Pub Date : 2019-11-01DOI: 10.1109/BIA48344.2019.8967475
I. Balabanova, S. Kostadinova, V. Markova, G. Georgiev
This report presents an evaluation of artificial neural networks in terms of computational efficiency, by analyzing transmitted information flows for determination the type of defined traffic categories using artificial intelligence. The subject of study are Markov M/M/c circuits with unlimited number of waiting calls in the queue and fixed number of server stations in accordance with the desired test categories, as follows c=5, c=10 and c=15. Three layer architectures are applied to different types of neural output activators with Levenberg-Marquardt training, respectively linear, tangent-sigmoidal and logarithmic-sigmoidal. The lowest values of the Mean Squared Error (MSE) of 0.0080, 0.0041, and 0.1923 are experimentally established at 7, 3, and 25 hidden neurons for the indicated activation functions. An accuracy levels of 94.4%, 100.0%, and 70.6% were obtained against indicator levels for identical numbers of neurons.
{"title":"Analysis and Categorization of Traffic Streams by Artificial Intelligence","authors":"I. Balabanova, S. Kostadinova, V. Markova, G. Georgiev","doi":"10.1109/BIA48344.2019.8967475","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967475","url":null,"abstract":"This report presents an evaluation of artificial neural networks in terms of computational efficiency, by analyzing transmitted information flows for determination the type of defined traffic categories using artificial intelligence. The subject of study are Markov M/M/c circuits with unlimited number of waiting calls in the queue and fixed number of server stations in accordance with the desired test categories, as follows c=5, c=10 and c=15. Three layer architectures are applied to different types of neural output activators with Levenberg-Marquardt training, respectively linear, tangent-sigmoidal and logarithmic-sigmoidal. The lowest values of the Mean Squared Error (MSE) of 0.0080, 0.0041, and 0.1923 are experimentally established at 7, 3, and 25 hidden neurons for the indicated activation functions. An accuracy levels of 94.4%, 100.0%, and 70.6% were obtained against indicator levels for identical numbers of neurons.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"171 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79455681","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967453
Vasiliki Bougou, I. Mporas, P. Schirmer, T. Ganchev
In this paper an architecture for the classification of Schizophrenia using EEG-based brain connectivity is proposed. Functional and effective networks were constructed from the EEG using a variety of connectivity measures and with graph theory metrics complex network features were extracted. Several classification algorithms were used for the evaluation of the architecture. Promising results were observed when using connectivity measures that also capture directionality properties of the network. The best classification accuracy was 82.36% and was achieved by Random Forest classifier with Direct Transfer Function as a connectivity measure.
{"title":"Evaluation of EEG Connectivity Network Measures based Features in Schizophrenia Classification","authors":"Vasiliki Bougou, I. Mporas, P. Schirmer, T. Ganchev","doi":"10.1109/BIA48344.2019.8967453","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967453","url":null,"abstract":"In this paper an architecture for the classification of Schizophrenia using EEG-based brain connectivity is proposed. Functional and effective networks were constructed from the EEG using a variety of connectivity measures and with graph theory metrics complex network features were extracted. Several classification algorithms were used for the evaluation of the architecture. Promising results were observed when using connectivity measures that also capture directionality properties of the network. The best classification accuracy was 82.36% and was achieved by Random Forest classifier with Direct Transfer Function as a connectivity measure.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"124 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75811903","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967450
Kalin Kalinkov, T. Ganchev, V. Markova
We present an adaptive feature selection method that makes use of Fisher’s discriminant ratio (FDR) with flexible threshold which is adjusted in a person-specific manner. The proposed method is shown to improve the detection of high-arousal negative-valence (HANV) conditions, based on two combinations of physiological signals (ECG+GSR and PPG+GSR). We validate the proposed method in an experimental setup aiming at the automated detection of HANV conditions evoked by audio-visual stimuli and picture stimuli. The experimental results support that the proposed method yields to an improvement of the classification accuracy of an SVM-based detector on average with 5.6%±0.6% in comparison with the traditional non-adaptive FDR-based feature selection using threshold 0.3, and with the full set of 39 features.
