Pub Date : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016484
Xiao Fei, Liao Jianping, Tian Jie, Wang Guangshuo
Wavelet analysis is a variant of Fourier analysis, which can be used for time-frequency analysis of signal processing, and has achieved remarkable results in the field of image processing. The spike neural network is called the third-generation neural network, which is different from the previous generation, the neural network of the spike neural network is more inspired by neuroscience, and this neural network is constructed in a way closer to the human brain mechanism, which can be applied to many machine learning tasks. Image classification is one of the basic tasks in the field of computer vision. We explore the application of wavelet analysis to the training process of the spiking neural network, before the original data is input into the neural network, we process it with wavelet transform, so that the characteristics of the input data are easier to be learned by the neural network.
{"title":"Research on Image Classification Combining Wavelet Analysis and Spiking Neural Network","authors":"Xiao Fei, Liao Jianping, Tian Jie, Wang Guangshuo","doi":"10.1109/ICCWAMTIP56608.2022.10016484","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016484","url":null,"abstract":"Wavelet analysis is a variant of Fourier analysis, which can be used for time-frequency analysis of signal processing, and has achieved remarkable results in the field of image processing. The spike neural network is called the third-generation neural network, which is different from the previous generation, the neural network of the spike neural network is more inspired by neuroscience, and this neural network is constructed in a way closer to the human brain mechanism, which can be applied to many machine learning tasks. Image classification is one of the basic tasks in the field of computer vision. We explore the application of wavelet analysis to the training process of the spiking neural network, before the original data is input into the neural network, we process it with wavelet transform, so that the characteristics of the input data are easier to be learned by the neural network.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130027765","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 : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016574
Xia Peng, Z. Di, Gao Ming
With the continuous increase of highway ETC access to the national toll stations entrance, some private cars use the ETC rule loopholes to rub ETC situation more and more. Therefore, to completely solve this problem and speed up toll collection, we have developed this system, which can record the vehicle’s current latitude and longitude in real time through BDS positioning, and compare it with the latitude and longitude record in the system, when the vehicle passes through the longitude and latitude of the junction will be automatically judged, and in accordance with the requirements of the high-speed automatic toll payment, a little bit, to completely avoid traffic jams and rub ETC situation.
{"title":"Freeway Free-Flow Payment System Based On Beidou","authors":"Xia Peng, Z. Di, Gao Ming","doi":"10.1109/ICCWAMTIP56608.2022.10016574","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016574","url":null,"abstract":"With the continuous increase of highway ETC access to the national toll stations entrance, some private cars use the ETC rule loopholes to rub ETC situation more and more. Therefore, to completely solve this problem and speed up toll collection, we have developed this system, which can record the vehicle’s current latitude and longitude in real time through BDS positioning, and compare it with the latitude and longitude record in the system, when the vehicle passes through the longitude and latitude of the junction will be automatically judged, and in accordance with the requirements of the high-speed automatic toll payment, a little bit, to completely avoid traffic jams and rub ETC situation.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133751794","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 : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016593
Zhixin Zhai
Few-shot conditional image generation, which refers to synthesizing images from new conditions based on few training samples, is challenging. Previous works either stick to learning from scratch with enlarged training samples by data augmentation or transferring fixed knowledge grasped from source data to describe target data distribution. They often result in unsatisfied performance due to the overfitting or underfitting brought by rare samples. To address the above issue, we propose a simple yet effective approach, namely EVolving giAnt (EVA), to make the pretrained giant generative model evolve to properly fit target data distribution with few samples (e.g., 1-shot, 10-shot and 50-shot). Specifically, we maintain most prior knowledge stored in model parameters to prevent overfitting, add a new module to accept target conditions, and adapt few parameters for out-bounded features extracted from the target data to avoid underfitting. Extensive experiments confirm the high diversity and quality of our synthesized samples as well as the practicality of our approach in the extreme 1-shot generation.
