Pub Date : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150456
M. Mahrukh, M. Thomas
Power Systems are the backbone of the economic activities and security of modern-day society. Simultaneously the size and complexity of the systems go on increasing at a rapid pace as the requirement for continuous and reliable power supply increases. With the ongoing modernization leading from the large-scale integration of operation and information technologies (OT and IT), power systems are becoming smarter and simultaneously prone to cyberattacks and their frequency of occurrence is on the rise. Malicious cyberattacks on the power system impose huge societal risks. Timely mitigation of these attacks thus becoming a necessity for reliably operating the power system. Load Altering Attacks (LAAs) are an important category of cyberattacks in power systems that tend to increase load abruptly with the motive of damaging the system and causing various losses to the whole society. This work gives a thorough review of load altering attacks, the various types, that can be launched against a power system, and then their mitigation techniques presented in various works of literature.
{"title":"Load Altering Attacks- a Review of Impact and Mitigation Strategies","authors":"M. Mahrukh, M. Thomas","doi":"10.1109/REEDCON57544.2023.10150456","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150456","url":null,"abstract":"Power Systems are the backbone of the economic activities and security of modern-day society. Simultaneously the size and complexity of the systems go on increasing at a rapid pace as the requirement for continuous and reliable power supply increases. With the ongoing modernization leading from the large-scale integration of operation and information technologies (OT and IT), power systems are becoming smarter and simultaneously prone to cyberattacks and their frequency of occurrence is on the rise. Malicious cyberattacks on the power system impose huge societal risks. Timely mitigation of these attacks thus becoming a necessity for reliably operating the power system. Load Altering Attacks (LAAs) are an important category of cyberattacks in power systems that tend to increase load abruptly with the motive of damaging the system and causing various losses to the whole society. This work gives a thorough review of load altering attacks, the various types, that can be launched against a power system, and then their mitigation techniques presented in various works of literature.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134553938","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}
This paper introduces a novel technique for transforming 2D floor plans into 3D models by combining image processing and augmented reality. The method involves using a smartphone camera to scan a 2D blueprint, followed by extracting the layout and dimensions of the area using computer vision algorithms. Augmented reality techniques are then applied to generate a 3D model that can be manipulated and navigated in real-time. The effectiveness and efficiency of the approach were evaluated using real-world floor plans, and the results were promising. The method has the potential to revolutionize the way architects and designers produce and present floor plans, providing a more immersive and interactive experience that can improve communication and collaboration among design teams. Clients can also benefit from this approach as it can assist them in comprehending and visualizing their designs. Furthermore, the approach can be used in other domains, such as virtual staging for real estate or in virtual reality training simulations for emergency responders. Overall, this pioneering approach has the potential to significantly impact various industries and can pave the way for future advancements in the field of 3D modeling and augmented reality.
{"title":"2D to 3D Floor plan Modeling using Image Processing and Augmented Reality","authors":"Pradnya Deshmukh, Srushti Kulkarni, Denzil Samuel, Jayesh Mishra, L. Sankpal, Chaitanya Kulkarni, Prasad Kulkarni","doi":"10.1109/REEDCON57544.2023.10151165","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151165","url":null,"abstract":"This paper introduces a novel technique for transforming 2D floor plans into 3D models by combining image processing and augmented reality. The method involves using a smartphone camera to scan a 2D blueprint, followed by extracting the layout and dimensions of the area using computer vision algorithms. Augmented reality techniques are then applied to generate a 3D model that can be manipulated and navigated in real-time. The effectiveness and efficiency of the approach were evaluated using real-world floor plans, and the results were promising. The method has the potential to revolutionize the way architects and designers produce and present floor plans, providing a more immersive and interactive experience that can improve communication and collaboration among design teams. Clients can also benefit from this approach as it can assist them in comprehending and visualizing their designs. Furthermore, the approach can be used in other domains, such as virtual staging for real estate or in virtual reality training simulations for emergency responders. Overall, this pioneering approach has the potential to significantly impact various industries and can pave the way for future advancements in the field of 3D modeling and augmented reality.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"411 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134302292","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 : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10151281
Abdullah, I. Faye, Md Rafiqul Islam
In brain-computer interfaces, electroencephalogram channel selection picks the most informative channels. To speed up the model training and improve accuracy by selecting a small number of optimal channels. In this study, we trained an agent that automatically learned the policy to choose an optimal channel, from given EEG data, even without hand engineering. We frame the problem of EEG channel selection as a Markov decision process (MDP), offer a productive method for parameterizing it, and then apply deep reinforcement learning (DRL) to solve it. After the agent has been trained, it tries to learn a policy for channel selection that directs it to choose channels sequentially while leveraging EEG signals and previously selected tracks. The study also offers two reward systems for the DRL environment simulation and analyzes them in trials. This is the first work to look at a DRL model for EEG data interpretation, opening up a new field of study and highlighting DRL’s immense potential in the brain-computer interface.
