Pub Date : 2018-06-01DOI: 10.1109/ISNCC.2018.8531066
Ahmed Alabish, A. Kara, Y. Dalveren
As 5G communication may use Millimeter waves (mmWave) bands, it is necessary to evaluate short-range indoor links from the link blockage point of view. This paper presents some initial studies for characterizing effects of human body movements on short range indoor links at 18–22 GHz. Firstly, measurement system is described, and then, calibration measurements along with initial results of the impact of human body movement on the channel are presented for some scenarios. To the best of our knowledge, this study is the first to experimentally examine the effects of human body movements at this band. Yet, as this study constitutes a part of an ongoing research, further results will be anticipated to present the effects of objects over and around the link on the directional propagation at mmWave bands (28–30 GHz).
{"title":"An Experimental Study towards Examining Human Body Movements in Indoor Wave Propagation at 18–22 GHz","authors":"Ahmed Alabish, A. Kara, Y. Dalveren","doi":"10.1109/ISNCC.2018.8531066","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8531066","url":null,"abstract":"As 5G communication may use Millimeter waves (mmWave) bands, it is necessary to evaluate short-range indoor links from the link blockage point of view. This paper presents some initial studies for characterizing effects of human body movements on short range indoor links at 18–22 GHz. Firstly, measurement system is described, and then, calibration measurements along with initial results of the impact of human body movement on the channel are presented for some scenarios. To the best of our knowledge, this study is the first to experimentally examine the effects of human body movements at this band. Yet, as this study constitutes a part of an ongoing research, further results will be anticipated to present the effects of objects over and around the link on the directional propagation at mmWave bands (28–30 GHz).","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132906366","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8531009
Massimo Marchiori
Pedestrian pathways are a crucial networking components of our cities, and yet they are somehow seen as subordinate to streets in many areas that are not central. As a result, detection of their actual status, and corresponding maintenance, is often far from optimal. In this work we look for solutions to the problem of pathways status detection, and look for novel solutions that allow us to assess the status of a pedestrian pathway. We develop a system that enables to collect data from the pathways in a very economical and flexible way, and then experiment to see whether the data allow to actually produce a reliable status prediction. The results, tested on the field, show that the obtained system is both convenient to use and precise, paving the way for better ways of handling pedestrian pathways networking within a smarter city environment.
{"title":"Fix Me Up: Smart Pathways Status Detection","authors":"Massimo Marchiori","doi":"10.1109/ISNCC.2018.8531009","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8531009","url":null,"abstract":"Pedestrian pathways are a crucial networking components of our cities, and yet they are somehow seen as subordinate to streets in many areas that are not central. As a result, detection of their actual status, and corresponding maintenance, is often far from optimal. In this work we look for solutions to the problem of pathways status detection, and look for novel solutions that allow us to assess the status of a pedestrian pathway. We develop a system that enables to collect data from the pathways in a very economical and flexible way, and then experiment to see whether the data allow to actually produce a reliable status prediction. The results, tested on the field, show that the obtained system is both convenient to use and precise, paving the way for better ways of handling pedestrian pathways networking within a smarter city environment.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125997611","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8531054
G. Saggio, G. Orengo, A. Pallotti, V. Errico, M. Ricci
Sensor-based systems for detecting, recognizing and measuring the position and movement of the human body in a three-dimensional space with great accuracy and precision have been widespread in last decades. Starting from consolidated optical systems, which still represent the reference for other cost effective systems, this work presents smart solutions for motion capture and posture recognition systems, either based on the most popular inertial sensors, but also flex sensors, such as the sensory gloves for measurement of bending angles of finger joints, whose development increases at the same rate of application developed to exploit the potential of these systems. Recently surface electromyography (sEMG) is gaining more and more importance in gesture recognition systems for disabled skills assessment and prosthesis control of transradial amputees.