{"title":"Adaptive Feature Selection through Fisher Discriminant Ratio","authors":"Kalin Kalinkov, T. Ganchev, V. Markova","doi":"10.1109/BIA48344.2019.8967450","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967450","url":null,"abstract":"We present an adaptive feature selection method that makes use of Fisher’s discriminant ratio (FDR) with flexible threshold which is adjusted in a person-specific manner. The proposed method is shown to improve the detection of high-arousal negative-valence (HANV) conditions, based on two combinations of physiological signals (ECG+GSR and PPG+GSR). We validate the proposed method in an experimental setup aiming at the automated detection of HANV conditions evoked by audio-visual stimuli and picture stimuli. The experimental results support that the proposed method yields to an improvement of the classification accuracy of an SVM-based detector on average with 5.6%±0.6% in comparison with the traditional non-adaptive FDR-based feature selection using threshold 0.3, and with the full set of 39 features.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"22 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81178578","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967451
L. Anishchenko, E. Smirnova
Bioradiolocation is a remote method for biological object vital signs detection. In particular, it may be used for noncontact fall detection in elderly. The present paper considers the combined usage of wavelet transform and deep learning techniques in fall detection by means of bioradar data processing. The time-frequency representation of the bio-radar signal representing the absolute values of the wavelet transform coefficients was used as input data for convolutional neural network. The network architecture of AlexNet has been adapted to solve the problem of detecting falls. The proposed method for the fall – non-fall classification was tested on the data gathered in realistic surrounding conditions by five volunteers. The proposed method has the accuracy of 95 % and Cohen’s kappa of 91 %.
{"title":"Fall Detection with Bioradar Using Wavelet Analysis and Deep Learning","authors":"L. Anishchenko, E. Smirnova","doi":"10.1109/BIA48344.2019.8967451","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967451","url":null,"abstract":"Bioradiolocation is a remote method for biological object vital signs detection. In particular, it may be used for noncontact fall detection in elderly. The present paper considers the combined usage of wavelet transform and deep learning techniques in fall detection by means of bioradar data processing. The time-frequency representation of the bio-radar signal representing the absolute values of the wavelet transform coefficients was used as input data for convolutional neural network. The network architecture of AlexNet has been adapted to solve the problem of detecting falls. The proposed method for the fall – non-fall classification was tested on the data gathered in realistic surrounding conditions by five volunteers. The proposed method has the accuracy of 95 % and Cohen’s kappa of 91 %.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"1 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81846068","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967472
Marinela Petrova, Chavdar Aleksandrov
This report describes, by means of a comparative analysis, the different types of monitoring and information transfer systems, depending on the communication environment. Criteria were evaluated such as: price, scope and coverage of each of the data transmission systems, rapid use of exchange and consumption of need. The application of technical means of communication in wireless sensor networks (WSN) are examined. Communications can be accomplished through GPRS/GSM, AIS (VHF), LoRaWAN, Inmarsat Data Pro, WiFi, Bluetooth - each of these tools has been described and analyzed as a data medium in wireless sensor networks.
