Theses supervised by Mehmet Bodur
10 theses · Eastern Mediterranean University
Prediction of International Stock Market Movements Using a Statistical Time Series Analysis Method
The thesis has used econometric time series models to model and forecast the development in closing prices of main international stock markets. These are New York, London, Tokyo and Shanghai stock market. The time series data set includes the trading days from 1st January, 2008 to 31st December, 2012 i.e. (5 years). After pre-processing the data to substitute the missing values using interpolation method and convert all closing prices to USD currency, the first attempt of this thesis employs the Auto Regressive Moving Average (ARMA) framework, which has been used to model a time series data set. It is found that the model can be used to fit the data in the estimation period. The Root Mean Square Error (RMSE) is used to find an estimating order of the parameter in ARMA model i.e. r, m proper values. The forecasting process is constructed based on the ARMA model to forecast the future value for the data indices in the period (2010-2012) in New York, London, Tokyo, and Shanghai stock market. The idea of forecasting in this work is predicting two-days-ahead closing price based on previous two years closing price for each two days. The forecasting is very important in the analysis of economic and industrial time series, and in sailing and buying movement. The money was invested in these stock markets and the results made it clear that the investment in London stock market is the best investment. Keywords: Time series analysis, ARMA, RMSE, Forecastıng and Investment.
Temporal Ultrasound Image Enhancement for Kidney Diagnosis
Ultrasound imaging enables the physician to view the tissues and organs in abdominal region of the body without hazards of ionization compared to the other radiation based internal organ inspection devices. It provides highly accurate imaging of a kidney on suspected acute renal diseases. This thesis proposes temporal filtering methods to enhance the ultrasound images from ultrasound kidney video for the purposes of identification and diagnosis of kidney diseases by processing consecutive images of the acquired kidney video extending the spatial mean, median and weighted mean image filters to temporal dimension after cropping and aligning the image frames manually in MATLAB by Image Processing Toolbox to suppress speckle noise, and improve information content for a diagnosis by a medical doctor. The assessment of the filtered images by 10 medical experts indicates that the proposed temporal mean, median, and weighted mean filters improve the images better than the common spatial mean, median and weighted mean filters. The evaluators ranked the temporal weighted mean filtered images as the least preferable, while they scored the temporal median filtered images as the best preferable ultrasound images for the purpose of renal diagnosis. Keywords: Ultrasound Kidney Image, Image Enhancement by Video, Temporal Mean filter, Temporal Median Filter, Temporal Weighted Mean Filter.
Comparison of Return Rate Efficiencies of Forecasting Methods in Stock Market Investment
Prediction of prices in stock market is an important research topic to direct investments to items with high return rates. This thesis compares available time series prediction methods for predicting of stock market prices. The available methods that have been employed for time series forecasting are support vector regression, autoregressive moving average and k-nearest neighbours. They are applied on four years of stock market data obtained from London Stock Exchange to train each model and to test the performance of the proposed techniques to select the best forecasting method. The result of the tests show that support vector regression gives less forecasting error compared to other methods of forecasting. Keywords: Stock Market Forecasting, Support Vector Regression, ARMA, k-Nearest Neighbours.
Improving Time Series Forecasting Performance by Fuzzy Decision Fusion
Time series data can be collected in many domains including econometric, signal processing, weather forecasting, and earthquake prediction. Accurate prediction of time series prices is essential for investors, meteorologist, or statisticians. Forecasting of the financial time series has intrinsic complexity due to uncertainties of factors that affect it. In this study, better forecasting of the financial stock market time series movements is targeted using the closing prices of the stock market. In this work, our objective is to implement a set of well-known financial time series forecasting models such as Autoregressive-Integrating-Moving-Average (ARIMA), Exponential Smoothing, Support Vector Regression (SVR), Long-Short Time Memory (LSTM), and to merge the forecasted decision by using fuzzy knowledge-based decision system. The difference of this thesis compared to the previous works is mainly the expert-decided membership functions instead of clustering in building the fuzzy rule base. An experimental demonstration has been carried out on the S&P 500 index using the closing prices of this Index. The results shows that the fuzzy decision fusion procedure gives lower cumulative absolute prediction error than cumulative error of forecasts of each individual model. Keywords: time series, time series forecasting, fuzzy decision fusion, fuzzy logic system, fuzzy rule generation.
