The Joint Symposium Computational Intelligence (JSCI) is an event which was first organised in 2016. The event was initiated by IEEE Computational Intelligence Society Thailand Chapter (IEEE-CIS Thailand), that aims to support research students and young researchers, to create a place enabling participants to share and discuss on their research prior to publishing their works. The event is open to all researchers who want to broaden their knowledge in the field of computational intelligence. The symposium will feature paper presentations as well as an invited talk. JSCI9 will be held on December 18, 2020.
This is a very good opportunity to share and discuss your work with other researchers in the field of computational intelligence. If you are interested in presenting your work at this symposium, please submit a paper at [CMT]. The paper must conform to the standard of IEEE Manuscript Templates for Conference Proceedings which is available to download at [IEEE] or [Overleaf]. A 4 pages paper must be submitted to be reviewed. The papers will be double-blind peer-reviewed. Accepted papers will be available online in JSCI9 proceedings. All JSCI9 papers are invited to extend and submit their revised paper to a special session at the 17th International Conference on Computing and Information Technology (IC2IT2021), May 13-14, Bangkok, Thailand, that will be published by Springer in the Recent Advances in Information and Communication Technology 2021, which is in the Advances in Intelligent Systems and Computing (AISC) series. The books of this series are submitted to be indexed in ISI Proceedings, EI-Compendex, DBLP, SCOPUS, Google Scholar and Springerlink.
Important Dates for JSCI9/Special Session in IC2IT2021
Submission Deadline to JSCI9: November 30, 2020 (4 pages IEEE format)
Notification of Acceptance: December 11, 2020
Camera-ready Manuscript Submission: December 14, 2020
JSCI Symposium Date: December 18, 2020
Extended Paper Submission Deadline to IC2IT2021: December 24, 2020 (10 pages Springer format)
Notification of Acceptance: December 31, 2020
Camera-ready Manuscript Submission: January 4-11, 2021
Registration: January 4-11, 2021
Conference Date: May 13-14, 2021
Venue
Virtual and/or King Mongkut’s University of Technology North Bangkok (JSCI9)
Organizing Committee
Advisory
Chair
Organising Committee
Register
Free registration [Click Here]
Tentative Program
| Time | Activities/Paper Presentation | Abstract | Student Presenters | Paper |
| 9:00 – 9:15 | Opening Speech | Chair of IEEE CIS Thailand Chapter, Associate Professor Dr. Jonathan Chan (School of Information Technology, King Mongkut’s University of Technology Thonburi), | ||
| Session Chair: Assoc. Prof. Dr. Phayung Meesad, Department of Information Technology Management, Faculty of Information Technology and Digital Innovation, KMUTNB | ||||
| 9:15 – 10:00 | Keynote Speech: Associate Professor Dr. Lipo Wang, School of Electrical and Electronic Engineering, Nanyang Technological University of Singapore | Topic: Machine Learning for Data and Image Classification | ||
| 10:00-10:30 | DAGAT: Data Augmentation and Generation for Anomalous Time Series Signals | Anomaly detection tasks using learning methods are still challenging. Especially, in deep learning, a model requires a high amount of training data, which are opposed to a limited number of anomalous data that are rare events, such as high privacy concerns, secret records, and difficult gathering data. One of the efficient solutions for this problem is data augmentation to increase the number of synthesized data for training. However, data augmented with simple mathematical techniques cannot provide a high variety of patterns for learning purposes. Hence, this paper proposed a novel framework of data augmentation and generation for anomalous time series signals (DAGAT). This framework was applied on a Secure Water Treatment (SWaT) dataset, recorded from various sensors, containing anomalous events occurred on the test bed of secure water treatment system. The performance of DAGAT shows that, from only one sample of the rare case, it can be generated up to almost three thousands of reliable samples with a high variety of patterns for deep learning. | Thasorn Chalongvorachai, KMITL | |