本报告通过比较分析，描述了不同类型的监测和信息传递系统，视通信环境而定。评价的标准包括:价格、每个数据传输系统的范围和覆盖范围、交换的迅速使用和需要的消耗。研究了通信技术手段在无线传感器网络中的应用。通信可以通过GPRS/GSM, AIS (VHF)， LoRaWAN, Inmarsat Data Pro, WiFi，蓝牙完成-这些工具中的每一个都被描述和分析为无线传感器网络中的数据媒介。
{"title":"Comparative Analysis of Means of Communication on Wireless Sensor Networks","authors":"Marinela Petrova, Chavdar Aleksandrov","doi":"10.1109/BIA48344.2019.8967472","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967472","url":null,"abstract":"This report describes, by means of a comparative analysis, the different types of monitoring and information transfer systems, depending on the communication environment. Criteria were evaluated such as: price, scope and coverage of each of the data transmission systems, rapid use of exchange and consumption of need. The application of technical means of communication in wireless sensor networks (WSN) are examined. Communications can be accomplished through GPRS/GSM, AIS (VHF), LoRaWAN, Inmarsat Data Pro, WiFi, Bluetooth - each of these tools has been described and analyzed as a data medium in wireless sensor networks.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"5 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87329789","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967449
Satyam Chaturvedi, Amartya Gupta, A. Bhat, Harish Kumar Kamat
Prosthetics are some of the most common and oldest biomechanical devices in use. Upper limb prosthetic used in Congenital Hand differences, which are deficiencies that occur from birth, play a vital role in the functional capabilities of affected individuals. Desirable properties of the prosthetics include, appearance and aesthetics, comfort, and functionality. In this study, a 3D printed prosthesis with a desirable appearance and comfort was used to implement functional modifications to the device. The modifications implemented are that of dorsiflexion and an increase in thumb mobility to the existing device. These modifications are required to make the prosthetic biomechanically accurate in its function and increase its utility to the patient. The changes are designed into the prosthetic and the model is 3D printed to create a device that serves as a proof of concept. The results show that the changes made meet the project objectives. This leaves validation through a clinical study on patients as a future objective. Once this is done, the device can be released to the online community to be used and improved on a global scale.
{"title":"Fucntional Modification of Upper Limb Prosthesis for Below Elbow Congential Deficiencies","authors":"Satyam Chaturvedi, Amartya Gupta, A. Bhat, Harish Kumar Kamat","doi":"10.1109/BIA48344.2019.8967449","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967449","url":null,"abstract":"Prosthetics are some of the most common and oldest biomechanical devices in use. Upper limb prosthetic used in Congenital Hand differences, which are deficiencies that occur from birth, play a vital role in the functional capabilities of affected individuals. Desirable properties of the prosthetics include, appearance and aesthetics, comfort, and functionality. In this study, a 3D printed prosthesis with a desirable appearance and comfort was used to implement functional modifications to the device. The modifications implemented are that of dorsiflexion and an increase in thumb mobility to the existing device. These modifications are required to make the prosthetic biomechanically accurate in its function and increase its utility to the patient. The changes are designed into the prosthetic and the model is 3D printed to create a device that serves as a proof of concept. The results show that the changes made meet the project objectives. This leaves validation through a clinical study on patients as a future objective. Once this is done, the device can be released to the online community to be used and improved on a global scale.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"15 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73281713","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967470
Veselin Atanasov, Yordan Sivkov
In modern life, electronic devices are implement in all areas of life, but one of the most evolving field is medical electronics, which serve to monitor the parameters of the human body, such as peripheral temperature, pulse, ECG, movement dynamics. The introduction of an electronic tool following the parameters of seafarers placed in a risky situation would lead to continuous monitoring and signaling for changes of parameters from nominal values of the human body, early diagnostics of altered cardiovascular function, signs of overload and fatigue, which will allow taking out people from the risk environment.To develop a system for reporting parameters of the human body is proposed architecture and evaluation criteria for specific implementations.
{"title":"Application of a sensor network to measure the characteristics of the human body in shipping","authors":"Veselin Atanasov, Yordan Sivkov","doi":"10.1109/BIA48344.2019.8967470","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967470","url":null,"abstract":"In modern life, electronic devices are implement in all areas of life, but one of the most evolving field is medical electronics, which serve to monitor the parameters of the human body, such as peripheral temperature, pulse, ECG, movement dynamics. The introduction of an electronic tool following the parameters of seafarers placed in a risky situation would lead to continuous monitoring and signaling for changes of parameters from nominal values of the human body, early diagnostics of altered cardiovascular function, signs of overload and fatigue, which will allow taking out people from the risk environment.To develop a system for reporting parameters of the human body is proposed architecture and evaluation criteria for specific implementations.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"67 1","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80324053","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967468
V. Aleksieva, H. Valchanov, A. Huliyan
The insurance business is looking for solutions to minimize its operational costs and time to process claims for losses. Blockchain technology gives advantages such as transaction security, process identification, process automation and payment speed. This paper presents an experimental implementation of smart contracts based on Ethereum blockchain for insurance services. A decentralized crypto-token, based on ERC20 standard for smart contract, is implemented. A web-based interface is created for sales of these crypto-tokens. The results from the experimental tests are presented.