Effect of Temporal Filters on Face Images
Face detection from low-resolution videos is a challenging research area. This thesis explores the effect of a temporal filtering method by Dr. Bodur on face images. The temporal mean and median filters calculate the intensity of pixels using the intensities of surrounding neighbour pixels, and temporal neighbour pixels in consecutive images. The effect of the proposed technique on the image is measured by the mean square error (MSE) and the peak signal noise ratio (PSNR) values using the pixels of the original high resolution image as reference values to measure the error and noise figures of the pixels of filtered low resolution images. Results demonstrate a significant effect of the proposed filters on the consecutıve frames of face vıdeo record. In the tests, the medıan fılter ıs found more effective compared to mean fılter. Keywords: Temporal Mean Filter, Temporal Median Filter, Image Resolution, Effectiveness of Image Filter.
Sensitivity Analysis of Change of Currency Exchange ARIMA Modeling Parameters between (0,1,1) and (1,1,0) Depending on Economic Policies
This thesis contains a literature survey of exchange rates, and forecasting exchange rates by using ARIMA models. The thesis shows that the best forecasting ARIMA parameters are changing in time, looking like the characteristics of the time series is changing randomly. A search of forecasting parameters within AR and MA orders 1 to 5 indicated that (1,1,1) is successful in forecasting the five-day ahead values. This study tested the sensitivity of the change of best-forecasting model parameters between AR (p=1, d=1, q=0) and MA (p=0, d=1, q=1) characters by using the financial policy decision dates as a predictor. The test is evaluated on GBP=X time series using the Federal Bank Federal Fund Rate decision dates. The test results indicate that the statistical value of sensitivity for 26 FFR decision dates is almost 5% shifted on the decision dates, indicating that the FFR decisions had a considerable structural effect on the dynamics of the market.
Enhancement of Vehicle License Plate Images by Temporal Filtering
Optical Character recognition is used widely as a tool in intelligent transportation systems for recognition of the car license plate from a still image or video. The accuracy of Optical Character Recognition partially depends on the quality of the input image. In this study, a set of simple and efficient methods are proposed to improve the quality of the car license plate image extracted from video clips to reduce the error rate for the license plate OCR even at low resolutions. Mean, median, and maximum filters are commonly used algorithms to filter noise and enhance an image. The proposed technique by Dr. Bodur extends them to time domain by including the pixels of the consequent images of the video clip in filtering algorithm. The OCR error rate is tested on fifty road and street video clips by decreasing the resolution of the images and filtering them with common and proposed filtering methods. The test results indicate that all proposed methods, improve the accuracy of OCR, and the highest reduction of error is obtained by the proposed temporal maximum filtering method. Keywords: License Plate Recognition, temporal image enhancement, Vehicle Plate OCR.
Visualization of 3D Object on Planar Screen Using View Angle
The aim of this thesis is to develop and demonstrate a practical method to support 3D perception of stationary objects in a virtual space through the motion of a two dimensional projection image. The structure of a human eye is naturally equipped by some tools to perceive the depth from several hints such as the size of image compared to the its expected size, and the sharpness of the image at different focal lengths of the lens, the parallax difference in the images from the left and right eyes, and, if the image moves, by comparing the images at different view angles. In this thesis, the movement of the observer is detected by a software using the video camera frames, and the expected 2D projection of the virtual objects is transformed for the detected position of the observer to support a depth feeling of the observer. The developed program is coded in MATLAB, to determine the position of a red marker that is attached to the head of the observer, to compose the transformation matrix that converts 3D corner points of the virtual objects to expected perspective projection for the determined view-angle, and to draw the projection on the screen for the observation. The code is written in a flexible form to work with any PC with a web-cam, and graphical screen. The implemented system is