Pub Date : 2020-10-05DOI: 10.1109/SIU49456.2020.9302277
Furkan Muhammed Taydaş, G. Bozdag, H. Yiğit, H. Aniktar
In this study, a mechanically tunable pyramidal horn antenna operating in 3.5 - 5.9 GHz frequency range is designed. The antenna is modeled and numerically analysied by using CST MWS software. The designed antenna is prototyped very fast by employing a novel additive manufacturing technique. Simulated and measured S11 results of the antenna are compared and highly consistent results are obtained. Additionaly, analytical and simuated results for the radiation chracteristics of the antenna are in a very good agreement.
{"title":"Additively Manufactured Mechanically Tunable Horn Antenna Design","authors":"Furkan Muhammed Taydaş, G. Bozdag, H. Yiğit, H. Aniktar","doi":"10.1109/SIU49456.2020.9302277","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302277","url":null,"abstract":"In this study, a mechanically tunable pyramidal horn antenna operating in 3.5 - 5.9 GHz frequency range is designed. The antenna is modeled and numerically analysied by using CST MWS software. The designed antenna is prototyped very fast by employing a novel additive manufacturing technique. Simulated and measured S11 results of the antenna are compared and highly consistent results are obtained. Additionaly, analytical and simuated results for the radiation chracteristics of the antenna are in a very good agreement.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123652568","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302319
Erdi Kaya, Elif Haytaoglu, Suayb S. Arslan
In this paper, centralized and independent repair approaches based on device-to-device communication for the repair of the lost nodes have been investigated in a cellular network where distributed caching is applied whose fault tolerance is provided by erasure codes. The caching mechanisms based on Reed-Solomon codes and minimum bandwidth regenerating codes are adopted. The proposed approaches are analyzed in a simulation environment in terms of base station utilization load during the repair process. Based on the intuitive assumption that the base station is usually more costly than device-to-device communication, the centralized repair approach demonstrates a better performance than the independent repair approaches on the number of symbols retrieved from the base station. On the other hand, the centralized approach has not achieved a dramatic reduction in the number of symbols downloaded from the other devices. Keywords—distributed systems, caching, device-to-device communication, erasure codes.
{"title":"Data Repair in BS-assisted Distributed Data Caching","authors":"Erdi Kaya, Elif Haytaoglu, Suayb S. Arslan","doi":"10.1109/SIU49456.2020.9302319","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302319","url":null,"abstract":"In this paper, centralized and independent repair approaches based on device-to-device communication for the repair of the lost nodes have been investigated in a cellular network where distributed caching is applied whose fault tolerance is provided by erasure codes. The caching mechanisms based on Reed-Solomon codes and minimum bandwidth regenerating codes are adopted. The proposed approaches are analyzed in a simulation environment in terms of base station utilization load during the repair process. Based on the intuitive assumption that the base station is usually more costly than device-to-device communication, the centralized repair approach demonstrates a better performance than the independent repair approaches on the number of symbols retrieved from the base station. On the other hand, the centralized approach has not achieved a dramatic reduction in the number of symbols downloaded from the other devices. Keywords—distributed systems, caching, device-to-device communication, erasure codes.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121172829","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302514
Serkan Cizmeciogullari, M. Koçak, S. Mihçin, A. Tosun, A. Akan
One of the methods used in upper extremity function assessment is the Range of Motion (ROM) measurements. In practice, these measurements are performed by a clinicians' personal observations and/or goniometric measurements. In these measurements, there are some problems related to repeatibility and reliability criterias. In this study, a novel system which contains only a single camera to perform ROM calculations objectively in upper extremity is suggested. For this purpose shoulder and elbow flexion movements were recorded and analyzed. The system was compared with which was known as a “Gold Standard” system. The nine male and nine female volunteers were participated in the study. Kinect camera was used to record movements of upper limb. The Kinect camera results were compared with that of OptiTrack camera system. The shoulder and elbow flexion angles were computed for both systems. The agreement between the two systems were examined statistically by using the computed ROM values. Bland-Altman plots revealed the agreement within 95 % interval of confidence, between the two systems for shoulder flexion and elbow flexion in both males and females. This study provides evidence for the suitability of the proposed system for a clinical work.
