M. Maliosz, Csaba Simon, David Balla, A. Ngo, Daniel Gehberger
{"title":"Scaling in OpenStack Using Client Feedback","authors":"M. Maliosz, Csaba Simon, David Balla, A. Ngo, Daniel Gehberger","doi":"10.1109/TSP.2018.8441221","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441221","url":null,"abstract":"Horizontal scaling in cloud systems provides adaptation in the virtual infrastructure of the services according to the changing loads. By automatic scaling the system reacts based on measured metrics regarding the operational properties of the virtual infrastructure, however, it is not easy to decide when to initiate the scaling. This paper evaluates CPU utilization based automatic scaling and proposes a new method where direct feedback from the clients is incorporated into the decision when a scaling operation has to be started. We demonstrate the usability of this new method in a Video on Demand service case study. We show that using client feedback on the perceived playback quality supports more accurate decision making when to scale, avoiding unnecessarily scale out events that also leads to cost savings.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129091002","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}
M. Minea, Răzvan Andrei Gheorghiu, V. Iordache, M. Surugiu, Mihai Dima
{"title":"A Survey on ZigBee Communications Efficiency for Subway Additional Services","authors":"M. Minea, Răzvan Andrei Gheorghiu, V. Iordache, M. Surugiu, Mihai Dima","doi":"10.1109/TSP.2018.8441391","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441391","url":null,"abstract":"Subway transportation is very efficient in crowded cities. The subway infrastructure and interlocking equipment are exploited on a continuous basis and there remains short time intervals for revisions. A solution to this problem would be the usage of robotic carts, having different embedded sensors and capable of transmitting live data regarding different safety parameters measured. In this paper we investigate possible usability of ZigBee communications in tunnels for this application. A series of experimental tests have been performed in different conditions on M4 line in Bucharest subway mainline and comparative results are presented in this paper.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122196351","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}
I. Mocanu, Dana Axinte, O. Cramariuc, B. Cramariuc
{"title":"Human Activity Recognition with Convolution Neural Network Using TIAGo Robot","authors":"I. Mocanu, Dana Axinte, O. Cramariuc, B. Cramariuc","doi":"10.1109/TSP.2018.8441486","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441486","url":null,"abstract":"This paper presents a two layer convolutional neural network for performing activity recognition. We combine spatial and temporal information extracted from images acquired from RGB cameras. Spatial information are extracted from videos by splitting them into RGB channel frames and do a one frame at a time classification. Temporal information from videos are extracted by computing their optical flow. The results are combined in order to build a real time human activity recognition system. The network is tested using TIAGo robot for performing activity recognition. The accuracy of the system is 87,05 %, that is comparable with the state of the art. Also, results are obtaining in real time.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122220143","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":"Impact of Segment Size and Parallel Streams on TCP BBR","authors":"J. Crichigno, Zoltan Csibi, E. Bou-Harb, N. Ghani","doi":"10.1109/TSP.2018.8441250","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441250","url":null,"abstract":"TCP BBR has been recently proposed as a congestion control algorithm. BBR represents a disruption from the window-based loss-based congestion control used during the last 30 years. While BBR has been tested for trivial applications (e.g., browsing, YouTube), its use for moving big data has not been extensively studied yet. Features that largely impact the efficiency of transporting big flows are the use of parallel streams and the maximum segment size (MSS). This paper studies the impact of these two features on big flows, in the presence of packet losses and latency. Empirical results demonstrate that BBR reacts better than window-based loss-based algorithms (Cubic, Reno, HTCP) to large MSS. Similarly, as the number of parallel streams used in a data transfer increases, the performance gap between BBR and Cubic, Reno, and HTCP increases in favor of BBR. For example, in a 20-millisecond RTT, 10 Gbps network with high corruption rate (0.01%), BBR's average improvement factor from using multiple streams is almost 4. In contrast, HTCP's, Cubic's, and Reno's improvement factors are below 2. Using large MSS and parallel streams permit BBR to sustain high throughput, even in the presence of a significant corruption rate.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116623480","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}
Georgian Nicolae, A. Gaita, A. Radoi, C. Burileanu
{"title":"A Method for Chainsaw Sound Detection Based on Haar-like Features","authors":"Georgian Nicolae, A. Gaita, A. Radoi, C. Burileanu","doi":"10.1109/TSP.2018.8441379","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441379","url":null,"abstract":"Illegal deforestation has long been a major environmental issue causing climate changes, flooding, landslides, global warming, species extinction, etc. This paper deals with the detection of actively-cutting chainsaw for the efficient real-time monitoring of forest areas. As a solution to this problem, we propose a novel technique based on the extraction of 2D Haar wavelet coefficients from the spectrogram of environmental sounds. Considering an accuracy of 97%, our method can be used to develop a good detection system for preventing the illegal logging.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116776362","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}
