet platform of smartphones, an APP that integrates scale testing and inertial sensor data collection to study the detection of subjects with GAD in task state is developed. A behavior patterns extraction method is proposed using sliding windows to split behavior data, and processing data segments for clustering to extract behavior patterns. Distribution information extracted from the subjects' behavior patterns and combine them with the descriptive statistical features of the sample are combined to identify GAD. The results show that the recognition accuracy of this method in female GAD subjects is 66.44%, and in male GAD subjects is 71.43%.

Classification of resting state EEG data in patients with depression

Lee Dzhao (XiamenUniversity, China); Jintao Tang (Xiamen University, China); Li DingZhao (XiamenUniversity, China)

0
Depression is a common mental disease, and it is committed to promote the research of depression assessment based on physiological signals. By collecting the resting state EEG data of depressive disorder, we collected the resting state EEG data of 14 patients with depression and 17 normal people. Through the analysis, the number of troughs of each person's data was statistically analyzed, combined with the convolution neural network model. The accuracy rate of some data is 94.88% by the statistical trough number method, and the accuracy rate of the remaining part of the test data set is 85.0% through the convolution neural network model, and the final fusion accuracy rate is 86.88%. The experimental results show that the combination of statistical trough number and convolution neural network can distinguish depression patients better in resting state EEG data.

A novel bimodal fusion-based model for depression recognition

Zhenyu Liu (Lanzhou Univerisity, China); Dongyu Wang (Lanzhou University, China); ZhiJie Ding (Tianshui Third People’s Hospital, China); Qiongqiong Chen (Second Provincial People's Hospital of Gansu, China)

0
Depression is a common mental disorder which is harmful to our family, economics and society. A primary way for reducing harm is finding an objective and effective depression detection approach. Speech and video are two promising behavior indicators for depression. In this paper, we proposed a speech and video bimodal fusion model based on time-frequency analysis and convolutional neural network for this goal. For the testing of the proposed method, a speech and video dataset of 292 participants were employed for cross-validation. Compared with the single modal classification results, the classification accuracy and generalization ability of this gender-independent model are further improved, which is helpful for the identification of depression.

Session D2-R3

Communications and Networking

Conference
7:00 PM — 9:00 PM HKT
Local
Mar 2 Tue, 6:00 AM — 8:00 AM EST

Casualty Rescue Algorithm Based on Joint Planning of Multi-UAV

Qinhao Wu (National University of Defense Technology, China)

0
UAVs have been widely used in production, life and military fields in recent years. UAVs can not only monitor a certain area, but also perform a variety of tasks, such as rescue of the wounded. When encountering natural disasters, drones can take the lead in entering disaster relief areas before humans, and thus carry out rescue operations. Under special conditions such as earthquakes, humans are usually unable to enter the disaster area for rescue due to the collapse of buildings. At this time, drones are needed to enter the disaster area to detect the lives of the wounded. What we consider is the path planning problem of multiple UAVs under the background of earthquakes. The modified q-learning learning algorithm is used to realize the joint planning of multiple UAVs. Simulation experiments have proved the effectiveness of the algorithm.

Liquid Metal-filled 3D Structure Wearable Sensor for Finger Bending Monitoring

Guoqiang Li, Mingyang Zhang, Junjie Wu and Man Yuan (Harbin Institute of Technology (Shenzhen), China); Zhiyuan Liu (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, China); Xing Ma (Harbin Institute of Technology (Shenzhen), China)

0
Wearable sensors have many potential applications in health and tactile touch monitoring. In particular, Liquid Metal (LM) based wearable sensors have attracted more and more attentions as they can measure large deformations without failure. However, most of the current LM-based wearable sensors are 2D flaky structure, which making them position unstable while wearing, and induce measurement errors. In this report, a novel finger bending angle monitoring sensor with 3D hollow design based on embedded LM microchannels is presented. Because of the hollow design, this sensor can be easily worn on the finger joints and can accurately distinguish the finger bending angle. And real-time monitoring can be achieved by measuring the inductance value. The results suggest that the studied wearable sensor has excellent stability and reliability. And this sensor has better practical applications in finger action health detection.

Indoor Localization Using Multi-Color Fingerprinting

Till Rexhausen (RWTH Aachen University, Germany); Chung Shue Chen and Fabio Pianese (Nokia Bell Labs, France)

0
VLC based indoor positioning system is a natural choice thanks to LED technology and future trend. We can reuse existing LED lighting installations to design an appropriate scheme to provide indoor localization. By receiving basic information such as the light intensity and knowing the position of the transmitters for example through Visible Light Communication (VLC), one can estimate its position with the potential of high accuracy. In this paper, we use a multi-color sensor and build an indoor localization system based on the light fingerprint, which is suitable for smart cities and homes, health-care centers, hospitals or similar. There are, however, several practical problems that make it a technology that is not yet sufficiently developed to be used in our everyday life. In this paper, a new perspective is given by looking into indoor localization using multi color fingerprinting and different machine learning methods. Experiment results have shown its effectiveness and potentials with mean localization errors of around ten centimeters.

System Design for Data Analysis with Multiscale Entropy

Halmon Lui and Chen-Hsiang Yu (Wentworth Institute of Technology, USA)

1
An engineered lightweight architecture has been used on the server side for different purposes. One of them was to provide an environment for data collection and analysis. Since most of the data analysis is static- and post-process, there is a challenge to apply existing data analysis to data collected in real time. In this paper, we propose an architecture that uses the multiscale entropy analysis (MSE) method to analyze data. This system was used to analyze real electrocardiogram (ECG) data in pseudo real-time. The architecture is divided into three parts: (1) a lightweight back-end system that includes Node.js, MongoDB, Nginx, (2) the use of physiological data from PhysioNet to simulate a real-time environment, and (3) the use of MSE to analyze the simulated data. The current findings are beneficial to the community of health science since it removes the necessity of setting up a real-time environment in order to run the tests on new algorithms and methods.

Classifying ECG exams of different formats and sources Using Convolutional Networks

Jessica dos Santos de Oliveira, Maria Fernanda Wanderley, Clement Bernardo Marques, Priscilla Wagner and Walter Martins Filho (NeuralMed, Brazil)

1
ECG is an important exam to detect cardiac conditions. New algorithms to aid the classification of these exams are arising, but although the exam is widely available, the format of the generated data is not standardized. This paper presents an algorithm developed to detect abnormalities in the exam and classify them between rhythm and beat abnormalities. Three different sources were used with at least six different formats in total. The results show the generalization power of the model, achieving an AUC of 0.96 to detect rhythm conditions, 0.91 to detect abnormalities in general, and a minimum AUC of 0.84 to detect specific beat conditions.

Made with in Toronto · Privacy Policy · © 2022 Duetone Corp.