ICTLab
- Director: Pierre Larmande, IRD
- Location: The 5th floor, USTH building, VAST Campus, 18 Hoang Quoc Viet, Cau Giay, Hanoi
- Website: http://ictlab.usth.edu.vn
This joint Laboratory was set up in 2014 with the mentioned partners.
In recent years, the assessment and management of complex socio-environmental systems have increasingly relied on the design and use of computer models as a way to inform, support and sometimes supplement human decision. However, the scale at which problems are now raised, the simultaneous abundance of raw data and scarcity of information available on these systems, the necessity to adopt perspectives that take multiple, possibly conflicting, goals, into account, all of these reasons plead for the development of ICT methods and tools that go beyond the current state of the art and cover all aspects of environmental decision-making processes, including the gathering and processing of quantitative and qualitative data, the design of models that account for the complexities, non-linearities, heterogeneities, and multiple scales of space and time, the intelligent exploration of their outcomes in multiple scenarios and the continuous monitoring of the strategies implemented.
The goal of ICTLab, in that respect, is to design and deliver such methods and tools by conducting and combining investigations in different domains of ICT:
- Modeling and Simulation;
- Machine Learning and Data Mining;
- Image and Speech Processing;
- Information Retrieval;
- Expert User Interactions;
- Sensor Networks and Embedded Systems;
- High Performance Computing;
- BioInformatics.
2. Partnership
- Vietnamese partners : VAST-IOIT
- International partners : Université La Rochelle-L3i; IRD-UMMISCO
3. Funding sources
- USTH
- IRD-UMMISCO
- University of La Rochelle, France
- French Embassy in Vietnam
- Vietnam Academy of Science and Technology
4. Equipment
ICTLab is equipped with a small scale GPU-based High Performance Computing Cluster. The cluster consists of 9 machines in total.
All of the computing nodes are running with a single/dual socket 6-core Intel Xeon CPUs configuration, with at least 24GB of RAM and 1TB storage (HDD or SSD). The installed GPUs range from GTX 690 (2 x 1536 cores), GTX Titan Black (2880 cores), Tesla K40c (2880 cores) to Tesla K80 (2 x 2496 cores). GPU memory ranges from 4GB to 12GB for each install card. The computing nodes are interconnected by both 1Gbps Ethernet and FDR 56Gbps Infiniband. A shared 15TB RAID storage is provided to each node.
The cluster is currently used for various scientific problems, such as deep learning, computer vision, speech synthesis and recognition, etc.
5. Ongoing research activities
ICTLab is currently working with the four following research projects:
- ESCAPE is an ANR project that focus on the simulation of urban area evacuation in case of catastrophe. The simulator is based on the gama simulation platform and is based on agent-based modeling of the evacuation process: this allow to explore individually based strategy, including individual knowledge about evacuation plan, emotion during egress and individually based mobility model with several modes. The project focus on three case studies: chemical risk with industry explosion in the center of the city of Rouen (France), flash flood risk at the valley of Authion (France) and Hoa Binh dam break in the region of Hanoi - Red River (Vietnam).
- Gen* is an open source java library that make it possible to generate spatially explicit and socially connected synthetic population using any survey and GIS data. The toolkit is also available as a Gama plugin and can be used through the Kepler workflow management tool. How aim is to provide to computer scientist and none programmers the access to state of the art algorithms to solve synthetic population generation, explicit localization and network generation of synthetic entities. The library is under development but already provide several algorithms for each of this three part: gospl, spll and spin. See https://github.com/ANRGenstar/genstar for further information.
- AgroLD (The Agronomic Linked Data project): Recent advances in high-throughput technologies have resulted in tremendous increase in the amount of data in the agronomic domain. This data explosion in-conjunction with its heterogeneity presents a major challenge in adopting an integrative approach towards research. We are developing AgroLD, a knowledge system that exploits the Semantic Web technology and some of the relevant standard domain ontologies, to integrate information on rice species and in this way facilitating the formulation of new scientific hypotheses. The objective of this effort is to provide the community with a platform for domain specific knowledge, capable of answering complex biological questions. The current phase covers information on genes, proteins, ontology associations, homology predictions, metabolic pathways, plant traits, and germplasm, on the Arabidopsis and rice species.
- LungCancerCare (A system to support doctors in Lung Cancer Diagnosis and Treatment): Lung cancer is one of the most serious and common types of cancer all over the world, both in number of new patients and in number of fatalities. There were total 1.69 millions of fatalities because of lung cancer in 2015 only (source: World Health Organization). Lung cancer is the most common type of cancer for both genders in Vietnam. According to statistics from Ministry of Health, Vietnam has 25200 new patients in 2017 and expected 30.000 new patents per year in 2020. The goal of this project is to study and develop efficient deep learning models in order to improve the accuracy and computational performance to lung cancer image analysis algorithms. Specific goals include: (1) Building an annotated image dataset for lung cancer analysis with case studies in Vietnamese hospitals; (2) Studying and proposing deep learning models for efficient detection and classification of lung tumors as benign and malignant; (3) Developing a decision support software to assist doctors in lung cancer detection.
