Pub Date : 2020-08-01DOI: 10.1109/COINS49042.2020.9191672
M. Brandalero, Muhammad Ali, Laurens Le Jeune, Hector Gerardo Muñoz Hernandez, M. Veleski, B. Silva, J. Lemeire, Kristof Van Beeck, A. Touhafi, T. Goedemé, N. Mentens, D. Göhringer, M. Hübner
New achievements in Artificial Intelligence (AI) and Machine Learning (ML) are reported almost daily by the big companies. While those achievements are accomplished by fast and massive data processing techniques, the potential of embedded machine learning, where intelligent algorithms run in resource-constrained devices rather than in the cloud, is still not understood well by the majority of the industrial players and Small and Medium Entereprises (SMEs). Nevertheless, the potential embedded machine learning for processing high-performance algorithms without relying on expensive cloud solutions is perceived as very high. This potential has led to a broad demand by industry and SMEs for a practical and application-oriented feasibility study, which helps them to understand the potential benefits, but also the limitations of embedded AI. To address these needs, this paper presents the approach of the AITIA project, a consortium of four Universities which aims at developing and demonstrating best practices for embedded AI by means of four industrial case studies of high-relevance to the European industry and SMEs: sensors, security, automotive and industry 4.0.
{"title":"AITIA: Embedded AI Techniques for Embedded Industrial Applications","authors":"M. Brandalero, Muhammad Ali, Laurens Le Jeune, Hector Gerardo Muñoz Hernandez, M. Veleski, B. Silva, J. Lemeire, Kristof Van Beeck, A. Touhafi, T. Goedemé, N. Mentens, D. Göhringer, M. Hübner","doi":"10.1109/COINS49042.2020.9191672","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191672","url":null,"abstract":"New achievements in Artificial Intelligence (AI) and Machine Learning (ML) are reported almost daily by the big companies. While those achievements are accomplished by fast and massive data processing techniques, the potential of embedded machine learning, where intelligent algorithms run in resource-constrained devices rather than in the cloud, is still not understood well by the majority of the industrial players and Small and Medium Entereprises (SMEs). Nevertheless, the potential embedded machine learning for processing high-performance algorithms without relying on expensive cloud solutions is perceived as very high. This potential has led to a broad demand by industry and SMEs for a practical and application-oriented feasibility study, which helps them to understand the potential benefits, but also the limitations of embedded AI. To address these needs, this paper presents the approach of the AITIA project, a consortium of four Universities which aims at developing and demonstrating best practices for embedded AI by means of four industrial case studies of high-relevance to the European industry and SMEs: sensors, security, automotive and industry 4.0.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125362120","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191393
Georgios Tertytchny, M. Michael
Intelligent Fault Detection (IFD), the use of machine learning-based methods and algorithms for the fault detection in modern systems becomes nowadays important due to the large number of data being generated by devices embedded in such systems. A typical example of such systems is Internet of Things (IoT)-based Cyber-Physical Systems (CPS) where IoT devices are used for better monitoring and control of such systems but at the same time due to their nature are susceptible to component faults. IFD depends on the number of data generated in such systems and their representation using system characteristics (features). Instance-based dataset reduction schemes used in Machine Learning (ML) aim to reduce the volume of data required during training while maintaining or preserving testing accuracy. Such reductions lead to less storage and processing time required for the trained models, which enables the use of lightweight IFD approaches in embedded devices found in the core of IoT-based CPS systems. In this work, we propose a machine learning-based framework for instance-based dataset reduction applied for IFD models. Our proposed framework is experimentally evaluated over two datasets. Results show that reduction is possible for up to 15.51% with an average accuracy improvement of 17% on the set of evaluated classification algorithms.
