Pub Date : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9753971
G. Praveenkumar, R. Nagaraj
This paper presents a novel adaptive anisotropic diffusion filtered deep neural network (AADF-DNN) model for achieving effective image classification with increase the accuracy and reduces the running time, false-positive ratio. The proposed AADF-DNN model uses deep learning and Gaussian activation function to reduce the false-positive ratio. First, a number of input images are given to the input layer get pre-processed by adaptive anisotropic diffusion filtered reducing the noise. Then, the input layer sends the input images into hidden layers. The hidden layer is used to extract significant features such as shape, color, texture, and size for reducing the running time. Next, the Gaussian activation function is used to classify the images into corresponding classes based on the measurement value between the extracted features and pre-stored features. Finally, the classification results of input images are obtained. Experimental results illustrate that the AADF-DNN model enhances the classification of image performance with higher accuracy at the minimal running time than compared to the PCGRBM.
{"title":"Intelligent Adaptive Anisotropic Diffusion Filtered Deep Neural Network With Gaussian Activation For Image Classification","authors":"G. Praveenkumar, R. Nagaraj","doi":"10.1109/ICCMC53470.2022.9753971","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9753971","url":null,"abstract":"This paper presents a novel adaptive anisotropic diffusion filtered deep neural network (AADF-DNN) model for achieving effective image classification with increase the accuracy and reduces the running time, false-positive ratio. The proposed AADF-DNN model uses deep learning and Gaussian activation function to reduce the false-positive ratio. First, a number of input images are given to the input layer get pre-processed by adaptive anisotropic diffusion filtered reducing the noise. Then, the input layer sends the input images into hidden layers. The hidden layer is used to extract significant features such as shape, color, texture, and size for reducing the running time. Next, the Gaussian activation function is used to classify the images into corresponding classes based on the measurement value between the extracted features and pre-stored features. Finally, the classification results of input images are obtained. Experimental results illustrate that the AADF-DNN model enhances the classification of image performance with higher accuracy at the minimal running time than compared to the PCGRBM.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116025170","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9754118
L. M, J. J. Jeya Sheela M.E
The kitchen is among the highly crucial rooms in any home. While working in the kitchen, many safety precautions must be performed. An uncontrolled fire, an excessive rise in temperatures, the existence of leaking gas, and other factors can all contribute to surprise explosions. The explosions must be spotted and, cleared as soon as possible. The paper's principle goal is to discover and, remedy kitchen safety concerns. When there is a significant rise in leakages, the Sensor senses it and, the exhaust system turns on, the alarm goes on, when the gas level surpasses the recommended amount. It also automatically shuts down the supply of gas. Even, the information is notified to the users' mobile phone, by the app. Additionally, many Fire detecting systems are deployed in this system, to detect the fire. In the event of a fire, it senses it and, immediately sprays water to shut off the flic and, shut off the Gas supply. When the temperature is high in the kitchen, it ventilates it by exhaust system, thus by dropping the room temperature. It even uses a PIR sensor, to inspect for signs of a person, in the kitchen. Finally, this technology can be deployed to automate the kitchen, allowing users to utilize the kitchen equipment. All of these controls and, the information is accessed using the Blynk app, which can be accessed by smart phones. This solution is envisioned to increase home Protection, in the Kitchen, along with to automate your kitchen and, daily tasks for senior users.
