发布求助
文献互助 智能选刊 最新文献

Proceedings of the 2020 4th International Conference on Digital Signal Processing最新文献

筛选
英文 中文
A Reconfigurable Branch Predictor for Spatial Computing Architectures 空间计算体系结构的可重构分支预测器
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408168
Yanan Lu, Leibo Liu, Jian Liu, S. Yin, Shaojun Wei
{"title":"A Reconfigurable Branch Predictor for Spatial Computing Architectures","authors":"Yanan Lu, Leibo Liu, Jian Liu, S. Yin, Shaojun Wei","doi":"10.1145/3408127.3408168","DOIUrl":"https://doi.org/10.1145/3408127.3408168","url":null,"abstract":"Branch predictors are widely used in general purpose processors to deal with control flows. However, control flows are spatially dispersed in spatial computing architectures and traditional branch predictors are not so much effective. This paper proposes a novel branch predictor that can be configured into different prediction modes according to the control flow characteristics. Experiment results show that the proposed predictor exceeds all the traditional predictors in terms of accuracy on a coarsegrained reconfigurable array platform. It improves the prediction accuracy by 5.09% compared to a state-of-the-art technique in the cost of slight area increment.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"15 42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124256724","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}
引用次数: 0
Person Re-identification Method Based on Cross-domain Image Style Conversion 基于跨域图像样式转换的人物再识别方法
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408169
Chenkui Wang, Yuelin Chen, Xiaodong Cai, Wenjing Tian
{"title":"Person Re-identification Method Based on Cross-domain Image Style Conversion","authors":"Chenkui Wang, Yuelin Chen, Xiaodong Cai, Wenjing Tian","doi":"10.1145/3408127.3408169","DOIUrl":"https://doi.org/10.1145/3408127.3408169","url":null,"abstract":"The existing cross-domain person re-identification technology has a large difference between the source domain and the target domain, and the performance of the model trained in single-domain is significantly reduced when directly used on another domain. In this paper, a person image style conversion method is used to increase the sample diversity, which narrows the difference between the source domain and the target domain sample. By Cycle Generative Adversarial Networks, the similarity of the source domain image combined with the image style of another domain is closer to the similarity of the target domain data, and the sample diversity is enhanced before the unconverted, which reduces the inter-domain difference of the sample and makes the model have better generalization ability. The experimental results show that after translating the styles of the Market-1501, DukeMTMC-reID and MSMT17 datasets, and then extracting global features through ResNet-50, the accuracy of cross-domain re-identification is significantly improved. At the same time, the model can achieve better re-recognition results without incorporating the style of the target domain dataset or when there are fewer target datasets, which is better than other cross-domain pedestrian re-recognition methods that currently perform well.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"217 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122151329","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}
引用次数: 0
A Stable Modulation Classification Method in Dynamic Environments Using Improved Genetic Algorithm 基于改进遗传算法的动态环境下稳定调制分类方法
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408150
Yunchao Ma, Z. Dou, Wenwen Li
{"title":"A Stable Modulation Classification Method in Dynamic Environments Using Improved Genetic Algorithm","authors":"Yunchao Ma, Z. Dou, Wenwen Li","doi":"10.1145/3408127.3408150","DOIUrl":"https://doi.org/10.1145/3408127.3408150","url":null,"abstract":"With the development of software radio and cognitive radio technology, much work so far has focused on automatic classification of communication signals, but it still cannot meet the requirements in dynamic environments. Starting from the robustness of feature set, a communication signal modulation classification method with dynamic signal noise ratio(SNR) adaptability is proposed. Firstly, the four categories of features of the signal, such as the instantaneous features of the signal, the high-order cumulant features, the fractal theory features and the entropy features, are extracted to form the original feature set. Besides, the anti-noise evaluation function is constructed by analyzing the variation law of each feature under different SNR. Then, we get a robust feature set through this evaluation function. But there are still a lot of problems such as poor classification ability and information redundancy, thus, the second reduction based on our improved genetic algorithm(GA) is proposed. The experimental results show that the new algorithm improves the classification performance of feature subsets at the expense of time cost.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127027965","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}
