المستخلص: A pattern recognition system based on the n - tuple technique is developed and evaluated for use in classifying non - deterministic data with particular reference to medical image. The pattern recognition system presented in this work fulfills the requirements of simplicity and efficiency making it attractive to practical use in present day for industrial and medical environments. It is an effective solution for providing healthcare with reduced cost, especially for the rural areas and far away patients. Ordinary doctors (not specialist in blood diseases), will be able to perform extra - ordinary tasks.In this work Digital Learning Network has been designed for classification of different shapes of abnormal Red Blood Cells. Digital Learning Network is of low cost hardware and implementation, and one shot learning, using networks of RAMs. Many parameters have been investigated in details which affect the recognition rate. These parameters are presented to allow the system to be optimized, giving an increase in the performance of the system. Modification method of Feedback Digital Learning Network, which is an improving process of Digital Learning Network, has been implemented. The obtained results show that high performance (96.6%) can be achieved, providing evidence of the validity of the proposed technique.

الصفحات الاولى:

الكلمات الدلالية:

Pattern Recognition
RAM - based Weightless Neural Network

مكان الجامعة: بغداد

اللغة: الانكليزية

الجامعة: الجامعة التكنولوجية - قسم الهندسة الكهربائية - فرع الهندسة الالكترونية

الدرجة: ماجستير

الموضوع الدقيق: هندسة الالكترونيك

السنة: 2014

الموضوع العام: هندسة الكهرباء والالكترون والاتصالات

اسم المشرف: محمود حمزة المفرجي

اسم المؤلف: سهاد قاسم غلام حسين حداد

التركيب السليكوني النانوي في الخلايا الشمسية Nanostructured Silicon Based On Solar Cells

المستخلص: تعتبر الخلايا الشمسية تكنولوجيا واعدة وقابلة للتجديد حيث ازداد الطلب عليها نتيجة لزيادة الاهتمام بالطاقة الكهروضوئية. ان التحسين المستمر لكفاءة الخلايا الشمسية بايجاد التقنيات والمفاهيم الجديدة يجب ان يمتد على نحو متزايد باعتبارها واحدة من اهم مصادر الط | The demand for solar cells has been growing rapidly with an increasing social interest in photovoltaic energy. The improvement of energy conversion efficiency of solar cells is performed by developing the technology and concepts that have been increasingly extended as one of the key components in our future global energy supplement. But, the main problem of photovoltaic modules are their rather high production and energy cost. Three generations of solar cell technologies have been established in the previous century.Nanostructured silicon substrates based on p - type crystalline Silicon (c - Si) have been prepared in this work. Electrochemical Etching (ECE) of the Silicon (Si) wafers in Hydrofluoric (HF) acid was employed to synthesize porous layers consisting of silicon nanostructures. The process was carried out at different etching time and different current densities which are considered as effective parameters in ECE process. It is found that a homogeneous porous layer could be obtained with porosity value of (87%) when the current density is (60 mA/ cm2) and the etching time of (10 min). Among the Transparent Conductive Oxide (TCO) materials available, Zinc Oxide (ZnO) films show promising electrical and optical properties in combination with low cost alternatives. It can function as Anti - Reflecting Coating (ARC), window material, transparent electrode and active layer in heterojunction solar cells. n - type ZnO thin films are grown on p - type nanostructured silicon substrates by using Pulsed Laser Deposition (PLD) technique with Q - switching Nd : YAG laser beam Second Harmonic Generation (SHG) [?=(532 nm), number of pulses (140) pulses, and laser energy (820 mJ)], vacuum of (10 - 3 Torr), ambient oxygen pressure of (10 - 1 Torr), and substrate temperature of (400 °C). The morphological, optical, chemical and structural properties were investigated using Atomic Force Microscopy (AFM), Ultraviolet - Visible (UV - VIS) spectroscopy, Fourier Transform Infrared (FTIR) spectroscopy, and X?Ray Diffraction (XRD) techniques, respectively.Surface morphology and optical properties results show densely packed highly crystalline growth of ZnO thin film on nanostructured silicon substrate grown at optimum condition with an average grain size around (88.57 nm). The average roughness, root mean square, and ten - point height estimated from AFM quantitative analysis, are found to be (3.02 nm), (3.62 nm), and (8.76nm) respectively. The thickness is calculated and found to be (100 nm). The film shows high transparency (above 80%) and the estimated Energy - gap (Eg) is found to be about (3.4 eV). This is important for its applications as transparent conductive films and solar cell windows. The chemical and structural properties results characterize ZnO at (420 cm - 1) and (766 cm - 1) absorption bands respectively and the thin film is polycrystalline with hexagonal Wurtzite structure.