{"title":"Designing an IoT based Kitchen Monitoring and Automation System for Gas and Fire Detection","authors":"L. M, J. J. Jeya Sheela M.E","doi":"10.1109/ICCMC53470.2022.9754118","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9754118","url":null,"abstract":"The kitchen is among the highly crucial rooms in any home. While working in the kitchen, many safety precautions must be performed. An uncontrolled fire, an excessive rise in temperatures, the existence of leaking gas, and other factors can all contribute to surprise explosions. The explosions must be spotted and, cleared as soon as possible. The paper's principle goal is to discover and, remedy kitchen safety concerns. When there is a significant rise in leakages, the Sensor senses it and, the exhaust system turns on, the alarm goes on, when the gas level surpasses the recommended amount. It also automatically shuts down the supply of gas. Even, the information is notified to the users' mobile phone, by the app. Additionally, many Fire detecting systems are deployed in this system, to detect the fire. In the event of a fire, it senses it and, immediately sprays water to shut off the flic and, shut off the Gas supply. When the temperature is high in the kitchen, it ventilates it by exhaust system, thus by dropping the room temperature. It even uses a PIR sensor, to inspect for signs of a person, in the kitchen. Finally, this technology can be deployed to automate the kitchen, allowing users to utilize the kitchen equipment. All of these controls and, the information is accessed using the Blynk app, which can be accessed by smart phones. This solution is envisioned to increase home Protection, in the Kitchen, along with to automate your kitchen and, daily tasks for senior users.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121960731","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9753760
Angad Sethi, Kavinder Singh
Existing automated scoring models implement layers of traditional recurrent neural networks to achieve reasonable performance. However, the models provide limited performance due to the limited capacity to encode long-term dependencies. The paper proposed a novel architecture incorporating pioneering language models of the natural language processing community. We leverage pre-trained language models and integrate it with adapter modules, which use a bottle-neck architecture to reduce the number of trainable parameters while delivering excellent performance. We also propose a model by re-purposing the bidirectional attention flow model to detect adversarial essays. The model we put forward achieves state-of-the-art performance on most essay prompts in the Automated Student Assessment Prize data set. We outline the previous methods employed to attempt this task, and show how our model outperforms them.
{"title":"Natural Language Processing based Automated Essay Scoring with Parameter-Efficient Transformer Approach","authors":"Angad Sethi, Kavinder Singh","doi":"10.1109/ICCMC53470.2022.9753760","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9753760","url":null,"abstract":"Existing automated scoring models implement layers of traditional recurrent neural networks to achieve reasonable performance. However, the models provide limited performance due to the limited capacity to encode long-term dependencies. The paper proposed a novel architecture incorporating pioneering language models of the natural language processing community. We leverage pre-trained language models and integrate it with adapter modules, which use a bottle-neck architecture to reduce the number of trainable parameters while delivering excellent performance. We also propose a model by re-purposing the bidirectional attention flow model to detect adversarial essays. The model we put forward achieves state-of-the-art performance on most essay prompts in the Automated Student Assessment Prize data set. We outline the previous methods employed to attempt this task, and show how our model outperforms them.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117230914","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9754102
Bin Feng, Ke Xu, Lisha Chen
Based on the existing scholars’ research on consumption upgrading, this paper analyzes the connotation and trend of consumption upgrading and other related theories, and then uses the combination of Maslow’s demand theory and questionnaire survey to study the development trend of rural leisure sports consumption. Completed Design of crowdfunding platform based on blockchain and cloud payment. Expand the design part according to the three-tier architecture, including the interface layer, data encapsulation layer, and business logic layer. The interface layer involves the underlying interface of the blockchain, and developer identity verification is required before interface calls are made.
{"title":"Security Analysis of Rural Sports Consumption Upgrade Based on Cloud Payment and Blockchain","authors":"Bin Feng, Ke Xu, Lisha Chen","doi":"10.1109/ICCMC53470.2022.9754102","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9754102","url":null,"abstract":"Based on the existing scholars’ research on consumption upgrading, this paper analyzes the connotation and trend of consumption upgrading and other related theories, and then uses the combination of Maslow’s demand theory and questionnaire survey to study the development trend of rural leisure sports consumption. Completed Design of crowdfunding platform based on blockchain and cloud payment. Expand the design part according to the three-tier architecture, including the interface layer, data encapsulation layer, and business logic layer. The interface layer involves the underlying interface of the blockchain, and developer identity verification is required before interface calls are made.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125962533","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9753700
ChangChun Yan, Jiajia Zhang
In this paper, the basic theory of neural network introduces the basic concept, development process and application of neural network, analyzes the basic working principle of the network and the relationship between neural network and pattern recognition, and qualitatively demonstrates the basic mechanism of neural network fusion recognition. On the basis of discussing the connotation of current Chinese industrial modernization, a set of 23 specific indicators including industrial system construction, production system construction. The level evaluation index system reveals the regional differentiation characteristics of China's industrial modernization development level. The characteristics of multi-source data have the characteristics of high dimensionality and the shortcomings of the network in solving such problems. Several improved methods of network learning algorithms have been studied.
