Pub Date : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817349
Shereen S. Ismail, Diana W. Dawoud, H. Reza
Handling nodes identities and authentication is one of the current critical security challenges in an Internet of Things (IoT) environment, which consists of numerous devices with limited computation, communication, storage, and power capabilities. Motivated by the need to maintain trustworthiness in IoT networks to secure node-to-node or user-to-node communication, a blockchain-based identity management and secure authentication mechanism for a Wireless Sensor Network (WSN) scenario is proposed in this paper. The considered WSN is assumed to have three types of nodes: base station, cluster heads, and monitor nodes. The WSN is connected through the base station to the IoT cloud. The proposed system employs a private blockchain for internal authentication of cluster heads and monitor nodes, while a public blockchain is deployed between the base station and the IoT cloud to authenticate communication across different WSNs and end-users. Furthermore, a machine learning-based detection module is utilized to mitigate possible denial-of-service (DoS) attacks that may target cluster head nodes, raising the registration and authentication costs for monitor nodes within its vicinity and amplifying other blockchain attacks.
{"title":"Towards A Lightweight Identity Management and Secure Authentication for IoT Using Blockchain","authors":"Shereen S. Ismail, Diana W. Dawoud, H. Reza","doi":"10.1109/aiiot54504.2022.9817349","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817349","url":null,"abstract":"Handling nodes identities and authentication is one of the current critical security challenges in an Internet of Things (IoT) environment, which consists of numerous devices with limited computation, communication, storage, and power capabilities. Motivated by the need to maintain trustworthiness in IoT networks to secure node-to-node or user-to-node communication, a blockchain-based identity management and secure authentication mechanism for a Wireless Sensor Network (WSN) scenario is proposed in this paper. The considered WSN is assumed to have three types of nodes: base station, cluster heads, and monitor nodes. The WSN is connected through the base station to the IoT cloud. The proposed system employs a private blockchain for internal authentication of cluster heads and monitor nodes, while a public blockchain is deployed between the base station and the IoT cloud to authenticate communication across different WSNs and end-users. Furthermore, a machine learning-based detection module is utilized to mitigate possible denial-of-service (DoS) attacks that may target cluster head nodes, raising the registration and authentication costs for monitor nodes within its vicinity and amplifying other blockchain attacks.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114406940","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817185
Bharat S. Rawal, Lingampally Shiva Kumar, Sriram Maganti, Varun Godha
A hash function is a useful one-way trap cryptographic algorithm that converts an input of any size to an output of a fixed length of bits based on the choice of the hash function. In this paper, we compared various hash optimization techniques to reduce extra hashes while mining cryptocurrencies. Also, we introduce the concept of higher performance by splitting the hashing tasks over various servers. In most exceptionally reliable systems, subsystem or module failures that do not affect a system failure can still worsen system performance. The split system approach introduces a more effective way of offering reliability in a distributed system in general. To assess the system's reliability, this paper proposed a simple mathematical model that can capture the reliability of the system and higher throughput.
{"title":"Comparative Study of Sha-256 Optimization Techniques","authors":"Bharat S. Rawal, Lingampally Shiva Kumar, Sriram Maganti, Varun Godha","doi":"10.1109/aiiot54504.2022.9817185","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817185","url":null,"abstract":"A hash function is a useful one-way trap cryptographic algorithm that converts an input of any size to an output of a fixed length of bits based on the choice of the hash function. In this paper, we compared various hash optimization techniques to reduce extra hashes while mining cryptocurrencies. Also, we introduce the concept of higher performance by splitting the hashing tasks over various servers. In most exceptionally reliable systems, subsystem or module failures that do not affect a system failure can still worsen system performance. The split system approach introduces a more effective way of offering reliability in a distributed system in general. To assess the system's reliability, this paper proposed a simple mathematical model that can capture the reliability of the system and higher throughput.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114583402","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817177
R. R. Maaliw, K. Quing, Julie Ann B. Susa, Jed Frank S. Maraueses, A. Lagman, Rossana Adao, Ma.Corazon Fernando Raguro, Ranie B. Canlas
Grit plays a crucial role in determining high individual success more than intellectual talent alone. However, there is no existing literature that ventured into the trait identification in an e-learning environment. This study presents a comprehensive computational-driven strategy for detecting a learner's grit using machine learning. Empirical results show that DBSCAN and Random Forest models produce average accurate prediction consistency of 92.67% against the questionnaire method. Knowledge interpretation using feature importance and association mining quantifies perseverance and sustained interest as the most pressing component of grit. Correlational analysis reveals that grit has a weak connection with course grades (short-term goal) but demonstrates a strong positive association with professional achievement (long-term goal) and maturation. Collectively, our findings substantiate that breakthrough accomplishment is contingent not solely on cognitive ability but on constant interests and resilience.
