In this paper, we propose a lightweight machine learning (ML) framework based on unsupervised spectral domain discretization for hyperspectral image (HSI) classification. Firstly, the high-dimensional HSI data is mapped into a discretized image by unsupervised learning method, and then the histogram statistics of discrete features are performed to align feature vectors. Finally, supervised ML method is used for classification, thus achieving a lightweight ML method of high-dimensional HSIs. Practical applications and comparative studies on three publicly available HSI datasets show that the framework approaches and surpasses deep learning models in classification accuracy while significantly compressing computational time consumption. The performance of six unsupervised clustering methods in HSI spectral domain discretization is compared in the study. Among them, K-means and GMM are superior in terms of classification accuracy. And SOM provides high classification accuracy while its discretization results are better interpretable due to better maintenance of topology during discretization.
{"title":"A lightweight hyperspectral image classification framework based on spectral domain discretization","authors":"Chengcheng Zhong, Kaiwen Zhang, Zitong Zhang, Chunlei Zhang","doi":"10.1117/12.2667232","DOIUrl":"https://doi.org/10.1117/12.2667232","url":null,"abstract":"In this paper, we propose a lightweight machine learning (ML) framework based on unsupervised spectral domain discretization for hyperspectral image (HSI) classification. Firstly, the high-dimensional HSI data is mapped into a discretized image by unsupervised learning method, and then the histogram statistics of discrete features are performed to align feature vectors. Finally, supervised ML method is used for classification, thus achieving a lightweight ML method of high-dimensional HSIs. Practical applications and comparative studies on three publicly available HSI datasets show that the framework approaches and surpasses deep learning models in classification accuracy while significantly compressing computational time consumption. The performance of six unsupervised clustering methods in HSI spectral domain discretization is compared in the study. Among them, K-means and GMM are superior in terms of classification accuracy. And SOM provides high classification accuracy while its discretization results are better interpretable due to better maintenance of topology during discretization.","PeriodicalId":128051,"journal":{"name":"Third International Seminar on Artificial Intelligence, Networking, and Information Technology","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132028449","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}
Knowledge distillation (KD) transfers knowledge of a teacher model to improve the performance of a student model which is usually equipped with a lower capacity. The standard KD framework, however, neglects that the DNNs exhibit a wide range of class-wise accuracy and the performance of some classes is even decreased after distillation. Observing the above phenomena, we propose a novel Class-Wise Knowledge Distillation method to find the hard classes with a simple yet effective technique and then make the students take more effort to learn these hard classes. In the experiments on image classification tasks using CIFAR-100 dataset, we demonstrate that the proposed method outperforms the other KD methods and achieves excellent performance enhancement on various networks.
{"title":"Class-wise knowledge distillation","authors":"Fei Li, Yifang Yang","doi":"10.1117/12.2667603","DOIUrl":"https://doi.org/10.1117/12.2667603","url":null,"abstract":"Knowledge distillation (KD) transfers knowledge of a teacher model to improve the performance of a student model which is usually equipped with a lower capacity. The standard KD framework, however, neglects that the DNNs exhibit a wide range of class-wise accuracy and the performance of some classes is even decreased after distillation. Observing the above phenomena, we propose a novel Class-Wise Knowledge Distillation method to find the hard classes with a simple yet effective technique and then make the students take more effort to learn these hard classes. In the experiments on image classification tasks using CIFAR-100 dataset, we demonstrate that the proposed method outperforms the other KD methods and achieves excellent performance enhancement on various networks.","PeriodicalId":128051,"journal":{"name":"Third International Seminar on Artificial Intelligence, Networking, and Information Technology","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134373313","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}
To improve the accuracy of grain yield prediction, a grain yield prediction model based on wavelet transform and long short-term memory (LSTM) is proposed. Firstly, the original data is decomposed by wavelet transform algorithm to obtain a series of sub-sequences of different scales, and then LSTM prediction models are built for the sub-sequences, finally wavelet reconstruction is used to obtain the predicted yield and analyze the model performance. The article uses China's 1999-2018 grain yield as experimental data. The experiment shows that the method proposed in this article has excellent performance in both short-term and medium-term predictions compared to the existing methods.
