Ruzelita Ngadiran
Thumbnail Image
Preferred name
Ruzelita Ngadiran
Official Name
Ruzelita, Ngadiran
Alternative Name
Ngadiran, Ruzelita
Ngadiran, R.
Binti Ngadiran, Ruzelita
Main Affiliation
Scopus Author ID
36548898800
Researcher ID
ABF-3045-2020

Research Output

Filters

1 1
17
Reset filters

Settings
Now showing 1 - 10 of 17
  • Publication
    IoT-based Door Access Using Three Security-Layers
    ( 2023-10-06)
    Aznan M.A.
    ;
    Siti Zuraidah Ibrahim
    ;
    Ku Nurul Fazira Ku Azir
    ;
    Ruzelita Ngadiran
    ;
    Mohd Noh F.H.
    This paper demonstrates an Internet-of-Things, IoT-based Door Access using three security layers, which are biometric identification, authentication, and authorized reply. The IoT-based door access is developed with Closed Circuit Television (CCTV) monitoring to control door access by authorized users using facial recognition technique and the Telegram application along with a database to record user logs. In the first security layer, the user’s face will be captured by CCTV camera and then processed to match to the registered face. In the authentication layer, the system will use Telegram Bot to send a message to the user registered Telegram Chat Identification (ID) only for entering the password. In the third security layer, if the password is valid, the system will send a signal to the hardware to unlock the door. The results showed that the developed prototype of this system successfully operated as expected.
  • Publication
    Background Subtraction Algorithm Comparison on the Raspberry Pi Platform for Real Video Datasets
    ( 2022-01-01)
    Iszaidy Ismail
    ;
    Ruzelita Ngadiran
    ;
    Ramli N.
    ;
    Nazren A.R.A.
    ;
    Nasruddin M.W.
    ;
    Jais M.I.
    Background subtraction is an advanced method used for video monitoring and is commonly used for indexing of moveable objects. Over the years, several algorithms have been implemented and the implementation of algorithms on the embedded platform can be difficult because the embedded platform has minimal computing resources. The purpose of this study is to conduct a comparative review of background subtraction algorithms available on the embedded platform: Raspberry Pi. The algorithms are compared using a real video dataset based on segmentation accuracy (precision, recall, and f-measure) and hardware efficiency (CPU utilization and time consumption).
      2  50
  • Publication
    Perceptual-based features for blind image quality assessment using extreme learning machine for biodiversity monitoring
    ( 2024-02-08)
    Verak N.
    ;
    Pakhlen Ehkan
    ;
    Ruzelita Ngadiran
    ;
    Jungjit S.
    ;
    Fazrul Faiz Zakaria
    ;
    Mohd Nazri Mohd Warip
    ;
    Ilyas M.Z.
    Blind Image Quality Assessment (BIQA) is crucial for various image processing applications, including image denoising, transmission evaluation, optimization, watermarking, and situations where a reference image is unavailable. However, existing state-of-the-art Image Quality Assessment (IQA) metrics are often specific to certain types of distortion and fail to align with human perception. To address this issue, our research study proposes a novel approach that incorporates perceptual-based features and utilizes a pooling algorithm based on Extreme Learning Machine (ELM). By considering human visual characteristics and the impact on image content, we aim to mimic human perception, which can detect noticeable differences at specific frequency ranges, akin to neurons. The work is divided into three phases. In the first phase, we derive perceptual features using lifting wavelet, focusing on texture, edge, and contrast components. Subsequently, in the second phase, these features are trained to generate output for pooling using Extreme Learning Machine (ELM). The pooling strategy of ELM is chosen due to its ability to overcome limitations found in previous pooling techniques like Neural Networks (NNs) and Support Vector Regression (SVR). This approach enables us to evaluate the quality score of images accurately, benefiting from ELM's superior learning accuracy and faster learning speed. The third phase involves performance evaluation, including statistical analysis for algorithm validation and a comparison with existing BIQA methods using MATLAB software. We verify our proposed approach on diverse image databases containing various distortion types, aiming to create a general-purpose BIQA solution. The outcomes of this work will have significant implications in several image processing applications, such as optimizing image enhancement for medical purposes like tumor or cancer detection, image watermarking for security applications, image coding and compression, and image forensic analysis. In biodiversity monitoring, image enhancement plays a crucial role in tracking and data collection.
      1  55
  • Publication
    An Analysis of Background Subtraction on Embedded Platform Based on Synthetic Dataset
    ( 2021-03-01)
    Iszaidy Ismail
    ;
    Ruzelita Ngadiran
    ;
    R Badlishah Ahmad
    ;
    Ramli N.
    ;
    Jais M.I.
    ;
    Vijayasarveswari Veeraperumal
    Background subtraction is a preliminary technique used for video surveillance and a widely used approach for indexing moving objects. Arange of algorithms have been introduced over the years, and it might be hard to implement the algorithms on the embedded platform because the embedded platform comes up with limited processing power. The goal of this study is to provide a comparative analysis of available background subtraction algorithms on the embedded platform:-Raspberry Pi. The algorithms are compared based on the segmentation quality (precision, recall, and f-measure) and hardware performance(CPU usage and time consumption) using a synthetic video from BMC Dataset with different challenges like normal weather, sunny, cloudy, foggy and windy weather.
      52  1
  • Publication
    Full reference image quality assessment algorithm based on Haar wavelet and edge perceptual similarity