tested successfully comparing the views of a set of virtual geometric objects on a platform with respect to the view of similar objects physically on a test platform. Keywords: Depth perception, Colour detection and tracking, 3D-visualization. ÖZ: Bu tezin amacı sanal uzaydaki duran nesnelerin 3D algısını iki boyutlu izdüşümlerindeki hareket aracılığıyla destekleyen bir yöntem geliştirmek ve göstermektir. Insan gözü doğal olarak görüntünün büyüklüğüyle beklenen büyüklüğünü karşılaştırmak, görüntünün değişik odak derinliklerindeki keskinlik ve bulanıklığı, sağ ve sol göz görüntülerindeki fark, ve görüntü hareket ederse değişik gözlem açılarından görünüşünü analiz gibi derinlik algılamaya elverişli bir takım araçlarla donatılmıştır. Bu tezde, gözlemcinin hareketleri bir yazılım sayesinde bir video kameranın yolladığı çerçevelerden algılanarak sanal nesnelerin belirlenen gözlemci yerine karşılık beklenen 2D izdüşümlerine dönüştürülerek, bu yolla, gözlemcinin nesneler hakkında bir derinlik duygusu oluşturulması sağlanmaktadır. MATLAB’da kodlanmak üzere geliştirilen program gözlemcinin başına iliştirilmiş kırmızı bir işaretin yerini belirlemekte, ve gözlemcinin bakış açılarını tayin ederek sanal nesnelerin 3D köşe noktalarının perspektif izdüşümü için gereken dönüştürme matrisini hesaplayıp ekrana 2D izdüşümünü çizmektedir. Kod, video kamera ve grafik ekran donanımlı herhangi bir PC de çalışacak esneklikte yazılmıştır. Uygulanan sistem sanal geometrik nesnelerin görünümlerini benzer nesnelerin fiziksel bir test platformundaki görüntüsüyle karşılaştırılarak başarıyla sınanmıştır. Anahtar kelimeler: Derinlik algısı, Renk tespit ve izleme, Üç boyutlu-görüntüleme,
Development of Topological Mappings for Autonomous Agricultural Vehicles
Automation system of agricultural crop plantation requires many subsystems such as low level tracking, path planning, obstacle detection, manoeuvres at the path terminations, etc. This study proposes semantic annotation for the information flow between the automation subsystems, filling the gap between the planning and implementation of crop production by developing two missing subunits: determination of obstacles that may threaten agricultural vehicles using the satellite images of target field, and determination of proper path for the agricultural vehicles to process rows of crops. For the attributes of obstacles, semantic annotation on the map of target field is preferred using Resource Description Framework/Extensible Mark-up Language (RDF/XML) in order to be exchangeable and reusable with other stages, systems, devices and applications. Developed Matlab code determines the target field by a GPS coordinate inside the field. An interactive initialization stage provides download of the satellite images from Google Maps API for determination of the field boundaries. The code for detection and positioning of the circular shaped obstacles are using Prewitt, Sobel, Roberts, and Canny edge detection, and Hough transformation algorithms. The developed method is tested on 51 target fields. It provides 45% improvement in detection error rate compared to raw application of the algorithms. Keywords: Image processing, Obstacle detection, Path planning, Semantic annotation, RDF/XML mapping.
Prediction of International Stock Market Movement Using Technical Analysis Methods and TSK
This research aimed to propose a method to improve forecasting accuracy of the technical analysis of future closing price using Takagi-Sugeno-Kang (TSK) fuzzy model to merge the forecasting of three technical prediction methods. The historical data available for London Stock Market is employed in this study to verify the performance of the proposed model compared to technical predictions. Fuzzy data modelling emerges as an advanced technique in predicting future closing prices. In this study, the predictions of three technical analysis methods were modelled by Fuzzy Methods to enhance the predicted closing price. The fuzzy rules were extracted by using Fuzzy-C-Means (FCM) algorithm. Data set from year 2008 to 2012 is dividing in two parts for training and verification purpose. The Fuzzy C-Means clustering (FCM) is applied on the six days Moving Average (SDMA), the Moving Average Convergence Divergence (MACD), and the Relative Strength Index (RSI) technical analysis to predict the future price, which is, target variable of the TSK fuzzy model. A prediction accuracy close to 94.7%, is achieved in predicting two days ahead closing prices of London Stock Market. The results are very encouraging and easy to implement in real-time trading system. Keywords: Technical Forecasting, Fuzzy Modelling, TSK, FCM, clustering, moving average.