{"title":"Gender Recognition from PPG Signals of People with Different Blood Pressure","authors":"T. Aydemir, Mehmet Sahin, Önder Aydemir","doi":"10.1109/SIU53274.2021.9477787","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9477787","url":null,"abstract":"Photoplethysmography (PPG) is an opto-electronic technique that measures the blood volume within micro-vascular tissue. Studies based on measuring blood pressure level with PPG have been widely used. In this study, gender recognition was performed using PPG signals recorded from people with different blood pressure levels. The obtained results showed that the sum of the derivative, kurtosis, median, skewness, variance, variance of the second derivative calculated from the wavelet transform coefficients can be used in gender recognition as an attribute. By using these features, a classification accuracy of 74.77% and a polygon area metric of 0.4961 were obtained with the decision tree classifier. It is thought that gender recognition can be achieved with PPG signals, which can also be measured on touch screens (smart phones, watches and tablets) with the proposed method.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"26 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":"131670710","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}
Aydin Yügrük, Erkan Danaci, A. K. Doğan, A. Salman
{"title":"The Effects of Sequential and Multiple Measurement on RF Power","authors":"Aydin Yügrük, Erkan Danaci, A. K. Doğan, A. Salman","doi":"10.1109/SIU53274.2021.9477768","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9477768","url":null,"abstract":"Automatic RF power measurements have become indispensable for reliable and accurate measurements in high frequency systems, which are increasingly used nowadays. In the project subject to this study, an automatic RF power measurement software that can perform multiple measurements has been developed. In this study, manual RF power measurements and automatically RF power measurement by using developed software are evaluated and also advantages of automatic power measurement and contributions of automatic measurement to power measurement uncertainty calculations are presented.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"48 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":"133283762","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}
{"title":"Calculation of Resonant Frequency and Bandwidth of Rectangular Microstrip Antennas via Genetic Algorithm","authors":"Zeynep Sidika Seven, S. Can","doi":"10.1109/SIU53274.2021.9478054","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9478054","url":null,"abstract":"In this study, the resonant frequency and bandwidths of rectangular shaped patch antennas were calculated with the genetic algorithm method used in solving electromagnetic problems in recent years. The parameters for the length and width of the rectangular microstrip antennas were obtained for different resonant frequencies, various substrate permeability values and different thickness values of the antenna. Calculation results were compared with experimental results, obtained with high accuracy.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"15 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":"133349786","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}
Muhammed Coskun Irmak, Mehmet Bilge Han Tas, Sedat Turan, A. Hasiloglu
{"title":"Comparative Breast Cancer Detection with Artificial Neural Networks and Machine Learning Methods","authors":"Muhammed Coskun Irmak, Mehmet Bilge Han Tas, Sedat Turan, A. Hasiloglu","doi":"10.1109/SIU53274.2021.9477991","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9477991","url":null,"abstract":"The number of cancer patients is increasing all over the world due to reasons such as environmental pollution, excess of technological and biological wastes, climate change, and increased consumption of unnatural foods. According to the data of the World Health Organization in 2020, there are over 19 million cancer patients in the world. The most common type of cancer is breast cancer with 11.7%. Breast cancer is as high as 24.5% in women and 15.5% of these cases result in death. Therefore, it is important to detect cancer at an early stage. The purpose of this study is to detect cancer in the fastest way and with the highest accuracy rates. In the study, high performance results were obtained by comparing artificial neural networks and traditional machine learning methods. In the study; Logistic Regression (LR), k-Nearest Neighbors (kNN), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Xgboost (XGB) and Artificial Neural Network (ANN) were used. The highest result obtained using traditional machine learning methods is 98.08% with LR. In addition, using ANN, the highest value was obtained with an accuracy rate of 99.36%.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"62 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":"127946460","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}
{"title":"The Effect of Background Subtraction on Abnormal Event Detection in Video Surveillance","authors":"E. Şengönül, R. Samet","doi":"10.1109/SIU53274.2021.9478002","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9478002","url":null,"abstract":"In this study, the effect of background subtraction in the proposed method for abnormal event detection in video surveillance was investigated. Extracted video frames have passed through various processes and trained the model in the Long Short-Term Memory Network (LSTM) based Convolution Autoencoder architecture. There is no labeling in the data. Semisupervised learning model has been implemented by training with the normal video images. The trained model is structured according to the input data and new frames are tested on the model. The conformity of the tested frames to the model was observed with the generated regularity score. The outputs of the model trained by the background subtracted frames and the model trained by the normal frames were compared. According to the results, it was observed that background subtraction increases the accuracy in detecting abnormal events.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"13 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":"127977702","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}
