Search

Magnetic Levitation System (MLS) has become a current study in the field of engineering due to its advantages such as low energy consumption and minimum friction. MLSs are nonlinear unstable systems. Due to the complexity of the structure and the difficulty of the controls, many advanced control theories can be applied on these systems and the performance of the controllers can be evaluated. In this article, Proportional-Integral-Derivative (PID) and Linear-Quadratic Regulator (LQR) controller methods are applied on MLS mathematically modeled in MATLAB environment. Controller performances were compared in the results found. The results obtained on the applicability of PID and LQR control methods for MLS were evaluated. In addition, the system performance of the controllers was compared with five parameters. These are rise time, settling time, maximum overshoot, overshoot and steady-state error. LQR controller produced great stability and homogeneous response compared to PID controller.

Battery management systems (BMS) are becoming essential for all types of electric vehicles using battery packs. Various factors, such as battery temperature and balance, directly affect the life, safety, and efficiency of batteries used in vehicles. For security and robustness, these factors should be monitored and adjusted instantly. Today, battery management systems are constantly being developed using different production methods and algorithms. In the studies, calculations are made by measuring parameters such as temperature, current, current balance, load status, and health status of the battery cells, and the control of the battery group is provided with these calculations. Instant and continuous measurement and processing of all these data and the creation of a control algorithm according to the calculation result are possible with the use of powerful processors. FPGA is a processor that can provide the speed and functionality required for BMS. In the battery management system, the FPGA is responsible for receiving and processing all signals from the battery cells and producing results. It instantly processes the data from temperature, current, and voltage sensors and applies the control stage required for balancing. In addition, the charge and discharge capacity of the battery is calculated by instantly measuring the state of charge (SOC). SOC is of great importance in the battery management system to ensure the safety of the battery pack. Therefore, the SOC needs to be estimated accurately and in real-time. Thanks to its parallel processing capability, the FPGA can simultaneously read data from the sensors and perform related calculations. In this study, a versatile system design with real-time, high computational speed for BMS was carried out on FPGA. The voltage and current of an experimental battery based on the embedded system were monitored in real time in a simulation environment. Experimental results show that the instantaneous SOC estimation is successful, and the system returns instant results to the incoming sensor data. The use of FPGA as a management unit will provide significant advantages in BMS with its high operating speed, real-time monitoring, low power consumption, and re-programmability.

In this paper, a simulation study enhanced to model that the speed control of brushless direct current (BLDC) motors used in electric vehicles with intelligent control methods. The simulation study was prepared in Matlab/Simulink environment. The first control method is Type-1 fuzzy logic control (T1FLC), and the second control method is the Intermittent Type-2 fuzzy logic control (IT2FLC) model. Membership functions for different membership numbers have been created for both types of FLC models. These are 3×3, 5×5, 7×7. Control methods are prepared in Matlab/M-file environment. The model is defined as the input variable of the error, which is the difference between the reference speed and the motor speed, and the output variable of the Pulse Width Modulation (PWM) signal applied to the motor. The simulation study maintains the speed of the BLDC motor up to the reference speed with T1FLC and IT2FLC controllers, depending on the reference speed and applied load values. Depending on the number of different memberships, the effects of controller performances on the control of motor speed have been observed. The graphs and findings of the experiment are shown in the results and discussion section.

Beyin-Bilgisayar Arayüzü (BCI), bilgiyi doğrudan beyinden harici cihazlara aktaran ve deşifre eden bir iletişim sistemidir. Elektroensefalogram (EEG) tekniği, işlevleri kontrol etmek için beyinde oluşan komutlara karşılık gelen elektrik sinyallerini ölçmek için kullanılır. BCI'de kontrol uygulamaları için kullanılan sinyallere Motor Görüntüsü (MI) EEG sinyalleri denir. EEG sinyalleri gürültülüdür, bu nedenle örüntüleri doğru tanımak için doğru yöntemleri kullanmak önemlidir. Bu çalışmada, Topluluk Altuzay Diskriminantı sınıflandırıcı kullanarak ağları eğitmek için farklı sınıflandırma şemalarının performansları incelendi. Ayrıca, Komşuluk Bileşen Analizi kullanılarak en verimli öznitelik uzayı bulunmuştur. Sağ yön ve sol yöne karşılık gelen MI sinyallerini sınıflandırmada maksimum ortalama doğruluk, konuya özel bir sınıflandırma şeması ve 250 özellik ile %80,4 olarak bulunmuştur.

