Mammogram is the best way of breast cancer detection nowadays, as breast cancer is the most common form of cancer in the female gender and this form of cancer usually causes death. Many scientists, doctors, and engineers are working together to deal with such serious issues in human life. This paper, it is aimed to develop a new computer-aided system with a graphical coded language to detect abnormalities in mammogram images by using machine learning technics such as ANN and SVM. The developed algorithm has a graphical user interface (GUI) and all results are shown in there. The algorithm was created using three different stages. These are image processing and mass segmentation, feature selection and extraction, and classification. To test the accuracy of the system as the sensitivity, specificity, and accuracy, mammogram images with forty benign and forty malignant masses were used. The obtained results for measuring the sensitivity, specificity, and accuracy are 95%, 97.5%, and 96.25% for ANN and 97.5%, 97.5, and 97.5 for SVM, respectively. As can be said that the algorithm, user-friendly due to its user interface, can be preferred because it can detect many cancerous cells such as breast cancer with high accuracy.
乳房 X 线照相术是当今检测乳腺癌的最佳方法，因为乳腺癌是女性最常见的癌症，而且这种癌症通常会导致死亡。许多科学家、医生和工程师都在共同努力解决人类生活中的这一严重问题。本文旨在开发一种新的计算机辅助系统，该系统采用图形化编码语言，利用机器学习技术（如 ANN 和 SVM）检测乳房 X 光图像中的异常情况。所开发的算法具有图形用户界面（GUI），所有结果都显示在图形用户界面上。该算法通过三个不同阶段创建。这三个阶段分别是图像处理和大规模分割、特征选择和提取以及分类。为了测试系统的灵敏度、特异性和准确性，使用了包含 40 个良性肿块和 40 个恶性肿块的乳房 X 光图像。结果显示，ANN 的灵敏度、特异度和准确度分别为 95%、97.5% 和 96.25%，SVM 的灵敏度、特异度和准确度分别为 97.5%、97.5% 和 97.5%。可以说，该算法的用户界面非常友好，能以较高的准确率检测出乳腺癌等多种癌细胞，因此值得优先考虑。
{"title":"The Design of Machine Learning-Based Computer-Aided System with LabVIEW For Abnormalities in Mammogram Images","authors":"İman Hamadamin, Hasan Güler","doi":"10.55525/tjst.1424371","DOIUrl":"https://doi.org/10.55525/tjst.1424371","url":null,"abstract":"Mammogram is the best way of breast cancer detection nowadays, as breast cancer is the most common form of cancer in the female gender and this form of cancer usually causes death. Many scientists, doctors, and engineers are working together to deal with such serious issues in human life. This paper, it is aimed to develop a new computer-aided system with a graphical coded language to detect abnormalities in mammogram images by using machine learning technics such as ANN and SVM. The developed algorithm has a graphical user interface (GUI) and all results are shown in there. The algorithm was created using three different stages. These are image processing and mass segmentation, feature selection and extraction, and classification. To test the accuracy of the system as the sensitivity, specificity, and accuracy, mammogram images with forty benign and forty malignant masses were used. The obtained results for measuring the sensitivity, specificity, and accuracy are 95%, 97.5%, and 96.25% for ANN and 97.5%, 97.5, and 97.5 for SVM, respectively. As can be said that the algorithm, user-friendly due to its user interface, can be preferred because it can detect many cancerous cells such as breast cancer with high accuracy.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140991823","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}
Image compression is fundamental to the efficient and cost-effective use of digital media, including but not limited to medical imagery, satellite images, and daily photography. Wavelet transform is one of the best methods used in compression. This study conducts a meticulous comparative analysis of various established wavelet families and introduces a novel wavelet named nwi, shedding light on its performance compared to well-established counterparts. This research conducts a meticulous comparative analysis of various wavelet families to assess their performance in image compression. Leveraging quantitative metrics such as Compression Ratio (CR) and Peak Signal-to-Noise Ratio (PSNR), extensive data presented in tables and figures provides a comprehensive overview of the effectiveness of different Wavelet transforms. The results show that an average compression ratio of around 75% can be achieved with a 38 dB PSNR value for all test images. The best result was achieved with the test-2 image from the proposed nwi wavelet. The research evaluates eight wavelet families and shows that the performance of image compression depends on both image type and selected wavelet family while keeping the coding algorithm the same for all calculations of image processing scenarios. This systematic exploration contributes valuable insights to the field, aiding practitioners in selecting optimal Wavelet transforms for diverse image processing applications. In image compression, the introduction of new wavelet families, such as the nwi, has the potential to enhance performance and achieve better results.
