Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170041
Hitendra Chavan, Dr Shankar M. Patil, Nikita Gupta, Vaishnavi Rajput, Suchit Gaikwad, Sakshi Gaul
This Food waste is a global issue that affects people all over the globe. Food waste amounts to 1.3 billion tons annually, and this provides food for those who are hungry, claim food groups. Without a question, the government supplies food in accordance with the population graph, but in today’s world, as the population is growing and the nation is developing, food waste has reached a record high. Many people want to give sustenance to the poor, but they are unsure of how to go about doing it. Our initiative focuses on assisting the Feed People by establishing connections between NGOs and Donors. Applications for a Food Waste Management System built on Android and Machine Learning can help gather leftover food hotels and restaurants or the people who want to donate the food to distribute among those in need.
{"title":"Caritas- ‘Serving Smiles’","authors":"Hitendra Chavan, Dr Shankar M. Patil, Nikita Gupta, Vaishnavi Rajput, Suchit Gaikwad, Sakshi Gaul","doi":"10.1109/IConSCEPT57958.2023.10170041","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170041","url":null,"abstract":"This Food waste is a global issue that affects people all over the globe. Food waste amounts to 1.3 billion tons annually, and this provides food for those who are hungry, claim food groups. Without a question, the government supplies food in accordance with the population graph, but in today’s world, as the population is growing and the nation is developing, food waste has reached a record high. Many people want to give sustenance to the poor, but they are unsure of how to go about doing it. Our initiative focuses on assisting the Feed People by establishing connections between NGOs and Donors. Applications for a Food Waste Management System built on Android and Machine Learning can help gather leftover food hotels and restaurants or the people who want to donate the food to distribute among those in need.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134251270","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170224
P. V. Yeswanth, Sammeta Kushal, Garvit Tyagi, Molapally Tharun Kumar, S. Deivalakshmi, Sriram Prakash Ramasubramanian
Since ancient times, agricultural diseases brought on by pests, bacteria, viruses, and fungus have caused significant food loss that requires worldwide attention. Therefore, crop disease diagnosis as early as possible can significantly prevent loss of yield as well increase monetary value. The disease in crop may be identified by carefully analysing either a leaf, node, or stem. Here, accurate disease diagnosis will typically depend on the resolution of the image. Iterative Super-Resolution Network (ISNR) model is used for analysing low resolution potato leaf and identifying the disease. Through a stochastic iterative denoising procedure, ISNR accomplishes super-resolution while adjusting denoising diffusion probability models by image to image translation. The presented ISNR model is evaluated using the publicly accessible PlantVillage dataset with super resolution factors 2, 4, and 6. For super resolution factors 2, 4, and 6, our model gets PSNR 33.781 dB, 35.292 dB, 37.538 dB, SSIM 0.817, 0.892, 0.953, and classification accuracies of 99.61, 98.05, and 96.09 respectively.
{"title":"Iterative Super Resolution Network (ISNR) for Potato Leaf Disease Detection","authors":"P. V. Yeswanth, Sammeta Kushal, Garvit Tyagi, Molapally Tharun Kumar, S. Deivalakshmi, Sriram Prakash Ramasubramanian","doi":"10.1109/IConSCEPT57958.2023.10170224","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170224","url":null,"abstract":"Since ancient times, agricultural diseases brought on by pests, bacteria, viruses, and fungus have caused significant food loss that requires worldwide attention. Therefore, crop disease diagnosis as early as possible can significantly prevent loss of yield as well increase monetary value. The disease in crop may be identified by carefully analysing either a leaf, node, or stem. Here, accurate disease diagnosis will typically depend on the resolution of the image. Iterative Super-Resolution Network (ISNR) model is used for analysing low resolution potato leaf and identifying the disease. Through a stochastic iterative denoising procedure, ISNR accomplishes super-resolution while adjusting denoising diffusion probability models by image to image translation. The presented ISNR model is evaluated using the publicly accessible PlantVillage dataset with super resolution factors 2, 4, and 6. For super resolution factors 2, 4, and 6, our model gets PSNR 33.781 dB, 35.292 dB, 37.538 dB, SSIM 0.817, 0.892, 0.953, and classification accuracies of 99.61, 98.05, and 96.09 respectively.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134324993","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170117
Sayanti Chatterjee, M. Misbahuddin, Pabbathi Vamsi, Md Hassan Ahmed
