Program
Tuesday, December 21
Tuesday, December 21 7:30 - 8:20 (Asia/Saigon)
Registration
Tuesday, December 21 8:20 - 10:00 (Asia/Saigon)
CI-1: Computational Intelligence
- 8:20 Enhanced Approaches for Cluster Newton Method for Underdetermined Inverse Problems
- 8:40 An Adaptive Method for Classification of Noisy Respiratory Sounds
- 9:00 An Application Improving the Accuracy of Image Classification
- 9:20 An Embedded Machine Learning System for Real-Time Face Mask Detection and Human Temperature Measurement
- 9:40 Named Entity Recognition for Vietnamese Real Estate Advertisements
COM-1: Communication and Networking
- 8:20 A Circularly Polarized Array Antenna for GPS Application
- 8:40 Evaluation of Smartphone and Smartwatch Accelerometer Data in Activity Classification
- 9:00 A New Back-Projection Algorithm in Frequency Domain for Multi-Receiver Synthetic Aperture Sonar
- 9:20 A Random Access Protocol for Massive MIMO: The Adaptive ACB Based Collision Resolution
- 9:40 An Ensemble Feature Selection Algorithm for Machine Learning Based Intrusion Detection System
FCS-1: Foundations of Computer Science
- 8:20 On the Unmixedness Problems of Colored Pushdown Automata
- 8:40 Performance Evaluation of Quine-McCluskey Method on Multi-Core CPU
- 9:00 Attention in Crowd Counting Using the Transformer and Density Map to Improve Counting Result
- 9:20 Blockchain-Enabled Electronic Medical Record with Hyperledger Composer
- 9:40 Image Encryption Through Lucas Sequence, S-Box and Chaos Theory
SE-1: Software Engineering
- 8:20 Detecting Drivers Falling Asleep Algorithm Based on Eye and Head States
- 8:40 Function Exclusion in Automated Security Patch Testing Using Chopped Symbolic Execution
- 9:00 Socially Aware Robot Navigation Framework in Crowded and Dynamic Environments: A Comparison of Motion Planning Techniques
- 9:20 Detect Repackaged Android Applications by Using Representative Graphs
- 9:40 Forensics Analysis of FacePlay Application to Seek Digital Artifacts on Data Ownership and Privacy
Tuesday, December 21 10:00 - 10:30 (Asia/Saigon)
Coffee break
Tuesday, December 21 10:30 - 12:10 (Asia/Saigon)
CI-2: Computational Intelligence
- 10:30 A Personalized Adaptive Algorithm for Sleep Quality Prediction Using Physiological and Environmental Sensing Data
- 10:50 DeepInsight-Convolutional Neural Network for Intrusion Detection Systems
- 11:10 Modified CNN Model-Based Forgery Detection Applied to Multiple-Resolution Tampered Images
- 11:30 Enhancing Twin Delayed Deep Deterministic Policy Gradient with Cross-Entropy Method
- 11:50 Efficiency Enhancement of Evolutionary Neural Architecture Search via Training-Free Initialization
COM-2: Communication and Networking
- 10:30 LS-SPP: A LSTM-Based Solar Power Prediction Method from Weather Forecast Information
- 10:50 FedChain: A Collaborative Framework for Building Artificial Intelligence Models Using Blockchain and Federated Learning
- 11:10 An Approach for Service Function Chain Orchestration in Combination with SDN-Based Network
- 11:30 Template Waveform Synthesize Technique for Ultra-Wide Band Signal in Measuring Distance
- 11:50 Change Detection in Multiple-Temporal Synthetic Aperture Radar Images Based on Averaged Heterogeneous Factors of Neighbourhood Areas
FCS-2: Foundations of Computer Science
- 10:30 An Augmented Embedding Spaces Approach for Text-Based Image Captioning
- 10:50 IoMT Security: SHA3-512, AES-256, RSA and LSB Steganography
- 11:10 Image Retrieval with Text Feedback Based on Transformer Deep Model
- 11:30 Guided Anchoring Cascade R-CNN: An Intensive Improvement of R-CNN in Vietnamese Document Detection
- 11:50 DR-Unet: Rethinking the ResUnet++ Architecture with Dual ResPath Skip Connection for Nuclei Segmentation
SE-2: Software Engineering
- 10:30 An Efficient Method for Automated Regression Test Data Generation for C/C++ Projects
- 10:50 Page Object Detection with YOLOF
- 11:10 Assessing a Voice-Based Conversational AI Prototype for Banking Application
- 11:30 A Lightweight Model for Remote Sensing Image Retrieval with Knowledge Distillation and Mining Interclass Characteristics
