Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936260
B. Nataraj, K. R. Prabha, S. Aravind, M. D. Eshwar, N. Jagadeeshwari
This paper deals with a recommendation and rating system using machine learning algorithms like linear regression, random forest regression and support vector model. Recommendation and rating systems are subdivision of structures that filter information. These structures normally are dedicated software program components, which contribute to a bigger software program machine, but also can be standalone equipment. Our recommendation and rating system’s main aim is to give suggestions for items that the user demands which can be favorable in a collaborative approach using machine learning models. The recommendations are associated with specific choice-making mechanisms, distinctive techniques, which includes, what commodities to shop for, what shows to watch, or what holiday places to look for. This collaborative technique should be able to compute the relationship among distinct clients and depending upon their ratings and prescribe items to others who’ve comparable tastes and also finally allowing users to discover more.
{"title":"Recommendation and Rating System using Machine Learning","authors":"B. Nataraj, K. R. Prabha, S. Aravind, M. D. Eshwar, N. Jagadeeshwari","doi":"10.1109/ICECAA55415.2022.9936260","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936260","url":null,"abstract":"This paper deals with a recommendation and rating system using machine learning algorithms like linear regression, random forest regression and support vector model. Recommendation and rating systems are subdivision of structures that filter information. These structures normally are dedicated software program components, which contribute to a bigger software program machine, but also can be standalone equipment. Our recommendation and rating system’s main aim is to give suggestions for items that the user demands which can be favorable in a collaborative approach using machine learning models. The recommendations are associated with specific choice-making mechanisms, distinctive techniques, which includes, what commodities to shop for, what shows to watch, or what holiday places to look for. This collaborative technique should be able to compute the relationship among distinct clients and depending upon their ratings and prescribe items to others who’ve comparable tastes and also finally allowing users to discover more.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123926743","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936090
M. Siva Ramkumar, M. Kannagopalan, A. Amudha, S. Divyapriya
Conversion of wind energy is becoming more popular as a viable renewable energy source to meet electricity demand, both economically and environmentally. A DFIG grid-connected wind power production systems with such a modular multilevel power converters has been suggested as an architecture (M3C). Multilevel converters may be a viable alternative to big WECSs because of their great dependability, controllability, and power ratings. Using a Multilevel Inverters Matrix Conversion in a multi-megawatt wind turbine was the subject of this research.This research models and simulates the workings of a DFIG in detail, and uses space vector modulated matrices conversion for rotor current management. The use of a matrix converter to regulate rotor current is shown. Using the RST regulator, wind energy may be captured at its greatest potential and the actual and reactive power of the system can be effectively controlled. Finally, the results from different operating points show that the system has a good ability to govern itself.
{"title":"Wind Energy Conversion Control for a Double Fed Induction Generator with Modular Multi-Level Matrix Converter","authors":"M. Siva Ramkumar, M. Kannagopalan, A. Amudha, S. Divyapriya","doi":"10.1109/ICECAA55415.2022.9936090","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936090","url":null,"abstract":"Conversion of wind energy is becoming more popular as a viable renewable energy source to meet electricity demand, both economically and environmentally. A DFIG grid-connected wind power production systems with such a modular multilevel power converters has been suggested as an architecture (M3C). Multilevel converters may be a viable alternative to big WECSs because of their great dependability, controllability, and power ratings. Using a Multilevel Inverters Matrix Conversion in a multi-megawatt wind turbine was the subject of this research.This research models and simulates the workings of a DFIG in detail, and uses space vector modulated matrices conversion for rotor current management. The use of a matrix converter to regulate rotor current is shown. Using the RST regulator, wind energy may be captured at its greatest potential and the actual and reactive power of the system can be effectively controlled. Finally, the results from different operating points show that the system has a good ability to govern itself.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"278 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123303699","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936417
Kushal B J, N. P, Nikil S Raaju, Kushal Gowda G V, A. P, G. S
Research in the realm of the agriculture sector is expanding. More than half of India's population depends on agriculture for livelihood, and it is a major contributor to the country's economic growth. Soil quality is changing drastically, affecting the agricultural crop yield. Machine learning and deep learning algorithms are effectively helping to predict the crop based on the soil quality of the land. Data on temperature, humidity, rainfall, soil moisture, and pH are needed to train the machine-learning models. This work has been carried out using the following machine learning models: Decision Tree classifier, K-Neighbor classifier, and Random Forest classifier models. The accuracy of the Random Forest classifier is 93.11 percent, which is higher than the accuracy of the Decision Tree classifier (90.96 percent) and the accuracy of the K-Neighbors classifier (87.63 percent). Along with accuracy, the following performance metrics, such as precision, F1 score, recall, mean absolute error, and log loss, are taken into account. Web-based software has been developed to forecast the crop prediction of farmland based on soil conditions. The real-time data on the soil quality is gathered using the IoT devices from the farm, and the data is saved in the cloud. The data is fed to the machine learning model to predict the crop that would be most suited for cultivation on the farm. Since this is a real-time strategy, farmers can predict the crop with greater accuracy, resulting in higher yields.
