Pub Date : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00037
Prince Abudu, A. Markham
Learning emergent communication remains a longstanding challenge in distributed Internet of Things (IoT) settings. The need to overcome tedious, complex design of hand-engineered communication protocols coupled with superior prediction and classification capabilities, make Deep Networks attractive for distributed, cooperative IoT settings. In such settings, sensing devices must sense, communicate and provide actuation whilst executing a resource-aware operation. Reliance on the Cloud for knowledge discovery is fraught with latency, connectivity, and bandwidth issues. We continue to see the emergence of edge-centric paradigms in which sensing devices at the network edge are endowed with intelligence. In turn, these devices are equipped with self-organization capabilities, robust real-time capabilities, reduced bandwidth requirements and greater context awareness. In this paper, we propose a novel, scalable communicating Convolutional Recurrent Neural Network (C-RNN) architecture for distributed IoT settings. Our framework automatically learns emergent communication in a purely data-driven way. Extensive experimental evaluation shows that our framework can learn to solve distributed image classification tasks, optimises for communication cost, is robust to lossy-links and can scale to multiple nodes.
{"title":"Deep Emergent Communication for the IoT","authors":"Prince Abudu, A. Markham","doi":"10.1109/SMARTCOMP50058.2020.00037","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00037","url":null,"abstract":"Learning emergent communication remains a longstanding challenge in distributed Internet of Things (IoT) settings. The need to overcome tedious, complex design of hand-engineered communication protocols coupled with superior prediction and classification capabilities, make Deep Networks attractive for distributed, cooperative IoT settings. In such settings, sensing devices must sense, communicate and provide actuation whilst executing a resource-aware operation. Reliance on the Cloud for knowledge discovery is fraught with latency, connectivity, and bandwidth issues. We continue to see the emergence of edge-centric paradigms in which sensing devices at the network edge are endowed with intelligence. In turn, these devices are equipped with self-organization capabilities, robust real-time capabilities, reduced bandwidth requirements and greater context awareness. In this paper, we propose a novel, scalable communicating Convolutional Recurrent Neural Network (C-RNN) architecture for distributed IoT settings. Our framework automatically learns emergent communication in a purely data-driven way. Extensive experimental evaluation shows that our framework can learn to solve distributed image classification tasks, optimises for communication cost, is robust to lossy-links and can scale to multiple nodes.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132430038","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 : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00058
C. Puliafito, A. Virdis, E. Mingozzi
Integration between fog computing and the Internet of Things (IoT) paves the way to a plethora of promising opportunities. Device mobility might however impair fog computing benefits (e.g., low latency), which are indeed an outcome of fog proximity to end users/devices. A solution to this problem is to migrate the fog service across the fog infrastructure, thus to keep the distance to the served mobile device as low as possible. In this paper, we consider a fog service to be implemented as the combination of two containers, and we detail the demo through which we plan to show the impact of fog service migration on application performance. To this purpose, we plan to deploy an Augmented Reality (AR) application that detects vehicles in video frames and augments the latter with bounding boxes built around the detected vehicles. We offer to the audience the possibility to: (i) interact with the employed testbed by triggering device mobility; (ii) visualise the difference between migrating and not migrating the fog service in response to device mobility.
{"title":"Migration of Multi-container Services in the Fog to Support Things Mobility","authors":"C. Puliafito, A. Virdis, E. Mingozzi","doi":"10.1109/SMARTCOMP50058.2020.00058","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00058","url":null,"abstract":"Integration between fog computing and the Internet of Things (IoT) paves the way to a plethora of promising opportunities. Device mobility might however impair fog computing benefits (e.g., low latency), which are indeed an outcome of fog proximity to end users/devices. A solution to this problem is to migrate the fog service across the fog infrastructure, thus to keep the distance to the served mobile device as low as possible. In this paper, we consider a fog service to be implemented as the combination of two containers, and we detail the demo through which we plan to show the impact of fog service migration on application performance. To this purpose, we plan to deploy an Augmented Reality (AR) application that detects vehicles in video frames and augments the latter with bounding boxes built around the detected vehicles. We offer to the audience the possibility to: (i) interact with the employed testbed by triggering device mobility; (ii) visualise the difference between migrating and not migrating the fog service in response to device mobility.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130100223","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 : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00046
D. Grimm, Simon Leiner, Martin Sommer, Felix Pistorius, E. Sax