BLDC motors have many advantages such as a better speed versus torque characteristics, high dynamic response, high efficiency and reliability, low cost drives, long operating life (no brush erosion), noiseless operation, higher speed ranges, and reduction of electromagnetic interference. For this reason, it is used in many different fields today. A BLDC motor requires an inverter and a sensor to achieve commutation process. However, the hall sensor presents quite a few disadvantages from the standpoint of drive’s cost, machine size, temperature sensitivity requiring special arrangements and noise protection. As a result, with the increasing power of embedded computing in recent years sensorless control techniques have been developed and widely used. Additionly, conventional controllers do not give the desired results as these motors are non-linear in nature. Many techniques for BLDC motor speed control have been developed such as PID, Fuzzy logic controller, adaptive neuro fuzzy inference system. But the responses obtained were oscillatory and when a load was applied to these systems, the system's responses were much lower than the reference value. To remove oscillations and achieve a better performance, some new techniques were required. Due to their ability to handle uncertainty with robust and adaptive structure against complex systems, type-2 fuzzy logic systems, which is one of the artificial intelligence techniques started to use in recently years. In this study, the brushless motor was used as without sensor with back emf technique and zero crossing detection. Type-2 fuzzy logic controller was used to better resolve the uncertainties in the system. Simulation performed in Matlab – Simulink and PID, type-1, type-2 fuzzy logic controller results were compared and as a result, it was observed that type-2 fuzzy logic controller gave the most suitable system response to reference value.

Thanks to their electrochemical structure, batteries are the elements that can store electrical energy and spend on a load when the electrical energy they store is needed. Today, with the widespread use of electrically powered mobile devices, rechargeable batteries have become widespread and battery technologies have developed. With the idea that the latest technology systems and electric vehicles will become widespread in the future, the studies on batteries are increasing day by day. In this study, charge state estimation of Li-ion battery cell used to provide power in many applications was realized by using adaptive neural fuzzy inference system (ANFIS). A Li-ion battery was discharged using variable electrical loads with a battery discharge circuit modeled on MATLAB Simulink and current, voltage, temperature and current power parameters of the battery were selected as input variables. Battery parameters and charge status data obtained from discharge tests using different electrical loads on MATLAB Simulink were used as training and test parameters of neural network. Using the MATLAB ANFIS toolbox, the system was trained with 80% of the battery parameters obtained in the battery discharge experiments and with 20% as testing data, the success performance was interpreted by applying the adaptive neural fuzzy inference system.

This study presents a Zero-IF structured Stepped Frequency Continuous Wave (SFCW) radar system for range, respiration rate, and DOA estimation of the targets behind the walls. The radar hardware is a combination of SFCW and Uniform Linear Array (ULA) techniques. Four main improvements are done in signal processing. Averaging Delay Line Cancellation (ADLC) is proposed for moving-target indication. As a post-processing solution to the disruptive effects, a self-acting SVD-based algorithm is offered. The displacement signals of the targets are obtained after applying an additional phase extraction and wavelet-based filtering to lessen the phase discontinuities and noises. The Direction of Arrival (DOA) is estimated over the positive and negative range profiles of two separate antenna pairs. The median of these four angle values is used as the final DOA estimation. The performance of the system is tested with more than 150 experiments and compared with state-of-the-art studies.

In this study, an unsupervised retina blood vessel segmentation process was performed on the gray level images with PCA and the green channel of the RGB image, which most clearly shows retinal vessels and the results were compared. The average accuracy rate obtained for the gray level image with PCA after the study was 0,9443, while the average accuracy rate obtained for the green channel was 0,9685. The study was performed using 40 images in the DRIVE data set which is one of the most common retina data sets known.

WOS: 000461302800005, PubMed: 30874907, 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., Selcuk University Scientific Research Projects Coordination Office (BAP) [15101020], This work was supported by the project number 15101020 by Selcuk University Scientific Research Projects Coordination Office (BAP).

