{"title":"On the Properties of the System Mismatch Covariance Matrix in the LMS Adaptive Algorithm","authors":"Laura-Maria Dogariu, S. Ciochină, C. Paleologu","doi":"10.1109/ICCOMM.2018.8430137","DOIUrl":"https://doi.org/10.1109/ICCOMM.2018.8430137","url":null,"abstract":"Ahstract-The system mismatch covariance matrix is of major interest in some of the optimization approaches of the least-mean-square type adaptive algorithms. Some examples are the ones based on the Kalman filtering theory, or the variable step-size algorithms based on the minimization of the mean square system mismatch. All of them require information about this specific matrix. The usual assumption is to approximate this matrix with a scaled unity one. This paper analyzes the validity conditions of this assumption. Simulation results support the theoretical findings.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124050456","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":"Deep Convolutional Neural Networks Versus Multilayer Perceptron for Financial Prediction","authors":"V. Neagoe, Adrian-Dumitru Ciotec, G. Cucu","doi":"10.1109/iccomm.2018.8484751","DOIUrl":"https://doi.org/10.1109/iccomm.2018.8484751","url":null,"abstract":"This paper presents a new approach to apply and evaluate Deep Learning (DL) Convolutional Neural Networks (CNN) versus Multilayer Perceptron (MLP) for financial prediction. We have designed and evaluated a credit scoring model based on neural network classifiers in two variants: (a) MLP with eight layers; (b) DCNN with thirteen layers (six main layers and seven secondary layers). The experiments have used the German credit dataset and the Australian credit dataset. The model performances are evaluated by the following indices: Overall Accuracy (OA); False Alarm Rate (FAR); Missed Alarm Rate (MAR). The experimental results have confirmed the effectiveness of the proposed approach, pointing out the significant advantage of DCNN over the MLP. For German credit dataset, the DCNN leads to the best OA of 90.85%, versus the corresponding best MLP performance of only 81.20%. For Australian credit dataset, the DCNN has led to the best OA of 99.74%, while the MLP has obtained the best corresponding OA of 90.75%.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116023895","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":"5G Fixed Wireless Access-Mobile Operator Perspective","authors":"E. Oproiu, Iulian Gimiga, I. Marghescu","doi":"10.1109/iccomm.2018.8484810","DOIUrl":"https://doi.org/10.1109/iccomm.2018.8484810","url":null,"abstract":"Nowadays the demand of capacity, performance and reliability for telecommunications services is increasing a lot. The telecom operators are facing with the increasing traffic demand, new solutions in their network to accommodate the growth must be found. One solution could be the use of 5G Fixed Wireless Access to deliver to the customers a fast and affordable broadband service with a very high performance, more capacity for data traffic, greater download speeds and low latency. In this paper we will provide an overview of such a FWA solution; main advantages, technical characteristics, used spectrum, high level depiction of such system. For the creation of this we've analyzed existing studies and trials that have been performed on this solution, around the globe. Our interest in this solution is high mainly as we see this as an opportunity to achieve convergence fixed mobile in an easier way and secondly as this summer we will be part of the first multi-vendor 5G fixed wireless access customer trial in Europe, here in Romania. Orange Romania will collaborate with Orange Group, Samsung Electronics and Cisco on this 5G millimeter wave trial. The trial will be in the second half of 2018, across multiple homes in Romania.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"726 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116981429","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}
Haitao Zhao, Qiangjian Dong, Luo Chen, Yongxiang Liu, Honghu Hua
{"title":"Offloading Channel Allocation to Terminals in High-Density IoTs for Next Generation Networks","authors":"Haitao Zhao, Qiangjian Dong, Luo Chen, Yongxiang Liu, Honghu Hua","doi":"10.1109/iccomm.2018.8484836","DOIUrl":"https://doi.org/10.1109/iccomm.2018.8484836","url":null,"abstract":"Machine-to-Machine (M2M) communications in high-density Internet of Things (IoTs) pose significant challenges in accessing the wireless channel for concurrent transmissions. In this scenario, the channel allocation plays a crucial role, which usually involves a centralized coordination (such as a base station). With the increasing number of edge terminals as well as the dynamic network environment, the computation and information exchange for the centralized channel allocation would be a big burden for the coordination. In this paper, we tackle this challenging problem by proposing a distributed channel allocation method with blind rendezvous to enable collision-free concurrent transmission over multiple channels. Specifically, we first present a receiver-oriented channel allocation algorithm to reduce interference and then focus on a receiver-wait sender-jump blind channel rendezvous algorithm based on channel hopping techniques. The proposed channel allocation method allows each sender-receiver pair to obtain an appropriate channel for transmission without interfering other pairs, in a distributed manner. This study may help network researchers to contribute in the development of next generation high-density IoTs.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125427274","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":"Human and Artificial Intelligence Driven Incentive-Operation Model and Algorithms for a Multi-Purpose Integrated Crowdsensing-Crowdsourcing Scalable System","authors":"V. Greu, Petrica Ciotirnae, L. Tuta, F. Popescu","doi":"10.1109/iccomm.2018.8484793","DOIUrl":"https://doi.org/10.1109/iccomm.2018.8484793","url":null,"abstract":"The future sensing systems seem to need more performant crowdsensing, using highest technologies as artificial intelligence, but being also more complex by volunteer participation and progressively changing from crowdsensing to crowdsourcing. Our work main idea is to use human/artificial intelligence in order to provide highest incentives arguments and commitments for participants and users, transforming data into information and eventually in knowledge. The human/artificial intelligence support is used first to find the most desired/used tasks/targets/questions/issues, then to control the crowdsensing/crowdsourcing operation with learned artificial intelligence rules, based on two algorithms, first for implementing an optimal efficiency tasks covering strategy as reference and second for attracting participants to enlarge/improve accuracy of service by extending crowdsensing-crowdsourcing with correlation incentive/operation added features.