{"title":"Electroencephalogram Channel Selection using Deep Q-Network","authors":"Abdullah, I. Faye, Md Rafiqul Islam","doi":"10.1109/REEDCON57544.2023.10151281","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151281","url":null,"abstract":"In brain-computer interfaces, electroencephalogram channel selection picks the most informative channels. To speed up the model training and improve accuracy by selecting a small number of optimal channels. In this study, we trained an agent that automatically learned the policy to choose an optimal channel, from given EEG data, even without hand engineering. We frame the problem of EEG channel selection as a Markov decision process (MDP), offer a productive method for parameterizing it, and then apply deep reinforcement learning (DRL) to solve it. After the agent has been trained, it tries to learn a policy for channel selection that directs it to choose channels sequentially while leveraging EEG signals and previously selected tracks. The study also offers two reward systems for the DRL environment simulation and analyzes them in trials. This is the first work to look at a DRL model for EEG data interpretation, opening up a new field of study and highlighting DRL’s immense potential in the brain-computer interface.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"192 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122357809","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 : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150698
H. Fatima, Mir Tabish Altaf, M. Jamil
The environment is the major concern of today’s world due to global warming; cities are getting more polluted day by day. To keep the environment clean and green, every vehicle manufacturer is thinking of making electric vehicles but charging EVs became a major issue for EV owners due to its range anxiety. In a busy schedule, even a fast charger takes up to 30-40 minutes to charge an EV which is much more as compared to battery swapping which takes only 3-4 minutes, which is analogous to refilling a conventional vehicle from petrol or diesel or gas in the gas station and it motivates to use more electric vehicles. Charging a battery during peak hours increases the load on the grid and also increases the cost. To reduce the charging cost, the concept of charging during off-peak hours is proposed in this paper using the genetic algorithm to minimize the overall cost of charging in a battery-swapping station.
{"title":"Optimizing the charging cost of a battery swapping station using the genetic algorithm","authors":"H. Fatima, Mir Tabish Altaf, M. Jamil","doi":"10.1109/REEDCON57544.2023.10150698","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150698","url":null,"abstract":"The environment is the major concern of today’s world due to global warming; cities are getting more polluted day by day. To keep the environment clean and green, every vehicle manufacturer is thinking of making electric vehicles but charging EVs became a major issue for EV owners due to its range anxiety. In a busy schedule, even a fast charger takes up to 30-40 minutes to charge an EV which is much more as compared to battery swapping which takes only 3-4 minutes, which is analogous to refilling a conventional vehicle from petrol or diesel or gas in the gas station and it motivates to use more electric vehicles. Charging a battery during peak hours increases the load on the grid and also increases the cost. To reduce the charging cost, the concept of charging during off-peak hours is proposed in this paper using the genetic algorithm to minimize the overall cost of charging in a battery-swapping station.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115986845","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 : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10151027
Aditi Saxena, J. Kumar, V. Deolia
In contrast to conventional rigid-linked robots, soft robotic manipulators can assume a variety of complex morphologies in response to control inputs and gravitational loads. This paper presents a novel technique for modelling flexible robotic manipulators using inverse dynamics. This study provides mathematical modelling of a manipulator robot’s kinematic and dynamic behavior under the influence of nonlinear material properties and a distributed mass payload. The kinematic model is used to develop a control strategy that optimizes the robot’s kinematic performance. The dynamic model takes into account the robot’s pace. The static model, on the other hand, allows for autonomous trajectory tracking in specific situations. In addition, the Simulation of the proposed treatment parallels the evolution of control systems. In this paper, a concise analysis of soft robotics and research in the direction of modelling a flexible manipulator are presented, along with a performance comparison between link 1 and link 2 under varying parameter conditions. Experiments are performed to test the validity of hypotheses
