Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top

2018 | Book

A Secured Smartphone-Based Architecture for Prolonged Monitoring of Neurological Gait Read chapter Read first chapter

Internet of Things (IoT) Technologies for HealthCare

4th International Conference, HealthyIoT 2017, Angers, France, October 24-25, 2017, Proceedings

Editors: Mobyen Uddin Ahmed, Shahina Begum, Jean-Baptiste Fasquel

Publisher: Springer International Publishing

Book Series : Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

Part of: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Login to get access
insite
SEARCH

About this book

This book constitutes the proceedings of the Fourth International Conference on Internet of Things (IoT) Technologies for HealthCare, HealthyIoT 2017, held in Angers, France, in October 2017. The IoT as a set of existing and emerging technologies, notions and services can provide many solutions to delivery of electronic healthcare, patient care, and medical data management. The 17 revised full papers presented were carefully reviewed and selected from 23 submissions. The papers cover topics such as healthcare support for the elderly, real-time monitoring systems, security, safety and communication, smart homes and smart caring environments, intelligent data processing and predictive algorithms in e-Health, emerging e-Health IoT applications, signal processing and analysis , the smartphones as a healthy thing, machine learning and deep learning, and cloud computing.

Table of Contents

Frontmatter
Erratum to: Internet of Things (IoT) Technologies for HealthCare
Mobyen Uddin Ahmed, Shahina Begum, Jean-Baptiste Fasquel

