Pub Date : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492791
Céline Rabouy, Sébastien Paris, H. Glotin
Sparse Coding (SC) is an approach widely used in image classification. It allows to reconstruct the signal with few elements and follows the specific scheme of Bag-of-Words (BoW). However, we can observe a decorrelation between input patches and reconstructed patches. To answer that, Graph regularized Sparse Coding (GSC) exists. As GSC works on the training set, we propose a new modeling, Joint Sparse Coding (JSC), for the testing set. JSC can be seen as a tradeoff between SC and GSC. To go furthermore, we explore the simple fusion of models. To explain the observations of the fusion results, we will be led to study the orthogonality properties by the cosine computation. These applied on UIUCsports, 17Flowers and scenes15 lead us to put forward the various qualities of the studied bases and sparse representation. We demonstrate a significant improvement of the State-of-the-Art for the UIUCsports database.
{"title":"Improving image classification by orthogonality of sparse codes","authors":"Céline Rabouy, Sébastien Paris, H. Glotin","doi":"10.1109/SOCPAR.2015.7492791","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492791","url":null,"abstract":"Sparse Coding (SC) is an approach widely used in image classification. It allows to reconstruct the signal with few elements and follows the specific scheme of Bag-of-Words (BoW). However, we can observe a decorrelation between input patches and reconstructed patches. To answer that, Graph regularized Sparse Coding (GSC) exists. As GSC works on the training set, we propose a new modeling, Joint Sparse Coding (JSC), for the testing set. JSC can be seen as a tradeoff between SC and GSC. To go furthermore, we explore the simple fusion of models. To explain the observations of the fusion results, we will be led to study the orthogonality properties by the cosine computation. These applied on UIUCsports, 17Flowers and scenes15 lead us to put forward the various qualities of the studied bases and sparse representation. We demonstrate a significant improvement of the State-of-the-Art for the UIUCsports database.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133123694","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492783
Y. Herdiyeni, Asep Rahmat Ginanjar, M. Rake, Linggar Anggoro, S. Douady, Ervizal A. M. Zuhud
We presents a mobile biodiversity informatics tools for identifying and mapping Indonesian medicinal plants. The system - called MedLeaf - has been developed as a prototype data resource for documenting, integrating, disseminating, and identifying of Indonesian medicinal plants. Identification of medicinal plant is done automatically based on digital image processing. Fuzzy Local Binary Pattern (LBP) and geometrical features are used to extract leaves features. Probabilistic Neural Network is used as classifier for discrimination. Data set consist of 85 species of Indonesian medicinal plants with 3,502 leaves digital images. Our results indicate that combination of leaves features outperform than using single features with accuracy 88.5%. The distribution of medicinal plants can be shown on mobile phone using GIS application. The application is essential to help people identify the medicinal plants and disseminate information of medicinal plants distribution in Indonesia.
{"title":"MedLeaf: Mobile biodiversity informatics tool for mapping and identifying Indonesian medicinal Plants","authors":"Y. Herdiyeni, Asep Rahmat Ginanjar, M. Rake, Linggar Anggoro, S. Douady, Ervizal A. M. Zuhud","doi":"10.1109/SOCPAR.2015.7492783","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492783","url":null,"abstract":"We presents a mobile biodiversity informatics tools for identifying and mapping Indonesian medicinal plants. The system - called MedLeaf - has been developed as a prototype data resource for documenting, integrating, disseminating, and identifying of Indonesian medicinal plants. Identification of medicinal plant is done automatically based on digital image processing. Fuzzy Local Binary Pattern (LBP) and geometrical features are used to extract leaves features. Probabilistic Neural Network is used as classifier for discrimination. Data set consist of 85 species of Indonesian medicinal plants with 3,502 leaves digital images. Our results indicate that combination of leaves features outperform than using single features with accuracy 88.5%. The distribution of medicinal plants can be shown on mobile phone using GIS application. The application is essential to help people identify the medicinal plants and disseminate information of medicinal plants distribution in Indonesia.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133830367","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492806
Bo-Wen Hsieh, Wei-Lun Chen, Jian-Hung Chen
Uploading and sharing video has become a populartrend on internet recently. However, it is very difficult to understand which parts of video gain more attentions than other parts. Comment-popping video sharing websites, such as Niconico, is a new kind of emerging video sharing websites. Such websites allows users to input timestamp comments within shared video. This paper proposes two video summarization systems for comment-popping video websites based on the concept of folksonomy. The timestamp comments are analyzed and mined, and then the significant clips are chosen based on the mined information and the frequency of comments or keywords. Hereafter, a summary video is merged from these significant clips.
