Pub Date : 2023-05-26DOI: 10.1109/INCET57972.2023.10169994
Kalluri Srinivasa Rao, S. Joga, V. H. S. Dinesh, S. Mounika, B. M. Naidu, M. Sai
An energy meter, also known as a watt-hour meter, is a device used to measure the quantity of electrical energy consumed by a home or building. It is typically installed by the utility company or a qualified electrician at the main electrical panel or circuit breaker box. Energy meters can be mechanical or digital in nature. Mechanical meters use rotating dials or a spinning disc to measure energy consumption, while digital meters use electronic sensors and display screens to provide real-time energy usage data. This paper explains the development of a smart energy meter with overload protection and power theft control features. The proposed meter employs a microcontroller-based system that monitors and records the energy consumption of a household or building. The system also incorporates an overload protection mechanism that automatically switches off the power supply when the load exceeds a safe limit, thereby preventing damage to the electrical appliances and wiring. In addition to the overload protection, the smart energy meter is equipped with a power theft control feature that detects and reports any unauthorized tampering with the meter. This is achieved by monitoring the voltage and current levels, and comparing them with the expected values based on the load and power factor of the connected appliances. If any discrepancies are detected, an alert is generated, and the utility company is notified.
{"title":"Innovative Digital Energy Meter with Overload Indication and Power Theft Monitoring","authors":"Kalluri Srinivasa Rao, S. Joga, V. H. S. Dinesh, S. Mounika, B. M. Naidu, M. Sai","doi":"10.1109/INCET57972.2023.10169994","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10169994","url":null,"abstract":"An energy meter, also known as a watt-hour meter, is a device used to measure the quantity of electrical energy consumed by a home or building. It is typically installed by the utility company or a qualified electrician at the main electrical panel or circuit breaker box. Energy meters can be mechanical or digital in nature. Mechanical meters use rotating dials or a spinning disc to measure energy consumption, while digital meters use electronic sensors and display screens to provide real-time energy usage data. This paper explains the development of a smart energy meter with overload protection and power theft control features. The proposed meter employs a microcontroller-based system that monitors and records the energy consumption of a household or building. The system also incorporates an overload protection mechanism that automatically switches off the power supply when the load exceeds a safe limit, thereby preventing damage to the electrical appliances and wiring. In addition to the overload protection, the smart energy meter is equipped with a power theft control feature that detects and reports any unauthorized tampering with the meter. This is achieved by monitoring the voltage and current levels, and comparing them with the expected values based on the load and power factor of the connected appliances. If any discrepancies are detected, an alert is generated, and the utility company is notified.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126562747","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170340
Eldiya Thomas V, Maya Mohan
The quantity of image data is increasing rapidly with the discovery of big data and internet technology. Currently, the majority of image retrieval techniques rely on plain text images. It is a threat to several professional fields like medicine, the military, and the government. One of the limitations of the current data model is that it is difficult to effectively retrieve images with low quality samples. LE-GAN networks can be utilized to enhance the appearance of images. Then the enhanced images are fed into the network for retrieving images securely. Using a deep artificial neural network model to extract characteristics from training data can increase the security of an image's network transmission. Then, image retrieval [1] is devised and coupled with an image encryption technique that complements and secures image retrieval [1]. The recommended method can comfy the ciphertext images' retrieval and also can increase retrieval performance. Feature extraction has accomplished the usage of AlexNet and a chaotic algorithm is used as an encryption algorithm. To safeguard the image feature facts, the encryption technique is split into components so that the image information can nevertheless be successfully covered. To enforce the feature of image encryption, Arnold Mapping, and 2D Logistic Mapping are employed.