{"title":"Clustering and Classification Models For Student's Grit Detection in E-Learning","authors":"R. R. Maaliw, K. Quing, Julie Ann B. Susa, Jed Frank S. Maraueses, A. Lagman, Rossana Adao, Ma.Corazon Fernando Raguro, Ranie B. Canlas","doi":"10.1109/aiiot54504.2022.9817177","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817177","url":null,"abstract":"Grit plays a crucial role in determining high individual success more than intellectual talent alone. However, there is no existing literature that ventured into the trait identification in an e-learning environment. This study presents a comprehensive computational-driven strategy for detecting a learner's grit using machine learning. Empirical results show that DBSCAN and Random Forest models produce average accurate prediction consistency of 92.67% against the questionnaire method. Knowledge interpretation using feature importance and association mining quantifies perseverance and sustained interest as the most pressing component of grit. Correlational analysis reveals that grit has a weak connection with course grades (short-term goal) but demonstrates a strong positive association with professional achievement (long-term goal) and maturation. Collectively, our findings substantiate that breakthrough accomplishment is contingent not solely on cognitive ability but on constant interests and resilience.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"266 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116397925","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817366
Laily Mariz A. Bengua, Vanessa Jane D. De Guzman, Danica Mae S. Macunat, Efren D. Villaverde, Aubee T. Mahusay, R. R. Maaliw, A. Lagman, A. Alon
The electro-mechanical salted egg grading system was developed to support producers by streamlining the cleaning process, delivering a sorted outcome, saving time, decrease human resources needs, labor costs, and minimized egg breakage, consequently boosting production efficiency. OpenCV (Open Source Computer Vision Library) was employed as a development platform and the Raspberry Pi 3 Model B as a microcomputer due to its speedier and more powerful CPU, which is required to operate the system's components and process the acquired images for classification. In addition, a Raspberry Pi camera module V2 was employed to capture the images for scanning, LED bulb for candling, and an SG90 micro servo for sorting. Furthermore, we used B66 and B35 V-belts for the conveyor assembly. An induction motor of 0.125 horse power is used to rotate the conveyor assembly, a chain, and sprocket to reduce its speed. The researchers also used soft bristles brushes which are ideal for cleaning the eggshell. For cleansing, sprinklers were used along with the water PVC pipe that holds pressurized water of 30 psi. The camera's captured images are categorized as clean, dirty, well-pickled, and spoilt eggs. Empirical results exhibited that the detection accuracy achieved 96% and 93% for cleanliness and quality, respectively. It establishes the model and prototype's robustness in cleaning, sorting, and grading salted eggs.
开发电子机械咸蛋分级系统是为了支持生产者简化清洗过程，提供分类结果，节省时间，减少人力资源需求，劳动力成本，并最大限度地减少鸡蛋破损，从而提高生产效率。采用OpenCV (Open Source Computer Vision Library)作为开发平台，采用Raspberry Pi 3 Model B作为微机，因为其CPU速度更快，功能更强大，需要对系统的组件进行操作，并对采集到的图像进行分类处理。此外，采用树莓派V2摄像模块采集图像进行扫描，LED灯泡进行烛光照射，SG90微伺服进行分选。此外，我们使用B66和B35 v带的输送机组件。一台0.125马力的感应电动机用于旋转传送带组件、链条和链轮以降低其速度。研究人员还使用了软毛刷，这是清洁蛋壳的理想选择。为了清洁，洒水器和PVC水管一起使用，PVC水管可以容纳30 psi的加压水。相机拍摄的图像分为干净鸡蛋、脏鸡蛋、腌制鸡蛋和变质鸡蛋。实验结果表明，该方法在清洁度和质量方面的检测准确率分别达到96%和93%。建立了模型和原型在咸蛋清洗、分类和分级方面的稳健性。
{"title":"Salted Egg Cleaning and Grading System Using Machine Vision","authors":"Laily Mariz A. Bengua, Vanessa Jane D. De Guzman, Danica Mae S. Macunat, Efren D. Villaverde, Aubee T. Mahusay, R. R. Maaliw, A. Lagman, A. Alon","doi":"10.1109/aiiot54504.2022.9817366","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817366","url":null,"abstract":"The electro-mechanical salted egg grading system was developed to support producers by streamlining the cleaning process, delivering a sorted outcome, saving time, decrease human resources needs, labor costs, and minimized egg breakage, consequently boosting production efficiency. OpenCV (Open Source Computer Vision Library) was employed as a development platform and the Raspberry Pi 3 Model B as a