{"title":"Sensory Systems for Human Body Gesture Recognition and Motion Capture","authors":"G. Saggio, G. Orengo, A. Pallotti, V. Errico, M. Ricci","doi":"10.1109/ISNCC.2018.8531054","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8531054","url":null,"abstract":"Sensor-based systems for detecting, recognizing and measuring the position and movement of the human body in a three-dimensional space with great accuracy and precision have been widespread in last decades. Starting from consolidated optical systems, which still represent the reference for other cost effective systems, this work presents smart solutions for motion capture and posture recognition systems, either based on the most popular inertial sensors, but also flex sensors, such as the sensory gloves for measurement of bending angles of finger joints, whose development increases at the same rate of application developed to exploit the potential of these systems. Recently surface electromyography (sEMG) is gaining more and more importance in gesture recognition systems for disabled skills assessment and prosthesis control of transradial amputees.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126153555","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8531022
Juanita Blue, Eoghan Furey
The upcoming implementation of the European Union General Data Protection Regulation (GDPR) will require many organisations throughout the EU to comply with new requirements that are intended to better protect personal data. Large increases in responsibility, penalties and fines will place great pressure on organisations to ensure they are compliant and adequately protect user data that is associated with online accounts. Non-compliant legacy databases are those that store authentication credentials in plaintext or utilizing obsolete one-way encryption techniques that fail to adhere to best practice guidelines. Companies who remain reliant on these vulnerable systems will be forced to reconsider and improve their architecture, or risk the exposure of personal data and the debilitating penalties that will also be incurred. Authentication databases are frequently a target of attack as they potentially provide an avenue to commit further, more lucrative crimes. Lacking or substandard implementations have cultivated an environment where authentication databases and the data stored therein are insecure. This was demonstrated in the 2016 exposure of a breach experienced by Yahoo where approximately one billion user credentials were stolen. The global technology company was found to be using obsolete security mechanisms to protect user passwords. This paper offers a novel solution for improving the protection of currently non-compliant legacy authentication databases stored on Apache servers. The method applies best practice mechanisms in the form of salt, one-way encryption (hashing) and iterations to both pre-existing and newly created passwords held within the databases. The proposed solution can be implemented server-side, with little alteration to the existing infrastructure and unbeknownst to the user. It possesses the potential to improve system security, preserve privacy, and aid implementation of GDPR requirements.
{"title":"A Novel Approach for Protecting Legacy Authentication Databases in Consideration of GDPR","authors":"Juanita Blue, Eoghan Furey","doi":"10.1109/ISNCC.2018.8531022","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8531022","url":null,"abstract":"The upcoming implementation of the European Union General Data Protection Regulation (GDPR) will require many organisations throughout the EU to comply with new requirements that are intended to better protect personal data. Large increases in responsibility, penalties and fines will place great pressure on organisations to ensure they are compliant and adequately protect user data that is associated with online accounts. Non-compliant legacy databases are those that store authentication credentials in plaintext or utilizing obsolete one-way encryption techniques that fail to adhere to best practice guidelines. Companies who remain reliant on these vulnerable systems will be forced to reconsider and improve their architecture, or risk the exposure of personal data and the debilitating penalties that will also be incurred. Authentication databases are frequently a target of attack as they potentially provide an avenue to commit further, more lucrative crimes. Lacking or substandard implementations have cultivated an environment where authentication databases and the data stored therein are insecure. This was demonstrated in the 2016 exposure of a breach experienced by Yahoo where approximately one billion user credentials were stolen. The global technology company was found to be using obsolete security mechanisms to protect user passwords. This paper offers a novel solution for improving the protection of currently non-compliant legacy authentication databases stored on Apache servers. The method applies best practice mechanisms in the form of salt, one-way encryption (hashing) and iterations to both pre-existing and newly created passwords held within the databases. The proposed solution can be implemented server-side, with little alteration to the existing infrastructure and unbeknownst to the user. It possesses the potential to improve system security, preserve privacy, and aid implementation of GDPR requirements.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130255015","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8531063
Faiza Al-Salti, K. Day, N. Alzeidi, A. Touzene
We propose a mathematical model for multiple sink placement in Underwater Wireless Sensor Networks (UWSNs). The model is constructed for a 3D mesh topology. Our objective is to minimize the overall number of hops of every source-closest sink pair of cells. We analyze the constructed model, and prove its hardness by reducing the k-median problem, a well-known NP-hard problem to our problem. We then use the Partitioning Around Medoid (PAM) approximation algorithm to find a near optimal solution to our sink placement problem. We test the solutions obtained by this approximation algorithm by comparing them with the optimal solutions obtained using a brute force method. We also compare the approximate solutions with solutions obtained using a random-based heuristic. Results show that the proposed PAM-based approximation achieves remarkably near-optimal solutions.