{"title":"Secure Image Retrieval of Poor Quality Images by Combining LE-GAN, Arnold Mapping and Logistic Mapping","authors":"Eldiya Thomas V, Maya Mohan","doi":"10.1109/INCET57972.2023.10170340","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170340","url":null,"abstract":"The quantity of image data is increasing rapidly with the discovery of big data and internet technology. Currently, the majority of image retrieval techniques rely on plain text images. It is a threat to several professional fields like medicine, the military, and the government. One of the limitations of the current data model is that it is difficult to effectively retrieve images with low quality samples. LE-GAN networks can be utilized to enhance the appearance of images. Then the enhanced images are fed into the network for retrieving images securely. Using a deep artificial neural network model to extract characteristics from training data can increase the security of an image's network transmission. Then, image retrieval [1] is devised and coupled with an image encryption technique that complements and secures image retrieval [1]. The recommended method can comfy the ciphertext images' retrieval and also can increase retrieval performance. Feature extraction has accomplished the usage of AlexNet and a chaotic algorithm is used as an encryption algorithm. To safeguard the image feature facts, the encryption technique is split into components so that the image information can nevertheless be successfully covered. To enforce the feature of image encryption, Arnold Mapping, and 2D Logistic Mapping are employed.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"24 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122259907","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170219
T. Muthamizhan, M. Janarthanan, P. Nalin, M. Nirmal
A solar PV, wind energy and battery energy storage system (BESS), connected to a dc bus by a quadratic boost converter (QBC), controlled by a closed loop PI and ANN Control is instigated in this work. The QBC for renewable energy sources (RES), energy storage elements and a DC Micro-Grid with resistive and dc motor loads with different control topologies are analysed. When compared to a PI controller, ANN confirms the power balance and grid stability even in worst environmental conditions and load variation, with respect to time. Open loop DC micro-grid system (DC-MGs) framework with disturbance, closed loop PI control and ANN based Data Management frameworks are formed and pretended using MATLAB/Simulink simulation software. Assessment of the time-domain parameters exhibit the accomplishment of DC-MGs framework control. The proposed framework has characteristics like minimal error towards the disturbance and have a quick response for the proposed system.
{"title":"ANN-Based Energy Storage System for an EV Charging Station Using Quadratic Boost Converter","authors":"T. Muthamizhan, M. Janarthanan, P. Nalin, M. Nirmal","doi":"10.1109/INCET57972.2023.10170219","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170219","url":null,"abstract":"A solar PV, wind energy and battery energy storage system (BESS), connected to a dc bus by a quadratic boost converter (QBC), controlled by a closed loop PI and ANN Control is instigated in this work. The QBC for renewable energy sources (RES), energy storage elements and a DC Micro-Grid with resistive and dc motor loads with different control topologies are analysed. When compared to a PI controller, ANN confirms the power balance and grid stability even in worst environmental conditions and load variation, with respect to time. Open loop DC micro-grid system (DC-MGs) framework with disturbance, closed loop PI control and ANN based Data Management frameworks are formed and pretended using MATLAB/Simulink simulation software. Assessment of the time-domain parameters exhibit the accomplishment of DC-MGs framework control. The proposed framework has characteristics like minimal error towards the disturbance and have a quick response for the proposed system.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126769562","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}
Leukocytes, sometimes referred to as white blood cells (WBCs), are crucial to the healthy operation of the human body. WBC distribution in human body are biological markers that determine the immunity of human body to fight against infectious diseases. WBC detection and classification plays an important role in medical application. However, using manual microscopic evaluation is complicated and time consuming. To tackle the limitations associated with traditional methods, recently deep learning (D.L) based methods are much experimented and explored. In this paper, we implemented various D.L models for automatic classification of WBCs. A comparative study among pretrained networks namely Inceptionv3, MobileNetV3 and VGG-19 was performed using transfer learning on publicly available WBC images from Kaggle. Classification accuracy of WBC images using Inceptionv3, MobileNetV3 and VGG-19 is 99.76%, 99.25% and 86.50% respectively. Inceptionv3 was further compared with the existing works in the literature and is found to be superior.
