Elektrik Elektronik Mühendisliği/Makale Koleksiyonu

Bu koleksiyon için kalıcı URI

https://hdl.handle.net/20.500.12395/15593

Listeleniyor 1 - 20 / 54

Determination of the ADF and IVOMD Content of Sugarcane Using Near Infrared Spectroscopy Coupled with Chemometrics
(Selçuk Üniversitesi, 2022) Çataltaş, Özcan; Tütüncü, Kemal
Sugarcane is a plant whose quality parameters are required to be determined both for being one of the substances used in sugar production and for being used as animal feed. Near-infrared spectroscopy is a technique that has already been used for predicting the parameters of various plants and has gained popularity in recent years. This study proposes a near-infrared spectroscopy-based model for the rapid and effortless analysis of acid detergent fiber fraction and vitro organic matter digestibility parameters of the sugarcane plant. Partial least squares regression was combined with common preprocessing methods for modeling. This model yielded an R 2 CV value of 0.935 and 0.953 for the acid detergent fiber fraction and vitro organic matter digestibility parameters, respectively. Then, the spectra from three handheld spectrometers were combined using a proposed combination method to generate new spectra with higher spectral resolution. New models were built using these generated spectra and compared to the previous result. Obtained results showed that combining spectra from different spectrometers can improve model performance.
Comparison of Plant Detection Performance of CNN-based Single-Stage and Two-Stage Models for Precision Agriculture
(Selçuk Üniversitesi, 2022) Özcan, Recai; Tütüncü, Kemal; Karaca, Murat
The fact that arable land is not increasing in proportion to the ever-increasing population will increase the need for food in the coming years. For this reason, it is necessary to increase the yield of crops to make optimum use of arable land. One of the most important reasons for the decrease in yield and quality of crops is weeds. Herbicides are generally preferred for weed management. Due to deficiencies in herbicide application methods, only 0.015-6% of herbicides reach their target. The use of herbicides, which is an important part of the agricultural system, is an issue that needs to be emphasized, considering the risk of residue and environmental damage. In parallel with the rapid development of electronic and computer technologies, artificial intelligence applications have had the opportunity to develop. In this context, the use of artificial intelligence for plant detection in the subsystems of herbicide application machines will contribute to the development of precision agriculture techniques. In this study, the plant detection performances of single-stage and two-stage Convolutional Neural Network (CNN)-based deep learning (DL) models are evaluated. In this context, a dataset was created by taking images of Zea mays, Rhaponticum repens (L.) Hidalgo, and Chenopodium album L. plants in agricultural lands in Konya. With this dataset, the training of the models was carried out by the transfer learning method. The evaluation metrics of the trained models were calculated using the error matrix. In addition, training time and prediction time were used as quantitative metrics in the evaluation of the models. The plant detection performance, training time, and prediction time of the models were 85%, 8 h, 1.21 s for SSD MobileNet v2 and 99%, 22 h, 2.32 s for Faster R-CNN Inception v2, respectively. According to these results, Faster R-CNN Inception v2 is outperform in terms of accuracy. However, in cases where training time and prediction time are important, the SSD MobileNet v2 model can be trained with more data to increase its accuracy.
Adaptif bulanık mantık kontrolü ile maksimum güç noktası izleyici tasarımı ve gerçeklemesi
(Selçuk Üniversitesi, 2019) Zorlu, Kübra Nur; Saday, Abdülkadir; Sarıtaş, İsmail
Enerji ihtiyacının teknolojik gelişmelere ve popülasyona bağlı olarak günden güne artması, insanları alternatif enerji kaynakları bulmaya yönlendirmektedir. Alternatif enerji kaynakları arasında en çok kullanılan kaynak, farklı enerji türlerine dönüştürülebilmesi ve kolay erişilebilmesi nedeniyle güneş enerjisidir. Ülkemiz, güneş enerjisinin kaynak olarak kullanılması açısından elverişli bir konuma sahiptir. Güneş enerjisinden elektrik enerjisinin üretilebilmesi için fotovoltaik paneller kullanılmaktadır. Bu noktada önemli olan, fotovoltaik paneller yardımıyla kaynaktan alınan enerjiden mümkün olduğunca çok verim sağlayabilmektir. Yüksek seviyede verimin elde edebilmesi için, güneş ışınlarının panele mümkün olduğunca dik ve uzun süre ulaşması gerekmektedir. Bu amaçla da panelin güneşi izlediği sistemler geliştirilmiştir. Güneşi takip sistemleri tek veya iki eksenli olarak tasarlanmaktadır. Bu çalışmanın amacı, adaptif bulanık mantık kontrolü kullanarak, güneş takip sistemlerinin kontrolünü sağlamak ve güneş enerjisinden elde edilen verimin artırılmasını sağlamaktır. Bu amaç doğrultusunda, güneş enerjisinden maksimum verimin elde edilebilmesi için, adaptif bulanık mantık kontrollü bir maksimum güç noktası izleyici (MPPT) sistemi tasarlanarak gerçekleştirilmiştir.