Modern cars are equipped with a wide variety of sensors generating continually growing amounts of data. This data is transmitted via bus systems such as Controller Area Network (CAN) inside of the vehicle to the microcontroller-based Electronic Control Units. By connecting the vehicle to its surroundings using wireless interfaces, this data becomes accessible to the vehicle manufacturer from a distance. Through the opening to the outside, cyber attacks can exploit these interfaces and introduce major risks to the privacy and safety of vehicle users. Hence, suitable methods for vehicle security monitoring such as intrusion detection and logging are needed. In this work, we focus on the logging of network data, since this data is useful for the development of security updates, countermeasures and incident signatures. On this account, we propose a new method to aggregate the data of the CAN bus. The method combines CAN frames into so-called flows. Each flow contains a set of packets that share a certain common attribute (e.g.: frame type and identifier). To integrate security monitoring of vehicle fleets seamlessly into backend server systems, the gathered CAN flow data is stored in an industry standard data format. Additionally, the payload data is included in the flow format using a compression algorithm to leverage deep-packet inspection. The evaluation results with realworld vehicle data indicate that in our case about 40 % reduction of the overall data size is possible with our method compared to industry-standard formats for storing CAN frames. On this account, we propose a new method to aggregate the data of the CAN bus. The method combines CAN frames into so-called flows. Each flow contains a set of packets that share a certain common attribute (e.g.: frame type and identifier). To integrate security monitoring of vehicle fleets seamlessly into backend server systems, the gathered CAN flow data is stored in an industry standard data format. Additionally, the payload data is included in the flow format using a compression algorithm to leverage deep-packet inspection. The evaluation results with realworld vehicle data indicate that in our case about 40 % reduction of the overall data size is possible with our method compared to industry-standard formats for storing CAN frames.
{"title":"Flow-based Aggregation of CAN Frames with Compressed Payload","authors":"D. Grimm, Simon Leiner, Martin Sommer, Felix Pistorius, E. Sax","doi":"10.1109/SMARTCOMP50058.2020.00046","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00046","url":null,"abstract":"Modern cars are equipped with a wide variety of sensors generating continually growing amounts of data. This data is transmitted via bus systems such as Controller Area Network (CAN) inside of the vehicle to the microcontroller-based Electronic Control Units. By connecting the vehicle to its surroundings using wireless interfaces, this data becomes accessible to the vehicle manufacturer from a distance. Through the opening to the outside, cyber attacks can exploit these interfaces and introduce major risks to the privacy and safety of vehicle users. Hence, suitable methods for vehicle security monitoring such as intrusion detection and logging are needed. In this work, we focus on the logging of network data, since this data is useful for the development of security updates, countermeasures and incident signatures. On this account, we propose a new method to aggregate the data of the CAN bus. The method combines CAN frames into so-called flows. Each flow contains a set of packets that share a certain common attribute (e.g.: frame type and identifier). To integrate security monitoring of vehicle fleets seamlessly into backend server systems, the gathered CAN flow data is stored in an industry standard data format. Additionally, the payload data is included in the flow format using a compression algorithm to leverage deep-packet inspection. The evaluation results with realworld vehicle data indicate that in our case about 40 % reduction of the overall data size is possible with our method compared to industry-standard formats for storing CAN frames. On this account, we propose a new method to aggregate the data of the CAN bus. The method combines CAN frames into so-called flows. Each flow contains a set of packets that share a certain common attribute (e.g.: frame type and identifier). To integrate security monitoring of vehicle fleets seamlessly into backend server systems, the gathered CAN flow data is stored in an industry standard data format. Additionally, the payload data is included in the flow format using a compression algorithm to leverage deep-packet inspection. The evaluation results with realworld vehicle data indicate that in our case about 40 % reduction of the overall data size is possible with our method compared to industry-standard formats for storing CAN frames.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127863590","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 : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00083
S. Saponara, Abdussalam Elhanashi, A. Gagliardi
This work presents a video-camera-based fire/smoke sensing technique for early warning in antifire surveillance systems. By exploiting R-CNN (Region Convolutional Neural Network), a detection technique is developed for the measurement of the smoke and fire characteristics in restricted video surveillance environments, both indoor (e.g. a railway carriage, container, bus wagon, homes, offices), or outdoor (e.g. storage or parking areas). The considered application scenario, to reduce costs, is composed of a single, fixed camera per scene, working in the visible spectral range already installed in a closed-circuit television system for surveillance purposes. The training phase is done with indoor and outdoor image sets, with both smoke and non-smoke scenarios to assess the capability of true-positive/true-negative detection and false-positive/false-negative rejection. To generate the training set, a Ground Truth Labeler app is used and applied to the open-access Firesense dataset, including tens of indoor and outdoor fire/ smoke scenes developed as the output of an FP7 project, plus other videos not publicly available, provided by Trenitalia during specific fire/smoke tests on railway wagons performed at their testing facility in Osmannoro, Italy. The achieved results show that the proposed R-CNN technique is suitable for the creation of a smart video-surveillance system for fire/smoke detection.
