Teknik Bilimler Meslek Yüksekokulu / Vocational School of Technical Sciences
Permanent URI for this collectionhttps://hdl.handle.net/11727/2031
Browse
9 results
Search Results
Item The Effects of Illumination on the Current Conduction Mechanisms of the Au/C20H12/N-Si Schottky Barrier Diode (SBD)(2023) Bengi, Seda; 0000-0002-3348-0712; HPH-9613-2023Using the I-V characteristics both in the dark and under varied illumination-intensities (50-250 mW.cm(-2)) by 50 mW.cm(-2) steps in the wide range bias-voltage (+/- 5 V), specific fundamental electrical and photo effects parameters of the Au/C20H12/n-Si SBD were examined. Due to the creation of electron-hole pairs and their drift in opposite directions under the influence of an electric field, the value of photocurrent in the reverse bias (I-ph) increases when illumination density is increased. The barrier height (Phi(B0)) tended to decrease due to the increase in photocurrent, while the diode's ideality factor (n) increased with increasing illumination intensity. Also, the Schottky structure's open-circuit voltage (V-oc), short circuit current (I-sc), filling factor (FF), and efficiency (eta) were determined to be 0.358 V, 95.5 mu A, 33%, and 0.028% under 50 mW.cm(-2), respectively. The R-s and R-sh values found using Ohm's law are a vital function of illumination and voltage which decrease with increasing illumination intensity. Additionally, using the forward bias I-V data and accounting for the bias dependent of the effective barrier height (Phi(e)) and ideality factor n(V) for different illumination intensities, the energy density distribution profile of surface states (N-ss) was obtained. According to these results, the organic interlayer consisting of C20H12 is light-sensitive and suitable for optoelectronic devices such as photodetectors and photodiodes.Item Sequential Decision Making for Elevator Control(2023) Tartan, Emre Oner; Ciflikli, Cebrail; 0000-0002-5688-4226; JVD-9650-2023In the last decade Reinforcement Learning (RL) has significantly changed the conventional control paradigm in many fields. RL approach is spreading with many applications such as autonomous driving and industry automation. Markov Decision Process (MDP) forms a mathematical idealized basis for RL if the explicit model is available. Dynamic programming allows to find an optimal policy for sequential decision making in a MDP. In this study we consider the elevator control as a sequential decision making problem, describe it as a MDP with finite state space and solve it using dynamic programming. At each decision making time step we aim to take the optimal action to minimize the total of hall call waiting times in the episodic task. We consider a sample 6-floor building and simulate the proposed method in comparison with the conventional Nearest Car Method (NCM).Item Brain Tumor Prediction with Deep Learning and Tumor Volume Calculation(2021) Karayegen, Gokay; Aksahin, Mehmet FeyziItem Deep Learning Based Multi Modal Approach for Pathological Sounds Classification(2020) Ankishan, Haydar; Kocoglu, ArifAutomatic detection of voice disorders is very important because it makes the diagnosis process simpler, cheaper and less time consuming. In the literature, there are many studies available on the analysis of voice disorders based on the characteristics of the voice and subdividing the result of this analysis. In general, these studies have been carried out in order to subdivide the sound into pathological - normally sub - groups by means of certain classifiers as a result of subtraction of the features on frequency, time or hybrid axis. In contrast to existing approaches, in this study, a multiple- deep learning model using feature level fusion is proposed to distinguish pathological-normal sounds from each other. First, a feature vector (HOV) on the hybrid axis was obtained from the raw sound data. Then two CNN models were used. The first model has used raw audio data and the second model has used HOV as an input. Feature data in both model SoftMax layers were obtained as a matrix, and canonical correlation analysis (Canonical Correlation Analysis (CCA) was applied at feature level fusion. The new obtained feature vector was used as an input for multiple support vector machines (M-SVMs), Decision Tree (DTC) and naive bayes (NBC) classifiers. When the experimental results are examined, it is seen that the new multi-model based deep learning architecture provides superior success in classifying pathological sound data. With the results of the study, it will be possible to automatically detect and classify the pathology of these patients according to the proposed system.Item An Approach to the Classification of Environmental Sounds by LSTM Based Transfer Learning Method(2020) Ankishan, HaydarThis electronic Effective frequency extraction from acoustic environmental sounds in frequency and time axis increases the importance of voice recognition, sound detection, environmental classification in recently. For this purpose, there are many studies in the literature on the discrimination of acoustic environmental sounds. These studies generally perform these operations with the help of machine learning and deep learning algorithms. In this study, a new artificial intelligence architecture using two long short term memory networks (LSTM) is designed. The structure, which uses both raw data and the proposed feature vector at its inputs, is reinforced by the transfer learning approach. The obtained classification results were fused at the decision level. As a result of experimental studies, five different environmental acoustic sounds were subdivided into 97.15% test accuracy. In environmental studies conducted in pairs, it is seen that the environmental sounds have reached 100% accuracy. Experimental results have shown that the proposed artificial intelligence architecture with fusion support at decision level is capable of discriminating acoustic environmental sounds.Item Detecting COVID-19 from