{"title":"Video summarization of timestamp comments videos based on concept of folksonomy","authors":"Bo-Wen Hsieh, Wei-Lun Chen, Jian-Hung Chen","doi":"10.1109/SOCPAR.2015.7492806","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492806","url":null,"abstract":"Uploading and sharing video has become a populartrend on internet recently. However, it is very difficult to understand which parts of video gain more attentions than other parts. Comment-popping video sharing websites, such as Niconico, is a new kind of emerging video sharing websites. Such websites allows users to input timestamp comments within shared video. This paper proposes two video summarization systems for comment-popping video websites based on the concept of folksonomy. The timestamp comments are analyzed and mined, and then the significant clips are chosen based on the mined information and the frequency of comments or keywords. Hereafter, a summary video is merged from these significant clips.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121172293","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492782
K. Kinoshita
This paper describes estimation of the inverse model by multi-layered neural network. The back-propagation rule requires a sensitivity function of a system. If the system has uncertainly, then we can not calculate the sensitivity function. Hence, we propose a learning rule based on particle swarm optimization (PSO) combining with simultaneous perturbation. PSO and simultaneous perturbation are suitable for estimation of the inverse model with uncertainly, because they can update by only value of the objective function. PSO has a capability of finding a global minimum and simultaneous perturbation can search local area efficiently. We introduce two adaptation method of the combination ratio. One of them is to adapt it depending on the distance from gbest. The other is to adapt it depending on the value of the objective function. The proposed method are investigated using inverse kinematics problem. The simulation results show that the proposed methods obtain the more accurate inverse model.
{"title":"Estimation of inverse model by PSO and simultaneous perturbation method","authors":"K. Kinoshita","doi":"10.1109/SOCPAR.2015.7492782","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492782","url":null,"abstract":"This paper describes estimation of the inverse model by multi-layered neural network. The back-propagation rule requires a sensitivity function of a system. If the system has uncertainly, then we can not calculate the sensitivity function. Hence, we propose a learning rule based on particle swarm optimization (PSO) combining with simultaneous perturbation. PSO and simultaneous perturbation are suitable for estimation of the inverse model with uncertainly, because they can update by only value of the objective function. PSO has a capability of finding a global minimum and simultaneous perturbation can search local area efficiently. We introduce two adaptation method of the combination ratio. One of them is to adapt it depending on the distance from gbest. The other is to adapt it depending on the value of the objective function. The proposed method are investigated using inverse kinematics problem. The simulation results show that the proposed methods obtain the more accurate inverse model.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115981697","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492820
Yu-Min Chiang, Yih-Lon Lin, Wei-Hong Chien
Nowadays, touch panel is used as the interface of many portable consumer electronic products, such as smart phone, digital camera, GPS, and notebook. To ensure the quality of touch panel, it is necessary to inspect the serious defects during the production process. The manufacturing processes of the capacitive touch panel are complicated. The touch sensor is one of the most important components because it directly defines the function of touch panels. The quality of the touch sensor will greatly influence the overall quality and cost of the touch panel. Regular textures can be found on the touch sensor, and it would increase the workload of manual inspection. The automated machine vision can be applied to improve these problems if a good defect detection algorithm can be provided. This research develops an automated surface defect inspection system for capacitive touch sensor by using several image processing methods. First, Fourier transformation and a multi band-pass filter is applied to filter out regular texture. Second, based on Canny edge detection, binarization, and morphology method, the defects can be detected. 60 touch sensor images of size 640×320 are tested. The average accuracy is 96.67% and the processing time is 0.15 seconds for each image.
