Dyslexia is developed by neurobiological in origin which is categorized as
learning disorder that affect the ability to read, spell, write and speak. The
most common dyslexia symptom can easily be identified through the
handwriting pattern. There are many intelligence and computational
methods that have been proposed, and they have provided various and
different performance to evaluate the proposed system ability. However,
system performances are varied and nonstandardized in each assesment on
dyslexic children to validate the presence of dyslexia symptom. The recent
deep learning models have been employed to improve the assesment
performance and (the models/ they have shown) shows significant output to
detect and classify the present of dyslexia symptoms among school children.
Therefore, there is a crucial need in deep learning, specifically for
Convolutional Neural Network ( CNN) to validate performances of different
networks, so that the most performed CNN could be a bench mark in
evaluation to detect such symptom. This study aims to compare different deep
learning networks specifically the CNN models to validate its performance
in terms of the capability to classify dyslexic handwriting among school
children. This study is proposed to compare different CNN models such as
CNN-1, CNN-2, CNN-3 and LeNet-5. The proposed methods to compare the
CNN performances are developed by using Jupyter notebook as platform.
Meanwhile, keras is the higher-level API framework to provide a more
flexible way for defining models. It specifically allows to define multiple
input or output models as well as models that share layers. The tensorflow is
also used for machine learning applications such as neural networks. Before
that, the dataset of handwriting image is preprocessed by the augmentation
process which includes the rotation of all images. CNN models have shown
significant performance and provided sufficient results of performance with
more than 87% of accuracy in classifying the potential dyslexia symptom
based on handwritten images.
Repair and maintenance in power distribution is an important factor that
affects the continuous productivity services and power efficiency in electrical
supply systems. Thermographic inspection has been often used as a
maintenance tool, as it allows detection of early-stage failure from the system
in electrical distribution. Failure in the system can lead to catastrophic
failure like a high-voltage arc fault. The presence of fault is caused by the
higher temperature of the instrument that leads to the formation of hotspots.
The use of infrared inspection is useful in detecting the hotspot that is hardly
noticeable. It helps to overcome the problems that arise during operation
and maintenance in the distribution systems. In this research, a fault
detection system is proposed with the application of Artificial Neural
Network (ANN) in identifying faults on electrical equipment. This method
was trained by using the temperature parameter on the IR images taken from
TNB Distribution. As a result, it will lead to faults detection. Thus, the
purpose of this project is to ensure the correct recommendation of corrective
actions in the maintenance procedure of the electrical system. The actions to
the detection of faults taken are based on the results of the temperature
measured. The neural network training performance for the temperature of
hotspot detection was developed with a minimum error of 0.00084165 MSE
at epoch 39. The study shows the best-fitting allows detection of early-stage
failure. It can be concluded that the current method in conducting the
prediction process by using Thermographic inspection is suitable for
electrical equipment based on the training result.