发布求助
文献互助 智能选刊 最新文献

2019 27th Signal Processing and Communications Applications Conference (SIU)最新文献

筛选
英文 中文
A Comparative Analysis of Practices in Training Deep Models for Fashion Attribute Detection 时尚属性检测深度模型训练实践对比分析
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806278
Mustafa Sercan Amac, Aykut Erdem, Erkut Erdem
{"title":"A Comparative Analysis of Practices in Training Deep Models for Fashion Attribute Detection","authors":"Mustafa Sercan Amac, Aykut Erdem, Erkut Erdem","doi":"10.1109/SIU.2019.8806278","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806278","url":null,"abstract":"With the rapid increase of smartphone technologies and social media apps, we live in a time where every day billions of photographs are shared by people through their personal devices, and a large amount of these photos involves person images or selfies. In this study, we investigate the problem of recognizing and classifying fashion attributes in person images. We perform extensive experiments on the StreetStyle-27k dataset with the, a recently proposed large-scale dataset collected for this purpose, in which we analyze the current best practices such as Sthochasthic Gradient Descent with Warm Restarts,Focal loss,Temperature Scaling that are generally used for effective training of deep convolutional networks. Especially, we elaborate on a specific challenge that commonly arise in in-the-wild problems such as ours, which is learning when the distribution of labels is unbalanced.The results we get with the best model is %3.67 better than StreetStyle. We hope that our results will shed some light and be useful to other researchers.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122116650","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
Turkish Sign Language Recognition Using Kinect Skeleton and Convolutional Neural Network 使用Kinect骨架和卷积神经网络识别土耳其手语
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806380
Berkan Unutmaz, Ali Can Karaca, M. Güllü
{"title":"Turkish Sign Language Recognition Using Kinect Skeleton and Convolutional Neural Network","authors":"Berkan Unutmaz, Ali Can Karaca, M. Güllü","doi":"10.1109/SIU.2019.8806380","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806380","url":null,"abstract":"In this paper, a system that converts Turkish signs to words using convolutional neural networks is presented. Skeleton data obtained by Microsoft's Kinect device is used in the proposed system. User located in front of Kinect sensor makes the signs of corresponding word for a limited time. Afterwards, skeleton joints are extracted. Finally, skeleton points on consecutive frames are merged, and Word classification is performed by convulational neural network. In experimental studies, evaluations are carried out with our own dataset and performance of the proposed method is compared with various classification methods. Moreover, the effect of being closer or further to the camera and movements in different speeds are also investigated. In the lights of the experimental results, it is seen that proposed convolutional neural network gives better performances than other classifiers such as Gaussian SVM, Linear SVM, weighted KNN and decision trees.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128244470","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
Pixel Defect Detection in LCD TV Images using Adaptive Thresholding 基于自适应阈值的液晶电视图像像素缺陷检测
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806412
Aydin Sümer, A. Çelik, Ayhan Küçükmanísa, A. Çelebi, O. Urhan
{"title":"Pixel Defect Detection in LCD TV Images using Adaptive Thresholding","authors":"Aydin Sümer, A. Çelik, Ayhan Küçükmanísa, A. Çelebi, O. Urhan","doi":"10.1109/SIU.2019.8806412","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806412","url":null,"abstract":"Nowadays, there is a trend towards higher physical size and resolution in LCD TV production. However, there are still undesired situations such as pixel defects in spite of developing manufacturing technologies. In this study, an adaptive thresholding based pixel defect detection method is proposed. The system, which is evaluated by the F1-score criterion, shows that it can be an alternative to human controlled approaches with its high detection performance. When compared with a machine learning based method in the literature, the proposed method stands out with its working time and detection performance.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129442477","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
Semi-Automatic Formatting of Spelled Out Numbers 拼出数字的半自动格式
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806236
Abdullah Samil Güser, Mustafa Erden, L. Arslan
{"title":"Semi-Automatic Formatting of Spelled Out Numbers","authors":"Abdullah Samil Güser, Mustafa Erden, L. Arslan","doi":"10.1109/SIU.2019.8806236","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806236","url":null,"abstract":"In this paper, we present a semi-automatic method to transform Turkish numeric entities such as telephone numbers, monetary amounts, time and date written in spoken form into their grammatical format using deep neural networks. The method consists of two stages. The first stage consists of sequence labeling model which labels the parts that need to be formatted in a given text and the second stage is a sequence to sequence model which transforms these parts into their numerical format. Given a text normalizer that can transform numerical entities into their spoken format, our method is able to learn reverse transform automatically, without requiring a predetermined set of transform rules. To the best of our knowledge, this is the first work that is conducted on Turkish language. Resulting transformation accuracy of the model in the test set is 92.1%.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124109262","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
DDoS Attack Detection Using Greedy Algorithm and Frequency Modulation 基于贪心算法和调频的DDoS攻击检测
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806266
Çagatay Ates, Süleyman Özdel, Metehan Yildirim, E. Anarim
{"title":"DDoS Attack Detection Using Greedy Algorithm and Frequency Modulation","authors":"Çagatay Ates, Süleyman Özdel, Metehan Yildirim, E. Anarim","doi":"10.1109/SIU.2019.8806266","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806266","url":null,"abstract":"Distributed Denial of Service (DDoS) attack is one of the major threats to the network services. In this paper, we propose a DDoS attack detection algorithm based on the probability distributions of source IP addresses and destination IP addresses. According to the behavior of source and destination IP addresses during DDoS attack, the distance between these features is calculated and used.It is calculated with using the Greedy algorithm which eliminates some requirements associated with Kullback-Leibler divergence such as having the same rank of the probability distributions. Then frequency modulation is proposed in the detection phase to reduce false alarm rates and to avoid using static threshold. This algorithm is tested on the real data collected from Boğaziçi University network.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123631377","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
