发布求助
文献互助 智能选刊 最新文献

2021 Signal Processing Symposium (SPSympo)最新文献

筛选
英文 中文
Sparse Neural Networks with Topologies Inspired by Butterfly Structures 受蝴蝶结构启发的稀疏神经网络拓扑
2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593501
D. Puchala, K. Stokfiszewski
{"title":"Sparse Neural Networks with Topologies Inspired by Butterfly Structures","authors":"D. Puchala, K. Stokfiszewski","doi":"10.1109/spsympo51155.2020.9593501","DOIUrl":"https://doi.org/10.1109/spsympo51155.2020.9593501","url":null,"abstract":"In this paper we propose sparse neural networks with topologies inspired by fast computational butterfly structures of selected linear transforms, namely: fast discrete cosine transform, and Beneš network like topologies. We demonstrate that sparse neural networks allow to obtain high reduction in the number of arithmetic operations and weights needed by neural structures while preserving good efficiency in selected tasks where dense neural networks find their applications. In order to verify the efficiency of the considered structures we conducted a series of experiments in data compression and image recognition. The obtained experimental results confirm good efficiency of the considered sparse neural structures and reveal that such topologies allow for significant reduction in the number of arithmetic operations and weights that must be trained and stored in order to re-use trained neural networks.","PeriodicalId":380515,"journal":{"name":"2021 Signal Processing Symposium (SPSympo)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123654682","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 Hybrid Algorithm for Radar Cross Section Calculation of Electrically Large Targets 电大目标雷达截面计算的混合算法
2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593337
Zhuo Liu, Xu Zhang, Hai-Peng Wang, Feng Wang
{"title":"A Hybrid Algorithm for Radar Cross Section Calculation of Electrically Large Targets","authors":"Zhuo Liu, Xu Zhang, Hai-Peng Wang, Feng Wang","doi":"10.1109/spsympo51155.2020.9593337","DOIUrl":"https://doi.org/10.1109/spsympo51155.2020.9593337","url":null,"abstract":"In our previous study, we proposed the bidirectional analytical ray tracing (BART). BART is based on geometrical optics (GO) and physical optics (PO) to calculate the multiple reflections of electromagnetic waves by dividing the target into many small facets, which can calculate the radar cross section (RCS) of electrically large targets quickly. However, GO can only calculate the contribution of incident and reflected field, and cannot solve the diffraction problem such as edge and vertex, which makes the calculation results of BART inaccurate under some angles. The uniform geometrical theory of diffraction (UTD) can compensate for the shortcomings of GO to overcome the failure in the shadow area and the discontinuity at the boundary between shadow area and bright area. A hybrid algorithm combining the BART and UTD is proposed in this paper. UTD is introduced into the BART to solve the problem that there is no electric field in the shadow area and discontinuity at the boundary. While ensuring calculation efficiency, it improves the accuracy of BART in calculating the RCS of electrically large targets.","PeriodicalId":380515,"journal":{"name":"2021 Signal Processing Symposium (SPSympo)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116781314","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
Comparison of slip-compensated odometry for tracked, four- and six-wheel vehicles 履带式、四轮和六轮车辆滑差补偿里程计的比较
2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593508
Łukasz Chlebowicz, Mateusz Kujawiński, Damian Wronski, B. Cybulski, G. Granosik
{"title":"Comparison of slip-compensated odometry for tracked, four- and six-wheel vehicles","authors":"Łukasz Chlebowicz, Mateusz Kujawiński, Damian Wronski, B. Cybulski, G. Granosik","doi":"10.1109/spsympo51155.2020.9593508","DOIUrl":"https://doi.org/10.1109/spsympo51155.2020.9593508","url":null,"abstract":"Wheel slippage is mostly an unwanted but sometimes inevitable disturbance, especially in mobile robots with over-constrained suspension or operating on slippery surfaces. Improving odometry alone can increase overall localization accuracy, especially when other sources of position information are unavailable. There are several publications dealing with slippage detection and odometry correction, however, they are mostly related to identification of surface for single specific robot type and they require external measurement system for tests. This paper presents a methodology and experiment comparing slip-compensated odometry and tries to extrapolate it to three different suspensions. The main idea behind this article was to check, if different mechanical suspensions with the same kinematic structure (skid-steering), could achieve similar localization accuracy according to the same slip compensation method and using only onboard sensors. The research platform was a custom modular robot. Its chassis allows it to swap the suspension to skid steer six- and four-wheel and tracks. Four chapters of the paper are are organized as follows: in the Introduction, the problem is described in mathematical formulas, then the experiment setup, process and a method for calculating an algorithm-specific coefficient are discussed, followed by presentation of results and summary.","PeriodicalId":380515,"journal":{"name":"2021 Signal Processing Symposium (SPSympo)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121733893","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
Hand measurement based on integrated vision system – Leap Motion 基于综合视觉系统- Leap Motion的手部测量
2021 Signal Processing Symposium (SPSympo) Pub Date : 2021-09-20 DOI: 10.1109/spsympo51155.2020.9593489
Martyna Samowicz, Anna Wieteska, Justyna Redlicka, Katarzyna Koter, Igor Zubrycki
{"title":"Hand measurement based on integrated vision system – Leap Motion","authors":"Martyna Samowicz, Anna Wieteska, Justyna Redlicka, Katarzyna Koter, Igor Zubrycki","doi":"10.1109/spsympo51155.2020.9593489","DOIUrl":"https://doi.org/10.1109/spsympo51155.2020.9593489","url":null,"abstract":"This paper presents a measurement system for after-stroke patients with disabled hands, based on an integrated vision system – Leap Motion. The device provides a simplified way to measure a set of hand parameters such as hand size, wrist, and fingers range of motions. Using the homogeneous-matrix-based notation, we derive medically relevant medical parameters. We provide a user interface for ease of data processing, experiments, and tracking patient progress. The system is evaluated for precision and measurement variation and compared to measurements based on goniometer and caliper. Evaluation of the system shows comparable results to caliper measurements for hand bone lengths while higher variation and large difference in wrist and finger flexion range of motion measurements compared to goniometer.","PeriodicalId":380515,"journal":{"name":"2021 Signal Processing Symposium (SPSympo)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133234300","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: 1
首页 上一页
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