{"title":"Dataset Reduction Framework For Intelligent Fault Detection In IoT-based Cyber-Physical Systems Using Machine Learning Techniques","authors":"Georgios Tertytchny, M. Michael","doi":"10.1109/COINS49042.2020.9191393","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191393","url":null,"abstract":"Intelligent Fault Detection (IFD), the use of machine learning-based methods and algorithms for the fault detection in modern systems becomes nowadays important due to the large number of data being generated by devices embedded in such systems. A typical example of such systems is Internet of Things (IoT)-based Cyber-Physical Systems (CPS) where IoT devices are used for better monitoring and control of such systems but at the same time due to their nature are susceptible to component faults. IFD depends on the number of data generated in such systems and their representation using system characteristics (features). Instance-based dataset reduction schemes used in Machine Learning (ML) aim to reduce the volume of data required during training while maintaining or preserving testing accuracy. Such reductions lead to less storage and processing time required for the trained models, which enables the use of lightweight IFD approaches in embedded devices found in the core of IoT-based CPS systems. In this work, we propose a machine learning-based framework for instance-based dataset reduction applied for IFD models. Our proposed framework is experimentally evaluated over two datasets. Results show that reduction is possible for up to 15.51% with an average accuracy improvement of 17% on the set of evaluated classification algorithms.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128995840","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191429
François Bouchaud, T. Vantroys, G. Grimaud, Pierrick Buret
More and more things around us are becoming digital and connected to the Internet. This market ranges from smart devices, wellness and health control to smart cities. This development offers to malicious parties the possibility of carrying out attacks, directly impacting the consumers of these new services. Thus, the connected objects are actors or witnesses of events that have occurred. This opens up a challenge for security and forensic investigations on the Internet of Things (IoT).In this article, we present the problem of finding connected objects on an offence scene. In the absence of a technical solution, the investigators limit themselves to a manual search. Hidden objects are often neither detected nor found. Thus, we aim to give a clear and precise image of the current devices. We also want to determine their position.This work focuses on the study of the digital signature of the scene and the radio frequency characteristics of the objects. To understand the electromagnetic environment, we use a software defined radio (SDR) and we develop several tools: a sensor for a single protocol and a mesh network of sensors. The SDR returns the used frequencies. The single receiver offers a global mapping of the environment on a given protocol. The multi-sensor mesh network gives a precise and targeted vision of the infrastructure connected to several protocols and frequencies. We propose to assess the relevance of the measurement methods in relation to operational needs, on the basis of a use case and feedbacks.
{"title":"Discovering Connected Objects in the Criminal Investigations","authors":"François Bouchaud, T. Vantroys, G. Grimaud, Pierrick Buret","doi":"10.1109/COINS49042.2020.9191429","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191429","url":null,"abstract":"More and more things around us are becoming digital and connected to the Internet. This market ranges from smart devices, wellness and health control to smart cities. This development offers to malicious parties the possibility of carrying out attacks, directly impacting the consumers of these new services. Thus, the connected objects are actors or witnesses of events that have occurred. This opens up a challenge for security and forensic investigations on the Internet of Things (IoT).In this article, we present the problem of finding connected objects on an offence scene. In the absence of a technical solution, the investigators limit themselves to a manual search. Hidden objects are often neither detected nor found. Thus, we aim to give a clear and precise image of the current devices. We also want to determine their position.This work focuses on the study of the digital signature of the scene and the radio frequency characteristics of the objects. To understand the electromagnetic environment, we use a software defined radio (SDR) and we develop several tools: a sensor for a single protocol and a mesh network of sensors. The SDR returns the used frequencies. The single receiver offers a global mapping of the environment on a given protocol. The multi-sensor mesh network gives a precise and targeted vision of the infrastructure connected to several protocols and frequencies. We propose to assess the relevance of the measurement methods in relation to operational needs, on the basis of a use case and feedbacks.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125602156","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191370
Arijit Nandi, F. Xhafa, L. Subirats, Santiago Fort
Emotions play a crucial role in learning. To improve and optimize electronic learning (e-Learning) outcomes, many researchers have investigated the role of emotions. Also, researchers have come up with many approaches to utilize one or many data modalities to achieve this goal, and they have been successful. But the recent advancements in technology and the internet of things (IoT) devices have brought a new dimension in e-Learning, with many input devices (such as webcams, fit-bands etc.) for interacting with e-Learners. This new dimension brings not only massive amounts of data with volume, variety, and velocity called multimodal data streams but also more challenges of mining those data in real-time. In this work, we have focused on state-of-the-art emotion recognition in e-Learning utilizing the multimodal data streams of learners. Also, we have thoroughly investigated the past research and surveys on emotion recognition methods in e-Learning to find the affecting emotions and their relations with the emotion measurement channels; and we have compared several data-stream classifiers for emotion recognition by utilizing multimodal physiological data streams. Finally, the future research opportunities to be addressed are also discussed.