Main Track

Frontmatter
A Secured Smartphone-Based Architecture for Prolonged Monitoring of Neurological Gait
Abstract
Gait monitoring is one of the most demanding areas in the rapidly growing mobile health field. We developed a smartphone-based architecture (called “NeuroSENS”) to improve patient-clinician interaction and to promote the prolonged monitoring of neurological gait by the patients themselves. A particular attention was paid to the security and privacy issues in patient’s data transfer, that are assured at three levels in an in-depth defense strategy (data storage, mobile and web apps and data transmission). Although of very wide application, our architecture offers a first application to detect intermittent claudication and gait asymmetry by estimating duty cycle and ratio between odd and even peaks of autocorrelation from vertical accelerometer signal and rotation of the trunk by the fusion of accelerometer, gyroscope and magnetometer signals in 3D. During exercices on volunteers, sensor data were recorded through the presented architecture with different speeds, durations and constrains. Estimated duty cycles, autocorrelation peaks ratios and trunk rotations showed statistically significant difference (\(p<0.05\)) with knee brace compared to free walk. In conclusion, the NeuroSENS architecture can be used to detect walking irregularities using a readily available mobile platform that addresses security and privacy issues.
Pierre Gard, Lucie Lalanne, Alexandre Ambourg, David Rousseau, François Lesueur, Carole Frindel
Vision-Based Remote Heart Rate Variability Monitoring Using Camera
Abstract
Heart Rate Variability (HRV) is one of the important physiological parameter which is used to early detect many fatal disease. In this paper a non-contact remote Heart Rate Variability (HRV) monitoring system is developed using the facial video based on color variation of facial skin caused by cardiac pulse. The lab color space of the facial video is used to extract color values of skin and signal processing algorithms i.e., Fast Fourier Transform (FFT), Independent Component Analysis (ICA), Principle Component Analysis (PCA) are applied to monitor HRV. First, R peak is detected from the color variation of skin and then Inter-Beat-Interval (IBI) is calculated for every consecutive R-R peak. HRV features are then calculated based on IBI both in time and frequency domain. MySQL and PHP programming language is used to store, monitor and display HRV parameters remotely. In this study, HRV is quantified and compared with a reference measurement where a high degree of similarities is achieved. This technology has significant potential for advancing personal health care especially for telemedicine.
Hamidur Rahman, Mobyen Uddin Ahmed, Shahina Begum
How Accurate Are Smartphone Accelerometers to Identify Intermittent Claudication?
Abstract
Claudication is a cramping pain that is worsened by walking and relieved with rest. It is caused by inadequate blood flow to the leg muscles because of atherosclerosis. Recently, smartphones and their sensors have been proposed in the context of mobile health to monitor gait. However, their use remains disputed: objections concern the quality of the collected data. Therefore, the work presented in this paper proposes to study three main sources of noise observed in smartphone accelerometers and to objectively assess their impact on claudication detection. To do so, we first observe three noise sources in four different smartphones to get an idea of their ranges; we second compare the smartphones’ signals to a ground truth from a vision-based system and third propose to detect claudication by estimating duty cycle from the vertical accelerometer signal and to evaluate the impact of the three noise sources on this basis.
Carole Frindel, David Rousseau
Distributed Multivariate Physiological Signal Analytics for Drivers’ Mental State Monitoring
Abstract
This paper presents a distributed data analytics approach for drivers’ mental state monitoring using multivariate physiological signals. Driver’s mental states such as cognitive distraction, sleepiness, stress, etc. can be fatal contributing factors and to prevent car crashes these factors need to be understood. Here, a cloud-based approach with heterogeneous sensor sources that generates extremely large data sets of physiological signals need to be handled and analysed in a big data scenario. In the proposed physiological big data analytics approach, for driver state monitoring, heterogeneous data coming from multiple sources i.e., multivariate physiological signals are used, processed and analyzed to aware impaired vehicle drivers. Here, in a distributed big data environment, multi-agent case-based reasoning facilitates parallel case similarity matching and handles data that are coming from single and multiple physiological signal sources.
Shaibal Barua, Mobyen Uddin Ahmed, Shahina Begum
An Efficient Design of a Machine Learning-Based Elderly Fall Detector
Abstract
Elderly fall detection is an important health care application as falls represent the major reason of injuries. An efficient design of a machine learning-based wearable fall detection system is proposed in this paper. The proposed system depends only on a 3-axial accelerometer to capture the elderly motion. As the power consumption is proportional to the sampling frequency, the performance of the proposed fall detector is analyzed as a function of this frequency in order to determine the best trade-off between performance and power consumption. Thanks to efficient extracted features, the proposed system achieves a sensitivity of 99.73% and a specificity of 97.7% using a 40 Hz sampling frequency notably outperforming reference algorithms when tested on a large dataset.
L. P. Nguyen, M. Saleh, R. Le Bouquin Jeannès
Characterization of Home-Acquired Blood Pressure Time Series Using Multiscale Entropy for Patients Treated Against Kidney Cancer
Abstract
This study deals with the telemonitoring, with a connected tensiometer, of 16 patients treated for a kidney cancer. Each one of these patients recorded his/her blood pressure at home during 63 days and the data was sent to his/her medical doctor. At the same time they were treated with antihypertensive medication when necessary. In this work, our goal was to analyze the complexity of the blood pressure time series. For this purpose, we proposed to use the refined composite multiscale entropy (RCMSE) measures. Our results show that the patterns of RCMSE through temporal scales evolve with the antihypertensive medication. The later might therefore have an impact on home-acquired blood pressure complexity. RCMSE could therefore be an interesting information theory-based tool to study home-acquired physiological data.
