Convolutional neural networks (CNNs) have been used over the past years to solve many different artificial intelligence (AI) problems, providing significant advances in some domains and leading to state-of-the-art results. Nonetheless, the design of CNNs architecture remains to be a meticulous and cumbersome process that requires the participation of specialists in the field. In this work, we have explored the neuro-evolution application to the automatic design of CNN topologies, developing a novel solution based on Artificial Bee Colony (ABC). The MNIST dataset is used to evaluate the proposed method, which is proved being highly competitive with the state-of-the-art.
{"title":"Evolutionary Convolutional Neural Networks Using ABC","authors":"Wenbo Zhu, Weichang Yeh, Jianwen Chen, Dafeng Chen, Aiyuan Li, Yangyang Lin","doi":"10.1145/3318299.3318301","DOIUrl":"https://doi.org/10.1145/3318299.3318301","url":null,"abstract":"Convolutional neural networks (CNNs) have been used over the past years to solve many different artificial intelligence (AI) problems, providing significant advances in some domains and leading to state-of-the-art results. Nonetheless, the design of CNNs architecture remains to be a meticulous and cumbersome process that requires the participation of specialists in the field. In this work, we have explored the neuro-evolution application to the automatic design of CNN topologies, developing a novel solution based on Artificial Bee Colony (ABC). The MNIST dataset is used to evaluate the proposed method, which is proved being highly competitive with the state-of-the-art.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129516085","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}
Li Wei, Xiang Li, Tingrong Cao, Quan Zhang, LiangQi Zhou, Wenli Wang
Image verification code is the main mode of security verification in current network applications. The identification efficiency of verification code is a difficult problem that affects network data crawling, which has realistic research significance and value. This paper proposed an SVM (Support Vector Machine)-based recognition method. On the basis of fully analyzing the existing SVM recognition mechanism process, the image is first binarized and filtered for character image preprocessing, then feature extraction, and then classification model is established for recognition. It is proved that this method can achieve fast and accurate results by training and comparing characters in many categories such as adhesion and rotation.
{"title":"Research on Optimization of CAPTCHA Recognition Algorithm Based on SVM","authors":"Li Wei, Xiang Li, Tingrong Cao, Quan Zhang, LiangQi Zhou, Wenli Wang","doi":"10.1145/3318299.3318355","DOIUrl":"https://doi.org/10.1145/3318299.3318355","url":null,"abstract":"Image verification code is the main mode of security verification in current network applications. The identification efficiency of verification code is a difficult problem that affects network data crawling, which has realistic research significance and value. This paper proposed an SVM (Support Vector Machine)-based recognition method. On the basis of fully analyzing the existing SVM recognition mechanism process, the image is first binarized and filtered for character image preprocessing, then feature extraction, and then classification model is established for recognition. It is proved that this method can achieve fast and accurate results by training and comparing characters in many categories such as adhesion and rotation.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124571708","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}
Ali Shariq Imran, Vetle Haflan, Abdolreza Sabzi Shahrebabaki, Negar Olfati, T. Svendsen
This paper presents a study evaluating different acoustic feature map representations in two-dimensional convolutional neural networks (2D-CNN) on the speech dataset for various speech-related activities. Specifically, the task involves identifying useful 2D-CNN input feature maps for enhancing speaker identification with an ultimate goal to improve speaker authentication and enabling voice as a biometric feature. Voice in contrast to fingerprints and image-based biometrics is a natural choice for hands-free communication systems where touch interfaces are inconvenient or dangerous to use. Effective input feature map representation may help CNN exploit intrinsic voice features that not only can address the instability issues of voice as an identifier for textindependent speaker authentication while preserving privacy but can also assist in developing efficacious voice-enabled interfaces. Three different acoustic features with three possible feature map representations are evaluated in this study. Results obtained on three speech corpora shows that an interpolated baseline spectrogram performs best compared to Mel frequency spectral coefficients (MFSC) and Mel frequency cepstral coefficient (MFCC) when tested on a 5-fold cross-validation method using 2D-CNN. On both textdependent and text-independent datasets, raw spectrogram accuracy is 4% better than the traditional acoustic features.
