Claim Missing Document
Check
Articles

Found 13 Documents
Search

Development of control system for quadrotor unmanned aerial vehicle using LoRa wireless and GPS tracking Teddy Surya Gunawan; Wan Athereah Yahya; Erwin Sulaemen; Mira Kartiwi; Zuriati Janin
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 5: October 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i5.16716

Abstract

In the past decades, there has been a growing interest in unmanned aerial vehicles (UAVs) for educational, research, business, and military purposes. The most critical data for a flight system is the telemetry data from the GPS and wireless transmitter and also from the gyroscope and accelerometer.  The objective of this paper is to develop a control system for UAV using long-range wireless communication and GPS. First, Matlab simulation was conducted to obtain an optimum PID gains controller. Then LoRa wireless was evaluated during clear and rainy days. Static and dynamic points measurement was conducted to validate and optimize GPS accuracy. GeoMapping in Matlab and Google GPS GeoPlanner were then used to analyze the traveled UAV flight path.
Development of video-based emotion recognition using deep learning with Google Colab Teddy Surya Gunawan; Arselan Ashraf; Bob Subhan Riza; Edy Victor Haryanto; Rika Rosnelly; Mira Kartiwi; Zuriati Janin
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 5: October 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i5.16717

Abstract

Emotion recognition using images, videos, or speech as input is considered as a hot topic in the field of research over some years. With the introduction of deep learning techniques, e.g., convolutional neural networks (CNN), applied in emotion recognition, has produced promising results. Human facial expressions are considered as critical components in understanding one's emotions. This paper sheds light on recognizing the emotions using deep learning techniques from the videos. The methodology of the recognition process, along with its description, is provided in this paper. Some of the video-based datasets used in many scholarly works are also examined. Results obtained from different emotion recognition models are presented along with their performance parameters. An experiment was carried out on the fer2013 dataset in Google Colab for depression detection, which came out to be 97% accurate on the training set and 57.4% accurate on the testing set.
On the use of voice activity detection in speech emotion recognition Muhammad Fahreza Alghifari; Teddy Surya Gunawan; Mimi Aminah binti Wan Nordin; Syed Asif Ahmad Qadri; Mira Kartiwi; Zuriati Janin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (903.469 KB) | DOI: 10.11591/eei.v8i4.1646

Abstract

Emotion recognition through speech has many potential applications, however the challenge comes from achieving a high emotion recognition while using limited resources or interference such as noise. In this paper we have explored the possibility of improving speech emotion recognition by utilizing the voice activity detection (VAD) concept. The emotional voice data from the Berlin Emotion Database (EMO-DB) and a custom-made database LQ Audio Dataset are firstly preprocessed by VAD before feature extraction. The features are then passed to the deep neural network for classification. In this paper, we have chosen MFCC to be the sole determinant feature. From the results obtained using VAD and without, we have found that the VAD improved the recognition rate of 5 emotions (happy, angry, sad, fear, and neutral) by 3.7% when recognizing clean signals, while the effect of using VAD when training a network with both clean and noisy signals improved our previous results by 50%.
A critical insight into multi-languages speech emotion databases Syed Asif Ahmad Qadri; Teddy Surya Gunawan; Muhammad Fahreza Alghifari; Hasmah Mansor; Mira Kartiwi; Zuriati Janin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (303.859 KB) | DOI: 10.11591/eei.v8i4.1645

Abstract

With increased interest of human-computer/human-human interactions, systems deducing and identifying emotional aspects of a speech signal has emerged as a hot research topic. Recent researches are directed towards the development of automated and intelligent analysis of human utterances. Although numerous researches have been put into place for designing systems, algorithms, classifiers in the related field; however the things are far from standardization yet. There still exists considerable amount of uncertainty with regard to aspects such as determining influencing features, better performing algorithms, number of emotion classification etc. Among the influencing factors, the uniqueness between speech databases such as data collection method is accepted to be significant among the research community. Speech emotion database is essentially a repository of varied human speech samples collected and sampled using a specified method. This paper reviews 34 `speech emotion databases for their characteristics and specifications. Furthermore critical insight into the imitational aspects for the same have also been highlighted.
A critical insight into multi-languages speech emotion databases Syed Asif Ahmad Qadri; Teddy Surya Gunawan; Muhammad Fahreza Alghifari; Hasmah Mansor; Mira Kartiwi; Zuriati Janin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (303.859 KB) | DOI: 10.11591/eei.v8i4.1645

Abstract

With increased interest of human-computer/human-human interactions, systems deducing and identifying emotional aspects of a speech signal has emerged as a hot research topic. Recent researches are directed towards the development of automated and intelligent analysis of human utterances. Although numerous researches have been put into place for designing systems, algorithms, classifiers in the related field; however the things are far from standardization yet. There still exists considerable amount of uncertainty with regard to aspects such as determining influencing features, better performing algorithms, number of emotion classification etc. Among the influencing factors, the uniqueness between speech databases such as data collection method is accepted to be significant among the research community. Speech emotion database is essentially a repository of varied human speech samples collected and sampled using a specified method. This paper reviews 34 `speech emotion databases for their characteristics and specifications. Furthermore critical insight into the imitational aspects for the same have also been highlighted.
On the use of voice activity detection in speech emotion recognition Muhammad Fahreza Alghifari; Teddy Surya Gunawan; Mimi Aminah binti Wan Nordin; Syed Asif Ahmad Qadri; Mira Kartiwi; Zuriati Janin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (903.469 KB) | DOI: 10.11591/eei.v8i4.1646

