Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299250
M. Karakaş, F. Latifoğlu
The Squirrel Search Algorithm, one of the newly introduced metaheuristic algorithm, has been applied for high performance and low grade FIR filter design in MATLAB environment and the results of this design are shared.
{"title":"Finite Impulse Response Filter Design Using Squirrel Search Algorithm","authors":"M. Karakaş, F. Latifoğlu","doi":"10.1109/TIPTEKNO50054.2020.9299250","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299250","url":null,"abstract":"The Squirrel Search Algorithm, one of the newly introduced metaheuristic algorithm, has been applied for high performance and low grade FIR filter design in MATLAB environment and the results of this design are shared.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121578025","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}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299306
T. Aydemir, ve Mehmet Şahi̇n, Önder Aydemir
In parallel with technological developments, the usage areas of biometric systems are getting more attention. Photoplethysmography (PPG) based biometry applications have attracted attention in recent years with their safe and practical applicability. In this study, PPG signals were recorded from 7 volunteers not only in resting state but also during squat movement, and biometric recognition performances were compared. Total amplitude, covariance, kurtosis, skewness, quadratic integral and maximum fractal length values of the first derivative of the signals were extracted as features from the PPG signals. These have been tested with k-nearest neighborhood, naive Bayesian and decision tree classifiers. The results showed that the PPG signals recorded during the squat movement, with 99.65%, would provide higher recognition than the PPG signals of the resting state.
{"title":"Biometric Recognition System Based on Photoplethysmography Signals Recorded During Squat Movement and Rest","authors":"T. Aydemir, ve Mehmet Şahi̇n, Önder Aydemir","doi":"10.1109/TIPTEKNO50054.2020.9299306","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299306","url":null,"abstract":"In parallel with technological developments, the usage areas of biometric systems are getting more attention. Photoplethysmography (PPG) based biometry applications have attracted attention in recent years with their safe and practical applicability. In this study, PPG signals were recorded from 7 volunteers not only in resting state but also during squat movement, and biometric recognition performances were compared. Total amplitude, covariance, kurtosis, skewness, quadratic integral and maximum fractal length values of the first derivative of the signals were extracted as features from the PPG signals. These have been tested with k-nearest neighborhood, naive Bayesian and decision tree classifiers. The results showed that the PPG signals recorded during the squat movement, with 99.65%, would provide higher recognition than the PPG signals of the resting state.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122139922","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}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299258
Veli Baysal
Studies have shown that neurons exposed to two or more signals with different frequencies can fire at frequencies other than these. This phenomenon is known as Ghost Resonance (GR). In this study, GR phenomenon was investigated in a two-layer feed forward loop (FFL) network consisting of Hodgkin-Huxley (H-H) neurons. Periodic signals with different frequencies were applied to each of the two neurons in the first layer of the FFL network. The firing behavior of the neuron in the second layer of the FFL network has been studied. The results show that the third neuron in the FLL network fires at a frequency that is the absolute value of the difference between the frequencies of the signals applied to the first and second neurons. These results reveal the presence of GR phenomenon in H-H neurons.
{"title":"Ghost Resonance in Hodgkin-Huxley Neurons","authors":"Veli Baysal","doi":"10.1109/TIPTEKNO50054.2020.9299258","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299258","url":null,"abstract":"Studies have shown that neurons exposed to two or more signals with different frequencies can fire at frequencies other than these. This phenomenon is known as Ghost Resonance (GR). In this study, GR phenomenon was investigated in a two-layer feed forward loop (FFL) network consisting of Hodgkin-Huxley (H-H) neurons. Periodic signals with different frequencies were applied to each of the two neurons in the first layer of the FFL network. The firing behavior of the neuron in the second layer of the FFL network has been studied. The results show that the third neuron in the FLL network fires at a frequency that is the absolute value of the difference between the frequencies of the signals applied to the first and second neurons. These results reveal the presence of GR phenomenon in H-H neurons.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123242223","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}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299238
Muharrem Çelebi
Biomedical signals are the primary data source for diagnosis of diseases and monitoring of patients. These kinds of operations are carried out in hospital environment with huge devices. Today, due to rapid development of embedded systems, sizes of these devices have been reduced to small dimensions. In this way, while the patients continue their daily lives, the small sized devices make it easier to record biomedical signs related to their diseases. In this study, the electrocardiogram (ECG) sign, one of the most basic signs for heart diseases, is detected and displayed on the graphic display. To determined for this goal, ECG sensor card, wireless communication module, ARDUINO nano and TFT LCD screen are used. The idea is designed independently in two circuits and all circuits are supplied with small batteries for compact size. In this way, the circuits are realized in small sizes. According to the results, the system proposed can detect heart signals and heart beats and the system can show results to users.