{"title":"Evaluating Acoustic Feature Maps in 2D-CNN for Speaker Identification","authors":"Ali Shariq Imran, Vetle Haflan, Abdolreza Sabzi Shahrebabaki, Negar Olfati, T. Svendsen","doi":"10.1145/3318299.3318386","DOIUrl":"https://doi.org/10.1145/3318299.3318386","url":null,"abstract":"This paper presents a study evaluating different acoustic feature map representations in two-dimensional convolutional neural networks (2D-CNN) on the speech dataset for various speech-related activities. Specifically, the task involves identifying useful 2D-CNN input feature maps for enhancing speaker identification with an ultimate goal to improve speaker authentication and enabling voice as a biometric feature. Voice in contrast to fingerprints and image-based biometrics is a natural choice for hands-free communication systems where touch interfaces are inconvenient or dangerous to use. Effective input feature map representation may help CNN exploit intrinsic voice features that not only can address the instability issues of voice as an identifier for textindependent speaker authentication while preserving privacy but can also assist in developing efficacious voice-enabled interfaces. Three different acoustic features with three possible feature map representations are evaluated in this study. Results obtained on three speech corpora shows that an interpolated baseline spectrogram performs best compared to Mel frequency spectral coefficients (MFSC) and Mel frequency cepstral coefficient (MFCC) when tested on a 5-fold cross-validation method using 2D-CNN. On both textdependent and text-independent datasets, raw spectrogram accuracy is 4% better than the traditional acoustic features.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115892784","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}
Character-level sequence label tagging is the most efficient way to solve unknown words problem for Chinese word segment. But the most widely used model, Conditional Random Fields (CRF), needs a large amount of manual design features. So it is appropriate to combine CRF and neural networks such as recurrent neural network (RNN), which is adopted in many natural language processing (NLP) tasks. However, RNN is rather slow because of the timing dependence between computations and not good at capturing local information of the sentence. In order to solve this problem, we introduce a self-attention mechanism, which completes the calculation between the different positions of the sentence with the same distance, into CWS. And we propose a deep neural network, which combines convolution neural networks and self-attention mechanism. Then, we evaluate the model on the PKU dataset and the MSR dataset. The results show that our model perform much better.
{"title":"A Deep Attention Network for Chinese Word Segment","authors":"Lanxin Li, Ping Gong, L. Ji","doi":"10.1145/3318299.3318351","DOIUrl":"https://doi.org/10.1145/3318299.3318351","url":null,"abstract":"Character-level sequence label tagging is the most efficient way to solve unknown words problem for Chinese word segment. But the most widely used model, Conditional Random Fields (CRF), needs a large amount of manual design features. So it is appropriate to combine CRF and neural networks such as recurrent neural network (RNN), which is adopted in many natural language processing (NLP) tasks. However, RNN is rather slow because of the timing dependence between computations and not good at capturing local information of the sentence. In order to solve this problem, we introduce a self-attention mechanism, which completes the calculation between the different positions of the sentence with the same distance, into CWS. And we propose a deep neural network, which combines convolution neural networks and self-attention mechanism. Then, we evaluate the model on the PKU dataset and the MSR dataset. The results show that our model perform much better.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127215503","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}
A new algorithm for automatic tomato detection in regular color images is proposed, which can reduce the influence of illumination, color similarity as well as suppress the effect of occlusion. The method uses a Support Vector Machine (SVM) with Histograms of Oriented Gradients (HOG) to detect the tomatoes, followed by a color analysis method for false positive removal. And the Non-Maximum Suppression Method (NMS) is employed to merge the detection results. Finally, a total of 144 images were used for the experiment. The results showed that the recall and precision of the classifier were 96.67% and 98.64% on the test set. Compared with other methods developed in recent years, the proposed algorithm shows substantial improvement for tomato detection.
