Eng Swee Kheng
Thumbnail Image
Preferred name
Eng Swee Kheng
Official Name
Eng, Swee Kheng
Alternative Name
Swee Kheng, Eng
Kheng, Eng Swee
Main Affiliation
Scopus Author ID
36959579500
Researcher ID
ERV-1458-2022

Research Output

Filters

5 1
2
5
Reset filters

Settings
Now showing 1 - 5 of 5
No Thumbnail Available
Publication

Implementation of music emotion classification using deep learning

2025-06 , Qing Xiang Sow , Eng Swee Kheng

Music plays a crucial role in shaping emotions and experiences, making its classification an important area of research with applications in therapy, recommendation systems, and affective computing. This study develops a deep learning-based system to classify music into three emotional categories: "Angry," "Happy," and "Sad." The dataset, consisting of 22 audio files collected from YouTube, was manually labelled, segmented into 30-second clips, and augmented using pitch shifting and time stretching to enhance diversity. Features were extracted using Mel-Frequency Cepstral Coefficients (MFCC) and spectral contrast to analyse the harmonic and timbral characteristics of the audio. Three deep learning models, CNN, CNN-LSTM, and CNN-GRU, were evaluated. CNN-GRU achieved the highest weighted accuracy of 99.10%, demonstrating superior performance. Future work includes adding more emotion categories, diversifying the dataset, exploring advanced architectures like transformers, optimising hyperparameters, implementing real-time applications, and conducting user studies to assess effectiveness. This research successfully developed and evaluated a music emotion classification system, contributing to advancements in the field.

View
Thumbnail Image
Publication

Microwave dielectric analysis on porous hydroxyapatite/starch composites with various ratio of hydroxyapatite to starch

2020-07-09 , You B.C. , Cheng Ee Meng , Shahriman Abu Bakar , Nashrul Fazli Mohd Nasir , Eng Swee Kheng , Mohd Shukry Abdul Majid , Mohd Ridzuan Mohd Jamir , Khor Shing Fhan

This study aims to investigate the dielectric response of the porous hydroxyapatite/starch composites by varying the starch proportion in determining the feasibility of the microwave sample characterization technique in bone tissue engineering. The porous hydroxyapatite/starch composites were fabricated by using natural starch (gelatinization and retrogradation) through the solvent casting and particulate leaching technique. The dielectric constant (ϵ′) and loss factor (ϵ″) of the complex permittivity of the porous hydroxyapatite/starch composites were measured in the Ku band frequency of 12.4-18.0 GHz. ϵ′ and ϵ″ of the porous composites increase with frequency. The highly porous composite that due to higher starch proportion exhibit higher ϵ′ and ϵ″, resulting in the significant dielectric responses.

View
No Thumbnail Available
Publication

Performance evaluation of deep learning techniques for human activity recognition system

2023 , Low Kah Sin , Eng Swee Kheng

Human Activity Recognition (HAR) is crucial in various applications, such as sports and surveillance. This paper focuses on the performance evaluation of a HAR system using deep learning techniques. Features will be extracted using 3DCNN, and classification will be performed using LSTM. Meanwhile, 3DCNN and RNN are two additional, well-known classification techniques that will be applied in order to compare the effectiveness of the three classifiers. The 3DCNN-LSTM approach contributes the highest overall accuracy of 86.57%, followed by 3DCNN-3DCNN and 3DCNN-RNN with the overall accuracy of 86.07% and 79.60%, respectively. Overall, this paper contributes to the field of HAR and provides valuable insights for the development of activity recognition systems.

View
Thumbnail Image
Publication

The Effect of the Amylose/Amylopectin Contents of Starch on Porosity and Dielectric Properties of the Porous Hydroxyapatite/Starch Composites

2020-07-09 , Chong You B. , Cheng Ee Meng , Abu Bakar S. , Nashrul Fazli Mohd Nasir , Eng Swee Kheng , Mohd Shukry Abdul Majid , Mohd Ridzuan Mohd Jamir , Khor Shing Fhan

This study aims to determine the effect of the amylose/amylopectin contents of starch on the porosity and dielectric properties of porous hydroxyapatite/starch composites. The porous hydroxyapatite/starch composites were prepared by utilizing the starches (rice, corn and potato starch) via gelatinization and retrogradation process. The complex permittivity of the porous hydroxyapatite/starch composites were evaluated in the frequency range of 12.4-18.0 GHz. The porous composites were exhibited the higher average porosity by using the starch with higher amylopectin content. The highly porous hydroxyapatite/starch composites with higher amylopectin content show the significant fluctuation peaks (at 13.8 and 16.6 GHz) and the higher imaginary part of the complex permittivity (ϵ′′) at higher frequency in the dielectric spectrum, respectively. The real (ϵ′) and imaginary part (ϵ′′) of the complex permittivity of the porous composites could be enhanced by increasing the average porosity and the amylopectin contents.

View
Thumbnail Image
Publication

Dielectric and biodegradation properties of biodegradable nano-hydroxyapatite/starch bone scaffold

2022 , Beh Chong You , Cheng Ee Meng , Nashrul Fazli Mohd Nasir , Emma Ziezie Mohd Tarmizi , Khor Shing Fhan , Eng Swee Kheng , Mohd Shukry Abdul Majid , Mohd Ridzuan Mohd Jamir

This study is aim to investigate the dielectric properties (dielectric constant, ε′ and loss factor, ε′′) and the biodegradation properties of the nano-hydroxyapatite/starch bone scaffold with various starch proportion in simulated body fluid. The nano-hydroxyapatite/starch bone scaffolds with starch proportions 30, 40, 50, 60, 70, 80, and 90 wt.% were fabricated. The ε′ and ε′′ of nano-hydroxyapatite/starch composite decrease when frequency increases. However, it increases when starch proportion and temperature increase. The biodegradation properties of the nano-hydroxyapatite/starch bone scaffold can be improved when the dielectric properties and porosity are enhanced. The enhancement of dielectric properties and porosity is due to the increment of starch proportion. The nano-hydroxyapatite/starch bone scaffold with the high starch proportion exhibits nano-hydroxyapatite/starch interfaces with strong intermolecular interactions that can stabilize biodegradation and biomineralization. The dielectric properties of the simulated body solutions are highly sensitive to the variation of the ion concentrations (calcium and phosphate). The nano-hydroxyapatite/starch bone scaffold with 80 wt.% starch proportion exhibits significant dielectric and biodegradation properties. It has potential to be a biodegradable inorganic/organic bone scaffold.

View