{"title":"Comparative Analysis of Wavelet Families in Image Compression, Featuring the Proposed New Wavelet","authors":"İbrahim Öz","doi":"10.55525/tjst.1428424","DOIUrl":"https://doi.org/10.55525/tjst.1428424","url":null,"abstract":"Image compression is fundamental to the efficient and cost-effective use of digital media, including but not limited to medical imagery, satellite images, and daily photography. Wavelet transform is one of the best methods used in compression. This study conducts a meticulous comparative analysis of various established wavelet families and introduces a novel wavelet named nwi, shedding light on its performance compared to well-established counterparts. This research conducts a meticulous comparative analysis of various wavelet families to assess their performance in image compression. Leveraging quantitative metrics such as Compression Ratio (CR) and Peak Signal-to-Noise Ratio (PSNR), extensive data presented in tables and figures provides a comprehensive overview of the effectiveness of different Wavelet transforms. The results show that an average compression ratio of around 75% can be achieved with a 38 dB PSNR value for all test images. The best result was achieved with the test-2 image from the proposed nwi wavelet. The research evaluates eight wavelet families and shows that the performance of image compression depends on both image type and selected wavelet family while keeping the coding algorithm the same for all calculations of image processing scenarios. This systematic exploration contributes valuable insights to the field, aiding practitioners in selecting optimal Wavelet transforms for diverse image processing applications. In image compression, the introduction of new wavelet families, such as the nwi, has the potential to enhance performance and achieve better results.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140371678","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}
In this work, mapping diversity technique is exploited for generalized spatial modulation. In this context, multiple constellations, obtained as the solution of the optimization problem that maximizes Euclidean distance between the elements of the signal set, are employed in the active transmit antennas of generalized spatial modulation scheme. Supported with analytical analysis and simulation results, the proposed scheme is shown to enhance the error rate performance of conventional generalized spatial modulation.
{"title":"Improved Spatial Modulation with Mapping Diversity","authors":"Mümtaz Yılmaz","doi":"10.55525/tjst.1334701","DOIUrl":"https://doi.org/10.55525/tjst.1334701","url":null,"abstract":"In this work, mapping diversity technique is exploited for generalized spatial modulation. In this context, multiple constellations, obtained as the solution of the optimization problem that maximizes Euclidean distance between the elements of the signal set, are employed in the active transmit antennas of generalized spatial modulation scheme. Supported with analytical analysis and simulation results, the proposed scheme is shown to enhance the error rate performance of conventional generalized spatial modulation.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140373756","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}
In this study, the Bauschringer Effect (BE) resulting from tension-compression deformation applied to nanowires obtained by placing Cu atoms in , and highly symmetric crystallographic directions was investigated using the Molecular Dynamics (MD) simulation method. The forces between atoms were determined from the gradient of the Embedded Atom Method (EAM) potential function, which includes many-body interactions. It was determined that there is an asymmetry between the stress-strain curves obtained as a result of the tension and compression deformation process applied to the model system. From this asymmetry, it was determined that the yield stress obtained in the drawing process for nanowire with crystallographic orientation was greater than the yield strain obtained as a result of the compression process. In contrast, the opposite was found for nanowires with crystallographic orientation and . In addition, after the yield strain value is exceeded as a result of the drawing process applied to the model nanowire system, compression deformation process was applied at different pre-strain values. The existence of the Bauschinger Effect (BE), which is expressed as the yield strength value as a result of forward loading corresponding to the tension operation, is smaller than the yield value obtained as a result of the compression process in which the loading is removed, was determined. To clarify the effect of BE on Cu nanowires with different crystallographic orientations, Bauschinger Stress parameter (BSP) and Bauschinger Parameter (BP) values were calculated.