{"title":"Real Time Crop Prediction based on Soil Analysis using Internet of Things and Machine Learning","authors":"Kushal B J, N. P, Nikil S Raaju, Kushal Gowda G V, A. P, G. S","doi":"10.1109/ICECAA55415.2022.9936417","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936417","url":null,"abstract":"Research in the realm of the agriculture sector is expanding. More than half of India's population depends on agriculture for livelihood, and it is a major contributor to the country's economic growth. Soil quality is changing drastically, affecting the agricultural crop yield. Machine learning and deep learning algorithms are effectively helping to predict the crop based on the soil quality of the land. Data on temperature, humidity, rainfall, soil moisture, and pH are needed to train the machine-learning models. This work has been carried out using the following machine learning models: Decision Tree classifier, K-Neighbor classifier, and Random Forest classifier models. The accuracy of the Random Forest classifier is 93.11 percent, which is higher than the accuracy of the Decision Tree classifier (90.96 percent) and the accuracy of the K-Neighbors classifier (87.63 percent). Along with accuracy, the following performance metrics, such as precision, F1 score, recall, mean absolute error, and log loss, are taken into account. Web-based software has been developed to forecast the crop prediction of farmland based on soil conditions. The real-time data on the soil quality is gathered using the IoT devices from the farm, and the data is saved in the cloud. The data is fed to the machine learning model to predict the crop that would be most suited for cultivation on the farm. Since this is a real-time strategy, farmers can predict the crop with greater accuracy, resulting in higher yields.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"436 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123609276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936480
Ritu Patidar, Sachin Patel
E-Commerce portals and online selling websites are becoming popular day by day. This paper presents a product recommender model using the natural language processing of the reviews and feedbacks of the customers to enhance the quality of recommendation module. The descriptive data mining can be used to find the most accurate recommendations based on their preferences and behaviors. Various studies on product recommendation for e-commerce portals are being conducted to improve the selection in the quickest time frame, and it has been found that the majority of recommender system only works on selection frequency and user rating. The user's past buying history, as well as the opinions of other users on a product, can aid the development of trust in an online shopping website. In this dimension, an approach is being used and implemented on a variety of relevant projects to investigate the gap area in the traditional system and potential solutions to close it. This research work considers unstructured dataset as data input and perform data cleaning followed by stop word removal and lemmatization. Afterwards Sentiwordnet and ambiguity word net library has been used to estimate two different sentiment score for same sentence to prepare a hybrid sentimental score based on natural meaning and probability of ambiguous word arrangement. This work also integrates FP Intersect clustering algorithm to improvise searching queries after product recommendation. Proposed solution has been implemented using java technology and hadoop ecosystem to provide a big data infrastructure and consider Amazon dataset for experimental analysis. The complete solution was estimated on basis of computation time and also performed for two different dataset to evaluate the consistency of proposed solution. A significant improvement has been observed in multi node cluster solution in compare to single node cluster setup irrespective of enhancement in data size.
