Pub Date : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773650
Hajrah Sultan, Muhammad Hamza Zafar, Saba Anwer, Asim Waris, Haris Ijaz, Moaz Sarwar
Over past few years there have been significant improvements in the field of artificial intelligence. In presented paper an automatic attendance marking setup based on the concept of face recognition has been proposed. Presented system not only mark the attendance but make an excel sheet to keep the record safe. This system successfully identifies the faces from different directions as well. First an HD 1080p camera captures the face images and then after noise reduction, histogram-oriented gradient (HOG) technique is used to detect the fascial features. Dlib face recognition API has been used in this system with 97.38 % accuracy of face recognition. System can recognize all the students present in the frame and make the record of all those students whose features matches with the database. Presented system is also capable of recognizing the students' face from multiple directions. This system can also be implemented to formulate a full proof surveillance set up in certain organization based on the concept of face recognition.
{"title":"Real Time Face Recognition Based Attendance System For University Classroom","authors":"Hajrah Sultan, Muhammad Hamza Zafar, Saba Anwer, Asim Waris, Haris Ijaz, Moaz Sarwar","doi":"10.1109/ICAI55435.2022.9773650","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773650","url":null,"abstract":"Over past few years there have been significant improvements in the field of artificial intelligence. In presented paper an automatic attendance marking setup based on the concept of face recognition has been proposed. Presented system not only mark the attendance but make an excel sheet to keep the record safe. This system successfully identifies the faces from different directions as well. First an HD 1080p camera captures the face images and then after noise reduction, histogram-oriented gradient (HOG) technique is used to detect the fascial features. Dlib face recognition API has been used in this system with 97.38 % accuracy of face recognition. System can recognize all the students present in the frame and make the record of all those students whose features matches with the database. Presented system is also capable of recognizing the students' face from multiple directions. This system can also be implemented to formulate a full proof surveillance set up in certain organization based on the concept of face recognition.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123630289","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773750
Jahanzeb Shahid, Z. Muhammad, Zafar Iqbal, Muhammad Sohaib Khan, Y. Amer, Weisheng Si
The widespread adoption of eCommerce, iBanking, and eGovernment institutions has resulted in an exponential rise in the use of web applications. Due to a large number of users, web applications have become a prime target of cybercriminals who want to steal Personally Identifiable Information (PII) and disrupt business activities. Hence, there is a dire need to audit the websites and ensure information security. In this regard, several web vulnerability scanners are employed for vulnerability assessment of web applications but attacks are still increasing day by day. Therefore, a considerable amount of research has been carried out to measure the effectiveness and limitations of the publicly available web scanners. It is identified that most of the publicly available scanners possess weaknesses and do not generate desired results. In this paper, the evaluation of publicly available web vulnerability scanners is performed against the top ten OWASP11OWASP® The Open Web Application Security Project (OWASP) is an online community that produces comprehensive articles, documentation, methodologies, and tools in the arena of web and mobile security. vulnerabilities and their performance is measured on the precision of their results. Based on these results, we proposed an Integrated Multi-Agent Blackbox Security Assessment Tool (SAT) for the security assessment of web applications. Research has proved that the vulnerabilities assessment results of the SAT are more extensive and accurate.
{"title":"SAT: Integrated Multi-agent Blackbox Security Assessment Tool using Machine Learning","authors":"Jahanzeb Shahid, Z. Muhammad, Zafar Iqbal, Muhammad Sohaib Khan, Y. Amer, Weisheng Si","doi":"10.1109/ICAI55435.2022.9773750","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773750","url":null,"abstract":"The widespread adoption of eCommerce, iBanking, and eGovernment institutions has resulted in an exponential rise in the use of web applications. Due to a large number of users, web applications have become a prime target of cybercriminals who want to steal Personally Identifiable Information (PII) and disrupt business activities. Hence, there is a dire need to audit the websites and ensure information security. In this regard, several web vulnerability scanners are employed for vulnerability assessment of web applications but attacks are still increasing day by day. Therefore, a considerable amount of research has been carried out to measure the effectiveness and limitations of the publicly available web scanners. It is identified that most of the publicly available scanners possess weaknesses and do not generate desired results. In this paper, the evaluation of publicly available web vulnerability scanners is performed against the top ten OWASP11OWASP® The Open Web Application Security Project (OWASP) is an online community that produces comprehensive articles, documentation, methodologies, and tools in the arena of web and mobile security. vulnerabilities and their performance is measured on the precision of their results. Based on these results, we proposed an Integrated Multi-Agent Blackbox Security Assessment Tool (SAT) for the security assessment of web applications. Research has proved that the vulnerabilities assessment results of the SAT are more extensive and accurate.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127962865","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773408
Ammar Haider, Nosheen Sabahat
Smartphones are now omnipresent in all aspects of our lives. Innovation interconnects people towards sparing information, accessing data and personal information on smartphones. However, there is continuously a security threat. For this reason, modern smartphones have utilized face recognition feature to authenticate the users. Smartphone manufacturers claim that the face recognition technology is dependable, trustable, and secure. This research is done to test the usability measurement and accuracy analysis of face recognition by experiencing the user experiments on 200 participants, within lab swot, along with user experience and adoption decision. We explore the five usability components and fourteen diverse face behaviours and representation to authentication.
