https://repository.sustech.edu/handle/123456789/23801 Thu, 09 Apr 2026 00:48:48 GMT 2026-04-09T00:48:48Z https://repository.sustech.edu/handle/123456789/24280 A Type-2 Fuzzy Logic Based System for Decision Support to Minimize Financial Default in the Sudanese Banking Sector Salih, Ahmed; Hagras, Hani The recent global financial-economic crisis has led to the collapse of several companies from all over the world. This has created the need for powerful frameworks which can predict and reduce the potential risks in financial applications. Such frameworks help organizations to enhance their services quality and productivity as well as reducing the financial risk. The widely used techniques to build predictive models in the financial sector are based on statistical regression, which is deployed in many financial applications such as risk forecasting, customers’ loan default and fraud detection. However, in the last few years, the use of Artificial Intelligence (AI) techniques has increased in many financial institutions because they can provide powerful predictive models. However, the vast majority of the existing AI techniques employ black box models like Support Vector Machine (SVMs) and Neural Network (NNs) which are not able to give clear and transparent reasoning to explain the extracted decision. However, nowadays transparent reasoning models are highly needed for financial applications. This paper presents a type-2 fuzzy logic system for predicting default in financial systems. the researchers used a real dataset collected from the banking sector in Sudan. The proposed system resulted in transparent outputs which could be easily understood, analyzed and augmented by the human stakeholders. Besides, the proposed system resulted in an average recall of 83.5%, which outperformed its type-1 counterpart by 20.66%. Thu, 26 Dec 2019 00:00:00 GMT https://repository.sustech.edu/handle/123456789/24280 2019-12-26T00:00:00Z https://repository.sustech.edu/handle/123456789/24279 Study of High Pressure Heaters and Its Influence on Operation Cost in Power Plants: Case Study Garri -4 O. Aburass, Tariq; Nogoud, Yasser; M. Osman Mohammed, Ahmed -Electricity is one of the most important achievements that modern sciences have given to mankind. It became a part of modern life and one cannot think of a world without it. It has many uses in our daily life. Recently, in Sudan, there are some problems related to its continuity and availability of electrical and thermal power generation. This paper presents a part of the solution for the generation of thermal power for Garri-4. The characteristics of electrical energy are sustainability, easy transmission, and easy utilization. All these factors make electrical energy desirable. The main problem of electrical power is the high cost of production due to the high cost of fuel. Through the centuries, there is a lot of work done to reduce the energy cost, by rising up the efficiency and increase the performance of the systems. This paper shows the effect of high-pressure (HP) heaters out of service in the Garri-4 power plant. It aims to investigate the influence of HP heaters on the power plant's overall performance. The mathematical modeling is used through thermodynamic and heat transfer equations to study the efficiency and the operation cost for the power plant. The paper concludes that HP heaters have a clear influence on the power plant performance by increasing the overall power plant efficiency and reduce the operation cost. It also makes it less harmful to the environment through less emission due to less fuel consumption. There is an increase the overall power plant efficiency by 3.78% , 1.03%., and 2.56%, from 27.67%, for different cases studied in this paper Thu, 26 Dec 2019 00:00:00 GMT https://repository.sustech.edu/handle/123456789/24279 2019-12-26T00:00:00Z https://repository.sustech.edu/handle/123456789/24193 Recognition of Correct Pronunciation for Arabic Letters Using Artificial Neural Networks M. K. Osman, Abeer; A. Ibrahim, Hussain; Adaney, Mohamed Automatic speech recognition (ASR) plays an important role in taking technology to the people. There are numerous applications of speech recognition such as direct voice input in aircraft, data entry and speech-to-text processing. The aim of this paper was to develop a voice-learning model for correct Arabic letter pronunciation using machine learning algorithms. The system was designed and implemented through three different phases: signal preprocessing, feature extraction and feature classification. MATLAB platform was used for feature extraction of voice using Mel Frequency Cepstrum Coefficients (MFCC). Matrix of MFCC features was applied to back propagation neural networks for Arabic letter features classification. The overall accuracy obtained from this classification was 65% with an error of 35% for one consonant letter, 87% accuracy and an error of 13% for 10 isolated different letters and 6 vowels each and finally 95% accuracy and an error of 5% for 66 different examples of one letter (vowels, words and sentences) stored in one voice file Sun, 22 Dec 2019 00:00:00 GMT https://repository.sustech.edu/handle/123456789/24193 2019-12-22T00:00:00Z https://repository.sustech.edu/handle/123456789/24097 Review on Image Guided Surgery Systems Omara, Akram; M. Gaddoura, Omer; B. Eltayb, Megdy Nowadays modern imaging techniques can grant an excellent quality 3D images that clearly show the anatomy, vascularity, pathology and active functions of the tissues. The ability to register these preoperative images to each other, to offer a comprehensive information, and later the ability to register the image space to the patient space intraoperatively is the core for the image guided surgery systems (IGS). Other main elements of the system include the process of tracking the surgical tools intraoperatively by reflecting their positions within the 3D image model. In some occasions an intraoperative image may be acquired and registered to the preoperative images to make sure the 3D model used to guide the operation describes the actual situation at surgery time. This survey overviews the history of IGS and discusses the modern system components for a reliable application and gives information about the different applications in medical specialties that benefited from the use of IGS. Sun, 15 Dec 2019 00:00:00 GMT https://repository.sustech.edu/handle/123456789/24097 2019-12-15T00:00:00Z