{"title":"A Comparative Analysis for Leukocyte Classification Based on Various Deep Learning Models Using Transfer Learning","authors":"Aruna Kumari Kakumani, Vikas Katla, Vinisha Rekhawar, Anish Reddy Yellakonda","doi":"10.1109/INCET57972.2023.10170443","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170443","url":null,"abstract":"Leukocytes, sometimes referred to as white blood cells (WBCs), are crucial to the healthy operation of the human body. WBC distribution in human body are biological markers that determine the immunity of human body to fight against infectious diseases. WBC detection and classification plays an important role in medical application. However, using manual microscopic evaluation is complicated and time consuming. To tackle the limitations associated with traditional methods, recently deep learning (D.L) based methods are much experimented and explored. In this paper, we implemented various D.L models for automatic classification of WBCs. A comparative study among pretrained networks namely Inceptionv3, MobileNetV3 and VGG-19 was performed using transfer learning on publicly available WBC images from Kaggle. Classification accuracy of WBC images using Inceptionv3, MobileNetV3 and VGG-19 is 99.76%, 99.25% and 86.50% respectively. Inceptionv3 was further compared with the existing works in the literature and is found to be superior.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114069132","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170420
K. Chaudhari, Dhruvi Joshi, Pratik Harugade, Kritik Jambusariya, Vaibhav Tiwari
The purity of air plays a major role on mortal health of people. Poor quality of air leads to many forms of diseases, most probably in the kids. Looking at the vulnerability of air quality standards the government further decides to take important acts for prevention of such diseases. Ancient ways of tackling diseases have a short range of success due to no access to huge sets of data. For this project , we have considered using machine’s algorithm to augur Air quality pointer for megacity Mumbai. Our created model can analyze closer to 93percent of aqi(air quality index), it further also predicts many oxides of carbon,nitrogen,sulfur and oxygen. Therefore,we as a country feel the need to have a machine to read the pollution levels for us to maintain the environment and to start taking respective precautions needed. In numerous artificial and civic regions at the moment,balancing the air index for human health is the biggest task right now. The burning of fossil energies, business patterns, and artificial variables all have a big impact on air pollution. We need to apply models that will record information regarding the attention of air pollutants because of the rising pollutant situations. The quality of people's lives is being impacted by the buildup of these dangerous chemicals in the air, particularly in metropolitan areas. Several lab tests have lately started using the Big Data Analytics fashion as per rise of pollutants in air.
{"title":"Predicting Mumbai's Air Quality Index by Machine Learning","authors":"K. Chaudhari, Dhruvi Joshi, Pratik Harugade, Kritik Jambusariya, Vaibhav Tiwari","doi":"10.1109/INCET57972.2023.10170420","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170420","url":null,"abstract":"The purity of air plays a major role on mortal health of people. Poor quality of air leads to many forms of diseases, most probably in the kids. Looking at the vulnerability of air quality standards the government further decides to take important acts for prevention of such diseases. Ancient ways of tackling diseases have a short range of success due to no access to huge sets of data. For this project , we have considered using machine’s algorithm to augur Air quality pointer for megacity Mumbai. Our created model can analyze closer to 93percent of aqi(air quality index), it further also predicts many oxides of carbon,nitrogen,sulfur and oxygen. Therefore,we as a country feel the need to have a machine to read the pollution levels for us to maintain the environment and to start taking respective precautions needed. In numerous artificial and civic regions at the moment,balancing the air index for human health is the biggest task right now. The burning of fossil energies, business patterns, and artificial variables all have a big impact on air pollution. We need to apply models that will record information regarding the attention of air pollutants because of the rising pollutant situations. The quality of people's lives is being impacted by the buildup of these dangerous chemicals in the air, particularly in metropolitan areas. Several lab tests have lately started using the Big Data Analytics fashion as per rise of pollutants in air.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121102245","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170165
Devesh Joshi, N. Mohd.
We use computers, mobile phones, and numerous other devices for computation and storage purposes. All these devices use some specific hardware to process data and give us a meaningful outcome in our everyday activities. Classical computer which we use in our daily lives are probabilistic, deterministic and logical. These devices help us tackle many tasks such as education, medical issues, banking and many others. As the data increases in our world the shortage of storage capacity and computation of such a massive data is increasing day by day. We therefore need a new device that can deal with the problem and deliver outcomes that are satisfactory. Quantum Computers are a new, forthcoming technology that can help with these challenges. These computers can store and process information that a classical computer cannot, by using entangled quantum bits (qubits). The power of computation and storage grows exponentially as qubit entanglement rises. This could introduce us to a new realm of powerful computation and alter how we handle huge datasets.