- 11:50 A Graph Analysis Based Approach for Specification-Driven Testing of Model Transformations
Tuesday, December 21 12:10 - 1:30 (Asia/Saigon)
Lunch break
Tuesday, December 21 1:30 - 1:50 (Asia/Saigon)
Opening ceremony
Tuesday, December 21 1:50 - 2:50 (Asia/Saigon)
Keynote speaker #1: CRYScanner: Finding cryptographic libraries misuse
Abstract: Cryptographic libraries have become an integral part of every digital device. Studies have shown that these systems are not only vulnerable due to bugs in cryptographic libraries, but also due to misuse of these libraries. In this paper, we focus on vulnerabilities introduced by the application developer. We performed a survey on the potential misuse of well-known libraries such as PKCS #11. We introduce a generic tool CRYScanner, which is designed to identify such misuses during and post development. It works on the similar philosophy of an intrusion detection system for an internal network. The tool provides verification functions needed to check the safety of code, such as detecting incorrect call flow and input parameters. We performed a feature-wise comparison with the existing state of the art solutions. Our tool aimed to add more features, keeping all the capabilities of both static and dynamic analysis. We also show the detection of potential vulnerabilities in the several sample codes found online.
Biography: Sylvain Guilley is General Manager and CTO at Secure-IC, a French company offering cybersecurity solutions for embedded systems and connected objects. Secure-IC's flagship product is the multi-certified Securyzr integrated Secure Element (iSE). He is an alumnus from École Polytechnique and Télécom Paris. Sylvain is also professor at Télécom Paris and research associate at École Normale Supérieure (ENS). His research interests include trusted computing, cyber-physical security, secure prototyping in FPGA & ASIC, and formal / mathematical methods. Since 2012, he organizes the PROOFS workshop (http://www.proofs-workshop.org/), which brings together researchers who share the objective to increase the trust in embedded systems security. Sylvain is also lead editor of international standards, such as ISO/IEC 20897 (Physically Unclonable Functions), ISO/IEC 20085 (Calibration of non-invasive testing tools), and ISO/IEC 24485 (White Box Cryptography). He is leading the topic "High Level Principles for Design & Architecture'' in the editing team of TR68 (Autonomous Vehicles---Singapore, Standards Development Organization), and is member of the French BNA (Bureau de Normalisation de l'Automobile i.e. Automotive Standardization Office). Member of the IACR, senior member of the IEEE and the CryptArchi club, Sylvain is also associate editor of the Springer Journal of Cryptography Engineering (JCEN), has co-authored 250+ research papers and filed 40+ invention patents.
- 1:50 CRYScanner: Finding Cryptographic Libraries Misuse
Tuesday, December 21 2:50 - 3:20 (Asia/Saigon)
Tuesday, December 21 3:20 - 5:00 (Asia/Saigon)
CI-3: Computational Intelligence
- 3:20 Understanding Community Mobility Through Life Satisfaction, Human Development, and ICT Development: A Data Mining Approach
- 3:40 Exploring the Performances of Stacking Classifier in Predicting Patients Having Stroke
- 4:00 An Efficient Algorithm for Mining Maximal Co-Location Pattern Using Instance-Trees
- 4:20 Self-Supervised Visual Feature Learning for Polyp Segmentation in Colonoscopy Images Using Image Reconstruction as Pretext Task
- 4:40 Deep Feature Rotation for Multimodal Image Style Transfer
CI-4: Computational Intelligence
- 3:20 VNAnomaly: A Novel Vietnam Surveillance Video Dataset for Anomaly Detection
- 3:40 Real-Time Siamese Visual Tracking with Lightweight Transformer
- 4:00 Classification of Anatomical Landmarks from Upper Gastrointestinal Endoscopic Images
- 4:20 HSUM-HC: Integrating Bert-Based Hidden Aggregation to Hierarchical Classifier for Vietnamese Aspect-Based Sentiment Analysis
- 4:40 UIT-DroneFog: Toward High-Performance Object Detection via High-Quality Aerial Foggy Dataset
COM-3: Communication and Networking