{"title":"A Robust Mature Tomato Detection in Greenhouse Scenes Using Machine Learning and Color Analysis","authors":"Guoxu Liu, Shuyi Mao, Hui Jin, J. H. Kim","doi":"10.1145/3318299.3318338","DOIUrl":"https://doi.org/10.1145/3318299.3318338","url":null,"abstract":"A new algorithm for automatic tomato detection in regular color images is proposed, which can reduce the influence of illumination, color similarity as well as suppress the effect of occlusion. The method uses a Support Vector Machine (SVM) with Histograms of Oriented Gradients (HOG) to detect the tomatoes, followed by a color analysis method for false positive removal. And the Non-Maximum Suppression Method (NMS) is employed to merge the detection results. Finally, a total of 144 images were used for the experiment. The results showed that the recall and precision of the classifier were 96.67% and 98.64% on the test set. Compared with other methods developed in recent years, the proposed algorithm shows substantial improvement for tomato detection.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116845929","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}
In person re-identification (re-ID), most state-of-the-art models extract features by convolutional neural networks to do similarity comparison. Feature representation becomes the key task for person re-ID. However, the learned features are not good enough based on a single-path and single-loss network because the learned objective only achieves one of the multiple minima. To improve feature representation, we propose a multi-path and multi-loss network (MPMLN) and concatenate multi-path features to represent pedestrian. Subsequently, we design MPMLN based on ResNet-50 and construct an end-to-end architecture. The backbone of our proposed network shares the local parameters for multiple paths and multiple losses. It has fewer parameters than multiple independent networks. Experimental results show that our MPMLN achieves the state-of-the-art performance on the public Market1501, DukeMTMC-reID and CUHK03 person re-ID benchmarks.
{"title":"Multi-Path and Multi-Loss Network for Person Re-Identification","authors":"Jiabao Wang, Shanshan Jiao, Yang Li, Zhuang Miao","doi":"10.1145/3318299.3318331","DOIUrl":"https://doi.org/10.1145/3318299.3318331","url":null,"abstract":"In person re-identification (re-ID), most state-of-the-art models extract features by convolutional neural networks to do similarity comparison. Feature representation becomes the key task for person re-ID. However, the learned features are not good enough based on a single-path and single-loss network because the learned objective only achieves one of the multiple minima. To improve feature representation, we propose a multi-path and multi-loss network (MPMLN) and concatenate multi-path features to represent pedestrian. Subsequently, we design MPMLN based on ResNet-50 and construct an end-to-end architecture. The backbone of our proposed network shares the local parameters for multiple paths and multiple losses. It has fewer parameters than multiple independent networks. Experimental results show that our MPMLN achieves the state-of-the-art performance on the public Market1501, DukeMTMC-reID and CUHK03 person re-ID benchmarks.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114925832","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}
Top-k multiclass classification is one of the central problems in machine learning and computer vision. It aims at classifying instances into one of three or more classes and allows k guesses to evaluate classifiers based on the top-k error. However, existing solutions either simply ignore the specific structure of the top-k error by directly solving the top-1 error minimization problem or consider convex relaxation approximation for the original top-k error model. In this paper, we formulate the top-k multiclass classification problem as an ℓ0 norm minimization problem. Although the model is NP-hard, we reformulate it as an equivalent mathematical program with equilibrium constraints and consider an exact penalty method to solve it. The algorithm solves a sequence of convex optimization problems to find a desirable solution for the original nonconvex problem. Finally, we demonstrate the efficacy of our method on some real-world data sets. As a result, our method achieves state-of-the-art performance in term of accuracy
{"title":"An Exact Penalty Method for Top-k Multiclass Classification Based on L0 Norm Minimization","authors":"Haoxian Tan","doi":"10.1145/3318299.3318335","DOIUrl":"https://doi.org/10.1145/3318299.3318335","url":null,"abstract":"Top-k multiclass classification is one of the central problems in machine learning and computer vision. It aims at classifying instances into one of three or more classes and allows k guesses to evaluate classifiers based on the top-k error. However, existing solutions either simply ignore the specific structure of the top-k error by directly solving the top-1 error minimization problem or consider convex relaxation approximation for the original top-k error model. In this paper, we formulate the top-k multiclass classification problem as an ℓ0 norm minimization problem. Although the model is NP-hard, we reformulate it as an equivalent mathematical program with equilibrium constraints and consider an exact penalty method to solve it. The algorithm solves a sequence of convex optimization problems to find a desirable solution for the original nonconvex problem. Finally, we demonstrate the efficacy of our method on some real-world data sets. As a result, our method achieves state-of-the-art performance in term of accuracy","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126091011","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}
