AI in 5G networks

AI in 5G networks

The telecommunications industry have pursued efforts to realize the idea of 5G networks. Besides increasing speeds and more efficient utilization of spectrum, a main goal is to establish the foundation and the common framework of new innovative network services.
5G operators may create new revenue streams from hosting 3rd party applications in their infrastructure in addition to the provisioning of their own services.
To achieve the aims of 5G, the development of scalable self-managed software and cloud platforms that supports the rapid deployment of services are needed. European Telecommunications Standards Institute (ETSI) has specified the Network Functions Virtualisation concept where Network Services are constructed by an appropriate chaining of
Network Functions (either physical network functions or virtualized network functions — VNF). The NFV initiative transformed the way telecom network operators architect their networks. It embraced virtualization techniques widely used in the IT industry and introduced the Infrastructure-as-a-Service cloud computing model into the Telco world.Some use cases of 5G applications have strict requirements (i.e., high availability and low latency for VR, AR, V2X, etc.) that can be achieved by the careful engineering, the new operating rules of cloud platforms and the optimal placement of application components. In the talk, the application possibilities of AI will be outlined for the efficient operation and management of 5G networks.

Prof. Do Van Tien – Budapest University Of Technology And Economics (Hungary)

Tien Van Do received the M.Sc. and Ph.D. degrees in telecommunications engineering from the Technical University of Budapest, Hungary, in 1991 and 1996, respectively. He is a professor in the Department of Telecommunications of the Budapest University of Technology and Economics, and a leader of Communications Network Technology and Internetworking Laboratory. He habilitated at BME, and received the DSc from the Hungarian Academy of Sciences in 2011. He has participated and lead work packages in the COPERNICUS-ATMIN 1463, the FP4 ACTS AC310 ELISA, FP5 HELINET, FP6 CAPANINA projects funded by EC (where he acted as a work package leader). He led various projects on network planning and software implementations that results are directly used for industry such ATM & IP network planning software for Hungarian Telekom, GGSN tester for Nokia, performance testing program for the performance testing of the NOKIA’s IMS product, automatic software testing framework for Nokia Siemens Networks. His research interests are queuing theory, telecommunication networks, cloud computing, performance evaluation and planning of ICT Systems. He is also a board member of Discrete Dynamics in Nature and Society, Hindawi.

General Game Playing: a Challenge for AI

General Game Playing: a Challenge for AI

Games represent an exciting challenge for Artificial Intelligence. The ability of computers to confront human beings in a convincing manner, or even to defeat them, fascinate most people. Besides, games are a good framework to test algorithms developed for more general problems. Thus games are a good area to test out AI techniques and to develop new approaches. Recently, stronger results were provided and, for many games, computer skills are far away from human abilities.
We focus in this talk on the challenge of General Game Playing. The topic of General Game Playing (GGP) is to develop artificial agents able to play any game, without human intervention. The rules of each game are described in a declarative representation language, called Game Description Language (GDL). These rules are given to the agent only a few minutes before playing, which makes it difficult to apply current techniques. We discuss in this talk the difficulty of this challenge, some recent results and some possible applications in real life.

Assoc. Prof. Sylvain Lagrue – University of Artois (France)

LAGRUE Sylvain is an Associate Professor of Computer Science at Université d’Artois/CRIL CNRS UMR 8188 (France). His research includes Artificial Intelligence, Knowledge Representation, Uncertainty in AI and Games. He is currently invited at the VNU in the framework of the EU Project Aniage.

Answer set programming and its Applications

Answer set programming and its Applications

ASP is an emerging declarative programming paradigm. It has been used in several practical applications. This talk will present the basic idea of ASP and demonstrates its use in several applications such as distributed constraints optimization problems, reasoning about truthfulness of agents’ statements, smart home scheduling etc.

