Pub Date : 2021-11-24DOI: 10.1109/urucon53396.2021.9647233
Carolina Allende, Efrain Buksman, A. F. De Oliveira
This work introduces a novel structure based on universal quantum circuits which uses classical machine learning techniques in order to solve a quantum problem: the decomposition of a generic quantum operator into a sequence of elementary unitary matrices (universal basic quantum gates). Even though the postulates of quantum mechanics guarantee any unitary operation as a feasible operation over a quantum system, there is no simple method to implement an arbitrary algorithm. By means of a multilayer hybrid neural network in which the basic cell is made up of CNOTs and universal one-qubit unitary gates, this work offers a solution to the given problem. These specific gates were chosen since they are the gates available in real quantum computers such as IBMQ's quantum processors. The network learns the unitary gates classically using the method of the steepest descent and is aided in learning the entangling gates by the use of two types of quantum correlations: Mutual Information (MI) and Cumulative Correlation Measure (CCM). The algorithm implemented in this case is a type of supervised learning. The results show that the model fits the data gracefully and correctly predicts a wide range of algorithms.
{"title":"Quantum circuit design using neural networks assisted by entanglement","authors":"Carolina Allende, Efrain Buksman, A. F. De Oliveira","doi":"10.1109/urucon53396.2021.9647233","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647233","url":null,"abstract":"This work introduces a novel structure based on universal quantum circuits which uses classical machine learning techniques in order to solve a quantum problem: the decomposition of a generic quantum operator into a sequence of elementary unitary matrices (universal basic quantum gates). Even though the postulates of quantum mechanics guarantee any unitary operation as a feasible operation over a quantum system, there is no simple method to implement an arbitrary algorithm. By means of a multilayer hybrid neural network in which the basic cell is made up of CNOTs and universal one-qubit unitary gates, this work offers a solution to the given problem. These specific gates were chosen since they are the gates available in real quantum computers such as IBMQ's quantum processors. The network learns the unitary gates classically using the method of the steepest descent and is aided in learning the entangling gates by the use of two types of quantum correlations: Mutual Information (MI) and Cumulative Correlation Measure (CCM). The algorithm implemented in this case is a type of supervised learning. The results show that the model fits the data gracefully and correctly predicts a wide range of algorithms.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"262 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133355934","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647292
Jefferson Yallico Tapia, D. Avila-Pesantez
Versatility is the main intrinsic characteristic of Blockchain, making this technology applicable to a great variety of fields such as Agriculture, Healthcare, Artificial Intelligence, Smart Cities, and many others, all of them within the Internet of Things environment and aimed to its integration. This paper presents a detailed review of IoT fields in which Blockchain is currently being applied, the challenges they face towards their integration, and the current role of Blockchain concerning the security environment. The authors used inclusion and exclusion criteria, and as a result, 164 articles ranging from 2018 to 2021 were utilized to fulfill this objective. Additionally, the authors found 11 environments where Blockchain is being integrated. Moreover, a quantitative study was carried out to determine which of the challenges are the focus of attention.
{"title":"Blockchain and IoT - Challenges and Its Role in Security: A Brief Overview","authors":"Jefferson Yallico Tapia, D. Avila-Pesantez","doi":"10.1109/urucon53396.2021.9647292","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647292","url":null,"abstract":"Versatility is the main intrinsic characteristic of Blockchain, making this technology applicable to a great variety of fields such as Agriculture, Healthcare, Artificial Intelligence, Smart Cities, and many others, all of them within the Internet of Things environment and aimed to its integration. This paper presents a detailed review of IoT fields in which Blockchain is currently being applied, the challenges they face towards their integration, and the current role of Blockchain concerning the security environment. The authors used inclusion and exclusion criteria, and as a result, 164 articles ranging from 2018 to 2021 were utilized to fulfill this objective. Additionally, the authors found 11 environments where Blockchain is being integrated. Moreover, a quantitative study was carried out to determine which of the challenges are the focus of attention.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"123 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124185660","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647240
Wilson De Souza Junior, Victor Croisfelt, T. Abrão
Rate-splitting multiple access (RSMA) combines the concepts of non-orthogonal multiple access (NOMA) and space-division multiple access (SDMA) to provide higher sum-rates (SRs). In particular, one-layer RSMA splits the users' message into two parts: a single common message for all users and a private message for each user. In this work, we consider the problem of maximizing the downlink (DL) energy efficiency (EE) for one-layer RSMA subject to specific quality of service (QoS) constraints and under consideration of a single-input single-output (SISO) system. The solution to this multi-objective problem depends on finding: i) the optimal DL transmit powers, ii) the optimal rate allocation, and iii) the optimal radio frequency (RF) transmit power that must be selected by the base station (BS) so as to obtain the best EE. Thus, we decouple the original problem into three sub-problems that find each part of the solution sequentially. We take advantage of an earlier solution available in the literature for the first two decoupled sub-problems and extend it to an algorithm that maximizes the EE. Numerical results demonstrate consistent performance bounds of our proposed algorithm to the optimal EE values, comparing them to NOMA and orthogonal multiple access (OMA) solutions.