Climate change or global warming is a global threat to both human communities and natural systems. In recent years, there is an increasingly public debate on the existence of climate change or global warming, but data describing such discussions are difficult to access. Social media provide a new data source to survey public perceptions and attitudes toward such topics. However, enabling computers to automatically determine users' attitudes towards climate change based on social media contents is still challenging. Taking Twitter data as an example, this study analyzed public discussions about climate change and global warming in year 2016. The objectives are: (1) to develop an optimized Deep Neural Network (DNN) classifier to identify users who are climate change deniers based on tweet contents; (2) to examine the temporal patterns of climate change discussions on Twitter and its driving factors. Results demonstrate that the developed DNN model successfully identified climate change deniers based on tweet contents with an overall accuracy of 88%. There are more climate change discussions during September to December 2016, whereas the percentages of climate change deniers were lower in the same period. Public interests and attitudes on climate change were driven by extreme weather events and environmental policy changes. The developed methodology will shed lights on the utility of deep learning in natural language processing, while the results provide improved understanding of factors affecting public attitudes on climate change.
{"title":"Detecting Climate Change Deniers on Twitter Using a Deep Neural Network","authors":"Xingyu Chen, L. Zou, Bo Zhao","doi":"10.1145/3318299.3318382","DOIUrl":"https://doi.org/10.1145/3318299.3318382","url":null,"abstract":"Climate change or global warming is a global threat to both human communities and natural systems. In recent years, there is an increasingly public debate on the existence of climate change or global warming, but data describing such discussions are difficult to access. Social media provide a new data source to survey public perceptions and attitudes toward such topics. However, enabling computers to automatically determine users' attitudes towards climate change based on social media contents is still challenging. Taking Twitter data as an example, this study analyzed public discussions about climate change and global warming in year 2016. The objectives are: (1) to develop an optimized Deep Neural Network (DNN) classifier to identify users who are climate change deniers based on tweet contents; (2) to examine the temporal patterns of climate change discussions on Twitter and its driving factors. Results demonstrate that the developed DNN model successfully identified climate change deniers based on tweet contents with an overall accuracy of 88%. There are more climate change discussions during September to December 2016, whereas the percentages of climate change deniers were lower in the same period. Public interests and attitudes on climate change were driven by extreme weather events and environmental policy changes. The developed methodology will shed lights on the utility of deep learning in natural language processing, while the results provide improved understanding of factors affecting public attitudes on climate change.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125770304","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}
The application research of machine learning methods has attracted attention in the meteorological field. In this paper, we establish a spatiotemporal temperature deviation prediction model (PredTemp) based on convolution and long short-term memory network (ConvLSTM). The model is trained with numerical weatherprediction (NWP), and the prediction results are used to correct the temperature prediction in NWP. Exploring the influence of the weather elements added to the model on the prediction results is also the focus of this paper. Two datasets are constructed for this purpose: the temperature forecast deviationdataset (dataset1) is constructed by using the temperature forecastsand the analysis field in NWP, a precipitation forecast dataset (dataset2) was constructed using the precipitation forecasts in NWP. The experimental results show that the model is effective. Using dataset1 as dataset for training, the accuracy rate of temperaturecorrected by PredTempwas increased by 3%compared to NWP; using dataset1 and dataset2 as dataset for training, the accuracy rate of temperature corrected by PredTemp was increased by 4%. The addition of precipitation elements has played a positive role in improving the accuracy of the model prediction.