{"title":"Design of a New System for Upper Extremity Movement Ability Assessment","authors":"Serkan Cizmeciogullari, M. Koçak, S. Mihçin, A. Tosun, A. Akan","doi":"10.1109/SIU49456.2020.9302514","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302514","url":null,"abstract":"One of the methods used in upper extremity function assessment is the Range of Motion (ROM) measurements. In practice, these measurements are performed by a clinicians' personal observations and/or goniometric measurements. In these measurements, there are some problems related to repeatibility and reliability criterias. In this study, a novel system which contains only a single camera to perform ROM calculations objectively in upper extremity is suggested. For this purpose shoulder and elbow flexion movements were recorded and analyzed. The system was compared with which was known as a “Gold Standard” system. The nine male and nine female volunteers were participated in the study. Kinect camera was used to record movements of upper limb. The Kinect camera results were compared with that of OptiTrack camera system. The shoulder and elbow flexion angles were computed for both systems. The agreement between the two systems were examined statistically by using the computed ROM values. Bland-Altman plots revealed the agreement within 95 % interval of confidence, between the two systems for shoulder flexion and elbow flexion in both males and females. This study provides evidence for the suitability of the proposed system for a clinical work.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"398 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114087911","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302273
H. Boz, Mert Gürkan, B. Yanikoglu
Biometrics based keystroke dynamics aim to perform user identification and authentication based on users' typing behaviour on digital devices. In this study, keystroke timing and regional distributions extracted from free-text are utilized to perform user identification. In order to obtain the highest representative set of attributes, attributes based on directional graph, hold time and keyboard distance have been extracted and used in different configurations. In order to process the generated feature sets more effectively, unlike the existing studies, a multilayer artificial neural network model with attention mechanism was used and 0.13% FAR and 2.5% FRR results were obtained.
{"title":"Keystroke Dynamics Based Biometric Identification","authors":"H. Boz, Mert Gürkan, B. Yanikoglu","doi":"10.1109/SIU49456.2020.9302273","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302273","url":null,"abstract":"Biometrics based keystroke dynamics aim to perform user identification and authentication based on users' typing behaviour on digital devices. In this study, keystroke timing and regional distributions extracted from free-text are utilized to perform user identification. In order to obtain the highest representative set of attributes, attributes based on directional graph, hold time and keyboard distance have been extracted and used in different configurations. In order to process the generated feature sets more effectively, unlike the existing studies, a multilayer artificial neural network model with attention mechanism was used and 0.13% FAR and 2.5% FRR results were obtained.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116333065","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302148
Ozan Alp Topal, Günes Karabulut-Kurt
The main motivation behind the covert communication is hiding the very existence of a communication between two users. In this work, we study the covert communication performance in non-orthogonal multiple access (NOMA) networks with amplify-and-forward (AF) relaying. In the considered system model, the relay aims at detecting the covert transmission, while the transmitter hides the covert transmission by mixing the covert message with an open message for another user. We study the covert communication performance under different qualityof-service (QoS) and detection error probability requirements. The presented numerical results indicate the effect of covertness requirement to the considered system performance.
{"title":"Covert Communication in Cooperative NOMA Networks","authors":"Ozan Alp Topal, Günes Karabulut-Kurt","doi":"10.1109/SIU49456.2020.9302148","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302148","url":null,"abstract":"The main motivation behind the covert communication is hiding the very existence of a communication between two users. In this work, we study the covert communication performance in non-orthogonal multiple access (NOMA) networks with amplify-and-forward (AF) relaying. In the considered system model, the relay aims at detecting the covert transmission, while the transmitter hides the covert transmission by mixing the covert message with an open message for another user. We study the covert communication performance under different qualityof-service (QoS) and detection error probability requirements. The presented numerical results indicate the effect of covertness requirement to the considered system performance.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116489393","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302077
Hüseyin Efe Öztufan, Göktuğ Yıldırım, E. Arisoy
The main purpose of this study is to automatically highlight important regions of lecture video subtitles. Even though watching videos is an effective way of learning, the main disadvantage of video-based education is limited interaction between the learner and the video. With the developed system, important regions that are automatically determined in lecture subtitles will be highlighted with the aim of increasing the learner’s attention to these regions. In this paper first the lecture videos are converted into text by using an automatic speech recognition system. Then continuous space representations for sentences or word sequences in the transcriptions are generated using Bidirectional Encoder Representations from Transformers (BERT). Important regions of the subtitles are selected using a clustering method based on the similarity of these representations. The developed system is applied to the lecture videos and it is found that using word sequence representations in determining the important regions of subtitles gives higher performance than using sentence representations. This result is encouraging in terms of automatic highlighting of speech recognition outputs where sentence boundaries are not defined explicitly.
