Nik Adilah Hanin Zahri
Thumbnail Image
Preferred name
Nik Adilah Hanin Zahri
Official Name
Nik Adilah Hanin , Zahri
Alternative Name
Zahri, Nik Adilah Hanin Binti
Zahri, N. A.H.
Hanin, Nik Adilah
Zahri, Nik Adilah Hanin
Adilah Hanin Zahri, Nik
Main Affiliation
Scopus Author ID
57191919794
Researcher ID
GJQ-4994-2022

Research Output

Filters

2
Reset filters

Settings
Now showing 1 - 2 of 2
  • Publication
    Voice-based Malay commands recognition by using audio fingerprint method for smart house applications
    (IOP Publishing, 2020)
    Abu, Masyitah
    ;
    Amiza Amir
    ;
    Nik Adilah Hanin Zahri
    ;
    Ruzelita Ngadiran
    Voice-based command recognition is commonly used in security systems, phones, household appliances and hardware designed for handicapped people. Most of the current research study the voice command recognition for the smart home in English. Lack of study for voice command recognition in Malay makes it challenging to apply the voice command services for the smart home in Malaysia. Also, voice recognition is a non-trivial task in natural language processing. This project is to identify the command used for smart home appliances using Malay and design the algorithm for this system. Then, the proposed algorithm will be deployed on a Raspberry Pi to see the performance of Malay command in accuracy and the suitability of the algorithm to be deployed on low cost embedded devices. Light, fan, and television had been chosen as electrical appliances to build the command. An algorithm that previously used to recognize songs, the robust quad algorithm, is used in this project for voice command recognition. The proposed method has two main processes, known as feature extraction and voice recognition. In the feature extraction process, the audio fingerprint will extract data from the command spectral peak. For voice recognition, audio fingerprint matching will be used to analyze the audio commands. The outcome of this project is when the voice command is given by the user by activate or deactivate the target home appliance. The second outcome is the background noise that affects the system is reduced by using robust quad algorithm and increase the accuracy of the system. The results of this project have shown that the proposed algorithm is suitable to be implemented on a Raspberry Pi and achieve a high recognition rate with 87%. In the presence of noise with 15 dB, the proposed algorithm can maintain the high recognition rate with 82%.
      7  2
  • Publication
    Machine learning algorithms for optic pathway disease diagnostics: a review
    (IOP Publishing, 2020)
    Abu, Masyitah
    ;
    Nik Adilah Hanin Zahri
    ;
    Amiza Amir
    ;
    Iszaidy Ismail
    Most of people are unaware that some of the indicators of optic pathway diseases such as stroke or tumor can be detected from the loss part of human vision, or referred as visual field defect. Ophthalmologist will manually examine the site, size and margin of the lesion from patient’s visual field points mapped by Humphrey Field Analyzer. Different site, size and margin of lesion indicates different type of defects and disease that associated with it. Therefore, an effective automated detection mechanism of multi class visual field defect is in demand to help decision making by ophthalmologist. In this paper, we review multiple techniques of supervised and unsupervised learning method for detection of optic pathway disease.
      1  5