{"title":"Application of ConvLSTM Network in Numerical Temperature Prediction Interpretation","authors":"Hong Lin, Yunzi Hua, Leiming Ma, Lei Chen","doi":"10.1145/3318299.3318381","DOIUrl":"https://doi.org/10.1145/3318299.3318381","url":null,"abstract":"The application research of machine learning methods has attracted attention in the meteorological field. In this paper, we establish a spatiotemporal temperature deviation prediction model (PredTemp) based on convolution and long short-term memory network (ConvLSTM). The model is trained with numerical weatherprediction (NWP), and the prediction results are used to correct the temperature prediction in NWP. Exploring the influence of the weather elements added to the model on the prediction results is also the focus of this paper. Two datasets are constructed for this purpose: the temperature forecast deviationdataset (dataset1) is constructed by using the temperature forecastsand the analysis field in NWP, a precipitation forecast dataset (dataset2) was constructed using the precipitation forecasts in NWP. The experimental results show that the model is effective. Using dataset1 as dataset for training, the accuracy rate of temperaturecorrected by PredTempwas increased by 3%compared to NWP; using dataset1 and dataset2 as dataset for training, the accuracy rate of temperature corrected by PredTemp was increased by 4%. The addition of precipitation elements has played a positive role in improving the accuracy of the model prediction.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134353159","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}
The kNN classification performance entirely depends on the selected neighbors. In the past, many nearest neighbor (NN)-based methods mainly focus on learning distance measure metrics so that a neighborhood of an approximately constant posteriori probability can be produced, whereas limited works are performed to study the influences of the distribution characteristics of each neighbor. In this paper, we point out why the best distance measurement (BDM) is sensitive to malicious samples, and then a robust best distance measurement (RBDM) is suggested to solve this problem. Moreover, we also investigated the influences of the distribution characteristics of each neighbor for the classification performance, so that a two-stage method, called weighted robust best distance measurement kNN method (WRBDMkNN), is proposed aiming to minimize the misclassification rate of the nearest neighbor rule. Extensive experiments on diversity datasets indicate that the proposed method can achieve more encouraging results compared with some state-of-the-art NN-based methods.
{"title":"Minimizing the Misclassification Rate of the Nearest Neighbor Rule Using a Two-stage Method","authors":"Yunlong Gao, Si-Zhe Luo, Jinyan Pan, Baihua Chen, Peng Gao","doi":"10.1145/3318299.3318339","DOIUrl":"https://doi.org/10.1145/3318299.3318339","url":null,"abstract":"The kNN classification performance entirely depends on the selected neighbors. In the past, many nearest neighbor (NN)-based methods mainly focus on learning distance measure metrics so that a neighborhood of an approximately constant posteriori probability can be produced, whereas limited works are performed to study the influences of the distribution characteristics of each neighbor. In this paper, we point out why the best distance measurement (BDM) is sensitive to malicious samples, and then a robust best distance measurement (RBDM) is suggested to solve this problem. Moreover, we also investigated the influences of the distribution characteristics of each neighbor for the classification performance, so that a two-stage method, called weighted robust best distance measurement kNN method (WRBDMkNN), is proposed aiming to minimize the misclassification rate of the nearest neighbor rule. Extensive experiments on diversity datasets indicate that the proposed method can achieve more encouraging results compared with some state-of-the-art NN-based methods.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133476594","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：