Garuda - Garba Rujukan Digital

Formant characteristics of Malay vowels Izzad Ramli; Nursuriati Jamil; Norizah Ardi
International Journal of Evaluation and Research in Education (IJERE) Vol 9, No 1: March 2020
Publisher : Institute of Advanced Engineering and Science

The purpose of this study was to investigate and examined the eight vowels formant characteristic of Malay language. Previous research of Malay language only investigated six basic vowels /a/, /e/, /i/, /o/, /u/, /ə/. The vowels /ɔ/, /ε/ that usually exist in a dialect were not included in the previous investigations. In this study, the vowels sound were collected from five men and four women producing the vowels /a/, /e/, /i/, /o/, /u/, /ə/, /ɔ/, /ε/ from different regions and dialects in Malaysia. Formant contours, F1 until F4 of the vowels were measured using interactive editing tool called Praat. Analysis of the formant data showed numerous differences between vowels in terms of average frequencies of F1 and F2, and the degree of overlap among adjacent vowels. When compared with the International Phonetic Alphabet (IPA), most pronunciation of the Malay vowels were at the same position but the vowel /ε/ seen more likely to become a front vowel instead of a central vowel. Consequently, vowel features of the two Malay allophones /ɔ/ and /ε/ were documented and added to the IPA vowel chart. The findings form the fundamental basis for further research of speech synthesis, speech rehabilitation and speech reproduction of the Malay language.

Evaluations of Internet of Things-based personal smart farming system for residential apartments Fatin Natasya Shuhaimi; Nursuriati Jamil; Raseeda Hamzah
Bulletin of Electrical Engineering and Informatics Vol 9, No 6: December 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v9i6.2496

Urban farming is popularly accepted by communities living in cities as they are more health-conscious and to help support the high cost of living. Unfortunately, farming takes a considerable amount of time specially to monitor the plant’s growth. Therefore, smart farming using Internet of Things (IoT) should be adopted to realize urban farming. In this study, two IoT-based smart farming system designs for personal usages in a residential apartment were proposed and evaluated. As the design was meant for beginners, two utmost parameters for maintaining plant growth was evaluated, that are humidity and temperature. The humidity and temperature readings of design A using DHT 11 sensor and design B using DHT 22 sensor were recorded for 3 days and were compared against the actual humidity and temperature of the environment. After comparing the sum of absolute difference (SAD) of both designs, the implementation costs, and the consumption power, there is an inconclusive finding in terms of accuracy and costs. However, the basic design and cost of implementing a personal IoT-based smart farming system were proposed. The factors to be considered in constructing a personal smart farming system were also described.

Evaluation of Support Vector Machine and Decision Tree for Emotion Recognition of Malay Folklores Mastura Md Saad; Nursuriati Jamil; Raseeda Hamzah
Bulletin of Electrical Engineering and Informatics Vol 7, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science

In this paper, the performance of Support Vector Machine (SVM) and Decision Tree (DT) in classifying emotions from Malay folklores is presented. This work is the continuation of our storytelling speech synthesis work to add emotions for a more natural storytelling. A total of 100 documents from children short stories are collected and used as the datasets of the text-based emotion recognition experiment. Term Frequency-Inverse Document Frequency (TF-IDF) is extracted from the text documents and classified using SVM and DT. Four types of common emotions, which are happy, angry, fearful and sad are classified using the two classifiers. Results showed that DT outperformed SVM by more than 22.2% accuracy rate. However, the overall emotion recognition is only at moderate rate suggesting an improvement is needed in future work. The accuracy of the emotion recognition should be improved in future studies by using semantic feature extractors or by incorporating deep learning for classification.

Evaluation of Support Vector Machine and Decision Tree for Emotion Recognition of Malay Folklores Mastura Md Saad; Nursuriati Jamil; Raseeda Hamzah
Bulletin of Electrical Engineering and Informatics Vol 7, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science

In this paper, the performance of Support Vector Machine (SVM) and Decision Tree (DT) in classifying emotions from Malay folklores is presented. This work is the continuation of our storytelling speech synthesis work to add emotions for a more natural storytelling. A total of 100 documents from children short stories are collected and used as the datasets of the text-based emotion recognition experiment. Term Frequency-Inverse Document Frequency (TF-IDF) is extracted from the text documents and classified using SVM and DT. Four types of common emotions, which are happy, angry, fearful and sad are classified using the two classifiers. Results showed that DT outperformed SVM by more than 22.2% accuracy rate. However, the overall emotion recognition is only at moderate rate suggesting an improvement is needed in future work. The accuracy of the emotion recognition should be improved in future studies by using semantic feature extractors or by incorporating deep learning for classification.