- 3:20 Performance Evaluation of Cooperative NOMA-IRS Network Using Particle Swarm Optimization
- 3:40 Wireless Wearable ElectroMyography Acquisition System Utilizing Reduced-Graphene-Oxide Based Sensor
- 4:00 An X-Band Reflectarray Antenna Using Concentric Rings and a Cross
- 4:20 A Low Complexity Detector for Two-Way Relay Stations in Wireless MIMO-SDM-PNC Systems
COM-4: Communication and Networking
- 3:20 Investigation on Radiation Characteristics of Dielectric Lens Antennas at Millimeter-Wave
- 3:40 AlertTrap: On Designing an Edge-Computing Remote Insect Monitoring System
- 4:00 Design of a High-Speed 8-Bit Flash ADC Using Double-Tail Comparator on 180nm CMOS Process
- 4:20 A Robust PCA Feature Selection to Assist Deep Clustering Autoencoder-Based Network Anomaly Detection
- 4:40 A Tourism Support Framework Using Beacons Technology
Tuesday, December 21 6:00 - 9:00 (Asia/Saigon)
Banquet
Wednesday, December 22
Wednesday, December 22 8:30 - 9:30 (Asia/Saigon)
Keynote speech #2: Advanced Terahertz Devices and Systems Toward 6G and Beyond
Abstract: A wide untapped region exists between radio waves and light in the electromagnetic spectrum: terahertz (THz) waves. THz frequencies combine the penetration of radio waves and the large bandwidth of light, which makes them excellent candidates for next-generation information communication technology, 6G and beyond, such as ultra-broadband wireless communication, spectroscopic sensing, nondestructive imaging, and high-resolution ranging. However, THz frequencies are at the upper limit of the capabilities of conventional electronics, and the development of THz devices and systems is a challenging field of interdisciplinary research. In particular, it is difficult to generate a significant amount of power from THz sources. THz devices must, therefore, be as efficient as possible to conserve limited power. Resonant tunneling diodes are a major candidate for both THz transmitters and receivers because of their simple and low-power electronic devices. In addition, a low-loss platform for integrating THz devices is essential for various practical systems. However, the propagation loss of transmission lines based on conventional electronics is high in the THz region, mainly owing to the high ohmic loss in metals. Thus, an alternative, metal-free integrated platform based on THz silicon photonics or photonic crystals is necessary to manipulate THz waves.
Biography: Masayuki Fujita received the Ph.D. degree from Yokohama National University, Yokohama, Japan, where he focused on ultrasmall and ultralow-threshold microdisk lasers, in 2002. Subsequently, he joined the Department of Electronic Science and Engineering, Kyoto University, Kyoto, Japan, and initiated research on photonic crystals, including spontaneous emission control in photonic crystals and high-efficiency light extraction in light-emitting diodes and silicon light emitters. Next, he moved to Osaka University, Toyonaka, Japan, in 2011 and was appointed the Research Director of the strategic basic research program CREST, "Development of terahertz integrated technology platform through fusion of resonant tunneling diodes and photonic crystals" and "Development of integrated devices and systems to control time domain and space distribution of terahertz waves," of the Japan Science and Technology Agency. He is currently an Associate Professor with the Graduate School of Engineering Science, Osaka University. His research interests include terahertz materials, devices, systems, and photonic nanostructures, microstructures, and their applications. He is a Member of the Japan Society of Applied Physics, the Laser Society of Japan, the Institute of Electronics, Information and Communication Engineers (IEICE), Japan, the Japanese Photochemistry Association, and Optica, formerly OSA. From 1999 to 2002 and from 2003 to 2006, he was a Research Fellow of the Japan Society for the Promotion of Science. He is currently an Associate Editor for Applied Physics Express and a Chair of the Technical Group on Terahertz Application Systems of IEICE, Japan.