{"title":"Modelling and Analysis Of flexible manipulator: Soft robotics","authors":"Aditi Saxena, J. Kumar, V. Deolia","doi":"10.1109/REEDCON57544.2023.10151027","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151027","url":null,"abstract":"In contrast to conventional rigid-linked robots, soft robotic manipulators can assume a variety of complex morphologies in response to control inputs and gravitational loads. This paper presents a novel technique for modelling flexible robotic manipulators using inverse dynamics. This study provides mathematical modelling of a manipulator robot’s kinematic and dynamic behavior under the influence of nonlinear material properties and a distributed mass payload. The kinematic model is used to develop a control strategy that optimizes the robot’s kinematic performance. The dynamic model takes into account the robot’s pace. The static model, on the other hand, allows for autonomous trajectory tracking in specific situations. In addition, the Simulation of the proposed treatment parallels the evolution of control systems. In this paper, a concise analysis of soft robotics and research in the direction of modelling a flexible manipulator are presented, along with a performance comparison between link 1 and link 2 under varying parameter conditions. Experiments are performed to test the validity of hypotheses","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125824036","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 : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150839
A. Mazid, M. Manaullah, S. Kirmani
Power theft is a persistent problem faced by electricity supply companies, leading to non-technical losses that can negatively impact the quality of electricity as well as profits. The emergence of advanced metering infrastructure (AMI) has presented a new opportunity to detect power theft using data from smart meters. In this study, we propose a hybrid approach that combines principal component analysis (PCA) and deep convolution neural network (CNN) to identify power theft and improve electricity monitoring. Our proposed technique involves three stages, namely feature selection, extraction, and classification, which are applied to smart meter data to assist energy supplier companies. The CNN is responsible for classifying the extracted features into either theft or non-theft categories, with optimized hyperparameters that enhance the accuracy of the model. The CNN-PCA method proposed in this study achieves a high accuracy rate of 94.76%, outperforming previous approaches. The models generated from this research exhibit high accuracy and low error rates in extensive simulations, making them a valuable tool for power supply companies to combat power theft.
{"title":"A Hybrid Approach Based on Principal Component Analysis and Convolution Neural Network For Power Theft Detection","authors":"A. Mazid, M. Manaullah, S. Kirmani","doi":"10.1109/REEDCON57544.2023.10150839","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150839","url":null,"abstract":"Power theft is a persistent problem faced by electricity supply companies, leading to non-technical losses that can negatively impact the quality of electricity as well as profits. The emergence of advanced metering infrastructure (AMI) has presented a new opportunity to detect power theft using data from smart meters. In this study, we propose a hybrid approach that combines principal component analysis (PCA) and deep convolution neural network (CNN) to identify power theft and improve electricity monitoring. Our proposed technique involves three stages, namely feature selection, extraction, and classification, which are applied to smart meter data to assist energy supplier companies. The CNN is responsible for classifying the extracted features into either theft or non-theft categories, with optimized hyperparameters that enhance the accuracy of the model. The CNN-PCA method proposed in this study achieves a high accuracy rate of 94.76%, outperforming previous approaches. The models generated from this research exhibit high accuracy and low error rates in extensive simulations, making them a valuable tool for power supply companies to combat power theft.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125936566","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 : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10151058
Rassiya Massarat, M. Thomas
With the growing concerns about the continuous increase in the concentration of CO2, in the atmosphere, resulting in global warming, there is an increasing trend towards a shift from internal combustion engine-based vehicles which rely solely on fossil fuels for their operation to electric vehicles. Wider adoption of Electric Vehicles (EVs) would not be possible without the installation of Electric Vehicle Charging Stations (EVCSs). The optimal placement of EVCSs is one of the concerns for large-scale deployment of EVs. If not placed optimally they can lead to range anxiety in drivers and cause stability problems at the grid. Researchers have used various optimization techniques for their optimal placement. Based on objective functions and optimization techniques this review work presents the optimal placement of charging stations (CS) to effectively solve the problem of their placement. This review work also presents various constraints which are to be followed while planning the CS location.