{"title":"A Usability and Accuracy Measurement of Smartphones Face Recognition","authors":"Ammar Haider, Nosheen Sabahat","doi":"10.1109/ICAI55435.2022.9773408","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773408","url":null,"abstract":"Smartphones are now omnipresent in all aspects of our lives. Innovation interconnects people towards sparing information, accessing data and personal information on smartphones. However, there is continuously a security threat. For this reason, modern smartphones have utilized face recognition feature to authenticate the users. Smartphone manufacturers claim that the face recognition technology is dependable, trustable, and secure. This research is done to test the usability measurement and accuracy analysis of face recognition by experiencing the user experiments on 200 participants, within lab swot, along with user experience and adoption decision. We explore the five usability components and fourteen diverse face behaviours and representation to authentication.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121621075","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773375
Bushra Rasheed, M. Usama, Asmara Safdar
Hybrid Unmanned Ground Vehicle (HUGV) can drive on any terrain including walls and fly as well, using the multi directional thrust force of propellers. In the era of industrial revolution, hybrid UGVs need to be autonomous with intelligent decision making capabilities. During wall climbing of hybrid UGVs, stability is essential and depends on real time feedback from multiple sensors. To increase stability and control, it is proposed that PID control loops should be replaced by AI based algorithms that reduce the decision time and mathematical complexity. For autonomous movement in any terrain using the proposed model, intelligent UGVs can map and localize simultaneously.They can make intelligent decisions about mode of movement i.e. driving on ground or wall, steering on ground or wall, flying and maneuvering by using real time sensor readings. Integration of the proposed AI models with HUGV can be applied to many areas which are hard for humans to access, for instance; inspection of large structures, bio & nuclear hazard environments, planetary exploration & magnetic fields detection.
{"title":"Robust Artificial Intelligence Approach to Stabilize and Control Propeller Driven Hybrid UGV","authors":"Bushra Rasheed, M. Usama, Asmara Safdar","doi":"10.1109/ICAI55435.2022.9773375","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773375","url":null,"abstract":"Hybrid Unmanned Ground Vehicle (HUGV) can drive on any terrain including walls and fly as well, using the multi directional thrust force of propellers. In the era of industrial revolution, hybrid UGVs need to be autonomous with intelligent decision making capabilities. During wall climbing of hybrid UGVs, stability is essential and depends on real time feedback from multiple sensors. To increase stability and control, it is proposed that PID control loops should be replaced by AI based algorithms that reduce the decision time and mathematical complexity. For autonomous movement in any terrain using the proposed model, intelligent UGVs can map and localize simultaneously.They can make intelligent decisions about mode of movement i.e. driving on ground or wall, steering on ground or wall, flying and maneuvering by using real time sensor readings. Integration of the proposed AI models with HUGV can be applied to many areas which are hard for humans to access, for instance; inspection of large structures, bio & nuclear hazard environments, planetary exploration & magnetic fields detection.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134302204","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773561
Mati Ullah, Chunhui Zhao, Hamid Maqsood, Alam Nasir, M. Humayun, Mahmood Ul Hassan, Faiz Alam
This paper addresses the quadrotor vehicle control problem in the presence of parametric uncertainties and exogenous disturbances by introducing a finite-time extended disturbance observer-based adaptive neural sliding mode control (FTEDO-ANSMC) approach. The proposed FTEDO makes the controller robust to exogenous disturbances while eliminating the chattering issue in the control input. The designed SMC utilizes an adaptive neural network to tune its parameters online while a sliding mode concept-based weight update law is employed in the neural network to auto-update its weight parameters instead of conventional error-based weight update law without increasing the computational complexities, thereby enhancing the network's learning speed. The stability of the proposed control strategy is verified via Lyapunov theory. The simulation results of the proposed control strategy and its comparison with the conventional control strategy confirm its validity and efficacy.