Abstract

Emotion recognition through speech has many potential applications, however the challenge comes from achieving a high emotion recognition while using limited resources or interference such as noise. In this paper we have explored the possibility of improving speech emotion recognition by utilizing the voice activity detection (VAD) concept. The emotional voice data from the Berlin Emotion Database (EMO-DB) and a custom-made database LQ Audio Dataset are firstly preprocessed by VAD before feature extraction. The features are then passed to the deep neural network for classification. In this paper, we have chosen MFCC to be the sole determinant feature. From the results obtained using VAD and without, we have found that the VAD improved the recognition rate of 5 emotions (happy, angry, sad, fear, and neutral) by 3.7% when recognizing clean signals, while the effect of using VAD when training a network with both clean and noisy signals improved our previous results by 50%.
A critical insight into multi-languages speech emotion databases Syed Asif Ahmad Qadri; Teddy Surya Gunawan; Muhammad Fahreza Alghifari; Hasmah Mansor; Mira Kartiwi; Zuriati Janin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (303.859 KB) | DOI: 10.11591/eei.v8i4.1645

Abstract

With increased interest of human-computer/human-human interactions, systems deducing and identifying emotional aspects of a speech signal has emerged as a hot research topic. Recent researches are directed towards the development of automated and intelligent analysis of human utterances. Although numerous researches have been put into place for designing systems, algorithms, classifiers in the related field; however the things are far from standardization yet. There still exists considerable amount of uncertainty with regard to aspects such as determining influencing features, better performing algorithms, number of emotion classification etc. Among the influencing factors, the uniqueness between speech databases such as data collection method is accepted to be significant among the research community. Speech emotion database is essentially a repository of varied human speech samples collected and sampled using a specified method. This paper reviews 34 `speech emotion databases for their characteristics and specifications. Furthermore critical insight into the imitational aspects for the same have also been highlighted.
On the use of voice activity detection in speech emotion recognition Muhammad Fahreza Alghifari; Teddy Surya Gunawan; Mimi Aminah binti Wan Nordin; Syed Asif Ahmad Qadri; Mira Kartiwi; Zuriati Janin
Bulletin of Electrical Engineering and Informatics Vol 8, No 4: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (903.469 KB) | DOI: 10.11591/eei.v8i4.1646

Abstract

Emotion recognition through speech has many potential applications, however the challenge comes from achieving a high emotion recognition while using limited resources or interference such as noise. In this paper we have explored the possibility of improving speech emotion recognition by utilizing the voice activity detection (VAD) concept. The emotional voice data from the Berlin Emotion Database (EMO-DB) and a custom-made database LQ Audio Dataset are firstly preprocessed by VAD before feature extraction. The features are then passed to the deep neural network for classification. In this paper, we have chosen MFCC to be the sole determinant feature. From the results obtained using VAD and without, we have found that the VAD improved the recognition rate of 5 emotions (happy, angry, sad, fear, and neutral) by 3.7% when recognizing clean signals, while the effect of using VAD when training a network with both clean and noisy signals improved our previous results by 50%.
Design of travel angle control of quanser bench-top helicopter using mamdani-based fuzzy logic controller Hasmah Mansor; Mohamad K. Azmi Mat Esa; Teddy Surya Gunawan; Zuriati Janin
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 2: February 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v17.i2.pp815-825

Abstract

This research focuses on travel angle control of a laboratory scale bench-top helicopter developed by Quanser Inc.  Bench top-helicopter is usually used by engineers and researchers to test their designed controllers before applying to the actual helicopter. Bench-top helicopter has the same behavior as the real helicopter, with 3 degree of freedom.  The bench-top helicopter is mounted on a flat surface with two rotors that depends on the voltage supplied to change the direction of the helicopter in 3 different angles. The movement of the helicopter is based on the direction of three-different angles; travel, pitch and yaw angles. The existing Linear Quadratic Regulator-Integral controller used by Quanser Inc has some limitations in terms of tracking capability and settling time; therefore this research is proposed. The objective of this research is to develop Mamdani-based Fuzzy Logic Controller for travel angle control of bench-top helicopter. Performance comparison has been done with the existing Linear Quadratic Regulator-Integral controller in both simulation and hardware. From the test results, it was found that the performance of Fuzzy Logic Controller is better than LQR-I controller especially for closed-loop simulation at desired angle of 30°. The percentage of overshoot of the Fuzzy Logic Controller has been improved from the existing controller which is 4.912% compared to 7.002% for LQR-I.
Performance evaluation of portable air quality measurement system using raspberry pi for remote monitoring Muhammad Farhan Mohd Pu’ad; Teddy Surya Gunawan; Mira Kartiwi; Zuriati Janin
Indonesian Journal of Electrical Engineering and Computer Science Vol 17, No 2: February 2020
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v17.i2.pp564-574

Abstract

United Nations’ Sustainable Development Goals focuses on good health and well-being for all. Air pollution becomes a huge threat to delivering on the vision of a better world and related at least to Goal 3, 7, 11, and 13. In Malaysia, air pollution index were monitored on 68 locations. The Department of Environment monitors air quality using costly continuous air quality monitoring stations (CAQMs) installed at fixed locations of highly populated and industrial areas. The objective of this paper is to develop a portable air quality measurement system which can measure particulate matters (PM) smaller than 10 and 2.5 microns, and four hazardous gasses, including carbon monoxide, sulphur dioxide, ground level ozone and nitrogen dioxide, as well as humidity and temperature. Six sensors were used and validated using several rigorous experiments. The functionality of the system was evaluated by measuring sub-API readings in areas with low and high traffic volumes. Experimental results showed that the proposed system was highly responsive and able to detect the types and concentrations of air pollutants instantly. Furthermore, equipped with the mobile internet, geo-tagged GPS location and web server on Raspberry Pi, the developed portable system could be accessed remotely.