{"title":"Portable ECG Monitoring Device Design Based on ARDUINO","authors":"Muharrem Çelebi","doi":"10.1109/TIPTEKNO50054.2020.9299238","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299238","url":null,"abstract":"Biomedical signals are the primary data source for diagnosis of diseases and monitoring of patients. These kinds of operations are carried out in hospital environment with huge devices. Today, due to rapid development of embedded systems, sizes of these devices have been reduced to small dimensions. In this way, while the patients continue their daily lives, the small sized devices make it easier to record biomedical signs related to their diseases. In this study, the electrocardiogram (ECG) sign, one of the most basic signs for heart diseases, is detected and displayed on the graphic display. To determined for this goal, ECG sensor card, wireless communication module, ARDUINO nano and TFT LCD screen are used. The idea is designed independently in two circuits and all circuits are supplied with small batteries for compact size. In this way, the circuits are realized in small sizes. According to the results, the system proposed can detect heart signals and heart beats and the system can show results to users.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128338032","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}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299261
S. Frolov, A. Potlov, S. Proskurin, T. Frolova
A method for in vivo evaluation the value of the modulus of longitudinal elasticity (Young’s modulus) for the large blood vessel walls was described. Digital processing of a sequence of optical coherence tomography (OCT) structural images of the investigated blood vessels’ walls is the key feature of the described method. The pulse wave is used as a physiological and therefore relatively safe deforming impact. The absolute displacement of the blood vessel wall structures is calculated from the shift of peaks in the averaged A-scan interferograms. The size of the deformable region in the structural OCT images and the deforming area are considered to be equal to the coherence probing depth and the scanning area of the intravascular probe, respectively. The described method is to be used for choosing the optimal flowdiverter for correct treatment of cerebral arteries with aneurysms.
{"title":"Young’s Modulus Evaluation of the Walls of Cerebral Arteries with Aneurysms","authors":"S. Frolov, A. Potlov, S. Proskurin, T. Frolova","doi":"10.1109/TIPTEKNO50054.2020.9299261","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299261","url":null,"abstract":"A method for in vivo evaluation the value of the modulus of longitudinal elasticity (Young’s modulus) for the large blood vessel walls was described. Digital processing of a sequence of optical coherence tomography (OCT) structural images of the investigated blood vessels’ walls is the key feature of the described method. The pulse wave is used as a physiological and therefore relatively safe deforming impact. The absolute displacement of the blood vessel wall structures is calculated from the shift of peaks in the averaged A-scan interferograms. The size of the deformable region in the structural OCT images and the deforming area are considered to be equal to the coherence probing depth and the scanning area of the intravascular probe, respectively. The described method is to be used for choosing the optimal flowdiverter for correct treatment of cerebral arteries with aneurysms.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124670346","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}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299244
Bora Cebeci, A. Akan, T. Demiralp, M. Erbey
In this study, it is determined individual-based features which are used to estimate emotional negative valence and compared the features effectiveness with different classifiers. Ten movie clips are shown to subjects as an emotional stimuli and EEG recording is recorded synchronously. Emotional valence value is scored in [–7 7] Likert scale by the subjects immediately after video ended. According to lowest and highest valence values, two classes are generated. The data is processed on an individual basis and personal spatial filters is obtained by Independent Component Analysis. After calculating the spectrogram of the spatial filtered data, features are extracted by subtracting amplitudes of 3Hz averaged frequency bands. The result of feature selection, it is observed that features from beta and gamma bands are much more effective. The success rate of the selected features was tested with five classifiers by cross validation, and high performance was obtained from multilayer perceptron classifiers and the instance- based k-nearest neighborhood algorithm (IBk-NN). The average accuracies of IBk-NN and multilayer classifier are achieved 86% ±8 and 83% ±9, respectively.