{"title":"Adaptive Neural-Sliding Mode Control of a Quadrotor Vehicle with Uncertainties and Disturbances Compensation","authors":"Mati Ullah, Chunhui Zhao, Hamid Maqsood, Alam Nasir, M. Humayun, Mahmood Ul Hassan, Faiz Alam","doi":"10.1109/ICAI55435.2022.9773561","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773561","url":null,"abstract":"This paper addresses the quadrotor vehicle control problem in the presence of parametric uncertainties and exogenous disturbances by introducing a finite-time extended disturbance observer-based adaptive neural sliding mode control (FTEDO-ANSMC) approach. The proposed FTEDO makes the controller robust to exogenous disturbances while eliminating the chattering issue in the control input. The designed SMC utilizes an adaptive neural network to tune its parameters online while a sliding mode concept-based weight update law is employed in the neural network to auto-update its weight parameters instead of conventional error-based weight update law without increasing the computational complexities, thereby enhancing the network's learning speed. The stability of the proposed control strategy is verified via Lyapunov theory. The simulation results of the proposed control strategy and its comparison with the conventional control strategy confirm its validity and efficacy.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115240503","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773451
Hamad Younis, Muhammad Hassan, Shahzad Younis, Muhammad Shafique
Deep neural networks (DNNs) have latterly accomplished enormous success in various image recognition tasks. Although, training large DNN models are computationally expensive and memory intensive. So the natural idea is to do network compression and acceleration without significantly diminishing the performance of the model. In this paper, we propose a rapid and accurate method of training a neural network that has a small computation time and fewer parameters. The features are extracted using the Discrete Wavelet Transform (DWT) method. A voting-based classifier comprising a team of tiny artificial neural networks is proposed. The proposed classifier combines all the classification votes from the different sub-bands (models) to obtain the final class label, thus, achieving a similar classification accuracy of standard neural network architecture. The experiments were illustrated on benchmark data-sets of MNIST and EMNIST. On MNIST dataset, the trained models achieve the highest accuracy of 93.16 % for original and 90.44 % for Low-Low (LL) sub-band images. On the EMNIST dataset, accuracy of 90.13% for original and 87.40% for LL sub-band images has been obtained, respectively.
{"title":"Team of Tiny ANNs: A Way Towards Cost-Efficient Scalable Deep Learning","authors":"Hamad Younis, Muhammad Hassan, Shahzad Younis, Muhammad Shafique","doi":"10.1109/ICAI55435.2022.9773451","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773451","url":null,"abstract":"Deep neural networks (DNNs) have latterly accomplished enormous success in various image recognition tasks. Although, training large DNN models are computationally expensive and memory intensive. So the natural idea is to do network compression and acceleration without significantly diminishing the performance of the model. In this paper, we propose a rapid and accurate method of training a neural network that has a small computation time and fewer parameters. The features are extracted using the Discrete Wavelet Transform (DWT) method. A voting-based classifier comprising a team of tiny artificial neural networks is proposed. The proposed classifier combines all the classification votes from the different sub-bands (models) to obtain the final class label, thus, achieving a similar classification accuracy of standard neural network architecture. The experiments were illustrated on benchmark data-sets of MNIST and EMNIST. On MNIST dataset, the trained models achieve the highest accuracy of 93.16 % for original and 90.44 % for Low-Low (LL) sub-band images. On the EMNIST dataset, accuracy of 90.13% for original and 87.40% for LL sub-band images has been obtained, respectively.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"94 23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129071724","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773617
Zainullah Khan, Farhat Naseer, Fahad Iqbal Khawaja, Sara Ali, Muhammad Sajid, Y. Ayaz
Gait generation is the process of finding a sequence of robot leg movements, which propel the robot in the desired direction when executed in a certain order. It is an optimization problem where multiple parameters need to be tuned in order to generate an optimal gait. In this paper, we propose a novel technique to improve the gait quality of a quadrupedal robot. In our proposed technique, we create an optimal fitness function for a Genetic Algorithm (GA) optimizer and use a trapezoidal velocity profile for joint movements. Our quadrupedal robot consists of 8 joints, 2 per leg. All joints are actuated by servo motors. The robot joints are controlled using a single layer Artificial Neural Network (ANN) whose inputs are the current robot joint angles and outputs are the target joint angles. The ANN is called every time the joints reach their target positions. A GA is used to optimize the ANN weights. The GA runs for a total of 100 generations over a population size of 10. The fitness function is a combination of the total distance traveled by the robot, and a scaling factor for the fitness value based on the overall joint movements. This discourages the GA from optimizing gaits that tend to an idle state. The controllers are selected based on how well they maximize the fitness function. The simulation of the robot is carried out in Open Dynamics Engine (ODE). The results show that the proposed technique considerably improves the overall fitness of the gait and the total distance traveled by the robot. Moreover, the proposed technique converges to an optimal gait in under 20 generations whereas the existing method takes over 40 generations. Furthermore, the robot joint movement is much smoother in the proposed method hence reducing the jerking in the robot motion.
