Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749531
S. Kulaç, H. Arslan
Health care applications of wireless communication have been finding places dramatically. One of these applications is communication of implantable medical devices (IMD)s. It is expected that the number of IMDs will increase greatly in the near future. As a result, significant congestion will be experienced in medical implant communication service (MICS) band, leading to interference problems. In this study, we propose reliable listen-before-talk (LBT) mechanism at low signal-to-noise ratios (SNR)s for medical implant communication systems in order to mitigate the interference effects. In our method, we have just brought out power difference between mean peak and mean lowest power spectral values and it provides reliable and simple monitoring of MICS channels' occupation fastly. Our proposed method has superior performance when threshold power level is considered according to the federal communication commission (FCC) Part 95 regulatory standard.
{"title":"Reliable listen-before-talk mechanism for medical implant communication systems","authors":"S. Kulaç, H. Arslan","doi":"10.1109/HealthCom.2016.7749531","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749531","url":null,"abstract":"Health care applications of wireless communication have been finding places dramatically. One of these applications is communication of implantable medical devices (IMD)s. It is expected that the number of IMDs will increase greatly in the near future. As a result, significant congestion will be experienced in medical implant communication service (MICS) band, leading to interference problems. In this study, we propose reliable listen-before-talk (LBT) mechanism at low signal-to-noise ratios (SNR)s for medical implant communication systems in order to mitigate the interference effects. In our method, we have just brought out power difference between mean peak and mean lowest power spectral values and it provides reliable and simple monitoring of MICS channels' occupation fastly. Our proposed method has superior performance when threshold power level is considered according to the federal communication commission (FCC) Part 95 regulatory standard.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125589970","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749505
Y. Matsumoto, M. Ogawa, M. Tsuji
This study aims at evaluating the economic effect of a e-ambulance project, or emergency telemedicine in the rural areas in Kouchi Prefecture in Japan. Ambulances equipped with ICT devices which transmit images of acute patients to remote hospitals are focused on. Kouchi Prefecture started the e-ambulance project in Aki and Muroto Cities in 2012. From two cities, it takes approximately one hour to reach emergency hospitals located in Kouchi City, the prefectural capital. One of the merits of e-ambulance with the image transmitting system is that doctors in accepting hospitals can monitor real time situation of a patient and prepare for necessary treatment prior to the time patient arrives. They thus save time and effort. In measuring benefit, this study employs different methodology; the e-ambulance project enhances wellness of residents since they perceive more secure. Thus the CVM (Contingent valuation method) is applied and WTP (willingness to pay) is used as an index of benefit and estimated based on surveys to residents, which amounts to 1,747 yen per resident per year. Total cost calculated is 381,792,228 yen over three years, and accordingly, B/C ratio amounts 0.459.
{"title":"Economic evaluation of m-Health: Case of e-ambulance in Japan","authors":"Y. Matsumoto, M. Ogawa, M. Tsuji","doi":"10.1109/HealthCom.2016.7749505","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749505","url":null,"abstract":"This study aims at evaluating the economic effect of a e-ambulance project, or emergency telemedicine in the rural areas in Kouchi Prefecture in Japan. Ambulances equipped with ICT devices which transmit images of acute patients to remote hospitals are focused on. Kouchi Prefecture started the e-ambulance project in Aki and Muroto Cities in 2012. From two cities, it takes approximately one hour to reach emergency hospitals located in Kouchi City, the prefectural capital. One of the merits of e-ambulance with the image transmitting system is that doctors in accepting hospitals can monitor real time situation of a patient and prepare for necessary treatment prior to the time patient arrives. They thus save time and effort. In measuring benefit, this study employs different methodology; the e-ambulance project enhances wellness of residents since they perceive more secure. Thus the CVM (Contingent valuation method) is applied and WTP (willingness to pay) is used as an index of benefit and estimated based on surveys to residents, which amounts to 1,747 yen per resident per year. Total cost calculated is 381,792,228 yen over three years, and accordingly, B/C ratio amounts 0.459.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129961356","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749462
A. Paulin, Christoph Thuemmler
This paper describes the use of the Secure SQL Server system (SecSQL) - a system for dynamic fine-grained access control, in the context of e-Health. The system was used in two heterogeneous use-cases of a European project, namely: to govern drugs along the supply chain from the manufacturer to the consumer (to fight counterfeit drugs, and to recall drugs), and to govern the movement of things in the operating theatre. This way, the feasibility of SecSQL to be used as a system to dynamically govern fine-grained access control to Hippocratic data in the e-Health context has been demonstrated.