Plamen T. Semov, P. Koleva, Nikolay Dandanov, V. Poulkov, Oleg Asenov
{"title":"Performance Optimization in Heterogeneous Wireless Access Networks Based on User Heat Maps","authors":"Plamen T. Semov, P. Koleva, Nikolay Dandanov, V. Poulkov, Oleg Asenov","doi":"10.1109/TSP.2018.8441319","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441319","url":null,"abstract":"In this paper an approach for dynamic and proactive performance optimization in dense and dynamic heterogeneous wireless access networks taking into consideration the user distribution, mobility and activity is proposed. The approach is based on building up User Heat Maps (UHM) in consecutive time slots for a given area and predicting the map state in the next time slot. To avoid storage of big volumes of data and computational complexity and to ensure real-time operation the prediction is based on a Neural Network (NN) architecture utilizing the data from UHM. The approach is demonstrated with a scenario for optimizing the overall cell throughput based on controlling the electrical tilt of the antenna at the serving access node. The simulation results show that such an approach could lead to performance improvement in dense and dynamic heterogeneous access networks characterized by frequent changes in user activity and mobility.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134098816","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":"Sparse Depth Map Interpolation using Deep Convolutional Neural Networks","authors":"Ilya Makarov, A. Korinevskaya, Vladimir Aliev","doi":"10.1109/TSP.2018.8441443","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441443","url":null,"abstract":"The problem of dense depth map inference from sparse depth values is considered in this paper. We address this issue in situation when one has low-cost sensor data and limited computational resources. We propose a method that performs interpolation and then super-resolution while comparing our approach with the state-of-the-art direct RGB-to-Dense reconstruction solutions. In particular, we use an encoder-decoder model of CNN with loss consisting of standard mean squared error and perceptual loss function. Futhermore, it has been shown that the described approach could be adopted to estimate rough depth map in real-time.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133179740","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":"Investigation of the Neural Network Model for Security and Quality of Service for a Multi-Cloud System in Virtual Data Center","authors":"D. Parfenov, I. Bolodurina","doi":"10.1109/TSP.2018.8441435","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441435","url":null,"abstract":"In this study, a prototype of an autonomous system was developed and investigated to provide cyber security and quality of service for multi-cloud platforms. Based on the developed system is a mathematical model of traffic analysis. The mathematical model is based on the neural network. A hybrid neural network based on a multi-layer perceptron and a self-organizing Kohonen network was designed. This approach allowed to more accurately classify and detect malicious traffic. The conducted experimental researches have shown that using the proposed approach allows to increase the effectiveness of detection of such attacks as denial of service. At the same time, during the attack, the required quality of service is maintained in the multi-cloud platform network.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132162071","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":"An Adaptive Offloading Decision Scheme in Two-Class Mobile Edge Computing Systems","authors":"Kahlan Aljobory, Mehmet Akif Yazici","doi":"10.1109/TSP.2018.8441475","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441475","url":null,"abstract":"We propose an adaptive offloading decision algorithm for mobile edge computing (MEC) systems based on minimization of task sojourn time where the MEC server uses a weighted round-robin scheduler. In this setting, we define high-and low-class mobile users, where high-class users get better service.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132172834","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":"Prediction of Estimates' Accuracy for Linear Regression with a Small Sample Size","authors":"V. Fursov, A. Gavrilov, A. Kotov","doi":"10.1109/TSP.2018.8441385","DOIUrl":"https://doi.org/10.1109/TSP.2018.8441385","url":null,"abstract":"We consider the problem of linear regression in the case of an extremely small sample size. It is difficult to obtain good estimates of model parameters and confidence interval in this case. We develop an approach based on the conformity estimation principle. Within this approach we form a set of subsystems with square matrixes and calculate a set of estimates for them. Then we choose a subsystem from initial system for which these estimates mutually the closest (function of mutual proximity is minimum). Then, we calculate a final estimate on this subsystem. We also used the mutual conformity function to predict the estimate's accuracy. Our approach is based on the assumption that there is a relationship between the estimation errors and values of the mutual conformity function. That is a new view on the problem of small sample size confidence intervals.","PeriodicalId":383018,"journal":{"name":"2018 41st International Conference on Telecommunications and Signal Processing (TSP)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133821726","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}