In this study, it is aimed to improve the maximum range and range resolution while detecting multiple targets’ respiration rates. An original algorithm has been proposed for this purpose, and a Stepped Frequency Continuous Wave radar has been set up for experiments. Experiments have been executed with periodically moving plates and human targets. With a resolution of 30 cm, the detected maximum ranges are 7 m and 6.3 m for moving plate and human targets, respectively. In moving plate experiments, the average accuracies of the frequency measurements are above 98% for both single and multiple-target scenarios. In human target experiments, the average accuracy of the respiration rate measurements is 96.58% for single target experiments while it is 94.44% for multiple targets. The results show that the proposed structure outperforms the state-of-the-art benchmark in terms of the capability of sensing the respiration rate in a wide range with a high resolution.

Electromagnetic filters (EMF) are used to clean magnetic particles in industrial liquids which play important roles to sustain the high-quality material production in industrial fields. In this study, an FPGA-based adaptive fuzzy controller is realized to sustain high performance of an EMF. An experiment is performed by using realized adaptive controller on an EMF set. The results obtained from the experiment are compared with the results of the conventional fuzzy controller. It is observed that adaptive fuzzy controller is performed better than the conventional fuzzy controller.

Image processing is a field of which its popularity increases and continues and, that grows dynamically with new technologies. Nowadays, image processing finds itself in use in almost every field. One of these uses is undoubtedly in the field of medicine, where diagnosis and treatment planning are made from images and, which is constantly changing with newly developed techniques. Of course, the most important factor in using this so widely in the medical field is the acquisition of images on every medical field. With the help of these images, the complaints can be seen more easily and the doctor can follow a path in the treatment of the disease. In our study, we used the Region Growing segmentation method to detect the intestinal mass. This study compares the area determined by the specialist with the area obtained with the segmentation process and, it is seen that the created software system can be used as an auxiliary system to specialist doctors.

International Scientific and Practical Conference Engineering Systems 2019, ISPCES 2019 -- 4 April 2019 through 5 April 2019 -- 155575, An artificial neural network system has been developed to detect Parkinson's Disease (PD). Three samples were taken from each patient and included in the system. The importance of the study is based on the development and use of a new subject-based ANN approach that takes into account the dependent nature of the data in a replicated measure-based design. In order to evaluate the performance of the proposed system, an audio replication-based experiment was performed to differentiate healthy people from PD patients. The UCI Experiment consisted of 80 subjects, half of whom were affected by PD. Although the proposed system has a reduced number of subjects, the system is able to distinguish people with PD from an acceptable degree of healthy people with an accuracy rate of 94.93% in an artificial neural network. © Published under licence by IOP Publishing Ltd., British Association for Psychopharmacology, This study has been supported by Selcuk University’s Scientific Research Unit (BAP).

International Scientific and Practical Conference Engineering Systems 2019, ISPCES 2019 -- 4 April 2019 through 5 April 2019 -- 155575, Tree-seed algorithm (TSA) is a nature-inspired and population-based algorithm for solving continuous optimization problems. The tree-seed relationship is the main motivation of this algorithm. TSA has only two peculiar parameters which are the total number of trees in the stand (pop) and the controller of the seed production (search tendency). Although many problems have been solved in the literature by TSA which is the successful optimizer for low dimensional unconstrained continuous problems, real-life problems have not been addressed yet. In this study, six continuous unconstrained real-life optimization problems (gas transmission compressor design, optimal capacity of gas production facility, gear train design, frequency modulation sounds parameter identification, the spread spectrum radar polyphase code design with 10 decision variables, the spread spectrum radar polyphase code design with 20 decision variables) have been solved. It is seen that choosing the number of the population as 50 and the value of search tendency as 0.1 is appropriate according to experimental results for these problems. © Published under licence by IOP Publishing Ltd.

Wheat is the main food source of the humankind. After its harvest, it goes through many procedures from its separation from chaff to its packaging. With the development in technology, many of these procedures are realized with automatic systems which saves the manufacturer the cost of labour, time and provides the customer with more quality food. One of the main concerns of quality food production is to provide a customer with the product in its purest form which means the product must be separated from all foreign matters. In this study, type-1252 durum wheat seeds have been separated from junk using the morphological properties of wheat seeds through the uncompressed video image taken with the camera Prosilica GT2000c. The main references for the quality measurement of wheat seeds are the shape and the dimensions of a wheat seed. Aiming for high quality wheat grain storage with no junk, this article has adopted various image processing techniques from image preprocessing to feature extraction. The image processing has been realized in a computer environment and the results show that the image processing is successful and the detection of wheat seeds from junk was accurate.

