Mekatronik Mühendisliği Bölümü Yayın Koleksiyonu
Permanent URI for this collectionhttps://hdl.handle.net/20.500.12416/255
Browse
4 results
Search Results
Article Citation - WoS: 4Citation - Scopus: 4Window Length Insensitive Real-Time Emg Hand Gesture Classification Using Entropy Calculated From Globally Parsed Histograms(Sage Publications Ltd, 2023) Alguner, Ayber Eray; Ergezer, HalitElectromyography (EMG) signal classification is vital to diagnose musculoskeletal abnormalities and control devices by motion intention detection. Machine learning assists both areas by classifying conditions or motion intentions. This paper proposes a novel window length insensitive EMG classification method utilizing the Entropy feature. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. The main goal of this study is to show that entropy can be used as the only feature for fast real-time classification of EMG signals of hand gestures. Additionally, the entropy feature can classify feature vectors of different sliding window lengths without including them in the training data. Many kinds of entropy feature succeeded in electroencephalography (EEG) and electrocardiography (ECG) classification research. However, to the best of our knowledge, the Entropy Feature proposed by Shannon stays untested for EMG classification to this day. All the machine learning models are tested on datasets NinaPro DB5 and the newly collected SingleMyo. As an initial analysis to test the entropy feature, classic Machine Learning (ML) models are trained on the NinaPro DB5 dataset. This stage showed that except for the K Nearest Neighbor (kNN) with high inference time, Support Vector Machines (SVM) gave the best validation accuracy. Later, SVM models trained with feature vectors created by 1 s (200 samples) sliding windows are tested on feature vectors created by 250 ms (50 samples) to 1500 ms (300 samples) sliding windows. This experiment resulted in slight accuracy differences through changing window length, indicating that the Entropy feature is insensitive to this parameter. Lastly, Locally Parsed Histogram (LPH), typical in standard entropy functions, makes learning hard for ML methods. Globally Parsed Histogram (GPH) was proposed, and classification accuracy increased from 60.35% to 89.06% while window length insensitivity is preserved. This study shows that Shannon's entropy is a compelling feature with low window length sensitivity for EMG hand gesture classification. The effect of the GPH approach against an easy-to-make mistake LPH is shown. A real-time classification algorithm for the entropy features is tested on the newly created SingleMyo dataset.Article Citation - WoS: 2Citation - Scopus: 3Control Structure Design With Constraints for a Slung Load Quadrotor System(Sage Publications Ltd, 2024) Leblebicioglu, Kemal; Ergezer, HalitWe propose a control structure for a quadrotor carrying a slung load with swing-angle constraints. This quadrotor is supposed to pass through the waypoints at specified speeds. First, a cascaded PID autopilot is designed, which adaptively gives attention to position and speed requirements as a function of their errors. Its parameters are found from an optimization problem solved using the PSO algorithm. Second, this controller's performance is improved by adding the Complementary Controller employing an ANN. 5. Training data for the ANN is created by solving optimal control problems. The ANN is activated when the swing angle constraint is about to be violated. It is trained using optimal control values corresponding to the cases where the swing angle falls in a particular band about the upper swing angle constraint. Simulations are performed in a MATLAB environment. Finally, some of the simulation results are validated on a physical system.Article Citation - WoS: 32Citation - Scopus: 36Effect of Powder Metallurgy Cu-B4c Electrodes on Workpiece Surface Characteristics and Machining Performance of Electric Discharge Machining(Sage Publications Ltd, 2016) Cogun, Ferah; Akturk, Nizami; Cogun, Can; Esen, Ziya; Genc, AsimThe main aim of this study is to produce new powder metallurgy (PM) Cu-B4C composite electrode (PM/(Cu-B4C)) capable of alloying the recast workpiece surface layer during electric discharge machining process with boron and other hard intermetallic phases, which eventually yield high hardness and abrasive wear resistance. The surface characteristics of the workpiece machined with a PM/(Cu-B4C) electrode consisted of 20 wt% B4C powders were compared with those of solid electrolytic copper (E/Cu) and powder metallurgy pure copper (PM/Cu) electrodes. The workpiece surface hardness, surface abrasive wear resistance, depth of the alloyed surface layer and composition of alloyed layers were used as key parameters in the comparison. The workpiece materials, which were machined with PM/(Cu-B4C) electrodes, exhibited significantly higher hardness and abrasive wear resistance than those of machined with the E/Cu and PM/Cu. The main reason was the presence of hard intermetallic phases, such as FeB, B4C (formed due to the boron in the electrode) and Fe3C in the surface layer. The improvement of the surface hardness achieved for steel workpiece when using PM/(Cu-B4C) electrodes was significantly higher than that reported in the literature. Moreover, the machining performance outputs (workpiece material removal rate, electrode wear rate and workpiece average surface roughness (Ra)) of the electrodes were also considered in this study.Article Citation - WoS: 28Citation - Scopus: 37Effective Damage Mechanisms and Performance Evaluation of Ceramic Composite Armors Subjected To Impact Loading(Sage Publications Ltd, 2014) Gulgec, Mufit; Evci, CelalResearches on the armor systems composed of composite materials with ceramic frontal face and polymer-based back-support are continuously developing further. This study, which mainly covers the impact behavior of ceramic composite armors, is a two-stage research. The first stage involves the investigation of component-level impact characteristics and failure mechanisms of the ceramic composite armors. At this stage, low-velocity impact behavior of ceramics and fiber-reinforced composites is investigated. Impact test results revealed that impact loading is of dynamic nature and strength of the composite materials under dynamic loading increases considerably as a result of strain rate sensitivity, which makes them the right choice to be used in conjunction with ceramics in armor systems. The second stage examines the ballistic impact behavior and ballistic performance of the armor systems. The extent and pattern of impact damage related to projectile velocity are determined for the armor components and the armor itself.