microcomputer due to its speedier and more powerful CPU, which is required to operate the system's components and process the acquired images for classification. In addition, a Raspberry Pi camera module V2 was employed to capture the images for scanning, LED bulb for candling, and an SG90 micro servo for sorting. Furthermore, we used B66 and B35 V-belts for the conveyor assembly. An induction motor of 0.125 horse power is used to rotate the conveyor assembly, a chain, and sprocket to reduce its speed. The researchers also used soft bristles brushes which are ideal for cleaning the eggshell. For cleansing, sprinklers were used along with the water PVC pipe that holds pressurized water of 30 psi. The camera's captured images are categorized as clean, dirty, well-pickled, and spoilt eggs. Empirical results exhibited that the detection accuracy achieved 96% and 93% for cleanliness and quality, respectively. It establishes the model and prototype's robustness in cleaning, sorting, and grading salted eggs.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124040105","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817270
B. Abegaz
Electric power-assisted steering (EPAS) is a mechanism of using electric power to enhance the efficiency, performance, and reliability of steering operations in vehicles. In the modern-day fully-autonomous and semi-autonomous vehicles, the real-time operation of EPAS systems has challenges related to the unmodeled dynamics, irregularity of the system operation, and variable road conditions. In this paper, a machine learning-based control system (ADMSV) that incorporates motion-related inputs such as direction, velocity, and torque has been developed to optimize and improve the overall efficiency of electric power-assisted steering in intelligent vehicles. The proposed system is used to calculate numerous external inputs and generate steering-related outputs (angular velocity, angular difference, output torque) which could help supply the adequate amount of torque that helps the vehicle to maneuver the wheels more easily or comfortably depending on various road and driving conditions.
{"title":"ADMSV - A Differential Machine Learning based Steering Controller for Smart Vehicles","authors":"B. Abegaz","doi":"10.1109/aiiot54504.2022.9817270","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817270","url":null,"abstract":"Electric power-assisted steering (EPAS) is a mechanism of using electric power to enhance the efficiency, performance, and reliability of steering operations in vehicles. In the modern-day fully-autonomous and semi-autonomous vehicles, the real-time operation of EPAS systems has challenges related to the unmodeled dynamics, irregularity of the system operation, and variable road conditions. In this paper, a machine learning-based control system (ADMSV) that incorporates motion-related inputs such as direction, velocity, and torque has been developed to optimize and improve the overall efficiency of electric power-assisted steering in intelligent vehicles. The proposed system is used to calculate numerous external inputs and generate steering-related outputs (angular velocity, angular difference, output torque) which could help supply the adequate amount of torque that helps the vehicle to maneuver the wheels more easily or comfortably depending on various road and driving conditions.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129530726","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817273
Mohammed Faisal Naji, C. Joumaa, Yousef Alswailem, Abdulrahman Alobthni, Rayan Albusilan
Coronavirus is a large family of viruses known to cause diseases ranging from the common cold to more serious diseases, and the methods for controlling epidemics of such viruses are difficult to deal with. One of the most dangerous things about COVID-19 is the speed with which it spreads. Therefore, we introduced a smart machine Iearning-based system for monitoring social distancing and mask wearing. The proposed system is used to monitor people and identify those who violate the rules of mask wearing or do not observe social distancing. It will help to control the epidemic, reduce the spread of COVID-19 and stress the importance of social distancing. The experimental results of the proposed system illustrate its robustness and accuracy.