{"title":"EVA: Evolving Giant Pretrained Model for Few-Shot Conditional Image Generation","authors":"Zhixin Zhai","doi":"10.1109/ICCWAMTIP56608.2022.10016593","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016593","url":null,"abstract":"Few-shot conditional image generation, which refers to synthesizing images from new conditions based on few training samples, is challenging. Previous works either stick to learning from scratch with enlarged training samples by data augmentation or transferring fixed knowledge grasped from source data to describe target data distribution. They often result in unsatisfied performance due to the overfitting or underfitting brought by rare samples. To address the above issue, we propose a simple yet effective approach, namely EVolving giAnt (EVA), to make the pretrained giant generative model evolve to properly fit target data distribution with few samples (e.g., 1-shot, 10-shot and 50-shot). Specifically, we maintain most prior knowledge stored in model parameters to prevent overfitting, add a new module to accept target conditions, and adapt few parameters for out-bounded features extracted from the target data to avoid underfitting. Extensive experiments confirm the high diversity and quality of our synthesized samples as well as the practicality of our approach in the extreme 1-shot generation.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129676076","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 a mature and open mobile operating system, Android runs on many IoT devices, which has led to Android-based IoT devices have become a hotbed of malware. Existing static detection methods for malware using artificial intelligence algorithms focus only on the java code layer when extracting API features, however there is a lot of malicious behavior involving native layer code. Thus, to make up for the neglect of the native code layer, we propose a heterogeneous information network-based Android malware detection method with cross-layer features. We first translate the semantic information of apps and API calls into the form of meta-paths, and construct the adjacency of apps based on API calls, then combine information from different meta-paths using multi-core learning. We implemented our method on the dataset from VirusShare and AndroZoo, and the experimental results show that the accuracy of our method is 93.4%, which is at least 2% higher than other related methods using heterogeneous information networks for malware detection.
{"title":"Android Malware Detection Based on Heterogeneous Information Network with Cross-Layer Features","authors":"Ren Xixuan, Zhao Lirui, Wang Kai, Xue Zhixing, Hou Anran, Shao Qiao","doi":"10.1109/ICCWAMTIP56608.2022.10016587","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016587","url":null,"abstract":"As a mature and open mobile operating system, Android runs on many IoT devices, which has led to Android-based IoT devices have become a hotbed of malware. Existing static detection methods for malware using artificial intelligence algorithms focus only on the java code layer when extracting API features, however there is a lot of malicious behavior involving native layer code. Thus, to make up for the neglect of the native code layer, we propose a heterogeneous information network-based Android malware detection method with cross-layer features. We first translate the semantic information of apps and API calls into the form of meta-paths, and construct the adjacency of apps based on API calls, then combine information from different meta-paths using multi-core learning. We implemented our method on the dataset from VirusShare and AndroZoo, and the experimental results show that the accuracy of our method is 93.4%, which is at least 2% higher than other related methods using heterogeneous information networks for malware detection.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126325274","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 : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016592
Peng Chong
The growing popularity of edge techniques, such as IoT, 5G, blockchain, make it increasingly challenging to protect sensitive data due to the amount of data increases and the growing volume of regulatory policies. To properly protect sensitive data, it is very important to identify sensitive data and implement data anonymization to ensure the quality and proper use of data anonymization techniques. This work focuses on proactively sensitive data identification, classification and anonymization using machine learning techniques. We first investigated the sensitive data extraction from both structured data and unstructured data, in which Bert models and Regular expressions were used to achieve the identification of sensitive data in real-time. Meanwhile, we propose a comprehensive sensitive detection framework combining the Bert model with regular expressions that can achieve high precision and good generalization capability with not so large corpus. The experimental results demonstrate the effectiveness of proposed solution.
{"title":"Deep Learning Based Sensitive Data Detection","authors":"Peng Chong","doi":"10.1109/ICCWAMTIP56608.2022.10016592","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016592","url":null,"abstract":"The growing popularity of edge techniques, such as IoT, 5G, blockchain, make it increasingly challenging to protect sensitive data due to the amount of data increases and the growing volume of regulatory policies. To properly protect sensitive data, it is very important to identify sensitive data and implement data anonymization to ensure the quality and proper use of data anonymization techniques. This work focuses on proactively sensitive data identification, classification and anonymization using machine learning techniques. We first investigated the sensitive data extraction from both structured data and unstructured data, in which Bert models and Regular expressions were used to achieve the identification of sensitive data in real-time. Meanwhile, we propose a comprehensive sensitive detection framework combining the Bert model with regular expressions that can achieve high precision and good generalization capability with not so large corpus. The experimental results demonstrate the effectiveness of proposed solution.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127596349","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 : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016494
Deng Yang, Yang Yujun, Qiu Laixiang, Zhouyi Wang
Cancer is a serious threat to people's health, and its heterogeneous nature and its ability to divide and proliferate make it difficult to cure. For women around the world, breast cancer has been affecting their health and even the risk of life. Therefore, earlier and more accurate diagnosis can save patient's lives. As research into machine learning has become more advanced, different algorithms have been applied to various datasets, including medical data. In this paper, mainly introduce three algorithms that are commonly used and superior in cancer diagnosis, K-Nearest Neighbor algorithm, Naive Bayesian algorithm based on Bayes' theorem and Support Vector Machine. An experimental case is used to illustrate the F1 score, accuracy and recall rate of these two algorithms on the same data set.
