Browsing Theses & Dissertations by Title
Now showing items 367-386 of 677
-
Human stress level computation using multiple physiological signals-based on fusion technique through dynamic bayesian network
(Universiti Malaysia Perlis (UniMAP)School of Mechatronic Engineering, 2014)This study investigates to improve the stress levels computation and its reliability using multiple physiological signals. In which, stress inducement, physiological signal acquisition, preprocessing, feature extraction, ... -
Human-machine interaction by tracking hand movements
(Universiti Malaysia Perlis (UniMAP)School of Mechatronic Engineering, 2013)The vision-based hand tracking and gesture recognition is an extremely challenging problem due to the intricate nature of hand gestures this is a reason that available computer vision algorithms are computationally complex. ... -
A hybrid human sensory mimicking approach: an integrated e-nose and e-tongue system
(Universiti Malaysia Perlis (UniMAP)School of Mechatronic Engineering, 2012)Taste and smell are two of the five human senses that are common among mammalians. These two senses are usually used together to make up the brain’s perception of flavour. This has lead to the study of data fusion ... -
A hybrid input - output based relation test suite generation strategy
The cause of large enumeration space the systemized sample test data have the active research to meet t-way testing strategies during the previous 20 years Hence that (t) indicates to interaction strength Despite of ... -
Hybrid solar and grid-connected system with multi-mode operations
(Universiti Malaysia Perlis (UniMAP), 2012)Solar energy is beginning to take place as the most important alternative energy source in replacing conventional fuels such as crude oil, coal and natural gas. This is due to the increasing of energy demand in which ... -
I-V curve tracer based on capasitor charging method for photovoltaic (PV) power system
Measuring the I–V characteristics is of high importance since it can be considered as a quality and performance certificate for each PV generator. The capacitor charging method is considered as the cheapest and most ... -
Identification and characterization of natural latex from Tapioca (Manihot Esculenta)
This research was focused on the identification and characterization of natural latex from tapioca. The extraction of natural latex from tapioca leaves and stalk was made up by using blender method. The chemical properties, ... -
Image analysis for blood spatter problems
(Universiti Malaysia Perlis (UniMAP)School of Computer and Communication Engineering, 2015)Violent crime scenes are becoming increasingly common nowadays. Usually in such cases, the obvious evidence of the crime is blood spatter. Forensic specialists try to predict the event of the crime as accurately as possible ... -
Image denoising in wavelet and spatial domain
The goal of any de-noising technique is to remove noise from an image which is the first step in any image processing. The noise removal method should be applied watchful manner otherwise artefacts can be introduced which ... -
Image enhancement and feature extraction techniques for intelligent thalassemia screening procedures
Thalassemia is an inherited blood disease that effects the production of red blood cells (RBC) in the body. The deficiency of RBC that constitutes 99% of blood cells will affect their main function as oxygen carrier. The ... -
Implementation and analysis of GMM-based speaker identification on FPGA
(Universiti Malaysia Perlis (UniMAP)School of Computer and Communication Engineering, 2012)The use of highly accurate identification systems is required in today’s society. Existing systems such as pin numbers and passwords can be forgotten or forged easily and they are no longer considered to offer a high level ... -
Implementation and performance of a taste sensing system for quality assessment of agrobased products
(Universiti Malaysia Perlis (UniMAP)School of Computer and Communication Engineering, 2011)The trend in human food consumption is seeing a shift in demand, from consumer’s side demanding increase of health elements in food and from manufacturer’s side demanding higher palatability. Currently, quality of farm ... -
Implementation of a cloud based embedded platform for object detection and recognition
With the recent advancements in deep learning-based computer vision models, object detection and recognition applications such as video surveillance, Bio-Imaging, autonomous cars are increasing in number. Object detection ... -
Implementation of adaptive pole assignment PID controller on Dc-Dc converters for renewable energy sources
(Universiti Malaysia Perlis (UniMAP)School of Electrical Systems Engineering, 2013)This thesis presents the implementation of adaptive pole assignment PID controller on DC-DC converters for renewable energy sources. This study involves the modeling and development of proposed converters; buck and boost ... -
An implementation of controller and observer for pittman 8692 brush dc motor
(Universiti Malaya (UM), 2012)The project focused on DC motor position control system. The main objective is to implement controller and observer for Pittman 8692 rush DC motor, where several controller designs with state-space approaches have been ... -
Implementation of feature extraction and classification for speech dysfluencies
(Universiti Malaysia Perlis (UniMAP)School of Mechatronic Engineering, 2011)Speech is prone to disruption of involuntary dysfluent events especially repetitions and prolongations of sounds, syllables and words which lead to dysfluency in communication. Traditionally, speech language pathologists ... -
Implementation of feature selection and weighting methods for emotion recognition from human actions
Emotion is a natural, instinctive state of mind emanating from one's circumstances, mood or relationships with others. Emotion can be characterized primarily by the psycho-physiological expressions, biological reactions, ... -
Implementation of FPGA-based artificial neural network for character recognition
(Universiti Malaysia Perlis (UniMAP)School of Computer and Communication Engineering, 2014)Artificial Neural Networks (ANN) are non-linear applied math knowledge data modeling tools, usually used model advanced relationships between inputs and outputs or to seek out patterns in data. A generic hardware primarily ... -
Implementation of FPGA-based artificial neural network for character recognition
(Universiti Malaysia Perlis (UniMAP)School of Computer and Communication Engineering, 2014)Artificial Neural Networks (ANN) are non-linear applied math knowledge data modeling tools, usually used model advanced relationships between inputs and outputs or to seek out patterns in data. A generic hardware primarily ... -
Implementation of image super-resolution on Rasberry Pi
Improving image quality has been a bottle neck of image technology for the past few decades. High resolution is a continuous and on-going need and it becomes essential to have the best quality of image in some applications ...