Pub Date : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975955
I. Zualkernan, Nadeen Ahmed, A. Elmeligy, Adham Abdelnaby, Nouran Sheta
Sensor data consistency in Internet of Things (IoT) Applications is the problem of ensuring that large number of sensors in a system are providing mutually consistent values. Detection of data inconsistency can be used to detect unusual conditions like malicious intrusion and other anomalous situation. Machine learning-based anomaly detection approaches can be used to detect sensor data inconsistency. This paper studies the problem of sensor data consistency in the context of detecting hotspots in sensor data being generated in pairs of sensors embedded in a commercial IoT system deployed to monitor grain in large horizontal grain bins. The paper explores how well traditional anomaly detection machine learning algorithms like Location Factor, Isolation Forest, and One class support vector machine work in this environment. A memory efficient Long Short-Term Memory (LSTM) deep learning model was proposed that outperformed the traditional machine learning approaches.
{"title":"IoT Sensor Data Consistency using Deep Learning","authors":"I. Zualkernan, Nadeen Ahmed, A. Elmeligy, Adham Abdelnaby, Nouran Sheta","doi":"10.1109/IoTaIS56727.2022.9975955","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975955","url":null,"abstract":"Sensor data consistency in Internet of Things (IoT) Applications is the problem of ensuring that large number of sensors in a system are providing mutually consistent values. Detection of data inconsistency can be used to detect unusual conditions like malicious intrusion and other anomalous situation. Machine learning-based anomaly detection approaches can be used to detect sensor data inconsistency. This paper studies the problem of sensor data consistency in the context of detecting hotspots in sensor data being generated in pairs of sensors embedded in a commercial IoT system deployed to monitor grain in large horizontal grain bins. The paper explores how well traditional anomaly detection machine learning algorithms like Location Factor, Isolation Forest, and One class support vector machine work in this environment. A memory efficient Long Short-Term Memory (LSTM) deep learning model was proposed that outperformed the traditional machine learning approaches.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123439666","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975857
Rhenaldy, Ladysa Stella Karenza, Ivan Halim Parmonangan, F. Kurniadi
The perceived audio quality is one of the key factors that may determine a text-to-speech system’s success in the market. Therefore, it is important to conduct audio quality evaluation before releasing such system into the market. Evaluating the synthesized audio quality is usually done either subjectively or objectively with their own advantages and disadvantages. Subjective methods usually require a large amount of time and resources, while objective methods lack human influence factors, which are crucial for deriving the subjective perception of quality. These human influence factors are manifested inside an individual’s brain in forms such as electroencephalograph (EEG). Thus, in this study, we performed audio quality prediction using EEG data. Since the data used in this study is small, we also compared the prediction result of the augmented and the non-augmented data. Our result shows that certain method yield significantly better prediction with augmented training data.
{"title":"Predicting Text-To-Speech Quality using Brain Activity","authors":"Rhenaldy, Ladysa Stella Karenza, Ivan Halim Parmonangan, F. Kurniadi","doi":"10.1109/IoTaIS56727.2022.9975857","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975857","url":null,"abstract":"The perceived audio quality is one of the key factors that may determine a text-to-speech system’s success in the market. Therefore, it is important to conduct audio quality evaluation before releasing such system into the market. Evaluating the synthesized audio quality is usually done either subjectively or objectively with their own advantages and disadvantages. Subjective methods usually require a large amount of time and resources, while objective methods lack human influence factors, which are crucial for deriving the subjective perception of quality. These human influence factors are manifested inside an individual’s brain in forms such as electroencephalograph (EEG). Thus, in this study, we performed audio quality prediction using EEG data. Since the data used in this study is small, we also compared the prediction result of the augmented and the non-augmented data. Our result shows that certain method yield significantly better prediction with augmented training data.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128541531","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975941
Walaa Othman, A. Kashevnik
Developing vehicles with the Internet of Thing technology including driver health monitoring systems, driver safety systems, and accident prevention has drawn the attention of researchers in the last few years. The monitoring system should prevent any dangerous situation and be comfortable for the driver inside the cabin. In this paper, we introduce a remote video-based method for detecting the heart rate in real-time using smartphone cameras, which can be used for the analysis of the driver’s physiological parameters to enhance driving safety. We propose to use 3DDFA for automatic facial landmarks detection to extract the driver’s face and a 3d-classification-based model for detecting the heart rate. The experiments showed good results with mean absolute error (MAE) equal to 6.8 on the LGI-PPGI dataset and 18.68 on our DriverMVT dataset that was recorded in the wild.
