Publications
● GIAT: a machine learning for identification automatic of gemstones
○ Researcher at South Can Tho University (SCTU) ○ en.nctu.edu.vn
○ Collaboration with Hanoi University of Mining and Geology (HUMG) ○ humg.edu.vn
○ Collaboration with Liulab Gemological Center (LGC) ○ liulab.edu.vn
○ Reference: Le Ngoc Nang {lengocnang@liulab.edu.vn}; Assoc.Prof. Giang Khac Nguyen {nguyenkhacgiang@humg.edu.vn};
● Description:
Currently, gemstone sorting and verification are mostly handled through manual and time-consuming techniques. By utilizing artificial intelligence techniques, the project hopes to create simple tools, called GIAT (Gems Identification Automatic Tools) to serve the complex tasks of gemstone appraisal and grading. Because the gem data sources cannot be collected at the same time in a short time, but mainly through gem inspection orders. Gemstone groups and their sub-sectors are not determined from the beginning but through data from orders appearing over time, which accumulate gradually. Therefore, the project requires an intelligent system that can be integrated in real time.
○ Keywords:
machine learning, dynamic classification, streaming data, one-class, SVM; human-computer interaction, gemstone classification, machine learning application.
● Publications:
soon available ...
● A3M: a machine learning for identification automatic of antique glass artifacts
○ Researcher at UNESCO Centre for Research and Preservation for the Vietnamese Antiquity (UNESCO-VNA) ○ unesco-vna.org (in updating periode)
○ Collaboration with Hanoi University of Mining and Geology (HUMG) ○ humg.edu.vn
○ Collaboration with Quang Ngai Museum (QNM) ○ baotangquangngai.com
○ Reference: Assoc.Prof. Hoang Bac Bui {buihoangbac@humg.edu.vn}; Dr. Doan Ngoc Khoi {dnkhoi-svhtt@quangngai.gov.vn}
● Description:
Ancient glassware was found widely in Vietnam (Dong Son, Sa Huynh, Oc Eo) through the ancient and complicated trading process today. From the perspective of the researcher in the field of private collections, in the particular case of Sa Huynh culture, the jewelry of other cultures (Dong Son, Oc Eo) often causes complication in classification. In this project, we try to go into the direction of analyzing the surface composition structure of Sa Huynh glass jewelry, thereby providing an analysis of the unique identification characteristics of Sa glass jewelry. Through artificial intelligence techniques, we offer standards tools (so-called A3M or Antique Artifacts Automatic Identification Machine) to compare the distinguishing characteristics between Sa Huynh glassware and current glass jewelry (antique imitation glass, new glass ... ) and glassware of different cultures from the perspective of gemology and mineralogy.
○ Keywords:
machine learning, streaming data, antique glass classification, antique glass identification, sa huynh - oc eo - dong son glass characteristics.
● Publications:
Anh Khoi Ngo Ho, Van Phuc Vo, Trong Co Nguyen, Ngoc Khoi Doan, Hoang Bac Bui, Thi Thuy Tran, AI System for Application of Oc Eo glass identification, Conference of Oc Eo (Ba The - Nen Chua) Archeological System, accepted.
Anh Khoi Ngo Ho, Hoang Bac Bui, Giang Nguyen Khac, The Luc Trinh, Ancient glass stone in history, Journal of Developmental Philosophy, accepted.
Anh Khoi Ngo Ho, Trong Co Nguyen, Ngoc Khoi Doan, Hoang Bac Bui, The Luc Trinh, Distinct gemological properties of Sa Huynh glass ornaments, International Workshop On Heritage Values Of Ly Son - Sa Huynh Geopark, Quang Ngai, Vietnam, 2019.