- iMorph (Detection of geometric morphometric landmarks in 2D insect wing images): The field of morphometrics, or morphometry, is concerned with the analysis of form, which is defined by shape and size, of an object. Shape is defined as the set of geometric properties of an object that are invariant to position, orientation, and scale. In a population of specimens of interest, shape variability with size, i.e. allometry, is also considered. The main goal of morphometrics is to elucidate how shapes vary and their covariance with other variables such as diseases, environmental stresses, or development etc. Morphometrics is very important in biology because it allows quantitative descriptions of organisms, hence facilitating comparative studies by statistical analysis methods. Landmark-based geometric morphometrics uses a set of landmarks to describe shape. Landmark, a two- or three-dimensional point represented by locus coordinates, is described by a tightly defined set of rules that indicates the evolutionary significance for the organism in question. Given these defined rules, it is next necessary to identify the landmarks on each specimen. This task is normally done by an expert, however, it is time-consuming and error-prone. Therefore, in this project, we aim to automate this by processing object images and employing an image recognition & machine learning model to propose landmark candidates.
6. Members
No |
Full name |
Position |
University/Institute |
Remark |
Vietnamese members |
||||
1 |
LUONG Chi Mai |
Senior Researcher |
IOIT-VAST |
|
2 |
TRAN Giang Son |
Researcher |
USTH |
|
3 |
DOAN Nhat Quang |
Researcher |
USTH |
|
4 |
NGHIEM Thi Phuong |
Researcher |
USTH |
|
5 |
GIANG Anh Tuan |
Researcher |
USTH |
|
6 |
NGUYEN Hoang Ha |
Researcher |
USTH |
|
7 |
LE Huu Ton |
Researcher |
USTH |
|
8 |
NGUYEN Minh Huong |
Researcher |
USTH |
|
9 |
TRAN Hoang Tung |
Researcher |
USTH |
|
10 |
HO Bich Hai |
Researcher |
IOIT-VAST |
|
11 |
DO Quoc Truong |
Researcher |
VAIS Co., Ltd. |
|
12 |
NGUYEN The Loc |
Researcher |
HUMG |
|
13 |
PHAM Tri Cong |
PhD student |
USTH |
|
14 |
NGUYEN Chi Cuong |
PhD student |
USTH |
|
15 |
PHAM Ngoc Phuong |
PhD student |
IOIT-VAST |
|
International members |
||||
1 | Pierre LARMANDE | Director | IRD-UMMISCO | |
2 | Antoine DOUCET | Senior Researcher | University of La Rochelle | |
3 | Alexis DROGOUL | Senior Researcher | IRD-UMMISCO | |
4 | Benoit GAUDOU | Senior Researcher | IRD-UMMISCO | |
5 | Karell BERTET | Senior Researcher | University of La Rochelle | |
6 | Jean-Christophe BURIE | Senior Researcher | University of La Rochelle | |
7 | Yacine GHAMRI | Senior Researcher | University of La Rochelle | |
8 | Nicolas SIDÈRE | Senior Researcher | University of La Rochelle | |
9 | Muriel VISANI | Senior Researcher | University of La Rochelle | |
10 | Arthur BRUGIERE | Invited Researcher | IRD-UMMISCO |
7. Featured publications
No |
Publications |
Authors |
Journal / Conference |
Year |
1 |
AgroPortal: an ontology repository for agronomy |
Jonquet C, Toulet A, Arnaud E, Aubin E, Dzalé-Yeumo E, Emonet V, Graybeal J, Laporte M-A, Musen M, Pesce V, Larmande Pierre |
Computers and Electronics in Agriculture |
2018 |
2 |
Progress in single access information systems for wheat and rice crop improvement |
Scheben A., Chan K., Mansueto L., Mauleon R., Larmande Pierre, Alexandrov N., Wing R., McNally K., Quesneville, H., Edwards D. |
Briefing in Bioinformatics |
2018 |
3 |
Synthetic population in social simulation: a review of methods and practices |
Kevin Chapuis, Patrick Taillandier, Thiriot Samuel & Alexis Drogoul |
Journal of Artificial Societies and Social Simulation (to be published) |
2018 |
4 |
Gen*: a generic toolkit to generate spatially explicit synthetic populations |
Kevin Chapuis, Patrick Taillandier, Misslin Renaud & Alexis Drogoul |
International Journal of Geographical Information Science |
2018 |
5 |
Towards Real-Time Smile Detection based on Faster Region Convolutional Neural Network |
Chi Cuong Nguyen, Giang Son Tran, Thi Phuong Nghiem, Nhat Quang Doan, Damien Gratadour, Jean Christophe Burie and Chi Mai Luong |
International Conference on Multimedia Analysis |
2018 |
6 |
Study of CNN Based Classification for Small Specific Datasets |
Huu Ton Le, Thierry Urruty, Marie Beurton-Aimar, Thi Phuong Nghiem, Hoang Tung Tran, Romain Verset, Marie Ballere, Hien Phuong Lai and Muriel Visani |
10th Asian Conference on Intelligent Information and Database Systems |
