Pub Date : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157645
Bhavatarini N, Akash B N, A. R. Avinash, Akshay H M
This Object detection and classification using Hyperspectral images is a critical aspect of remote sensing and computer vision. This technology involves identifying objects of interest within an image and classifying them based on their spectral signatures. Hyperspectral imaging provides a more detailed representation of objects compared to traditional color images, enabling more precise classification. The increased accuracy and reliability provided by this technology make it useful in a range of applications, such as environmental monitoring, military surveillance, and agriculture. However, object detection and classification in hyperspectral images can be challenging due to the large size of the data and the complexity of the algorithms involved. Nevertheless, ongoing research in this area continues to improve the performance of object detection and classification using hyperspectral images. In this paper, we are utilizing the K-Nearest Neighbor algorithm as part of the research work to determine the accuracy of our model.
{"title":"Object Detection and Classification of Hyperspectral Images Using K-NN","authors":"Bhavatarini N, Akash B N, A. R. Avinash, Akshay H M","doi":"10.1109/ICEEICT56924.2023.10157645","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157645","url":null,"abstract":"This Object detection and classification using Hyperspectral images is a critical aspect of remote sensing and computer vision. This technology involves identifying objects of interest within an image and classifying them based on their spectral signatures. Hyperspectral imaging provides a more detailed representation of objects compared to traditional color images, enabling more precise classification. The increased accuracy and reliability provided by this technology make it useful in a range of applications, such as environmental monitoring, military surveillance, and agriculture. However, object detection and classification in hyperspectral images can be challenging due to the large size of the data and the complexity of the algorithms involved. Nevertheless, ongoing research in this area continues to improve the performance of object detection and classification using hyperspectral images. In this paper, we are utilizing the K-Nearest Neighbor algorithm as part of the research work to determine the accuracy of our model.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133780652","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157272
Mukul Sharma, Bharti Koul
This paper proposes an alternate method of opt-mization approach for solar photovoltaic (PV) systems using VI- based synchronous inverters with adaptive dynamic programming controllers. The goal is to enhance the performance of the Grid-connected PV system. A synchronous inverter that is based on VI is used in order to transform the direct current (DC) electricity that is produced by the photovoltaic panels into alternating current (AC) power suitable for use in households or for feeding back into the grid. The adaptive dynamic programming controller is used for the purpose of achieving optimum performance from the inverter and the PV system, taking into account the dynamic behavior of the system and the varying environmental conditions. The proposed approach is evaluated using simulation studies, and the results show that it can significantly improve the performance of the PV system. The approach has the potential to make solar energy more competitive in the market when compared to more traditional electric power sources.
{"title":"Frequency Optimization in Solar PV Systems Using VI-based Synchronous Inverters with ADP Controller","authors":"Mukul Sharma, Bharti Koul","doi":"10.1109/ICEEICT56924.2023.10157272","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157272","url":null,"abstract":"This paper proposes an alternate method of opt-mization approach for solar photovoltaic (PV) systems using VI- based synchronous inverters with adaptive dynamic programming controllers. The goal is to enhance the performance of the Grid-connected PV system. A synchronous inverter that is based on VI is used in order to transform the direct current (DC) electricity that is produced by the photovoltaic panels into alternating current (AC) power suitable for use in households or for feeding back into the grid. The adaptive dynamic programming controller is used for the purpose of achieving optimum performance from the inverter and the PV system, taking into account the dynamic behavior of the system and the varying environmental conditions. The proposed approach is evaluated using simulation studies, and the results show that it can significantly improve the performance of the PV system. The approach has the potential to make solar energy more competitive in the market when compared to more traditional electric power sources.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"45 14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114818911","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157756
Monica Gupta, Manisha, R. Jha, Ruchika Kumari, Ankit Singh
In this paper, the existing write driver designs for SRAM are analyzed at 32 nm technology node. The performance of the designs are compared on the basis of Write Delay, Write Power consumption, Energy per Switching activity and Complexity of the design. The simulations are also done under PVT-variations to observe the impact of different operating conditions on the performance of the design. From the results, it is observed that the NOR gate based design performs fastest write operation with up to 9 % improvement in Write Delay. The Pass gate based design consumes least Write Power and Energy per Switching activity with up to 55.9 % and 51.5 % reduction respectively at TT corner, 1.1 V, 27 °C. In addition, the results show that the Write Delay of all the designs suffer at SF corner, low supply voltage and low temperatures. Alternatively, the designs perform faster write operation at FS corner, high supply voltages and high temperatures. The Write Power consumption is minimum at SS corner, low supply voltages and high temperatures and maximum at FF corner, high supply voltages and high temperatures. The Energy consumed per Switching activity is least at SS corner, low supply voltages and high temperatures.