{"title":"Machine Learning-based System for Monitoring Social Distancing and Mask Wearing","authors":"Mohammed Faisal Naji, C. Joumaa, Yousef Alswailem, Abdulrahman Alobthni, Rayan Albusilan","doi":"10.1109/aiiot54504.2022.9817273","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817273","url":null,"abstract":"Coronavirus is a large family of viruses known to cause diseases ranging from the common cold to more serious diseases, and the methods for controlling epidemics of such viruses are difficult to deal with. One of the most dangerous things about COVID-19 is the speed with which it spreads. Therefore, we introduced a smart machine Iearning-based system for monitoring social distancing and mask wearing. The proposed system is used to monitor people and identify those who violate the rules of mask wearing or do not observe social distancing. It will help to control the epidemic, reduce the spread of COVID-19 and stress the importance of social distancing. The experimental results of the proposed system illustrate its robustness and accuracy.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129883941","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817348
Tristan Erney, M. Chowdhury
Intrusion detection and prevention are necessary security measures for modern systems and networks which provide the services we use every day. This survey will attempt to provide a comprehensive overview on modern Intrusion Detection and Prevention Systems. Included will be a summarization of the literature which was studied from and sources which aide that research. The topics which are described within this survey involve implementing new Intrusion Detection and Prevention System (IDPS) architectures, methodologies, and polymerizing different technologies to create new methods of automated detection and prevention. Among these topics are implementations of Network IDPSs, creation of algorithms for Industrial Network Intrusion Detection Systems, generation of benchmark datasets for training Machine Learning models, creating new datasets for training Machine Learning models, using Neural Network models to create automated IDPSs, protecting Smart Grid technologies using IDPS, and implementing Intrusion Detection and Prevention tools using microcomputers.
{"title":"A Survey of Intrusion Detection and Prevention Systems","authors":"Tristan Erney, M. Chowdhury","doi":"10.1109/aiiot54504.2022.9817348","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817348","url":null,"abstract":"Intrusion detection and prevention are necessary security measures for modern systems and networks which provide the services we use every day. This survey will attempt to provide a comprehensive overview on modern Intrusion Detection and Prevention Systems. Included will be a summarization of the literature which was studied from and sources which aide that research. The topics which are described within this survey involve implementing new Intrusion Detection and Prevention System (IDPS) architectures, methodologies, and polymerizing different technologies to create new methods of automated detection and prevention. Among these topics are implementations of Network IDPSs, creation of algorithms for Industrial Network Intrusion Detection Systems, generation of benchmark datasets for training Machine Learning models, creating new datasets for training Machine Learning models, using Neural Network models to create automated IDPSs, protecting Smart Grid technologies using IDPS, and implementing Intrusion Detection and Prevention tools using microcomputers.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116681994","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817247
Opeoluwa Tosin Eluwole, Segun Akande, O. Adegbola
From the golden era of science fiction which dates to the late 1930s, scientific and technological advances in artificial intelligence (AI), along with one of its key subsets, machine learning (ML) have been growing significantly, especially in recent years. In 2021 alone, notable feats included an AI program capable of creating images from seen or previously unseen textual captions, an AI model that effectively integrates computer vision and natural language processing, and a novel AI framework for diagnosing dementia in 24 hours with real-world feasibility underway amongst a host of other fascinating breakthroughs. This paper briefly delves into AI/ML and recaps some key essentials, covering AI and ML subfields, ML methods, industries where AI/ML finds relevance, key stages and the common technical challenges in ML development. Importantly, the paper shifts attention from the latter to underscore the duo of transparency and ethics in AI, highlighting specifically what these are and why they are important, subsequently positing a PESTEL (Political, Economic, Social, Technological, Environmental and Legal) framework for AI design, build and implementation. It is anticipated that the upshot of this would be the facilitation of continuous adoption and long-term sustainability of AI/ML.