This paper employs the newly proposed time delayed switching filter paradigm for active power quality improvement for grid-connected Photovoltaic (PV) systems. Thereafter fault diagnosis scheme for the same system has been recommended using machine learning technique. The main novelty of this paper work can be enumerated as (i) Proposed time delayed switching filter paradigm for active power quality improvement and (ii) fault diagnosis scheme for the same system using machine learning technique which can speeds up fault detection time and detect the fault location 95-99% accurately. The Cascaded Hybrid Multilevel Inverter (CHMI) used here for core inverter comprises of number of switches which in turn, increases the power losses. The Kalman filter controller is utilized to predict the state and to improve power sharing injected by renewable energy resources. But in the practical case, it is also assumed that the measurement noise of the filter are not accurately known. To estimate the states properly under these proposed circumstances, this work suggests adaptive estimation based Kalman Filter. Again, due to the switching of MIs, the state equation of the system has been changed and time delayed is present in the output. This problem deals with to use of switching Time delayed Adaptive Kalman Filter (TAKF). To enhance the reliability, a fault diagnosis technique has been planned here for CHMI. This paper presents a Machine learning based fault diagnosis technique. The proposed scheme can diagnosis the continuous and intermittent faults for open circuit. The efficacy of the scheme, proposed here is authenticated by the simulation study of a PV system.
{"title":"Power Quality Improvement and Fault Diagnosis of PV System By Machine Learning Techniques","authors":"Sayanti Chatterjee, M. Misbahuddin, Pabbathi Vamsi, Md Hassan Ahmed","doi":"10.1109/IConSCEPT57958.2023.10170117","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170117","url":null,"abstract":"This paper employs the newly proposed time delayed switching filter paradigm for active power quality improvement for grid-connected Photovoltaic (PV) systems. Thereafter fault diagnosis scheme for the same system has been recommended using machine learning technique. The main novelty of this paper work can be enumerated as (i) Proposed time delayed switching filter paradigm for active power quality improvement and (ii) fault diagnosis scheme for the same system using machine learning technique which can speeds up fault detection time and detect the fault location 95-99% accurately. The Cascaded Hybrid Multilevel Inverter (CHMI) used here for core inverter comprises of number of switches which in turn, increases the power losses. The Kalman filter controller is utilized to predict the state and to improve power sharing injected by renewable energy resources. But in the practical case, it is also assumed that the measurement noise of the filter are not accurately known. To estimate the states properly under these proposed circumstances, this work suggests adaptive estimation based Kalman Filter. Again, due to the switching of MIs, the state equation of the system has been changed and time delayed is present in the output. This problem deals with to use of switching Time delayed Adaptive Kalman Filter (TAKF). To enhance the reliability, a fault diagnosis technique has been planned here for CHMI. This paper presents a Machine learning based fault diagnosis technique. The proposed scheme can diagnosis the continuous and intermittent faults for open circuit. The efficacy of the scheme, proposed here is authenticated by the simulation study of a PV system.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128847013","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170048
R. J. Vijaya Saraswathi, V. Krishnakumar, V. Vasan Prabhu
Electric vehicles (EV) are gaining a high demand due to its non-reliance on renewable energy and no release of harmful gases. Considering the current condition of high-level pollution in various cities, electric vehicles are the most feasible solution for this problem. Electric vehicles also come with their own disadvantages. The effectiveness of the EV battery, availability of charging station or charging points, correct prediction of remaining battery life and battery health are considered the major issues in EV. Various charging algorithms are used to alleviate many of these problems. The battery part of EV’s plays a major role. Many algorithms have been developed to monitor various parameters of the battery of EVs and also predict their behavioural pattern. The paper discusses the RC parameter optimization algorithms which are used to optimize the parameters of a resistor-capacitor (RC) circuit, which is often used to model the behaviour of an EV battery. These algorithms are used for enhancing the estimates of the battery's State of Charge (SOC) and State of Health (SOH). The optimization algorithms such as Genetic Algorithm (GA), Differential Evolution (DE), Particle Swarm Optimization (PSO), Simulated Annealing (SA) and Levenberg-Marquardt (LM) algorithms are discussed. An overview of various algorithms that are used to monitor EV battery’s performance are also discussed here. These algorithms can help to improve the exactness in estimation of the battery's SOC and SOH, and can be used to optimize the performance of EV batteries. However, the algorithm choice depends on the application's specific requirements and the available data.