{"title":"PVT-variation based Comparative Analysis of Write Driver Designs for SRAM at 32 nm","authors":"Monica Gupta, Manisha, R. Jha, Ruchika Kumari, Ankit Singh","doi":"10.1109/ICEEICT56924.2023.10157756","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157756","url":null,"abstract":"In this paper, the existing write driver designs for SRAM are analyzed at 32 nm technology node. The performance of the designs are compared on the basis of Write Delay, Write Power consumption, Energy per Switching activity and Complexity of the design. The simulations are also done under PVT-variations to observe the impact of different operating conditions on the performance of the design. From the results, it is observed that the NOR gate based design performs fastest write operation with up to 9 % improvement in Write Delay. The Pass gate based design consumes least Write Power and Energy per Switching activity with up to 55.9 % and 51.5 % reduction respectively at TT corner, 1.1 V, 27 °C. In addition, the results show that the Write Delay of all the designs suffer at SF corner, low supply voltage and low temperatures. Alternatively, the designs perform faster write operation at FS corner, high supply voltages and high temperatures. The Write Power consumption is minimum at SS corner, low supply voltages and high temperatures and maximum at FF corner, high supply voltages and high temperatures. The Energy consumed per Switching activity is least at SS corner, low supply voltages and high temperatures.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114642492","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157052
K. R. Chandra, Somasekhar Borugadda
In recent years, there has been an increase in demand for wireless cellular networks to have higher capacity. Operating costs have increased because operators use more energy to build new cell sites or boost the transmission power at existing locations to satisfy demand. Since energy costs are so high, lowering them must be a top goal. Non-orthogonal multiple access (NOMA), which has increased efficiency, has become a practical multiple access technique in wireless network construction. To improve energy efficiency and reduce power consumption, this paper proposes a Deep Q-Network policy with a novel power allocation method for NOMA-enabled network devices. The Multi-Agent Deep Reinforcement Learning (MADRL) with Deep Q-Network (DQN) model is presented for simultaneous wireless information and power transfer in NOMA-enabled devices. We investigate ways to increase the total transmission rate simultaneously and collect energy while meeting each NOMA system's minimum transmission rate and harvested energy requirements using the power splitting (PS) approach. To create an objective function, combine the transmission rates from information decoding with the transformed throughput from energy harvesting. We investigate wireless network development delays and dynamic energy-efficient resource allocation. We develop the resource allocation (i.e., time allocation and power control) problem as a dynamic stochastic optimization model that maximizes system energy efficiency (EE) while simultaneously satisfying a certain quality of service (QoS) in terms of delay. While ensuring throughput and fairness, MADRL-DQN enables the system to maximize energy efficiency; DQN allows energy savings by reducing the number of resources assigned to a user when signal traffic transmission dominates energy utilization. Compared to the methods already in use, the simulation results demonstrated the effectiveness of the proposed MADRL-DQN resource allocation algorithm.
{"title":"Multi Agent Deep Reinforcement learning with Deep Q-Network based energy efficiency and resource allocation in NOMA wireless Systems","authors":"K. R. Chandra, Somasekhar Borugadda","doi":"10.1109/ICEEICT56924.2023.10157052","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157052","url":null,"abstract":"In recent years, there has been an increase in demand for wireless cellular networks to have higher capacity. Operating costs have increased because operators use more energy to build new cell sites or boost the transmission power at existing locations to satisfy demand. Since energy costs are so high, lowering them must be a top goal. Non-orthogonal multiple access (NOMA), which has increased efficiency, has become a practical multiple access technique in wireless network construction. To improve energy efficiency and reduce power consumption, this paper proposes a Deep Q-Network policy with a novel power allocation method for NOMA-enabled network devices. The Multi-Agent Deep Reinforcement Learning (MADRL) with Deep Q-Network (DQN) model is presented for simultaneous wireless information and power transfer in NOMA-enabled devices. We investigate ways to increase the total transmission rate simultaneously and collect energy while meeting each NOMA system's minimum transmission rate and harvested energy requirements using the power splitting (PS) approach. To create an objective function, combine the transmission rates from information decoding with the transformed throughput from energy harvesting. We investigate wireless network development delays and dynamic energy-efficient resource allocation. We develop the resource allocation (i.e., time allocation and power control) problem as a dynamic stochastic optimization model that maximizes system energy efficiency (EE) while simultaneously satisfying a certain quality of service (QoS) in terms of delay. While ensuring throughput and fairness, MADRL-DQN enables the system to maximize energy efficiency; DQN allows energy savings by reducing the number of resources assigned to a user when signal traffic transmission dominates energy utilization. Compared to the methods already in use, the simulation results demonstrated the effectiveness of the proposed MADRL-DQN resource allocation algorithm.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123684152","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157402
R. Maruthi, P. Anusha, P. Sankar, K. Thiyagaragan
Image Quality (IQ) assessment is a very complex task and it is extremely important to evaluate the images with the metrics. The metrics applied can be a full reference, partial reference or no-reference metric and it depends on the application and availability of the ground truth. Most of the IQ metrics are developed by considering the Visual System (VS) of humans. The assessment methods studied in this paper focuses on some of the Full-Reference (FR) measures and it is used to estimate the remote sensing noisy images. The effectiveness of the measures demonstrates a considerable outcome and demonstrates how well the noisy remote sensing images are being quantified.
