Pub Date : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674163
Ejiyi Chukwuebuka Joseph, O. Bamisile, Nneji Ugochi, Qin Zhen, Ndalahwa Ilakoze, Chikwendu A. Ijeoma
This paper explicates the systematic advancements that were observed from the inception of the YOLO (You Only Look Once) object detector to the most recent version 4. Since its introduction in late 2015, YOLO has recorded tremendous implementation as well as improvements and applications. In this work, a brief survey of the YOLO network is presented considering the introduction that was made to each version that succeeded each preceding version and the advancement on how the model performed with detection. We used the latest version of the network (YOLOv4) to train 50 classes of objects that we considered popular objects for real-time detection. The model trained obtained an mAP of 64.80% @IoU of 0.5 and when deployed for real-time detection, it achieved a 43FPS speed of detection.
{"title":"Systematic Advancement of Yolo Object Detector For Real-Time Detection of Objects","authors":"Ejiyi Chukwuebuka Joseph, O. Bamisile, Nneji Ugochi, Qin Zhen, Ndalahwa Ilakoze, Chikwendu A. Ijeoma","doi":"10.1109/ICCWAMTIP53232.2021.9674163","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674163","url":null,"abstract":"This paper explicates the systematic advancements that were observed from the inception of the YOLO (You Only Look Once) object detector to the most recent version 4. Since its introduction in late 2015, YOLO has recorded tremendous implementation as well as improvements and applications. In this work, a brief survey of the YOLO network is presented considering the introduction that was made to each version that succeeded each preceding version and the advancement on how the model performed with detection. We used the latest version of the network (YOLOv4) to train 50 classes of objects that we considered popular objects for real-time detection. The model trained obtained an mAP of 64.80% @IoU of 0.5 and when deployed for real-time detection, it achieved a 43FPS speed of detection.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121308080","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674104
Liu Yaning, Wang Juan, Li Liangxiao, Ma Quan, Gong Xuepeng
This paper decomposes the multi-element DXF format design file, extracts the most important layer, block, entity element and the number of entities according to the elements, and constitutes the characteristics of the design file; Then, the extracted features are taken as the underlying leaves, and the Merkel tree based on MD5 algorithm is used to get the tamper proof code. By comparing the tamper resistant code, we can detect whether tampering occurs and locate the tampering location, and store the tamper resistant code and tampering location information on the chain, using the characteristics of the blockchain to ensure that they are not tampered and traceable.
{"title":"Research on Design Document Tampering Detection and Location Based on Blockchain Technology","authors":"Liu Yaning, Wang Juan, Li Liangxiao, Ma Quan, Gong Xuepeng","doi":"10.1109/ICCWAMTIP53232.2021.9674104","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674104","url":null,"abstract":"This paper decomposes the multi-element DXF format design file, extracts the most important layer, block, entity element and the number of entities according to the elements, and constitutes the characteristics of the design file; Then, the extracted features are taken as the underlying leaves, and the Merkel tree based on MD5 algorithm is used to get the tamper proof code. By comparing the tamper resistant code, we can detect whether tampering occurs and locate the tampering location, and store the tamper resistant code and tampering location information on the chain, using the characteristics of the blockchain to ensure that they are not tampered and traceable.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123759100","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674114
Song Zhengyan
The fractal property of networks, that is, self-similarity, is a basic but important topic in the area of complex networks. In the process of studying the fractal characteristics of complex networks, the topological distance of unweighted networks is often used to represent the network. However, this ignores some local information of the network, such as the contribution of edges to node degrees. It is inconsistent with common sense. Therefore, in this paper, we propose a new algorithm which replace the traditional topological distance with the effective distance to calculate fractal dimension reasonably. Moreover, we apply this algorithm to five real networks, and the experiment results show the effectiveness and correctness of using effective distance instead of topological distance.