{"title":"Anatomy of Quantum Computer Framework using Qiskit","authors":"Devesh Joshi, N. Mohd.","doi":"10.1109/INCET57972.2023.10170165","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170165","url":null,"abstract":"We use computers, mobile phones, and numerous other devices for computation and storage purposes. All these devices use some specific hardware to process data and give us a meaningful outcome in our everyday activities. Classical computer which we use in our daily lives are probabilistic, deterministic and logical. These devices help us tackle many tasks such as education, medical issues, banking and many others. As the data increases in our world the shortage of storage capacity and computation of such a massive data is increasing day by day. We therefore need a new device that can deal with the problem and deliver outcomes that are satisfactory. Quantum Computers are a new, forthcoming technology that can help with these challenges. These computers can store and process information that a classical computer cannot, by using entangled quantum bits (qubits). The power of computation and storage grows exponentially as qubit entanglement rises. This could introduce us to a new realm of powerful computation and alter how we handle huge datasets.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115286394","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170692
Rishabh Sharma, V. Kukreja, D. Bordoloi
Pepper Leaf Blight Disease (PLBD) is a widespread plant ailment that has a severe impact on pepper cultivation across the globe. The rapid detection and precise classification of PLBD severity levels are crucial for efficient disease control and optimal agricultural productivity. The present study introduces a novel model based on Faster region-based convolutional neural network (R-CNN) for the efficient detection and multi-classification of PLBD in pepper leaves. The dataset used for training and testing the model consisted of 10,000 images. The model’s performance was evaluated based on its detection accuracy and multi-classification accuracy, which were found to be 99.39% and 98.38%, respectively. The model’s computational efficiency was assessed and determined to be sufficient for deployment in real-time disease detection applications. The model’s average inference time of 0.23 seconds per image renders it appropriate for deployment in high-throughput disease detection applications. The study’s findings indicate that the faster RCNN model is a successful method for detecting and classifying PLBD in pepper leaves. This has the potential to enhance disease management and crop yield in pepper farming.
{"title":"Deep Learning Meets Agriculture: A Faster RCNN Based Approach to pepper leaf blight disease Detection and Multi-Classification","authors":"Rishabh Sharma, V. Kukreja, D. Bordoloi","doi":"10.1109/INCET57972.2023.10170692","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170692","url":null,"abstract":"Pepper Leaf Blight Disease (PLBD) is a widespread plant ailment that has a severe impact on pepper cultivation across the globe. The rapid detection and precise classification of PLBD severity levels are crucial for efficient disease control and optimal agricultural productivity. The present study introduces a novel model based on Faster region-based convolutional neural network (R-CNN) for the efficient detection and multi-classification of PLBD in pepper leaves. The dataset used for training and testing the model consisted of 10,000 images. The model’s performance was evaluated based on its detection accuracy and multi-classification accuracy, which were found to be 99.39% and 98.38%, respectively. The model’s computational efficiency was assessed and determined to be sufficient for deployment in real-time disease detection applications. The model’s average inference time of 0.23 seconds per image renders it appropriate for deployment in high-throughput disease detection applications. The study’s findings indicate that the faster RCNN model is a successful method for detecting and classifying PLBD in pepper leaves. This has the potential to enhance disease management and crop yield in pepper farming.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116669154","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170683
R. S. Reddy, Rohan Sirimalla, K. Sushma, P. Kishore
Due to the increasing complexity in modern communication systems, data communication systems make extensive use of digital hardware. Modern data communication systems utilize a lot of digital hardware because of the complexity of modern communication systems, which is expanding. The frequency tuning function is converted from analog to digital and implementation in addition to baseband digital processing, with integration, cost, and programming case as the main drivers. The objectives are producing a cost-efficient hardware implementation that is optimized. An FPGA-based implementation platform is necessary due to the many hardware requirements for these systems, including processing speed, flexibility, integration, and time taken to market. According to the characteristics of each communication system, they have different purposes, using different modulation methods, different encoding methods, and hardware-based communications systems and traditional systems cannot meet people's needs. In