    (IOP Publishing, 2020)
    F Mokhtar
    ;
    Ruzelita Ngadiran
    The research on image quality assessment (IQA) has been become a hot topic in image processing. Many studies show that HVS edge information plays crucial role when human perceive the quality of an image. The proposed metric is called HEPSI. The method from HaarPSI metric is combined with edge structural similarity and a contrast map is added for pooling the structural similarity map, Validation is taken by comparing HEPSI with the well-known state-of-the-art IQA metrics: PSNR, SSIM, MSSIM, FSIM and HaarPSI over the LIVE database. Experiment shows that HEPSI achieved better performance than other 5 IQA metrics.
      1  7
  • 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%.
      10  3
  • Publication
    IOT Smart Guidance Parking Search System for Open Space Parking Area
    ( 2021-07-26)
    Iszaidy Ismail
    ;
    Ruzelita Ngadiran
    ;
    Nazren A.R.A.
    ;
    Wafi N.M.
    ;
    Ramli N.
    ;
    Vijayasarveswari Veeraperumal
    ;
    Leow W.Z.
    Open parking facilities can be automated and parking spaces can be easily operated by the implementation of IoT technology (Internet of Things). In this article, we present the evolution and prototyping of the open space smart guidance-parking search system, an IoT-based smart parking search system. The Smart Guidance Parking Searches System consists of i) An IOT module to monitor the availability of a parking slot and to update the parking lot status; and (ii) A web-based software allows users to view parking spaces available for a specific open space area. This paper addresses the existing system, device description, its functional specifications, the methods, and technologies used, the development/deployment of prototypes, along with the findings from the demonstration. This device serves as a guide for the user/driver to search for the parking slot occupancy in open/outdoor environments.
      57  13
  • Publication
    A hybrid modified sine cosine algorithm using inverse filtering and clipping methods for low autocorrelation binary sequences
    ( 2022-01-01)
    Rosli S.J.
    ;
    Hasliza A Rahim @ Samsuddin
    ;
    Khairul Najmy Abdul Rani
    ;
    Ruzelita Ngadiran
    ;
    Wan Azani Wan Mustafa
    ;
    Abdulmalek M.
    ;
    Mohd Najib Mohd Yasin
    ;
    Muzammil Jusoh
    ;
    Thennarasan Sabapathy
    ;
    Wan Nur Suryani Firuz Wan Ariffin
    ;
    Alkhayyat A.
    The essential purpose of radar is to detect a target of interest and provide information concerning the target's location, motion, size, and other parameters. The knowledge about the pulse trains' properties shows that a class of signals is mainlywell suited to digital processing of increasing practical importance. A low autocorrelation binary sequence (LABS) is a complex combinatorial problem. The main problems of LABS are low Merit Factor (MF) and shorter length sequences. Besides, the maximumpossibleMF equals 12.3248 as infinity length is unable to be achieved. Therefore, this study implemented two techniques to propose a new metaheuristic algorithm based on Hybrid Modified Sine Cosine Algorithm with Cuckoo Search Algorithm (HMSCACSA) using Inverse Filtering (IF) and clipping method to achieve better results. The proposed algorithms, LABS-IF and HMSCACSA-IF, achieved better results with two large MFs equal to 12.12 and 12.6678 for lengths 231 and 237, respectively, where the optimal solutions belong to the skew-symmetric sequences. TheMFoutperformed up to 24.335% and 2.708% against the state-of-the-art LABS heuristic algorithm, xLastovka, and Golay, respectively. These results indicated that the proposed algorithm's simulation had quality solutions in terms of fast convergence curve with better optimal means, and standard deviation.
      3  32
  • Publication
    Threading implementation on different hardware for travel time estimation purpose
    ( 2017-03-06)
    Iszaidy Ismail
    ;
    Ruzelita Ngadiran
    ;
    R Badlishah Ahmad
    ;
    Mohd Ilman Jais
    ;
    Shuhaizar Daud
    The travel time estimation is one of traffic management system which provide time taken from one point to another point. Travel time estimation system consists of an embedded platform with image sensor for detecting and tracking the vehicle. Due to limited resources of embedded board, it makes challenging to measure the travel time especially for fast moving vehicle. Capturing system required a high capturing rate of the camera to capture most current frame for fast moving vehicle. Threading is implemented in this system to improve embedded board resource utilization and input-output latency between camera and embedded board. In this paper, the threading technology is applied to two types of Raspberry Pi model and the performance of the embedded board is recorded and analyzed.
      45  15
  • Publication
    Tomato Diseases Classification Using Extreme Learning Machine
    ( 2023-10-06)
    Xian T.S.
    ;
    Ruzelita Ngadiran
    ;
    Iszaidy Ismail
    ;
    Amiza Amir
    ;
    Siti Zuraidah Ibrahim
    ;
    Taha T.B.
    Plant disease classification is essential to the agriculture industry. In this work, a tomato disease classification using Extreme Learning Machine (ELM) with image-based features. Extreme Learning Machine (ELM), a classification algorithm with a single layer feed-forward neural network where it can be combined with few activation functions. The image features as the input where the image is pre-processed via HSV colour space and extracted using Haralick textures, colour moments and HSV histogram. The features are then loaded in the ELM classifier to perform the ELM training and testing. The accuracy result of ELM classification is then analysed after the validation. The dataset used for disease detection is tomato plant leaves which is a subset of the Plant-Village dataset. The results produced from the ELM demonstrate an accuracy of around 84.94% which is comparable to classifiers such as the Support Vector Machine and Decision Tree.
      2  56