本研究采用分子动力学（MD）模拟方法，研究了通过将铜原子置于Ⅴ和高度对称的晶体学方向上而获得的纳米线所产生的拉伸-压缩变形所导致的鲍施林格效应（BE）。原子间的作用力由嵌入式原子法（EAM）势函数的梯度确定，其中包括多体相互作用。结果表明，模型系统在拉伸和压缩变形过程中获得的应力-应变曲线不对称。根据这种不对称性，可以确定具有晶体取向的纳米线在拉伸过程中获得的屈服应力大于压缩过程中获得的屈服应变。此外，在对模型纳米线系统进行拉伸过程而超过屈服应变值后，以不同的预应变值进行压缩变形过程。鲍辛格效应（Bauschinger Effect，BE）是指在拉伸过程中向前加载时的屈服强度值小于在压缩过程中去除加载后的屈服强度值。为了明确 BE 对不同晶体取向的铜纳米线的影响，计算了鲍辛格应力参数 (BSP) 和鲍辛格参数 (BP) 值。
{"title":"Molecular Dynamics Simulation of Bauschinger Effect in Cu Nanowire with Different Crystallographic Orientation","authors":"S. Kazanç, Canan Aksu Canbay","doi":"10.55525/tjst.1358465","DOIUrl":"https://doi.org/10.55525/tjst.1358465","url":null,"abstract":"In this study, the Bauschringer Effect (BE) resulting from tension-compression deformation applied to nanowires obtained by placing Cu atoms in , and highly symmetric crystallographic directions was investigated using the Molecular Dynamics (MD) simulation method. The forces between atoms were determined from the gradient of the Embedded Atom Method (EAM) potential function, which includes many-body interactions. It was determined that there is an asymmetry between the stress-strain curves obtained as a result of the tension and compression deformation process applied to the model system. From this asymmetry, it was determined that the yield stress obtained in the drawing process for nanowire with crystallographic orientation was greater than the yield strain obtained as a result of the compression process. In contrast, the opposite was found for nanowires with crystallographic orientation and . In addition, after the yield strain value is exceeded as a result of the drawing process applied to the model nanowire system, compression deformation process was applied at different pre-strain values. The existence of the Bauschinger Effect (BE), which is expressed as the yield strength value as a result of forward loading corresponding to the tension operation, is smaller than the yield value obtained as a result of the compression process in which the loading is removed, was determined. To clarify the effect of BE on Cu nanowires with different crystallographic orientations, Bauschinger Stress parameter (BSP) and Bauschinger Parameter (BP) values were calculated.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140376601","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}
Purpose: This study aims to prepare a double-network hydrogels as hybrid networks bearing both natural and synthetic polymers to obtain scaffolds with increased swelling capacity and tunable mechanical and morphological properties. Physically cross-linked alginate hydrogel was reinforced with various ratios of Poly(ethylene glycol) (PEG) polymers which were chemically gellated via UV light exposure with a water soluble initiator. Method: The synthesis methodology involves a sequential crosslinking approach by carefully controlling the reaction parameters to achieve a hybrid structure to mimic the natural tissue extracellular matrix. Physicochemical properties of the resulting hydrogels were systematically investigated via Fourier-transform infrared spectroscopy (FT-IR) for chemical composition and Scanning Electron Microscopy (SEM) for their morphological features like porosity. Furthermore, the effect of PEG amount in the final hydrogel (10, 20 and 40%) on the swelling capacity was evaluated as well as the rheological properties. Results: Prepared double-network hydrogels were demonstrated to be composed of both natural alginate polymer and synthetic PEG chains in FT-IR spectrum. Although 10%PEG containing hydrogel was not significantly different in terms of swelling capacity from the alginate hydrogel alone, increasing PEG amount has an ameliorating effect. Comparative reological studies presented that introducing covalently cross-linked PEG network into alginate one increased crosspoint of storage and loss moduli almost 12 times more providing a stiffer scaffold. Also, increasing PEG content decreased the pore size on SEM images, indicating more crosslinking points in final hydrogel structure. Conclusion: Hybrid double-network hydrogels were successfully prepared by introducing increasing amounts of dimethacrylated PEG chains into the physically cross-linked biocompatible alginate network. Known as its good water solubility, PEG chains were shown to have a better effect on the swelling capacity and mechanical properties of the final hydrogel, together with providing tunable pore size.