{"title":"Design & Implementation of Product Recommendation Solution using Sentiment Analysis","authors":"Ritu Patidar, Sachin Patel","doi":"10.1109/ICECAA55415.2022.9936480","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936480","url":null,"abstract":"E-Commerce portals and online selling websites are becoming popular day by day. This paper presents a product recommender model using the natural language processing of the reviews and feedbacks of the customers to enhance the quality of recommendation module. The descriptive data mining can be used to find the most accurate recommendations based on their preferences and behaviors. Various studies on product recommendation for e-commerce portals are being conducted to improve the selection in the quickest time frame, and it has been found that the majority of recommender system only works on selection frequency and user rating. The user's past buying history, as well as the opinions of other users on a product, can aid the development of trust in an online shopping website. In this dimension, an approach is being used and implemented on a variety of relevant projects to investigate the gap area in the traditional system and potential solutions to close it. This research work considers unstructured dataset as data input and perform data cleaning followed by stop word removal and lemmatization. Afterwards Sentiwordnet and ambiguity word net library has been used to estimate two different sentiment score for same sentence to prepare a hybrid sentimental score based on natural meaning and probability of ambiguous word arrangement. This work also integrates FP Intersect clustering algorithm to improvise searching queries after product recommendation. Proposed solution has been implemented using java technology and hadoop ecosystem to provide a big data infrastructure and consider Amazon dataset for experimental analysis. The complete solution was estimated on basis of computation time and also performed for two different dataset to evaluate the consistency of proposed solution. A significant improvement has been observed in multi node cluster solution in compare to single node cluster setup irrespective of enhancement in data size.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"111 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120883920","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936250
X. Cao
In this paper, a distributed heterogeneous data interoperability HIM model is designed by combining the main features of the two traditional data interoperability methods with the wide-area distributed environment. This model takes into account the advantages of both, and is more suitable for a wide-area distributed environment than using an integrated solution alone. This paper attempts to explore how the various factors affecting consumers' willingness to use in the original model indirectly affect the willingness to use through perceived trust. This paper collects valid data through questionnaire method, and uses SPSS19.0 statistical software to conduct empirical analysis on the data. On the basis of simple e-commerce connotation and development status, it analyzes consumer behavior in e-commerce environment, and discusses e-commerce environment. impact on consumer behavior.
{"title":"Intelligent Modeling System of E-commerce Consumption Behavior based on Distributed Data Integration Algorithm","authors":"X. Cao","doi":"10.1109/ICECAA55415.2022.9936250","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936250","url":null,"abstract":"In this paper, a distributed heterogeneous data interoperability HIM model is designed by combining the main features of the two traditional data interoperability methods with the wide-area distributed environment. This model takes into account the advantages of both, and is more suitable for a wide-area distributed environment than using an integrated solution alone. This paper attempts to explore how the various factors affecting consumers' willingness to use in the original model indirectly affect the willingness to use through perceived trust. This paper collects valid data through questionnaire method, and uses SPSS19.0 statistical software to conduct empirical analysis on the data. On the basis of simple e-commerce connotation and development status, it analyzes consumer behavior in e-commerce environment, and discusses e-commerce environment. impact on consumer behavior.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121146916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936295
Yuhuan Cheng
The role of enterprises in social and economic development is irreplaceable, and the essence of enterprises to enhance their competitiveness is to rely on technical talents to play the best performance. The strategic human resource management method and the traditional human resource management method are distinguished in terms of management status, management concept and management goals, and then the strategic human resource management method has played an important role in the growth of an enterprise. key role, and then help to enhance the core competitiveness of enterprises. The quality of the results is very limited due to the lack of some teaching programs. so in order to realize the teaching reform as soon as possible, this paper takes the course "Data Processing Technology and SPSS" as the main body, and briefly analyzes the teaching reform in the data era.