Wednesday, December 22 9:30 - 10:00 (Asia/Saigon)
Coffee break
Wednesday, December 22 10:00 - 11:40 (Asia/Saigon)
CI-5: Computational Intelligence
- 10:00 UIT-Anomaly: A Modern Vietnamese Video Dataset for Anomaly Detection
- 10:20 In-Bed Posture Classification Using Pressure Sensor Data and Spiking Neural Network
- 10:40 Tire Wear Detection for Accident Avoidance Employing Convolutional Neural Networks
- 11:00 EMG Signals Classification on Human Activity Recognition Using Machine Learning Algorithm
- 11:20 Autonomous Detection and Approach Tracking of Moving Ship on the Sea by VTOL UAV Based on Deep Learning Technique Through Simulated Real-Time On-Air Image Acquisitions
CI-6: Computational Intelligence
- 10:00 Socially Aware Robot Navigation Framework: Social Activities Recognition Using Deep Learning Techniques
- 10:20 U-Net Semantic Segmentation of Digital Maps Using Google Satellite Images
- 10:40 A Modified FCN-Based Method for Left Ventricle Endocardium and Epicardium Segmentation with New Block Modules
- 11:00 Enhancing COVID-19 Prediction Using Transfer Learning from Chest X-Ray Images
- 11:20 Rotation Forest Ensemble Classifier to Improve the Cardiovascular Disease Risk Prediction Accuracy
COM-5: Communication and Networking
- 10:00 Prediction of Working Frequencies for Ionospheric Radio Links
- 10:20 Highly Secure Data Encryption Devices Using Unique Physically Unclonable Key
- 10:40 Design of a Ka-Band MMIC Low Noise Amplifier for 5G Applications
- 11:00 Federated Learning-Based Intrusion Detection in SDN-Enabled IIoT Networks
- 11:20 Performance Evaluation of Neural Network-Based Channel Detection for STT-MRAM
COM-6: Communication and Networking
- 10:00 A Cost-Effective High-Performance Conducted Emission Test Solution to Comply with MIL-STD-461F/G Standard
- 10:20 Jammer Detection by Random Pilots in Massive MIMO Spatially-Uncorrelated Rician Channels
- 10:40 Design and Implementation of a V2X-Tag for IoT-Based Smart On-Street Parking System
- 11:00 An Approach to Design a Multi-Protocol Gateway Device for Internet of Things System
- 11:20 ODLIE: On-Demand Deep Learning Framework for Edge Intelligence in Industrial Internet of Things
Wednesday, December 22 11:40 - 1:30 (Asia/Saigon)
Lunch break
Wednesday, December 22 1:50 - 3:30 (Asia/Saigon)
SS#1: 6G Emerging Technology for Wireless Communications
- 1:50 On the Improvement of Machine Learning Based Intrusion Detection System for SDN Networks
- 2:10 Secrecy Performance of RIS-Assisted Wireless Networks Under Rician Fading
- 2:30 Hybrid Similarity Matrix in Neighborhood-Based Recommendation System
- 2:50 Analysis of Multi-Ray Propagation for DSRC Communication on Street with RISs on Sidewalls
Wednesday, December 22 1:30 - 1:50 (Asia/Saigon)
SS#2 Advanced Communication and Signal Processing Technologies for IoT-based Smart Farming
Wednesday, December 22 1:50 - 3:30 (Asia/Saigon)
SS#2: Advanced Communication and Signal Processing Technologies for IoT-based Smart Farming
- 1:50 Aquaculture Environment Prediction Based on Improved LSTM Deep Learning Model
- 2:10 Real-Time Agriculture Field Monitoring Using IoT-Based Sensors and Unmanned Aerial Vehicles
- 2:30 Vulnerabilities of Internet of Things, for Healthcare Devices and Applications
- 2:50 A Novel Adaptive Neural Controller for Narrowband Active Noise Control Systems
- 3:10 SupSLAM: A Robust Visual Inertial SLAM System Using SuperPoint for Unmanned Aerial Vehicles
Wednesday, December 22 1:30 - 3:10 (Asia/Saigon)
SS#3: Advanced Applications of Digital Transformation, Security and Intelligence
- 1:30 Predicting Job Titles from Job Descriptions with Multi-Label Text Classification
- 1:50 Digitalization of Administrative Documents - A Digital Transformation Step in Practice
- 2:10 An Approach to Evaluate Alternatives in Multi-Attribute Decision Making Problems Based on Linguistic Many-Valued Logic
- 2:30 Automated Attendance System in the Classroom Using Artificial Intelligence and Internet of Things Technology
- 2:50 Secret Key Group Implementation Using Chain Topology
Wednesday, December 22 1:30 - 1:50 (Asia/Saigon)
SS#4 Advanced mm-Wave technologies: Systems and Applications
The increase of IoT devices is producing a massive amount of data to be computed by data centers, pushing the network to the limit. The storage and speed bandwidth has become a bottleneck as there are too many objects sharing the same streams. This is leading to slow speeds, lagging and delays. How does the industry try to tackle this challenge? The answer is to deploy more intelligence at the Edge. To sustain the growth of IoT and continue to deliver stronger, better, faster applications, the industry requires new efficient technologies. FD-SOI is certainly the most attractive technology to keep up the speed of our innovations at the Edge. The talk will review the challenges of Edge computing and will show how FD-SOI has already started to power the revolution.