Pub Date : 2019-07-01DOI: 10.1109/IWMN.2019.8805005
S. Baglio, A. Cammarata, P. Cortis, L. L. Bello, P. Maddío, S. Nicosia, Gaetano Patti, S. Sciberras, Johann Scicluna, Vincenzo Scuderi, R. Sinatra, C. Trigona
The objective of this work concerns the study of virtual biosensors for the estimation of medical precursors. The principle is based on the combination of the signals coming from the patient (vital functions), the transduction of such acquired signals and the processing of the obtained information. The method will use n input variables (the classic physiological parameters and/or signals detected by using additive sensors) and one output variable which is correlated with the clinical condition of the patient. A model will produce an association between the input variables and the output variable by using a data set established with the medical team. The proposed methodology improves standard systems such as "track and trigger" and threshold (Early Warning Score) through the adoption of the Fuzzy Set Theory.
{"title":"Virtual biosensors for the estimation of medical precursors","authors":"S. Baglio, A. Cammarata, P. Cortis, L. L. Bello, P. Maddío, S. Nicosia, Gaetano Patti, S. Sciberras, Johann Scicluna, Vincenzo Scuderi, R. Sinatra, C. Trigona","doi":"10.1109/IWMN.2019.8805005","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8805005","url":null,"abstract":"The objective of this work concerns the study of virtual biosensors for the estimation of medical precursors. The principle is based on the combination of the signals coming from the patient (vital functions), the transduction of such acquired signals and the processing of the obtained information. The method will use n input variables (the classic physiological parameters and/or signals detected by using additive sensors) and one output variable which is correlated with the clinical condition of the patient. A model will produce an association between the input variables and the output variable by using a data set established with the medical team. The proposed methodology improves standard systems such as \"track and trigger\" and threshold (Early Warning Score) through the adoption of the Fuzzy Set Theory.","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117231132","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 : 2019-07-01DOI: 10.1109/IWMN.2019.8805009
F. Abate, A. Espírito-Santo, G. Monte, V. Paciello
This paper presents a new method for earthquake early warning alert that uses a smart sampling technique that expose the signal information in a way that it is simpler to infer knowledge. The objective is to estimate, from the first few seconds of the P wave, if the incoming earthquake is destructive or not. The proposed method is described and compared to conventional approaches. Performance results for real seismic data are shown highlighting the results for earthquakes of different magnitudes. Preliminary results are excellent for inferring damage based on the approach of a single seismic station.
{"title":"Smart Sensor Efficient Signal Processing for Earthquake Early Detection","authors":"F. Abate, A. Espírito-Santo, G. Monte, V. Paciello","doi":"10.1109/IWMN.2019.8805009","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8805009","url":null,"abstract":"This paper presents a new method for earthquake early warning alert that uses a smart sampling technique that expose the signal information in a way that it is simpler to infer knowledge. The objective is to estimate, from the first few seconds of the P wave, if the incoming earthquake is destructive or not. The proposed method is described and compared to conventional approaches. Performance results for real seismic data are shown highlighting the results for earthquakes of different magnitudes. Preliminary results are excellent for inferring damage based on the approach of a single seismic station.","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134088155","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 : 2019-07-01DOI: 10.1109/IWMN.2019.8804987
Alaa Eddin Alchalabi, S. Shirmohammadi, S. Mohammed
Cloud Gaming systems are among the most challenging networked-applications, since they deal with streaming high-quality and bulky video in real-time to players’ devices. While all industry solutions today are centralized, in this paper we introduce an AI-assisted hybrid networking architecture that, in addition to the central cloud servers, also uses some players’ computing resources as additional points of service. We describe the problem, its mathematical formulation, and potential solution strategy.