{"title":"Review Of Various Algorithms Used To Monitor The Performance Of EV Battery","authors":"R. J. Vijaya Saraswathi, V. Krishnakumar, V. Vasan Prabhu","doi":"10.1109/IConSCEPT57958.2023.10170048","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170048","url":null,"abstract":"Electric vehicles (EV) are gaining a high demand due to its non-reliance on renewable energy and no release of harmful gases. Considering the current condition of high-level pollution in various cities, electric vehicles are the most feasible solution for this problem. Electric vehicles also come with their own disadvantages. The effectiveness of the EV battery, availability of charging station or charging points, correct prediction of remaining battery life and battery health are considered the major issues in EV. Various charging algorithms are used to alleviate many of these problems. The battery part of EV’s plays a major role. Many algorithms have been developed to monitor various parameters of the battery of EVs and also predict their behavioural pattern. The paper discusses the RC parameter optimization algorithms which are used to optimize the parameters of a resistor-capacitor (RC) circuit, which is often used to model the behaviour of an EV battery. These algorithms are used for enhancing the estimates of the battery's State of Charge (SOC) and State of Health (SOH). The optimization algorithms such as Genetic Algorithm (GA), Differential Evolution (DE), Particle Swarm Optimization (PSO), Simulated Annealing (SA) and Levenberg-Marquardt (LM) algorithms are discussed. An overview of various algorithms that are used to monitor EV battery’s performance are also discussed here. These algorithms can help to improve the exactness in estimation of the battery's SOC and SOH, and can be used to optimize the performance of EV batteries. However, the algorithm choice depends on the application's specific requirements and the available data.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124675413","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170538
Rutuja Deepak Abhang, Bhakti Deepak Bailurkar, Sakshi Shailesh Save, P. Ingale, M. Patekar
Restaurant ratings and reviews have a noteworthy influence on shaping the public’s perception of a restaurant and influencing the dining decisions of individuals. With the rise of online platforms and review websites, it is now easier for customers to share their experiences and opinions about restaurants. Potential diners can easily access information about the quality of food, service, atmosphere, and value for money offered by a restaurant. Many customers visit a restaurant based on reviews given by the customer or other app users. India has a rich culinary heritage and offers a diverse range of cuisines that cater to different tastes and preferences. The restaurant industry in India is growing rapidly, and new restaurants are popping up all the time, offering customers an ever-increasing variety of dining options. Starting a new restaurant can be challenging, especially in a highly competitive market like India, where there are already many established restaurants. Major challenges that persist in the industry comprise elevated real estate expenses, escalating food prices, insufficient skilled labour, and customer acquisition. The system aims to perform sentimental analysis and exploratory data analysis on Zomato reviews. Sentimental analysis is performed using the SVM approach to determine the accuracy of the sentiment model. The model would deliver the top three cuisines in a location based on sentiment analysis, which would help new restaurants make decisions. The system shows factors affecting restaurant businesses by doing data analysis on various parameters of the dataset. The SVM model has adequate accuracy.