这项工作提出了一种基于视频摄像机的火灾/烟雾传感技术，用于防火监视系统的早期预警。通过利用R-CNN(区域卷积神经网络)，开发了一种检测技术，用于测量室内(例如铁路车厢，集装箱，公共汽车车厢，家庭，办公室)或室外(例如仓库或停车场)受限视频监控环境中的烟雾和火灾特征。为了降低成本，考虑的应用方案是在一个闭路电视系统中安装一个固定的摄像机，在可见光范围内工作，用于监视目的。训练阶段使用室内和室外图像集，烟雾和非烟雾场景来评估真阳性/真阴性检测和假阳性/假阴性拒绝的能力。为了生成训练集，使用了Ground Truth Labeler应用程序，并将其应用于开放获取的Firesense数据集，包括数十个室内和室外火灾/烟雾场景，作为FP7项目的输出，以及其他未公开的视频，这些视频由意大利铁路公司在其位于意大利Osmannoro的测试设施中对铁路车厢进行了特定的火灾/烟雾测试。所取得的结果表明，所提出的R-CNN技术适用于创建用于火灾/烟雾探测的智能视频监控系统。
{"title":"Exploiting R-CNN for video smoke/fire sensing in antifire surveillance indoor and outdoor systems for smart cities","authors":"S. Saponara, Abdussalam Elhanashi, A. Gagliardi","doi":"10.1109/SMARTCOMP50058.2020.00083","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00083","url":null,"abstract":"This work presents a video-camera-based fire/smoke sensing technique for early warning in antifire surveillance systems. By exploiting R-CNN (Region Convolutional Neural Network), a detection technique is developed for the measurement of the smoke and fire characteristics in restricted video surveillance environments, both indoor (e.g. a railway carriage, container, bus wagon, homes, offices), or outdoor (e.g. storage or parking areas). The considered application scenario, to reduce costs, is composed of a single, fixed camera per scene, working in the visible spectral range already installed in a closed-circuit television system for surveillance purposes. The training phase is done with indoor and outdoor image sets, with both smoke and non-smoke scenarios to assess the capability of true-positive/true-negative detection and false-positive/false-negative rejection. To generate the training set, a Ground Truth Labeler app is used and applied to the open-access Firesense dataset, including tens of indoor and outdoor fire/ smoke scenes developed as the output of an FP7 project, plus other videos not publicly available, provided by Trenitalia during specific fire/smoke tests on railway wagons performed at their testing facility in Osmannoro, Italy. The achieved results show that the proposed R-CNN technique is suitable for the creation of a smart video-surveillance system for fire/smoke detection.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"351 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115956787","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 : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00079
K. Bakker, R. Knight, J. Leape, Alan K. Mackworth, R. Ng, Max Ritts
This paper presents a meta-review of digital technology applications for dynamic environmental management, which provide contemporaneous signals and incentives to influence resource users' behaviours, thereby generating more spatially and temporally flexible responses to variable ecosystem conditions.
{"title":"Digital Technologies and Dynamic Resource Management","authors":"K. Bakker, R. Knight, J. Leape, Alan K. Mackworth, R. Ng, Max Ritts","doi":"10.1109/SMARTCOMP50058.2020.00079","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00079","url":null,"abstract":"This paper presents a meta-review of digital technology applications for dynamic environmental management, which provide contemporaneous signals and incentives to influence resource users' behaviours, thereby generating more spatially and temporally flexible responses to variable ecosystem conditions.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125309583","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 : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00067
Lena Oden, Thorsten Witt
Wearables providing fall detection can provide faster emergency services for elderly, yet privacy concerns limit acceptance of this technology. In this work, we evaluate a machine learning algorithm, called Bosnai, for embedded edge devices to detect falls. The prototype is Arduino based and can be integrated into fabrics for clothes, belts, or other accessories. The fall detection is performed offline on the device. We used data from public datasets of movement and fall events to train a tree-based machine learning model. We evaluated different combinations of prepossessed parameters as input features for the learning algorithm. The learned model is transferred to the microcontroller and can classify the sensor data offline but in real-time. We evaluate the performance of our device by performing intensive test runs with the prototype. The microcontroller is extremely limited in terms of memory capacity and computing performance, which only allows a limited number of features for learning. For this reason, it is especially important to preprocess the raw accelerator data and select the right features for training and inference. Our results show that the best performance (approx. 94.2 % accuracy) is achieved when we choose absolute acceleration and variance as features, with a sampling rate of 20 Hz and a recording window of 3s, as this system is the most robust against external interference.