{"title":"Neural Computing and Data Fusion Modeling Analysis of the Index System of China's Industrial Modernization Level","authors":"ChangChun Yan, Jiajia Zhang","doi":"10.1109/ICCMC53470.2022.9753700","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9753700","url":null,"abstract":"In this paper, the basic theory of neural network introduces the basic concept, development process and application of neural network, analyzes the basic working principle of the network and the relationship between neural network and pattern recognition, and qualitatively demonstrates the basic mechanism of neural network fusion recognition. On the basis of discussing the connotation of current Chinese industrial modernization, a set of 23 specific indicators including industrial system construction, production system construction. The level evaluation index system reveals the regional differentiation characteristics of China's industrial modernization development level. The characteristics of multi-source data have the characteristics of high dimensionality and the shortcomings of the network in solving such problems. Several improved methods of network learning algorithms have been studied.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"98 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124679607","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9753840
N. B. Raja, P. Selvi Rajendran
Agriculture, along with its related industries, is without a doubt India’s largest source of income. Plant disease is a major concern in agriculture today, as it decreases food production and quality. Plant diseases, that are previously infected, microbes, fungus, roundworms, and nutrient deficiency, inflict significant damage to crops and have the following consequences: lower crop yield and quality. It also kills the plant, reduces the farmer’s profits, and raises the cost of production throughout the control period. The banana is the most important fruit in Pacific and the Asia. The banana plant was susceptible to several ailments, the effects of that can be seen on the leaves. The infections would be Streak Virus, yellow Sigatoka, Panama, Black Sigatoka, and Banana Bunchy Top Virus. As a result, early detection of plant diseases is important. These researches greatly focus on Deep learning algorithms. In this study, huge potential efforts are made to study the complete background of banana disease detection. In the end, this study also highlights a comparison of recent research directions in banana leaf disease detection using various classification methods.
{"title":"Comparative Analysis of Banana Leaf Disease Detection and Classification Methods","authors":"N. B. Raja, P. Selvi Rajendran","doi":"10.1109/ICCMC53470.2022.9753840","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9753840","url":null,"abstract":"Agriculture, along with its related industries, is without a doubt India’s largest source of income. Plant disease is a major concern in agriculture today, as it decreases food production and quality. Plant diseases, that are previously infected, microbes, fungus, roundworms, and nutrient deficiency, inflict significant damage to crops and have the following consequences: lower crop yield and quality. It also kills the plant, reduces the farmer’s profits, and raises the cost of production throughout the control period. The banana is the most important fruit in Pacific and the Asia. The banana plant was susceptible to several ailments, the effects of that can be seen on the leaves. The infections would be Streak Virus, yellow Sigatoka, Panama, Black Sigatoka, and Banana Bunchy Top Virus. As a result, early detection of plant diseases is important. These researches greatly focus on Deep learning algorithms. In this study, huge potential efforts are made to study the complete background of banana disease detection. In the end, this study also highlights a comparison of recent research directions in banana leaf disease detection using various classification methods.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128752500","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9754001
B. Pattanaik, Mukil Alagirisamy
Although EV offers several advantages such as being terrain friendly, producing less noise, and reducing dependency on reactive powers, it also has significant drawbacks. High power and high energy force systems for EVs will be obtained concurrently through the integration of batteries and ultra-capacitors. As a result, ultra-capacitors manage short-term power demands, while batteries provide long-term mobility for the vehicle. A novel algorithm, cold-thoroughbred GOA-GA, is proposed by combining the GOA and GA. The proposed hybrid GOA-GA has a strong eventuality to escape original optima while achieving the convergence. The proposed crossbred algorithm is used to perform a multi-objective function optimization to drop the HESS mass as well as increase the vehicle's operating range. By exercising the MATLAB/ Goad software, the entire frame was erected with the FTP-75, US06 (maximum speed as well as demanded acceleration) and HWFET driving cycles. When compared to an equivalent EV posted with a single HESS unit, the proposed binary-HESS armature has increased driving range while lowering the HESS mass.