{"title":"Physicochemical Effects of PEG content in Alginate-based Double Network Hydrogels as Hybrid Scaffolds","authors":"Ozgul Gok","doi":"10.55525/tjst.1410187","DOIUrl":"https://doi.org/10.55525/tjst.1410187","url":null,"abstract":"Purpose: This study aims to prepare a double-network hydrogels as hybrid networks bearing both natural and synthetic polymers to obtain scaffolds with increased swelling capacity and tunable mechanical and morphological properties. Physically cross-linked alginate hydrogel was reinforced with various ratios of Poly(ethylene glycol) (PEG) polymers which were chemically gellated via UV light exposure with a water soluble initiator. \u0000 \u0000Method: The synthesis methodology involves a sequential crosslinking approach by carefully controlling the reaction parameters to achieve a hybrid structure to mimic the natural tissue extracellular matrix. Physicochemical properties of the resulting hydrogels were systematically investigated via Fourier-transform infrared spectroscopy (FT-IR) for chemical composition and Scanning Electron Microscopy (SEM) for their morphological features like porosity. Furthermore, the effect of PEG amount in the final hydrogel (10, 20 and 40%) on the swelling capacity was evaluated as well as the rheological properties. \u0000 \u0000Results: Prepared double-network hydrogels were demonstrated to be composed of both natural alginate polymer and synthetic PEG chains in FT-IR spectrum. Although 10%PEG containing hydrogel was not significantly different in terms of swelling capacity from the alginate hydrogel alone, increasing PEG amount has an ameliorating effect. Comparative reological studies presented that introducing covalently cross-linked PEG network into alginate one increased crosspoint of storage and loss moduli almost 12 times more providing a stiffer scaffold. Also, increasing PEG content decreased the pore size on SEM images, indicating more crosslinking points in final hydrogel structure. \u0000 \u0000Conclusion: Hybrid double-network hydrogels were successfully prepared by introducing increasing amounts of dimethacrylated PEG chains into the physically cross-linked biocompatible alginate network. Known as its good water solubility, PEG chains were shown to have a better effect on the swelling capacity and mechanical properties of the final hydrogel, together with providing tunable pore size.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140380247","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}
İki çeşit kayısı örnekleri farklı daldırma sürelerinde çeşitli Sodyum metabisülfit konsantrasyonlarında kükürtlendi. Taze ve açık havada bir hafta kurutulmuş kayısı örneklerinin kükürt içerikleri daldırma süresinin fonksiyonu olarak belirlendi. İki çeşit kayısı örneklerinin kükürt içeriğine bağlı olarak K1, D2 ve E vitaminlerinin ve fitosterollerin değişimleri saptandı. Sodyum metabisülfit konsantrasyonunun ve daldırma süresinin artmasıyla K1, D2 ve E vitaminlerinin miktarlarının azaldığı gözlendi. Ayrıca, her iki kayısı örneklerinde de kükürt içeriğiyle fitosterol değişimleri arasında düzenli bir ilişkinin olmadığı gözlendi. Palmitik asit, miristik asit ve oleik asit gibi yağ asitleri bütün kayısını numunelerinde saptanırken, pamitoleik asit, stearik asit ve araşidonik asit bazı kayısı örneklerinde bulunmuştur
用不同浓度的焦亚硫酸钠和不同的浸泡时间对两个品种的杏样品进行硫化。测定了新鲜杏样品和干燥一周的杏样品的硫含量与浸泡时间的关系。测定了维生素 K1、D2 和 E 以及植物甾醇的变化与两个品种杏样品硫含量的函数关系。结果发现，维生素 K1、D2 和 E 的含量随着焦亚硫酸钠浓度和浸泡时间的增加而减少。同时还发现，硫含量与两种杏样品中植物甾醇的变化之间没有规律性的关系。在所有杏样品中发现了棕榈酸、肉豆蔻酸和油酸等脂肪酸，而在一些杏样品中发现了帕米托利克酸、硬脂酸和花生四烯酸。
{"title":"Vitamins, Phytosterols and Oil Acids in Sulphurized Apricots","authors":"F. Kamişli, N. G. Mutlu","doi":"10.55525/tjst.1356308","DOIUrl":"https://doi.org/10.55525/tjst.1356308","url":null,"abstract":"İki çeşit kayısı örnekleri farklı daldırma sürelerinde çeşitli Sodyum metabisülfit konsantrasyonlarında kükürtlendi. Taze ve açık havada bir hafta kurutulmuş kayısı örneklerinin kükürt içerikleri daldırma süresinin fonksiyonu olarak belirlendi. İki çeşit kayısı örneklerinin kükürt içeriğine bağlı olarak K1, D2 ve E vitaminlerinin ve fitosterollerin değişimleri saptandı. Sodyum metabisülfit konsantrasyonunun ve daldırma süresinin artmasıyla K1, D2 ve E vitaminlerinin miktarlarının azaldığı gözlendi. Ayrıca, her iki kayısı örneklerinde de kükürt içeriğiyle fitosterol değişimleri arasında düzenli bir ilişkinin olmadığı gözlendi. Palmitik asit, miristik asit ve oleik asit gibi yağ asitleri bütün kayısını numunelerinde saptanırken, pamitoleik asit, stearik asit ve araşidonik asit bazı kayısı örneklerinde bulunmuştur","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140378786","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}