{"title":"Automated surface defect inspection system for capacitive touch sensor","authors":"Yu-Min Chiang, Yih-Lon Lin, Wei-Hong Chien","doi":"10.1109/SOCPAR.2015.7492820","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492820","url":null,"abstract":"Nowadays, touch panel is used as the interface of many portable consumer electronic products, such as smart phone, digital camera, GPS, and notebook. To ensure the quality of touch panel, it is necessary to inspect the serious defects during the production process. The manufacturing processes of the capacitive touch panel are complicated. The touch sensor is one of the most important components because it directly defines the function of touch panels. The quality of the touch sensor will greatly influence the overall quality and cost of the touch panel. Regular textures can be found on the touch sensor, and it would increase the workload of manual inspection. The automated machine vision can be applied to improve these problems if a good defect detection algorithm can be provided. This research develops an automated surface defect inspection system for capacitive touch sensor by using several image processing methods. First, Fourier transformation and a multi band-pass filter is applied to filter out regular texture. Second, based on Canny edge detection, binarization, and morphology method, the defects can be detected. 60 touch sensor images of size 640×320 are tested. The average accuracy is 96.67% and the processing time is 0.15 seconds for each image.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131866558","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492827
Llewyn Salt, B. Kusy, R. Jurdak
Long-term tracking is an expanding field with applications in logistics, ecology and wearable computing. The main challenge for longevity of tracking applications is the high energy consumption of GPS, which has been addressed by using low power sensors to trigger GPS activation upon detecting events of interest. While triggering can reduce power consumption, static thresholds can underperform in the longterm as context changes. This paper presents an auto-covariance based triggering algorithm that adapts trigger thresholds based on the incoming data and is effective with limited prior knowledge. We test the algorithm on empirical data from flying foxes and show that it outperforms static thresholding and existing adaptive algorithms from the literature.
{"title":"Adaptive threshold triggering of GPS for long-term tracking in WSN","authors":"Llewyn Salt, B. Kusy, R. Jurdak","doi":"10.1109/SOCPAR.2015.7492827","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492827","url":null,"abstract":"Long-term tracking is an expanding field with applications in logistics, ecology and wearable computing. The main challenge for longevity of tracking applications is the high energy consumption of GPS, which has been addressed by using low power sensors to trigger GPS activation upon detecting events of interest. While triggering can reduce power consumption, static thresholds can underperform in the longterm as context changes. This paper presents an auto-covariance based triggering algorithm that adapts trigger thresholds based on the incoming data and is effective with limited prior knowledge. We test the algorithm on empirical data from flying foxes and show that it outperforms static thresholding and existing adaptive algorithms from the literature.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124632378","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492824
Sang-Muk Jo, Sung-Bae Cho
Various user's situation and small screen compared with computer keyboard influence the performance of the IME (Input Method Editor, a program that allows users to enter characters and symbols). According to the hand that a user is using, it has a significant effect on the IME input. In this paper, we propose a method based on decision tree to generate GUI automatically for the IME. We collect sensor data from Android smartphone and key data that user enters with IME. A comparison experiment with different input postures was conducted to show the feasibility of the proposed method.
{"title":"Automatic generation of GUI for smartphone IME by classifying user behavior patterns","authors":"Sang-Muk Jo, Sung-Bae Cho","doi":"10.1109/SOCPAR.2015.7492824","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492824","url":null,"abstract":"Various user's situation and small screen compared with computer keyboard influence the performance of the IME (Input Method Editor, a program that allows users to enter characters and symbols). According to the hand that a user is using, it has a significant effect on the IME input. In this paper, we propose a method based on decision tree to generate GUI automatically for the IME. We collect sensor data from Android smartphone and key data that user enters with IME. A comparison experiment with different input postures was conducted to show the feasibility of the proposed method.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130905983","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492779
Katsuhiro Honda, Masahiro Omori, S. Ubukata, A. Notsu
k-anonymization is a basic technique for privacy preserving data analysis of personal information. This paper studies the applicability of a fuzzy clustering-based anonymization approach to crowd movement analysis, in which each individual movement is captured through face recognition in camera images. Before utilizing each face feature values, k-anonymization is performed by coding cluster elements, which are extracted by fuzzy k-member clustering. In an experimental study, the advantage and availability of fuzzy partitions are investigated through comparisons of reproduction qualities and anonymization costs with several fuzzy degree settings.