{"title":"Dynamic fine-grained access control in e-Health using: The secure SQL server system as an enabler of the future Internet","authors":"A. Paulin, Christoph Thuemmler","doi":"10.1109/HealthCom.2016.7749462","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749462","url":null,"abstract":"This paper describes the use of the Secure SQL Server system (SecSQL) - a system for dynamic fine-grained access control, in the context of e-Health. The system was used in two heterogeneous use-cases of a European project, namely: to govern drugs along the supply chain from the manufacturer to the consumer (to fight counterfeit drugs, and to recall drugs), and to govern the movement of things in the operating theatre. This way, the feasibility of SecSQL to be used as a system to dynamically govern fine-grained access control to Hippocratic data in the e-Health context has been demonstrated.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130320212","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749494
Mashrura Tasnim, Rifat Shahriyar, Nowshin Nahar, Hossain Mahmud
Depression is a familiar psychological disorder caused by a combination of genetic, biological, environmental, and psychological factors. Untreated depression carries a high cost in terms of relationship problems, family suffering, and loss of work productivity. However diagnosis and treatment of depression is difficult due to varied severity, frequency, and duration of symptoms in depressed individuals. In this study, correlation between depression levels and behavioral trends of individuals has been established through a survey involving around 120 undergraduate students. The survey outcome is analyzed from a psychological viewpoint and finally some design implications on an automated system of depression detection and support system have been proposed.
{"title":"Intelligent depression detection and support system: Statistical analysis, psychological review and design implication","authors":"Mashrura Tasnim, Rifat Shahriyar, Nowshin Nahar, Hossain Mahmud","doi":"10.1109/HealthCom.2016.7749494","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749494","url":null,"abstract":"Depression is a familiar psychological disorder caused by a combination of genetic, biological, environmental, and psychological factors. Untreated depression carries a high cost in terms of relationship problems, family suffering, and loss of work productivity. However diagnosis and treatment of depression is difficult due to varied severity, frequency, and duration of symptoms in depressed individuals. In this study, correlation between depression levels and behavioral trends of individuals has been established through a survey involving around 120 undergraduate students. The survey outcome is analyzed from a psychological viewpoint and finally some design implications on an automated system of depression detection and support system have been proposed.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131734445","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749435
R. B. Salah, T. Hadidi, I. B. Salah, K. Ouni, S. Mansouri, S. Chabchoub
The innovation of our method is to design a new techniques with multiple capabilities, autonomy and automatic applications in the tele-monitoring and diagnosis of some cardiovascular parameters relative to a certain categories of patients (elderly, children, pregnant women) with cardiovascular diseases. Theoretical model of transthoracic impedance is performed in order to determine aortic pressure with a non-invasive method: the bioimpedance method. The start idea is that aortic impedance variation depends on aortic section, which depends on systolic and diastolic pressure, during cardiac cycle. Theoretical relationships, between electrical bioimpedanc signal and aortic and ventricular pressures are therefore established. The second parameters are the cardiac output Q. The third parameters determined is the arterial compliance C. Results reflect those reached in bibliography, that Cp is significantly reduced in hypertensive patients (Cp=0.48 ± 0.09 E-10 m5.N; normal value of Cp is 1.76 ± 0.28 E-10 m5.N). All this parameters are monitored using telemedicine techniques.