{"title":"QNetwork: AI-Assisted Networking for Hybrid Cloud Gaming","authors":"Alaa Eddin Alchalabi, S. Shirmohammadi, S. Mohammed","doi":"10.1109/IWMN.2019.8804987","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8804987","url":null,"abstract":"Cloud Gaming systems are among the most challenging networked-applications, since they deal with streaming high-quality and bulky video in real-time to players’ devices. While all industry solutions today are centralized, in this paper we introduce an AI-assisted hybrid networking architecture that, in addition to the central cloud servers, also uses some players’ computing resources as additional points of service. We describe the problem, its mathematical formulation, and potential solution strategy.","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133773132","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 : 2019-07-01DOI: 10.1109/IWMN.2019.8805017
Claudia Parera, A. Redondi, M. Cesana, Qi Liao, Ilaria Malanchini
The ability to predict the quality of a wireless channel is essential for enabling anticipatory networking tasks. Traditional channel quality prediction problems encompass predicting future conditions based on past measurements of the same channel. In this paper we study the channel quality prediction problem across different wireless channels. To this extent, we consider a reference scenario including multiple 4G cells, each of which operates on multiple concurrent frequency carriers. We propose a framework based on transfer learning to predict the channel quality of a given frequency carrier when no or minimal information is available on the very same frequency carrier for model training. For the transfer learning task we use convolutional neural networks and long short-term memory networks. We compare their performance against statistical methods on a dataset collected from a commercial 4G mobile radio network. The performance evaluation carried out on the reference dataset demonstrates the validity of the proposed transfer learning approach, achieving a root mean squared error of 0.3 on average.
{"title":"Transfer Learning for Channel Quality Prediction","authors":"Claudia Parera, A. Redondi, M. Cesana, Qi Liao, Ilaria Malanchini","doi":"10.1109/IWMN.2019.8805017","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8805017","url":null,"abstract":"The ability to predict the quality of a wireless channel is essential for enabling anticipatory networking tasks. Traditional channel quality prediction problems encompass predicting future conditions based on past measurements of the same channel. In this paper we study the channel quality prediction problem across different wireless channels. To this extent, we consider a reference scenario including multiple 4G cells, each of which operates on multiple concurrent frequency carriers. We propose a framework based on transfer learning to predict the channel quality of a given frequency carrier when no or minimal information is available on the very same frequency carrier for model training. For the transfer learning task we use convolutional neural networks and long short-term memory networks. We compare their performance against statistical methods on a dataset collected from a commercial 4G mobile radio network. The performance evaluation carried out on the reference dataset demonstrates the validity of the proposed transfer learning approach, achieving a root mean squared error of 0.3 on average.","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"16 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123262482","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 : 2019-07-01DOI: 10.1109/IWMN.2019.8805048
N. Pasquino, G. Ventre, S. Zinno, Federica Ignarro, S. Petrocelli
Quality characterization of a Long Term Evolution (LTE) cellular network with Multiple Input Multiple Output (MIMO) configuration is carried out through an experimental multivariate analysis of the main parameters of signal quality, which is crucial to optimize network performance. We adopted a technique based on the Expectation-Maximization (EM) algorithm that aims at statistically model radio-layer parameters with a blind machine learning technique that clusters data collected by a mobile operator. Data are retrieved with a smartphone-based methodology during a drive-test campaign.Clustering of the performance indicators has also been done spatially, by locating areas with different levels of signal quality on a map, to highlight those spots were improvements are required to overcome porr signal quality mostly due to the presence of co-channel or adjacent channel interference.
{"title":"Multivariate LTE Performance Assessment through an Expectation-Maximization Algorithm Approach","authors":"N. Pasquino, G. Ventre, S. Zinno, Federica Ignarro, S. Petrocelli","doi":"10.1109/IWMN.2019.8805048","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8805048","url":null,"abstract":"Quality characterization of a Long Term Evolution (LTE) cellular network with Multiple Input Multiple Output (MIMO) configuration is carried out through an experimental multivariate analysis of the main parameters of signal quality, which is crucial to optimize network performance. We adopted a technique based on the Expectation-Maximization (EM) algorithm that aims at statistically model radio-layer parameters with a blind machine learning technique that clusters data collected by a mobile operator. Data are retrieved with a smartphone-based methodology during a drive-test campaign.Clustering of the performance indicators has also been done spatially, by locating areas with different levels of signal quality on a map, to highlight those spots were improvements are required to overcome porr signal quality mostly due to the presence of co-channel or adjacent channel interference.","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127228963","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 : 2019-07-01DOI: 10.1109/IWMN.2019.8805015
M. Carratù, M. Ferro, A. Pietrosanto, P. Sommella, V. Paciello
Nowadays, the air quality has become one of the most important problem in modern cities. The particulate matters in the air represents one of the principal causes of respiratory problems. The industrial products and the vehicular traffic had contributed to several phenomena in the increasing of atmospheric pollutants as ammonia, carbon dioxide, PM and so on. Although the importance regarding the monitoring of this substances, in the European countries still be a low number of air quality measurement stations probably due to the high cost of them and the not neglectable dimensions. However, in recent years, low-cost sensors for the air-quality have grown up in several private applications. These sensors are characterized by poor metrological performances that not enable the use of them in a public scenario agreeing with the European law in term of air quality. The authors, in this paper, present a possible integration of a low-cost air quality sensors for the monitoring of PM10 particles in a modern short-range Wireless Sensor Network (WSN) usually adopted in Smart Cities for Smart Metering applications (Gas and Water). The use of a high number of those sensors, thanks to the WSN, will be used to make up for the lack of measurement quality exhibited by the single sensor. The feasibility of the proposal will be demonstrated against the real measurement of two fixed air quality station in Campania region (Italy).