{"title":"A study on fuzzy clustering-based k-anonymization for privacy preserving crowd movement analysis with face recognition","authors":"Katsuhiro Honda, Masahiro Omori, S. Ubukata, A. Notsu","doi":"10.1109/SOCPAR.2015.7492779","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492779","url":null,"abstract":"k-anonymization is a basic technique for privacy preserving data analysis of personal information. This paper studies the applicability of a fuzzy clustering-based anonymization approach to crowd movement analysis, in which each individual movement is captured through face recognition in camera images. Before utilizing each face feature values, k-anonymization is performed by coding cluster elements, which are extracted by fuzzy k-member clustering. In an experimental study, the advantage and availability of fuzzy partitions are investigated through comparisons of reproduction qualities and anonymization costs with several fuzzy degree settings.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133423572","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492807
Jérémie Sublime, Nistor Grozavu, Younès Bennani, A. Cornuéjols
Collaborative clustering is a recent field of Machine Learning that shows similarities with both transfer learning and ensemble learning. It uses two-step approaches where different clustering algorithms first process data individually and then exchange their information and results with a goal of mutual improvement. In this article, we introduce a new collaborative learning approach based on collaborative clustering principles and applied to the Generative Topographic Mapping (GTM) algorithm. Our method consists in applying the GTM algorithm on different data sets where similar clusters can be found (same feature spaces and similar data distributions), and then to use a collaborative framework on the generated maps with the goal of transferring knowledge between them. The proposed approach has been validated on several data sets, and the experimental results have shown very promising performances.
{"title":"Vertical collaborative clustering using generative topographic maps","authors":"Jérémie Sublime, Nistor Grozavu, Younès Bennani, A. Cornuéjols","doi":"10.1109/SOCPAR.2015.7492807","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492807","url":null,"abstract":"Collaborative clustering is a recent field of Machine Learning that shows similarities with both transfer learning and ensemble learning. It uses two-step approaches where different clustering algorithms first process data individually and then exchange their information and results with a goal of mutual improvement. In this article, we introduce a new collaborative learning approach based on collaborative clustering principles and applied to the Generative Topographic Mapping (GTM) algorithm. Our method consists in applying the GTM algorithm on different data sets where similar clusters can be found (same feature spaces and similar data distributions), and then to use a collaborative framework on the generated maps with the goal of transferring knowledge between them. The proposed approach has been validated on several data sets, and the experimental results have shown very promising performances.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114594400","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 : 2015-11-01DOI: 10.1109/SOCPAR.2015.7492811
Whina Ayu Lestari, Y. Herdiyeni, L. Prasetyo, W. Hasbi, K. Arai, H. Okumura
Nitrogen (N) is one of nutrient required by plant in huge amounts. N availability of plant is needed to be estimated before applying fertilizers to determine proper N application rate. The purpose of this study is to estimate N of paddy (Oryza sativa, sp.) based on leaf reflectance using Artificial Neural Network (ANN). In this study, 45 leaf samples were randomly selected under various environmental condition. Leaf reflectance was measured by handheld spectroradiometer while actual leaf N content was determined by Kjeldahl method. Spectral reflectance data in visible band (400–700 nm wavelength region) and actual N content were used as input and target data in ANN model building. K-fold cross-validation (k=3) method was applied to select the best model and measure the overall performance of model. Results indicated that ANN model with 17 neurons of hidden layer in relatively could estimate N properly. It was shown by the lowest root mean square error (RMSE) of 0.23 and the highest prediction accuracy of 93%. This study promises to help farmers predicting N content of paddy for optimal N fertilizer application.
{"title":"Nitrogen estimation of paddy based on leaf reflectance using Artificial Neural Network","authors":"Whina Ayu Lestari, Y. Herdiyeni, L. Prasetyo, W. Hasbi, K. Arai, H. Okumura","doi":"10.1109/SOCPAR.2015.7492811","DOIUrl":"https://doi.org/10.1109/SOCPAR.2015.7492811","url":null,"abstract":"Nitrogen (N) is one of nutrient required by plant in huge amounts. N availability of plant is needed to be estimated before applying fertilizers to determine proper N application rate. The purpose of this study is to estimate N of paddy (Oryza sativa, sp.) based on leaf reflectance using Artificial Neural Network (ANN). In this study, 45 leaf samples were randomly selected under various environmental condition. Leaf reflectance was measured by handheld spectroradiometer while actual leaf N content was determined by Kjeldahl method. Spectral reflectance data in visible band (400–700 nm wavelength region) and actual N content were used as input and target data in ANN model building. K-fold cross-validation (k=3) method was applied to select the best model and measure the overall performance of model. Results indicated that ANN model with 17 neurons of hidden layer in relatively could estimate N properly. It was shown by the lowest root mean square error (RMSE) of 0.23 and the highest prediction accuracy of 93%. This study promises to help farmers predicting N content of paddy for optimal N fertilizer application.","PeriodicalId":409493,"journal":{"name":"2015 7th International Conference of Soft Computing and Pattern Recognition (SoCPaR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123907821","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：