2021 23rd International Conference on Control Systems and Computer Science (CSCS)最新文献

Working with Datasets: Experience from Research Projects 使用数据集:来自研究项目的经验

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00072

F. Pop, C. Dobre, E. Apostol, Radu-Ioan Ciobanu, Ciprian-Octavian Truică, Ion-Dorinel Filip, Catalin Negru

引用次数: 1

New opportunities for older adults care transition from traditional to personalised assistive care: vINCI platform 老年人护理从传统到个性化辅助护理的新机遇:vINCI平台

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00090

C. Dobre, Lidia Bajenaru, Ion Alexandru Marinescu, M. Tomescu, G. Prada, S. Spinsante

{"title":"New opportunities for older adults care transition from traditional to personalised assistive care: vINCI platform","authors":"C. Dobre, Lidia Bajenaru, Ion Alexandru Marinescu, M. Tomescu, G. Prada, S. Spinsante","doi":"10.1109/CSCS52396.2021.00090","DOIUrl":"https://doi.org/10.1109/CSCS52396.2021.00090","url":null,"abstract":"Today, we are witnessing profound changes in the provision of healthcare services, shifting from illness-centred systems to patient-centred ones, able to deliver a personalised and integrated experience. This new approach has been generated by the tendencies of recent decades regarding the continuous increase of chronic medical conditions associated with both the modern lifestyle and the accelerated rate of population ageing. Therefore, under the pressure of the three requirements that shape the future of care services (better quality care, improving patient experience and health, while reducing total costs), we are moving towards a new ecosystem-based model of care that incorporates the following key features: permanent innovation, self and continuous care based on emergent technologies (Internet of Things (IoT), Artificial Intelligence, Big data etc.) available nearby or at home, patient engagement, personalised assistance, data and analytics. In this regard, as part of the European research effort, in this paper it is presented a new integrated and validated framework using IoT to provide non-intrusive monitoring and personalised assistance services to older adults: the vINCI platform. This system is a clinically-validated environmental framework, in which several smart devices work together to aggregate a solution able to contribute at the improvement of the older adults' quality of life.","PeriodicalId":399710,"journal":{"name":"2021 23rd International Conference on Control Systems and Computer Science (CSCS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121066564","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}

引用次数: 3

On Complexity and Topology Measures for Evaluation of Intercellular Connectivity in Human Colon Adenocarcinomas 人类结肠腺癌细胞间连通性评价的复杂性和拓扑度量

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00042

P. Waliszewski, Grzegorz Banaszak

{"title":"On Complexity and Topology Measures for Evaluation of Intercellular Connectivity in Human Colon Adenocarcinomas","authors":"P. Waliszewski, Grzegorz Banaszak","doi":"10.1109/CSCS52396.2021.00042","DOIUrl":"https://doi.org/10.1109/CSCS52396.2021.00042","url":null,"abstract":"We report here on the results of co-application of complexity and topological measures in the evaluation of intercellular connectivity; a critical feature of cancer cells that determines their metastatic potential. We studied fractal geometry and topology of intestinal crypts in 10 different specimens of human normal colon and in 40 colon carcinomas. Our findings confirm the previous observations made in a model of prostate carcinomas. The natural evolution of the spatial structure in carcinomas is determined by increasing values of entropy and goes towards increased complexity. Intercellular connectivity in colon carcinomas is decreased in comparison with normal intestinal crypts. That conclusion is supported by changes in both global and local measures of complexity as well as topology. The values of both the global and local spatial fractal dimensions are increased and the values of the 1st-Betti numbers are decreased. At the local scale, one observes variability of the local clustering coefficient from zero to one. The combination of complexity and topology measures enables the objective selection of the reference set of carcinomas for the quantitative evaluation of biological tumor aggressiveness by convoluted neural network.","PeriodicalId":399710,"journal":{"name":"2021 23rd International Conference on Control Systems and Computer Science (CSCS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127123493","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}

引用次数: 0

Human Action Recognition Methods Based on CNNs for RGB Video Input 基于cnn的RGB视频输入人体动作识别方法

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00026

B. Radulescu, A. Florea

{"title":"Human Action Recognition Methods Based on CNNs for RGB Video Input","authors":"B. Radulescu, A. Florea","doi":"10.1109/CSCS52396.2021.00026","DOIUrl":"https://doi.org/10.1109/CSCS52396.2021.00026","url":null,"abstract":"Human Action recognition is a complex problem that attracts more and more researchers from the scientific community due to its applicability in domains such as security and behavior analysis. At its core, this problem entails classifying an action into a finite set of classes. Neural network based approaches, and especially convolutional neural networks, are a good starting point for solving the problem of human action recognition. Due to their nature, they can recognize spatio-temporal features very well, making them ideal for working with sequences of RGB images. In this paper are proposed three types of convolutional neural network architectures that contribute to solving the problem of Human Action Recognition. The first one is based on 2D kernels, the second one on 3D kernels, and the third one on TCN (Temporal Convolutional Network) units. Each one is presented with its structure, advantages and disadvantages, along with metrics that measure their performance. The one based on 2D convolutions is the fastest, but it also has the lowest performances. The second one is a good middle ground, useful in certain situations which require a fast classifier operating on different action classes. Finally, the one based on TCNs performs close to some of the best existent models. It represents a viable solution to the proposed problem. It can classify many actions, using only RGB images of fairly low resolution, in real time. The three models have been tested on the RGB part of the NTU RGB+D dataset. The 2D convolution-based model obtained an accuracy of 7.43% on the Cross-Subject split and 10.28% on the Cross-View split. The 3D convolution-based model obtained 58.77% on Cross Subject and 56.11% on Cross-View. Finally, the TCN-based model obtained an accuracy of 80.45% on Cross-Subject and an accuracy of 82.57% on Cross-View.","PeriodicalId":399710,"journal":{"name":"2021 23rd International Conference on Control Systems and Computer Science (CSCS)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127496145","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}

