The Joint Symposium on Computational Intelligence (JSCI) is an event that was first organized in 2016. The event was initiated by IEEE Computational Intelligence Society Thailand Chapter (IEEE-CIS Thailand), which aims to support research students and young researchers, to create a place enabling participants to share and discuss 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 student paper presentations as well as invited talks.
JSCI is a rehearsal platform for students who would like to extend the work to present and publish at Scopus conference proceedings or to submit for Scopus-Indexed Journals. JSCI is a stage for undergraduate and graduate students to practice their research works under supervision by professors in the community. It is an activity organized by the IEEE Computational Intelligence Society Thailand Chapter. Students who participated in this event will gain some experience in both the presentation and written academic papers for conferences and journals.
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 https://easychair.org/conferences/?conf=jsci13. The paper must conform to the standard of IEEE Manuscript Templates for Conference Proceedings which is available to download at https://www.ieee.org/conferences/publishing/templates.html or https://www.overleaf.com/latex/templates/ieee-conference-template/grfzhhncsfqn. A 4-6 pages paper must be submitted to be reviewed. The papers will be double-blind peer-reviewed (please do not include authors’ names for the first-round submission).
Areas of Interest:
The topics cover neural networks, connectionist systems, fuzzy systems, hybrid intelligent systems, and evolutionary computation, i.e., nature-inspired optimization (metaheuristics) such as genetic algorithms, particle swarm optimization, firefly algorithm, etc., including theory, design, application, and development of biologically and linguistically motivated computational intelligence.
Important Dates
– Paper submission: April 19th, 2023
– Author notification: May 10th, 2023
– Camera-ready copies: May 19th, 2023
– Presenter Registration: May 19th, 2023
– Symposium dates: May 26th, 2023 (hybrid)
Invited Speakers
Organizing Committee
Advisory
General Chair
Organising Committee
Registration: Click here to register for JSCI13
TENTATIVE SCHEDULE ON MAY 26, 2023
| Time | Activities/Paper Presentation | Abstract | Presenters | Paper |
| 8:55 – 9:00
9:00 – 9:45 |
Opening Remarks
Invited Talk: Mathematical Models in Social Interaction |
School of Information Technology, KMUTT
Prof. Dr. Kazushi IKEDA (Nara Institute of Science and Technology) |
||
| 9:45 – 10:05 | Gastro-Intestinal Tract Segmentation Using an Explainable 3D Unet | In treating gastrointestinal cancer using radiotherapy, the role of the radiation oncologist is to administer high doses of radiation, through x-ray beams, toward the tumor while avoiding the stomach and intestines. With the advent of precise radiation treatment technology such as the MR-Linac, oncologists can visualize the daily positions of the tumors and intestines, which may vary day to day. Before delivering radiation, radio oncologists must manually outline the position of the gastrointestinal organs in order to determine position and direction of the x-ray beam. This is a time consuming and labor intensive process that may substantially prolong a patient’s treatment. A deep learning (DL) method can automate and expedite the process. However, many deep neural networks approaches currently in use are black-boxes which lack interpretability which render them untrustworthy and impractical in a healthcare setting. To address this, an emergent field of AI known as Explainable AI (XAI) may be incorporated to improve the transparency and viability of a model. This paper proposes a deep learning pipeline that incorporates XAI to address the challenges of organ segmentation. |
Kai Li | [PDF] |
| 10:05 – 10:25 | Data Imputation Using Multivariate-VAE Approach for Time Series Signals | Missing data is one of the most common and frequent problems found in data processing tasks. The incomplete data, specifically anomaly signals, could potentially degrade the performance of most machine learning applications. The challenges come from the noise in a signal and the complexity of the data. Hence, there are many attempts to solve this issue by using a variety of methods. Nevertheless, most techniques still suffer from inaccurate data filling and are incompetent to regenerate extreme data losses. Importantly, they are not suitable for reconstructing missing data from anomalous signals, due to their inability to handle high complexity and noisy data. Therefore, here, we demonstrate the Variational Autoencoder (VAE) approach to impute anomaly time series data, applying the concept of VAE to reconstruct missing values. The experiments simulated missing data in real-world anomalous datasets. Then, we compare the performance of signal imputation using traditional methods (No VAE), single-variate VAE, and multivariate VAE models. Experimental results show that not only can VAE handle highdimensional and noisy data, but it also has better performances in both root-mean-square error and accuracy. The reason is that the VAE model is trained with more features. |
Thasorn Chalongvorachai | [PDF] |
| 10:25 – 11:10 | Invited Talk (online): Cooperatively Managing and Exploiting Distributed Co-occurrence Graphs | Asst. Prof. Dr.-Ing. Supaporn SIMCHAROEN (King Mongkut’s University of Technology North Bangkok) | ||
| 11:10 – 11:30 | 2D X-Ray Solder Joint Segmentation based on K-Means Clustering and Deep Learning | Chukiat Boonkorkoer | [PDF] | |
| 11:30 – 11:50 | Applications of Machine Learning in Detecting Afghan Fake Banknotes | Hamida Ashna | [PDF] | |
| 11:50 – 12:10 | Spelling Check with A New Brain-Inspired Sequence Learning Memory | This study focused on enhancing learning sequences using a method inspired by the brain, following Hawkins’s approach. Capable of not only recognizing existing sequences but also learning new ones and ensuring faulttolerant operations, the learning method was evaluated through a spelling check. The evaluation utilized the standard TREC-5 Confusion Track dataset to automatically correct incorrect words. The new method was compared with other techniques, such as Levenshtein Distance, pyspellchecker, LSTM, and Elmosclstm (Semantically Conditioned LSTM and Elmo Transformer), which is the state-of-the-art. The results demonstrated that the highest accuracy at the word level was 79.35%%, surpassing Elmosclstm’s 74.41%. Additionally, at the sentence level, the brain-inspired method achieved 90.75% accuracy, outperforming Elmosclstm’s 72.18%. |
Thasayu Soisoonthorn | [PDF] |
| 12:10 – 13:10 | Lunch Break |
| Time | Activities/Paper Presentation | Abstract | Presenters | Paper |
| 13:10 – 13:55 | Invited Talk (online): Question Generation Using Sequence-to-Sequence Model with Semantic Role Labels |
Prof. Dr. Aijun AN (York University) | ||
| 13:55 – 14:15 | Improvement of 3DVAE-LSTM for Extremely Rare Anomaly Signal Generation | Thongchai Kaewkiriya | [PDF] | |
| 14:15 – 14:35 | A Machine Learning Approach to Detect Dehydration in Afghan Children | Ziaullah Momand | [PDF] | |
| 14:35 – 15:20 | Invited Talk (online): Recent Developments in Task-Oriented and Context-Sensitive Information Retrieval | Prof. Dr. Jimmy HUANG (York University) | ||
| 15:20 – 17:00 | Selected Poster Presentations from CSC532 Machine Learning class | [ | ||