{"title":"On the Energy Efficiency of One-Layer SISO Rate-Splitting Multiple Access","authors":"Wilson De Souza Junior, Victor Croisfelt, T. Abrão","doi":"10.1109/urucon53396.2021.9647240","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647240","url":null,"abstract":"Rate-splitting multiple access (RSMA) combines the concepts of non-orthogonal multiple access (NOMA) and space-division multiple access (SDMA) to provide higher sum-rates (SRs). In particular, one-layer RSMA splits the users' message into two parts: a single common message for all users and a private message for each user. In this work, we consider the problem of maximizing the downlink (DL) energy efficiency (EE) for one-layer RSMA subject to specific quality of service (QoS) constraints and under consideration of a single-input single-output (SISO) system. The solution to this multi-objective problem depends on finding: i) the optimal DL transmit powers, ii) the optimal rate allocation, and iii) the optimal radio frequency (RF) transmit power that must be selected by the base station (BS) so as to obtain the best EE. Thus, we decouple the original problem into three sub-problems that find each part of the solution sequentially. We take advantage of an earlier solution available in the literature for the first two decoupled sub-problems and extend it to an algorithm that maximizes the EE. Numerical results demonstrate consistent performance bounds of our proposed algorithm to the optimal EE values, comparing them to NOMA and orthogonal multiple access (OMA) solutions.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128014919","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647149
Bonillo Pena Ramon Alfredo, Perez Mendez Daniel Alejandro
Marco para la implementación de microrredes coordinadas con Blockchain en Uruguay
在乌拉圭实施区块链协调微电网的框架
{"title":"Marco para la implementación de microrredes coordinadas con Blockchain en Uruguay","authors":"Bonillo Pena Ramon Alfredo, Perez Mendez Daniel Alejandro","doi":"10.1109/urucon53396.2021.9647149","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647149","url":null,"abstract":"Marco para la implementación de microrredes coordinadas con Blockchain en Uruguay","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129212486","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647378
André Herrera-Chacón, L. Chavarría-Zamora
Color transfer is one of the main concerns on automatic colorization of gray-scale images [1]. Modern approaches were created based on Welsh's colorization algorithm, improving the core method but relying on specialized hardware. In this paper, we explored a series of algorithms, previously tested in gray-scale image scenarios, to colorize night-vision images on common security systems using affordable hardware. In addition, we demonstrated the efficiency of borrowing color from standard to IR images applying a similarity function integrating luminance information and chromatic values of previously colorized pixels [2].
{"title":"Evaluation of color transfer algorithm in IR images nocturnal scenes","authors":"André Herrera-Chacón, L. Chavarría-Zamora","doi":"10.1109/urucon53396.2021.9647378","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647378","url":null,"abstract":"Color transfer is one of the main concerns on automatic colorization of gray-scale images [1]. Modern approaches were created based on Welsh's colorization algorithm, improving the core method but relying on specialized hardware. In this paper, we explored a series of algorithms, previously tested in gray-scale image scenarios, to colorize night-vision images on common security systems using affordable hardware. In addition, we demonstrated the efficiency of borrowing color from standard to IR images applying a similarity function integrating luminance information and chromatic values of previously colorized pixels [2].","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116907221","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647383
Dharun Anandayuvaraj, R. Lent
The Licklider Transmission Protocol (LTP) is a standard convergence layer for the Bundle Protocol that is suitable for lossy and long-delay channels. It is part of the Delay-Tolerant Networking architecture that is being developed for space and other challenged networks. In this study, the performance sensitivity of LTP to the choice of the maximum payload size and the signal loss is experimentally verified. This parameter determines how data blocks get segmented and directly affects the total amount of header overhead involved in the data transmissions. While large segments are expected to produce less total overhead than small segments, they entail a larger loss probability which may extend the delivery latency due to the extra sessions needed to handle the segment retransmissions. A series of tests were conducted with the ION-DTN reference implementation of the protocol running over a channel with controllable gain provided by Universal Software Radio Peripherals (USRP), i.e., software-defined radio (SDR). The measurements confirm the tradeoffs involved in the payload size selection and the receive signal level of the channel.