{"title":"A Survey on Multimodal Data Stream Mining for e-Learner’s Emotion Recognition","authors":"Arijit Nandi, F. Xhafa, L. Subirats, Santiago Fort","doi":"10.1109/COINS49042.2020.9191370","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191370","url":null,"abstract":"Emotions play a crucial role in learning. To improve and optimize electronic learning (e-Learning) outcomes, many researchers have investigated the role of emotions. Also, researchers have come up with many approaches to utilize one or many data modalities to achieve this goal, and they have been successful. But the recent advancements in technology and the internet of things (IoT) devices have brought a new dimension in e-Learning, with many input devices (such as webcams, fit-bands etc.) for interacting with e-Learners. This new dimension brings not only massive amounts of data with volume, variety, and velocity called multimodal data streams but also more challenges of mining those data in real-time. In this work, we have focused on state-of-the-art emotion recognition in e-Learning utilizing the multimodal data streams of learners. Also, we have thoroughly investigated the past research and surveys on emotion recognition methods in e-Learning to find the affecting emotions and their relations with the emotion measurement channels; and we have compared several data-stream classifiers for emotion recognition by utilizing multimodal physiological data streams. Finally, the future research opportunities to be addressed are also discussed.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133525186","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191390
Matthias Knapp, Thomas Greiner, Xinyi Yang
This paper proposes a smart contract based approach enabling Internet of Things devices to exchange data in a secure and automatic way. This leads to new digital business models as pay-per-use establishing the vision of the Economy of Things. By using a blockchain there is no need for a trusted third party to secure transactions. We propose a novel use of smart contracts for assurance of data integrity, encryption key provision and payment. Thereby, a three layer architecture consisting of physical layer, on-chain layer and off-chain layer is designed. Proof of concept is based on an Ethereum Blockchain using Bosch XDK devices.
{"title":"Pay-per-use Sensor Data Exchange between IoT Devices by Blockchain and Smart Contract based Data and Encryption Key Management","authors":"Matthias Knapp, Thomas Greiner, Xinyi Yang","doi":"10.1109/COINS49042.2020.9191390","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191390","url":null,"abstract":"This paper proposes a smart contract based approach enabling Internet of Things devices to exchange data in a secure and automatic way. This leads to new digital business models as pay-per-use establishing the vision of the Economy of Things. By using a blockchain there is no need for a trusted third party to secure transactions. We propose a novel use of smart contracts for assurance of data integrity, encryption key provision and payment. Thereby, a three layer architecture consisting of physical layer, on-chain layer and off-chain layer is designed. Proof of concept is based on an Ethereum Blockchain using Bosch XDK devices.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124512010","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191653
M. Lücking, Raphael Manke, Markus Schinle, L. Kohout, S. Nickel, W. Stork
Analytics over data streams from Internet of Things (IoT) devices have become valuable information sources of user data, benefiting both healthcare service providers and patients. Current approaches of connecting IoT devices directly to central cloud architectures come with a number of disadvantages. One of the main disadvantages is that patient health data cannot be easily shared among different healthcare applications or service providers, limitating the full potential of data-driven analysis over healthcare data streams. In this paper, we present a new decentralized and permissionless data management system which empowers patients to securely and selectively share their own personal data among other patients or healthcare service providers. We depart from current decentralized data management approaches that often involve high transaction fees, scalability problems or a high computational overhead that are not acceptable for resource-constrained IoT devices. The contribution of our work lies in coupling the IOTA Tangle technology as auditable and distributed data storage of the patients encrypted time-series IoT data streams with an efficient key management scheme in order to define fine-grained stream-specific access policies. Based on a reference implementation, different experimental tests were made to highlight the feasibility and applicability of our decentralized data management system for end-to-end encrypted IoT data streams.