In this study, artificial neural networks (ANN) method is used for the diagnosis of rheumatoid arthritis in order to support medical diagnostics. For the diagnosis of rheumatoid arthritis, backpropagation algorithm was examined in Matlab R2015b environment in artificial neural networks. With the system, the data in a data set, which are received from the patients with rheumatoid arthritis and from the people who are not suffering from rheumatoid arthritis, are classified successfully. Also, ANN backpropagation algorithm results and the results found by Perceptron algorithm are compared in terms of performance. Whereas %82 accuracy percentage is obtained with the Backpropagation method in performance tests in the data set, the accuracy percentage is calculated %71 with Perceptron method.

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 extract features 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.

In this study, the types of wheat seeds are classified using present data with artificial neural network (ANN) approach. Seven inputs, one hidden layer with 10 neurons and one output has been used for the ANN in our system. All of these parameters were real-valued continuous. The wheat varieties, Kama, Rosa and Canadian, characterized by measurement of main grain geometric features obtained by X-ray technique, have been analyzed. Results indicate that the proposed method is expected to be an effective method for recognizing wheat varieties. These seven input parameters reaches the 10-neurons hidden layer of the network and they are processed and then classified with an output. The classification process of 210 units of data using ANN is determined to make a successful classification as much as the actual data set. The regression results of the classification process is quite high. It is determined that the training regression R is 0,9999, testing regression is 0,99785 and the validation regression is 0,9947, respectively. Based on these results, classification process using ANN has been seen to achieve outstanding success.

In this study, an artificial neural network (ANN) was developed to determine whether patients have breast cancer or not. Whether patients have cancer or not and if they have its type can be determined by using ANN and BI-RADS evaluation and based on the age of the patient, mass shape, mass border and mass density. Though this system cannot diagnose cancer conclusively, it helps physicians in deciding whether a biopsy is required by providing information about whether the patient has breast cancer or not. Data obtained from 800 patients who were diagnosed with cancer definitively through biopsy. The definitive diagnosis corresponding to each patient and the data from ANN model results were investigated using Confusion matrix and ROC analyses. In the test data of the ANN model that was implemented as a result of these analyses, disease prediction rate was 90.5% and the health ratio was 80.9%. It is seen from these high predictive values that the ANN model is fast, reliable and without any risks and therefore can be of great help to physicians.

Magnetic filters are used effectively in many industrial areas to clean up technological liquids and gases from micron and submicron size magnetic particles. Performance of the magnetic filter is affected by technological parameters like flow rate of the industrial liquid and concentration and flux magnitude of the magnetic filter. These parameters exhibit differences depending on the field of work. Controlling of magnetic filters without regard to these parameters has disadvantages such as low filter performance, ineffectiveness in parameter changes and high energy consumption. To remove these disadvantages, an adaptive fuzzy control system which considers these technological parameters was designed and realized. When the realized filter is compared to the filter that ignores technological parameters, it is observed that energy can be saved at a rate of 68% annually.

Biodiesel, bioethanol and biogas are the most important alternative fuels produced by using biologic origin sources. Effect of biofuel on engine performance is one of the research subjects of today. The engine experiments to test the engines are many times are hard, time consuming and high cost. Additionally, it is impossible to perform the test outside of limiting values. In this study, an artificial neural network, an artificial intelligence technique, is developed to successfully apply on automotive sector as well as many different areas of technology aiming to overcome difficulties of the experiments, minimize the cost, time and workforce waste. Diesel fuel, biodiesel, B20 and bioethanol-diesel fuel having different percentages (5%, 10%, and 15%) and biodiesel were mixed together, to use in developed artificial neural network. Mixtures were also controlled for their fuel properties and motor experiments were performed to collect the reference values. Power, moment, hourly fuel consumption and specific fuel consumption were estimated by using the artificial neural network developed by using the reference values. Estimated values and experiment results are compared. As a result, from the performed statistical analyses, it is seen that realized artificial intelligence model is an appropriate model to estimate the performance of the engine used in the experiments. Reliability value is calculated as 99.94% (p=0.9994 and p>0.05) by using statistical analyses.