{"title":"Highlighting of Lecture Video Closed Captions","authors":"Hüseyin Efe Öztufan, Göktuğ Yıldırım, E. Arisoy","doi":"10.1109/SIU49456.2020.9302077","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302077","url":null,"abstract":"The main purpose of this study is to automatically highlight important regions of lecture video subtitles. Even though watching videos is an effective way of learning, the main disadvantage of video-based education is limited interaction between the learner and the video. With the developed system, important regions that are automatically determined in lecture subtitles will be highlighted with the aim of increasing the learner’s attention to these regions. In this paper first the lecture videos are converted into text by using an automatic speech recognition system. Then continuous space representations for sentences or word sequences in the transcriptions are generated using Bidirectional Encoder Representations from Transformers (BERT). Important regions of the subtitles are selected using a clustering method based on the similarity of these representations. The developed system is applied to the lecture videos and it is found that using word sequence representations in determining the important regions of subtitles gives higher performance than using sentence representations. This result is encouraging in terms of automatic highlighting of speech recognition outputs where sentence boundaries are not defined explicitly.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124364568","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302184
B. Bolat, Mehmet Oğuz Kelek
In this study, made from observations in 4 different locations in Doha, the first location is close to the education campus with an open and flat area, the second location is the trade zone, the third location is a region with high buildings near the city center, and the fourth location is selected as the factory and workshop area. Three different algorithms, Bayes Based Analysis, Largest Sense Estimation, and Naive Bayes classifier, were used to estimate and predict spectrum usage on a data set, with 1 minute observation for each location, with a total of 4320 different readings in the 700 - 3000 MHz spectrum. The optimum solution was sought for the prediction and estimation of its use. After the optimum method was chosen, the relationship of the chosen method with the past and previous situations was examined. As a result of these algorithms, Bayes Based algorithm was chosen as the most suitable algorithm and performance was measured as %88:94.
{"title":"Spectrum Usage Estimating and Predicting","authors":"B. Bolat, Mehmet Oğuz Kelek","doi":"10.1109/SIU49456.2020.9302184","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302184","url":null,"abstract":"In this study, made from observations in 4 different locations in Doha, the first location is close to the education campus with an open and flat area, the second location is the trade zone, the third location is a region with high buildings near the city center, and the fourth location is selected as the factory and workshop area. Three different algorithms, Bayes Based Analysis, Largest Sense Estimation, and Naive Bayes classifier, were used to estimate and predict spectrum usage on a data set, with 1 minute observation for each location, with a total of 4320 different readings in the 700 - 3000 MHz spectrum. The optimum solution was sought for the prediction and estimation of its use. After the optimum method was chosen, the relationship of the chosen method with the past and previous situations was examined. As a result of these algorithms, Bayes Based algorithm was chosen as the most suitable algorithm and performance was measured as %88:94.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124087865","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302282
Bulut Kuskonmaz, H. Özkan, Ö. Gürbüz
In wireless networks, clients can be steered from one access point (AP) to another for a better internet connection. Although this client steering has large potential to improve overall network service and the user experience, such steering actions may not always yield the desired result and the client may remain persistently connected to its current AP. This issue is referred to as the sticky client problem, which prevents the intended improvement in the network. In this work, in order to address the sticky client problem, Support Vector Machine (SVM) as a batch method and kernel perceptron as an online method are examined based on various network features. Nonlinear classifiers of correct steering actions have been trained to maximize the accuracy of steering actions. In particular, the online kernel perceptron performs sequential learning at APs using the cloud data to decide about steering actions in real time. This algorithm is data-driven, and able to provide optimum steering in realtime. In our experiments, we observed that our batch approach identifies successful steering actions with %95 accuracy. On the other hand, our online algorithm is able to approximate the batch performance by a small margin while allowing real time steering with significantly lower computational complexity.
{"title":"Smart Steering with Machine Learning for Wireless Mesh Networks","authors":"Bulut Kuskonmaz, H. Özkan, Ö. Gürbüz","doi":"10.1109/SIU49456.2020.9302282","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302282","url":null,"abstract":"In wireless networks, clients can be steered from one access point (AP) to another for a better internet connection. Although this client steering has large potential to improve overall network service and the user experience, such steering actions may not always yield the desired result and the client may remain persistently connected to its current AP. This issue is referred to as the sticky client problem, which prevents the intended improvement in the network. In this work, in order to address the sticky client problem, Support Vector Machine (SVM) as a batch method and kernel perceptron as an online method are examined based on various network features. Nonlinear classifiers of correct steering actions have been trained to maximize the accuracy of steering actions. In particular, the online kernel perceptron performs sequential learning at APs using the cloud data to decide about steering actions in real time. This algorithm is data-driven, and able to provide optimum steering in realtime. In our experiments, we observed that our batch approach identifies successful steering actions with %95 accuracy. On the other hand, our online algorithm is able to approximate the batch performance by a small margin while allowing real time steering with significantly lower computational complexity.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126497164","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302506
Ezgi Paket, Kadir Ozlem, Hend Elmoughni, A. Atalay, O. Atalay, G. Ince
CardioVascular Diseases (CVDs) have a significant share over all medical problems. From this point of view, many studies have been conducted on heart diseases and different heartbeat monitoring systems have been developed. Although Electro-CardioGraphy (ECG) is the most widely used technique among other monitoring systems, ECG measurement with conventional electrodes have also many disadvantages that can be overcome if replaced with textile electrodes. This study involves creation of textile based ECG electrodes, related circuitry designs, signal processing, implementations of peak detection and heart rate calculation algorithms and finally, a real time ECG monitoring application. Moreover, Beat Per Minute (BPM) calculation and comparison of these values with existing ECG devices have been investigated.