{"title":"Video-Based Real-Time Heart Rate Detection for Drivers Inside the Cabin Using a Smartphone","authors":"Walaa Othman, A. Kashevnik","doi":"10.1109/IoTaIS56727.2022.9975941","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975941","url":null,"abstract":"Developing vehicles with the Internet of Thing technology including driver health monitoring systems, driver safety systems, and accident prevention has drawn the attention of researchers in the last few years. The monitoring system should prevent any dangerous situation and be comfortable for the driver inside the cabin. In this paper, we introduce a remote video-based method for detecting the heart rate in real-time using smartphone cameras, which can be used for the analysis of the driver’s physiological parameters to enhance driving safety. We propose to use 3DDFA for automatic facial landmarks detection to extract the driver’s face and a 3d-classification-based model for detecting the heart rate. The experiments showed good results with mean absolute error (MAE) equal to 6.8 on the LGI-PPGI dataset and 18.68 on our DriverMVT dataset that was recorded in the wild.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132090880","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975999
Andy Triwinarko, S. Cherkaoui, I. Dayoub
This paper proposed the use of physical (PHY) and medium access control (MAC) cross-layer approach to obtain two goals outlined by the next-generation V2X (NGV) ’s project authorisation request (PAR) of IEEE 802.11bd group, namely having twice the MAC layer throughput and able to operate in a high mobility scenario of up to 500 km/h. At the PHY layer, we suggested utilising mid-ambles channel estimation (MCE), dual-carrier modulation (DCM), and multiple-input multiple-output space-time block coding (MIMO-STBC). At the MAC layer, we suggested an aggregate MAC protocol data unit (A-MPDU) aggregation technique, choosing an appropriate contention window (CW) value, and setting a limit for re-transmissions. We designed a model utilising a cross-layer approach then we simulated the performance of normalised system throughput for two types of V2X applications, namely safety-related (high reliability) and non-safety (high throughput) V2X applications. To better portray the high-mobility scenario, we used the enhanced highway line of sight (LOS) channel model. Our simulation results showed two times normalized throughput performance improvement for both V2X applications in a high mobility environment, as requested by the NGV standard’s PAR.
{"title":"Performance of PHY/MAC Cross-Layer Design for Next-Generation V2X Applications","authors":"Andy Triwinarko, S. Cherkaoui, I. Dayoub","doi":"10.1109/IoTaIS56727.2022.9975999","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975999","url":null,"abstract":"This paper proposed the use of physical (PHY) and medium access control (MAC) cross-layer approach to obtain two goals outlined by the next-generation V2X (NGV) ’s project authorisation request (PAR) of IEEE 802.11bd group, namely having twice the MAC layer throughput and able to operate in a high mobility scenario of up to 500 km/h. At the PHY layer, we suggested utilising mid-ambles channel estimation (MCE), dual-carrier modulation (DCM), and multiple-input multiple-output space-time block coding (MIMO-STBC). At the MAC layer, we suggested an aggregate MAC protocol data unit (A-MPDU) aggregation technique, choosing an appropriate contention window (CW) value, and setting a limit for re-transmissions. We designed a model utilising a cross-layer approach then we simulated the performance of normalised system throughput for two types of V2X applications, namely safety-related (high reliability) and non-safety (high throughput) V2X applications. To better portray the high-mobility scenario, we used the enhanced highway line of sight (LOS) channel model. Our simulation results showed two times normalized throughput performance improvement for both V2X applications in a high mobility environment, as requested by the NGV standard’s PAR.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125592350","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9976004
Philipp Matthes, T. Springer
Processing data closer to the source to minimize latency and the amount of data to be transmitted is a major driver for research on the Internet of Things (IoT). Since data processing in many IoT scenarios heavily depends on machine learning (ML), designing ML models for resource constraint devices at the edge of IoT infrastructures is one of the big challenges. Which ML model performs best highly depends on the problem domain but also on the availability of resources. Thus, to find an appropriate ML model in the broad search space of options, the trade-off between accuracy and resource consumption in terms of memory, CPU, and energy needs to be considered. However, there are ML problems where most current research focuses on accuracy, and the resource consumption of applicable models is not well investigated yet. We show that transport mode detection (TMD) is such a problem and present a case study for designing an ML model running on smartphones. To transform the search for the needle in the haystack into a structured design process, we propose an engineering workflow to systematically evolve ML model candidates, considering portability and resource consumption in addition to model accuracy. At the example of the Sussex-Huawei-Locomotion (SHL) dataset, we apply this process to multiple ML architectures and find a suitable model that convinces with high accuracy and low measured resource consumption for smartphone deployment. We discuss lessons learned, enabling engineers and researchers to use our workflow as a blueprint to identify solutions for their ML problems systematically.