In this study, an artificial neural network has been devised that yields a prognostic result indicating whether patients have cancer or not using their free prostate-specific antigen, total prostate-specific antigen and age data. Though this system does not diagnose cancer conclusively, it helps the doctor in deciding whether a biopsy is necessary by providing information about whether the patient has prostate cancer or not. Data from 121 patients who were definitively diagnosed with cancer after biopsy were used in devising the system. The results of the definitive diagnoses of the patients and the results of the ANN that was performed were analysed using confusion matrix and ROC analyses. As a result of ANN, which was implemented on the basis of these analyses, success rates of 94.11% and 94.44% were achieved for prognosis of disease and validity, respectively. The ANN, which yielded these high rates of reliability, will help doctors make quick and reliable diagnoses without any risks and make it a better option to monitor patients with low prostate cancer risk on whom biopsies must not be carried out through a policy of wait and see.

In this study, a controlled fuzzy expert system (FES) was designed to provide the conditions necessary for operating rooms. For this purpose, existing operating rooms have been studied to see if there are more useful, reliable and comfortable ones. How an operating room can be controlled with FES and its advantages and disadvantages have also been researched. For a theoretically visible FES to show system's advantage a prototype operating room was built and a suitable configuration was designed. In this system, heat, humidity, oxygen and particles were used as input parameters, and a fresh air entrance and fan circulation were chosen as output parameters. With the help of an expert, appropriate linguistic expressions and the membership function of these expressions were defined. The sensors were classified and sensor information was transferred to computer by means of an interface designed. In order to transfer the data to the system simultaneously, an interface was written in C#. Whether it provides the most suitable control for the system prototype was determined by simulating the operation with varying numbers of patients and operation personnel. In these trials, input, output and other necessary parameters were collected in the computer.In the study, we obtained excellent results in prototype operating room control with FES. The analyses of the results carried out indicated that the controls performed with FES provide more economical, comfortable, reliable and consistent controls and that they are feasible in a real operating room.

In this study; a station has been set up containing three cameras, a wifi antenna, a solar power panel and a wind tribune in the wild sheep natural preservation area. To store and process the data collected by the system a unit consisting of a wifi receiver and computer are established in Technology Faculty of Selcuk University. The study are performed on the transferred images in the central unit by using image processing techniques of MATLAB software. In this study, image enhancement process are performed and the best images focused on Anatolian wild sheep are acquired. Improved static images are used for the determination of where the Anatolian wild sheep on the picture, area occupied by the sheep in pixels and number of the sheep by using the techniques of picture partitions.