{"title":"A non invasive and intelligent method for cardiovascular parameters tele-monitoring","authors":"R. B. Salah, T. Hadidi, I. B. Salah, K. Ouni, S. Mansouri, S. Chabchoub","doi":"10.1109/HealthCom.2016.7749435","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749435","url":null,"abstract":"The innovation of our method is to design a new techniques with multiple capabilities, autonomy and automatic applications in the tele-monitoring and diagnosis of some cardiovascular parameters relative to a certain categories of patients (elderly, children, pregnant women) with cardiovascular diseases. Theoretical model of transthoracic impedance is performed in order to determine aortic pressure with a non-invasive method: the bioimpedance method. The start idea is that aortic impedance variation depends on aortic section, which depends on systolic and diastolic pressure, during cardiac cycle. Theoretical relationships, between electrical bioimpedanc signal and aortic and ventricular pressures are therefore established. The second parameters are the cardiac output Q. The third parameters determined is the arterial compliance C. Results reflect those reached in bibliography, that Cp is significantly reduced in hypertensive patients (Cp=0.48 ± 0.09 E-10 m5.N; normal value of Cp is 1.76 ± 0.28 E-10 m5.N). All this parameters are monitored using telemedicine techniques.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122400296","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749536
W. Buchanan, N. V. Deursen
Information security threat intelligence is a prevalent topic amongst researchers, long-established IT-vendors and start-ups. The possibilities of Big Data analytics to security threat and vulnerability scanning offer a significant development in the protection of infrastructures. At the same time, industry research reports continue to state that the main contributing factor in the events leading to a data breach is human error. The common response of information security professionals is to resort to technological solutions to prevent these human errors. However, some very important information security intelligence is not hidden within the network traffic: it's available from the people that work with sensitive information. This article describes the Health Information risk (HI-risk) method to identify non-technical information security risks in healthcare. The method includes risks related to skills, behaviour, processes, organisational culture, physical security, and external influences. HI-risk offers a solution to collect intelligence about nontechnical information security incidents from across the healthcare sector to demonstrate past trends and to be ahead of future incidents. A test of a HI-risk forecast proved the feasibility of this approach in healthcare and beyond. It is suggested that HI-risk could become a valuable addition to existing technical threat and vulnerability monitoring tools.
{"title":"HI-risk: A method to analyse health information risk intelligence","authors":"W. Buchanan, N. V. Deursen","doi":"10.1109/HealthCom.2016.7749536","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749536","url":null,"abstract":"Information security threat intelligence is a prevalent topic amongst researchers, long-established IT-vendors and start-ups. The possibilities of Big Data analytics to security threat and vulnerability scanning offer a significant development in the protection of infrastructures. At the same time, industry research reports continue to state that the main contributing factor in the events leading to a data breach is human error. The common response of information security professionals is to resort to technological solutions to prevent these human errors. However, some very important information security intelligence is not hidden within the network traffic: it's available from the people that work with sensitive information. This article describes the Health Information risk (HI-risk) method to identify non-technical information security risks in healthcare. The method includes risks related to skills, behaviour, processes, organisational culture, physical security, and external influences. HI-risk offers a solution to collect intelligence about nontechnical information security incidents from across the healthcare sector to demonstrate past trends and to be ahead of future incidents. A test of a HI-risk forecast proved the feasibility of this approach in healthcare and beyond. It is suggested that HI-risk could become a valuable addition to existing technical threat and vulnerability monitoring tools.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128743629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749425
G. Dantanarayana, T. Sahama
Identification of appropriate performance measures in healthcare is fundamental for judging quality of service in any healthcare organisation. However, the dynamic nature of the healthcare context and complexity of stakeholder requirements have resulted in many difficulties in deciding appropriateness of performance factors to measure outcomes. Yet another facet that hinders achievement of successful performance measuring approaches is the unavailability of systematic guidance to identify the relationship between different types of performance measures. Further, it is important to analyse this relationship by using existing electronic data sets which will ensure the data quality in determining the healthcare service quality. This is an ongoing research attempting to establish a Return on Investment (ROI) model that could facilitate performance measurement of eHealth service deployment while overcoming the aforementioned deficiencies. The systematic guidance of deciding key performance factors considering different healthcare value perspectives in order to establish ROI metrics for the healthcare context, specifically in ICU clinical settings, have been introduced in this paper. It can be served as a theoretical basis in ensuring data quality in eHealth data sources. The advantage of the proposed guidance is in extracting appropriate key performance indicators for measuring outcomes of ICU clinical settings in terms of available process indicators while the relevant data for these indicators could be retrieved from the data warehouse.