{"title":"Selecting Resource-Efficient ML Models for Transport Mode Detection on Mobile Devices","authors":"Philipp Matthes, T. Springer","doi":"10.1109/IoTaIS56727.2022.9976004","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9976004","url":null,"abstract":"Processing data closer to the source to minimize latency and the amount of data to be transmitted is a major driver for research on the Internet of Things (IoT). Since data processing in many IoT scenarios heavily depends on machine learning (ML), designing ML models for resource constraint devices at the edge of IoT infrastructures is one of the big challenges. Which ML model performs best highly depends on the problem domain but also on the availability of resources. Thus, to find an appropriate ML model in the broad search space of options, the trade-off between accuracy and resource consumption in terms of memory, CPU, and energy needs to be considered. However, there are ML problems where most current research focuses on accuracy, and the resource consumption of applicable models is not well investigated yet. We show that transport mode detection (TMD) is such a problem and present a case study for designing an ML model running on smartphones. To transform the search for the needle in the haystack into a structured design process, we propose an engineering workflow to systematically evolve ML model candidates, considering portability and resource consumption in addition to model accuracy. At the example of the Sussex-Huawei-Locomotion (SHL) dataset, we apply this process to multiple ML architectures and find a suitable model that convinces with high accuracy and low measured resource consumption for smartphone deployment. We discuss lessons learned, enabling engineers and researchers to use our workflow as a blueprint to identify solutions for their ML problems systematically.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114222743","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9976024
Yuto Noda, K. Ishibashi, T. Yokotani
MQTT for IoT communication requires the deployment of multiple brokers to aggregate traffic from localized areas. However, the routing mechanisms among these brokers in a large-scale environment have yet to be specified. In this paper, a routing suitable for up-scaling based on the distribute MQTT broker by data link look up for traffic reduction (DMLT) is proposed. In this study, several up-scaling methods are proposed and compared in terms of traffic volume, scalability, and resilience. As a result, we chose an improved version of DMLT. A prototype of a wide-area DMLT system was constructed and verified by combining the DMLT method with an approach that the authors judged to be the most suitable for large-scale deployment.
{"title":"A proposal on the control mechanism among distributed MQTT brokers over wide area networks","authors":"Yuto Noda, K. Ishibashi, T. Yokotani","doi":"10.1109/IoTaIS56727.2022.9976024","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9976024","url":null,"abstract":"MQTT for IoT communication requires the deployment of multiple brokers to aggregate traffic from localized areas. However, the routing mechanisms among these brokers in a large-scale environment have yet to be specified. In this paper, a routing suitable for up-scaling based on the distribute MQTT broker by data link look up for traffic reduction (DMLT) is proposed. In this study, several up-scaling methods are proposed and compared in terms of traffic volume, scalability, and resilience. As a result, we chose an improved version of DMLT. A prototype of a wide-area DMLT system was constructed and verified by combining the DMLT method with an approach that the authors judged to be the most suitable for large-scale deployment.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115322109","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9976003
D. Pratama, L. V. Yovita, S. N. Hertiana
The integration of Software Defined Network (SDN) with Named Data Network (NDN) has the advantage of being able to save the time needed by consumers when receiving data. And the sender’s data was the producer, which is not known by the consumer. The integration of SDN and NDN can be developed to save resources in each company or in the field of education. Also, with SDN-NDN is a new architecture to make IP network integration with NDN.In this study, the author performed a performance analysis using the SDN-NDN based Best Route, Multicast, and Access Forwarding Strategy to measure Round Trip Time, Throughput, CPU Usage, and Memory Usage on the number of data packets sent. Based on the results obtained in this study, SDN-NDN has good performance compared to NDN during round trip time and throughput. But SDN-NDN uses more CPU and memory usage than NDN. Based on the implementation of the forwarding strategy, the Access Router strategy has a higher throughput and more round trip time than the Best-Route and Multicast forwarding strategies.