{"title":"Hybrid Energy Dual Storage Systems for EV Powertrain with Enhanced Algorithm GOA and GA","authors":"B. Pattanaik, Mukil Alagirisamy","doi":"10.1109/ICCMC53470.2022.9754001","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9754001","url":null,"abstract":"Although EV offers several advantages such as being terrain friendly, producing less noise, and reducing dependency on reactive powers, it also has significant drawbacks. High power and high energy force systems for EVs will be obtained concurrently through the integration of batteries and ultra-capacitors. As a result, ultra-capacitors manage short-term power demands, while batteries provide long-term mobility for the vehicle. A novel algorithm, cold-thoroughbred GOA-GA, is proposed by combining the GOA and GA. The proposed hybrid GOA-GA has a strong eventuality to escape original optima while achieving the convergence. The proposed crossbred algorithm is used to perform a multi-objective function optimization to drop the HESS mass as well as increase the vehicle's operating range. By exercising the MATLAB/ Goad software, the entire frame was erected with the FTP-75, US06 (maximum speed as well as demanded acceleration) and HWFET driving cycles. When compared to an equivalent EV posted with a single HESS unit, the proposed binary-HESS armature has increased driving range while lowering the HESS mass.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129838419","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9754135
D. P. Singh, Susheel George Joseph, V. Selvi, S. Karunakaran, A. G., B. Jegajothi
Content-based image retrieval (CBIR) is commonly employed to retrieve images from a massive set of unlabeled images. The design of CBIR model faces several limitations, as it is mainly based on the extraction of image features to calculate the similarity amongst the query image (QI) and database images. The recent advances of deep learning (DL) models help to attain remarkable retrieval outcomes. In this view, this paper presents a novel quasi-oppositional satin bowerbird optimizer with Densely Connected Networks (QOSBO-DCN) for CBIR. The proposed QOSBO-DCN technique aims to properly retrieve the images related to the QI in an effective and automated manner. The proposed QOSBO-DCN technique derives a DenseNet-77 model as a feature extractor to derive feature vectors from the QI and database images. Besides, the QOSBO algorithm is utilized to adjust the hyperparameter values of the DenseNet-77 model in such a way that the retrieval performance can be improved. Additionally, Euclidean distance is used as a similarity measurement approach to determine the highly resembling images and retrieve them. The simulation analysis of the QOSBO-DCN technique is performed using Corel10K dataset and the results reported the betterment of the QOSBO-DCN technique over the existing techniques.
{"title":"Quasi-Oppositional Satin Bowerbird with Deep Learning based Content based Image Retrieval","authors":"D. P. Singh, Susheel George Joseph, V. Selvi, S. Karunakaran, A. G., B. Jegajothi","doi":"10.1109/ICCMC53470.2022.9754135","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9754135","url":null,"abstract":"Content-based image retrieval (CBIR) is commonly employed to retrieve images from a massive set of unlabeled images. The design of CBIR model faces several limitations, as it is mainly based on the extraction of image features to calculate the similarity amongst the query image (QI) and database images. The recent advances of deep learning (DL) models help to attain remarkable retrieval outcomes. In this view, this paper presents a novel quasi-oppositional satin bowerbird optimizer with Densely Connected Networks (QOSBO-DCN) for CBIR. The proposed QOSBO-DCN technique aims to properly retrieve the images related to the QI in an effective and automated manner. The proposed QOSBO-DCN technique derives a DenseNet-77 model as a feature extractor to derive feature vectors from the QI and database images. Besides, the QOSBO algorithm is utilized to adjust the hyperparameter values of the DenseNet-77 model in such a way that the retrieval performance can be improved. Additionally, Euclidean distance is used as a similarity measurement approach to determine the highly resembling images and retrieve them. The simulation analysis of the QOSBO-DCN technique is performed using Corel10K dataset and the results reported the betterment of the QOSBO-DCN technique over the existing techniques.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"2016 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127343371","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9753979
Sheetal Prusty, Rutuparna Panda, Lingraj Dora, S. Agrawal
The unregulated and rapid growth of tissues in the brain causes a tumor. It may lead to death if not addressed in the early stages. Despite numerous considerable efforts and promising results, effective segmentation and classification remain a challenge. The differences in tumor location, shape, and size present a significant difficulty for brain tumor identification. The goal of this paper is to give a descriptive literature review about the identification of brain tumors using various scanning techniques to assist the scientists. The brain and its anatomy, publicly available datasets, modalities, and deep learning-based techniques are covered in this paper. This paper shows the use of various types of deep learning methods for brain segmentation and classification. Additionally, this survey includes all relevant material on detecting brain tumors. Moreover, their benefits, as well as limitations, are discussed. Finally, advancements and future trends are considered in our study to provide a research direction.