{"title":"Objective Full-Reference Image Assessment Metrics for Estimating the Quality of Remote Sensing Images","authors":"R. Maruthi, P. Anusha, P. Sankar, K. Thiyagaragan","doi":"10.1109/ICEEICT56924.2023.10157402","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157402","url":null,"abstract":"Image Quality (IQ) assessment is a very complex task and it is extremely important to evaluate the images with the metrics. The metrics applied can be a full reference, partial reference or no-reference metric and it depends on the application and availability of the ground truth. Most of the IQ metrics are developed by considering the Visual System (VS) of humans. The assessment methods studied in this paper focuses on some of the Full-Reference (FR) measures and it is used to estimate the remote sensing noisy images. The effectiveness of the measures demonstrates a considerable outcome and demonstrates how well the noisy remote sensing images are being quantified.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127337963","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157848
Fabeela Ali Rawther, Geevarghese Titus
Social engineering communities have become very popular among the kids and elderly alike. In this era of social media, the streaming of comments, opinions, reviews and communications is done via most common social media messaging communities like Twitter, Meta owned WhatsApp, FB and Instagram, Snapchat, telegram and YouTube comments. In this paper we perform a review on the different methods and models used to identify the offensive language using different datasets. Offensive language detection is a tedious task as it is country and language specific. The corpus used to identify the offensiveness and abusiveness is not covering all the word usages. We have done a comparison study of different methods on text to detect the post is offensive or not. The detection of abusive language is an unsolved and challenging problem to researchers in Natural Language Processing (NLP). This has led to be one of the reasons for increased level of mental instability among teenagers to elderly. The crime via social media has increased to a large value than older days. The study and surveys show that to recognize the structure and context of the language is the best way to solve this problem to an extent. The paper aims to four recent transformer models pretrained and fine-tuned for offensive language detection on the tweeteval dataset viz; DistilBERT, RoBERTa, DistilRoBERTa and DeBERTa. All the model had limitation in the performance based on the training data size used but are optimized by tuning hyper parameters during training. The models are limited to English language offensive words and recent works are going on in the area of multilingual tweets on both text and speech processing.
{"title":"Transformer Models for Recognizing Abusive Language An investigation and review on Tweeteval and SOLID dataset","authors":"Fabeela Ali Rawther, Geevarghese Titus","doi":"10.1109/ICEEICT56924.2023.10157848","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157848","url":null,"abstract":"Social engineering communities have become very popular among the kids and elderly alike. In this era of social media, the streaming of comments, opinions, reviews and communications is done via most common social media messaging communities like Twitter, Meta owned WhatsApp, FB and Instagram, Snapchat, telegram and YouTube comments. In this paper we perform a review on the different methods and models used to identify the offensive language using different datasets. Offensive language detection is a tedious task as it is country and language specific. The corpus used to identify the offensiveness and abusiveness is not covering all the word usages. We have done a comparison study of different methods on text to detect the post is offensive or not. The detection of abusive language is an unsolved and challenging problem to researchers in Natural Language Processing (NLP). This has led to be one of the reasons for increased level of mental instability among teenagers to elderly. The crime via social media has increased to a large value than older days. The study and surveys show that to recognize the structure and context of the language is the best way to solve this problem to an extent. The paper aims to four recent transformer models pretrained and fine-tuned for offensive language detection on the tweeteval dataset viz; DistilBERT, RoBERTa, DistilRoBERTa and DeBERTa. All the model had limitation in the performance based on the training data size used but are optimized by tuning hyper parameters during training. The models are limited to English language offensive words and recent works are going on in the area of multilingual tweets on both text and speech processing.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130162760","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157910
Sanoj Chakkithara Subramanian, Daniel D
Neural activity is the controlling signal used in enabling BCI to have direct communication with a computer. An array of EEG signals aid in the selection of the neural signal. The feature extractors and classifiers have a specific pattern of EEG control for a given BCI protocol, which is tailor-made and limited to that specific signal. Although a single protocol is applied in the deep neural networks used in EEG-based brain-computer interfaces, which are being used in the feature extraction and classification of speech recognition and computer vision, it is unclear how these architectures find themselves generalized in other area and prototypes. The deep learning approach used in transferring knowledge acquired from the source tasks to the target tasks is called transfer learning. Conventional machine learning algorithms have been surpassed by deep neural networks while solving problems concerning the real world. However, the best deep neural networks were identified by considering the knowledge of the problem domain. A significant amount of time and computational resources have to be spent to validate this approach. This work presents a deep learning neural network architecture based on Visual Geometry Group Network (VGGNet), Residual Network (ResNet), and inception network methods. Experimental results show that the proposed method achieves better performance than other methods.