| 10:30-11:00 | Handwritten Pashto Characters Dataset for Optical Character Recognition | In the proposed paper we introduced a new Pashtu character dataset having handwritten scanned images. we made the database freely accessible for use in science, research, and for Pashtu OCR system. Pashtu language is used by over fifty million citizens for both oral and written communications, but there is still no effort being made to the Pashtu language for Optical Character Recognition (OCR) system. |
Wahidullah Mudaser, KMUTT | |
| 11:00-11:30 | Image Recognition based on a Sequenced Edge Grid Image Technique | Currently there are many techniques and methods continuously proposed by researchers for Sign language recognition systems based-on machine learning. For data preprocessing for sign language, majority of researchers use single image of hands like static gesture images. Using only static hand images may not be efficient for real-world applications. In this paper, we propose an innovative technique for digital image data preparation called Sequenced Edge Grid Images (SEGI) for Sign Language recognition. The proposed SEGI is composed of images that represent the movement of hands within a single image, which can be applied to recognize a word or a sentence. To proof the concept, we have done several experiments with Thai sign language data collected from internet. SEGI was with existing techniques. Data are the Thai sign language learning video clips that are vocabularies to use in daily life. The proposed technique was implemented with convolutional neural network (CNN). For normal CNN, the experiments show that the best result based on SEGI with CNN approached up 99.95% recognition. | Supathep Satiman, KMUTNB | |
| 11:30-12:00 | A Study of English-Vietnamese Machine Translation based on Deep Learning | Machine translator (MT) is a popular program to translate text or speech from one language to another. MT also performs mechanic substitutions of words in one language for words in another but that rarely produces a good translation because recognition of whole phrases and the words sometimes belong to the context of conversation. In this paper, we build a MT for an English-Vietnamese translator using deep learning methods: Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU), Attention, and Transformer. The deep learning based machine translators were compared based on the test accuracy of results translation. It was found that best deep learning based machine translator model was the Attention mechanism, achieving 86.3% accuracy. The Transformer yielded second rank or 85.63% accuracy. | Nguyen Minh Tuan, KMUTNB | |
| 12:00-13:00 | Lunch Break | |||
| Session Chair: Asst. Prof. Dr. Maleerat Maliyam, Department of Information Technology, Faculty of Information Technolgoy and Digital Innovation, KMUTNB | ||||
| 13:00-13:45 | Industrial Keynote Speech: Tanut Karnwai (Data Science & AI Technical Specialist) | AI in decision making for insurance industry. Driving Better Decisions: Insurance | ||
| 13:45-14:15 | Hand Foot and Mouth Rash Detection Using Deep Convolution Neural Network | Hand-foot-mouth disease (HFMD) is an extremely contagious viral infection common in infants that may quickly develop into a server problem. The disease spreads easily through person-to-person contact with an infected person. To assist in diagnosing HFMD, we built a dataset of over 2000 images of various skin conditions. We propose a deep convolution neural to distinguish HFMD rash from other skin conditions. Experimental results show 0.954 accuracy on our curated dataset. Our proposed model can potentially facilitate a proper and early detection of HFMD rash to assist in containing HFMD outbreaks in the Asia Pacific region. | Naqibullah Vakili, KMUTT | |
| 14:15-14:45 | An Improved Hola Framework for Saliency Detection | Recently, a Hola framework was designed and implemented for saliency detection. It showed good performance among existing saliency detection methods. However, that proposed framework still have some rooms for performance improvement. Hence, this paper proposed an improved Hola (i-Hola) framework for saliency detection. The experimental results showed that the proposed framework can provide the improved performance of saliency detection. | Donyarut Kakanopas, KMITL | |
| 14:45-15:15 | Keynote Speech: Associate Professor Dr. Phayung Meesad (King Mongkut’s University of Technology North Bangkok) | Topic: Trends and Challenges in Big Data Analytics | ||
| 15:15-15:30 | Closing Remark | |||
| 15:30-16:30 | IEEE CIS Thailand Chapter Committee Meeting |