{"title":"Box-Covering Fractal Dimension of Complex Network: From the View of Effective Distance","authors":"Song Zhengyan","doi":"10.1109/ICCWAMTIP53232.2021.9674114","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674114","url":null,"abstract":"The fractal property of networks, that is, self-similarity, is a basic but important topic in the area of complex networks. In the process of studying the fractal characteristics of complex networks, the topological distance of unweighted networks is often used to represent the network. However, this ignores some local information of the network, such as the contribution of edges to node degrees. It is inconsistent with common sense. Therefore, in this paper, we propose a new algorithm which replace the traditional topological distance with the effective distance to calculate fractal dimension reasonably. Moreover, we apply this algorithm to five real networks, and the experiment results show the effectiveness and correctness of using effective distance instead of topological distance.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129633765","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674138
Tiankai Li, Jian-Pin Li, Xi He
Fuzzing is a technology that can automatically discover the vulnerabilities of the target program. It generates test cases from the seeds and runs the target program, monitors the abnormal behavior of the target program, and then discovers test samples that can trigger the vulnerabilities. As one of the cornerstones of the fuzzing field, American Fuzzy Lop (AFL) has been widely studied by industry and academia because of its high efficiency and strong practicability. After an in-depth study of AFL and its improved version AFLFast, it is found that gray-box fuzzing tools represented by AFL are more concerned with edge coverage and do not use function call depth as one of the indicators. This paper introduces the function call depth as one of the coverage indicators, optimizes the non-deterministic mutation stage of AFL, and developed a demo deepAFL. Experiments are carried out on the LAVA-M test set. The results show that the effectiveness of seeds and the efficiency of fuzzing are improved.
{"title":"An Improvement of AFL Based On The Function Call Depth","authors":"Tiankai Li, Jian-Pin Li, Xi He","doi":"10.1109/ICCWAMTIP53232.2021.9674138","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674138","url":null,"abstract":"Fuzzing is a technology that can automatically discover the vulnerabilities of the target program. It generates test cases from the seeds and runs the target program, monitors the abnormal behavior of the target program, and then discovers test samples that can trigger the vulnerabilities. As one of the cornerstones of the fuzzing field, American Fuzzy Lop (AFL) has been widely studied by industry and academia because of its high efficiency and strong practicability. After an in-depth study of AFL and its improved version AFLFast, it is found that gray-box fuzzing tools represented by AFL are more concerned with edge coverage and do not use function call depth as one of the indicators. This paper introduces the function call depth as one of the coverage indicators, optimizes the non-deterministic mutation stage of AFL, and developed a demo deepAFL. Experiments are carried out on the LAVA-M test set. The results show that the effectiveness of seeds and the efficiency of fuzzing are improved.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129719713","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674116
B. L. Y. Agbley, Jianping Li, A. Haq, E. K. Bankas, Sultan Ahmad, Isaac Osei Agyemang, D. Kulevome, Waldiodio David Ndiaye, Bernard M. Cobbinah, Shoistamo Latipova
Melanoma disease analysis is increasingly approached using statistical machine learning techniques, including deep learning. These techniques require large sizes of datasets. However, health institutions are inhibited from sharing their patients' data due to concerns regarding the privacy of subjects. This paper presents a methodology that utilizes Federated Learning (FL) in ensuring the preservation of subjects' privacy during training. We fused two modalities: skin lesion images and their corresponding clinical data. The performance of the global federated model was compared with the results of a Centralized Learning (CL) scenario. The FL model is on-par with the CL model with only 0.39% and 0.73% higher F1-Score and Accuracy performances, respectively, obtained by the CL model. Through extended fine-tuning, the performance difference could be further minimized. Moreover, the FL model was 3.27% more sensitive than the CL model, hence correctly classified more positives than the CL model. Our model also obtained competitive performance when compared with other models from literature. The results indicate the capability of federated learning in effectively learning high predictive models while ensuring no training data is shared among the participating clients.