{"title":"A Deep Learning Method for Classification in Brain-Computer Interface","authors":"Sanoj Chakkithara Subramanian, Daniel D","doi":"10.1109/ICEEICT56924.2023.10157910","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157910","url":null,"abstract":"Neural activity is the controlling signal used in enabling BCI to have direct communication with a computer. An array of EEG signals aid in the selection of the neural signal. The feature extractors and classifiers have a specific pattern of EEG control for a given BCI protocol, which is tailor-made and limited to that specific signal. Although a single protocol is applied in the deep neural networks used in EEG-based brain-computer interfaces, which are being used in the feature extraction and classification of speech recognition and computer vision, it is unclear how these architectures find themselves generalized in other area and prototypes. The deep learning approach used in transferring knowledge acquired from the source tasks to the target tasks is called transfer learning. Conventional machine learning algorithms have been surpassed by deep neural networks while solving problems concerning the real world. However, the best deep neural networks were identified by considering the knowledge of the problem domain. A significant amount of time and computational resources have to be spent to validate this approach. This work presents a deep learning neural network architecture based on Visual Geometry Group Network (VGGNet), Residual Network (ResNet), and inception network methods. Experimental results show that the proposed method achieves better performance than other methods.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"267 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128899161","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157306
Krittika Das, Chayan Ghosh, Raja Karmakar
The use of Unmanned Aerial Vehicles (UAVs) is proliferated and is prone to cyber attacks. Eavesdropping attack is an active threat to the security of an UAV as attackers intercept the communication medium over the wireless communication networks and get access to sensitive information. An active eavesdropper infiltrates the system and attacks the UAV during authentication. It involves the unauthorized interception of communication signals between the UAV and its control system. This type of intrusion can have severe consequences, including loss of control over the UAV, theft, espionage, and sabotage. To maintain the privacy and security of UAV communications and to protect sensitive information from unauthorized access, the detection of eavesdropping is of utmost importance. For the detection of eavesdropping attacks, we build an ensemble learning model with supervised machine learning algorithms (Logistic Regression, Decision Tree, Random Forest, k-Nearest Neighbours and Support Vector Machine) and unsupervised learning methods (One Class Support Vector Machine and K-Means Clustering). By combining the predictions of multiple algorithms, ensemble learning enhances the security and privacy of UAV communication. Additionally, by pooling together the strengths of different algorithms, ensemble learning improves the overall robustness and resilience of the UAV communication system and is a beneficial approach for the detection of eavesdropping attack packets. To train our proposed model we use the Kitsune Network Attack dataset. From the results, it is observed that our ensemble learning approach is a valid stratagem and can be used to detect eavesdropping attacks on UAV.
