Proceedings of the 2nd International Conference on Vision, Image and Signal Processing最新文献_第7页

An LSTM-based Indoor Positioning Method Using Wi-Fi Signals 基于lstm的室内Wi-Fi定位方法

Proceedings of the 2nd International Conference on Vision, Image and Signal Processing Pub Date : 2018-08-27 DOI: 10.1145/3271553.3271566

Ayesha Sahar, Dongsoo Han

{"title":"An LSTM-based Indoor Positioning Method Using Wi-Fi Signals","authors":"Ayesha Sahar, Dongsoo Han","doi":"10.1145/3271553.3271566","DOIUrl":"https://doi.org/10.1145/3271553.3271566","url":null,"abstract":"Recently, Wi-Fi fingerprints are often used for constructing indoor positioning systems. Wi-Fi fingerprint is a vector of Received Signal Strength (RSS) values at a particular location. Radio map is the collection of Wi-Fi fingerprints and their collected location at an area or a building. Positioning systems, mounted on top of the radio map, estimate locations using the information in the radio map. Many Wi-Fi fingerprint-based positioning algorithms have been developed. K-Nearest Neighbor(KNN), probabilistic method, fuzzy logic, neural network, multilayer perceptron are the examples. However, this field has not yet fully benefited from the potential of deep learning approaches. The sequence of Wi-Fi fingerprints implies that the deep recurrent network approaches, especially designed to handle sequential data, can play a vital role to enhance the performance of fingerprint-based positioning systems. In this paper, deep and recurrent approaches are studied rigorously for the improvement of the accuracy of positioning systems. We focus mainly on Long Short-Term Memory (LSTM) networks. An LSTM-based approach was compared with other state of the art approaches. A complete explanation to select the best hyper parameters is presented so that they can be referenced by the researchers in this field. A simple vanilla LSTM architecture is also compared with a stacked LSTM architecture on a Wi-Fi fingerprint dataset.","PeriodicalId":414782,"journal":{"name":"Proceedings of the 2nd International Conference on Vision, Image and Signal Processing","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132036927","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: 38

Integrating Independent Component Analysis with Hopfield Recurrent Neural Network to Estimate the Channel of MIMO-OFDM System 将独立分量分析与Hopfield递归神经网络相结合用于MIMO-OFDM系统信道估计

Proceedings of the 2nd International Conference on Vision, Image and Signal Processing Pub Date : 2018-08-27 DOI: 10.1145/3271553.3271593

Hao Jie

引用次数: 1

Automated Quantification of White Blood Cells in Light Microscopy Muscle Images: Segmentation Augmented by CNN 光学显微镜肌肉图像中白细胞的自动定量:由CNN增强的分割

Proceedings of the 2nd International Conference on Vision, Image and Signal Processing Pub Date : 2018-08-27 DOI: 10.1145/3271553.3271570

Yang Jiao, B. S. Schneider, E. Regentova, Mei Yang

引用次数: 2

Improved DMA Algorithm for the PXIE Bus PXIE总线的改进DMA算法

Proceedings of the 2nd International Conference on Vision, Image and Signal Processing Pub Date : 2018-08-27 DOI: 10.1145/3271553.3271591

Yun Li, Delin Cai, Yaohua Xu

引用次数: 0

Action Recognition by Jointly Using Video Proposal and Trajectory 基于视频提议和轨迹的动作识别

Proceedings of the 2nd International Conference on Vision, Image and Signal Processing Pub Date : 2018-08-27 DOI: 10.1145/3271553.3271563

Lei Qi, Xiaoqiang Lu, Xuelong Li

{"title":"Action Recognition by Jointly Using Video Proposal and Trajectory","authors":"Lei Qi, Xiaoqiang Lu, Xuelong Li","doi":"10.1145/3271553.3271563","DOIUrl":"https://doi.org/10.1145/3271553.3271563","url":null,"abstract":"As a popular research field in computer vision community, human action recognition in videos is a challenging task. In recent years, trajectory based methods have been proven effective for action recognition. However, because trajectory is generated around motion region, trajectory based methods often only pay attention to regions with high motion salience in video and ignore motionless but semantic objects. To compensate the shortage of trajectory based methods, video proposal is utilized for its ability to discover semantic object in this paper. In the proposed method, video proposal and trajectory are extracted simultaneously to capture motion information and object information. The proposed method can be divided into three steps: 1) trajectories and video proposals are extracted from video to capture motion information and object information respectively; 2) a trained Convolution Neural Network (CNN) model is employed to describe the extracted trajectories and video proposals; 3) the holistic representation of video is constructed by Fisher Vector model and then input to classifier to get the action label. The complementarity between trajectory and video proposal enables the discrimination power of the proposed method for kinds of actions. The proposed method is evaluated on UCF101 and HMDB51, on which the promising results prove the effectiveness of the proposed method.","PeriodicalId":414782,"journal":{"name":"Proceedings of the 2nd International Conference on Vision, Image and Signal Processing","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117055591","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