{"title":"Decentralized patient-centric data management for sharing IoT data streams","authors":"M. Lücking, Raphael Manke, Markus Schinle, L. Kohout, S. Nickel, W. Stork","doi":"10.1109/COINS49042.2020.9191653","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191653","url":null,"abstract":"Analytics over data streams from Internet of Things (IoT) devices have become valuable information sources of user data, benefiting both healthcare service providers and patients. Current approaches of connecting IoT devices directly to central cloud architectures come with a number of disadvantages. One of the main disadvantages is that patient health data cannot be easily shared among different healthcare applications or service providers, limitating the full potential of data-driven analysis over healthcare data streams. In this paper, we present a new decentralized and permissionless data management system which empowers patients to securely and selectively share their own personal data among other patients or healthcare service providers. We depart from current decentralized data management approaches that often involve high transaction fees, scalability problems or a high computational overhead that are not acceptable for resource-constrained IoT devices. The contribution of our work lies in coupling the IOTA Tangle technology as auditable and distributed data storage of the patients encrypted time-series IoT data streams with an efficient key management scheme in order to define fine-grained stream-specific access policies. Based on a reference implementation, different experimental tests were made to highlight the feasibility and applicability of our decentralized data management system for end-to-end encrypted IoT data streams.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126958730","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191392
M. Mozafari, F. Firouzi, Bahareh J. Farahani
Stress is a body’s natural way of responding to any kind of demand or challenge that everyone experiences from time to time. Although short-term stress typically does not impose a health burden, exposure to prolonged stress can lead to significant adverse physiological and behavioral changes. Coping with the impact of stress is a challenging task and in this context, stress assessment is essential in preventing detrimental long-term effects. The public embracement of connected wearable Internet of Things (IoT) devices, as well as the proliferation of Artificial Intelligence (AI) and Machine Learning (ML) technologies, have generated new opportunities for personalized stress tracking and management. Despite the advantages of this paradigm shift – including availability and accessibility, cost-effective delivery, and proactive intervention – still, many challenges need to be addressed to be able to develop ubiquitous solutions. In this paper, we present a comprehensive and generalizable IoT-based stress-level detection method with the following key attributes: (i) Connected: deploying vigilant IoT-based wearables and sensing technologies for continuous stress-related data collection; (ii) Data-driven: combining multimodal and heterogeneous data sources from sensor readouts; (iii) Hierarchical: consisting of device/sensor, data, intelligence, and service layers. Experimental results based on real-life stress datasets highlight the accuracy of the proposed approach for assessing the stress-level compared to state-of-the-art solutions.