{"title":"Unsupervised Discovery of Fingerspelled Letters in Sign Language Videos","authors":"Feyza Duman, Tanya Deniz Ipek, M. Saraçlar","doi":"10.1109/SIU53274.2021.9477880","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9477880","url":null,"abstract":"Automatic discovery and indexing in sign language videos would provide many valuable services such as search and retrieval in deaf social and news media which consists of sign language videos often with no associated texts available. As some of the context words in sign language conversations are fingerspelled, the discovery of fingerspelled letters plays a significant role. In this study, k-means clustering and Gaussian Mixture Model methods are used for the unsupervised discovery of fingerspelled letters. The clusers which mostly contain hand shapes corresponding to transitions between letters are eliminated based on their distortion level and Bayes information criterion values. The performance of the clustering methods are evaluated with the help of Adjusted Mutual Information metric. According to the results obtained with this metric, using a Gaussian Mixture Model for clustering yields better results than k-means clustering.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"76 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":"129236860","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}
{"title":"Comparison of Data-Driven and Morphological Features for Cell Segmentation in Histopathological Images","authors":"Omer Faruk Karaaslan, G. Bilgin","doi":"10.1109/SIU53274.2021.9477704","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9477704","url":null,"abstract":"In this study, it is aimed to increase the segmentation performance of the cells in digital histopathological images by morphological feature extraction methods. For this purpose, it is proposed to evaluate the features extracted by the extended morphological profiles method. First, principal component analysis of the images in the RGB color space of digital histopathological images is performed, then the features are extracted using the extended morphological profiles method. Then, a feature set is created from these attributes and classified with support vector machines, which are kernel based classifiers. The results are compared and evaluated according to three different metrics with other results that were previously obtained in the same data set. In the application results section, the results obtained in this study are presented in full detail.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"18 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":"116862861","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}
Anıl Tırlıoğlu, Ömer Bayram Demir, Alper Yazar, E. G. Schmidt
{"title":"Hardware Accelerators for Cloud Computing: Features and Implementation","authors":"Anıl Tırlıoğlu, Ömer Bayram Demir, Alper Yazar, E. G. Schmidt","doi":"10.1109/SIU53274.2021.9478015","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9478015","url":null,"abstract":"In this paper, hardware accelerator (FHA) applications realized on FPGA that can be offered as a service in cloud computing systems are discussed. It is necessary to know the hardware resources used by FHA applications and the performance they provide for the efficient meeting of the user requests and effective resource planning. To this end, the first contribution of this paper is to provide a compilation of the literature on the features of frequently used hardware accelerators (matrix multiplication, face detection, FFT) in the last three years, based on common parameters and metrics. The numerical values we provide can be used for cloud resource allocation and creation of sample cloud workloads. The second contribution of our paper is the implementation of the Canny edge detector, a sample hardware accelerator implemented in HLS (High-level Synthesis), using an open source library. In this way, the work flow for the implementation and operation of the hardware accelerator together with its performance are presented.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"31 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":"114180693","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}
Baris Büyüktas, Oguzhan Yetimoglu, Abdurrahman Dilmac, Z. C. Canbek, Huseyin Birkan Yilmaz
{"title":"A Mock Circulatory Network Testbed for Molecular Communications","authors":"Baris Büyüktas, Oguzhan Yetimoglu, Abdurrahman Dilmac, Z. C. Canbek, Huseyin Birkan Yilmaz","doi":"10.1109/SIU53274.2021.9478034","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9478034","url":null,"abstract":"Molecular communication is applied to advance the capabilities of healthcare and medical systems. These systems may be utilized for cancer cell localization, in-body synchronization, and anomaly detection applications. In this paper, a mock circulatory network testbed for molecular communication is introduced. A realistic mock circulary network is important to understand the human circulatory hemodynamics from molecular communication's perspective. The mock circulatory network testbed basically consists of a pulsatile pump (for mimicking heart), 3D printed left and right pulmonary artery, silicone mock vessel network, non-invasive pressure sensors, valves, information molecules, chemical sensors, and data acquisition center.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"8 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":"114182205","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}
{"title":"A New Hybrid Peak Detection Methods for Fiber Bragg Grating Temperature Sensor","authors":"Z. Saraç, Burak Kurt, Cihangir Erdemir","doi":"10.1109/SIU53274.2021.9478037","DOIUrl":"https://doi.org/10.1109/SIU53274.2021.9478037","url":null,"abstract":"The center of temperature measured in the Fiber Bragg Grating temperature sensor produces a shift in the Bragg wavelength. There are a wide variety of algorithms used to detect this shift. However, these algorithms are highly affected by the noise generated in the sensor system. In recent years, many techniques have emerged that suppress this noise. Of these, wavelet noise reduction stands out as a popular technique. When the literature is reviewed, it is stated that this popular approach is superior to traditional methods. Contrary to what is said in the literature, this study proves that without the need for complex wavelet system or even curve fitting, it leads us to the same results and sometimes even better than traditional filtering. The hybrid approach proposed here is based on the traditional Fourier Filtering technique and the maximum method, which is a direct method in determining the central wavelength. In the error analysis, it is seen that the hybrid algorithm based on Fourier Filtering, which is the traditional filtering technique, gives the smallest relative error when compared with the real value.","PeriodicalId":160693,"journal":{"name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","volume":"156 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":"114528874","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}