{"title":"A Review of the Optimal Allocation of Electric Vehicle Charging Stations","authors":"Rassiya Massarat, M. Thomas","doi":"10.1109/REEDCON57544.2023.10151058","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151058","url":null,"abstract":"With the growing concerns about the continuous increase in the concentration of CO2, in the atmosphere, resulting in global warming, there is an increasing trend towards a shift from internal combustion engine-based vehicles which rely solely on fossil fuels for their operation to electric vehicles. Wider adoption of Electric Vehicles (EVs) would not be possible without the installation of Electric Vehicle Charging Stations (EVCSs). The optimal placement of EVCSs is one of the concerns for large-scale deployment of EVs. If not placed optimally they can lead to range anxiety in drivers and cause stability problems at the grid. Researchers have used various optimization techniques for their optimal placement. Based on objective functions and optimization techniques this review work presents the optimal placement of charging stations (CS) to effectively solve the problem of their placement. This review work also presents various constraints which are to be followed while planning the CS location.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114137144","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 : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150466
Sandeep Bhatia, Z. Jaffery, S. Mehfuz
The Internet of Things (IoT) integration with wireless sensor networks (WSNs) used in various applications like smart cities, smart transportation, smart agriculture and real-time monitoring of industrial activities. The application of IoT-WSN is increasing day by day for different applications. For optimization of the crop quality various sensor nodes equipped with specific sensors like Soil, Temperature and Humidity sensor, Ultrasonic sensor to get signal about vertical growth of crop, Co2 sensor are randomly distributed across agriculture land. But, conventional WSN nodes have limited amount of energy that exist in sensor nodes. Recharging and replacement of the batteries at the sensor nodes becomes a difficult task. Heterogeneous sensor nodes placement provides many possibilities because of their sensing range and diverse computing power. The sensor node deployment, network connectivity, power consumption, coverage area and network lifetime are the primary issues in WSNs which need to be addressed. So, in this paper, our primary objective is to use intelligent deployment strategy for sensor node placement in IoT-WSN enabled smart agriculture (I-WSA) by using analytical algorithm like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) to minimize energy depletion of sensor nodes to prolong network lifetime using direct routing protocol and multi-hop routing protocol. Experimental results depict that the network lifetime can be increased up to an average of 140-150%. In the paper there is a comparison of GA and PSO. The benefit of heterogeneous networks has been explored in our paper through experimental results.
{"title":"Development and Analysis of IoT based Smart Agriculture System for Heterogenous Nodes","authors":"Sandeep Bhatia, Z. Jaffery, S. Mehfuz","doi":"10.1109/REEDCON57544.2023.10150466","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150466","url":null,"abstract":"The Internet of Things (IoT) integration with wireless sensor networks (WSNs) used in various applications like smart cities, smart transportation, smart agriculture and real-time monitoring of industrial activities. The application of IoT-WSN is increasing day by day for different applications. For optimization of the crop quality various sensor nodes equipped with specific sensors like Soil, Temperature and Humidity sensor, Ultrasonic sensor to get signal about vertical growth of crop, Co2 sensor are randomly distributed across agriculture land. But, conventional WSN nodes have limited amount of energy that exist in sensor nodes. Recharging and replacement of the batteries at the sensor nodes becomes a difficult task. Heterogeneous sensor nodes placement provides many possibilities because of their sensing range and diverse computing power. The sensor node deployment, network connectivity, power consumption, coverage area and network lifetime are the primary issues in WSNs which need to be addressed. So, in this paper, our primary objective is to use intelligent deployment strategy for sensor node placement in IoT-WSN enabled smart agriculture (I-WSA) by using analytical algorithm like Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) to minimize energy depletion of sensor nodes to prolong network lifetime using direct routing protocol and multi-hop routing protocol. Experimental results depict that the network lifetime can be increased up to an average of 140-150%. In the paper there is a comparison of GA and PSO. The benefit of heterogeneous networks has been explored in our paper through experimental results.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131262621","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 : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10151178
Prashant Hemrajani, V. Dhaka, Geeta Rani
Respiratory sleep disorders affect millions of people, with Obstructive Sleep Apnea being one of the most prevalent. Obstructive Sleep Apnea sufferers are often unaware of their illness, causing cardiovascular and neurological problems. Relaxation of the muscles that support the tongue and soft palate causes Obstructive Sleep Apnea. When these muscles relax, the patient’s airway constricts or closes, resulting in a brief cessation of breathing. Polysomnography is one of the tests used to diagnose Obstructive Sleep Apnea. While the patient is sleeping, they will be attached to technology that will monitor their heart, lungs, and brain activity, as well as their breathing patterns, leg movement, arm movement, and blood oxygen levels. Despite attempts to breathe, polysomnography reveals repeated instances of breathing delays. The majority of patients are untreated due to the difficulties caused in performing polysomnography. Using algorithms for machine learning, a number of researchers devised a variety of solutions to this issue. In the proposed work, detection of Obstructive Sleep Apnea was done by the integration of Long-Short Term Memory (LSTM) and the Gated Recurrent Unit (GRU) method. In order to validate the model, the suggested procedures made use of real-life clinical examples taken from the PhysioNet Apnea-ECG database, using thirty-five overnight sessions for Hybrid RNN (LSTM + GRU) attains 89.5% accuracy, 89.6% sensitivity, and 90.2 % percent specificity, demonstrating the efficacy of the presented method.