{"title":"Towards IoT-enabled Multimodal Mental Stress Monitoring","authors":"M. Mozafari, F. Firouzi, Bahareh J. Farahani","doi":"10.1109/COINS49042.2020.9191392","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191392","url":null,"abstract":"Stress is a body’s natural way of responding to any kind of demand or challenge that everyone experiences from time to time. Although short-term stress typically does not impose a health burden, exposure to prolonged stress can lead to significant adverse physiological and behavioral changes. Coping with the impact of stress is a challenging task and in this context, stress assessment is essential in preventing detrimental long-term effects. The public embracement of connected wearable Internet of Things (IoT) devices, as well as the proliferation of Artificial Intelligence (AI) and Machine Learning (ML) technologies, have generated new opportunities for personalized stress tracking and management. Despite the advantages of this paradigm shift – including availability and accessibility, cost-effective delivery, and proactive intervention – still, many challenges need to be addressed to be able to develop ubiquitous solutions. In this paper, we present a comprehensive and generalizable IoT-based stress-level detection method with the following key attributes: (i) Connected: deploying vigilant IoT-based wearables and sensing technologies for continuous stress-related data collection; (ii) Data-driven: combining multimodal and heterogeneous data sources from sensor readouts; (iii) Hierarchical: consisting of device/sensor, data, intelligence, and service layers. Experimental results based on real-life stress datasets highlight the accuracy of the proposed approach for assessing the stress-level compared to state-of-the-art solutions.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123282937","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191421
Alexander Lamprecht, Moritz Riesterer, S. Steinhorst
Recently, Electric Vehicles (EVs) are becoming more widespread. However, their mass adoption is hindered by the limited capacity of their Energy Storage System (ESS). Nowadays mainly Lithium-ion (Li-ion) technology is used for mobile applications, however, their energy density and cost put a hard limit on the maximum size of viable EV battery packs. Therefore, it is crucial to use existing technologies as effective as possible. To efficiently use a battery pack over its entire lifetime, the State of Health (SoH) of the cells needs to be taken into account. In this paper, we propose a novel SoH estimation method, based on the battery pack’s behavior during Active Charge Balancing (ACB). From this behavior we are deriving a metric and show that it strongly correlates with the SoH. We use this metric, together with other cell parameters, to train a Random Forest (RF) regression estimator. To gather the training data, we implemented a modular simulation framework, that is able to reproduce the charging and discharging cycles, the charge balancing processes, as well as the aging behavior of battery packs over their entire lifetime. Besides showing a strong correlation between balancing behavior and SoH, we are able to estimate the cells’ SoH with an accuracy of 1.94 % for the capacity and 4.28 % for the resistance, respectively. Our capacity SoH estimation outperforms state-of the-art machine learning approaches, while we are among very few to even provide an estimate for the resistance with a high accuracy.
{"title":"Random Forest Regression of Charge Balancing Data: A State of Health Estimation Method for Electric Vehicle Batteries","authors":"Alexander Lamprecht, Moritz Riesterer, S. Steinhorst","doi":"10.1109/COINS49042.2020.9191421","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191421","url":null,"abstract":"Recently, Electric Vehicles (EVs) are becoming more widespread. However, their mass adoption is hindered by the limited capacity of their Energy Storage System (ESS). Nowadays mainly Lithium-ion (Li-ion) technology is used for mobile applications, however, their energy density and cost put a hard limit on the maximum size of viable EV battery packs. Therefore, it is crucial to use existing technologies as effective as possible. To efficiently use a battery pack over its entire lifetime, the State of Health (SoH) of the cells needs to be taken into account. In this paper, we propose a novel SoH estimation method, based on the battery pack’s behavior during Active Charge Balancing (ACB). From this behavior we are deriving a metric and show that it strongly correlates with the SoH. We use this metric, together with other cell parameters, to train a Random Forest (RF) regression estimator. To gather the training data, we implemented a modular simulation framework, that is able to reproduce the charging and discharging cycles, the charge balancing processes, as well as the aging behavior of battery packs over their entire lifetime. Besides showing a strong correlation between balancing behavior and SoH, we are able to estimate the cells’ SoH with an accuracy of 1.94 % for the capacity and 4.28 % for the resistance, respectively. Our capacity SoH estimation outperforms state-of the-art machine learning approaches, while we are among very few to even provide an estimate for the resistance with a high accuracy.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134338934","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191652
Misha Abraham, K. Mohan
Blockchains are globally gaining traction and gradually disrupting the traditional transactional eco-systems by eliminating the non-value adding parties in the value chain. Although blockchains enables digital currency transactions, distributed consensus models and provenance, the problem of scalability, security and privacy has to be solved for the blockchains to be utilized in its full potential. Typically all the transactions recorded in blockchain are visible to all the participants. Even though some blockchain frameworks offers private transactions they still lack transactional privacy and confidentiality. Privacy preserving smart contracts is an emerging field which guarantees the privacy of transactions during runtime and ensures confidentiality as well. In this paper we analyze various frameworks and methodologies and propose a systematic way of choosing the right privacy preserving smart contract framework for enterprise needs and requirements.