this project, the most essential components of a digital radio system, including a Digital Up and Down Converter for Remote Radio Head for Long Term Evolution. A DUC performs the task of filtering and up-converting the baseband signal to a higher sample rate as part of the transmit route of the digital radio front end signal processing system. A DDC is a component of the reception path of a digital radio frontend signal processing system. By decimating to a lower sampling rate, it enables the extraction of information of interest. The most recent technology used in distributed architecture is the remote radio head. Each block of the DUC and DDC is done using a MATLAB tool. Current data communication systems utilise a lot of digital hardware because of the complexity of modern communication systems, which is expanding. This frequency tuning function will be converted from analogue to digital implementation in addition to baseband digital processing, with integration, cost, and programming case as the main drivers. In this project, a suggested method for using digital up converters and down converters is described. This method avoids the issue of bit growth in the cascaded integrator comb filter, which raises the bit error rate and lowers system performance owing to the development of words due to indeterminate data. The overall construction of a digital IF receiver is examined using a system generating platform, a digital controlled oscillator, and a decimation filter model in MATLAB/Simulink.
{"title":"Implementation of Digital Up Converter and Down Converter using System Generator","authors":"R. S. Reddy, Rohan Sirimalla, K. Sushma, P. Kishore","doi":"10.1109/INCET57972.2023.10170683","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170683","url":null,"abstract":"Due to the increasing complexity in modern communication systems, data communication systems make extensive use of digital hardware. Modern data communication systems utilize a lot of digital hardware because of the complexity of modern communication systems, which is expanding. The frequency tuning function is converted from analog to digital and implementation in addition to baseband digital processing, with integration, cost, and programming case as the main drivers. The objectives are producing a cost-efficient hardware implementation that is optimized. An FPGA-based implementation platform is necessary due to the many hardware requirements for these systems, including processing speed, flexibility, integration, and time taken to market. According to the characteristics of each communication system, they have different purposes, using different modulation methods, different encoding methods, and hardware-based communications systems and traditional systems cannot meet people's needs. In this project, the most essential components of a digital radio system, including a Digital Up and Down Converter for Remote Radio Head for Long Term Evolution. A DUC performs the task of filtering and up-converting the baseband signal to a higher sample rate as part of the transmit route of the digital radio front end signal processing system. A DDC is a component of the reception path of a digital radio frontend signal processing system. By decimating to a lower sampling rate, it enables the extraction of information of interest. The most recent technology used in distributed architecture is the remote radio head. Each block of the DUC and DDC is done using a MATLAB tool. Current data communication systems utilise a lot of digital hardware because of the complexity of modern communication systems, which is expanding. This frequency tuning function will be converted from analogue to digital implementation in addition to baseband digital processing, with integration, cost, and programming case as the main drivers. In this project, a suggested method for using digital up converters and down converters is described. This method avoids the issue of bit growth in the cascaded integrator comb filter, which raises the bit error rate and lowers system performance owing to the development of words due to indeterminate data. The overall construction of a digital IF receiver is examined using a system generating platform, a digital controlled oscillator, and a decimation filter model in MATLAB/Simulink.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125266440","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170630
Malika Malik, Kamaljit Singh Saini
Our research on the efficacy of deep reinforcement learning helps us comprehend the challenges encountered by NIDS (DRL). To find network anomalies, we suggest integrating Adversarial/Multi Agent Reinforcement Learning with Deep QLearning (AE-DQN). We compare our suggestions on the NSL-KDD dataset with the KDDTest+ dataset. In this article, we take a look at the difficulty of reducing an infinite number of possible categories down to only five. Our strategy yielded an overall F1 score of 79% and an accuracy of 80% across the board. Furthermore, our proposed method outperforms the Recurrent Neural Network (RNN) IDS (2) and the Adversarial Reinforcement Learning with SMOTE (AESMOTE) IDS in terms of the variety of assaults it can identify, as shown by its performance on the NSL-KDD dataset (3). Our major aim going forward is to enhance detection efficiency against different kinds of threats.
