Department of Electrical and Electronic Engineering

Permanent URI for this collection

Browse

Recent Submissions

Now showing 1 - 5 of 319
  • Item
    Remote Skin Diseases Diagnosis System Using Machine Learning Techniques
    (University of Khartoum, 2017) Edrees, Rana Mohammed Alhadi Abdalkareem Alsheikh
    Skin diseases have become one of the most common diseases all over the world, beside their painful effects they are spreading very fast to cover a larger area and also have a psychological effect to the patients, the diagnosis of the skin diseases requires a high level of expertise and they are subjective to the dermatologist, so computer aided skin diseases diagnosis system is proposed to provide more objective and reliable solution to this problem. This project aims to develop skin diseases diagnosis system with a mobile interface, the system is built on a machine learning model to classify the infected images using Bag of Features Model with SVM classifier and develop an ANDROID interface application to capture the images, the designed model has successfully able to classify the infected images of 3 sample classes with accuracy 94% of cross-validation method and 85% of holdout method. The system is built successfully and the interface application is communicating properly with the server established, and all the system functionalities is working properly, despite that there are some problems occurred through the development of the system starting with the data collected that are distorted by a watermark that obstacle the classification process and the synchronization between the server and the client sides of the system, The system developed is using a single server, which by the increase of the number of the users will face a performance issue, and also the system interface is available for the android users only, these are the proposed future improvements of the system
  • Item
    Design & Development of a Raspberry Pi Daughter Board to Support Bluetooth Communication Using Uart University of Khartoum
    (University of Khartoum, 2017-10) Mohammed, Mohannad Alhassein Alhassan
    Reliable and secure communication between two or more devices requires a wired connection. Wireless communication standard such as – Bluetooth, Wi-Fi, Zigbee etc. provide a flexible and inexpensive solution for remote applications. A large number of low cost hardware platforms such as Raspberry Pi, Arduino, embedded boards etc. are available that do not provide any built-in wireless modules but are equipped with UART, I2C ports for design and development of Internet of Things (IoT) and embedded applications. Designers face the difficulty of using such a low cost hardware for wireless communication in order to implement these applications. In this paper, Design & Development of a Raspberry Pi Daughter Board to support Bluetooth communication using UART is proposed as an integrated solution to this issue. Results of various Quality of Service parameters such as transmission rate, file format (text, pdf, image, and audio), baud rates, and range for Bluetooth communication between two devices are presented. The result shows that Bluetooth module is capable of transmitting files of different sizes at the same rate per KB. Proposed solution can further be extended to different protocols such as Wi-Fi and Zigbee etc.
  • Item
    Speech Activity Detection Implementation in Hearing Aids Using Deep Belief Network
    (University of Khartoum, 2017-10) Elbasheer, Eithar Alfatih Abdalrahman
    Hearing aids are small devices, hearing impaired and deaf people wear to compensate their hearing losses. Most of the affordable available hearing aids nowadays are designed only on one environment and for certain hearing characteristics. In our work, we proposed an intelligent hearing aid that is able to adjust to changing environment and it can be designed according to the patient hearing characteristic. Speech activity detection is implemented using deep belief networks. This step is used so that different processing steps will be done to the audio signal before it reaches the human ears. Two different features have been used to train the DBN and a comparison was made between them. MFCC and LPCC features were used and gave similar output results. A choice of using LPCC features is made because of they are easy to implement.
  • Item
    Design and Implementation of Temperature and Humidity Monitoring System for High Performance Servers Room University of Khartoum
    (University of Khartoum, 2017-10) Ahmed, Abadi Haider Mohammed
    Servers are used in organizations for storing and securing important data and providing a connection inside the organization (network). These data should be kept safe and accessed, therefore the safety of servers is essential for an organization to fulfill its goals and objectives. The Information Technology and Network Administration has servers that provide all important data and network distribution inside the University of Khartoum. The servers are in rooms where they should be kept in continuous observation and monitoring for keeping them safe and functional. Therefore, the Information Technology and Network Administration requested a design of a temperature and humidity system for the servers. The goal of this project is to implement the temperature and humidity system that will perform the observation and monitoring of the servers in the rooms, as well as sending alert messages to a specified phone number when the temperature and humidity exceed certain values that might affect and damage the servers. Another objective is to design a graphical user interface to give a user the control and accessibility to change the settings of the temperature and humidity sensor by entering the values that might damage the sensor and the desired phone number. The temperature and humidity system was implemented on a Printed Circuit Board (PCB). The system gave results when compared with other systems that measure temperature and humidity and gave a good accuracy.
  • Item
    Software Platform For Cellular System Performance Evaluation & Raw Data Collection
    (University of Khartoum, 2017) Wasfi, Mohammed Mahmoud Mohammed
    The mobile network operators always aspire to provide the best services to their clients, without any loss of data or interferences. Therefore, the ability of the mobile network operators to evaluate the performance of their networks is now more important than ever. One of the methods used to evaluate the performance of the network by collecting and analyzing raw data from the network is the Drive Test method. Although the Drive Test method fulfil the needs of the mobile networks operators, it is considered expensive and time consuming. In this thesis, a software platform is introduced as an alternative cheaper method that makes the data available at any time. The platform consist of a mobile application for raw data gathering, which is installed on the mobile phones of the clients. The data gathered is then sent to a web application, which is used to review the data and represent it in different forms for ease of read and analysis. The aims and objectives of this thesis was met, and the results obtained is encouraging. The platform was able to collect useful raw data, which might be used to evaluate the performance of the network. In addition, it was able to display the coverage and the quality of the network using the data acquired. The software platform was reviewed to state all possible future work, which can make it a suitable replacement for the Drive Test method.