2017 4th International Conference on Systems and Informatics (ICSAI)最新文献_第10页

Design of six bit random number generator based on single chip microcomputer 基于单片机的6位随机数发生器设计

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248395

Yang Bo

引用次数: 0

Novel hybrid wireless-power line video sensor networks with distributed cross-layer optimization 分布式跨层优化的新型混合无线电力线视频传感器网络

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248408

Kainan Zhu, Xu Zhu, Yufei Jiang, Weiqiang Xu

引用次数: 0

Relation classification using revised convolutional neural networks 基于修正卷积神经网络的关系分类

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248512

Bo Li, Xiang Zhao, Shuai Wang, Weihong Lin, W. Xiao

{"title":"Relation classification using revised convolutional neural networks","authors":"Bo Li, Xiang Zhao, Shuai Wang, Weihong Lin, W. Xiao","doi":"10.1109/ICSAI.2017.8248512","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248512","url":null,"abstract":"Relation classification plays an important part in the structuralization of text data via information extraction. Lately, neural network-based methods have been applied to relation classification, which use neural networks to encode and extract features from the input text. As convolution neural network based method can extract high-level features through convolution filters, it achieves competitive performance with other complex-structured networks by only using a standard convolution layer, a pooling layer, and a regression layer. However, it failed to capture the hierarchical and syntax information of sentence. Inspired by this, We introduce the hierarchical convolutional layers and dependency embedding to the CNN based methods. The hierarchical convolution layers capture the detail feature and high-level hierarchical features and concatenate these features as the sentence representation. The dependency embeddings help CNN capture the dependency structure in the window size, which improve the classification results. Experiments verify that the revised relation classification method provide state-of-the-art performance, even without additional artificial features.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114930035","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

Evaluation of synthetic data for deep learning stereo depth algorithms on embedded platforms 嵌入式平台上深度学习立体深度算法的综合数据评价

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248284

Kevin Lee, D. Moloney

{"title":"Evaluation of synthetic data for deep learning stereo depth algorithms on embedded platforms","authors":"Kevin Lee, D. Moloney","doi":"10.1109/ICSAI.2017.8248284","DOIUrl":"https://doi.org/10.1109/ICSAI.2017.8248284","url":null,"abstract":"Stereo vision is a very active field in the realm of computer vision and in recent years Convolutional Neural Networks (CNNs) have proven to be very competitive against the state-of-the-art. However the performance of these networks are limited by the quality of the data that is used when training the CNNs. Data acquisition of high quality labelled images is a time-consuming and expensive process. By exploiting the power of modern-day powerful GPUs, we present a synthetic dataset with fully rectified stereo image pairs and accompanying accurate ground truth information that can be used for training and testing stereo algorithms. We provide validation of the quality of our dataset by performing quantitative experiments that suggest pre-training deep learning algorithms on synthetic data can perform competitively against networks trained on real life data. Testing on the KITTI data-set[1], we found the accuracy performance difference between the real and synthetically trained networks was within a margin of 1.8%. We also illustrate the functionality synthetic data can provide, by conducting a key performance index on a selection of conventional and deep learning stereo algorithms available on embedded platforms and compared them under common metrics. We also focused on power consumption and performance and we were able to achieve a compute the matching cost from a CNN performing inference on an embedded device at 11.9 FPS at 1.2 Watts.","PeriodicalId":285726,"journal":{"name":"2017 4th International Conference on Systems and Informatics (ICSAI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133657122","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: 5

Pedestrian road detection based on shadow matching 基于阴影匹配的行人道路检测

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248498

Tingting Xiao, Wen Chen, Chao Yu, Yaxuan Dong, Yi Gao

引用次数: 0

Design and implementation of a location based service business management platform 基于位置服务的业务管理平台的设计与实现

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248545

Dong Wang, Zhaohui Li, Yan Chen

引用次数: 3

Individual game information evaluation using signal processing measurement 个体博弈信息评价用信号处理测量

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248505

Shuo Xiong, Long Zuo, Zeliang Zhang, H. Iida

引用次数: 0

Research of large-scale offline map management in visual SLAM 可视化SLAM中大规模离线地图管理的研究

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248292

Qihui Shen, Hanxu Sun, Ping Ye

引用次数: 1

Dynamic complexity of mobile internet business ecosystem 移动互联网商业生态系统的动态复杂性

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248344

B. Bai, Zhiqiong Guo

引用次数: 7

Forced vibration of a multidirectional nonlinear oscillator 多向非线性振荡器的强迫振动

2017 4th International Conference on Systems and Informatics (ICSAI) Pub Date : 2017-11-01 DOI: 10.1109/ICSAI.2017.8248554

Yang Chen, Yipeng Wu

引用次数: 3