{"title":"Multimodal Melanoma Detection with Federated Learning","authors":"B. L. Y. Agbley, Jianping Li, A. Haq, E. K. Bankas, Sultan Ahmad, Isaac Osei Agyemang, D. Kulevome, Waldiodio David Ndiaye, Bernard M. Cobbinah, Shoistamo Latipova","doi":"10.1109/ICCWAMTIP53232.2021.9674116","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674116","url":null,"abstract":"Melanoma disease analysis is increasingly approached using statistical machine learning techniques, including deep learning. These techniques require large sizes of datasets. However, health institutions are inhibited from sharing their patients' data due to concerns regarding the privacy of subjects. This paper presents a methodology that utilizes Federated Learning (FL) in ensuring the preservation of subjects' privacy during training. We fused two modalities: skin lesion images and their corresponding clinical data. The performance of the global federated model was compared with the results of a Centralized Learning (CL) scenario. The FL model is on-par with the CL model with only 0.39% and 0.73% higher F1-Score and Accuracy performances, respectively, obtained by the CL model. Through extended fine-tuning, the performance difference could be further minimized. Moreover, the FL model was 3.27% more sensitive than the CL model, hence correctly classified more positives than the CL model. Our model also obtained competitive performance when compared with other models from literature. The results indicate the capability of federated learning in effectively learning high predictive models while ensuring no training data is shared among the participating clients.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129822238","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674095
I. Obiri, Jingcong Yang, Qi Xia, Jianbin Gao
In the Internet of Things (IoT) environment, public key distribution and device authentication remain the most significant security challenges. To validate the authenticity of the identity of IoT devices, existing solutions depend on Public Key Infrastructure (PKI) backed by Certificate Authorities (CA). CA-based PKI has flaws in terms of a single point of failure and certificate transparency. While some blockchain-based PKI solutions exist, they either have a high storage overhead or require a lot of cryptographic computations in the smart contract, which can exceed the transaction size limit on the blockchain network. Hence, we propose a sovereign PKI for IoT devices based on blockchain technology, in which individual controls and maintains the public and private keys for the IoT devices he or she owns. Public keys are kept in a decentralized key store database (DKSB). The blockchain serves as the ground proof for authenticating identities (public keys) on the DKSB. Cryptographic operations like identity authentication are done off-chain without incurring transaction fees.
{"title":"A Sovereign PKI for IoT Devices Based on the Blockchain Technology","authors":"I. Obiri, Jingcong Yang, Qi Xia, Jianbin Gao","doi":"10.1109/ICCWAMTIP53232.2021.9674095","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674095","url":null,"abstract":"In the Internet of Things (IoT) environment, public key distribution and device authentication remain the most significant security challenges. To validate the authenticity of the identity of IoT devices, existing solutions depend on Public Key Infrastructure (PKI) backed by Certificate Authorities (CA). CA-based PKI has flaws in terms of a single point of failure and certificate transparency. While some blockchain-based PKI solutions exist, they either have a high storage overhead or require a lot of cryptographic computations in the smart contract, which can exceed the transaction size limit on the blockchain network. Hence, we propose a sovereign PKI for IoT devices based on blockchain technology, in which individual controls and maintains the public and private keys for the IoT devices he or she owns. Public keys are kept in a decentralized key store database (DKSB). The blockchain serves as the ground proof for authenticating identities (public keys) on the DKSB. Cryptographic operations like identity authentication are done off-chain without incurring transaction fees.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130938309","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9673712
Mou Jianhua, Zheng Qiaoyan, He Guotian
IoT devices constitute the key infrastructure to support various important IoT applications. To ensure the high reliability of these devices and their generated data, a dual verification framework based on a trusted execution environment and Blockchain was proposed to verify the device identity and data authenticity in this paper. In addition, the security of the framework is also analyzed. The scheme provides a data verification reference for the expansion of the ecological application of the IoT.
{"title":"Authenticity Verification Scheme Based On Tee and Blockchain","authors":"Mou Jianhua, Zheng Qiaoyan, He Guotian","doi":"10.1109/ICCWAMTIP53232.2021.9673712","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9673712","url":null,"abstract":"IoT devices constitute the key infrastructure to support various important IoT applications. To ensure the high reliability of these devices and their generated data, a dual verification framework based on a trusted execution environment and Blockchain was proposed to verify the device identity and data authenticity in this paper. In addition, the security of the framework is also analyzed. The scheme provides a data verification reference for the expansion of the ecological application of the IoT.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127165938","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674093
Liu Di, Kong Xinyue, Yong-Cheul Jun
With the development of machine learning, transfer learning has great development prospect and commercial value compared with the traditional supervised learning. As neural network developed, transfer learning based on metric learning is widely used in the field of Computer Vision and gradually applied to Natural Language Processing. This paper proposes to use BERT encoder and BiLSTM to improve the performance of intention detection especially in classification performance. SMP2017 data set shows that it can effectively improve the accuracy of intention detection when the sample size is small and uneven.