{"title":"Smooth Gait Generation for Quadrupedal Robots Based on Genetic Algorithm Optimization","authors":"Zainullah Khan, Farhat Naseer, Fahad Iqbal Khawaja, Sara Ali, Muhammad Sajid, Y. Ayaz","doi":"10.1109/ICAI55435.2022.9773617","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773617","url":null,"abstract":"Gait generation is the process of finding a sequence of robot leg movements, which propel the robot in the desired direction when executed in a certain order. It is an optimization problem where multiple parameters need to be tuned in order to generate an optimal gait. In this paper, we propose a novel technique to improve the gait quality of a quadrupedal robot. In our proposed technique, we create an optimal fitness function for a Genetic Algorithm (GA) optimizer and use a trapezoidal velocity profile for joint movements. Our quadrupedal robot consists of 8 joints, 2 per leg. All joints are actuated by servo motors. The robot joints are controlled using a single layer Artificial Neural Network (ANN) whose inputs are the current robot joint angles and outputs are the target joint angles. The ANN is called every time the joints reach their target positions. A GA is used to optimize the ANN weights. The GA runs for a total of 100 generations over a population size of 10. The fitness function is a combination of the total distance traveled by the robot, and a scaling factor for the fitness value based on the overall joint movements. This discourages the GA from optimizing gaits that tend to an idle state. The controllers are selected based on how well they maximize the fitness function. The simulation of the robot is carried out in Open Dynamics Engine (ODE). The results show that the proposed technique considerably improves the overall fitness of the gait and the total distance traveled by the robot. Moreover, the proposed technique converges to an optimal gait in under 20 generations whereas the existing method takes over 40 generations. Furthermore, the robot joint movement is much smoother in the proposed method hence reducing the jerking in the robot motion.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132512953","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773429
Mustafa Ur Rehman, Kamran Shah, Izhar ul Haq, H. Khurshid
Advancement in the field of rehabilitation has led to develop state-of-art multi-dexterous robotic hands such that to restore Activities of Daily Livings (ADLs) of upper limb amputees. However, these high-tech devices require an effective human-machine interface (HMI) for conversion of musculotendinous activities to myoelectric signals for control and functioning of robotic hands. In this study, a novel force myography (FMG) based HMI, considered as a potential alternate to sEMG, was developed. FMG band having five resistive based pressure sensors was developed for monitoring of change in stiffness of muscles during gestures. This flexible, un-stretchable, and adjustable FMG band is capable to be fastened on any adult forearm regardless of the size and shape of forearm. Voltage divider circuit was used to extract signals from FMG band. Five intact subjects participated in this study and protocol was developed for prediction of five static gestures such as relax, power, precision, supination, and pronation. All of subjects recorded selected gestures for three times. Gestures were classified using linear discriminant analysis (LDA) and support vector machines (SVM). SVM shows higher classification accuracy than LDA. LDA and SVM demonstrated prediction accuracies upto 87.2% and 93.3%, respectively.
{"title":"A Force Myography based HMI for Classification of Upper Extremity Gestures","authors":"Mustafa Ur Rehman, Kamran Shah, Izhar ul Haq, H. Khurshid","doi":"10.1109/ICAI55435.2022.9773429","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773429","url":null,"abstract":"Advancement in the field of rehabilitation has led to develop state-of-art multi-dexterous robotic hands such that to restore Activities of Daily Livings (ADLs) of upper limb amputees. However, these high-tech devices require an effective human-machine interface (HMI) for conversion of musculotendinous activities to myoelectric signals for control and functioning of robotic hands. In this study, a novel force myography (FMG) based HMI, considered as a potential alternate to sEMG, was developed. FMG band having five resistive based pressure sensors was developed for monitoring of change in stiffness of muscles during gestures. This flexible, un-stretchable, and adjustable FMG band is capable to be fastened on any adult forearm regardless of the size and shape of forearm. Voltage divider circuit was used to extract signals from FMG band. Five intact subjects participated in this study and protocol was developed for prediction of five static gestures such as relax, power, precision, supination, and pronation. All of subjects recorded selected gestures for three times. Gestures were classified using linear discriminant analysis (LDA) and support vector machines (SVM). SVM shows higher classification accuracy than LDA. LDA and SVM demonstrated prediction accuracies upto 87.2% and 93.3%, respectively.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115271296","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773464
Rabia Hasib, Atif Jan, G. Khan
A smart city ensures the safety of its citizens by the reduction of crime and terror threats. Despite intensive efforts to prevent and control anomalous human activities, they still pose a major risk and challenge to the society. This paper presents an automatic recognition of unusual human behavior captured by a CCTV camera in public areas, using spatio-temporal 3D convolutional neural networks. The weakly labeled benchmark dataset has been properly annotated to remove noise for accurately localizing anomalies within videos. This human-related dataset with real crime scenes is then compared to other state-of-the-art techniques such as Pseudo 3D and ResNet 3D. Our experimental results on the newly developed dataset outperforms most competing models in terms of area under the curve (AUC), obtaining 97.39% AUC.