{"title":"Metrics for eHealth services improvement","authors":"G. Dantanarayana, T. Sahama","doi":"10.1109/HealthCom.2016.7749425","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749425","url":null,"abstract":"Identification of appropriate performance measures in healthcare is fundamental for judging quality of service in any healthcare organisation. However, the dynamic nature of the healthcare context and complexity of stakeholder requirements have resulted in many difficulties in deciding appropriateness of performance factors to measure outcomes. Yet another facet that hinders achievement of successful performance measuring approaches is the unavailability of systematic guidance to identify the relationship between different types of performance measures. Further, it is important to analyse this relationship by using existing electronic data sets which will ensure the data quality in determining the healthcare service quality. This is an ongoing research attempting to establish a Return on Investment (ROI) model that could facilitate performance measurement of eHealth service deployment while overcoming the aforementioned deficiencies. The systematic guidance of deciding key performance factors considering different healthcare value perspectives in order to establish ROI metrics for the healthcare context, specifically in ICU clinical settings, have been introduced in this paper. It can be served as a theoretical basis in ensuring data quality in eHealth data sources. The advantage of the proposed guidance is in extracting appropriate key performance indicators for measuring outcomes of ICU clinical settings in terms of available process indicators while the relevant data for these indicators could be retrieved from the data warehouse.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123243436","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749440
Yair Enrique Rivera Julio
The paper focuses on the design of an open telematics architecture for telemedicine linked to a device mobile and ubiquitous, a standalone device with direct connection to the cellular data network LTE (Long Term Evolution). The device developed allows a multiplexing of biometric readings through adaptation of specialized Sensors and distributed in different parts of the body, which allow mapping the vitals signal: level of glycemia, Body Temperature Sensor, Blood Pressure Sensor, Pulse and Oxygen in Blood Sensor (SPO2), Airflow Sensor (Breathing), Galvanic Skin Response Sensor (GSR - Sweating), Electrocardiogram Sensor (ECG) and Electromyography Sensor (EMG). The system's modem (TELIT Le910) allows to obtain geo positioning signal of each patient in real time through GPS positioning GLONASS system. This set of data is sent and stored to a geographic health information system, where there is a specialized middleware for a georeferencing related in real time with those specialized health services and their physical infrastructures. A whole technological system that allows to take advantage of the services 4g and the geographic information systems of health monitoring care of patients with chronic diseases in Colombia, where there are some remote areas and difficult access.
{"title":"Design ubiquitous architecture for telemedicine based on mhealth Arduino 4G LTE","authors":"Yair Enrique Rivera Julio","doi":"10.1109/HealthCom.2016.7749440","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749440","url":null,"abstract":"The paper focuses on the design of an open telematics architecture for telemedicine linked to a device mobile and ubiquitous, a standalone device with direct connection to the cellular data network LTE (Long Term Evolution). The device developed allows a multiplexing of biometric readings through adaptation of specialized Sensors and distributed in different parts of the body, which allow mapping the vitals signal: level of glycemia, Body Temperature Sensor, Blood Pressure Sensor, Pulse and Oxygen in Blood Sensor (SPO2), Airflow Sensor (Breathing), Galvanic Skin Response Sensor (GSR - Sweating), Electrocardiogram Sensor (ECG) and Electromyography Sensor (EMG). The system's modem (TELIT Le910) allows to obtain geo positioning signal of each patient in real time through GPS positioning GLONASS system. This set of data is sent and stored to a geographic health information system, where there is a specialized middleware for a georeferencing related in real time with those specialized health services and their physical infrastructures. A whole technological system that allows to take advantage of the services 4g and the geographic information systems of health monitoring care of patients with chronic diseases in Colombia, where there are some remote areas and difficult access.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121755041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749419
V. Silva, M. Rodrigues, R. Barreto, V. Lucena
One of the biggest problems with chronical patients in treatment is medication adherence. Studies indicate that taking drugs out of time influence the patient's treatment decreasing the drugs effect. To minimize this problem, we developed a ubiquitous and intelligent system able to monitor the taking of medicines and to identify whether the patient is meeting the requirements prescribed by the doctor. An architecture provided with a decision system based on rules and trees to evaluate data collected from an intelligent medicine cabinet, sensors and electronic devices available in the patient's home was designed. The system classified the drugs taken pattern and released messages on social networks, SMS, and consumer electronic devices such as TV, smartphone and tablets, without human interference. Its goal is to help keeping the medication on time and helping to decide what to do in case of missing the right time. The algorithms J48, Rep and Random tree, were tested to classify the taking medicine patterns and to chose the right services available. The obtained results are very promising and reached an acceptable accuracy rate.