{"title":"Machine Learning Base Methods for Breast Cancer Diagnose","authors":"Deng Yang, Yang Yujun, Qiu Laixiang, Zhouyi Wang","doi":"10.1109/ICCWAMTIP56608.2022.10016494","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016494","url":null,"abstract":"Cancer is a serious threat to people's health, and its heterogeneous nature and its ability to divide and proliferate make it difficult to cure. For women around the world, breast cancer has been affecting their health and even the risk of life. Therefore, earlier and more accurate diagnosis can save patient's lives. As research into machine learning has become more advanced, different algorithms have been applied to various datasets, including medical data. In this paper, mainly introduce three algorithms that are commonly used and superior in cancer diagnosis, K-Nearest Neighbor algorithm, Naive Bayesian algorithm based on Bayes' theorem and Support Vector Machine. An experimental case is used to illustrate the F1 score, accuracy and recall rate of these two algorithms on the same data set.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121532209","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 : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016588
Esther Stacy E. B. Aggrey, Qin Zhen, Seth Larweh Kodjiku, K. Asamoah, Obed Barnes, Linda Delali Fiasam, Evans Aidoo, Henrietta Aggrey
Melanoma is the most dangerous and aggressive kind of skin cancer, which is also the most frequent form of cancer worldwide. Given the complexities involved, automatic melanoma detection using skin imaging has lately received interest within the machine learning field. Convolutional neural network has widely been employed in recent years to address this problem. However, existing CNN models for skin cancer classification have the drawback of ignoring crucial spatial relationship between features. They are only able to perform accurate classifications provided a predetermined set of features are present in the test data, regardless of how those features are distributed, which leads to false negatives. Furthermore, the CNN pooling layers responsible for down-sampling in these networks also result in loss of data and poor generalization performance. This study proposes a combination of convolutional block and Capsule Neural Network with a multi-task learning framework to address the aforementioned challenges and boost skin cancer classification. The model’s efficiency was measured by a number of metrics, including accuracy, specificity, recall, and F1 score. The accuracy of the proposed model achieved 98.93%, 98.52%, 95.7%, and 98.87%, respectively, indicating great efficiency when compared to other existing networks. As a result, the proposed method offers less sophisticated and robust architecture for automating the process of melanoma diagnoses and accelerating detection procedures in order to save a life.
{"title":"Detection of Melanoma Skin Cancer Using Capsule Network and Multi-Task Learning Framework","authors":"Esther Stacy E. B. Aggrey, Qin Zhen, Seth Larweh Kodjiku, K. Asamoah, Obed Barnes, Linda Delali Fiasam, Evans Aidoo, Henrietta Aggrey","doi":"10.1109/ICCWAMTIP56608.2022.10016588","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016588","url":null,"abstract":"Melanoma is the most dangerous and aggressive kind of skin cancer, which is also the most frequent form of cancer worldwide. Given the complexities involved, automatic melanoma detection using skin imaging has lately received interest within the machine learning field. Convolutional neural network has widely been employed in recent years to address this problem. However, existing CNN models for skin cancer classification have the drawback of ignoring crucial spatial relationship between features. They are only able to perform accurate classifications provided a predetermined set of features are present in the test data, regardless of how those features are distributed, which leads to false negatives. Furthermore, the CNN pooling layers responsible for down-sampling in these networks also result in loss of data and poor generalization performance. This study proposes a combination of convolutional block and Capsule Neural Network with a multi-task learning framework to address the aforementioned challenges and boost skin cancer classification. The model’s efficiency was measured by a number of metrics, including accuracy, specificity, recall, and F1 score. The accuracy of the proposed model achieved 98.93%, 98.52%, 95.7%, and 98.87%, respectively, indicating great efficiency when compared to other existing networks. As a result, the proposed method offers less sophisticated and robust architecture for automating the process of melanoma diagnoses and accelerating detection procedures in order to save a life.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122500711","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 : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016551
Li Xujin, L. Jinsong
Frame theory as a further development of wavelet theory, and K-frames are a further expansion of the general concept of frames. This article focuses on the property that K-frames remain invariant under the action of some specific linear operators. Moreover, a perturbation analysis of K-frames with the help of some mathematical tools gives frame-bound estimates for K-frames.