Evaluation of The Classification Performance of Methods Developed in ANN Training
(Selçuk Üniversitesi, 2021) Yasar, Ali; Saritas, Ismail
In this study, the performance and success of some models used in the training of artificial neural networks are compared. The UCI machine learning database was used for the performance evaluation and comparison process and for the IRIS dataset), which we often encounter in performance evaluations. In the study, the classification performances of our data sets were calculated using Feedforward Neural Network Cross-Validation (FNN-CV), Probabilistic Neural Network Cross-Validation (PNN-CV) and Recurrent Neural Network Cross-Validation (RNNCV) learning techniques. Our data has been classified using a 10-fold cross validation technique. The RNN-CV method for the IRIS data set proved to be a good classification method by achieving 100% accuracy success which shows that it should be used in classification problems.
Effects of nanographene added to the matrix material at different rates on the Charpy impact energy
(Selçuk Üniversitesi, 2021) Demirci, Ibrahim; Saritas, Ismail
In this study, the Charpy impact behaviors and hardness values of nanographene-added epoxies, which are used in the aviation and space, automotive, and maritime industries that require advanced technology, were investigated. The additive ratio of nanographene used as the filling material in the matrix should be determined. Otherwise, poorly determined additive ratios reduce the impact resistance of the epoxies. In this study, nano graphene additive rates were determined as 0.5%, 0.8% and 1.2% by weight. Charpy impact tests were performed on the epoxy composites at these ratios and their hardness values were determined. A comment was made regarding the link between the increased nanographene values and hardness.
Wavelet based denoising of the simulated chest wall motion detected by SFCW radar
(LGEP-SUPELEC, 2019) Acar, Yunus Emre; Şeflek, İbrahim; Yaldız, Ercan
Low power and compact radars have emerged with the development of electronic technology. This has enabled the use of radars in indoor environments and the realization of many applications. The detection, tracking and classification of human movements by radar are among the remarkable applications. Contactless detection of human vital signs improves the quality of life of patients being kept under observation and facilitates the work of experts. In this study, it was simulated that the movement of the chest wall was modeled and detected by the SFCW radar. Gaussian, Rician and uniformly distributed random noise types were added to the modeled chest motion at different levels. The noisy signal obtained at the receiver is denoised with different mother wavelet functions and the performances of these functions are presented comparatively.
Weld defect categorization from welding current using principle component analysis
(SCIENCE & INFORMATION SAI ORGANIZATION LTD, 2019) Arabaci, Hayri.; Laving, Salman.
Real time welding quality control still remains a challenging task due to the dynamic characteristic of welding. Welding current of gas metal arc welding possess valuable information that can be analyzed for weld quality assessment purposes. On-line monitoring of motor current can be provided information about the welding. In this study, current signals obtained during welding in the short- circuit metal transfer mode were used for real-time categorization of deliberately induced weld defects and good welds. A hall-effect current sensor was employed on the ground wiring of the welding machine to acquire the welding current signals during the welding process. Vector reduction of the current signals in time domain was achieved by principle component analysis. The reduced vector was then classified by various classification techniques such as support vector machines, decision trees and nearest neighbor to categorize the arc weld defects or pass it as a good weld. The proposed technique has proved to be successful with accurate classification of the welding categories using all three classifiers. The classification technique is fast enough so it can be used for real time weld quality control as all the signal processing is carried out in the time domain.
Towards a real-time sorting system: Identification of vitreous durum wheat kernels using ANN based on their morphological, colour, wavelet and gaborlet features
(ELSEVIER SCI LTD, 2019) Kaya, Esra.; Saritas, Ismail.
Wheat is the main ingredient of most common food products in our daily lives and obtaining good quality wheat kernels is an important matter for the production of food supplies. In this study, type-1252 durum wheat kernels which have vast harvest areas in Turkey and is the principal ingredient of pasta and semolina products were examined and classified to obtain top quality wheat kernels based on their vitreousness. Also, top quality provision of food supplies means that the products must be refined from all foreign materials so a classification process has been applied to extract foreign materials from wheat kernels. In this study, we have used a total of 236 morphological, colour, wavelet and gaborlet features to classify vitreous, starchy durum wheat kernels and foreign objects by training several Artificial Neural Networks (ANNs) with different amount of features based on the feature rank list obtained with ANOVA test. The data we have used in this study was video images of wheat kernels and foreign objects present on a conveyor belt camera system with illumination provided by daylight colour powerleds. The maximum classification accuracy was 93.46% obtained with 210 feature neural network function which was generated and applied on the video containing a mixture of wheat kernels and foreign objects.