{"title":"Individual-based Estimation of Valence with EEG","authors":"Bora Cebeci, A. Akan, T. Demiralp, M. Erbey","doi":"10.1109/TIPTEKNO50054.2020.9299244","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299244","url":null,"abstract":"In this study, it is determined individual-based features which are used to estimate emotional negative valence and compared the features effectiveness with different classifiers. Ten movie clips are shown to subjects as an emotional stimuli and EEG recording is recorded synchronously. Emotional valence value is scored in [–7 7] Likert scale by the subjects immediately after video ended. According to lowest and highest valence values, two classes are generated. The data is processed on an individual basis and personal spatial filters is obtained by Independent Component Analysis. After calculating the spectrogram of the spatial filtered data, features are extracted by subtracting amplitudes of 3Hz averaged frequency bands. The result of feature selection, it is observed that features from beta and gamma bands are much more effective. The success rate of the selected features was tested with five classifiers by cross validation, and high performance was obtained from multilayer perceptron classifiers and the instance- based k-nearest neighborhood algorithm (IBk-NN). The average accuracies of IBk-NN and multilayer classifier are achieved 86% ±8 and 83% ±9, respectively.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116550071","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}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299260
Mehmet Akif Ozdemir, Onan Guren, Ozlem Karabiber Cura, A. Akan, Aytuğ Onan
The heart is the most critical organ for the sustainability of life. Arrhythmia is any irregularity of heart rate that causes an abnormality in your heart rhythm. Clinical analysis of Electrocardiogram (ECG) signals is not enough to quickly identify abnormalities in the heart rhythm. This paper proposes a deep learning method for the accurate detection of abnormal and normal heartbeats based on 2-D Convolutional Neural Network (CNN) architecture. Two channels of ECG signals were obtained from the MIT-BIH arrhythmia dataset. Each ECG signal is segmented into heartbeats, and each heartbeat is transformed into a 2-D grayscale heartbeat image as an input for CNN structure. Due to the success of image recognition, CNN architecture is utilized for binary classification of the 2-D image matrix. In this study, the effect of different CNN architectures is compared based on the classification rate. The accuracies of training and test data are found as 100.00% and 99.10%, respectively for the best CNN model. Experimental results demonstrate that CNN with ECG image representation yields the highest success rate for the binary classification of ECG beats compared to the traditional machine learning methods, and one-dimensional deep learning classifiers.
{"title":"Abnormal ECG Beat Detection Based on Convolutional Neural Networks","authors":"Mehmet Akif Ozdemir, Onan Guren, Ozlem Karabiber Cura, A. Akan, Aytuğ Onan","doi":"10.1109/TIPTEKNO50054.2020.9299260","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299260","url":null,"abstract":"The heart is the most critical organ for the sustainability of life. Arrhythmia is any irregularity of heart rate that causes an abnormality in your heart rhythm. Clinical analysis of Electrocardiogram (ECG) signals is not enough to quickly identify abnormalities in the heart rhythm. This paper proposes a deep learning method for the accurate detection of abnormal and normal heartbeats based on 2-D Convolutional Neural Network (CNN) architecture. Two channels of ECG signals were obtained from the MIT-BIH arrhythmia dataset. Each ECG signal is segmented into heartbeats, and each heartbeat is transformed into a 2-D grayscale heartbeat image as an input for CNN structure. Due to the success of image recognition, CNN architecture is utilized for binary classification of the 2-D image matrix. In this study, the effect of different CNN architectures is compared based on the classification rate. The accuracies of training and test data are found as 100.00% and 99.10%, respectively for the best CNN model. Experimental results demonstrate that CNN with ECG image representation yields the highest success rate for the binary classification of ECG beats compared to the traditional machine learning methods, and one-dimensional deep learning classifiers.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121051242","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}
Allografts and autografts are widely used to repair damaged hard tissue. Various limitations such as immune response, long recovery times, and loss of mechanical and biological properties are frequently encountered in the clinic as a result of using grafts. The regenerated tissue should be biomechanically durable and effective. 3D synthetic scaffolds help the cells create their own matrices and integrate into the host tissue with the implant degradation over time. $beta$-TCP has been the most preferred bioceramic in recent years due to its high osteocompatibility and high mechanical strength. Flexibility is also critical in clinical practice to facilitate the surgeon's desired shape of the graft material in the surgical area during the operation. Shaping the graft material in the surgical field during the procedure prolongs the surgical time and increases the probability of infection. Ideal synthetic bone grafts should increase the adhesion and osteogenesis of bone cells while being degraded with body fluids. A certain concentrations of silicate additive have been shown in studies that increase bone regeneration capacity and increase osteogenesis. Within the scope of this study, osteoconductive $beta$-TCP and osteoinductive silicate additive tissue scaffolds were prepared by mixing with PLA in order to provide flexibility and mimic the extracellular matrix. After testing the biocompatibility of the scaffolds produced in vitro, mouse fibroblast cell was used to examine the effect on stem cell differentiation. For this purpose, cells were cultured into the produced scaffolds and the analysis of proliferation and viability of cells were done by using MTT assay and live and dead analysis.