{"title":"Robustness Analysis of Strategic Human Resource Management Information Platform based on SPSS Big Data Intelligent Debugging Algorithm","authors":"Yuhuan Cheng","doi":"10.1109/ICECAA55415.2022.9936295","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936295","url":null,"abstract":"The role of enterprises in social and economic development is irreplaceable, and the essence of enterprises to enhance their competitiveness is to rely on technical talents to play the best performance. The strategic human resource management method and the traditional human resource management method are distinguished in terms of management status, management concept and management goals, and then the strategic human resource management method has played an important role in the growth of an enterprise. key role, and then help to enhance the core competitiveness of enterprises. The quality of the results is very limited due to the lack of some teaching programs. so in order to realize the teaching reform as soon as possible, this paper takes the course \"Data Processing Technology and SPSS\" as the main body, and briefly analyzes the teaching reform in the data era.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121210040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936286
V. J, R. R
In today’s scenario, several brain and neurological disorders are being discovered and the complexity of structure of brain varies with age. The early diagnosis of these diseases is of utmost importance. so, the segmentation process of Magnetic resonance imaging is done to obtain maximum accuracy. Precise segmentation of the magnetic resonance imaging image is required for the diagnosing the brain tumor using laptop-based clinical requirement. Using each of the segmentation strategies, which method is best for segmenting the tumor can be identified from each of the images. This work proposes an advanced machine learning and deep learning based predictive method to forecast malignant and benign tumor. This is an effective and simple model for the detection and classification of brain tumor.
{"title":"Advanced Detection of Brain Disease using ML and DL Algorithm","authors":"V. J, R. R","doi":"10.1109/ICECAA55415.2022.9936286","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936286","url":null,"abstract":"In today’s scenario, several brain and neurological disorders are being discovered and the complexity of structure of brain varies with age. The early diagnosis of these diseases is of utmost importance. so, the segmentation process of Magnetic resonance imaging is done to obtain maximum accuracy. Precise segmentation of the magnetic resonance imaging image is required for the diagnosing the brain tumor using laptop-based clinical requirement. Using each of the segmentation strategies, which method is best for segmenting the tumor can be identified from each of the images. This work proposes an advanced machine learning and deep learning based predictive method to forecast malignant and benign tumor. This is an effective and simple model for the detection and classification of brain tumor.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121397537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936188
A. Yasmin, S. Kamalakkannan, P. Kavitha
Stock market prediction is the needed emerging economic statistics from business to normal middle-class peoples, to make their investment as a profitable one. This article has utilized the dynamic dataset of the company. The dataset includes the closing price of the stock of the last 290 working days. The dataset is downloaded using the yahoo finance (https://finance.yahoo.com), so the data is pretty accurate. Further, some technical analysis and machine learning techniques are used to predict the future prices and exchange of company’s stock. The machine learning models includes Linear Regression, Decision Tree, Random Forest, SVR, LSTM, Lasso Regression, KNN, Bayesian Ridge, Gradient Boosting, and Ada Boost are used in this article and suitable technique for the dataset is chosen for performing effective prediction of stock market.