{"title":"Optimization of Intention Detection Based on Metric Learning","authors":"Liu Di, Kong Xinyue, Yong-Cheul Jun","doi":"10.1109/ICCWAMTIP53232.2021.9674093","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674093","url":null,"abstract":"With the development of machine learning, transfer learning has great development prospect and commercial value compared with the traditional supervised learning. As neural network developed, transfer learning based on metric learning is widely used in the field of Computer Vision and gradually applied to Natural Language Processing. This paper proposes to use BERT encoder and BiLSTM to improve the performance of intention detection especially in classification performance. SMP2017 data set shows that it can effectively improve the accuracy of intention detection when the sample size is small and uneven.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126687601","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674175
Yang Yujun, Yang Yimei, Zhouqiong Wang, Xi Hongbo, Li Liyun
The quality and safety of agricultural products has been widely concerned by the whole society in recent years. Therefore, the traceability of agricultural products is a research hotspot of scholars. The quality and safety traceability system of agricultural products is an important method to monitor the quality and safety of agricultural products. The emergence and use of big data help to solve the problems of high cost, scattered information and incomplete industrial chain of quality and safety traceability of agricultural products and improve the efficiency and accuracy of the quality and safety traceability system of agricultural products. There are still some problems in the application of big data, such as weak pertinence. It is necessary to mine and use big data to realize the traceability of agricultural products.
{"title":"Research On The Construction of Agricultural Product Quality Maintenance And Quality Traceability System Based On Big Data","authors":"Yang Yujun, Yang Yimei, Zhouqiong Wang, Xi Hongbo, Li Liyun","doi":"10.1109/ICCWAMTIP53232.2021.9674175","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674175","url":null,"abstract":"The quality and safety of agricultural products has been widely concerned by the whole society in recent years. Therefore, the traceability of agricultural products is a research hotspot of scholars. The quality and safety traceability system of agricultural products is an important method to monitor the quality and safety of agricultural products. The emergence and use of big data help to solve the problems of high cost, scattered information and incomplete industrial chain of quality and safety traceability of agricultural products and improve the efficiency and accuracy of the quality and safety traceability system of agricultural products. There are still some problems in the application of big data, such as weak pertinence. It is necessary to mine and use big data to realize the traceability of agricultural products.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126788012","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 : 2021-12-17DOI: 10.1109/ICCWAMTIP53232.2021.9674061
Wang Jiao, Liao Jianqing
Blind identification of modulation and channel coding parameters is a very important research topic in civil-military communication systems. The traditional algorithm is mainly implemented in the way of hierarchical recognition, that is, modulation recognition of the signal first, then demodulation of the signal, and finally coding type recognition and parameter estimation of the demodulated information stream, so as to realize the joint recognition of modulation and coding. In this paper, we propose a deep learning (DL)-based joint recognition algorithm for modulation and coding, which can achieve the recognition of modulation type and coding parameters simultaneously without using additional demodulation algorithms. Simulation results show that the proposed method performs well for the recognition of various modulation and coding types under high signal-to-noise ratio (SNR) conditions.
{"title":"Joint Modulation and Coding Recognition Using Deep Learning","authors":"Wang Jiao, Liao Jianqing","doi":"10.1109/ICCWAMTIP53232.2021.9674061","DOIUrl":"https://doi.org/10.1109/ICCWAMTIP53232.2021.9674061","url":null,"abstract":"Blind identification of modulation and channel coding parameters is a very important research topic in civil-military communication systems. The traditional algorithm is mainly implemented in the way of hierarchical recognition, that is, modulation recognition of the signal first, then demodulation of the signal, and finally coding type recognition and parameter estimation of the demodulated information stream, so as to realize the joint recognition of modulation and coding. In this paper, we propose a deep learning (DL)-based joint recognition algorithm for modulation and coding, which can achieve the recognition of modulation type and coding parameters simultaneously without using additional demodulation algorithms. Simulation results show that the proposed method performs well for the recognition of various modulation and coding types under high signal-to-noise ratio (SNR) conditions.","PeriodicalId":358772,"journal":{"name":"2021 18th International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP)","volume":"14 16","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114060502","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：