2018 |
7 |
Customer clustering based on purchased items from social network |
Nguyen Huu Hai, Doan Nhat Quang, Pham Thanh Nam, Phan Trung Kien |
7th National Conference on Information Technology and its Applications |
2018 |
8 |
Hierarchical Laplacian Score for unsupervised feature selection |
Nhat-Quang Doan, Hanane Azzag, Mustapha Lebbah |
International Joint Conference on Neural Networks |
2018 |
9 |
Deep CNN and Data Augmentation for Skin Lesion Classification |
Tri-Cong Pham, Chi-Mai Luong, Muriel Visani, Van-Dung Hoang |
10th Asian Conference on Intelligent Information and Database Systems |
2018 |
10 |
Scientific workflows for computational reproducibility in the life sciences: Status, challenges and opportunities |
Cohen-Boulakia S, Belhajjame K, Collin O, Chopard J, Froidevaux C, Gaignard A, Hinsen K, Larmande Pierre, Le Bras Y, Lemoine F, Mareuil F, Ménager H, Pradal C, Blanchet C. |
Future Generation of Computer Systems |
2017 |
11 |
Developing data interoperability using standards: A wheat community use case |
Dzale Yeumo E, Alaux M, Arnaud E, Aubin S, Baumann U, Buche P, Richard F, Jonquet C, Laporte MA, Larmande Pierre, Pommier C, Protonotarios V, Reverte C, Shrestha R, Subirats I, Venkatesan A, Whan A and Quesneville H. |
F1000Research |
2017 |
12 |
Realistic urban road network modelling Form GIS Data |
Hoang Ha Nguyen, B. Desbenoit, and M. Daniel |
Eurographics Workshop on Urban Data Modelling and Visualisation |
2016 |
13 |
Improving the Accuracy in Wifi-based Indoor Positioning with Kalman |
Nguyen Thi Thu, Vuong Quang Phuong, Nguyen Hoang Ha, and Hoang Do Thanh Tung |
National conference on some selected issues in information and communication technology |
2016 |
14 |
Spatial capacity of IEEE 802.11p based VANET: models, simulations and experimentations |
Anh Tuan Giang, Anthony Busson, A. Lambert, D. Gruyer |
Vehicular Technology, IEEE Transactions on |
2016 |
15 |
Improving retrieval framework using information gain models |
Huu Ton Le, Thierry Urruty, Syntyche Gbèhounou, François Lecellier, Jean Martinet, Christine Fernandez |
Signal, Image and Video Processing |
2016 |
16 |
Extended Process Scheduler for Improving User Experience in Multi-core Mobile Systems |
Giang Son Tran, Thi Phuong Nghiem, Tuong Vinh Ho and Chi Mai Luong |
7th ACM International Symposium on Information and Communication Technology |
2016 |
17 |
Fast Parallel Blur Detection of Digital Images |
Giang Son Tran, Thi Phuong Nghiem, Nhat Quang Doan, Alexis Drogoul and Chi Mai Luong |
12th IEEE-RIVF International Conference on Computing and Communication Technologies |
2016 |
18 |
Dynamic Indexing for Content-Based Image Retrieval Systems using Hierarchical and Topological Network |
Nhat Quang Doan, Thi Phuong Nghiem and Giang Son Tran |
8th IEEE International Conference on Knowledge and Systems Engineering |
2016 |
19 |
Gigwa—Genotype investigator for genome- wide analyses |
Sempéré G, Philippe F, Dereeper A, Ruiz M, Sarah G, Larmande Pierre |
Gigascience |
2016 |
20 |
Cooperative iaas resource management: Policy and simulation framework |
Giang Son Tran and Thi Phuong Nghiem |
7th IEEE International Conference on Knowledge and Systems Engineering |
2015 |
21 |
Growing Hierarchical Trees for Data Stream Clustering and Visualization |
Nhat-Quang Doan, Mohammed Ghesmoune, Hanane Azzag, and Mustapha Lebbah |
International Joint Conference on Neural Networks |
2015 |
22 |
Cooperative Resource Management in a IaaS |
Giang Son Tran, Alain Tchana, Daniel Hagimont, and Noel De Palma |
Advanced Information Networking and Applications |
2015 |
8. Research outcomes or featured results have been achieved
The following research projects are completed at ICTLab:
- SWARMS: Say and Watch: Automated image/sound Recognition for Mobile monitoring Systems
- ARCHIVES: Analysis and Reconstruction of Catastrophes in History within Interactive Virtual Environments and Simulations
- GPU4SPACE: High Performance Computing with GPU for Aerospace Science
- STIC2: Grid and High Performance Computing (Objectives Labos STIC2)
- BlurEmbeded: Blur Detection on Embedded Devices
- ICTSYS: ICT Methods and Tools in Socio-Environmenal Systems
- ParallelBlur: Parallelization of Blur Detection of Digital Images
- FLEG: Feature line extraction of 3D models using GPGPU
- RNIR: Recurrent Neural Networks on Information Retrieval
- BBC: Building a booting system for thin clients based on open source software