With the developing technologies in the field of aviation, the transition to more electrical systems is increasing day by day. For this reason, research on the development of batteries has accelerated. Nowadays, Lithium ion (Li-ion) batteries are more widely preferred due to their energy-to-weight ratio and advantages such as having a lower self-discharge rate when not working compared to other battery technologies. Batteries produce energy as a result of chemical reactions and heat is released. The heat released negatively affects the battery's lifespan, charging/discharging time and battery output voltage. In order to see these negative effects and intervene in time, the battery must be modeled correctly. In this way, negative situations that may occur in the battery can be intervened at the right time without any incident. In this study, the unmanned aerial vehicle (UAV) is powered by Li-ion batteries. It is simulated in Matlab/Simulink environment using the electrical equivalent circuit. A detailed model is created, taking into account temperature, state of charge (SoC), cell dynamics and operating functions. To estimate state of health (SoH) of the battery, resistance values must be known. Resistance and capacity values in the equivalent circuit of the Li-ion battery are obtained with the help of the simulation model. The SoH of the Li-ion batteries can be accurately predicted with the results obtained.
{"title":"Detailed Analysis of Li-ion Batteries for Use in Unmanned Aerial Vehicles","authors":"Merve Nur Kaya, Zehra URAL BAYRAK","doi":"10.55525/tjst.1437348","DOIUrl":"https://doi.org/10.55525/tjst.1437348","url":null,"abstract":"With the developing technologies in the field of aviation, the transition to more electrical systems is increasing day by day. For this reason, research on the development of batteries has accelerated. Nowadays, Lithium ion (Li-ion) batteries are more widely preferred due to their energy-to-weight ratio and advantages such as having a lower self-discharge rate when not working compared to other battery technologies. Batteries produce energy as a result of chemical reactions and heat is released. The heat released negatively affects the battery's lifespan, charging/discharging time and battery output voltage. In order to see these negative effects and intervene in time, the battery must be modeled correctly. In this way, negative situations that may occur in the battery can be intervened at the right time without any incident. In this study, the unmanned aerial vehicle (UAV) is powered by Li-ion batteries. It is simulated in Matlab/Simulink environment using the electrical equivalent circuit. A detailed model is created, taking into account temperature, state of charge (SoC), cell dynamics and operating functions. To estimate state of health (SoH) of the battery, resistance values must be known. Resistance and capacity values in the equivalent circuit of the Li-ion battery are obtained with the help of the simulation model. The SoH of the Li-ion batteries can be accurately predicted with the results obtained.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140379224","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}
The prediction of heart disease has gained great importance in recent years. Efficient monitoring of cardiac patients can save tremendous number of lives. This paper presents a method for classification and prediction of electrocardiogram data obtained from 452 patients representing the risk of cardiac arrhythmia. The aim of the study is to select highly related features with arrhythmia risk by using three different feature selection algorithms. In addition, various machine learning models are utilized for the classification task such as k-Nearest Neighbors (k-NN), Support Vector Machines (SVM) and Decision Tree (DT). The experimental results show that combination of a purposed feature selection method which later is called “Matched Selection” using SVM classifier outperforms other combinations and have an accuracy of 76.6% while k-NN and DT classifiers have an accuracy of 68.80% and 71.11% respectively. The study, in which detailed analyses are presented comparatively, is promising for the future studies.