{"title":"Stock Market Prediction using Machine Learning Models","authors":"A. Yasmin, S. Kamalakkannan, P. Kavitha","doi":"10.1109/ICECAA55415.2022.9936188","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936188","url":null,"abstract":"Stock market prediction is the needed emerging economic statistics from business to normal middle-class peoples, to make their investment as a profitable one. This article has utilized the dynamic dataset of the company. The dataset includes the closing price of the stock of the last 290 working days. The dataset is downloaded using the yahoo finance (https://finance.yahoo.com), so the data is pretty accurate. Further, some technical analysis and machine learning techniques are used to predict the future prices and exchange of company’s stock. The machine learning models includes Linear Regression, Decision Tree, Random Forest, SVR, LSTM, Lasso Regression, KNN, Bayesian Ridge, Gradient Boosting, and Ada Boost are used in this article and suitable technique for the dataset is chosen for performing effective prediction of stock market.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114529211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936280
Wen-jia Wei
On the basis of summarizing the current situation of China's rural poverty alleviation model in the new century, this paper summarizes and summarizes the characteristics of innovation and integration of rural poverty alleviation model at this stage, and analyzes the development trend of rural poverty alleviation model. Management method, marketing model, and e-commerce platform model are set out to propose enlightening suggestions for the optimization of the parallel path of rural e-commerce, and then according to the content of demand analysis and system outline design, using Spearman correlation analysis method and ordinary least squares The estimation model analyzes the influencing factors of poverty, distinguishes the poverty-inducing and eradicating factors that have an impact on poverty, and obtains their impact on poverty, so as to provide a reference standard for determining the investment target range of poverty alleviation funds.
{"title":"The Latest Integration and Effect Evaluation Intelligent Algorithm of Rural Poverty Alleviation Model based on Parallel E-Commerce System Software Architecture","authors":"Wen-jia Wei","doi":"10.1109/ICECAA55415.2022.9936280","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936280","url":null,"abstract":"On the basis of summarizing the current situation of China's rural poverty alleviation model in the new century, this paper summarizes and summarizes the characteristics of innovation and integration of rural poverty alleviation model at this stage, and analyzes the development trend of rural poverty alleviation model. Management method, marketing model, and e-commerce platform model are set out to propose enlightening suggestions for the optimization of the parallel path of rural e-commerce, and then according to the content of demand analysis and system outline design, using Spearman correlation analysis method and ordinary least squares The estimation model analyzes the influencing factors of poverty, distinguishes the poverty-inducing and eradicating factors that have an impact on poverty, and obtains their impact on poverty, so as to provide a reference standard for determining the investment target range of poverty alleviation funds.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124312816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-13DOI: 10.1109/ICECAA55415.2022.9936261
Ayushi Gupta, R. Singh
This paper presents how to improve underwater images with non-uniform lighting, low contrast, blurriness, and degraded color using a Physical Neural Network (PNN)-based image-enhancing approach. The suggested method is built on the deep learning principle and focuses on a damaged or noisy underwater image's input images, weight & weight maps, and white balance data. The proposed method employs a variety of weight maps, including luminance, contrast, chromatic, and saliency, to create an image that overcomes the limits of the initial or noised image, which lacks distinct clarity. Reduced noise levels and better exposed dark regions, as well as increased global contrast and finer features and edges, can be found in the underwater image, created utilizing the aforementioned processes. The experiments are carried out on the EUVP dataset, and it is observed that the proposed method surpasses other state-of-the-art methods in terms of efficiency.
{"title":"A Deep Learning Approach to Enhance Underwater Images with Low Contrast, Blurriness and Degraded Color","authors":"Ayushi Gupta, R. Singh","doi":"10.1109/ICECAA55415.2022.9936261","DOIUrl":"https://doi.org/10.1109/ICECAA55415.2022.9936261","url":null,"abstract":"This paper presents how to improve underwater images with non-uniform lighting, low contrast, blurriness, and degraded color using a Physical Neural Network (PNN)-based image-enhancing approach. The suggested method is built on the deep learning principle and focuses on a damaged or noisy underwater image's input images, weight & weight maps, and white balance data. The proposed method employs a variety of weight maps, including luminance, contrast, chromatic, and saliency, to create an image that overcomes the limits of the initial or noised image, which lacks distinct clarity. Reduced noise levels and better exposed dark regions, as well as increased global contrast and finer features and edges, can be found in the underwater image, created utilizing the aforementioned processes. The experiments are carried out on the EUVP dataset, and it is observed that the proposed method surpasses other state-of-the-art methods in terms of efficiency.","PeriodicalId":273850,"journal":{"name":"2022 International Conference on Edge Computing and Applications (ICECAA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126485543","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：