● mOC-iSVM: a multi-purpose dynamic learning and classification
○ Project website: mOC-iSVM.com
○ Researcher at Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS) ○ liris.cnrs.fr
○ Collaboration with Computer Science Laboratory (LI 6300) ○ li.univ-tours.fr
○ References: Prof. Veronique Eglin {veronique.eglin@insa-lyon.fr}
● Description:
This research contributes to the field of dynamic learning and classification in case of stationary and non-stationary environments to deal with very small learning dataset at the beginning of the process and with abilities to adjust itself according to the variability of the incoming data inside a stream. For that purpose, we propose a solution based on a combination of independent one-class SVM classifiers having each one their own incremental learning procedure. Consequently, each classifier is not sensitive to crossed influences which can emanate from the configuration of the models of the other classifiers. The originality of our proposal comes from the use of the former knowledge kept in the SVM models (represented by all the found support vectors) and its combination with the new data coming incrementally from the stream. The proposed classification model (mOC-iSVM) is exploited through three variations in the way of using the existing models at each step of time. The mOC-iSVM.AP model selects the previous support vectors according to their « age »; the mOC-iSVM.EP model selects the support vectors according to their efficiency, and the mOC-iSVM.nB selects vectors from the n-best models in the history. Our contribution states in a state of the art where no solution is proposed today to handle at the same time, the concept drift, the addition or the deletion of concepts, the fusion or division of concepts while offering a privileged solution for interaction with the user. The experiments, at the same time on stationary and non-stationary environments, provide very good classification scores close or even better than those obtained with the most successful incremental classifiers at this moment. Furthermore, in contrary to our method, most of the other dynamic approaches are applicable only to particular environments.
○ Keywords:
machine learning, intelligent scanner, dynamic classification, streaming data, one-class, SVM; human-computer interaction.
● Publications:
Anh Khoi Ngo Ho, Nicolas Ragot, Jean-Yves Ramel, Veronique Eglin, Multi one-class incremental SVM with n-Best, Journal of Machine Learning, In progress.
Anh Khoi Ngo Ho, Nicolas Ragot, Jean-Yves Ramel, Veronique Eglin, A multi-purpose dynamic classifier: application to document classification, International Journal on Document Analysis and Recognition, 2017.
Anh Khoi Ngo Ho, Nicolas Ragot, Jean-Yves Ramel, Veronique Eglin, Multi one-class incremental SVM for document stream digitization, 12th IAPR International Workshop on Document Analysis Systems, Satorini, Greece, 2016.
● DigiDoc: an intelligent scanner of old documents
○ Project website: digidoc.labri.fr
○ Researcher at Computer Science Laboratory ○ li.univ-tours.fr
○ Collaboration with Laboratoire d'InfoRmatique en Image et Systèmes d'information (LIRIS) ○ liris.cnrs.fr
○ Collaboration with Laboratoire Bordelais de Recherche en Informatique (LaBRI) ○ labri.fr
○ Collaboration with Bibliotheque National de la France (BNF) ○ bnf.org
○ Collaboration with Arkhenum ○ arkhenum.fr
○ References: Prof. Jean-Yves Ramel {jean-yves.ramel@univ-tours.fr}; Prof. Nicolas Ragot {nicolas.ragot@univ-tours.fr}
● Description:
Inside the DigiDoc project (ANR-10-CORD-0020) - CONTenus et INTeractions (CONTINT), our research was applied to several scenarios of classification of image streams which can correspond to real cases in digitization projects. Most of the time, the processing of documents is considered as a well-defined task: the classes (also called concepts) are defined and known before the processing starts. But in real industrial workflows of document processes, it may frequently happen that the concepts can change during the time. In a context of document stream processing, the information and content included in the digitized pages can evolve over the time as well as the judgment of the user on what he wants to do with the resulting classification. The goal of this application is to create a module of learning, for a steam-based massive document images classification (specially dedicated to a massive digitization process), that adapts different situations for intelligent scanning tasks: adding, extending, contracting, splitting, or merging the classes in on an online mode of streaming data processing.
○ Keywords:
dynamic classification, incremental learning, one-class SVM, stationary and non-stationary environments, document image classification, digitization.
● Publications:
Anh Khoi Ngo Ho, Méthodes de classifications dynamiques et incrémentales : application à la numérisation cognitive d'images de documents, Doctoral dissertation, Ecole doctorale Mathématiques, Informatique, Physique Théorique et Ingénierie des Systèmes (Centre-Val de Loire), Tours, 2015.
Anh Khoi Ngo Ho, Nicolas Ragot, Jean-Yves Ramel, Veronique Eglin, Multi one-class incremental SVM for both stationary and non-stationary environment, CAp 2014, 16th Conférence Francophone sur l'Apprentissage Automatique, Saint-Etienne, France, 2014.
Anh Khoi Ngo Ho, Nicolas Ragot, Jean-Yves Ramel, Veronique Eglin, Nicolas Sidere, Document classification in a non-stationary environment: a one class SVM approach, ICDAR 2013, 12th International Conference on Document Analysis and Recognition, Washington DC, USA, 2013.