{"title":"Application of Smart Contracts based on Ethereum Blockchain for the Purpose of Insurance Services","authors":"V. Aleksieva, H. Valchanov, A. Huliyan","doi":"10.1109/BIA48344.2019.8967468","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967468","url":null,"abstract":"The insurance business is looking for solutions to minimize its operational costs and time to process claims for losses. Blockchain technology gives advantages such as transaction security, process identification, process automation and payment speed. This paper presents an experimental implementation of smart contracts based on Ethereum blockchain for insurance services. A decentralized crypto-token, based on ERC20 standard for smart contract, is implemented. A web-based interface is created for sales of these crypto-tokens. The results from the experimental tests are presented.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"22 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73355901","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967465
Stavros Nousias, Giwrgos Papoulias, O. Kocsis, M. Cabrita, A. Lalos, K. Moustakas
Current trend of population ageing at global level is accompanied by increased prevalence of chronic diseases and higher rates of early retirement and labor market exit. In particular, the lifestyle of office workers is characterized by prolonged sitting and overall sedentary life, which alone is a high risk factor for cardiometabolic diseases, obesity and other related chronic diseases. The SmartWork unobtrusive monitoring system allows for continuous monitoring of various lifestyle, health, behavioural and work related parameters of office workers targeting to empower work ability sustainability. The large amounts of collected data in such systems are often characterized by the presence of missing entries. This work is an exploratory study on the potential of a Laplacian matrix completion variant for data imputation on the multi-channel time-series data collected with wearable or work devices in the SmartWork system.
{"title":"Coping with missing data in an unobtrusive monitoring system for office workers","authors":"Stavros Nousias, Giwrgos Papoulias, O. Kocsis, M. Cabrita, A. Lalos, K. Moustakas","doi":"10.1109/BIA48344.2019.8967465","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967465","url":null,"abstract":"Current trend of population ageing at global level is accompanied by increased prevalence of chronic diseases and higher rates of early retirement and labor market exit. In particular, the lifestyle of office workers is characterized by prolonged sitting and overall sedentary life, which alone is a high risk factor for cardiometabolic diseases, obesity and other related chronic diseases. The SmartWork unobtrusive monitoring system allows for continuous monitoring of various lifestyle, health, behavioural and work related parameters of office workers targeting to empower work ability sustainability. The large amounts of collected data in such systems are often characterized by the presence of missing entries. This work is an exploratory study on the potential of a Laplacian matrix completion variant for data imputation on the multi-channel time-series data collected with wearable or work devices in the SmartWork system.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"52 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74076895","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 : 2019-11-01DOI: 10.1109/BIA48344.2019.8967467
E. Pencheva, V. Markova, I. Atanasov, T. Ganchev
In many life situations, the reliable transmission of patient health data is an important and critical issue. The multi-connectivity feature of fifth generation (5G) mobile systems is a way to improve reliability, as it enables multiple simultaneous radio links from source to destination. The open access to this Radio Access Network functionality enables external application to manage the connectivity of user devices based on user location, information about radio conditions and level of cell congestion. In this paper, we propose an approach to open access to multi-connectivity using Multi-access Edge Computing.
{"title":"An Approach to Improve Reliability of Vital Signs Monitoring","authors":"E. Pencheva, V. Markova, I. Atanasov, T. Ganchev","doi":"10.1109/BIA48344.2019.8967467","DOIUrl":"https://doi.org/10.1109/BIA48344.2019.8967467","url":null,"abstract":"In many life situations, the reliable transmission of patient health data is an important and critical issue. The multi-connectivity feature of fifth generation (5G) mobile systems is a way to improve reliability, as it enables multiple simultaneous radio links from source to destination. The open access to this Radio Access Network functionality enables external application to manage the connectivity of user devices based on user location, information about radio conditions and level of cell congestion. In this paper, we propose an approach to open access to multi-connectivity using Multi-access Edge Computing.","PeriodicalId":6688,"journal":{"name":"2019 International Conference on Biomedical Innovations and Applications (BIA)","volume":"93 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74121139","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：