Image-Processing Based Signal Readout Method for MRD Biochip 基于图像处理的MRD生物芯片信号读出方法
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806457
F. Uslu, Kutay Içöz, Kasim Tasdemir
{"title":"Image-Processing Based Signal Readout Method for MRD Biochip","authors":"F. Uslu, Kutay Içöz, Kasim Tasdemir","doi":"10.1109/SIU.2019.8806457","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806457","url":null,"abstract":"The response of the cancer patients to chemotherapy treatment varies from person to person. For some patients cancer cells are resistant to treatment and these cells can relapse again which is known as minimal residual disease. A microfluidic-based biochip capable of monitoring minimal residual disease is under development by our research group. The role of the biochip is to capture the target cells, which were separated by immunomagnetic beads on micro square tiles. Then biochips are imaged using a bright field optical microscope and it is planned to perform image-processing methods to detect the target cells, immunomagnetic beads and micro tiles. In this work the current progress of image processing methods for differentiating the immunomagnetic beads and micro tiles is presented","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121150655","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
Learning Word Representations with Deep Neural Networks for Turkish 用深度神经网络学习土耳其语单词表示
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806491
E. Dündar, Ethem Alpaydin
{"title":"Learning Word Representations with Deep Neural Networks for Turkish","authors":"E. Dündar, Ethem Alpaydin","doi":"10.1109/SIU.2019.8806491","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806491","url":null,"abstract":"We test different word embedding methods in Turkish. The goal is to represent related words in a high dimensional space such that their positions reflect this relationship. We compare word2vec, fastText, and ELMo on three Turkish corpora of different sizes. Word2vec works at the word level, fastText works at the character level; ELMo, unlike the other two, is context dependent. Our experiments show that fastText is better on name and verb inflection, and word2vec is better on semantic/syntactic analogy tasks. Bag-of-words model is better than most trained word embedding models on classification.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127569065","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
Learning to Follow Verbal Instructions with Visual Grounding 通过视觉基础学习遵循口头指令
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806335
E. Ünal, Ozan Arkan Can, Y. Yemez
{"title":"Learning to Follow Verbal Instructions with Visual Grounding","authors":"E. Ünal, Ozan Arkan Can, Y. Yemez","doi":"10.1109/SIU.2019.8806335","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806335","url":null,"abstract":"We present a visually grounded deep learning model towards a virtual robot that can follow navigational instructions. Our model is capable of processing raw visual input and natural text instructions. The aim is to develop a model that can learn to follow novel instructions from instruction-perception examples. The proposed model is trained on data collected in a synthetic environment and its architecture allows it to work also with real visual data. We show that our results are on par with the previously proposed methods.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133289948","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
Outage Performance of NOMA with Majority Based TAS/MRC Scheme in Rayleigh Fading Channels 瑞利衰落信道中基于多数TAS/MRC方案的NOMA中断性能研究
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806525
Mahmoud Aldababsa, O. Kucur
{"title":"Outage Performance of NOMA with Majority Based TAS/MRC Scheme in Rayleigh Fading Channels","authors":"Mahmoud Aldababsa, O. Kucur","doi":"10.1109/SIU.2019.8806525","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806525","url":null,"abstract":"In this paper, we propose a new suboptimal antenna selection (AS) algorithm, majority based transmit antenna selection (TAS-maj), to maximize the system performance of the non-orthogonal multiple access (NOMA). The TAS-maj scheme chooses the transmit antenna with the majority. It has remarkable advantages over previously proposed AS algorithms. It has lower computational complexity than optimal AS scheme. Also, it provides better performance than the suboptimal AS algorithms, max-max-max (A3) and max-min-max (AIA), since these algorithms aim to maximize the performance of the strong and weak users, respectively. On the other hand, the TAS-maj scheme aims to optimize the performance of more than half of the mobile users in the NOMA network. In this paper, multiple-input multiple-output communication system is considered, in which all the nodes are equipped with multi-antenna. The diversity schemes TAS-maj and maximal ratio combining (MRC) are employed at the base station and mobile users, respectively. Meanwhile, the expression of the signal-to-interference-and-noise is derived. Then, the outage behavior of the NOMA with the TAS-maj/MRC scheme is investigated over Rayleigh fading channels by the Monte Carlo simulations.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115747879","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: 8
A Novel Narrowband Internet Of Things NPUSCH Format 2 Receiver 一种新型窄带物联网NPUSCH格式2接收机
2019 27th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2019-04-01 DOI: 10.1109/SIU.2019.8806411
Özge Özaltın, Ersin Eray Kargı, I. Altin
{"title":"A Novel Narrowband Internet Of Things NPUSCH Format 2 Receiver","authors":"Özge Özaltın, Ersin Eray Kargı, I. Altin","doi":"10.1109/SIU.2019.8806411","DOIUrl":"https://doi.org/10.1109/SIU.2019.8806411","url":null,"abstract":"In this study, we propose a new Narrowband IoT (NB-IoT) receiver design for NPUSCH Format 2, which is equivalent to the Minimum Mean Square Error (MMSE) receiver mathematically. The proposed design changes the scrambling operation, and replaces the hard decoding of BPSK modulation symbols with soft decision decoding. This method outperforms the BER performance of the standard receiver model that utilizes hard decision decoding.","PeriodicalId":326275,"journal":{"name":"2019 27th Signal Processing and Communications Applications Conference (SIU)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124389363","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 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：481959085
Book学术官方微信