49 research outputs found
Feature selection for traditional Malay musical instrument sound classification using rough set
No full textWith the growing volume of data and feature (attribute) schemes, feature selection
has become a very vital aspect in many data mining tasks including musical
instrument sounds classification problem. The purpose of feature selection is to
alleviate the effect of the „curse of dimensionality‟. This problem normally deals
with the irrelevant and redundant features. Using the whole set of features is also
inefficient in terms of processing time and storage requirement. In addition, it may be
difficult to interpret and may decrease the classification performance respectively. To
solve the problem, various feature selection techniques have been proposed in this
area of research. One of the potential techniques is based on the rough set theory.
The theory of rough set proposed by Pawlak in 1980s is a mathematical tool for
dealing with the vagueness and uncertainty data. The concepts of reduct and core in
rough set are relevant in feature selection to identify the important features among
the irrelevant and redundant ones. However, there are two common problems related
to the existing rough set-based feature selection techniques which are no warranty to
find an optimal reduction and high complexity in finding the optimal ones. Thus, in
this study, an alternative feature selection technique based on rough set theory for
traditional Malay musical instrument sounds classification was proposed. This
technique was developed using rough set approximation based on the maximum
degree of dependency of attributes. The idea of this technique was to choose the most
significant features by ranking the relevant features based on the highest dependency
of attributes and then removing the redundant features with the similar dependency
value. In overall, the results showed that the proposed technique was able to select
the 17 important features out of 37 full features (with 54% of reduction), achieve the
average of 98.84% accuracy rate, and reduce the complexity of the process (where
the time processing is less than 1 second) significantly
User-centred design and experience prototyping: Design and implementation of pre-handwriting intervention to children with coordination difficulties/dyspraxia
No full text
A personality career test for public secondary schools using android application
No full textPersonality test is a tool used to assess human personality which there are
two types of personality tests that is self-report inventories and projective tests where
most schools use self-report inventories by paper which is inefficient and require
resources more than what can be achieved by using mobile android application
instead. Existing applications of personality test in Google Play are not using the same
inventory tests that are used within public schools which makes it not viable as a
primary source for public schools. This project is about developing an android mobile
application that helps user to determine their personality and narrow down some of
the suggested types of career that suits the user’s personality. At the end of the test,
the application will calculate the user scores and present 3 keywords that represents
user personality instantly which saves time and resources required compared using
paper-based method that public schools use. The methodology used to develop this
project is Multimedia Content Development (MMCD) methodology to narrow down
system requirements and user requirements that is suitable for mobile learning
application. Testing phase is carried out amongst target user which is secondary
school students and the subject matter expert of this project by using google form for
testers to leave their review of their experience on using the application. The testing
results for this project gained positive feedback from the testers with the score of
81.38% in System Usability Scale (SUS) score
iHaji VR Simulasi: Pembangunan Aplikasi Simulasi Ibadah Haji Menggunakan Teknologi Realiti Maya
No full textIbadah Haji merupakan salah satu daripada lima rukun Islam dan wajib dilaksanakan oleh umat Islam yang berkemampuan. Namun, kaedah pembelajaran sedia ada seperti penggunaan buku teks dan video kurang mengandungi elemen interaktif dan imersif untuk memenuhi keperluan pembelajaran generasi kini. Oleh itu, aplikasi iHaji VR Simulasi telah dibangunkan menggunakan teknologi realiti maya (VR) sebagai alternatif pembelajaran Haji yang lebih menarik dan praktikal. Aplikasi ini dibangunkan untuk platform Android dengan menggunakan metodologi TRES-D sebagai pendekatan pembangunan, dan mengandungi dua modul utama, iaitu Modul Simulasi, yang membimbing pengguna melalui rukun dan wajib Haji secara maya, serta Modul Ziarah, yang membolehkan penerokaan lokasi penting seperti Masjidil Haram dan Padang Arafah. Gabungan elemen audio, visual dan interaktif digunakan bagi menghasilkan pengalaman pembelajaran yang lebih realistik dan imersif. Hasil ujian penerimaan pengguna menggunakan kaedah Skala Kebolehgunaan Sistem (SUS) menunjukkan skor purata 82.50, yang berada dalam kategori cemerlang, menunjukkan bahawa aplikasi iHaji VR Simulasi mempunyai tahap kebolehgunaan yang tinggi dan mesra pengguna. Secara keseluruhannya, iHaji VR Simulasi berpotensi besar dalam membantu pengguna memahami dan menghayati pelaksanaan ibadah Haji secara lebih mendalam melalui pengalaman maya yang interaktif
Lancar Solat: Aplikasi Hafazan Bacaan dalam Solat untuk Kanak-kanak Autisme
No full textSolat merupakan rukun Islam kedua dan wajib dilaksanakan setiap individu Muslim. Kanak-kanak autisme tidak diwajibkan menunaikan solat namun pendedahan awal pembelajaran solat amat penting. Kanak-kanak autisme biasanya mempelajari solat dengan mendengar dan mengulangi bacaan solat untuk membantu mereka mengingat. Walaubagaimanapun, aplikasi pembelajaran solat bagi kanak-kanak autisme masih terhad. Kebanyakan aplikasi sedia ada hanya memfokuskan kepada aspek pembelajaran solat secara umum tanpa menekankan kepada kaedah hafazan bacaan dalam solat. Oleh itu, aplikasi Lancar Solat dicadangkan bertujuan membangunkan aplikasi pembelajaran berasaskan permainan untuk membantu kanak-kanak autisme dalam menghafaz bacaan dalam solat. Kaedah tikrar iaitu kaedah hafazan secara ulangan digunakan dalam aplikasi ini. Metodologi Pembangunan Kandungan Mudah Alih Multimedia (MMCD) digunakan dalam pembangunan aplikasi ini. Hasil keputusan pengujian pengguna menggunakan kaedah Skala Kebolehgunaan Sistem (SUS) menunjukkan skor yang cemerlang iaitu 79.38. Hasil ini membuktikan aplikasi ini diterima oleh pengguna dari segi aspek kebolehgunaannya
Soft set theory for automatic classification of traditional pakistani musical instruments sounds
No full text