{"title":"Network Intrusion Detection System using Reinforcement learning","authors":"Malika Malik, Kamaljit Singh Saini","doi":"10.1109/INCET57972.2023.10170630","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170630","url":null,"abstract":"Our research on the efficacy of deep reinforcement learning helps us comprehend the challenges encountered by NIDS (DRL). To find network anomalies, we suggest integrating Adversarial/Multi Agent Reinforcement Learning with Deep QLearning (AE-DQN). We compare our suggestions on the NSL-KDD dataset with the KDDTest+ dataset. In this article, we take a look at the difficulty of reducing an infinite number of possible categories down to only five. Our strategy yielded an overall F1 score of 79% and an accuracy of 80% across the board. Furthermore, our proposed method outperforms the Recurrent Neural Network (RNN) IDS (2) and the Adversarial Reinforcement Learning with SMOTE (AESMOTE) IDS in terms of the variety of assaults it can identify, as shown by its performance on the NSL-KDD dataset (3). Our major aim going forward is to enhance detection efficiency against different kinds of threats.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125623211","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 : 2023-05-26DOI: 10.1109/INCET57972.2023.10170091
Shiva Mehta, V. Kukreja, Satvik Vats
Higher agricultural outputs are required due to the rising worldwide population, shifting nutritional preferences, and growing demand for food and basic materials for the industry. However, the farming sector confronts several difficulties, such as climate change and a rise in the severity of production risks, which have had a detrimental effect on food output. Crop production forecast algorithms have been created using machine learning and deep learning techniques to handle this issue. Traditional machine learning techniques, however, are less effective because many characteristics related to meteorological data, earth data, and agricultural management data are dispersed and isolated to specific organization computers or smart farming devices. Using about 9,876 pictures, a collaborative learning CNN method for wheat disease identification is suggested. The suggested method used the federated averaging technique to train the model on laterally dispersed datasets across various client devices. The suggested method beat current state-of-the-art models for detecting wheat illness, according to the findings of our experiments, obtaining high accuracy, precision, recall, and F1 score. The suggested method shows how federated learning can enhance machine learning models in a distributed environment. It can also be applied to other agricultural uses, such as crop forecast, soil analysis, and insect detection.
{"title":"Empowering Farmers with AI: Federated Learning of CNNs for Wheat Diseases Multi-Classification","authors":"Shiva Mehta, V. Kukreja, Satvik Vats","doi":"10.1109/INCET57972.2023.10170091","DOIUrl":"https://doi.org/10.1109/INCET57972.2023.10170091","url":null,"abstract":"Higher agricultural outputs are required due to the rising worldwide population, shifting nutritional preferences, and growing demand for food and basic materials for the industry. However, the farming sector confronts several difficulties, such as climate change and a rise in the severity of production risks, which have had a detrimental effect on food output. Crop production forecast algorithms have been created using machine learning and deep learning techniques to handle this issue. Traditional machine learning techniques, however, are less effective because many characteristics related to meteorological data, earth data, and agricultural management data are dispersed and isolated to specific organization computers or smart farming devices. Using about 9,876 pictures, a collaborative learning CNN method for wheat disease identification is suggested. The suggested method used the federated averaging technique to train the model on laterally dispersed datasets across various client devices. The suggested method beat current state-of-the-art models for detecting wheat illness, according to the findings of our experiments, obtaining high accuracy, precision, recall, and F1 score. The suggested method shows how federated learning can enhance machine learning models in a distributed environment. It can also be applied to other agricultural uses, such as crop forecast, soil analysis, and insect detection.","PeriodicalId":403008,"journal":{"name":"2023 4th International Conference for Emerging Technology (INCET)","volume":"257 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122665051","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：