{"title":"Eavesdropping Attack Detection in UAVs using Ensemble Learning","authors":"Krittika Das, Chayan Ghosh, Raja Karmakar","doi":"10.1109/ICEEICT56924.2023.10157306","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157306","url":null,"abstract":"The use of Unmanned Aerial Vehicles (UAVs) is proliferated and is prone to cyber attacks. Eavesdropping attack is an active threat to the security of an UAV as attackers intercept the communication medium over the wireless communication networks and get access to sensitive information. An active eavesdropper infiltrates the system and attacks the UAV during authentication. It involves the unauthorized interception of communication signals between the UAV and its control system. This type of intrusion can have severe consequences, including loss of control over the UAV, theft, espionage, and sabotage. To maintain the privacy and security of UAV communications and to protect sensitive information from unauthorized access, the detection of eavesdropping is of utmost importance. For the detection of eavesdropping attacks, we build an ensemble learning model with supervised machine learning algorithms (Logistic Regression, Decision Tree, Random Forest, k-Nearest Neighbours and Support Vector Machine) and unsupervised learning methods (One Class Support Vector Machine and K-Means Clustering). By combining the predictions of multiple algorithms, ensemble learning enhances the security and privacy of UAV communication. Additionally, by pooling together the strengths of different algorithms, ensemble learning improves the overall robustness and resilience of the UAV communication system and is a beneficial approach for the detection of eavesdropping attack packets. To train our proposed model we use the Kitsune Network Attack dataset. From the results, it is observed that our ensemble learning approach is a valid stratagem and can be used to detect eavesdropping attacks on UAV.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126630035","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157238
Shihabudeen H, Rajeesh J
Image fusion produces a single image from numerous images with complementary information. Infrared images collect information on the thermal distribution of the scene, whereas visible images collect textural information. The fusion of these images creates images with thermal and textural details suitable for night-vision cameras and surveillance applications. The proposed auto encoder network with selected residual paths extracts the salient features from the images and then combines them using the nuclear norm's optimization effectiveness. The combined images are created with 5 CNN layers with a 3 x 3 filter size, and the fused output retains more information from both inputs. The suggested algorithm generates images with improved objective evaluation metrics with values of 6.89971 for entropy, 0.76133 for structural similarity, 3.83682 for mutual information, and 0.91325 for feature mutual information. The model outper- forms similar models for the fusion, and the algorithm is suitable for other fusion problems.
{"title":"Infrared and Visible Image Fusion with Nuclear Norm Activity Level Measurement","authors":"Shihabudeen H, Rajeesh J","doi":"10.1109/ICEEICT56924.2023.10157238","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157238","url":null,"abstract":"Image fusion produces a single image from numerous images with complementary information. Infrared images collect information on the thermal distribution of the scene, whereas visible images collect textural information. The fusion of these images creates images with thermal and textural details suitable for night-vision cameras and surveillance applications. The proposed auto encoder network with selected residual paths extracts the salient features from the images and then combines them using the nuclear norm's optimization effectiveness. The combined images are created with 5 CNN layers with a 3 x 3 filter size, and the fused output retains more information from both inputs. The suggested algorithm generates images with improved objective evaluation metrics with values of 6.89971 for entropy, 0.76133 for structural similarity, 3.83682 for mutual information, and 0.91325 for feature mutual information. The model outper- forms similar models for the fusion, and the algorithm is suitable for other fusion problems.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"424 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126716400","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 : 2023-04-05DOI: 10.1109/ICEEICT56924.2023.10157264
J. K, M. P, S. J
Sleep problems are very common nowadays. Many conventional methods are there for analysing this types of problems. But these methods are often time consuming, expensive and also human interventions are needed. So the need automatic diagnostic tool is very much important. Different artificial intelligence technologies like deep learning ensure the full utilization of data with very less information loss. In this paper a diagnostic tool is proposed by using the methods in machine learning. Signals were pre-processed in the first module, and the feature extraction is done by power spectral density technique (PSD). In the final section, features that had been extracted were put into an ensemble classifier, also known as a rotational support vector machine (RotSVM). The accuracy & sensitivity for the sleep stages classification is also calculated. According to classification performance results, 1D channel EEG can be used to create a sleep monitoring system that is useful for the hospitals and home care monitoring systems.
{"title":"Machine learning-Based sleep stage prediction using EEG signals recorded in PSG","authors":"J. K, M. P, S. J","doi":"10.1109/ICEEICT56924.2023.10157264","DOIUrl":"https://doi.org/10.1109/ICEEICT56924.2023.10157264","url":null,"abstract":"Sleep problems are very common nowadays. Many conventional methods are there for analysing this types of problems. But these methods are often time consuming, expensive and also human interventions are needed. So the need automatic diagnostic tool is very much important. Different artificial intelligence technologies like deep learning ensure the full utilization of data with very less information loss. In this paper a diagnostic tool is proposed by using the methods in machine learning. Signals were pre-processed in the first module, and the feature extraction is done by power spectral density technique (PSD). In the final section, features that had been extracted were put into an ensemble classifier, also known as a rotational support vector machine (RotSVM). The accuracy & sensitivity for the sleep stages classification is also calculated. According to classification performance results, 1D channel EEG can be used to create a sleep monitoring system that is useful for the hospitals and home care monitoring systems.","PeriodicalId":345324,"journal":{"name":"2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123332967","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：