GA based selective harmonic elimination for multilevel inverter with reduced number of switches: an experimental study
(KAUNAS UNIV TECHNOLOGY, 2019) Bektas, Enes.; Karaca, Hulusi.
In power electronic applications, especially high power and medium voltage, multilevel inverters (MLIs) have been commonly used. MLIs ensure high quality load voltage and lower Total Harmonic Distortion (THD) than traditional inverter. In this paper, a multilevel inverter structure with reduced number of power switches is proposed. The proposed multilevel inverter is lower costed than conventional MLL Also, a Genetic Algorithm (GA) based Selective Harmonic Elimination (SHE) technique has been used for the first time in the proposed MLI structure with reduced number of switches. The proposed GA based SHE technique computes the optimum switching angles by solving nonlinear harmonic equations of multilevel inverter. Both Isochronous switching (IS) and SHE techniques have been applied to proposed MLI to demonstrate the effectiveness of the GA based SHE technique. Simulation and experimental results for 7, 11 and 13-level have been obtained. Results of 11-level inverter is analysed and given in detail. Results have clearly proved that desired order harmonics in proposed MLI topology can be eliminated by using GA based SHE technique and lower THD on the load voltage has been provided.
Feasibility of a novel technique using 3-dimensional modeling and augmented reality for access during percutaneous nephrolithotomy in two different ex-vivo models
(SPRINGER, 2019) Akand, Murat; Civcik, Levent; Büyükaslan, Ahmet; Altıntaş, Emre; Koçer, Erdinç; Koplay, Mustafa; Erdoğru, Tibet
PurposeWe describe a novel technique that uses mathematical calculation software, 3-dimensional (3D) modeling and augmented reality (AR) technology for access during percutaneous nephrolithotomy (PCNL) and report our first preliminary results in two different ex-vivo models.MethodsNovel software was created in order to calculate access point and angle by using pre-operative computed tomography (CT) obtained in 50 patients. Two scans, 27s and 10min after injection of contrast agent, were taken in prone PCNL position. By using DICOM objects, mathematical and software functions were developed to measure distance of stone from reference electrodes. Vectoral 3D modeling was performed to calculate the access point, direction angle and access angle. With specific programs and AR, 3D modeling was placed virtually onto real object, and the calculated access point and an access needle according to the calculated direction angle and access angle were displayed virtually on the object on the screen of tablet.ResultsThe system was tested on two different modelsa stone placed in a gel cushion, and a stone inserted in a bovine kidney that was placed in a chickenfor twice, and correct access point and angle were achieved at every time. Accuracy of insertion of needle was checked by feeling crepitation on stone surface and observing tip of needle touching stone in a control CT scan.ConclusionsThis novel device, which uses software-based mathematical calculation, 3D modeling and AR, seems to ensure a correct access point and angle for PCNL. Further research is required to test its accuracy and safety in humans.
Embedded fuzzy logic control system for refrigerated display cabinets
(SPRINGER HEIDELBERG, 2019) Tutuncu, Kemal.; Ozcan, Recai.
Having done in this study, embedded fuzzy logic control system (EFLCS) was designed and implemented for closed refrigerated display cabinets (CRDC) to meet the required storage conditions for the pastry productions stored in CRDCs. The system keeps the temperature and relative humidity (RH) of CRDC at approximately +4 degrees C and 80% RH, respectively. It has two fuzzy logic controllers. One of them controls the speed levels of the fans, and the other controls the steam level of ultrasonic atomizer. Temperature and RH values are read by sensor SHT11 and transferred to PIC18F4620 microcontroller that is programmed with fuzzy Logic approach. On the other hand, the compressor was controlled with on-off control in the range of 3-5 degrees C. On the condition of starting from +7 degrees C temperature, the time to approach to the set values (4 degrees C and 80% RH) for traditional system and EFLCS is 191.8 and 109.6 s, respectively. Additionally, the ranges of temperature and RH obtained by EFLCS are between 4.44 and 3.69 degrees C and between 81.33% RH and 78.57% RH, respectively. The temperature and RH values obtained by traditional system are between 5.56 and 3.2 degrees C and between 61.81% RH and 57.45% RH, respectively. Traditional system never reached to desired humidity value (80% RH). It has been seen that developed EFLCS becomes stable in shorter time than traditional system and kept the desired values as almost constants.