Evaluation of Support Vector Machine and Decision Tree for Emotion Recognition of Malay Folklores Mastura Md Saad; Nursuriati Jamil; Raseeda Hamzah
Bulletin of Electrical Engineering and Informatics Vol 7, No 3: September 2018
Publisher : Institute of Advanced Engineering and Science

In this paper, the performance of Support Vector Machine (SVM) and Decision Tree (DT) in classifying emotions from Malay folklores is presented. This work is the continuation of our storytelling speech synthesis work to add emotions for a more natural storytelling. A total of 100 documents from children short stories are collected and used as the datasets of the text-based emotion recognition experiment. Term Frequency-Inverse Document Frequency (TF-IDF) is extracted from the text documents and classified using SVM and DT. Four types of common emotions, which are happy, angry, fearful and sad are classified using the two classifiers. Results showed that DT outperformed SVM by more than 22.2% accuracy rate. However, the overall emotion recognition is only at moderate rate suggesting an improvement is needed in future work. The accuracy of the emotion recognition should be improved in future studies by using semantic feature extractors or by incorporating deep learning for classification.

Can Convolution Neural Network (CNN) Triumph in Ear Recognition of Uniform Illumination Invariant? Nursuriati Jamil; Ali Abd Almisreb; Syed Mohd Zahid Syed Zainal Ariffin; N. Md Din; Raseeda Hamzah
Indonesian Journal of Electrical Engineering and Computer Science Vol 11, No 2: August 2018
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v11.i2.pp558-566

Current deep convolution neural network (CNN) has shown to achieve superior performance on a number of computer vision tasks such as image recognition, classification and object detection. The deep network was also tested for view-invariance, robustness and illumination invariance. However, the CNN architecture has thus far only been tested on non-uniform illumination invariant. Can CNN perform equally well for very underexposed or overexposed images or known as uniform illumination invariant? This is the gap that we are addressing in this paper. In our work, we collected ear images under different uniform illumination conditions with lumens or lux values ranging from 2 lux to 10,700 lux. A total of 1,100 left and right ear images from 55 subjects are captured under natural illumination conditions. As CNN requires considerably large amount of data, the ear images are further rotated at every 5o angles to generate 25,300 images. For each subject, 50 images are used as validation/testing dataset, while the remaining images are used as training datasets. Our proposed CNN model is then trained from scratch and validation and testing results showed recognition accuracy of 97%. The results showed that 100% accuracy is achieved for images with lumens ranging above 30 but having problem with lumens less than 10 lux

SiulMalaya: an annotated bird audio dataset of Malaysia lowland forest birds for passive acoustic monitoring Nursuriati Jamil; Ahmad Nazem Norali; Muhammad Izzad Ramli; Ahmad Khusaini Mohd Kharip Shah; Ismail Mamat
Bulletin of Electrical Engineering and Informatics Vol 12, No 4: August 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v12i4.5243

The laborious point count method of conducting bird surveys is still a common practice in Malaysia. An alternative method known as passive acoustic monitoring (PAM) is deployed in many countries by placing sound recorders at surveying sites to collect bird sounds. Studies revealed that the number of bird densities counted by human observers was agreeable with those obtained using PAM. However, one of the most essential gaps in conducting PAM is the lack of expert-verified bird-call databases. Therefore, the aim of this study is to construct the first annotated Malaysia lowland forest bird sounds called SiulMalaya to be used as ground-truth datasets for PAM-related activities. The raw bird sounds dataset was downloaded from Macaulay Library using the eBird platform. Data pre-processing was done to produce annotated audio tracks that can be used as training datasets for bird classification. SiulMalaya dataset was further validated by two bird experts from the Department of Wildlife and National Parks, Malaysia. A bird identification experiment was carried out to assess and validate SiulMalaya dataset using a convolutional neural network (CNN) learning model. Even though the accuracy of bird identification is slightly above 50%, the annotated dataset is shown to be viable for PAM-related operations.

Vehicle detection and classification using three variations of you only look once algorithm Gehad Saleh Ahmed Mohammed; Norizan Mat Diah; Zaidah Ibrahim; Nursuriati Jamil
International Journal of Reconfigurable and Embedded Systems (IJRES) Vol 12, No 3: November 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijres.v12.i3.pp442-452

Vehicle detection and classification are essential for advanced driver assistance systems (ADAS) and even traffic camera surveillance. Yet, it is challenging due to complex backgrounds, varying illumination intensities, occlusions, vehicle size, and type variations. This paper aims to apply you only look once (YOLO) since it has been proven to produce high object detection and classification accuracy. There are various versions of YOLO, and their performances differ. An investigation on the detection and classification performance of YOLOv3, YOLOv4, and YOLOv5 has been conducted. The training images were from common objects in context (COCO) and open image, two publicly available datasets. The testing input images were captured on a few highways in two main cities in Malaysia, namely Shah Alam and Kuala Lumpur. These images were captured using a mobile phone camera with different backgrounds during the day and night, representing different illuminations and varying types and sizes of vehicles. The accuracy and speed of detecting and classifying cars, trucks, buses, motorcycles, and bicycles have been evaluated. The experimental results show that YOLOv5 detects vehicles more accurately but slower than its predecessors, namely YOLOv4 and YOLOv3. Future work includes experimenting with newer versions of YOLO.

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search