Artificial intelligence applications are commonly used in industry in many fields in parallel with the developments in the computer technology. In this study, a fire room was prepared for the resistance of wooden construction elements and with the mechanism here, the experiments of polished materials were carried out. By utilizing from the experimental data, an artificial neural network (ANN) was modelled in order to evaluate the final cross sections of the wooden samples remaining from the fire. In modelling, experimental data obtained from the fire room were used. In the developed system, the first weight of samples (ws-gr), preliminary cross-section (pcs-mm2), fire time (ft-minute), and fire temperature (t-oC) as input parameters and final cross-section (fcs-mm2) as output parameter were taken. When the results obtained from ANN and experimental data are compared after making statistical analyses, the data of two groups are determined to be coherent and seen to have no meaning difference between them. As a result, it is seen that ANN can be safely used in determining cross sections of wooden materials after fire and it prevents many disadvantages., {"references":["G. Koca, N. As and N. Arıoğlu, \"Ahşap Dış Cephe Kaplama\nElemanları\", 7. Ulusal Çatı & Cephe Sempozyumu, Yıldız Teknik\nÜniversitesi İstanbul, Turkey, 2013.","A. Kılıç, http://www.yangin.org/, 12 May 2014.","Ahşap Kaplamalar ve Uygulama Esasları, http://www.cs.sakarya.edu.tr/\nsites/ivural/file/AHSAP-KAPLAMALAR.pdf, 15 May 2014.","R. Stevens, S.D. Es van, R. Bezemer and A. Kranenbarg, \"The Structure\nActivity Relationship of Fire Retardant Phosphorus Compounds in\nWood\", Polymer Degradation and Stability, 91, 832-841, 2006.","Yangın Geciktirici Cila Sistemleri, http://www.hemel.com.tr/tr/urunler/\ndefault.aspx?lsn=1&KatID=1020501&UAd=Yangin-Geciktirici-Cila-\nSistemleri, 15 May 2014.","Ş. Tasdemir, S. Neşeli and S. Yaldız, \"Prediction of surface roughness\non turning with Artificial Neural Network\", Journal of Engineering and\nArchitecture Faculty of Eskişehir Osmangazi University 22(9), 65-75,\n2009","S. Tasdemir, S. Neseli, I. Saritas and S. Yaldiz, \"Prediction of Surface\nRoughness Using Artificial Neural Network in Lathe\",\nCompSysTech'08, IIIB.6-1- IIIB.6-8 pp., Gabrovo, Bulgaria, Haziran\n2008.","S. Tasdemir, I. Saritas, M. Ciniviz, C. Cinar, and N. Allahverdi,\n\"Application of artificial neural network for definition of a gasoline\nengine performance\", 4th International Advanced Technologies\nSymposium, Konya, Turkey, 28–30 September, pp. 1030–1034, 2005.","Y. Okayama, \"A primitive study of a fire detection method controlled by\nartificial neural net\", Fire Saf J, 17, 535-553, 1991.\n[10] S.L. Rose-Peherson, R.E. Shaffer, S.J. Hart, F.W. Williams, D.T.\nGottuk, B.D. Strehlen and A. Hill, \"Multi-criteria fire detection systems\nusing a probabilistic neural network\", Sensors and Actuators, B:\nChemical, 69, 325-335, 2000.\n[11] R. Jolivet, T. J. Lewis, and W. Gerstner, \"Generalized integrate-and-fire\nmodels of neuronal activity approximate spike trains of a detailed model\nto a high degree of accuracy\", J Neurophysiol 92, 959-976, 2004.\n[12] A. M. Fernandes, A. B. Utkin, A. V. Lavrov and R. M. Vilar,\n\"Development of Neural Network Committee Machines for Forest Fire\nDetection Using Lidar,\" Pattern Recognition, 37, 10, 2039-2047, 2004.\n[13] W.M. Lee, K.K. Yuen, S.M. Lo, K.C. Lam and G.H. Yeoh, \"A novel\nartificial neural network fire model for prediction of thermal interface\nlocation in single compartment fire\", Fire Safety Journal, 39, 67-87,\n2004.\n[14] W, Xue-gui, L. Siu-ming and Z. He-ping, \"Influence of Feature\nExtraction Duration and Step Size on ANN based Multisensor Fire\nDetection Performance\", Procedia Engineering 52, 413-421, 2013.\n[15] ISO 14001, \"Environmental management systems-Requirements with\nguidance for use\", 2004.\n[16] M. Altin, \"Determining behaviors of fire doors with thermal camera and\ntraditional methods comparatively\", Energy Education Science and\nTechnology Part A: Energy Science and Research, 30(1), 465-474,\n2012."]}

A number of shape features for automatic plant recognition based on digital image processing have been proposed by Pauwels et al. in 2009. Then Silva et al in 2014 have presented database comprises 40 different plant species. We performed in our study a classification process using dataset and artificial neural networks which have been prepared by Silva and et al. It has been determined that classification accuracy is over 92%.

This study is deals with artificial neural network (ANN) and fuzzy expert system (FES) modelling of a gasoline engine to predict engine power, torque, specific fuel consumption and hydrocarbon emission. In this study, experimental data, which were obtained from experimental studies in a laboratory environment, have been used. Using some of the experimental data for training and testing an ANN for the engine was developed. Also the FES has been developed and realized. In this systems output parameters power, torque, specific fuel consumption and hydrocarbon emission have been determined using input parameters intake valve opening advance and engine speed. When experimental data and results obtained from ANN and FES were compared by t-test in SPSS and regression analysis in Matlab, it was determined that both groups of data are consistent with each other for p > 0.05 confidence interval and differences were statistically not significant. As a result, it has been shown that developed ANN and FES can be used reliably in automotive industry and engineering instead of experimental work.