{"title":"Fall-detection on a wearable micro controller using machine learning algorithms","authors":"Lena Oden, Thorsten Witt","doi":"10.1109/SMARTCOMP50058.2020.00067","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00067","url":null,"abstract":"Wearables providing fall detection can provide faster emergency services for elderly, yet privacy concerns limit acceptance of this technology. In this work, we evaluate a machine learning algorithm, called Bosnai, for embedded edge devices to detect falls. The prototype is Arduino based and can be integrated into fabrics for clothes, belts, or other accessories. The fall detection is performed offline on the device. We used data from public datasets of movement and fall events to train a tree-based machine learning model. We evaluated different combinations of prepossessed parameters as input features for the learning algorithm. The learned model is transferred to the microcontroller and can classify the sensor data offline but in real-time. We evaluate the performance of our device by performing intensive test runs with the prototype. The microcontroller is extremely limited in terms of memory capacity and computing performance, which only allows a limited number of features for learning. For this reason, it is especially important to preprocess the raw accelerator data and select the right features for training and inference. Our results show that the best performance (approx. 94.2 % accuracy) is achieved when we choose absolute acceleration and variance as features, with a sampling rate of 20 Hz and a recording window of 3s, as this system is the most robust against external interference.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122672302","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 : 2020-09-01DOI: 10.1109/smartcomp50058.2020.00019
Sajal K. Das, H. Yamana, M. Conti, A. Dubey, K. Yasumoto
Smart computing aiming to at improve human quality of life and experience represents the next wave of computing. Key technologies contributing to the realization of smart and connected communities include sensing, IoT, mobile and pervasive computing, cyber-physical-social systems, big data, machine learning, data analytics, social and cognitive computing. Smart computing helps solve a wide variety of societal challenges related to transportation, energy, healthcare, finance, disaster management, and so on. At the core of these systems, critical issues are security, privacy, reliability, resiliency, and robustness.
{"title":"Message from General Chairs and TPC Chairs","authors":"Sajal K. Das, H. Yamana, M. Conti, A. Dubey, K. Yasumoto","doi":"10.1109/smartcomp50058.2020.00019","DOIUrl":"https://doi.org/10.1109/smartcomp50058.2020.00019","url":null,"abstract":"Smart computing aiming to at improve human quality of life and experience represents the next wave of computing. Key technologies contributing to the realization of smart and connected communities include sensing, IoT, mobile and pervasive computing, cyber-physical-social systems, big data, machine learning, data analytics, social and cognitive computing. Smart computing helps solve a wide variety of societal challenges related to transportation, energy, healthcare, finance, disaster management, and so on. At the core of these systems, critical issues are security, privacy, reliability, resiliency, and robustness.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132456647","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 : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00091
Antonio Biscotti, Carlo Giannelli, Cedric Franck Ngatcha Keyi, R. Lazzarini, Assunta Sardone, C. Stefanelli, Giovanni Virgilli
In modern society, food safety is becoming more and more important. The adoption of appropriate practices, such as the ones defined in the HACCP system, during food production, handling, preparation, and storage can reasonably guarantee food safety. However, it is not easy to apply HACCP methodologies in an automatic form, thus hindering its use in industrial machines. To solve this problem, the paper presents a novel solution adopting Internet of Things (IoT) and Blockchain technologies in the ice cream production process to automate the enforcement of HACCP directives. The new Carpigiani ice cream making machines exploit IoT for the automation of data gathering (in particular the temperature, that is of particular concern for dairy products) and a Blockchain solution for a tamper-proof and non-repudiable distributed storage of HACCP sensitive production data.
{"title":"Internet of Things and Blockchain Technologies for Food Safety Systems","authors":"Antonio Biscotti, Carlo Giannelli, Cedric Franck Ngatcha Keyi, R. Lazzarini, Assunta Sardone, C. Stefanelli, Giovanni Virgilli","doi":"10.1109/SMARTCOMP50058.2020.00091","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00091","url":null,"abstract":"In modern society, food safety is becoming more and more important. The adoption of appropriate practices, such as the ones defined in the HACCP system, during food production, handling, preparation, and storage can reasonably guarantee food safety. However, it is not easy to apply HACCP methodologies in an automatic form, thus hindering its use in industrial machines. To solve this problem, the paper presents a novel solution adopting Internet of Things (IoT) and Blockchain technologies in the ice cream production process to automate the enforcement of HACCP directives. The new Carpigiani ice cream making machines exploit IoT for the automation of data gathering (in particular the temperature, that is of particular concern for dairy products) and a Blockchain solution for a tamper-proof and non-repudiable distributed storage of HACCP sensitive production data.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132866218","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 : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00092
Kotaro Chinen, Hiroaki Anada
We consider the security definition of decentralized multi-authority anonymous authentication schemes (DMA-AAuth) which was proposed by Anada-Arita at ICICS2018. The security is against causing-misauthentication attack, and we modify it to capture a threat of corrupted key-issuing authorities. Then we prove that the concrete scheme proposed by Anada at CANDAR'19 is secure under the new definition. Next, we evaluate efficiency of the concrete scheme by implementation. We use the C programming language with the TEPLA library.