Antoine Jamin, Jean-Baptiste Fasquel, Anne Humeau-Heurtier, Pierre Abraham, Georges Leftheriotis, Samir Henni
A Heterogeneous IoT-Based Architecture for Remote Monitoring of Physiological and Environmental Parameters
Abstract
A heterogeneous Internet of Things (IoT) architecture for remote health monitoring (RHM) is proposed, that employs Bluetooth and IEEE 802.15.4 wireless connectivity. The RHM system encompasses Shimmer physiological sensors with Bluetooth radio, and OpenMote environmental sensors with IEEE 802.15.4 radio. This system architecture collects measurements in a relational database in a local server to implement a Fog node for fast data analysis as well as in a remote server in the Cloud.
Gordana Gardašević, Hossein Fotouhi, Ivan Tomasic, Maryam Vahabi, Mats Björkman, Maria Lindén
An RFID Based Activity of Daily Living for Elderly with Alzheimer’s
Abstract
With the proliferation of emerging technologies such as Internet of Things (IOT) and Radio Frequency identification (RFID), it is possible to collect massive amount of data for localization and tracking of people within commercial buildings & smart homes. In this paper we present the design, implementation and testing of an RFID system for monitoring the wandering about of an Elderly with Alzheimer’s at home. The novelty of the algorithm presented lies in its simplicity to detect the motion of elderly from one room to another for monitoring activity of daily living (ADL) and sending alert in case of an onset of emergency without the need for using massive sensors. The system was tested successfully in the lab and achieved an efficiency of 88%.
Muhammad Wasim Raad, Tarek Sheltami, Mohamed Abdelmonem Soliman, Muntadar Alrashed
Automated Recognition and Difficulty Assessment of Boulder Routes
Abstract
Due to fast distribution of powerful, portable processing devices and wearables, the development of learning-based IoT-applications for athletic or medical usage is accelerated. But besides the offering of quantitative features, such as counting repetitions or distances, there are only a few systems which provide qualitative services, e.g., detecting malpositions to avoid injuries or to optimize training success.
Therefore we present a novel, holistic, and sensor-based approach for qualitative analysis of asynchronous, non-recurrent human motion. Furthermore, we deploy it to automatically assess the difficulty level of boulder routes on basis of climbing movements. Within a comprehensive study encompassing 153 ascents of 18 climbers, we extract and examine features such as strength, endurance, and control and achieve a successful classification rate of difficulty levels of more than 98%.
André Ebert, Kyrill Schmid, Chadly Marouane, Claudia Linnhoff-Popien
e-PWV: A Web Application for Assessing Online Carotid-Femoral Pulse Wave Velocity
Abstract
This article presents e-PWV, a web application for the determination of Pulse Wave Velocity (PWV) running on a web platform called NooLib. e-PWV has been applied on signals recorded by an ultrasound system (\(PWV_{et}\), Aloka, Japan) and representing the arterial diameter changes in carotid and femoral sites. \(PWV_{et}\) measurements were compared to PWV recorded by a tonometric technique (\(PWV_{pp}\), PulsePen, Italy). The study was conducted on 120 patients. We found an excellent correlation of r = 0.95 between \(PWV_{et}\) et \(PWV_{pp}\) (\(P<0.0001\); 95% confidence interval of 0.91–0.96; \(PWV_{et}=0.88\times PWV_{pp} + 0.57\)). We observed a small offset of \(-0.33\) ms\(^{-1}\) on the Bland-Altman plot with a limit of agreement from \(-2.21\) to 1.54 ms\(^{-1}\). Our results suggest that e-PWV application can produce online a reliable marker of the regional aortic stiffness using an echotracking system.
Mathieu Collette, Naoures Hassine, Carlo Palombo, Georges Leftheriotis
Automatic Autism Spectrum Disorder Detection Thanks to Eye-Tracking and Neural Network-Based Approach
Abstract
Autism spectrum disorder (ASD) is a neurodevelopmental disorder quite wide and its numerous variations render diagnosis hard. Some works have proven that children suffering from autism have trouble keeping their attention and tend to have a less focused sight. On top of that, eye-tracking systems enable the recording of precise eye focus on a screen. This paper deals with automatic detection of autism spectrum disorder thanks to eye-tracked data and an original Machine Learning approach. Focusing on data that describes the saccades of the patient’s sight, we distinguish, out of our six test patients, young autistic individuals from those with no problems in 83% (five) of tested patients, with a results confidence up to 95%.
Romuald Carette, Federica Cilia, Gilles Dequen, Jerome Bosche, Jean-Luc Guerin, Luc Vandromme
Automatic Detector of Abnormal EEG for Preterm Infants
Abstract
Many of preterm babies suffer from neural disorders caused by birth complications. Hence, early prediction of neural disorders, in preterm infants, is extremely crucial for neuroprotective intervention. In this scope, the goal of this research was to propose an automatic way to study preterm babies Electroencephalograms (EEG). EEG were preprocessed and a time series of standard deviation was computed. These series were thresholded to detect Inter Burst Intervals (IBI). Features were extracted from bursts and IBI and were then classified as Abnormal or Normal using a Multiple Linear Regression. The method was successfully validated on a corpus of 100 infants with no early indication of brain injury. It was also implemented with a user-friendly interface using Java.
Nisrine Jrad, Daniel Schang, Pierre Chauvet, Sylvie Nguyen The Tich, Bassam Daya, Marc Gibaud
Non-invasive Analytics Based Smart System for Diabetes Monitoring
Abstract
Wearable devices have made it possible for health providers to monitor a patient’s health remotely using actuators, sensors and other mobile communication devices. Internet of Things for Medical Devices is poised to revolutionize the functioning of the healthcare industry by providing an environment where the patient data is transmitted via a gateway onto a secure cloud based platforms for storage, aggregation and analytics. This paper proposes new set of wearable devices - a smart neck band, smart wrist band and a pair of smart socks - to continuously monitor the condition of diabetic patients. These devices consist of different sensors working in tandem form a network that reports food intake, heart rate, skin moisture, ambient temperature, walking patterns and weight gain/loss. The devices with the aid of controllers send all the sensor values as a packet via Bluetooth to the Mobile App. With the help of Machine Learning algorithm, we have predicted the change in patient status and alert them.
M. Saravanan, R. Shubha