{"title":"Invariance of K-Frames in Hilbert Spaces","authors":"Li Xujin, L. Jinsong","doi":"10.1109/ICCWAMTIP56608.2022.10016551","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016551","url":null,"abstract":"Frame theory as a further development of wavelet theory, and K-frames are a further expansion of the general concept of frames. This article focuses on the property that K-frames remain invariant under the action of some specific linear operators. Moreover, a perturbation analysis of K-frames with the help of some mathematical tools gives frame-bound estimates for K-frames.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116028235","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 : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016477
Jiao Yang, S. Luyao, HU Xinyu, Xing Tian Yi, Li Jun Lin, Li Ya Bin, Wan Qun
In the field of positioning technology, the inertial measurement unit is widely used, it has the advantages of low cost and strong anti-interference. However, inertial navigation positioning produces cumulative errors and poor long-term positioning accuracy. This paper presents a method to suppress the cumulative error by measuring the arrival of the angle of a radiation source. By measuring the direction of a position-known radiation source in the inertial navigation plane at different nodes, the least squares method is used to find the current position coordinates of the node, which reduces the cumulative error of the inertial navigation by about 80%.
{"title":"An AOA-Based IMU Error Suppression Method","authors":"Jiao Yang, S. Luyao, HU Xinyu, Xing Tian Yi, Li Jun Lin, Li Ya Bin, Wan Qun","doi":"10.1109/ICCWAMTIP56608.2022.10016477","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016477","url":null,"abstract":"In the field of positioning technology, the inertial measurement unit is widely used, it has the advantages of low cost and strong anti-interference. However, inertial navigation positioning produces cumulative errors and poor long-term positioning accuracy. This paper presents a method to suppress the cumulative error by measuring the arrival of the angle of a radiation source. By measuring the direction of a position-known radiation source in the inertial navigation plane at different nodes, the least squares method is used to find the current position coordinates of the node, which reduces the cumulative error of the inertial navigation by about 80%.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"290 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132636479","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 : 2022-12-16DOI: 10.1109/ICCWAMTIP56608.2022.10016619
Zhengzhong He
Based on the robot's coordinates and angles, the decision-making system determines what the robot should do in response to the current field situation. The decision-making system of a soccer robot is its brain. Important duties of the football robot system's decision-making subsystem include deploying the players based on the current situation on the field, providing instructions to the players, and assuming the responsibilities of a coach. In this paper, we propose a strategy for decision-making systems competition based on fuzzy decision-making algorithms. A fuzzy comprehensive evaluation is utilized to determine the court's formation and role assignment. This method is capable of integrating a variety of court-related data, does not require the development of a precise mathematical model, and can make sound decisions in real time.
{"title":"The Design of a Soccer Robot Game Strategy Based on Fuzzy Decision Algorithms","authors":"Zhengzhong He","doi":"10.1109/ICCWAMTIP56608.2022.10016619","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP56608.2022.10016619","url":null,"abstract":"Based on the robot's coordinates and angles, the decision-making system determines what the robot should do in response to the current field situation. The decision-making system of a soccer robot is its brain. Important duties of the football robot system's decision-making subsystem include deploying the players based on the current situation on the field, providing instructions to the players, and assuming the responsibilities of a coach. In this paper, we propose a strategy for decision-making systems competition based on fuzzy decision-making algorithms. A fuzzy comprehensive evaluation is utilized to determine the court's formation and role assignment. This method is capable of integrating a variety of court-related data, does not require the development of a precise mathematical model, and can make sound decisions in real time.","PeriodicalId":159508,"journal":{"name":"2022 19th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130734839","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}