{"title":"Performance Analysis Forwarding Strategies Based Sdn-Ndn","authors":"D. Pratama, L. V. Yovita, S. N. Hertiana","doi":"10.1109/IoTaIS56727.2022.9976003","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9976003","url":null,"abstract":"The integration of Software Defined Network (SDN) with Named Data Network (NDN) has the advantage of being able to save the time needed by consumers when receiving data. And the sender’s data was the producer, which is not known by the consumer. The integration of SDN and NDN can be developed to save resources in each company or in the field of education. Also, with SDN-NDN is a new architecture to make IP network integration with NDN.In this study, the author performed a performance analysis using the SDN-NDN based Best Route, Multicast, and Access Forwarding Strategy to measure Round Trip Time, Throughput, CPU Usage, and Memory Usage on the number of data packets sent. Based on the results obtained in this study, SDN-NDN has good performance compared to NDN during round trip time and throughput. But SDN-NDN uses more CPU and memory usage than NDN. Based on the implementation of the forwarding strategy, the Access Router strategy has a higher throughput and more round trip time than the Best-Route and Multicast forwarding strategies.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121169262","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975886
Sota Nakajima, Daiki Sumiya, M. Morii, Nobuaki Mizutani, Akitsugu Shimano, M. Niswar, Shigeru Kashihara
There is a need to promote smart aquaculture using information science technologies such as ICT, IoT, and AI. Currently, smart aquaculture has been started in many species, such as oysters, mackerels, and shrimps. It is trying to improve work efficiency and secure appropriate production volume by converting what has been done by experienced and intuition into data. The paper focuses on crabs, especially Scylla Serrata, known as mud crab. Note that they have not yet been fully cultivated. To contribute to achieving the intelligent cultivation of these species, we first constructed an IoT-based experimental aquarium environment that can observe the ecology of these species on a laboratory scale. The sensing data and moving images acquired in the environment are displayed on the Web and can be easily checked remotely. The paper also introduces valuable examples through the operation and summarizes the future issues.
{"title":"IoT-based Experimental Aquarium Environment for Observing Crabs","authors":"Sota Nakajima, Daiki Sumiya, M. Morii, Nobuaki Mizutani, Akitsugu Shimano, M. Niswar, Shigeru Kashihara","doi":"10.1109/IoTaIS56727.2022.9975886","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975886","url":null,"abstract":"There is a need to promote smart aquaculture using information science technologies such as ICT, IoT, and AI. Currently, smart aquaculture has been started in many species, such as oysters, mackerels, and shrimps. It is trying to improve work efficiency and secure appropriate production volume by converting what has been done by experienced and intuition into data. The paper focuses on crabs, especially Scylla Serrata, known as mud crab. Note that they have not yet been fully cultivated. To contribute to achieving the intelligent cultivation of these species, we first constructed an IoT-based experimental aquarium environment that can observe the ecology of these species on a laboratory scale. The sensing data and moving images acquired in the environment are displayed on the Web and can be easily checked remotely. The paper also introduces valuable examples through the operation and summarizes the future issues.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131127134","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975939
Anthony Atkinson, Venkat Margapuri, Michael L. Neilsen
PiBase is a low-cost, Internet-of-Things-capable security systems. It offers users an integrated system of hardware and software in the form of a basic smart camera made from a Raspberry Pi and off-the-shelf parts, an Android app, and a backend built for Google Firebase. Using Haar-feature cascade classifiers and Linear Binary Pattern Histograms, it attempts to provide comprehensive detection and recognition of potential security threats. Being only a prototype there are some vulnerabilities in the initial design. This new design addresses one security threat, namely the possibility of mimicking an authorized user’s appearance. This is achieved through the integration of thermal imaging alongside the original camera used in the system. Some challenges with this approach include maintaining low-cost and part accessibility, working within limitations of the hardware, and choosing an effective method of integration. The proposed solution addresses each of these, in addition to the original issue, by transforming the output of a low-resolution thermal sensor array into a kind of clipping-mask to filter out non-human objects from the input image before performing its other operations.