In this study, the effect of tool geometry on surface roughness has been investigated in universal lathe. Machining process has been carried out on AISI 1040 steel in dry cutting condition using various insert geometry at depth of cut off 0.5 mm. At the end of the cutting operation, surface roughness has been measured using MAHR M1 perthometer. After experimental study, to predict the surface roughness, an ANN has been modelled using the data obtained. Modelling of ANN; tool nose radius (r), approach angle (K), rake angle (Y), tool overhang (L) have been used. In this study, surface roughness (Ra) is output data. The ANN has been designed on PC by using Matlab 6.5 software. Comparison of the experimental data and ANN results by means of statistically t test show that there is no significant difference and ANN has been used confidently.

The aim of this study is to help the doctors for diagnosis process of urinary system illnesses that causes obstruction in the urethra and the bladder. There are several reasons that cause obstructions in the urinary system. The common causes of these obstructions are prostate cancers, verimontanum hypertrophies, detrusor instabilities, urinary incontinence, the bladder cancer and malfunctions. This study is to help the specialist doctors about the evaluation process of the uroflowmetric measurements that are made to determine the intensity of the urinary obstructions. The average flowrate (ml) and the residual urine volume measured in the bladder are accepted as the input variables of the fuzzy logic system. The output variable is the urinary obstruction rate of the urethra. When the obstruction reaches the dangerous levels, it means that the severity of the obstruction in the urethra is high and this obstruction can easily give harm to the kidneys and at the advanced stages of the illness it can cause real failure. Matlab 7 Fuzzy Logic Toolbox is used for the simulation of the fuzzy logic urinary obstruction diagnosis system.

In this study, in order to determine the resistance characteristics of self-compacting concrete (SCC) samples, experiments were done in the Konya Cement Factory, Ready-mix Concrete Establishment. Four different mixture proportions were chosen in the experimental study. 24 samples of the 4 mixtures were selected in order to set the cube compression strength. For each mixture, these 24 samples were broken down within 28 days and the characteristics of cube compression strength were obtained. After 28 days, compression strength average was found to be 50.0300 MPa. A model of Artificial Neural Network (ANN) was designed for this study and the results were obtained in this model of ANN. Both experimental and ANN data was analyzed with SPSS statistical packet software. The result of statistical analysis (p=0.9972) has been done in 95% of confidence interval. It has been seen that the ANN can be used as reliable modelling method for similar studies.

Construction (building) sector is one of the sectors which adapt the rapid development of the technology. Especially in frame (skeleton) systems, very serious studies on columns that are vertical conveyors (carriers) are being done. Generally, these studies are implemented by experimentally and computer software is used in these studies as they offer good results.Artificial neural network (ANN) has been used in several engineering application areas including civil engineering. The use of ANN to predict the behaviour of reinforced concrete (R/C) members, using the vast amount of experimental data as a test-bed for learning and verification of results, proved to be available method for carrying out parametric studies.In the present study, columns under the axial load were manufactured from concrete that has been produced without carrying out the standards. Load conveying capacities and tension-unit deformation relationships of columns manufactured with different geometrical and equipment (outfit) properties and same cross-section area have been investigated. At the same time, research has been done via modelling by using ANN that is one of techniques of artificial intelligence and gained importance in recent years. SPSS statistical packet program is used to evaluate the results of this research. After comparisons of results obtained in the experiments, it has been determined that square column samples have the most axial load conveying capacity. It has also been determined that number of displacement is less in samples of columns wrapped (winded) with fret comparing to samples of columns wrapped with stirrup. The same results are obtained after modelling by ANN. As the result of statistical analyses that have been done in %5 reliability interval between data obtained from experiments and ANN, it has been seen that ANN can be used as reliable method.

One of the most effective methods to clean magnetic particles in industrial liquids is magnetic filtration. Magnetic filters (MF) are being used increasingly since they can work under various conditions like high temperature and radioactivity. However, there are many factors like particle concentration and flow speed that affect magnetic filter performance (MFP). In this study, a portable, compact MF kit that cleans micron-sized magnetic particles and is suitable for industrial purposes was designed and realized. A FPGA based fuzzy control system that considers the factors which influence MF performance was developed and integrated with MF kit. With this control system both the MF performance is kept at maximum and MF can clean itself. Thus, besides an effective filtration process which increases quality, sustainability of production and energy save is achieved.