El hareketi tanıma, insan-bilgisayar etkileşimi için anlamlı el hareketlerinin sınıflandırılmasına yönelik bir prosedürdür. Yüzey elektromiyografisi (sEMG), amaçlanan hareketlerle ilgili içsel bilgileri taşıdığı için el hareketi sınıflandırma çalışmalarında sıklıkla kullanılmaktadır. Bu tez çalışmasında, zaman-frekans (TF) matrislerinden çıkarılan özellikler ile TF matrislerinden Negatif Olmayan Matris Çarpanlarına Ayırma (NMF) yöntemiyle çıkarılan özelliklerin sınıflandırma başarısının karşılaştırılması sunulmaktadır. TF matrislerini elde etmek için 4 kanallı sEMG sinyaline Çok Değişkenli Sen ...Daha fazlası
The height of buildings in cities are of critical importance to urban planning and sustainable growth, as these factors are closely linked to environmental, economic, social, and aesthetic elements that shape the structure and character of cities. The main purpose of this study is to calculate building heights using machine learning algorithms based on airborne LiDAR and ICESat-2 data in urban areas. Sub-objectives of the study to achieve the main objective are: (a) investigate the relationships between spaceborne and airborne LiDAR data and integrate the data, (b) investigate the performance ...Daha fazlası
Generating captions and text descriptions of images will enable visually and hearing impaired extended accessibility to the real-world, thus reducing their social isolation, and improving their well-being, employability, and education experience. This thesis presents significant advancements in algorithmic approaches for generating captions and text descriptions. These enhancements are pivotal in processing and interpreting both image and audio data. The focus on algorithmic innovation ensures that the platform is not only efficient but also adaptable to various types of visual and auditory in ...Daha fazlası
The recent increase in life expectancy and changing living conditions have led to a
rise in developments regarding implants, particularly in orthopedic implants. It is
important to note that this statement is based on objective evidence and not
subjective evaluations. Despite these advances, issues with metallic implants such as
Ti, Ti alloy, Co-Cr alloy, and stainless steel (AISI 316L), which are currently
preferred, persist. There are several limitations to implant materials, including
corrosion due to the physiological environment, bacterial infection, and biofilm
formation. Although ...Daha fazlası
Mathematical models have been devised to comprehend and scrutinize biological neurons' structure and behavioural patterns. In order to assist in the utilization and visualization of these mathematical models for computations, simulations have been designed. In this thesis study, a simulator has been developed to be educational and to require no coding skills. It is intended to have a simple, understandable, and straightforward interface. This simulator includes simple interface pages where users can manually input parameters to be used in the models, and it also includes readymade experiments ...Daha fazlası
Polymers contain moisture due to their chemical structure. Moisture in polymers is important for the quality of the final product and ease of processing. For this reason, polymers are subjected to drying before processes such as injection and extrusion. Drying is carried out at temperatures and times specified by the polymer suppliers. Over-drying leads to increased viscosity (processing difficulty) while under-drying leads to flow marks, burrs, and reduced tensile strength and impact strength. Over-drying also causes excessive energy consumption. In this study, the drying process optimization ...Daha fazlası
The aim of this thesis was to develop a wearable tele-physiotherapy device that addresses the remote elbow joint rehabilitation. The developed device consists of a wearable exoskeleton equipped with servo motor, joint angle sensor, EMG sensor, battery and Wi-Fi module. By connecting with the Android mobile application, it enables real-time monitoring of EMG data and programming of personalized exercise programs. The device offers convenience and comfort to patients by eliminating the need for face-to-face physiotherapy sessions and aims to reduce treatment costs and treatment time.
The develo ...Daha fazlası
This thesis focuses on design and development of a robot manipulator with dexterous forceps for single-incision laparoscopic surgery. Integrating the robotic capabilities into laparoscopy instruments, the study aims to increase precision and reduce limitations such as mobility constraints. Main objective of the thesis is to develop a robotic articulating laparoscopy instrument. In light of the first trials, it is seen that the dexterity and robotic control advantages are promising while the trocar's mobility constraint limits the workspace of the robotic laparoscopy forceps. An alternative sur ...Daha fazlası
In this study, the Friction Stir Spot Welding (FSSW) method was employed to join thin AA6061-T4 series aluminum sheets. The AA6061-T4 alloy used in the study has various applications, including aerospace and automotive industries. During the joining process using the FSSW method, emphasis was placed on three parameters: tool rotational speed, pin length, and pin width, considering the advantages of the aluminum alloy used. A total of 12 welding operations were performed with different parameter combinations. The obtained specimens were examined for their mechanical properties, temperature meas ...Daha fazlası
İnme, günümüzde dünyada önde gelen ölüm nedenlerinden biridir. İnme geçiren hastaların tedavisi ve hayatta kalması için acil ve kesin tanı çok önemlidir. İskemik inmenin tanı ve tedavisi çoğunlukla manyetik rezonans görüntülemeye (MR) dayanmaktadır. Bu çalışmanın amacı, 2 boyutlu MR görüntüleri kullanarak U şeklinde bir evrişimsel sinir ağı mimarisi (CNN) oluşturarak iskemik inme lezyonunu bölütlemek ve çeşitli kayıp fonksiyonları kullanarak çalışmanın kayıp sonuçlarını, zar benzerlik katsayısını (DSC), hassasiyetini ve özgünlüğünü değerlendirmektir. Oluşturulan modeli eğitmek, doğrulamak ve t ...Daha fazlası
Motor imagery (MI) task classification is highly prevalent in Electroencephalography
(EEG)-based Brain-Computer Interface (BCI) research area. Extremity movement task
classification and finger movement classification studies are presented in this thesis.
In extremity movement classification, binary-class (right hand and left hand) and
multi-class (right hand, left hand, right hand, and left hand) classifications are
performed using 4 different feature extraction approaches and statistically
significance-based feature selection (the independent t-test, one-way ANOVA test).
Firstly, time- ...Daha fazlası
Duplex steels are materials that contain ferrite and austenite phases in their structure, have high resistance to corrosion, and also show improved mechanical values. While the austenite in its structure provides general corrosion resistance and ductility, ferrite provides resistance to stress corrosion cracking and mechanical strength. Duplex steels have widespread use, especially in shipping and petrochemistry. The current production method of duplex steels, which are in demand with a wide usage area, is generally argon oxygen decarburization furnaces (AOD). In addition to the production met ...Daha fazlası
6698 sayılı Kişisel Verilerin Korunması Kanunu kapsamında yükümlülüklerimiz ve çerez politikamız hakkında bilgi sahibi olmak için alttaki bağlantıyı kullanabilirsiniz.