Respiratory Sound Recordings with Transformers(2022) Aytekin, Idil; Dalmaz, Onat; Ankishan, Haydar; Saritas, Emine U.; Bagci, Ulas; Cukur, Tolga; Celik, Haydar; Drukker, K; Iftekharuddin, KMAuscultation is an established technique in clinical assessment of symptoms for respiratory disorders. Auscultation is safe and inexpensive, but requires expertise to diagnose a disease using a stethoscope during hospital or office visits. However, some clinical scenarios require continuous monitoring and automated analysis of respiratory sounds to pre-screen and monitor diseases, such as the rapidly spreading COVID-19. Recent studies suggest that audio recordings of bodily sounds captured by mobile devices might carry features helpful to distinguish patients with COVID-19 from healthy controls. Here, we propose a novel deep learning technique to automatically detect COVID-19 patients based on brief audio recordings of their cough and breathing sounds. The proposed technique first extracts spectrogram features of respiratory recordings, and then classifies disease state via a hierarchical vision transformer architecture. Demonstrations are provided on a crowdsourced database of respiratory sounds from COVID-19 patients and healthy controls. The proposed transformer model is compared against alternative methods based on state-of-the-art convolutional and transformer architectures, as well as traditional machine-learning classifiers. Our results indicate that the proposed model achieves on par or superior performance to competing methods. In particular, the proposed technique can distinguish COVID-19 patients from healthy subjects with over 94% AUC.Item Security and Privacy in Medical Internet of Things and Cluster-Based Wireless Sensor Networks for Health Care(2020) Hammoodi, Asmaa Salih; Ozdemir, Suat; Tuncer, A. Turgut; Celebi, Fatih VAdvances in sensing, networking, and the ambient intelligence of wireless sensor networks (WSNs) have been taking place in many applications recently. Growing health-care systems need wireless-based sensor networks to provide data on the health status and living environment of patients during periods of illness. Mainly WSNs use the mechanism of clustering to reduce the energy consumption required with hierarchical structures to enhance network performance. The second prevalent challenge concerns the security of WSN cluster nodes because of the big attacks and security investigations come in WSN-health care applications as a challenging and motivating problem. This paper focuses on two essential platforms adopted within WSN applications. The hardware platform characterizes the WSN cluster nodes specifying automatically encrypted nodes during routing. The software platform is a simulation performed with two features: one identical to the hardware platform to enhance the results and compare between them, a second structure implementing three encryption algorithms as a reasonable technique to secure cluster nodes: Caesar cipher, RC4, and advanced encryption standard (AES). The first goal achieved by our plan is our private and secure medical protocol, which depends on identity-based cryptography, accomplished via the hardware platform. The second goal derived from the simulation is increasing the number of PEGASIS chains when the time needed to perform the task is limited particularly in cases of emergency to preview history and data of patients, but more chains get many frames of data aggregation, which causes overlap. Eventually, the system provides a rapid, efficient, flexible, secure, and authoritative infrastructure where our results showed that data retention in the node and by using the appropriate cryptographic algorithms in the group achieved privacy and security in the health care centers.Item Blood pressure prediction from speech recordings(2020) Ankishan, HaydarThe aim of this study is to extract new features to show the relationship between speech recordings and blood pressure (BP). For this purpose, a database consisting of / a / vowels with different BP values under the same room and environment conditions is presented to the literature. Convolutional Neural Networks- Regression (CNN-R), Support Vector Machines- Regression (SVMs-R) and Multi Linear Regression (MLR) are used in this study to predict BP with extracted features. From the experiments, the highest accuracy rates of BP prediction from / a / vowel have been obtained based on Systolic BP values with CNNR. In the study, 89.43 % for MLR, 92.15 % for SVM-R and 93.65 % for CNN-R are obtained when ReliefF has been used. When the root mean square errors (RMSE) are considered, the lowest error value is obtained with CNN-R as RMSE = 0.2355. In conclusion, it can be observed that the proposed feature vector (FVx) shows a relationship between BP and the human voices, and in this direction, it can be used as an FVx in a system that will be developed in order to follow the tension of individuals. (C) 2020 Elsevier Ltd. All rights reserved.Item A viable snore detection system: hardware and software implementations(2020) Tuncer, Ahmet Turgut; Bilgen, MehmetA stand-alone, custom-made biomedical system was introduced for long-term monitoring of sleep and detection of snoring events. Commercially available electronic components were assembled for recording audio, pulse, and respiration signals. Its software was implemented for off-line processing of the acquired signals in C++ and MATLAB environments. The linear and nonlinear features of the signals were extracted and characterized using spectral energy distribution, entropy, and largest Lyapunov exponent (LLE). The performance of the system was evaluated with real physiological data gathered from 14 chronic snorers. Analysis of the cases indicated that the system identified the snoring events with an accuracy of 88.22%, sensitivity of 94.91%, and positive predictive value of 90.95%. This high level of validation confirmed the reliability and utility of the system in detecting snoring.