{"title":"Evaluating the Licklider Transmission Protocol using Software-Defined Radio","authors":"Dharun Anandayuvaraj, R. Lent","doi":"10.1109/urucon53396.2021.9647383","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647383","url":null,"abstract":"The Licklider Transmission Protocol (LTP) is a standard convergence layer for the Bundle Protocol that is suitable for lossy and long-delay channels. It is part of the Delay-Tolerant Networking architecture that is being developed for space and other challenged networks. In this study, the performance sensitivity of LTP to the choice of the maximum payload size and the signal loss is experimentally verified. This parameter determines how data blocks get segmented and directly affects the total amount of header overhead involved in the data transmissions. While large segments are expected to produce less total overhead than small segments, they entail a larger loss probability which may extend the delivery latency due to the extra sessions needed to handle the segment retransmissions. A series of tests were conducted with the ION-DTN reference implementation of the protocol running over a channel with controllable gain provided by Universal Software Radio Peripherals (USRP), i.e., software-defined radio (SDR). The measurements confirm the tradeoffs involved in the payload size selection and the receive signal level of the channel.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117228841","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647250
S. B. Righetto, L. T. Hattori, Guilherme Goncalves Nunes, E. G. Carvalho, M. A. Martins, S. de Francisci
Industry 4.0 opened new frontiers of the Smart Grid (SG) area to understand the behavior of the power grid assets. The asset sensor data stored has been supporting the analysis of the life cycle. Also, it helps to improve predictive maintenance activities. On the other hand, Machine Learning approaches have been achieving the current state-of-the-art in many problems of the SG area. In this context, this paper proposes a preliminary study using ML methods to predict failure in Automatic Reclosers (ARs). In this work, we compare five ML methods: Naive Bayes (NB), Deep Neural Network (DNN), Decision Tree (DT), Gradient Boosted Tree (GBT), and Random Forest (RF). A dataset was generated with temperature information and historical data of the ARs sensors. The failures were labeled using a rule-based approach proposed by the AR specialists. Among the ML methods, RF obtained the best result with 82.47% F1-Score in the test set, indicating a promising result for the failure prediction area.
{"title":"Failure Prediction in Automatic Reclosers Using Machine Learning Approaches","authors":"S. B. Righetto, L. T. Hattori, Guilherme Goncalves Nunes, E. G. Carvalho, M. A. Martins, S. de Francisci","doi":"10.1109/urucon53396.2021.9647250","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647250","url":null,"abstract":"Industry 4.0 opened new frontiers of the Smart Grid (SG) area to understand the behavior of the power grid assets. The asset sensor data stored has been supporting the analysis of the life cycle. Also, it helps to improve predictive maintenance activities. On the other hand, Machine Learning approaches have been achieving the current state-of-the-art in many problems of the SG area. In this context, this paper proposes a preliminary study using ML methods to predict failure in Automatic Reclosers (ARs). In this work, we compare five ML methods: Naive Bayes (NB), Deep Neural Network (DNN), Decision Tree (DT), Gradient Boosted Tree (GBT), and Random Forest (RF). A dataset was generated with temperature information and historical data of the ARs sensors. The failures were labeled using a rule-based approach proposed by the AR specialists. Among the ML methods, RF obtained the best result with 82.47% F1-Score in the test set, indicating a promising result for the failure prediction area.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114283235","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 : 2021-11-24DOI: 10.1109/urucon53396.2021.9647058
D. Avila-Pesantez, Brandon Alexander Tubon Usca, Bryan Gagnay Angamarca, L. Avila
It is necessary to consider metrics that integrate Game Learning Analytics (GLA) and technologies that improve user interfaces through the eye tracker to get better the Serious Games design. In this work, the Math4Fun game was developed using the ADDE methodology to support basic math operations for 7-year-old children, which allowed efficient communication to define the game's critical elements. The GLA metrics were implemented with eXperience API (xAPI) standard and visualized through a real-time dashboard, while Eye-tracking technology working with fixation time analysis on the game's interfaces improves gameplay and design. The results established that combining the GLA indicators with the user interface components obtained from the evaluation with eye-tracking allows redefining concepts in the design and programming inside SG in search of constant improvement.
{"title":"Improving the Serious Game design using Game Learning Analytics and Eye-tracking: A pilot study","authors":"D. Avila-Pesantez, Brandon Alexander Tubon Usca, Bryan Gagnay Angamarca, L. Avila","doi":"10.1109/urucon53396.2021.9647058","DOIUrl":"https://doi.org/10.1109/urucon53396.2021.9647058","url":null,"abstract":"It is necessary to consider metrics that integrate Game Learning Analytics (GLA) and technologies that improve user interfaces through the eye tracker to get better the Serious Games design. In this work, the Math4Fun game was developed using the ADDE methodology to support basic math operations for 7-year-old children, which allowed efficient communication to define the game's critical elements. The GLA metrics were implemented with eXperience API (xAPI) standard and visualized through a real-time dashboard, while Eye-tracking technology working with fixation time analysis on the game's interfaces improves gameplay and design. The results established that combining the GLA indicators with the user interface components obtained from the evaluation with eye-tracking allows redefining concepts in the design and programming inside SG in search of constant improvement.","PeriodicalId":337257,"journal":{"name":"2021 IEEE URUCON","volume":"680 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121995800","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：