Localization of Epileptogenic Zone: A Graph Theoretical Approach 癫痫区定位:一种图论方法

Proceedings of the 2nd International Conference on Vision, Image and Signal Processing Pub Date : 2018-08-27 DOI: 10.1145/3271553.3271596

G. Nithin, Shameer Aslam, P. S. Sathidevi, P. M. Ameer, S. Gopinath, K. Radhakrishnan, Harilal Parasuram

{"title":"Localization of Epileptogenic Zone: A Graph Theoretical Approach","authors":"G. Nithin, Shameer Aslam, P. S. Sathidevi, P. M. Ameer, S. Gopinath, K. Radhakrishnan, Harilal Parasuram","doi":"10.1145/3271553.3271596","DOIUrl":"https://doi.org/10.1145/3271553.3271596","url":null,"abstract":"For a class of focal epileptic patients having drug-resistant epilepsy, resective surgery seems to be a valid option for treatment. In case of surgery, a minimum amount of cerebral cortex known as Epileptogenic Zone (EZ) will be removed to achieve seizure freedom. Presurgical assessment is an important task since the outcome of surgery depends on how precisely EZ is localized. Analysis of electrical activities of the brain will help in localizing EZ. Stereo-Electroencephalogram (SEEG) is an invasive methodology to explore the bioelectrical activities of deep brain structures. Graph theory can be used for the analysis of SEEG, where each channel of SEEG is taken as a node and cross power transmission in beta and gamma frequency subbands are taken as an edge connecting them. Laplacian centrality measure is used to find the relative importance of a node in this graph and it represents the drop in Laplacian energy when that particular node is removed from the graph. In focal channels (channels in the EZ), at the seizure onset, there is a sharp increase in Laplacian centrality, which shows the extent of the contribution of these channel regions in seizure genesis. Finally, we have marked this extent of increase in centrality value to rank all the channels in the order of their epileptogenicity.","PeriodicalId":414782,"journal":{"name":"Proceedings of the 2nd International Conference on Vision, Image and Signal Processing","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131161895","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

Digital Image Processing for Counting Chips in Micro-End-Milling 微端铣削中计数芯片的数字图像处理

Proceedings of the 2nd International Conference on Vision, Image and Signal Processing Pub Date : 2018-08-27 DOI: 10.1145/3271553.3271579

Jue-Hyun Lee, Angela A. Sodemann

{"title":"Digital Image Processing for Counting Chips in Micro-End-Milling","authors":"Jue-Hyun Lee, Angela A. Sodemann","doi":"10.1145/3271553.3271579","DOIUrl":"https://doi.org/10.1145/3271553.3271579","url":null,"abstract":"In conventional milling, the cutting mechanism is dominated by shearing due to the sharp cutting edge. However, it is no longer possible to assume that the cutting edge is sharp in micro-end-milling since the size of the cutting edge of a micro-end-mill becomes comparable to the feed per tooth. As a result, more than one chip formation mechanism occurs in micro-end-milling at the tool-workpiece interface: shearing, elasto-plastic deformation, and ploughing. In the shearing-dominant chip formation, one chip per tooth cut occurs. However, the chip formation mechanism changes into the elasto-plastic deformation or ploughing when the cutting edge of a tool becomes dull due to the tool wear generating no chip per tooth cut. Therefore, the number of chips produced during a cutting operation can be an important indicator of the state of the interaction between a tool and a workpiece. In this paper, the chips from a slot micro-end-milling operation with a 200 pan tool are counted through digital image processing using Locally Adaptive Threshold Method. In order to count the chips, a chip counting system is developed. The chips are collected and images of the chips are taken by a digital USB microscope. Image processing is applied to the images using Locally Adaptive Threshold Method. The number of chips counted by Locally Adaptive Threshold Method shows less than 10 % counting error.","PeriodicalId":414782,"journal":{"name":"Proceedings of the 2nd International Conference on Vision, Image and Signal Processing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127112103","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