10
Archived Theses
0
DOIs Assigned
0%
DOI Rate
Discipline
İndüktif motorlarda uzman sistem ile vibrasyon analizi
This thesis presents an expert system for induction motor fault detection based on vibration analysis by using corvid expert system. Vibration signals of induction motors on four different actuating mechanism are collected with a specific vibration measuring device. The device evaluates the values with three harmonics in frequency domain. Expert system provides the recommendations as maintenance activity or the reason of the vibration by using vibration values. This system is tested and validated on four type of actuating mechanisms. Obtained results show that this system can detect faults in early stages with high accuracy and reliability. Thus, it provides malfunction and failure prevention and improves overall performance and efficiency of industrial systems.
RF enerji hasadi için empedans eşleştirme ve kalite faktörünün araştirmasi
The technology of energy harvesting has received a lot of attention by the researchers in light of the widespread use of electronic devices, especially wireless ones. It has become one of the most important research topics in the world for providing easy and free energy sources. This thesis presents the effect of RF energy harvesting parameters depend on the harvesting system efficiency and the output DC voltage for input power between -35dBm to 25 dBm. In this study, multi-stage Dickson voltage multiplier (DVM) from two to six stages are designed and implemented for various load resistance (i.e. 20, 50, 100, 500, and 1000) kΩ and with a different matching topology such L-matching, T-matching, and Pi-matching. Two Schottky diode models (e.g. HSMS-2852 and HSMS-2822) are used to design the DVM to see their effect on the efficiency and output DC voltage, also to show the quality factor for different impedance matching topology's. All the simulations were done by using the Advance Design System (ADS) 2017. The target frequency selected in the design is 915 MHZ for Industrial, Scientific and Medical Radio Band (ISM band). The simulation results showed an improvement in term of efficiency for the DVM circuit design with matching compared to the DVM circuit without matching at the low level input power. Also, the simulation results show that low load usage increases the efficiency of the harvesting circuit. Besides, using a HSMS-2852 Schottky diode model is better in term of efficiency than the HSMS-2822. And also, for low input power the harvesting system with matching circuit give an advantage over the harvesting system without matching circuit for all design depend on the efficiency level.
İleri biyolojik atık su arıtma tesislerinde koku kontrolü
Atık sular, özellikle kentleşmenin çoğalması ile beraber ve sanayileşme, globalleşme denklemi ile daha yoğun işlenen bir "alan" olmuştur. Bu "alana" yönelik birçok yöntem ve uygulama maalesef ki istenilen neticeyi tam anlamıyla verememektedir. Her ne kadar sağlık açısından sorunsallar hafifletilse de koku, görüntü ve diğer kötü neticeler ile halen mücadele edilmekte ve yeni metotlar literatüre kazandırılmaktadır. Atık su arıtma tesisleri ile işletmeler buna mühim ölçüde yanıt vermekle beraber şikayetleri de en az düzeye indirgemeyi başarabilmektedir. Yalnızca koku kontrol ünitelerinin olmadığı ya da istenen optimum düzeyde sisteme entegre edilemediği durumlar ise maddi ve manevi birçok soruna sebep olmaktadır. Bu çalışmanın amacı, atık su arıtma tesislerindeki koku kontrol ünitelerinde PLC kontrolü ve SCADA kullanılmasının etkisini analiz etmektir. Her ne kadar literatürde atık su arıtmaya yönelik ve atık su koku kontrol üniteleri bağlamında pek çok çalışma olsa da PLC kontrolü ve SCADA ile çözüm noktasında istenilen düzeyde çalışmalar bulunmamaktadır. Bu çalışma literatürdeki bu eksikliği gidermeyi amaçlamaktadır.
Alanlara göre robot yolu planlamasıbulanık c-ortamlarını kullanarak segmentasyonalgoritma ve partikül sürüoptimizasyon
Mobile robotics is a valuable tool for exploring environments inaccessible to humans due to their remoteness, cost or danger, and for performing unpleasant or laborious tasks. It is a relatively new field, until recently experimental, but it is already being applied to real problems with satisfactory result. In this work we have designed and implemented a system whose main purpose is to plan trajectories for this mobile robot. The main goal of this work is to decrease the cost of hardware implementation by using 3d design to simulate and environment which the robot can find the optimal path in it, we use the fuzzy C-means algorithm to cluster the image of the robot camera and the gray wolf optimization algorithm to decide which path to take.
Sözleşme algılamanın uygulanmasımakine kullanılan IoT ağlarında sistem öğrenme
Since the last decade, Internet of Things (IoT - Internet of Things) solutions have been created and applied in different branches of society, such as solutions for transport and urban communication, for example. In this way, IoT is a new paradigm, which is composed of a global network of machines and devices capable of interacting with each other [4]. IoT changes the way some real-world problems can be modeled in the cyber environment, and this is due to the ability to list device units on the network to perform small tasks, and then group the results. In this work we have designed and implemented a system whose main purpose is to assist in the process of implementing this approach, a machine learning technique known as Active Learning was used. This technique was chosen in the context of this work, due to its potential to induce predictive models from databases with the lowest number of labels. Thus, a particle swarm algorithm PSO was used on the database, which consists of a supervised learning algorithm to validate the results obtained, a second predictive model was induced, which did not use active learning for sample selection.This model was used as a basis for comparative analysis of the model resulting from the proposal of this work.