{"title":"Proliferation and Viability of L929 Cells in Synthetic Flexible Bone Grafts","authors":"İlker Gürgi̇t, Oğuzhan Gökmen, Aybike Kocatürkmen, Ilayda Namli, Günnur Onak, O. Karaman","doi":"10.1109/TIPTEKNO50054.2020.9299280","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299280","url":null,"abstract":"Allografts and autografts are widely used to repair damaged hard tissue. Various limitations such as immune response, long recovery times, and loss of mechanical and biological properties are frequently encountered in the clinic as a result of using grafts. The regenerated tissue should be biomechanically durable and effective. 3D synthetic scaffolds help the cells create their own matrices and integrate into the host tissue with the implant degradation over time. $beta$-TCP has been the most preferred bioceramic in recent years due to its high osteocompatibility and high mechanical strength. Flexibility is also critical in clinical practice to facilitate the surgeon's desired shape of the graft material in the surgical area during the operation. Shaping the graft material in the surgical field during the procedure prolongs the surgical time and increases the probability of infection. Ideal synthetic bone grafts should increase the adhesion and osteogenesis of bone cells while being degraded with body fluids. A certain concentrations of silicate additive have been shown in studies that increase bone regeneration capacity and increase osteogenesis. Within the scope of this study, osteoconductive $beta$-TCP and osteoinductive silicate additive tissue scaffolds were prepared by mixing with PLA in order to provide flexibility and mimic the extracellular matrix. After testing the biocompatibility of the scaffolds produced in vitro, mouse fibroblast cell was used to examine the effect on stem cell differentiation. For this purpose, cells were cultured into the produced scaffolds and the analysis of proliferation and viability of cells were done by using MTT assay and live and dead analysis.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129485524","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}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299281
Omer Lutfu Tortumlu, Hamza Osman Ilhan
The diagnosis of male factor based infertility is performed by the evaluation of semen specimens in laboratories. Semen samples are investigated in terms of sperm concentration, morphology and motility. These investigations are generally performed manually by experts using microscopes instead of using computer based systems due to their high costs. However, manual observation also known as Visual Assessment (VA), has demonstrated significant subjectivity, including intra-observer and inter-laboratory variations. In this study, two CNN models especially for the possible usage in mobile platforms have been tested in the sperm morphology classification problem to eliminate the human factor in the analysis. In the analysis, three well-known sperm morphology data sets namely, HuSHeM, SMIDS and SCIAN-Morpho have been employed. Due to the data imbalance and scarcity problem of the utilized data sets, data augmentation and epoch analysis are also presented.
{"title":"The Analysis of Mobile Platform based CNN Networks in the Classification of Sperm Morphology","authors":"Omer Lutfu Tortumlu, Hamza Osman Ilhan","doi":"10.1109/TIPTEKNO50054.2020.9299281","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299281","url":null,"abstract":"The diagnosis of male factor based infertility is performed by the evaluation of semen specimens in laboratories. Semen samples are investigated in terms of sperm concentration, morphology and motility. These investigations are generally performed manually by experts using microscopes instead of using computer based systems due to their high costs. However, manual observation also known as Visual Assessment (VA), has demonstrated significant subjectivity, including intra-observer and inter-laboratory variations. In this study, two CNN models especially for the possible usage in mobile platforms have been tested in the sperm morphology classification problem to eliminate the human factor in the analysis. In the analysis, three well-known sperm morphology data sets namely, HuSHeM, SMIDS and SCIAN-Morpho have been employed. Due to the data imbalance and scarcity problem of the utilized data sets, data augmentation and epoch analysis are also presented.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134011004","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}
Pub Date : 2020-11-19DOI: 10.1109/TIPTEKNO50054.2020.9299242
Mahdieh Farzin Asanjan, V. Purutçuoğlu, F. Arı, D. Gökçay
The missing data problem is one of the main challenges in many datasets. As long as the percentage of loss is under an acceptable range, different methods can be performed in order to fill these unobserved values. In this study the thresholding method, polynomial regression approach, smoothing splines, piecewise linear interpolation and the moving median approaches are used in order to fill the missing data. Among these alternatives, the smoothing spline method typically gives higher accuracy and captures the global feature of the data, whereas, it can eliminate the local changes in the measurements while smoothing. Hereby, in this study, we propose some alternative approaches, called normal ratio and normal ratio weighted with correlation together with modified moving median method in order to fill the missing data. These novel methods are previously applied in meteorological studies where the location of the missing values in a time-course dataset is important.
{"title":"Comparison of Data Interpolation Methods in Time Course Pupil Diameter Data","authors":"Mahdieh Farzin Asanjan, V. Purutçuoğlu, F. Arı, D. Gökçay","doi":"10.1109/TIPTEKNO50054.2020.9299242","DOIUrl":"https://doi.org/10.1109/TIPTEKNO50054.2020.9299242","url":null,"abstract":"The missing data problem is one of the main challenges in many datasets. As long as the percentage of loss is under an acceptable range, different methods can be performed in order to fill these unobserved values. In this study the thresholding method, polynomial regression approach, smoothing splines, piecewise linear interpolation and the moving median approaches are used in order to fill the missing data. Among these alternatives, the smoothing spline method typically gives higher accuracy and captures the global feature of the data, whereas, it can eliminate the local changes in the measurements while smoothing. Hereby, in this study, we propose some alternative approaches, called normal ratio and normal ratio weighted with correlation together with modified moving median method in order to fill the missing data. These novel methods are previously applied in meteorological studies where the location of the missing values in a time-course dataset is important.","PeriodicalId":426945,"journal":{"name":"2020 Medical Technologies Congress (TIPTEKNO)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132736423","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：