{"title":"Decision Framework and Detailed Analysis on Privacy Preserving Smart Contract Frameworks for Enterprise Blockchain Applications","authors":"Misha Abraham, K. Mohan","doi":"10.1109/COINS49042.2020.9191652","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191652","url":null,"abstract":"Blockchains are globally gaining traction and gradually disrupting the traditional transactional eco-systems by eliminating the non-value adding parties in the value chain. Although blockchains enables digital currency transactions, distributed consensus models and provenance, the problem of scalability, security and privacy has to be solved for the blockchains to be utilized in its full potential. Typically all the transactions recorded in blockchain are visible to all the participants. Even though some blockchain frameworks offers private transactions they still lack transactional privacy and confidentiality. Privacy preserving smart contracts is an emerging field which guarantees the privacy of transactions during runtime and ensures confidentiality as well. In this paper we analyze various frameworks and methodologies and propose a systematic way of choosing the right privacy preserving smart contract framework for enterprise needs and requirements.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133134490","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 : 2020-08-01DOI: 10.1109/COINS49042.2020.9191401
Stelios N. Neophytou, Ilias Alexopoulos, I. Kyriakides, Pavlos Tsiantis, Ehson Abdi, D. Hayes
Representing the complexity of natural and human processes in the maritime environment requires the collection and processing of large heterogeneous data sets. Due to the scarcity of sensing resources, information collection needs to be guided by intelligent, agile processes. Therefore, raw heterogeneous data sets need to be standardized and processed locally at the sensing node to reduce communication and computational load associated with transmitting data at a fusion and decision support center. This work presents an IoT framework for maritime applications that consists of two independent, yet compatible hardware designs. One provides maritime data standardization to enable interoperability of ocean sensing systems, and the other provides information acquisition agility to enable efficient allocation of limited edge node resources. An application for ocean sound classification using signal decomposition, suitable for edge processing on-board of IoT systems, is provided as an example of the use of the framework. Three different edge processing implementations are presented and the corresponding performance results are reported and compared.
{"title":"An IoT framework for Edge Processing of Ocean Sounds","authors":"Stelios N. Neophytou, Ilias Alexopoulos, I. Kyriakides, Pavlos Tsiantis, Ehson Abdi, D. Hayes","doi":"10.1109/COINS49042.2020.9191401","DOIUrl":"https://doi.org/10.1109/COINS49042.2020.9191401","url":null,"abstract":"Representing the complexity of natural and human processes in the maritime environment requires the collection and processing of large heterogeneous data sets. Due to the scarcity of sensing resources, information collection needs to be guided by intelligent, agile processes. Therefore, raw heterogeneous data sets need to be standardized and processed locally at the sensing node to reduce communication and computational load associated with transmitting data at a fusion and decision support center. This work presents an IoT framework for maritime applications that consists of two independent, yet compatible hardware designs. One provides maritime data standardization to enable interoperability of ocean sensing systems, and the other provides information acquisition agility to enable efficient allocation of limited edge node resources. An application for ocean sound classification using signal decomposition, suitable for edge processing on-board of IoT systems, is provided as an example of the use of the framework. Three different edge processing implementations are presented and the corresponding performance results are reported and compared.","PeriodicalId":350108,"journal":{"name":"2020 International Conference on Omni-layer Intelligent Systems (COINS)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124044857","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：