Computer-assisted automatic egg fertility control
(KAFKAS UNIV, VETERINER FAKULTESI DERGISI, 2019) Boga, Mustafa; Cevik, Kerim Kursat; Kocer, Hasan Erdinc; Burgut, Aykut
This research aimed to determine the fertilization control of the eggs in an incubator between 0th and 5th days by image processing techniques via low-priced tools. Three different datasets that were composed of eggs whose images taken at different times in the incubator were prepared. Several filtering and morphology methods, gray level conversion and dynamic thresholding were utilized to process the 15 egg images. Moreover, the original processing codes based on the problem were given. White and Black percentages of binary images were utilized to determine the egg control. According to the test results, for the first dataset; 73.34% of fertility accuracy was achieved on the third day; 100% of fertility accuracy was achieved on the fourth day, for the second dataset; 93.34% of fertility accuracy was achieved on the third day; 93.34% of fertility accuracy was achieved again on the fourth day; for the third dataset, 93.34% of fertility accuracy was achieved on the third day; 100% of fertility accuracy again was achieved on the fourth day. When the results were evaluated, it was seen that egg fertility has been determined successfully automated with low cost tools.
Computer-aided diagnosis system for detection of stomach cancer with image processing techniques
(SPRINGER, 2019) Yasar, Ali.; Saritas, Ismail.; Korkmaz, Huseyin.
Stomach cancer is a type of cancer that is hard to detect at an early stage because it gives almost no symptoms at the beginning. Stomach cancer is an increasing incidence of cancer both in the World as well as in Turkey. The most common method used worldwide for gastric cancer diagnosis is endoscopy. However, definitive diagnosis is made with endoscopic biopsy results. Diagnosis with endoscopy is a very specific and sensitive method. With high-resolution endoscopy it is possible to detect mild discolorations, bulges and structural changes of the surface of the mucosa. However, because the procedures are performed with the eye of a doctor, it is possible that the cancerous areas may be missed and / or incompletely detected. Because of the fact that the cancerous area cannot be completely detected may cause the problem of cancer recurrence after a certain period of surgical intervention. In order to overcome this problem, a computerized decision support system (CDS) has been implemented with the help of specialist physicians and image processing techniques. The performed CDS system works as an assistant to doctors of gastroenterology, helping to identify the cancerous area in the endoscopic images of the scaffold, to take biopsies from these areas and to make a better diagnosis. We believe that gastric cancer will be helpful in determining the area and biopsy samples taken from the patient will be useful in determining the area. It is therefore considered a useful model.
Intelligent systems and applications in engineering advanced technology and science
(2018) Ceylan, Rahime
Feature extraction that is detection of effective features is one of the phases of biomedical signal classification. In feature extraction phase, the detection of features that increase performance of classification is very important in terms of diagnosis of disease. Due to this reason, the using of an effective algorithm for feature extraction increases classification accuracy and also it decreases processing time of classifier. In this study, two well-known dictionary-learning algorithms are used to extract features of ECG signals. The features of ECG signals are extracted by using Method of Optimal Direction (MOD) and K-Singular Value Decomposition (K-SVD). However, the extracted features are classified by Artificial Neural Network (ANN). Twelve different ECG signal classes which taken from MIT-BIH ECG Arrhythmia Database are used. When the obtained results are examined, it is seen that performance of classifier increases in usage of K-SVD for feature extraction. The highest classification accuracy is obtained as 98.74% with 5 nonzero elements in [20 1] feature vector, while K-SVD is used in feature extraction phase. The obtained results are assessed by comparing with the results obtained when discrete wavelet transform and principal component analysis are used
The effects of speed and flow rate on power in thermoelectric generators
(2018) Ağaçayak, Abdullah Cem; Terzioğlu, Hakan; Çimen, Hasan; Neşeli, Süleyman; Yalçın, Gökhan
Geothermal energy is a kind of clean energy which has existed since the world existed. Every passing year new geotermal fields are invented and their area of usage is increasing rapidly. In our day, where there is tendency of rising in the energy costs; the geothermal energy rise in importance as an alternative resource. Therefore, in this study the design of the thermoelectric generator which directly transforms the geothermal energy that is one of the renewable energy sources to electrical energy and the execution of the system is carried out. In the system, two different types of TEC1-12706 and TEC1-12710 thermoelectric moduls which are made up of thermoelectric semiconductors that can be easily acquired in the markets are used in the energy transition. In the experimental studies that are performed, the power rating which thermalelectric generators produce in 3 different pressure and 3 different flow rate of hot and cold water are compared. Consequently, it is seen that the speed and the flow rate of the water is efficacious on the power which thermoelectric generators generate
Diagnosis of mesothelioma disease using different classification techniques
(2017) Tutuncu, Kemal; Çataltaş, Özcan
Mesothelioma, which is a disease of the pleura and peritoneum, is an asbestos-related environmental disease in undevelopedcountries. Although the incidence of this disease is lower than that of lung cancer, the reaction it creates in society is very high. In thisstudy, 9 different classification algorithms of data mining were applied to the Mesethelioma data set obtained from real patients in DicleUniversity, Faculty of Medicine and loaded into UCI Machine Learning Repository, and the results were compared. When the obtainedresults were examined, it has been seen that Artificial Neural Network (ANN) had %99.0740 correct classification ratio.