{"title":"Classification of the Cardiac Arrhythmia Using Feature Selection Algorithms","authors":"Murat Tunç, Gülnur Begüm Cangöz","doi":"10.55525/tjst.1324854","DOIUrl":"https://doi.org/10.55525/tjst.1324854","url":null,"abstract":"The prediction of heart disease has gained great importance in recent years. Efficient monitoring of cardiac patients can save tremendous number of lives. This paper presents a method for classification and prediction of electrocardiogram data obtained from 452 patients representing the risk of cardiac arrhythmia. The aim of the study is to select highly related features with arrhythmia risk by using three different feature selection algorithms. In addition, various machine learning models are utilized for the classification task such as k-Nearest Neighbors (k-NN), Support Vector Machines (SVM) and Decision Tree (DT). The experimental results show that combination of a purposed feature selection method which later is called “Matched Selection” using SVM classifier outperforms other combinations and have an accuracy of 76.6% while k-NN and DT classifiers have an accuracy of 68.80% and 71.11% respectively. The study, in which detailed analyses are presented comparatively, is promising for the future studies.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140380265","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}
This paper uses a cascade-connected fuzzy-PI controller to control the position and speed of a differential drive and four-wheel drive of an autonomous mobile robot for optimal path planning. The angular speed information obtained from the encoder of each motor and the instantaneous position and angle information of the robot were calculated. The angle and position error between the reference points and these values is applied to the fuzzy logic controller as an input signal. The robot angular and linear speed data obtained from the fuzzy logic output were converted into reference speed values with kinematic equations to be applied to the motors. The speed controls of the motors were carried out with a PI controller based on these reference values. The study was performed both as a simulation in the MATLAB program and experimentally in the laboratory environment for one and more reference coordinates. In the experimental study, reference values were sent to the robot via Bluetooth with the Android application designed. At the same time, the instant data of the robot was also collected on the Android device through the same application. These data collected in Excel format were transferred to the computer via e-mail and the graphics were drawn in the MATLAB program. When the results were examined, it was seen that both speed and position control were successfully implemented with the fuzzy-PI controller for optimum path planning of the robot.
本文使用级联模糊 PI 控制器控制自主移动机器人的差动驱动和四轮驱动的位置和速度，以实现最佳路径规划。计算了从每个电机的编码器获得的角速度信息以及机器人的瞬时位置和角度信息。参考点与这些值之间的角度和位置误差作为输入信号应用于模糊逻辑控制器。从模糊逻辑输出中获得的机器人角度和线速度数据被转换成带有运动学方程的参考速度值，并应用于电机。根据这些参考值，使用 PI 控制器对电机进行速度控制。这项研究既在 MATLAB 程序中进行了模拟，也在实验室环境中对一个和多个参考坐标进行了实验。在实验研究中，参考值通过设计的安卓应用软件通过蓝牙发送到机器人。与此同时，机器人的即时数据也通过同一应用程序收集到安卓设备上。这些以 Excel 格式收集的数据通过电子邮件传送到计算机，并在 MATLAB 程序中绘制图形。检查结果表明，使用模糊 PI 控制器成功地实现了速度和位置控制，从而实现了机器人的最佳路径规划。
{"title":"Realization of Fuzzy-PI Controller-Based Path Planning of Differential Drive Mobile Robot","authors":"Ahmet Top, Muammer Gökbulut","doi":"10.55525/tjst.1423794","DOIUrl":"https://doi.org/10.55525/tjst.1423794","url":null,"abstract":"This paper uses a cascade-connected fuzzy-PI controller to control the position and speed of a differential drive and four-wheel drive of an autonomous mobile robot for optimal path planning. The angular speed information obtained from the encoder of each motor and the instantaneous position and angle information of the robot were calculated. The angle and position error between the reference points and these values is applied to the fuzzy logic controller as an input signal. The robot angular and linear speed data obtained from the fuzzy logic output were converted into reference speed values with kinematic equations to be applied to the motors. The speed controls of the motors were carried out with a PI controller based on these reference values. The study was performed both as a simulation in the MATLAB program and experimentally in the laboratory environment for one and more reference coordinates. In the experimental study, reference values were sent to the robot via Bluetooth with the Android application designed. At the same time, the instant data of the robot was also collected on the Android device through the same application. These data collected in Excel format were transferred to the computer via e-mail and the graphics were drawn in the MATLAB program. When the results were examined, it was seen that both speed and position control were successfully implemented with the fuzzy-PI controller for optimum path planning of the robot.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140381131","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}