Posters Track

Frontmatter
Cloud-Based Data Analytics on Human Factor Measurement to Improve Safer Transport
Abstract
Improving safer transport includes individual and collective behavioural aspects and their interaction. A system that can monitor and evaluate the human cognitive and physical capacities based on human factor measurement is often beneficial to improve safety in driving condition. However, analysis and evaluation of human factor measurement i.e. demographics, behaviour and physiology in real-time is challenging. This paper presents a methodology for cloud-based data analysis, categorization and metrics correlation in real-time through a H2020 project called SimuSafe. Initial implementation of this methodology shows a step-by-step approach which can handle huge amount of data with variation and verity in the cloud.
Mobyen Uddin Ahmed, Shahina Begum, Carlos Alberto Catalina, Lior Limonad, Bertil Hök, Gianluca Di Flumeri
Run-Time Assurance for the E-care@home System
Abstract
This paper presents the design and implementation of the software for a run-time assurance infrastructure in the E-care@home system. An experimental evaluation is conducted to verify that the run-time assurance infrastructure is functioning correctly, and to enable detecting performance degradation in experimental IoT network deployments within the context of E-care@home.
Mobyen Uddin Ahmed, Hossein Fotouhi, Uwe Köckemann, Maria Lindén, Ivan Tomasic, Nicolas Tsiftes, Thiemo Voigt
Scalable Framework for Distributed Case-Based Reasoning for Big Data Analytics
Abstract
This paper proposes a scalable framework for distributed case-based reasoning methodology to provide actionable knowledge based on historical big amount of data. The framework addresses several challenges, i.e., promptly analyse big data, cross-domain, use-case specific data processing, multi-source case representation, dynamic case-management, uncertainty, check the plausibility of solution after adaptation etc. through its’ five modules architectures. The architecture allows the functionalities with distributed data analytics and intended to provide solutions under different conditions, i.e. data size, velocity, variety etc.
Shaibal Barua, Shahina Begum, Mobyen Uddin Ahmed
Deep Learning Based Person Identification Using Facial Images
Abstract
Person identification is an important task for many applications for example in security. A person can be identified using finger print, vocal sound, facial image or even by DNA test. However, Person identification using facial images is one of the most popular technique which is non-contact and easy to implement and a research hotspot in the field of pattern recognition and machine vision. In this paper, a deep learning based Person identification system is proposed using facial images which shows higher accuracy than another traditional machine learning, i.e. Support Vector Machine.
Hamidur Rahman, Mobyen Uddin Ahmed, Shahina Begum
Backmatter
Metadata
Title
Internet of Things (IoT) Technologies for HealthCare
Editors
Mobyen Uddin Ahmed
Shahina Begum
Jean-Baptiste Fasquel
Copyright Year
2018
Electronic ISBN
978-3-319-76213-5
Print ISBN
978-3-319-76212-8
DOI
https://doi.org/10.1007/978-3-319-76213-5

Premium Partner

    Image Credits