{"title":"Multiple Sink Placement Strategy for Underwater Wireless Sensor Networks","authors":"Faiza Al-Salti, K. Day, N. Alzeidi, A. Touzene","doi":"10.1109/ISNCC.2018.8531063","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8531063","url":null,"abstract":"We propose a mathematical model for multiple sink placement in Underwater Wireless Sensor Networks (UWSNs). The model is constructed for a 3D mesh topology. Our objective is to minimize the overall number of hops of every source-closest sink pair of cells. We analyze the constructed model, and prove its hardness by reducing the k-median problem, a well-known NP-hard problem to our problem. We then use the Partitioning Around Medoid (PAM) approximation algorithm to find a near optimal solution to our sink placement problem. We test the solutions obtained by this approximation algorithm by comparing them with the optimal solutions obtained using a brute force method. We also compare the approximate solutions with solutions obtained using a random-based heuristic. Results show that the proposed PAM-based approximation achieves remarkably near-optimal solutions.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120845321","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8530890
Manas Pradhan
The primary purpose of military anywhere around the world is to protect and serve the people. Over the years, the role of the military has diversified which has required the military to serve countries in several capabilities. Be it active wars, intelligence gathering, rescue operations, anti-terrorist operations etc., the modern military has to play a role. Since the military has to adapt to, prepare for and respond to the ever changing dynamics of people and surroundings around the world, it becomes necessary to look into what exists currently and what will form the future. Smart cities are such a phenomenon. The cities around the world are transforming to be “Smart”, to meet various future challenges such as population migration and how to manage the living of such a huge number of people in a relatively small area, improving the quality of various services delivered to citizens, saving and optimizing resource utilization and so on. In such a scenario, where the population and assets need to be protected in Smart Cities, the militaries need to get a hold of the technologies and know the emerging trends in the smart cities. This would give the defence sector a head-start in knowing what capabilities are and would be available so that they are ready to employ their services alongside the Smart City solutions and thus serve their motto optimally. This paper entails the various Smart City assets from various cities as well as involved Internet-of-Things (IoT) technologies and tries to provide a picture of what the military in future can integrate with their solutions to serve the Smart Cities.