{"title":"Research on grain yield prediction model based on wavelet transform and LSTM","authors":"Chunhua Zhu, Pengle Li","doi":"10.1117/12.2667499","DOIUrl":"https://doi.org/10.1117/12.2667499","url":null,"abstract":"To improve the accuracy of grain yield prediction, a grain yield prediction model based on wavelet transform and long short-term memory (LSTM) is proposed. Firstly, the original data is decomposed by wavelet transform algorithm to obtain a series of sub-sequences of different scales, and then LSTM prediction models are built for the sub-sequences, finally wavelet reconstruction is used to obtain the predicted yield and analyze the model performance. The article uses China's 1999-2018 grain yield as experimental data. The experiment shows that the method proposed in this article has excellent performance in both short-term and medium-term predictions compared to the existing methods.","PeriodicalId":128051,"journal":{"name":"Third International Seminar on Artificial Intelligence, Networking, and Information Technology","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134520764","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}
Nan Wang, Z. Zhang, Xiaodong Duo, Yingying Ma, Gang Chen
As a cornerstone of cloud-native systems, Kubernetes uses YAML, a data description language, to configure resources. However, YAML does not meet the configuration requirements of complex scenarios and has three major problems. First, YAML has no type checking mechanism and therefore data type mismatches cannot be detected during compilation. Second, YAML does not have the ability to reuse data descriptions and there are duplicate code for largescale data. Third, YAML lacks a type merging algorithm that meets the needs of multi-team development in enterprises. This paper implements an experimental cloud resource provisioning language, Hermias, which is based on the functional programming language OCaml. Hermias is used to describe the resource configuration of cloud servers, which solves the above three problems in YAML. The novelty of this work is to propose a type merging algorithm that computes records with common labels by union types and subtyping.
{"title":"The design of an experimental cloud resource provisioning language","authors":"Nan Wang, Z. Zhang, Xiaodong Duo, Yingying Ma, Gang Chen","doi":"10.1117/12.2667227","DOIUrl":"https://doi.org/10.1117/12.2667227","url":null,"abstract":"As a cornerstone of cloud-native systems, Kubernetes uses YAML, a data description language, to configure resources. However, YAML does not meet the configuration requirements of complex scenarios and has three major problems. First, YAML has no type checking mechanism and therefore data type mismatches cannot be detected during compilation. Second, YAML does not have the ability to reuse data descriptions and there are duplicate code for largescale data. Third, YAML lacks a type merging algorithm that meets the needs of multi-team development in enterprises. This paper implements an experimental cloud resource provisioning language, Hermias, which is based on the functional programming language OCaml. Hermias is used to describe the resource configuration of cloud servers, which solves the above three problems in YAML. The novelty of this work is to propose a type merging algorithm that computes records with common labels by union types and subtyping.","PeriodicalId":128051,"journal":{"name":"Third International Seminar on Artificial Intelligence, Networking, and Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134258846","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}
As the most popular cryptocurrency now, Bitcoin's transaction data is easy to obtain, so de-anonymizing Bitcoin becomes possible. This paper constructs a data set of Bitcoin addresses including 5 categories, analyzes and extracts the transaction features of Bitcoin addresses in more detail based on related work, and proposes two new features of fourth-order transaction moments and sample distribution. New features improve the performance of Bitcoin address classification. The accuracy of the LightGBM model was 0.94 and the F1 score was 0.91. This method can identify unknown types of Bitcoin addresses, which improves the ability of relevant agencies to investigate Bitcoin illegal activities.
{"title":"Research on Bitcoin address classification based on transaction history features","authors":"Lu Qin, Li Yi, Xiancheng Lin, Ziqiang Luo","doi":"10.1117/12.2667252","DOIUrl":"https://doi.org/10.1117/12.2667252","url":null,"abstract":"As the most popular cryptocurrency now, Bitcoin's transaction data is easy to obtain, so de-anonymizing Bitcoin becomes possible. This paper constructs a data set of Bitcoin addresses including 5 categories, analyzes and extracts the transaction features of Bitcoin addresses in more detail based on related work, and proposes two new features of fourth-order transaction moments and sample distribution. New features improve the performance of Bitcoin address classification. The accuracy of the LightGBM model was 0.94 and the F1 score was 0.91. This method can identify unknown types of Bitcoin addresses, which improves the ability of relevant agencies to investigate Bitcoin illegal activities.","PeriodicalId":128051,"journal":{"name":"Third International Seminar on Artificial Intelligence, Networking, and Information Technology","volume":"97 2-3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133055644","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}
Online public opinion warning for emergencies can help people understand the real situation, avoid panic, timely remind people not to go to high-risk areas, and help the government to carry out epidemic work.In this paper, key technologies of network public opinion warning were studied based on improved Stacking algorithm. COVID-19, herpangina, hand, foot and mouth, varicella and several emergency outbreaks were selected as public opinion research objects, and rough set was used to screen indicators and determine the final warning indicators.Finally, the warning model was established by the 50% fold Stacking algorithm, and the training accuracy and prediction accuracy experiments were carried out.According to the empirical study, the prediction accuracy of 50% Stacking is good, and the early warning model is practical and robust.This study has strong practicability in the early warning of the online public opinion of the sudden epidemic.