GA based selective harmonic elimination for Five-level inverter using cascaded H-bridge modules
(2016) Bektas, Enes; Karaca, Hulusi
Multilevel inverters (MLI) have been commonly used in industry especially to get quality output voltage in terms of total harmonic distortion (THD). In addition, development in semiconductor technology and advanced modulation techniques make MLI implementation more attractive. Selective Harmonic Elimination (SHE) that can be applied MLI at desired switching frequency offers elimination of harmonics in the output voltage. Also, by using SHE technique with cascaded H-bridge multilevel inverters, the necessity of using filter in the output can be minimized. In this paper, SHE equations have been solved by using of Genetic Algorithm (GA) Toobox&Matlab and it has been aimed to eliminate desired harmonic orders at fundamental output voltage. Simulation results have clearly demonstrated that GA based SHE techniques can eliminate the demanded harmonic orders.
Banknote classification using artificial neural network approach
(2016) Kaya, Esra; Yasar, Ali; Saritas, Ismail
In this study, clustering process has been performed using artificial neural network (ANN) approach on the pictures belonging to our dataset to determine if the banknotes are genuine or counterfeit. Four input parameters, one hidden layer with 10 neurons and one output has been used for the ANN. All of these parameters were real-valued continuous. Data were extracted from images that were taken from genuine and forged banknote-like specimens. For digitization, an industrial camera usually used for print inspection was used. The final images have 400x 400 pixels. Due to the object lens and distance to the investigated object gray-scale pictures with a resolution of about 660 dpi were gained. Wavelet Transform tool were used to extractfeatures from images. Four input parameters are processed in the hidden layer with 10 neurons and the output realizes the clustering process. The classification process of 1372 unit data by using ANN approach is sure to be a success as much as the actual data set. The regression results of the clustering process is considerably well. It is determined that the training regression is 0,99914, testing regression is 0,99786 and the validation regression is 0,9953, respectively. Based on the results obtained, it is seen that classification process using ANN is capable of achieving outstanding success
New approach in E-mail based text steganography
(2015) Tutuncu, Kemal; Hassan, Abdikarim Abi
: In this study combination of lossless compression techniques and Vigenere cipher was used in the e-mail based text steganography. It makes use of email addresses to be the keys to embed/to extract the secret message into/from the email text (cover text). After selecting the cover text that has highest repetition pattern regarding to the secret message the distance matrix was formed. The members of distance matrix were compressed by following lossless compression algorithms as in written sequence; Run Length Encoding (RLE) Burrows Wheeler Transform (BWT) Move to Front (MTF) Run Length Encoding (RLE) Arithmetic Encoding (ARI). Later on Latin Square was used to form stego key 1and then Vigenere cipher was used to increase complexity of extracting stego key 1. Final step was to choose e-mail addresses by using stego key 1 (K1) and stego key 2 (K2) to embed secret message into forward email platform. The experimental results showed that proposed method has reasonable performance in terms of capacity and also higher security in terms of complexity.
Transient Analysis of 380-kV Transmission System of Central Anatolia of Turkey
(IEEE, 2012) Aydın, Musa; Ünver, M. Uğur
In this paper, switching overvoltages are studied on part of 380 kV interconnected network of Central Anatolia of Turkey, which contains six busbars that are interconnected with five different transmission lines of different lengths and geometries. The studies are carried out by an electromagnetic transient software program called PSCAD/EMTDC. Overvoltages that take place due to energizing a line on no-load condition and switching off a line under load condition are studied and voltage related curves are obtained and their magnitudes are calculated by means of the computer. This study has the characteristic of being unique, since it is the only computer aided study which has been done on the interconnected system of Central Anatolia of Turkey.

Güncel Gönderiler