引用次数: 1

Sharing of Network Flow Data across Organizations using Searchable Encryption 使用可搜索的加密在组织之间共享网络流数据

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00038

Iulia-Maria Florea, Gabriel Ghinita, R. Rughinis

{"title":"Sharing of Network Flow Data across Organizations using Searchable Encryption","authors":"Iulia-Maria Florea, Gabriel Ghinita, R. Rughinis","doi":"10.1109/CSCS52396.2021.00038","DOIUrl":"https://doi.org/10.1109/CSCS52396.2021.00038","url":null,"abstract":"Given that an increasingly larger part of an organization's activity is taking place online, especially in the current situation caused by the COVID-19 pandemic, network log data collected by organizations contain an accurate image of daily activity patterns. In some scenarios, it may be useful to share such data with other parties in order to improve collaboration, or to address situations such as cyber-security incidents that may affect multiple organizations. However, in doing so, serious privacy concerns emerge. One can uncover a lot of sensitive information when analyzing an organization's network logs, ranging from confidential business interests to personal details of individual employees (e.g., medical conditions, political orientation, etc). Our objective is to enable organizations to share information about their network logs, while at the same time preserving data privacy. Specifically, we focus on enabling encrypted search at network flow granularity. We consider several state-of-the-art searchable encryption flavors for this purpose (including hidden vector encryption and inner product encryption), and we propose several customized encoding techniques for network flow information in order to reduce the overhead of applying state-of-the-art searchable encryption techniques, which are notoriously expensive.","PeriodicalId":399710,"journal":{"name":"2021 23rd International Conference on Control Systems and Computer Science (CSCS)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126063584","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}

引用次数: 1

Clean Code - Delivering A Lightweight Course 干净的代码-提供一个轻量级的课程

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00075

Alexandru Chirvase, Laura Ruse, Mihnea Muraru, M. Mocanu, Vlad Ciobanu

引用次数: 1

Context Awareness in Enterprise Systems Design 企业系统设计中的上下文感知

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00053

E. Oprea, M. Moisescu, S. Caramihai

引用次数: 1

Towards the development of a medical rehabilitation system 走向医疗康复体系的发展

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00091

Veronica Gavrila, Lidia Bajenaru, C. Dobre

引用次数: 1

Quantification of Collagen IV in Normal, Potentially Malignant and Malignant lesions of the Oropharynx: A Pilot Study 口咽部正常、潜在恶性和恶性病变中IV型胶原蛋白的定量:一项初步研究

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00041

Prarthna Clare, Kristine Nellany, R. Eid

{"title":"Quantification of Collagen IV in Normal, Potentially Malignant and Malignant lesions of the Oropharynx: A Pilot Study","authors":"Prarthna Clare, Kristine Nellany, R. Eid","doi":"10.1109/CSCS52396.2021.00041","DOIUrl":"https://doi.org/10.1109/CSCS52396.2021.00041","url":null,"abstract":"The incidence of oropharyngeal cancer is on the rise which is attributed to an increase in human papilloma virus (HPV) infections. HPV positive oropharyngeal carcinomas have a very different outcome to HPV negative malignancies and are therefore considered a separate disease entity. Some oropharyngeal lesions are preceded by dysplastic lesions; however, the behaviour of such lesions is unpredictable. In this pilot study, we aimed at assessing the distribution and morphology of collagen type IV expression, which is one of the constituents of blood vessel basement membrane, in the connective tissue of normal, potentially malignant and malignant oropharyngeal lesions. Histological sections were stained for collagen type IV using immunohistochemistry and scanned to obtain digital images. ImageJ was used to assess the distribution of collagen type IV positive particles using fractal geometry and to compare different morphometric parameters. Our data compared changes in the spatial distribution, size and shape of collagen type IV positive “particles” between normal, potentially malignant and malignant oropharyngeal tissues. Additionally, we compared these parameters between HPV positive and HPV negative oropharyngeal carcinoma samples. The observed patterns are indicative of changes in blood vessel formation and organisation associated with disease progression in the oropharynx. Quantification of changes in blood vessels is important from a clinical point of view as it enhances our understanding of the disease process and could aid in predicting disease progression, behaviour and potentially inform the development of new methods for drug delivery.","PeriodicalId":399710,"journal":{"name":"2021 23rd International Conference on Control Systems and Computer Science (CSCS)","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130670618","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}

引用次数: 1

Condition Monitoring of Manufacturing Production Lines Using Fractal Analysis of Energy Consumption Datasets 基于能耗数据集分形分析的制造业生产线状态监测

2021 23rd International Conference on Control Systems and Computer Science (CSCS) Pub Date : 2021-05-01 DOI: 10.1109/CSCS52396.2021.00048

Viorel Mihai, Cristian Dragana, D. Popescu, L. Ichim

引用次数: 0