{"title":"A Smart Wireless Sensor Network For PM10 Measurement","authors":"M. Carratù, M. Ferro, A. Pietrosanto, P. Sommella, V. Paciello","doi":"10.1109/IWMN.2019.8805015","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8805015","url":null,"abstract":"Nowadays, the air quality has become one of the most important problem in modern cities. The particulate matters in the air represents one of the principal causes of respiratory problems. The industrial products and the vehicular traffic had contributed to several phenomena in the increasing of atmospheric pollutants as ammonia, carbon dioxide, PM and so on. Although the importance regarding the monitoring of this substances, in the European countries still be a low number of air quality measurement stations probably due to the high cost of them and the not neglectable dimensions. However, in recent years, low-cost sensors for the air-quality have grown up in several private applications. These sensors are characterized by poor metrological performances that not enable the use of them in a public scenario agreeing with the European law in term of air quality. The authors, in this paper, present a possible integration of a low-cost air quality sensors for the monitoring of PM10 particles in a modern short-range Wireless Sensor Network (WSN) usually adopted in Smart Cities for Smart Metering applications (Gas and Water). The use of a high number of those sensors, thanks to the WSN, will be used to make up for the lack of measurement quality exhibited by the single sensor. The feasibility of the proposal will be demonstrated against the real measurement of two fixed air quality station in Campania region (Italy).","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124062334","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 : 2019-07-01DOI: 10.1109/IWMN.2019.8805029
A. Bernieri, G. Betta, G. Cerro, G. Miele, D. Capriglione
The compliance of cellular base stations electromagnetic field emissions with 24-hours exposure limits generally requires adopting suitable extrapolation techniques able to provide an upper boundary to the emitted power. As for 3rd and 4th generation cellular systems, the technical standards describing the related measurement methods allows using either Spectrum Analyzers or Vector Spectrum Analyzers. The latter ones are preferable because of their enhanced capability to isolate the single base station contributions. Nevertheless, Spectrum Analyzers are the most widespread measurement instruments adopted by technician operating in such a framework. Therefore, it could be useful to quantify the expected overestimation with respect to the Vector-type instruments. To this aim, in this paper an experimental comparison between the results achieved by applying extrapolation techniques with both acquisition devices is performed. To verify the results’ repeatability, such analyses have been carried out in different hours of the day and in different days. Our findings prove how Spectrum Analyzers generally overestimate the electric field magnitude with respect to Vector Analyzers even if different behaviors have been observed with respect to the different cellular systems.