{"title":"A Study on Brain Tumor Analysis Using Deep Learning Methods","authors":"Sheetal Prusty, Rutuparna Panda, Lingraj Dora, S. Agrawal","doi":"10.1109/ICCMC53470.2022.9753979","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9753979","url":null,"abstract":"The unregulated and rapid growth of tissues in the brain causes a tumor. It may lead to death if not addressed in the early stages. Despite numerous considerable efforts and promising results, effective segmentation and classification remain a challenge. The differences in tumor location, shape, and size present a significant difficulty for brain tumor identification. The goal of this paper is to give a descriptive literature review about the identification of brain tumors using various scanning techniques to assist the scientists. The brain and its anatomy, publicly available datasets, modalities, and deep learning-based techniques are covered in this paper. This paper shows the use of various types of deep learning methods for brain segmentation and classification. Additionally, this survey includes all relevant material on detecting brain tumors. Moreover, their benefits, as well as limitations, are discussed. Finally, advancements and future trends are considered in our study to provide a research direction.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130575437","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 : 2022-03-29DOI: 10.1109/ICCMC53470.2022.9754011
Shyam Chand G, H. R.
Plants are an important source of energy for all organisms on earth. But plant diseases act as a hindrance for effective consumption of plant products and also adversely affect the life of crops. When the farmers diagnose diseases manually, lot of difficulties arise due of the lack of knowledge and unavailability of professionals. It also requires much time in manually identifying and classifying crop diseases. In this context, a model is proposed for identifying plant diseases and to suggest remedial measures. Here a transfer learning based CNN model is implemented using VGG16 and ResNet50. The dataset used consists of 34824 training images and 8767 testing images of thirty-eight output classifications including 26 crop diseases found in fourteen crops. The VGG16 model shown 99.1 percentage accuracy and ResNet50 exhibited 99.3 percentage accuracy with considerable reduction of computation time than VGG16.
{"title":"Plant Disease Identification and Suggestion of Remedial Measures using Machine Learning","authors":"Shyam Chand G, H. R.","doi":"10.1109/ICCMC53470.2022.9754011","DOIUrl":"https://doi.org/10.1109/ICCMC53470.2022.9754011","url":null,"abstract":"Plants are an important source of energy for all organisms on earth. But plant diseases act as a hindrance for effective consumption of plant products and also adversely affect the life of crops. When the farmers diagnose diseases manually, lot of difficulties arise due of the lack of knowledge and unavailability of professionals. It also requires much time in manually identifying and classifying crop diseases. In this context, a model is proposed for identifying plant diseases and to suggest remedial measures. Here a transfer learning based CNN model is implemented using VGG16 and ResNet50. The dataset used consists of 34824 training images and 8767 testing images of thirty-eight output classifications including 26 crop diseases found in fourteen crops. The VGG16 model shown 99.1 percentage accuracy and ResNet50 exhibited 99.3 percentage accuracy with considerable reduction of computation time than VGG16.","PeriodicalId":345346,"journal":{"name":"2022 6th International Conference on Computing Methodologies and Communication (ICCMC)","volume":"225 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132443563","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：