{"title":"A Survey of Smart City Assets for Future Military Usage","authors":"Manas Pradhan","doi":"10.1109/ISNCC.2018.8530890","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8530890","url":null,"abstract":"The primary purpose of military anywhere around the world is to protect and serve the people. Over the years, the role of the military has diversified which has required the military to serve countries in several capabilities. Be it active wars, intelligence gathering, rescue operations, anti-terrorist operations etc., the modern military has to play a role. Since the military has to adapt to, prepare for and respond to the ever changing dynamics of people and surroundings around the world, it becomes necessary to look into what exists currently and what will form the future. Smart cities are such a phenomenon. The cities around the world are transforming to be “Smart”, to meet various future challenges such as population migration and how to manage the living of such a huge number of people in a relatively small area, improving the quality of various services delivered to citizens, saving and optimizing resource utilization and so on. In such a scenario, where the population and assets need to be protected in Smart Cities, the militaries need to get a hold of the technologies and know the emerging trends in the smart cities. This would give the defence sector a head-start in knowing what capabilities are and would be available so that they are ready to employ their services alongside the Smart City solutions and thus serve their motto optimally. This paper entails the various Smart City assets from various cities as well as involved Internet-of-Things (IoT) technologies and tries to provide a picture of what the military in future can integrate with their solutions to serve the Smart Cities.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124489964","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8530905
F. D. Stasio, M. Mondin, F. Daneshgaran
One of the main open problems for next generation wireless networks, is to find the new OFDM-based waveform to be used in 5G. The new modulation scheme must primarily be able to achieve higher spectral efficiency than its predecessor. The main 3GPP's candidate is a new version of OFDM, called Filtered Orthogonal Frequency-Division Modulation (f-OFDM), which is similar to OFDM but with additional filtering in order to reduce Out-Of-Band (OOB) emissions and to obtain a better spectral-localization. Another option is windowed-OFDM (w-OFDM), which is basically a classical OFDM scheme where each symbol is windowed and overlapped in the time domain. In this paper we compare classic OFDM signals using Cyclic Prefix (CP-OFDM) with f-OFDM and w-OFDM, each one with multiple parametric options and numerologies. A multirate transmitter simultaneously operating with multiple numerologies is considered, where the transmitted sub-bands must be up-sampled and interpolated in order to generate the composite numerical signal fed to the Digital to Analog Converter (DAC). Finally, we discuss advantages and disadvantages of the various schemes.
{"title":"Multirate 5G Downlink Performance Comparison for f-OFDM and w-OFDM Schemes with Different Numerologies","authors":"F. D. Stasio, M. Mondin, F. Daneshgaran","doi":"10.1109/ISNCC.2018.8530905","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8530905","url":null,"abstract":"One of the main open problems for next generation wireless networks, is to find the new OFDM-based waveform to be used in 5G. The new modulation scheme must primarily be able to achieve higher spectral efficiency than its predecessor. The main 3GPP's candidate is a new version of OFDM, called Filtered Orthogonal Frequency-Division Modulation (f-OFDM), which is similar to OFDM but with additional filtering in order to reduce Out-Of-Band (OOB) emissions and to obtain a better spectral-localization. Another option is windowed-OFDM (w-OFDM), which is basically a classical OFDM scheme where each symbol is windowed and overlapped in the time domain. In this paper we compare classic OFDM signals using Cyclic Prefix (CP-OFDM) with f-OFDM and w-OFDM, each one with multiple parametric options and numerologies. A multirate transmitter simultaneously operating with multiple numerologies is considered, where the transmitted sub-bands must be up-sampled and interpolated in order to generate the composite numerical signal fed to the Digital to Analog Converter (DAC). Finally, we discuss advantages and disadvantages of the various schemes.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121376145","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8530978
E. Pencheva, Denitsa Kireva-Mihova, I. Atanasov, V. Trifonov
Multi-access Edge Computing (MEC) is a cloud technology that converges telecommunication and computing capabilities at the Radio Access Network (RAN). The paper proposes an extension to existing MEC Application Programming Interfaces (API) for bandwidth management. The proposed extension allows authorized applications to supervise bandwidth allocation to any session or application considering up-to-date radio network information. Description of information flows, data models and actual API definition is provided. Resource state models reflect some implementation perspectives.
{"title":"An Extension of Mobile Edge Computing Bandwidth Management API","authors":"E. Pencheva, Denitsa Kireva-Mihova, I. Atanasov, V. Trifonov","doi":"10.1109/ISNCC.2018.8530978","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8530978","url":null,"abstract":"Multi-access Edge Computing (MEC) is a cloud technology that converges telecommunication and computing capabilities at the Radio Access Network (RAN). The paper proposes an extension to existing MEC Application Programming Interfaces (API) for bandwidth management. The proposed extension allows authorized applications to supervise bandwidth allocation to any session or application considering up-to-date radio network information. Description of information flows, data models and actual API definition is provided. Resource state models reflect some implementation perspectives.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116901881","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8531069
Andrés Munoz-Arcentales, W. Velásquez, J. Salvachúa
This paper describes a proof of concept of a Fast-Data architecture to generate early response alerts on unforeseen events. For achieving that, in this work is presented the implementation of a fully integrated system capable to handle and process streaming data in order to generate an alert response for each generated event. The deployment stated are composed by a simulated wireless sensor network for generating environmental values, a centralized Kafka server for data segmentation and a machine learning model deployed in a Spark cluster for generating the emergency alerts. Also, a simulation was conducted assuming that a fire had affected the simulated scenario in order to determine and evaluate the system's behavior. Finally, the classification model is presented as an early system alternative based on real-time processing and can be used in different areas of occupational safety.