{"title":"Research on key technologies of network public opinion warning based on improved stacking algorithm","authors":"Jing Luo","doi":"10.1117/12.2667477","DOIUrl":"https://doi.org/10.1117/12.2667477","url":null,"abstract":"Online public opinion warning for emergencies can help people understand the real situation, avoid panic, timely remind people not to go to high-risk areas, and help the government to carry out epidemic work.In this paper, key technologies of network public opinion warning were studied based on improved Stacking algorithm. COVID-19, herpangina, hand, foot and mouth, varicella and several emergency outbreaks were selected as public opinion research objects, and rough set was used to screen indicators and determine the final warning indicators.Finally, the warning model was established by the 50% fold Stacking algorithm, and the training accuracy and prediction accuracy experiments were carried out.According to the empirical study, the prediction accuracy of 50% Stacking is good, and the early warning model is practical and robust.This study has strong practicability in the early warning of the online public opinion of the sudden epidemic.","PeriodicalId":128051,"journal":{"name":"Third International Seminar on Artificial Intelligence, Networking, and Information Technology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124654305","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}
As the most important module in recommendation systems, click-through rate prediction has attracted the attention of industry and academia. Due to the powerful learning ability of deep learning, it is widely used in click-through rate prediction. Behavior sequences based on user is an important direction of click-through rate prediction. Although some results have been made in related directions, existing methods still have some problems, such as the inability to learn feature weights better, the presence of noise in user behavior sequences, not fully mining the hidden information in features, etc. In this paper, we propose a method for related problems, named DISFMN, which can dynamically learn the importance of features as well as filter out the noise in user behavior sequences. The method also combines high-order and low-order feature interactions to uncover more valuable information in features. Comparative experiments are conducted on different datasets and the experimental results showed the effectiveness of the proposed method.
{"title":"Click-through rate prediction based on behavioral sequences","authors":"Shoujian Yu, Xiaoxiao Huang, Xiaoling Xia","doi":"10.1117/12.2667249","DOIUrl":"https://doi.org/10.1117/12.2667249","url":null,"abstract":"As the most important module in recommendation systems, click-through rate prediction has attracted the attention of industry and academia. Due to the powerful learning ability of deep learning, it is widely used in click-through rate prediction. Behavior sequences based on user is an important direction of click-through rate prediction. Although some results have been made in related directions, existing methods still have some problems, such as the inability to learn feature weights better, the presence of noise in user behavior sequences, not fully mining the hidden information in features, etc. In this paper, we propose a method for related problems, named DISFMN, which can dynamically learn the importance of features as well as filter out the noise in user behavior sequences. The method also combines high-order and low-order feature interactions to uncover more valuable information in features. Comparative experiments are conducted on different datasets and the experimental results showed the effectiveness of the proposed method.","PeriodicalId":128051,"journal":{"name":"Third International Seminar on Artificial Intelligence, Networking, and Information Technology","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125340105","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}
As the most common captcha, text captcha can prevent others from maliciously using computer programs to log in or attack, and is an important safeguard in Internet authentication. In recent years, with the development of the Internet, the field of artificial intelligence has also developed at a high speed, and convolutional neural networks are widely used in various fields. In this context, for the common problem of character-based captcha recognition, this paper investigates captcha recognition based on a deep learning neural network framework used by the TensorFlow framework with modifications based on the VGG16 convolutional neural network. The 4-digit captcha randomly composed of 64 characters is then converted into an image, and after operations such as image processing and encoding of the captcha, a large number of training sets are generated and the recognition of the captcha is done by the convolutional neural network. Finally, the design GUI interface is deployed to mobile devices with a final accuracy rate of 85% on the test set.
{"title":"Deep learning captcha recognition for mobile based on TensorFlow","authors":"Xiangfeng Lin, Linfu Li, Yu Ren","doi":"10.1117/12.2667721","DOIUrl":"https://doi.org/10.1117/12.2667721","url":null,"abstract":"As the most common captcha, text captcha can prevent others from maliciously using computer programs to log in or attack, and is an important safeguard in Internet authentication. In recent years, with the development of the Internet, the field of artificial intelligence has also developed at a high speed, and convolutional neural networks are widely used in various fields. In this context, for the common problem of character-based captcha recognition, this paper investigates captcha recognition based on a deep learning neural network framework used by the TensorFlow framework with modifications based on the VGG16 convolutional neural network. The 4-digit captcha randomly composed of 64 characters is then converted into an image, and after operations such as image processing and encoding of the captcha, a large number of training sets are generated and the recognition of the captcha is done by the convolutional neural network. Finally, the design GUI interface is deployed to mobile devices with a final accuracy rate of 85% on the test set.","PeriodicalId":128051,"journal":{"name":"Third International Seminar on Artificial Intelligence, Networking, and Information Technology","volume":"90 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114030151","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：