{"title":"Security Reconsideration and Efficiency Evaluation of Decentralized Multi-authority Anonymous Authentication Scheme","authors":"Kotaro Chinen, Hiroaki Anada","doi":"10.1109/SMARTCOMP50058.2020.00092","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00092","url":null,"abstract":"We consider the security definition of decentralized multi-authority anonymous authentication schemes (DMA-AAuth) which was proposed by Anada-Arita at ICICS2018. The security is against causing-misauthentication attack, and we modify it to capture a threat of corrupted key-issuing authorities. Then we prove that the concrete scheme proposed by Anada at CANDAR'19 is secure under the new definition. Next, we evaluate efficiency of the concrete scheme by implementation. We use the C programming language with the TEPLA library.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"10 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132174490","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 : 2020-09-01DOI: 10.1109/SMARTCOMP50058.2020.00027
Fabrizio De Vita, Giorgio Nocera, Dario Bruneo, V. Tomaselli, Davide Giacalone, Sajal K. Das
Diagnosis of plant health conditions is gaining significant attention in smart agriculture. Timely recognition of early symptoms of a disease can help avoid the spread of epidemics on the plantations. In this regard, most of the existing solutions use some AI techniques on smart edge devices (IoTs or intelligent Cyber Physical Systems), typically equipped with a hardware like sensors and actuators. However, the resource constraints on such devices like energy (power), memory and computation capability, make the execution of complex operations and AI algorithms (neural network models) for disease detection quite challenging. To this end, compression and quantization techniques offer viable solutions to reduce the memory footprint of neural networks while maximizing performance on the constrained devices. In this paper, we realized a real intelligent CPS on top of which we implemented an AI application, called Deep Leaf running on a microcontroller of the STM32 family, to detect coffee plant diseases with the help of a Quantized Convolutional Neural Network (Q-CNN) model. We present a quantitative analysis of Deep Leaf by comparing five different deep learning models: a 32-bit floating point model, a compressed model, and three different types of quantized models exhibiting differences in terms of accuracy, memory utilization, average inference time, and energy consumption. Experimental results show that the proposed Deep Leaf detector is able to correctly classify the plant health condition with an accuracy of 96%, thus demonstrating the feasibility of our approach on a Smart Edge platform.
{"title":"Quantitative Analysis of Deep Leaf: a Plant Disease Detector on the Smart Edge","authors":"Fabrizio De Vita, Giorgio Nocera, Dario Bruneo, V. Tomaselli, Davide Giacalone, Sajal K. Das","doi":"10.1109/SMARTCOMP50058.2020.00027","DOIUrl":"https://doi.org/10.1109/SMARTCOMP50058.2020.00027","url":null,"abstract":"Diagnosis of plant health conditions is gaining significant attention in smart agriculture. Timely recognition of early symptoms of a disease can help avoid the spread of epidemics on the plantations. In this regard, most of the existing solutions use some AI techniques on smart edge devices (IoTs or intelligent Cyber Physical Systems), typically equipped with a hardware like sensors and actuators. However, the resource constraints on such devices like energy (power), memory and computation capability, make the execution of complex operations and AI algorithms (neural network models) for disease detection quite challenging. To this end, compression and quantization techniques offer viable solutions to reduce the memory footprint of neural networks while maximizing performance on the constrained devices. In this paper, we realized a real intelligent CPS on top of which we implemented an AI application, called Deep Leaf running on a microcontroller of the STM32 family, to detect coffee plant diseases with the help of a Quantized Convolutional Neural Network (Q-CNN) model. We present a quantitative analysis of Deep Leaf by comparing five different deep learning models: a 32-bit floating point model, a compressed model, and three different types of quantized models exhibiting differences in terms of accuracy, memory utilization, average inference time, and energy consumption. Experimental results show that the proposed Deep Leaf detector is able to correctly classify the plant health condition with an accuracy of 96%, thus demonstrating the feasibility of our approach on a Smart Edge platform.","PeriodicalId":346827,"journal":{"name":"2020 IEEE International Conference on Smart Computing (SMARTCOMP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131324573","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：