Detection of malicious URLs using machine learning
Data is a valuable and significant asset in computer systems for businesses, institutions, and governments, and it must be protected from malevolent computer crimes that try to steal and sell it. and be threatened by the most common URLs addresses and this threat is considered a cybersecurity threat and uses malicious URLs link containing unwanted content such as (spam, phishing, download- from the drive) and thus users are victims of fraud and are the loss of money or theft of information and software installation. Previously, malicious URLs were often detected by blacklists, but they currently lack edited URLs addresses that are newly created. The focus of the attackers is to use more effective methods of stealing information, which is phishing technology, which is one of the most used types of social engineering. Therefore, the research aims to develop a model to detect and classify URLs into legitimate URLs or malicious URLs by using Machine learning techniques, algorithms, and the lexical feature extracting from URLs. We also verify that a new set of samples that were never trained on as well as a plausible scenario that the predictive model can predict processes can distinguish between legitimate and malicious samples.
İlişki kuralı veri madenciliği tekniğiyle görüntü bölümlendirme
Smart grids are electric grids that are composed of multiple power sources and devices connected to each other to provide better reliability in power generation and power management, modern developments of the smart grid aim at either improving the control of power sources and loads connected to the smart grid by developing a specialized software/hardware, or by improving the communication within the parts of the smart grid and the central control. In this paper we aim at improving both sides of the smart grid system (communication and control), we propose a fuzzy logic-based controller for renewable energy and fossil fuel sources in a grid and an internet of things-based monitoring system which oversees the state of the smart grid, faults that occur in the grid, and how the fuzzy controller overcomes those faults, all in which provide an extra layer of support to the smart grid.
Makinenin örenmesi ile şeker hastalığını taşhisi
Artificial neural networks have been in the position of producing complex dynamics in control applications over the last decade, especially when they are linked to feedback. Although ANNs are strong for network design, the harder the design of the network, the more complex the desired dynamic is. Many researchers tried to automate the design process of ANN using computer programs. Search and optimization problems can be considered as the problem of finding the best parameter set for a network to solve a problem. Recently, the problem of optimizing ANN parameters to train different research datasets has been targeted by two commonly used stochastic genetic algorithms (GA) and particle swarm optimization (PSO). The process based on the neural network is optimized with GA and PSO to enable the robot to perform complex tasks. However, using such optimization algorithms to optimize the ANN training process cannot always be balanced or successful. These algorithms simultaneously aim to develop three main components of an ANN: synaptic weight, connections, architecture and transfer functions set for each neuron. Developed with the proposed approach, ANN is also compared with hand-designed Levenberg-Marquardt and Back Propagation algorithms.
Biyolojik ve internet sensorlarının kullanımı ile epilepsi nöbetlerinin/ krizlerinin tahmin edilmesi
The biosensors became most important for monitoring patient status; the seizure epilepsy is taken into consideration to monitor the patients and predict their status before the seizure happen. The epilepsy is the 4th most common neurologic disorder affecting people of different ages which about 65 million people affected around the world, this disease is happen randomly and may be caused a sadden unexpected death. The standard monitoring epileptic seizures system involves video/EEG (electro-encephalography), which is bothersome for the patient, as EEG electrodes are attached to the patient head. Seriously, help and alert patient before the seizure is one of the issue that the researchers and designers attention. For that there are spectrums of portable seizure detection systems available in markets which are based on non-EEG signal. This study is conducted to use the combined a portable wrist-band, together with smartphone which can easily carried by the patients. The portable wrist-band integrated four sensors to read the signal of three physiological parameters such as: Electromyography (EMG), Heart rate (HR), oxygen level (SpO2) and accelerometer (ACM) biosensor; for facilitate in providing separable signal variation to recognize the status of patients. The study applied on the Iraqi's patients whom visit the Department of Neurology at Baghdad Hospital, almost all the patients had no-seizure during the EEG-Video recording which was one of the problems was faced during the trials of device, according to this problem the work change from real monitoring into virtual study. In this study was incorporated Arduino platform ‗wrist-band‖ as a component part of the system. From the applied test it showed that the fixed wrist-band is confortable to use by the patient hand. Also, the used sensors were reflected a good signals of the studied parameters. The proposed system provide difference services such as heart rata tracking and oxygen level , user tracking location and emergency notification. The Arduino-wear and android-smartphone side of the proposed system is implemented by the Android studio using java programming, while the portable written by Arduino programing language. The results of the proposed system response show a promising outcome that can depend on for predicting the seizure. Keyword: Biosensors, Wearable sensors, Epilepsy, Seizures, Non-EEG, EMG, Autonomic Alterations in Epilepsy
K-mer sekans gösterimine dayalı microRNA-hastalık ilişkilerinin ve microRNA-tür ilişkilerinin sınıflandırılması
The dysregulated gene expression brings about a variety of diseases, and dysregulation of microRNA (miRNA) has a wide impact on disease development and cellular physiology. Thus, miRNAs play important roles in a variety of fundamental and significant biological processes related to human diseases. There are a lot of research about changes in the function of miRNAs have been published in many human diseases. Computational methods serve as a complementary process to traditional wet-lab experiments, which require many resources and time in terms of detecting potential miRNA-Disease associations. Furthermore, there is a need to present a novel approach that allows assignment of an unknown miRNA to its most likely species. An easy way to filter new data would be to ensure that the new miRNA is classified below the maximum distance to the species known to originate from. In this thesis, a computational model has been proposed for identifying miRNA-disease and miRNA-Species associations by depicting the miRNAs with their k-mer sequence representation and by utilizing machine learning methodologies. The difference of our approach is which we reveal disease and species associated the sequences of miRNA store information. This put a question about the miRNA's chemical compounds and their associations with different types of species and diseases. With this study, the new disease-disease and species-Species associations disclosed can be calculated for many different species and diseases, these approaches can develop to species and disease classification. Lastly, our study may open a door to redefine species and diseases classifications which have been used nowadays, also it may provide the improvement of treatment strategies and early diagnosis