{"title":"Practical Approach of Fast-Data Architecture Applied to Alert Generation in Emergency Evacuation Systems","authors":"Andrés Munoz-Arcentales, W. Velásquez, J. Salvachúa","doi":"10.1109/ISNCC.2018.8531069","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8531069","url":null,"abstract":"This paper describes a proof of concept of a Fast-Data architecture to generate early response alerts on unforeseen events. For achieving that, in this work is presented the implementation of a fully integrated system capable to handle and process streaming data in order to generate an alert response for each generated event. The deployment stated are composed by a simulated wireless sensor network for generating environmental values, a centralized Kafka server for data segmentation and a machine learning model deployed in a Spark cluster for generating the emergency alerts. Also, a simulation was conducted assuming that a fire had affected the simulated scenario in order to determine and evaluate the system's behavior. Finally, the classification model is presented as an early system alternative based on real-time processing and can be used in different areas of occupational safety.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114016905","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 : 2018-06-01DOI: 10.1109/ISNCC.2018.8530988
S. Shelke, Jacob Harbour, Baris Aksanli
Smart spaces have become an integral part of our daily routines to improve quality of life for many different groups of people. The use of embedded systems to build these smart spaces, in combination with data analytics, can provide real-time information about the environment and how it interacts with the people in it. In this paper, we demonstrate how one embedded system that acquires data based on a 2-dimensional positional-grid, movement, temperature and vibration is used to build a smart and pervasive space. Data collected from these sensors is used for real time localization in conjunction with machine learning mechanisms to analyze human activities. We evaluate five machine learning algorithms, namely Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, Naive Bayes and Artificial Neural Network applied on a dataset collected in our lab. Results show high classification performance for all methods giving up-to 99.95% classification accuracy. These patterns provide useful information about occupancy patterns, movement patterns, etc., which will be later used to allocate computational resources in the smart space accordingly. Furthermore, our implementation does not use any camera or microphone deployment, hence addressing potential privacy issues.
{"title":"Building an Intelligent and Efficient Smart Space to Detect Human Behavior in Common Areas","authors":"S. Shelke, Jacob Harbour, Baris Aksanli","doi":"10.1109/ISNCC.2018.8530988","DOIUrl":"https://doi.org/10.1109/ISNCC.2018.8530988","url":null,"abstract":"Smart spaces have become an integral part of our daily routines to improve quality of life for many different groups of people. The use of embedded systems to build these smart spaces, in combination with data analytics, can provide real-time information about the environment and how it interacts with the people in it. In this paper, we demonstrate how one embedded system that acquires data based on a 2-dimensional positional-grid, movement, temperature and vibration is used to build a smart and pervasive space. Data collected from these sensors is used for real time localization in conjunction with machine learning mechanisms to analyze human activities. We evaluate five machine learning algorithms, namely Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, Naive Bayes and Artificial Neural Network applied on a dataset collected in our lab. Results show high classification performance for all methods giving up-to 99.95% classification accuracy. These patterns provide useful information about occupancy patterns, movement patterns, etc., which will be later used to allocate computational resources in the smart space accordingly. Furthermore, our implementation does not use any camera or microphone deployment, hence addressing potential privacy issues.","PeriodicalId":313846,"journal":{"name":"2018 International Symposium on Networks, Computers and Communications (ISNCC)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2018-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122119927","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：