Azadeh Rezaeirad, Ö. Karasakal, Tuğba Kaman, Mesut Karahan
Autism spectrum disorder (ASD) is defined as a pervasive and multifactorial neurodevelopmental disorder. It is characterized by repetitive behavioral patterns as well as symptoms of social interaction and communication disorder. The cadherin (CDH) superfamily is a large group of synaptic cell adhesion molecules and has been widely associated with neurodevelopmental disorders, including autism. The aim of this study is to evaluate the potentially harmful missense SNPs in CDH8 and CDH10 genes, which are associated with autism spectrum disorder and cause amino acid changes, using internet-based software tools. To predict the possible harmful effects of Missense SNPs; SIFT, PolyPhen-2, PROVEAN, SNPs&GO, Meta-SNP and SNAP2 software tools were used and possible common harmful ones were determined in all of them. Its effect on protein stabilization was investigated with I-Mutant 3.0 and MUpro tools. Three-dimensional models of these common damaging amino acid changes were evaluated with the HOPE software. As a result of in silico analysis of 577 missense SNPs in the CDH8 gene; The rs145143780 (Y572C) polymorphism common damaging SNP has been detected by all software tools. According to the results of the in silico analysis of 526 missense SNPs found in the CDH10 gene; The rs13174039 (V459G), rs147882578 (N485K), rs201423740 (Y306C), rs201956238 (F317L) and rs373340564 (R128C) common damaging SNPs have been identified in all polymorphisms by all software tools. As a result of this study, it is thought that the data obtained will make important contributions to future relevant experimental studies.
{"title":"Evaluation of SNP in the CDH8 and CDH10 Genes Associated with Autism Using In-Silico Tools","authors":"Azadeh Rezaeirad, Ö. Karasakal, Tuğba Kaman, Mesut Karahan","doi":"10.55525/tjst.1344460","DOIUrl":"https://doi.org/10.55525/tjst.1344460","url":null,"abstract":"Autism spectrum disorder (ASD) is defined as a pervasive and multifactorial neurodevelopmental disorder. It is characterized by repetitive behavioral patterns as well as symptoms of social interaction and communication disorder. The cadherin (CDH) superfamily is a large group of synaptic cell adhesion molecules and has been widely associated with neurodevelopmental disorders, including autism. The aim of this study is to evaluate the potentially harmful missense SNPs in CDH8 and CDH10 genes, which are associated with autism spectrum disorder and cause amino acid changes, using internet-based software tools. To predict the possible harmful effects of Missense SNPs; SIFT, PolyPhen-2, PROVEAN, SNPs&GO, Meta-SNP and SNAP2 software tools were used and possible common harmful ones were determined in all of them. Its effect on protein stabilization was investigated with I-Mutant 3.0 and MUpro tools. Three-dimensional models of these common damaging amino acid changes were evaluated with the HOPE software. As a result of in silico analysis of 577 missense SNPs in the CDH8 gene; The rs145143780 (Y572C) polymorphism common damaging SNP has been detected by all software tools. According to the results of the in silico analysis of 526 missense SNPs found in the CDH10 gene; The rs13174039 (V459G), rs147882578 (N485K), rs201423740 (Y306C), rs201956238 (F317L) and rs373340564 (R128C) common damaging SNPs have been identified in all polymorphisms by all software tools. As a result of this study, it is thought that the data obtained will make important contributions to future relevant experimental studies.","PeriodicalId":516893,"journal":{"name":"Turkish Journal of Science and Technology","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140387823","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：