{"title":"Experimental Comparison of Extrapolation Techniques for 24-Hours Electromagnetic Fields Human Exposure Evaluation to UMTS and LTE Base Stations","authors":"A. Bernieri, G. Betta, G. Cerro, G. Miele, D. Capriglione","doi":"10.1109/IWMN.2019.8805029","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8805029","url":null,"abstract":"The compliance of cellular base stations electromagnetic field emissions with 24-hours exposure limits generally requires adopting suitable extrapolation techniques able to provide an upper boundary to the emitted power. As for 3rd and 4th generation cellular systems, the technical standards describing the related measurement methods allows using either Spectrum Analyzers or Vector Spectrum Analyzers. The latter ones are preferable because of their enhanced capability to isolate the single base station contributions. Nevertheless, Spectrum Analyzers are the most widespread measurement instruments adopted by technician operating in such a framework. Therefore, it could be useful to quantify the expected overestimation with respect to the Vector-type instruments. To this aim, in this paper an experimental comparison between the results achieved by applying extrapolation techniques with both acquisition devices is performed. To verify the results’ repeatability, such analyses have been carried out in different hours of the day and in different days. Our findings prove how Spectrum Analyzers generally overestimate the electric field magnitude with respect to Vector Analyzers even if different behaviors have been observed with respect to the different cellular systems.","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125930748","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 : 2019-07-01DOI: 10.1109/iwmn.2019.8804999
{"title":"[M&N 2019 Front matter]","authors":"","doi":"10.1109/iwmn.2019.8804999","DOIUrl":"https://doi.org/10.1109/iwmn.2019.8804999","url":null,"abstract":"","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127737531","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 : 2019-07-01DOI: 10.1109/IWMN.2019.8805044
Ayşe Rumeysa Mohammed, S. Mohammed, S. Shirmohammadi
The Internet is constantly growing in size and becoming more complex. The field of networking is thus continuously progressing to cope with this monumental growth of network traffic. While approaches such as Software Defined Networking (SDN) can provide a centralized control mechanism for network traffic measurement, control, and prediction, still the amount of data received by the SDN controller is huge. To process that data, it has recently been suggested to use Machine Learning (ML). In this paper, we review existing proposal for using ML in an SDN context for traffic measurement (specifically, classification) and traffic prediction. We will especially focus on approaches that use Deep learning (DL) in traffic prediction, which seems to have been mostly untapped by existing surveys. Furthermore, we discuss remaining challenges and suggest future research directions.
{"title":"Machine Learning and Deep Learning Based Traffic Classification and Prediction in Software Defined Networking","authors":"Ayşe Rumeysa Mohammed, S. Mohammed, S. Shirmohammadi","doi":"10.1109/IWMN.2019.8805044","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8805044","url":null,"abstract":"The Internet is constantly growing in size and becoming more complex. The field of networking is thus continuously progressing to cope with this monumental growth of network traffic. While approaches such as Software Defined Networking (SDN) can provide a centralized control mechanism for network traffic measurement, control, and prediction, still the amount of data received by the SDN controller is huge. To process that data, it has recently been suggested to use Machine Learning (ML). In this paper, we review existing proposal for using ML in an SDN context for traffic measurement (specifically, classification) and traffic prediction. We will especially focus on approaches that use Deep learning (DL) in traffic prediction, which seems to have been mostly untapped by existing surveys. Furthermore, we discuss remaining challenges and suggest future research directions.","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126821709","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 : 2019-07-01DOI: 10.1109/IWMN.2019.8804993
P. Serra, A. Espírito-Santo, J. Bonifácio, F. Relvas
Collecting information on wastewater treatment processes is critical to the efficiency of the treatment system. Detecting the water level inside of a macrophyte constructed wetlands, using a capacitive sensing element, allows knowing the operating state and efficiency of this infrastructure. The energy independence of the smart sensor is achieved through a microbial fuel cell that, by using the wastewater’s organic matter, allows it to operate indefinitely, avoiding a battery element and the associated replacement tasks. At the same time, integration of the smart sensor into a transducer network, observing the IEEE1451 standard, contributes to improve interoperability promoting cooperation among wastewater treatment subsystems.
{"title":"Capacitive Level Smart Sensors in the Management of Wastewater Treatment Processes","authors":"P. Serra, A. Espírito-Santo, J. Bonifácio, F. Relvas","doi":"10.1109/IWMN.2019.8804993","DOIUrl":"https://doi.org/10.1109/IWMN.2019.8804993","url":null,"abstract":"Collecting information on wastewater treatment processes is critical to the efficiency of the treatment system. Detecting the water level inside of a macrophyte constructed wetlands, using a capacitive sensing element, allows knowing the operating state and efficiency of this infrastructure. The energy independence of the smart sensor is achieved through a microbial fuel cell that, by using the wastewater’s organic matter, allows it to operate indefinitely, avoiding a battery element and the associated replacement tasks. At the same time, integration of the smart sensor into a transducer network, observing the IEEE1451 standard, contributes to improve interoperability promoting cooperation among wastewater treatment subsystems.","PeriodicalId":272577,"journal":{"name":"2019 IEEE International Symposium on Measurements & Networking (M&N)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124728034","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：