{"title":"Zomato Review Analysis Using Machine Learning","authors":"Rutuja Deepak Abhang, Bhakti Deepak Bailurkar, Sakshi Shailesh Save, P. Ingale, M. Patekar","doi":"10.1109/IConSCEPT57958.2023.10170538","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170538","url":null,"abstract":"Restaurant ratings and reviews have a noteworthy influence on shaping the public’s perception of a restaurant and influencing the dining decisions of individuals. With the rise of online platforms and review websites, it is now easier for customers to share their experiences and opinions about restaurants. Potential diners can easily access information about the quality of food, service, atmosphere, and value for money offered by a restaurant. Many customers visit a restaurant based on reviews given by the customer or other app users. India has a rich culinary heritage and offers a diverse range of cuisines that cater to different tastes and preferences. The restaurant industry in India is growing rapidly, and new restaurants are popping up all the time, offering customers an ever-increasing variety of dining options. Starting a new restaurant can be challenging, especially in a highly competitive market like India, where there are already many established restaurants. Major challenges that persist in the industry comprise elevated real estate expenses, escalating food prices, insufficient skilled labour, and customer acquisition. The system aims to perform sentimental analysis and exploratory data analysis on Zomato reviews. Sentimental analysis is performed using the SVM approach to determine the accuracy of the sentiment model. The model would deliver the top three cuisines in a location based on sentiment analysis, which would help new restaurants make decisions. The system shows factors affecting restaurant businesses by doing data analysis on various parameters of the dataset. The SVM model has adequate accuracy.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130905252","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170013
R. Arthi, Vemuri Jyothi Kiran, Anukiruthika, Mathan Krishna, Utkalika Das
Assistive technology has not yet reached an acceptable level of success in addressing the needs of visually impaired to navigate safely, comfortably, and independently. The proposed work addresses a prototype, real time assistive shoe designed and developed to facilitate safe navigation and mobility of visually impaired individuals. The prototype has been mounted with three pairs of ultrasonic sensors, PIR sensors and Infrared sensors, a moist sensor attached to bottom of the shoe that predicts the presence of water nearby, also detects objects at head level. The corresponding tactile outputs are provided by the buzzer with different type of sound and duration that is embedded in the shoe. It detects fall of the person as well and sends message along with location to the emergency contact. The developed shoe has been controlled by battery operation, cloud storage and involves use of IoT automation features too. The prototype helps in providing best offered track to the user within the kind of buzzer sound as an alert. The sensors square measure integrated with the shoe so the visually impaired cannot solely sight obstacles ahead of however, conjointly sight the presence of any major pits on the move. The proposed work results in enhancing the understanding of the issues faced by visually impaired in day-to-day basis that facilitates to move freelance in their daily lives.
{"title":"Real Time Assistive Shoe for Visually Impaired People using IoT","authors":"R. Arthi, Vemuri Jyothi Kiran, Anukiruthika, Mathan Krishna, Utkalika Das","doi":"10.1109/IConSCEPT57958.2023.10170013","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170013","url":null,"abstract":"Assistive technology has not yet reached an acceptable level of success in addressing the needs of visually impaired to navigate safely, comfortably, and independently. The proposed work addresses a prototype, real time assistive shoe designed and developed to facilitate safe navigation and mobility of visually impaired individuals. The prototype has been mounted with three pairs of ultrasonic sensors, PIR sensors and Infrared sensors, a moist sensor attached to bottom of the shoe that predicts the presence of water nearby, also detects objects at head level. The corresponding tactile outputs are provided by the buzzer with different type of sound and duration that is embedded in the shoe. It detects fall of the person as well and sends message along with location to the emergency contact. The developed shoe has been controlled by battery operation, cloud storage and involves use of IoT automation features too. The prototype helps in providing best offered track to the user within the kind of buzzer sound as an alert. The sensors square measure integrated with the shoe so the visually impaired cannot solely sight obstacles ahead of however, conjointly sight the presence of any major pits on the move. The proposed work results in enhancing the understanding of the issues faced by visually impaired in day-to-day basis that facilitates to move freelance in their daily lives.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130427566","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170225
A. Haripriya, S. Nagaraj, Samanth C
In this paper we have designed and analysed vedic multiplier using RCA and CSLA.The multiplier is a crucial part of digital signal processors. High-speed multiplier hardware is in extremely high demand. Speed, power, and area are three of the most important variables in determining how successful a multiplier is. The proposed Vedic multiplier utilizes the CSLA to increase the speed and efficiency of the multiplication process. The Urdhva-Tiryakbhyam algorithm is applied to break down the input operands into smaller sub-blocks, and the intermediate products are obtained by multiplying the sub-blocks using the algorithm. The final product is then obtained by adding the intermediate products using the CSLA. However, the CSLA is not an area-efficient one due to the dual RCA design.Using the CSLA,RCA,Halfadders,fulladder in Verilog HDL, a 16-bit Vedic multiplier is created using Modelsim to simulates and synthesised using Xilinx ISE 14.7. In this project we have implemented Vedic Multiplier using CSLA and compared it with the Vedic multiplier using RCA.The synthesis result is showns that CSLA has 3% greater area than RCA. CSLA has Reduced delay by 12%than Vedic ultiplier using RCA.
