2021 29th Signal Processing and Communications Applications Conference (SIU)最新文献

Anomaly Detection in Wide Area Imagery 广域图像中的异常检测

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9477987

Abdullah Hamza Sahin, H. Ates, B. K. Güntürk

引用次数: 1

Management of Service Function Chains in Programmable Data Plane 可编程数据平面中的业务功能链管理

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9478038

Özgür Yürekten

引用次数: 0

Deep Learning Based Image Segmantation and Classification for Fashion Detection on Smartphones 基于深度学习的智能手机时尚检测图像分割与分类

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9477905

Emre Üzüm

{"title":"Deep Learning Based Image Segmantation and Classification for Fashion Detection on Smartphones","authors":"Emre Üzüm","doi":"10.1109/SIU53274.2021.9477905","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9477905","url":null,"abstract":"With the rapid increase in smartphone technologies and social media applications, photo sharing among people has become widespread. Most of the photos shared include the clothes people use in daily life. Access to desired clothes is easier with online facilities. Identifying the outfit in a photograph is the first step to this. In this study, an original system with deep learning based segmentation and classification methods aiming at detecting the clothes used in daily life via smart phone is proposed. The image taken with a smartphone camera was segmented first, and the clothing boundaries in the image were determined and tagged for classification. The labeled image was trained with the convolutional neural network and the category to which the garment belongs was determined. Using different models in the segmentation part, the highest accuracy was obtained in the mask regional convolutional neural network on the DeepFashion2 da taset. In the classification part, the Xception architecture showed superiority in the trainings made with different convolutional neural networks. The models with the highest accuracy rate are combined with our Android application called Clothes Detection, which we developed to detect clothes. Thanks to our user-friendly application that has been developed, clothes can be detected on the photograph.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126073593","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

Modeling Brushless Direct Current Motor Of A Guided System 导向系统无刷直流电机建模

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9477923

Selçuk Kiyli, H. Ş. Bilge

引用次数: 1

An Uplink CoMP Transmission Scheme 上行CoMP传输方案

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9478020

Emre Bilican, Özge Özaltın, A. Yesil, Burak Dagdeviren

引用次数: 0

When does Synthetic Data Generation Work? 什么时候合成数据生成工作?

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9477956

A. Topal, M. Amasyali

{"title":"When does Synthetic Data Generation Work?","authors":"A. Topal, M. Amasyali","doi":"10.1109/SIU53274.2021.9477956","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9477956","url":null,"abstract":"Synthetic data generation is one of the methods used in machine learning to increase the performance of algorithms on datasets. However, these methods do not ensure success on each dataset. In this study, it has been investigated that which type of synthetic data generation algorithms are useful in which datasets by examining the effects of SMOTE, Borderline-SMOTE and Random data generation algorithms on 33 datasets. For this, each dataset has been fully balanced as a result of synthetic data generation. In order to evaluate the results, datasets are divided into three groups as balanced, partially balanced-unbalanced and unbalanced in accordance with the unbalance ratio. The datasets formed as a result of the data generation of the algorithms and the original datasets have been trained with an ANN models and their performance has been evaluated on the test set. Experimental results have shown that adding synthetic data to the datasets with the abovementioned algorithms generally increases the success in balanced and partially balanced-unbalanced datasets, but generally does not work in unbalanced datasets. Borderline-SMOTE, which produces border samples in balanced datasets, and SMOTE in partially balanced-unbalanced datasets have been more successful.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115024295","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

The Analysis of Feature Selection with Machine Learning for Indoor Positioning 基于机器学习的室内定位特征选择分析

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9478012

Hurkan M. Aydin, Muhammad Ammar Ali, Ece Gelal Soyak

引用次数: 3

Dual-Fed Wideband MIMO Antenna System Design for 5G Applications with Increased Gain with Superstrate 5G增增益双馈宽带MIMO天线系统设计

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9477829

M. Yerlikaya, S. S. Gültekin

{"title":"Dual-Fed Wideband MIMO Antenna System Design for 5G Applications with Increased Gain with Superstrate","authors":"M. Yerlikaya, S. S. Gültekin","doi":"10.1109/SIU53274.2021.9477829","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9477829","url":null,"abstract":"In this study, a compact microstrip MIMO antenna system design with broadband for fifth generation (5G) mobile applications, also known as the next generation, is presented. The proposed antenna system consists of two identical log-periodic dipole antennas (LPDA) placed at an angle of 90° to each other. LPDAs, each consisting of 5 element arrays, are designed with Rogers RT5880 dielectric material with a thickness of 0.508mm and a relative permeability of 2.2. The total size of the MIMO antenna system is determined as 20x20 mm2, where each LPDA's size is 4.15x13 mm2. The proposed antenna system offers impedance bandwidth in the 28 GHz resonance and frequency range of 26.2-30.4 GHz. However, an isolation level above 25 dB was achieved without the need for any additional structure between MIMO elements. To increase the gain value, a superstrate with 1.52 mm height and relative permeability of 3 was also added on the MIMO antenna system. Thus, a gain increase of over 50% was achieved for the whole operating band with this superstrate. With this top layer added, an increase of over 50% has been achieved in the recommended antenna gain for the entire operating band. All the designs and simulations in the study were carried out with the moment based HyperLynx 3D EM package program.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115567288","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

Subword Semantic Hashing for Intent Classification in Turkish Language ChatBots 土耳其语聊天机器人意图分类的子词语义哈希

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9478003

Rümeysa Eliöz, Berk Özsoy, Abdullah H. Ozcan, Hüseyin Kara, Lütfü Çakil

引用次数: 0

Robust and high-capacity audio watermarking basedon chirp z-transform 基于啁啾z变换的鲁棒高容量音频水印

2021 29th Signal Processing and Communications Applications Conference (SIU) Pub Date : 2021-06-09 DOI: 10.1109/SIU53274.2021.9477976

Omar Abodena

引用次数: 3