引用次数: 0
Magnitude-Based Amplitude Estimation of Single Sinusoid in AWGN AWGN中基于幅度的单正弦振幅估计
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408190
Fu Dong, Huang Weizu
{"title":"Magnitude-Based Amplitude Estimation of Single Sinusoid in AWGN","authors":"Fu Dong, Huang Weizu","doi":"10.1145/3408127.3408190","DOIUrl":"https://doi.org/10.1145/3408127.3408190","url":null,"abstract":"The structure of the maximum likelihood (ML) amplitude estimator that is based on the received signal magnitudes is derived for a single sinusoid in additive white Gaussian noise. This estimation problem is closely related to the classic open problem of parameter estimation of a Rician distribution. By exploiting tight, exponential, upper and lower bounds on the modified Bessel function of the first kind with order zero, it is shown analytically that the log-likelihood function is bounded by quadratic functions. This insight allows us to develop an efficient and effective numerical method for the implementation of the ML estimator. The simulation results confirm the validity of the theoretical and numerical analysis.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129077826","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}
引用次数: 0
Music Genre Classification with Transformer Classifier 音乐类型分类与变压器分类器
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408137
Yingying Zhuang, Yuezhang Chen, Jie Zheng
{"title":"Music Genre Classification with Transformer Classifier","authors":"Yingying Zhuang, Yuezhang Chen, Jie Zheng","doi":"10.1145/3408127.3408137","DOIUrl":"https://doi.org/10.1145/3408127.3408137","url":null,"abstract":"Music Genre Classification is a significant and practical field of Music Information Retrieval. Deep learning is increasingly being applied to Music Genre Classification for two main reasons. Firstly, it avoids the manual selection of audio signal features. Secondly, the hierarchical topology is consistent with the layering structure of music in the time and frequency domains. The existing work used CNNs or RNNs or their combination to classify music genre, which have limitations on learning dependencies between distant positions in a sequence. Inspired by an advance in Natural Language Processing (NLP), we designed a Transformer classifier. The Transformer classifier analyzes the relationship between different audio frames well and achieves better performance in Music Genre Classification.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124316566","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}
引用次数: 17
Proceedings of the 2020 4th International Conference on Digital Signal Processing 2020第四届数字信号处理国际会议论文集
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127
{"title":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","authors":"","doi":"10.1145/3408127","DOIUrl":"https://doi.org/10.1145/3408127","url":null,"abstract":"","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115434084","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}
引用次数: 0
CNN Based Model for Malaria Diagnosis with Knowledge Distillation 基于CNN的知识蒸馏疟疾诊断模型
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408159
K. M. F. Fuhad, J. Tuba, Tanzilur Rahman, Nabeel Mohammed
{"title":"CNN Based Model for Malaria Diagnosis with Knowledge Distillation","authors":"K. M. F. Fuhad, J. Tuba, Tanzilur Rahman, Nabeel Mohammed","doi":"10.1145/3408127.3408159","DOIUrl":"https://doi.org/10.1145/3408127.3408159","url":null,"abstract":"Malaria is a deadly disease caused by plasmodium parasites and carried by female anopheles mosquitoes. Bangladesh is one of the major malaria prone country with poor infrastructures, unable to diagnose Malaria rapid at a low cost. Here we propose a custom8 layers CNN architecture that is only 233.60KB in size meaning it can easily fit and work into a low cost smartphone. The model has been optimized through different preprocessing methods and model pruning techniques like knowledge distillation ensuring that the accuracy does not reduce due to smaller model size. The accuracy received from the optimized model is~ 96.51% when tested on NIH data-set containing images of infected and uninfected cells. Proposed model is a big step towards a complete mobile based rapid diagnostic platform that can be used in any resource restricted and hilly areas of Bangladesh.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124578362","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}
引用次数: 3