本文利用RCA和CSLA对吠陀乘法器进行了设计和分析。乘法器是数字信号处理器的重要组成部分。高速乘法器的硬件需求非常高。速度、功率和面积是决定乘法器成功与否的三个最重要的变量。提议的吠陀乘数法利用CSLA来提高乘法过程的速度和效率。采用Urdhva-Tiryakbhyam算法将输入操作数分解为更小的子块，并通过该算法将子块相乘得到中间乘积。然后通过使用CSLA添加中间产品来获得最终产品。然而，由于双RCA设计，CSLA不是一个面积效率高的。使用Verilog HDL中的CSLA,RCA,Halfadders, fullladder，使用Modelsim创建16位吠陀乘法器，使用Xilinx ISE 14.7进行模拟和合成。在这个项目中，我们使用CSLA实现了吠陀乘数，并将其与使用RCA的吠陀乘数进行了比较。合成结果表明，CSLA比RCA的面积大3%。CSLA比使用RCA的吠陀乘数减少了12%的延迟。
{"title":"Design and Analysis of 16-bit Vedic Multiplier using RCA and CSLA","authors":"A. Haripriya, S. Nagaraj, Samanth C","doi":"10.1109/IConSCEPT57958.2023.10170225","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170225","url":null,"abstract":"In this paper we have designed and analysed vedic multiplier using RCA and CSLA.The multiplier is a crucial part of digital signal processors. High-speed multiplier hardware is in extremely high demand. Speed, power, and area are three of the most important variables in determining how successful a multiplier is. The proposed Vedic multiplier utilizes the CSLA to increase the speed and efficiency of the multiplication process. The Urdhva-Tiryakbhyam algorithm is applied to break down the input operands into smaller sub-blocks, and the intermediate products are obtained by multiplying the sub-blocks using the algorithm. The final product is then obtained by adding the intermediate products using the CSLA. However, the CSLA is not an area-efficient one due to the dual RCA design.Using the CSLA,RCA,Halfadders,fulladder in Verilog HDL, a 16-bit Vedic multiplier is created using Modelsim to simulates and synthesised using Xilinx ISE 14.7. In this project we have implemented Vedic Multiplier using CSLA and compared it with the Vedic multiplier using RCA.The synthesis result is showns that CSLA has 3% greater area than RCA. CSLA has Reduced delay by 12%than Vedic ultiplier using RCA.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122262901","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170022
Narayana Darapaneni, A. Paduri, Anjan Arun Bhowmick, P. Ranjini, T. Kavitha, Suresh Rajendran, N. Veeresh, N. Vignesh
By providing non-linearity and enabling the network to understand complicated associations in the data, activation functions play a vital role in the performance of neural networks. Here, we introduce Esh, a brand-new activation function with the formula, $f(x) = xtanh(sigmoid(x))$. Using CNN architectures, we assess Esh’s performance on the MNIST, CIFAR10, and CIFAR-100 data sets. Our tests demonstrate that the Esh activation function outperforms a number of well-known activation functions, including ReLU, GELU, Mish, and Swish. In fact, compared to other activation functions, the Esh activation function has a more consistent loss landscape. Esh is a potential new activation function for deep neural networks, according to the findings of our study, and we anticipate that it will be widely used in the machine learning industry.
{"title":"ESH: A Non-Monotonic Activation Function For Image Classification","authors":"Narayana Darapaneni, A. Paduri, Anjan Arun Bhowmick, P. Ranjini, T. Kavitha, Suresh Rajendran, N. Veeresh, N. Vignesh","doi":"10.1109/IConSCEPT57958.2023.10170022","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170022","url":null,"abstract":"By providing non-linearity and enabling the network to understand complicated associations in the data, activation functions play a vital role in the performance of neural networks. Here, we introduce Esh, a brand-new activation function with the formula, $f(x) = xtanh(sigmoid(x))$. Using CNN architectures, we assess Esh’s performance on the MNIST, CIFAR10, and CIFAR-100 data sets. Our tests demonstrate that the Esh activation function outperforms a number of well-known activation functions, including ReLU, GELU, Mish, and Swish. In fact, compared to other activation functions, the Esh activation function has a more consistent loss landscape. Esh is a potential new activation function for deep neural networks, according to the findings of our study, and we anticipate that it will be widely used in the machine learning industry.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"17 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114127738","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170014
M. Anitha, L. S. Kumar
In India, where coal-fed Thermal Power Plants (TPPs) have been recognized as the country’s single largest source of air pollution, exposure to such air pollution is the biggest threat to the country’s environmental health. Rapid economic growth and rising electricity consumption have led to a sharp rise in NO2 and SO2 emissions from the power sector in India. This paper investigates the emission sources of NO2 and SO2 gases using Sentinel 5P TROPOMI satellite data for the Tamil Nadu region from 2019 to 2022. The monthly mean variation of TROPOMI data is analyzed over the Vallur and North Chennai TPP locations along with the Central Pollution Control Board’s (CPCB’s) Continuous Ambient Air Quality Monitoring Station (CAAQMS) data at Manali. The Google Earth Engine (GEE) platform is utilized to track and analyze trace gases.