{"title":"Hybrid RNN-based classification of Obstructive Sleep Apnea using single-lead ECG Signals","authors":"Prashant Hemrajani, V. Dhaka, Geeta Rani","doi":"10.1109/REEDCON57544.2023.10151178","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10151178","url":null,"abstract":"Respiratory sleep disorders affect millions of people, with Obstructive Sleep Apnea being one of the most prevalent. Obstructive Sleep Apnea sufferers are often unaware of their illness, causing cardiovascular and neurological problems. Relaxation of the muscles that support the tongue and soft palate causes Obstructive Sleep Apnea. When these muscles relax, the patient’s airway constricts or closes, resulting in a brief cessation of breathing. Polysomnography is one of the tests used to diagnose Obstructive Sleep Apnea. While the patient is sleeping, they will be attached to technology that will monitor their heart, lungs, and brain activity, as well as their breathing patterns, leg movement, arm movement, and blood oxygen levels. Despite attempts to breathe, polysomnography reveals repeated instances of breathing delays. The majority of patients are untreated due to the difficulties caused in performing polysomnography. Using algorithms for machine learning, a number of researchers devised a variety of solutions to this issue. In the proposed work, detection of Obstructive Sleep Apnea was done by the integration of Long-Short Term Memory (LSTM) and the Gated Recurrent Unit (GRU) method. In order to validate the model, the suggested procedures made use of real-life clinical examples taken from the PhysioNet Apnea-ECG database, using thirty-five overnight sessions for Hybrid RNN (LSTM + GRU) attains 89.5% accuracy, 89.6% sensitivity, and 90.2 % percent specificity, demonstrating the efficacy of the presented method.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128115927","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 : 2023-05-01DOI: 10.1109/REEDCON57544.2023.10150996
Mehwash Weqar, S. Mehfuz, Dhawal Gupta
The Internet of Things (IoT) has rapidly expanded into healthcare, leading to the emergence of the Internet of Healthcare Things (IoHT). IoHT refers to the interconnected network of devices, sensors, and systems used in the healthcare industry to monitor and manage patient health. While IoHT has the potential to revolutionize healthcare, it is also vulnerable to cybersecurity attacks. DNS (Domain Name System) traffic monitoring in IoHT (Internet of Health Things) provide valuable insights into the communication patterns and behaviours of the various IoT devices and systems within a healthcare network. We have explored some of the common attacks on IoHT networks and their impact on healthcare. Then performed comparative analysis of various DNS traffic monitoring techniques and proposed the best possible solutions to protect IoHT applications.
{"title":"DNS Traffic Monitoring to Access Vulnerability in the Internet of Healthcare Things Networks: A Survey","authors":"Mehwash Weqar, S. Mehfuz, Dhawal Gupta","doi":"10.1109/REEDCON57544.2023.10150996","DOIUrl":"https://doi.org/10.1109/REEDCON57544.2023.10150996","url":null,"abstract":"The Internet of Things (IoT) has rapidly expanded into healthcare, leading to the emergence of the Internet of Healthcare Things (IoHT). IoHT refers to the interconnected network of devices, sensors, and systems used in the healthcare industry to monitor and manage patient health. While IoHT has the potential to revolutionize healthcare, it is also vulnerable to cybersecurity attacks. DNS (Domain Name System) traffic monitoring in IoHT (Internet of Health Things) provide valuable insights into the communication patterns and behaviours of the various IoT devices and systems within a healthcare network. We have explored some of the common attacks on IoHT networks and their impact on healthcare. Then performed comparative analysis of various DNS traffic monitoring techniques and proposed the best possible solutions to protect IoHT applications.","PeriodicalId":429116,"journal":{"name":"2023 International Conference on Recent Advances in Electrical, Electronics & Digital Healthcare Technologies (REEDCON)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132699735","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：