{"title":"UbMed: A ubiquitous system for monitoring medication adherence","authors":"V. Silva, M. Rodrigues, R. Barreto, V. Lucena","doi":"10.1109/HealthCom.2016.7749419","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749419","url":null,"abstract":"One of the biggest problems with chronical patients in treatment is medication adherence. Studies indicate that taking drugs out of time influence the patient's treatment decreasing the drugs effect. To minimize this problem, we developed a ubiquitous and intelligent system able to monitor the taking of medicines and to identify whether the patient is meeting the requirements prescribed by the doctor. An architecture provided with a decision system based on rules and trees to evaluate data collected from an intelligent medicine cabinet, sensors and electronic devices available in the patient's home was designed. The system classified the drugs taken pattern and released messages on social networks, SMS, and consumer electronic devices such as TV, smartphone and tablets, without human interference. Its goal is to help keeping the medication on time and helping to decide what to do in case of missing the right time. The algorithms J48, Rep and Random tree, were tested to classify the taking medicine patterns and to chose the right services available. The obtained results are very promising and reached an acceptable accuracy rate.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128028347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2016-09-01DOI: 10.1109/HealthCom.2016.7749468
A. Pinho, Nuno Pombo, N. Garcia
This paper presents a suitable and efficient implementation for detecting minute based analysis of sleep apnea by Electrocardiogram (ECG) signal processing. Using the PhysioNet apnea-ECG database, a median filter was applied to the recordings in order to obtain the Heart Rate Variability (HRV) and the ECG-derived respiration (EDR). The subsequent extracted features were used for training, testing and validation of a Artificial Neural Network (ANN). Training and testing sets were obtained by randomly divide the data until it reaches a good performance using a k-fold cross validation (k=10). According to results, the ANN classification has sufficient accuracy for sleep apnea detection and diagnosis (82,120%). This promising early-stage result may leads to complementary studies including alternative features selection methods and/or other classification models.
{"title":"Sleep apnea detection using a feed-forward neural network on ECG signal","authors":"A. Pinho, Nuno Pombo, N. Garcia","doi":"10.1109/HealthCom.2016.7749468","DOIUrl":"https://doi.org/10.1109/HealthCom.2016.7749468","url":null,"abstract":"This paper presents a suitable and efficient implementation for detecting minute based analysis of sleep apnea by Electrocardiogram (ECG) signal processing. Using the PhysioNet apnea-ECG database, a median filter was applied to the recordings in order to obtain the Heart Rate Variability (HRV) and the ECG-derived respiration (EDR). The subsequent extracted features were used for training, testing and validation of a Artificial Neural Network (ANN). Training and testing sets were obtained by randomly divide the data until it reaches a good performance using a k-fold cross validation (k=10). According to results, the ANN classification has sufficient accuracy for sleep apnea detection and diagnosis (82,120%). This promising early-stage result may leads to complementary studies including alternative features selection methods and/or other classification models.","PeriodicalId":167022,"journal":{"name":"2016 IEEE 18th International Conference on e-Health Networking, Applications and Services (Healthcom)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130898602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：