Fixation Points Estimation Based on Binocular Stereo Vision 基于双目立体视觉的注视点估计
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408198
Hongwei Song, Minling Yang, Tianjun Li, Shengyong Chen
{"title":"Fixation Points Estimation Based on Binocular Stereo Vision","authors":"Hongwei Song, Minling Yang, Tianjun Li, Shengyong Chen","doi":"10.1145/3408127.3408198","DOIUrl":"https://doi.org/10.1145/3408127.3408198","url":null,"abstract":"This paper proposes a method of fixation points estimation combining the two-dimension mapping model with three-dimension stereo vision. The purpose of our study is to design an easy-to-use non-contact gaze tracking system under natural light. The method of two-dimension mapping is easy to achieve, however, it needs the user to keep the head being fixed. It could achieve higher estimation accuracy though it is still not easy for users to use the algorithm. To solve this problem, we have introduced the binocular cameras to calculate the pose of head and then add the related result into the result of 2D mapping to compensate the movement of head. The average error angles of gaze estimation in the case head fixed and head moving are 5.1°and 8.5°, respectively. This proposed method is easy to achieve and the experiment device is easy to mounted.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123570480","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}
引用次数: 0
Enhance the Focal Cortical Dysplasia Lesions in a MR-negative Image: A Case Study 磁共振阴性图像增强局灶性皮质发育不良病变:一个病例研究
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408193
Cuixia Feng, Hulin Zhao, Chen Yang, Miaomiao Lu, Maoyu Tian, Junhai Wen
{"title":"Enhance the Focal Cortical Dysplasia Lesions in a MR-negative Image: A Case Study","authors":"Cuixia Feng, Hulin Zhao, Chen Yang, Miaomiao Lu, Maoyu Tian, Junhai Wen","doi":"10.1145/3408127.3408193","DOIUrl":"https://doi.org/10.1145/3408127.3408193","url":null,"abstract":"Focal cortical dysplasia (FCD) is one of the malformations of cortical development and one of the common causes of intractable epilepsy. The method of image post-processing can enhance the lesion area of the magnetic resonance (MR) image, help doctors to make a better diagnosis, alleviate doctors' dependence on the experience of their supervisors, and reduce the probability of misdiagnosis. In this study, we first calculate the cortical thickness of the T1 weighted images (T1WI) by the three-dimensional (3D) Laplace method and then calculate the highlighted area of the Fluid Attenuated Inversion Recovery (FLAIR) image by the K-means method. Finally, we combine the cortical thickness feature, K-means feature, and normalized positron emission tomography (PET) image to effectively enhance the lesion area of an epileptic patient with MR-negative images. Compared with the traditional methods of junction map and extension map in the morphometric analysis program (MAP) algorithm, this method successfully detected the lesion of FCD, displayed the epileptogenic lesion area through three-dimensional visualization, and showed less false-positive area.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127244189","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}
引用次数: 0
Research on Optimization Strategy Based on Improved DDPG Algorithm in WSN 基于改进DDPG算法的WSN优化策略研究
Proceedings of the 2020 4th International Conference on Digital Signal Processing Pub Date : 2020-06-19 DOI: 10.1145/3408127.3408181
Zeshan Li, G. Guo
{"title":"Research on Optimization Strategy Based on Improved DDPG Algorithm in WSN","authors":"Zeshan Li, G. Guo","doi":"10.1145/3408127.3408181","DOIUrl":"https://doi.org/10.1145/3408127.3408181","url":null,"abstract":"Deep Deterministic Policy Gradient (DDPG) is a combination of Actor-Critic and DQN algorithms. It is one of the most classic algorithms in deep-strong chemistry and can be applied to wireless sensor networks (WSN). Aiming at the problems of low training efficiency, slow convergence rate and large synchronization error caused by the lack of tactical action filtering caused by DDPG, a DDPG algorithm based on weighted information entropy is proposed. The algorithm assigns weights to the training data in advance, trains the data according to the weight ratio, and integrates the results through neural networks. The experimental results show that compared with the DQN algorithm and the DDPG algorithm, the WIE-DDPG algorithm has significantly improved training efficiency and convergence speed, and the synchronization error is significantly reduced.","PeriodicalId":383401,"journal":{"name":"Proceedings of the 2020 4th International Conference on Digital Signal Processing","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127303128","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}
引用次数: 2
下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书