{"title":"Tracking of NO2 and SO2 trace gases emission from Thermal Power Plants in Tamil Nadu using Sentinel 5P Tropomi Satellite with observations from CPCB CAAQM station","authors":"M. Anitha, L. S. Kumar","doi":"10.1109/IConSCEPT57958.2023.10170014","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170014","url":null,"abstract":"In India, where coal-fed Thermal Power Plants (TPPs) have been recognized as the country’s single largest source of air pollution, exposure to such air pollution is the biggest threat to the country’s environmental health. Rapid economic growth and rising electricity consumption have led to a sharp rise in NO2 and SO2 emissions from the power sector in India. This paper investigates the emission sources of NO2 and SO2 gases using Sentinel 5P TROPOMI satellite data for the Tamil Nadu region from 2019 to 2022. The monthly mean variation of TROPOMI data is analyzed over the Vallur and North Chennai TPP locations along with the Central Pollution Control Board’s (CPCB’s) Continuous Ambient Air Quality Monitoring Station (CAAQMS) data at Manali. The Google Earth Engine (GEE) platform is utilized to track and analyze trace gases.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123851490","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170342
R. Nagaraj, L. S. Kumar
Surface water mapping is crucial to conserve and to plan water resources. The water body extraction and surface water extent estimation from the satellite images are challenging because the different land types have similar spectral responses. In this paper, the Machine Learning (ML) classifiers are trained to segment water bodies from satellite images. The features extracted through Convolutional Neural Network (CNN) and spectral indices methods are used for training. Gaussian Naive Bayes (GNB), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost) are the ML classifiers considered. Linear Imaging Self Scanning Sensor-III (LISS-III) images provided by the Resourcesat-2 satellite have been used for experimentation. The experimental results show that the RF and GNB are the best and least-performing ML classifiers for water body extraction. Additionally, the water extent of Vaigai dam is determined using the segmented maps. The surface water extent has good agreement with the rainfall and water capacity of the reservoir.
地表水制图对保护和规划水资源至关重要。由于不同土地类型具有相似的光谱响应，从卫星影像中提取水体和估算地表水范围具有挑战性。在本文中，训练机器学习(ML)分类器从卫星图像中分割水体。利用卷积神经网络(CNN)和谱指数方法提取的特征进行训练。高斯朴素贝叶斯(GNB)、决策树(DT)、随机森林(RF)、支持向量机(SVM)、自适应增强(AdaBoost)、极端梯度增强(XGBoost)、轻梯度增强机(LightGBM)和分类增强(CatBoost)是ML分类器。由Resourcesat-2卫星提供的线性成像自扫描传感器- iii (LISS-III)图像已被用于实验。实验结果表明，RF和GNB分别是水体提取中性能最好和最差的ML分类器。此外，利用分段图确定了围改坝的水位范围。地表水范围与库区降雨量和库容具有较好的一致性。
{"title":"Surface water body extraction and Change Detection Analysis using Machine Learning Algorithms: A Case study of Vaigai Dam, India","authors":"R. Nagaraj, L. S. Kumar","doi":"10.1109/IConSCEPT57958.2023.10170342","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170342","url":null,"abstract":"Surface water mapping is crucial to conserve and to plan water resources. The water body extraction and surface water extent estimation from the satellite images are challenging because the different land types have similar spectral responses. In this paper, the Machine Learning (ML) classifiers are trained to segment water bodies from satellite images. The features extracted through Convolutional Neural Network (CNN) and spectral indices methods are used for training. Gaussian Naive Bayes (GNB), Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost) are the ML classifiers considered. Linear Imaging Self Scanning Sensor-III (LISS-III) images provided by the Resourcesat-2 satellite have been used for experimentation. The experimental results show that the RF and GNB are the best and least-performing ML classifiers for water body extraction. Additionally, the water extent of Vaigai dam is determined using the segmented maps. The surface water extent has good agreement with the rainfall and water capacity of the reservoir.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116559269","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：