M. Almalchy, Sarmad Monadel Sabree Al-Gayar, N. Popescu
{"title":"Atrial Fibrillation Automatic Diagnosis Based on ECG Signal Using Pretrained Deep Convolution Neural Network and SVM Multiclass Model","authors":"M. Almalchy, Sarmad Monadel Sabree Al-Gayar, N. Popescu","doi":"10.1109/COMM48946.2020.9141994","DOIUrl":"https://doi.org/10.1109/COMM48946.2020.9141994","url":null,"abstract":"The paper presents a robust deep learning approach for ECG automatic diagnose. For this purpose, Deep Convolution Neural Network (D-CNN) algorithm and a multiclass model for SVM classifier will automate the detection process of ECG images specific to atrial fibrillation cases. In this research work, a pre-built and pre-trained D-CNN model is developed. It applies transfer learning which has been proved as a robust technique for computer vision. The early layers of convolutional network are frozen and only the last few layers are trained, identifying objects in images either through a database search or through real-time analysis and detection of the fetched image. Further, the study includes a comparison between the results of using data augmentation techniques and the results without using it. We achieved an average 99.21% of accuracy. The implementation environment of our work is based on MATLAB using Deep Network Designer toolbox.","PeriodicalId":405841,"journal":{"name":"2020 13th International Conference on Communications (COMM)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133277270","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}
Adriana Molder, C. Molder, I. Vizitiu, D. Mischianu, S. Dumitrescu
{"title":"Stroke Risk Assessment Using Atheroma Plaque Surface Features Evaluation","authors":"Adriana Molder, C. Molder, I. Vizitiu, D. Mischianu, S. Dumitrescu","doi":"10.1109/COMM48946.2020.9142016","DOIUrl":"https://doi.org/10.1109/COMM48946.2020.9142016","url":null,"abstract":"The purpose of this article is to obtain a fully automatic procedure for atheroma plaques surface characterization in order to prevent stroke. Stroke risk probability can be estimated by comparing many factors such as blood pressure, blood cholesterol, smoking, overweight, sedentary life, stress and heredity, but all these are only increasing probabilities. This article proposes a new method for classifying patients in three risk categories based on the evaluation of features extracted from the ultrasound images of atheroma plaque surface. The advantage of this method is a more precise estimation of the risk based on the current status of the patient. Moreover, this noninvasive technique has a great advantage over other methods that require biopsy.","PeriodicalId":405841,"journal":{"name":"2020 13th International Conference on Communications (COMM)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122384157","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}
Mihai Dogariu, Liviu-Daniel Stefan, M. Constantin, B. Ionescu
{"title":"Human-Object Interaction: Application to Abandoned Luggage Detection in Video Surveillance Scenarios","authors":"Mihai Dogariu, Liviu-Daniel Stefan, M. Constantin, B. Ionescu","doi":"10.1109/COMM48946.2020.9141973","DOIUrl":"https://doi.org/10.1109/COMM48946.2020.9141973","url":null,"abstract":"CCTV systems bring numerous advantages to security systems, but they require notable efforts from human operators in case of alarming events in order to detect the precise triggering moments. This paper proposes a system that can automatically trigger alarms when it detects abandoned luggage, detects the person that left the baggage and then tracks the suspicious person throughout the perimeter covered by a CCTV system. The system is based on Mask R-CNN and has been tested with several backbone configurations. Wee valuate each subsystem independently on datasets specific for their task. The network model proves to be robust enough to carry on all of the three different tasks as demonstrated by tests.","PeriodicalId":405841,"journal":{"name":"2020 13th International Conference on Communications (COMM)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124564104","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}
Veronica Gavrila, Lidia Bajenaru, M. Tomescu, C. Dobre
{"title":"Security Measures Analysis Related to Intellit Platform","authors":"Veronica Gavrila, Lidia Bajenaru, M. Tomescu, C. Dobre","doi":"10.1109/COMM48946.2020.9141977","DOIUrl":"https://doi.org/10.1109/COMM48946.2020.9141977","url":null,"abstract":"This research presents an analysis over the most common cyber-attacks, the vulnerabilities that they depend on and the possible mitigation solutions together with the complementary implementation of one or multiple proposed solutions in the INTELLIT platform. This platform will contribute for preserving and highlighting the Romanian literary heritage. The analysis presents applied solutions for the software level and own application code. We present some general security practices, as well as measures taken in each particular case of vulnerability and adding also a few generic tips to increase the protection against malicious attacks.","PeriodicalId":405841,"journal":{"name":"2020 13th International Conference on Communications (COMM)","volume":"1720 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129333083","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}
{"title":"OpenNIG - Open Neural Image Generator","authors":"Andrei-Marius Avram, Luciana Morogan, Stefan-Adrian Toma","doi":"10.1109/COMM48946.2020.9142009","DOIUrl":"https://doi.org/10.1109/COMM48946.2020.9142009","url":null,"abstract":"Generative models are statistical models that learn a true underlying data distribution from samples using unsupervised learning, aiming to generate new data points with some variation. In this paper, we introduce OpenNIG (Open Neural Image Generator), an open-source neural networks toolkit for image generation. It offers the possibility to easily train, validate and test state of the art models. The framework also contains a module that enables the user to directly download and process some of the most common databases used in deep learning. OpenNIG is freely available via GitHub.","PeriodicalId":405841,"journal":{"name":"2020 13th International Conference on Communications (COMM)","volume":"529 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132967340","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}