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125561878","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":"Characterization of Volterra Kernels for RF Power Amplifiers Using a Two-Tone Signal and a Large-Signal","authors":"M. Alizadeh, D. Rönnow, P. Händel","doi":"10.1109/iccomm.2018.8484805","DOIUrl":"https://doi.org/10.1109/iccomm.2018.8484805","url":null,"abstract":"The 3rd-order Volterra kernels of a radio frequency (RF) power amplifier (PA) are characterized using a large-signal and a two-tone probing-signal. In this technique, the magnitude and phase asymmetries of the kernels of the PA excited by the probing-signal are analyzed in different amplitude regions of the large-signal. The device under test is a class-AB PA operating at 2.14 GHz. The maximum sweeping frequency space of the probing-signal is 20 MHz. The results indicate that the Volterra kernels of the PA show different behaviors (frequency dependency and asymmetry) in different regions.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126633550","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":"Performance Evaluation of a Tracking Algorithm for Galileo E1 Signals","authors":"Alexandru Rusu Casandra, A. Paun","doi":"10.1109/iccomm.2018.8484774","DOIUrl":"https://doi.org/10.1109/iccomm.2018.8484774","url":null,"abstract":"Global Navigation Satellite System (GNSS) receivers are currently the standard equipment for precision positioning, navigation and timing, but their use in challenging environments, such as urban and natural canyons, is made difficult due to reduced Line of Sight visibility, multipath propagation conditions or RF interference from nearby sources. In the next years, given the announced plans of GNSS operators, the number of satellites will increase to more than 120 - with even more signals and frequencies. Today there are more than 70 operational GNSS satellites in orbit from several GNSS systems, transmitting a variety of signals on multiple frequencies. A multi-constellation receiver could benefit from the large envisioned number of visible satellites, especially in urban canyons and industrial areas with very tall obstacles, where only satellites at high elevations are in line of sight with the receiver, but this assumption is valid only if the receiver can actually acquire and track the respective satellite signals. This is hard to attain in difficult signal conditions with single-constellation receivers: if one or more signals are lost because of obstacles or interferences, the receiver might not be able to determine the position, in case less than four valid pseudoranges are available. This paper describes a tracking algorithm implemented in Mathworks Matlab for Galileo El Open Service. After an overview of the state of the art, the work evaluates the performance obtained through Matlab simulations, such as the variation of the correlator replicas and of the local carrier frequency. Conclusion are drawn about the capability of the loop to track the Galileo El signal at different SNR values that may be encountered in real-life situations.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125722549","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":"Transmitter Adaptation in Cognitive Radio Systems and Applications to Cognitive Radar","authors":"D. Popescu, O. Popescu","doi":"10.1109/ICCOMM.2018.8430150","DOIUrl":"https://doi.org/10.1109/ICCOMM.2018.8430150","url":null,"abstract":"The paper presents transmitter adaptation through interference avoidance (IA) for enabling more efficient use of the frequency spectrum in emerging cognitive radio (CR) systems. IA is introduced in a general signal space framework as a procedure that mitigates interference and improves the signal-to-interference+noise ratio (SINR) at the intended receiver by distributing the transmitted signal energy over signal dimensions with minimum interference. Application of IA for transmitter adaptation is illustrated in the context of spectral shaping for OFDM-based CR systems as well as SINR-based waveform design for cognitive radar for estimating the characteristics of multiple mutually interfering targets.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125923777","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":"Integrating Software Defined Networks with Traditional Hardware Networks","authors":"Ionuţ-Mihai Radu, Petrica Ciotirnae, F. Popescu","doi":"10.1109/ICCOMM.2018.8453729","DOIUrl":"https://doi.org/10.1109/ICCOMM.2018.8453729","url":null,"abstract":"This paper describes the behavior of software defined networking components connected through traditional hardware equipment and the compatibility between software elements combined with hardware elements. In order to study the compatibility of the two types of networks, two methods are proposed using switching hardware and router hardware. The readings made for each method present data packaging, packet processing delays, and the time it takes for the data to be transferred through the network. In the paper will be presented the differences between the virtual switches and the real hardware components of the network.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122529424","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}
S. Carata, V. Ghenescu, M. Ghenescu, Mihai Chindea, Roxana Mihaescu
{"title":"Salt and Pepper Noise Removal by Combining Genetic Algorithms - Neural Networks and Statistical Methods","authors":"S. Carata, V. Ghenescu, M. Ghenescu, Mihai Chindea, Roxana Mihaescu","doi":"10.1109/ICCOMM.2018.8430175","DOIUrl":"https://doi.org/10.1109/ICCOMM.2018.8430175","url":null,"abstract":"This paper presents an innovative method for salt and pepper noise removal, by combining neural networks, evolutive and statistical methods. The neural network used to detect the pixels affected by noise is Pulse Coupled Neural Network, whose parameters have been optimized using a Genetic Algorithm. The pixels that are affected by noise are corrected using a Gaussian Kernel. This algorithm proves to be a very efficient method of removing salt and pepper noise from images without compromising the quality of the unaffected pixels. The method has been tested on images from the Mars rover. These tests show how the image retains fine details of the scene even if the noise levels are high.","PeriodicalId":158890,"journal":{"name":"2018 International Conference on Communications (COMM)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122074338","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}