{"title":"Real-Time Anomaly Detection for Smart and Safe City Using Spatiotemporal Deep Learning","authors":"Rabia Hasib, Atif Jan, G. Khan","doi":"10.1109/ICAI55435.2022.9773464","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773464","url":null,"abstract":"A smart city ensures the safety of its citizens by the reduction of crime and terror threats. Despite intensive efforts to prevent and control anomalous human activities, they still pose a major risk and challenge to the society. This paper presents an automatic recognition of unusual human behavior captured by a CCTV camera in public areas, using spatio-temporal 3D convolutional neural networks. The weakly labeled benchmark dataset has been properly annotated to remove noise for accurately localizing anomalies within videos. This human-related dataset with real crime scenes is then compared to other state-of-the-art techniques such as Pseudo 3D and ResNet 3D. Our experimental results on the newly developed dataset outperforms most competing models in terms of area under the curve (AUC), obtaining 97.39% AUC.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116695790","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 : 2022-03-30DOI: 10.1109/ICAI55435.2022.9773747
A. Sarwar, Salva Hasan, W. Khan, Salman Ahmed, S. N. K. Marwat
The Internet of Things (IoT) is advancing technology by creating smart surroundings that make it easier for humans to do their work. This technological advancement not only improves human life and expands economic opportunities, but also allows intruders or attackers to discover and exploit numerous methods in order to circumvent the security of IoT networks. Hence, security and privacy are the key concerns to the IoT networks. It is vital to protect computer and IoT networks from many sorts of anomalies and attacks. Traditional intrusion detection systems (IDS) collect and employ large amounts of data with irrelevant and inappropriate attributes to train machine learning models, resulting in long detection times and a high rate of misclassification. This research presents an advance approach for the design of IDS for IoT networks based on the Particle Swarm Optimization Algorithm (PSO) for feature selection and the Extreme Gradient Boosting (XGB) model for PSO fitness function. The classifier utilized in the intrusion detection process is Random Forest (RF). The IoTID20 is being utilized to evaluate the efficacy and robustness of our suggested strategy. The proposed system attains the following level of accuracy on the IoTID20 dataset for different levels of classification: Binary classification 98 %, multiclass classification 83 %. The results indicate that the proposed framework effectively detects cyber threats and improves the security of IoT networks.
{"title":"Design of an Advance Intrusion Detection System for IoT Networks","authors":"A. Sarwar, Salva Hasan, W. Khan, Salman Ahmed, S. N. K. Marwat","doi":"10.1109/ICAI55435.2022.9773747","DOIUrl":"https://doi.org/10.1109/ICAI55435.2022.9773747","url":null,"abstract":"The Internet of Things (IoT) is advancing technology by creating smart surroundings that make it easier for humans to do their work. This technological advancement not only improves human life and expands economic opportunities, but also allows intruders or attackers to discover and exploit numerous methods in order to circumvent the security of IoT networks. Hence, security and privacy are the key concerns to the IoT networks. It is vital to protect computer and IoT networks from many sorts of anomalies and attacks. Traditional intrusion detection systems (IDS) collect and employ large amounts of data with irrelevant and inappropriate attributes to train machine learning models, resulting in long detection times and a high rate of misclassification. This research presents an advance approach for the design of IDS for IoT networks based on the Particle Swarm Optimization Algorithm (PSO) for feature selection and the Extreme Gradient Boosting (XGB) model for PSO fitness function. The classifier utilized in the intrusion detection process is Random Forest (RF). The IoTID20 is being utilized to evaluate the efficacy and robustness of our suggested strategy. The proposed system attains the following level of accuracy on the IoTID20 dataset for different levels of classification: Binary classification 98 %, multiclass classification 83 %. The results indicate that the proposed framework effectively detects cyber threats and improves the security of IoT networks.","PeriodicalId":146842,"journal":{"name":"2022 2nd International Conference on Artificial Intelligence (ICAI)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131384129","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：