{"title":"Verification of Feature Detection Through Thermal Imaging: An Extension of PiBase","authors":"Anthony Atkinson, Venkat Margapuri, Michael L. Neilsen","doi":"10.1109/IoTaIS56727.2022.9975939","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975939","url":null,"abstract":"PiBase is a low-cost, Internet-of-Things-capable security systems. It offers users an integrated system of hardware and software in the form of a basic smart camera made from a Raspberry Pi and off-the-shelf parts, an Android app, and a backend built for Google Firebase. Using Haar-feature cascade classifiers and Linear Binary Pattern Histograms, it attempts to provide comprehensive detection and recognition of potential security threats. Being only a prototype there are some vulnerabilities in the initial design. This new design addresses one security threat, namely the possibility of mimicking an authorized user’s appearance. This is achieved through the integration of thermal imaging alongside the original camera used in the system. Some challenges with this approach include maintaining low-cost and part accessibility, working within limitations of the hardware, and choosing an effective method of integration. The proposed solution addresses each of these, in addition to the original issue, by transforming the output of a low-resolution thermal sensor array into a kind of clipping-mask to filter out non-human objects from the input image before performing its other operations.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130169324","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 : 2022-11-24DOI: 10.1109/IoTaIS56727.2022.9975990
Talal Halabi, Martine Bellaïche, B. Fung
The Internet of Things (IoT) paradigm has led to an explosion in the number of IoT devices and an exponential rise in carbon footprint incurred by overburdened IoT networks and pervasive cloud/edge communications. Hence, there is a growing interest in industry and academia to enable the efficient use of computing infrastructures by optimizing the management of data center and IoT resources (hardware, software, network, and data) and reducing operational costs to slash greenhouse gas emissions and create healthy environments. Cybersecurity has also been considered in such efforts as a contributor to these environmental issues. Nonetheless, most green security approaches focus on designing low-overhead encryption schemes and do not emphasize energy-efficient security from architectural and deployment viewpoints. This paper sheds light on the emerging paradigm of adaptive cybersecurity as one of the research directions to support sustainable computing in green IoT. It presents three potential research directions and their associated methods for designing and deploying adaptive security in green computing and resource-constrained IoT environments to save on energy consumption. Such efforts will transform the development of data-driven IoT security solutions to be greener and more environment-friendly.
{"title":"Towards Adaptive Cybersecurity for Green IoT","authors":"Talal Halabi, Martine Bellaïche, B. Fung","doi":"10.1109/IoTaIS56727.2022.9975990","DOIUrl":"https://doi.org/10.1109/IoTaIS56727.2022.9975990","url":null,"abstract":"The Internet of Things (IoT) paradigm has led to an explosion in the number of IoT devices and an exponential rise in carbon footprint incurred by overburdened IoT networks and pervasive cloud/edge communications. Hence, there is a growing interest in industry and academia to enable the efficient use of computing infrastructures by optimizing the management of data center and IoT resources (hardware, software, network, and data) and reducing operational costs to slash greenhouse gas emissions and create healthy environments. Cybersecurity has also been considered in such efforts as a contributor to these environmental issues. Nonetheless, most green security approaches focus on designing low-overhead encryption schemes and do not emphasize energy-efficient security from architectural and deployment viewpoints. This paper sheds light on the emerging paradigm of adaptive cybersecurity as one of the research directions to support sustainable computing in green IoT. It presents three potential research directions and their associated methods for designing and deploying adaptive security in green computing and resource-constrained IoT environments to save on energy consumption. Such efforts will transform the development of data-driven IoT security solutions to be greener and more environment-friendly.","PeriodicalId":138894,"journal":{"name":"2022 IEEE International Conference on Internet of Things and Intelligence Systems (IoTaIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125844111","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：