{"title":"Major threats to the continued adoption of Artificial Intelligence in today's hyperconnected world","authors":"Opeoluwa Tosin Eluwole, Segun Akande, O. Adegbola","doi":"10.1109/aiiot54504.2022.9817247","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817247","url":null,"abstract":"From the golden era of science fiction which dates to the late 1930s, scientific and technological advances in artificial intelligence (AI), along with one of its key subsets, machine learning (ML) have been growing significantly, especially in recent years. In 2021 alone, notable feats included an AI program capable of creating images from seen or previously unseen textual captions, an AI model that effectively integrates computer vision and natural language processing, and a novel AI framework for diagnosing dementia in 24 hours with real-world feasibility underway amongst a host of other fascinating breakthroughs. This paper briefly delves into AI/ML and recaps some key essentials, covering AI and ML subfields, ML methods, industries where AI/ML finds relevance, key stages and the common technical challenges in ML development. Importantly, the paper shifts attention from the latter to underscore the duo of transparency and ethics in AI, highlighting specifically what these are and why they are important, subsequently positing a PESTEL (Political, Economic, Social, Technological, Environmental and Legal) framework for AI design, build and implementation. It is anticipated that the upshot of this would be the facilitation of continuous adoption and long-term sustainability of AI/ML.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132657086","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817309
E. Naderi, A. Asrari
Modern power and energy networks include a plethora of distributed control and monitoring equipment, exchanging data through information and communication technology (ICT). Hence, such networks are a combination of physical layers and cyber layers, classified as cyber-physical systems. Although smart power grids facilitate the task of automated system operation with less involvement of people in making decisions, they can be negatively affected by cyber threats targeting security systems. Among different types of cyberattacks, false data injection (FDI) attacks are more common since they are easier to be performed. Toward this end, this paper develops a deep learning framework to protect cyber-physical power systems against cyberattacks including but not limited to FDI attacks in both forms of false positive and false negative. The proposed detection mechanism takes advantage of long short-term memory (LSTM) and deep recurrent neural network (RNN) concurrently. Moreover, the developed hybrid detection framework is able to recognize potentially malicious activities occurring in the cyber layer of a typical power grid. To demonstrate the robust performance of the proposed approach in detecting different types of cyberattacks, it is applied on 1) the CIC-IDS2017 dataset to detect denial of service (DoS) and distributed DoS (DDoS) attacks and 2) a smart power grid in the transmission level to protect the system against FDI attacks. The obtained results confirm the effectiveness of the proposed artificial intelligence-based detection framework (e.g., detection rate of 99.46%) against different types of cyberattacks targeting modern power networks.
{"title":"Toward Detecting Cyberattacks Targeting Modern Power Grids: A Deep Learning Framework","authors":"E. Naderi, A. Asrari","doi":"10.1109/aiiot54504.2022.9817309","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817309","url":null,"abstract":"Modern power and energy networks include a plethora of distributed control and monitoring equipment, exchanging data through information and communication technology (ICT). Hence, such networks are a combination of physical layers and cyber layers, classified as cyber-physical systems. Although smart power grids facilitate the task of automated system operation with less involvement of people in making decisions, they can be negatively affected by cyber threats targeting security systems. Among different types of cyberattacks, false data injection (FDI) attacks are more common since they are easier to be performed. Toward this end, this paper develops a deep learning framework to protect cyber-physical power systems against cyberattacks including but not limited to FDI attacks in both forms of false positive and false negative. The proposed detection mechanism takes advantage of long short-term memory (LSTM) and deep recurrent neural network (RNN) concurrently. Moreover, the developed hybrid detection framework is able to recognize potentially malicious activities occurring in the cyber layer of a typical power grid. To demonstrate the robust performance of the proposed approach in detecting different types of cyberattacks, it is applied on 1) the CIC-IDS2017 dataset to detect denial of service (DoS) and distributed DoS (DDoS) attacks and 2) a smart power grid in the transmission level to protect the system against FDI attacks. The obtained results confirm the effectiveness of the proposed artificial intelligence-based detection framework (e.g., detection rate of 99.46%) against different types of cyberattacks targeting modern power networks.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134634971","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 : 2022-06-06DOI: 10.1109/aiiot54504.2022.9817321
S. Chawathe
This paper studies methods and datasets for automated classification of mushrooms as edible or poisonous based on easily observable properties such as colors, textures, and dimensions of mushroom parts. The focus is on data-intensive methods that build upon recent work that has led to an augmented database of mushroom features. This dataset is studied in detail with the goal of explicating properties and easing further use of the dataset by others. The merit of the database features for the classification task is quantified using several metrics. Results quantify the accuracy and efficiency of classification using all and only a few of the features.
{"title":"Automated Determination of Mushroom Edibility Using an Augmented Dataset","authors":"S. Chawathe","doi":"10.1109/aiiot54504.2022.9817321","DOIUrl":"https://doi.org/10.1109/aiiot54504.2022.9817321","url":null,"abstract":"This paper studies methods and datasets for automated classification of mushrooms as edible or poisonous based on easily observable properties such as colors, textures, and dimensions of mushroom parts. The focus is on data-intensive methods that build upon recent work that has led to an augmented database of mushroom features. This dataset is studied in detail with the goal of explicating properties and easing further use of the dataset by others. The merit of the database features for the classification task is quantified using several metrics. Results quantify the accuracy and efficiency of classification using all and only a few of the features.","PeriodicalId":409264,"journal":{"name":"2022 IEEE World AI IoT Congress (AIIoT)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114746365","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：