{"title":"ECG Monitoring System Using Textile Electrodes","authors":"Ezgi Paket, Kadir Ozlem, Hend Elmoughni, A. Atalay, O. Atalay, G. Ince","doi":"10.1109/SIU49456.2020.9302506","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302506","url":null,"abstract":"CardioVascular Diseases (CVDs) have a significant share over all medical problems. From this point of view, many studies have been conducted on heart diseases and different heartbeat monitoring systems have been developed. Although Electro-CardioGraphy (ECG) is the most widely used technique among other monitoring systems, ECG measurement with conventional electrodes have also many disadvantages that can be overcome if replaced with textile electrodes. This study involves creation of textile based ECG electrodes, related circuitry designs, signal processing, implementations of peak detection and heart rate calculation algorithms and finally, a real time ECG monitoring application. Moreover, Beat Per Minute (BPM) calculation and comparison of these values with existing ECG devices have been investigated.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128117052","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 : 2020-10-05DOI: 10.1109/SIU49456.2020.9302443
Gözde Ayse Tataroglu, G. Ozbulak, Kazim Kivanç Eren
Analysis of genetic variants is important for the detection of diseases associated with a variant. Detection of changes in the genetic variant is important for accurate diagnosis of the disease and appropriate solutions. One of the biggest problems in the classification of variants is the reliability of the data sets that will be presented as an input to modeling for the classification of variants. In this study, a system design based on machine learning, which determines the reliability of variants to be introduced to a variant scoring model, is proposed. Thus, it is aimed to provide more reliable training data for variant scoring systems. Shapley Additive Explanation (SHAP) method has been used to determine the most effective ones. In the experiments carried out on ClinVar, one of the data sets where this problem was observed, classifiers were created for the detection of contradictory situations by using Support Vector Machines (SVMs) and Gradient Boosting Trees (XGBoost) methods. In this study, 157 features were reduced to 41 attributes in SVM modeling and 13 attributes in XGBoost modeling for the detection of contradictory situations, and results were very close to the performance rates obtained with all attributes. Keywords—Variant Conflicting Detection, SHAP, Machine Learning Interpretability, SVM, XGBoost.
{"title":"Determination of the Genetic Variant Reliability Using SHAP Approach","authors":"Gözde Ayse Tataroglu, G. Ozbulak, Kazim Kivanç Eren","doi":"10.1109/SIU49456.2020.9302443","DOIUrl":"https://doi.org/10.1109/SIU49456.2020.9302443","url":null,"abstract":"Analysis of genetic variants is important for the detection of diseases associated with a variant. Detection of changes in the genetic variant is important for accurate diagnosis of the disease and appropriate solutions. One of the biggest problems in the classification of variants is the reliability of the data sets that will be presented as an input to modeling for the classification of variants. In this study, a system design based on machine learning, which determines the reliability of variants to be introduced to a variant scoring model, is proposed. Thus, it is aimed to provide more reliable training data for variant scoring systems. Shapley Additive Explanation (SHAP) method has been used to determine the most effective ones. In the experiments carried out on ClinVar, one of the data sets where this problem was observed, classifiers were created for the detection of contradictory situations by using Support Vector Machines (SVMs) and Gradient Boosting Trees (XGBoost) methods. In this study, 157 features were reduced to 41 attributes in SVM modeling and 13 attributes in XGBoost modeling for the detection of contradictory situations, and results were very close to the performance rates obtained with all attributes. Keywords—Variant Conflicting Detection, SHAP, Machine Learning Interpretability, SVM, XGBoost.","PeriodicalId":312627,"journal":{"name":"2020 28th Signal Processing and Communications Applications Conference (SIU)","volume":"72 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125634596","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：