Prof. Tran Cao Son – New Mexico State University (USA)

Tran Cao Son received his doctoral degree from the University of Texas at El Paso in 2000. He is currently a Computer Science Professor at the New Mexico State University in Las Cruces. Before joining NMSU, he was a post-doc at the Knowledge System Laboratory at Stanford University for almost a year. His main research interests are in knowledge representation and reasoning, especially logic programming and answer set programming and its applications in planning, negotiation, and multi-agent systems.

Developing Intelligent Systems based on Internet of Things: Some preliminary results

Developing Intelligent Systems based on Internet of Things: Some preliminary results

Recently, there has been a great interest to develop intelligent systems based on Internet of Things (IoT), which connects physical objects like sensors nodes to collect real time data accessible through the Internet. Nowadays, in simple terminology, IoT includes almost things such as cell phones, building maintenance services, jet engine of an airplane. It also aids clinicians in diagnosis of heart monitor implant or farmers in a biochip transponder in farm animals. The IoT-connected devices transfer data over a network and are the component members of IoT. In this talk, we would like to summarize our preliminary recent achievements in developing intelligent systems based on IoT typically smart city, electricity generation system, and air pollution minimization: A smart city utilizes the information and communication technology to make efficient consumption of limited resources like space, mobility, energy, etc. This research focuses on developing an effective system for impairments monitoring, traffic monitoring, and smart city innovation with digitalized software for fast and effective implementations; Electrical energy generation from multiple sensors for household appliances and industrial areas is conducted. Electricity from the renewable energy sources such as stress generated by the body weight, heat generated by human body, and movements of the body can be measured by different sensors and transferred to the control system for storing; Air pollution minimization is performed using IoT. Various sensors have been used such as temperature sensor, humidity sensor, smoke sensor and many others to collect data from dust and environment. This model allows finding vehicles which releases more carbon dioxide to reduce the pollution.

Assoc. Prof. Le Hoang Son – VNU University of Science (Vietnam)

Le Hoang Son obtained the PhD degree on Mathematics – Informatics at VNU University of Science, Vietnam National University (VNU). He has been promoted to Associate Professor in Information Technology since 2017. Currently, Dr. Son works as a researcher and Vice Director at the Center for High Performance Computing, VNU University of Science, Vietnam National University. His major field includes Artificial Intelligence, Data Mining, Soft Computing, Fuzzy Computing, Fuzzy Recommender Systems, and Geographic Information System. He is a member of International Association of Computer Science and Information Technology (IACSIT), Center for Applied Research in e-Health (eCARE), Vietnam Society for Applications of Mathematics (Vietsam). Dr. Son serves as Editorial Board of International Journal of Ambient Computing and Intelligence (IJACI, SCOPUS), Editorial Board of Vietnam Journal of Computer Science and Cybernetics (JCC), Associate Editor of International Journal of Engineering and Technology (IJET), Associate Editor of Neutrosophic Sets and Systems (NSS), and Associate Editor of Vietnam Research and Development on Information and Communication Technology (RD-ICT).

An application of Deep learning in smart city traffic management

An application of Deep learning in smart city traffic management

The report is on an effort to build smart traffic network management based on video surveillance and traffic light centralized in Vietnamese cities. A presentation of smart transportation management infrastructure with integration of network IP cameras, video analytic application running on high performance computing systems, automatic traffic data recognition, automatic calculation of traffic light control strategy for maximal flows in main city corridors. For extracting traffic flow data to input in optimization modelling system, an attempt to deploy deep learning/ tensorflow on specific hardware and software infrastructure: results and challenges.

Assoc. Prof. Pham Hong Quang – Vietnam Academy of Science and Technology (Vietnam)

Pham Hong Quang graduated from the Faculty of Applied Mathematics in Russian (1983), got Ph.D degree (1987) in Game Theory. From 2010 he is Director of Center for Informatics and Computing – Vietnam Academy of Science and Technology. His research interests are optimization control, high performance computing, signal processing and embedded computing… He has deep experiences in designing and realization of ICT infrastructure for Intelligent Transportation System, Smart Traffic Management for urban and highway network.

Applied machine learning for decision making in real-life problems

Applied machine learning for decision making in real-life problems

Machine learning has been a big shot in the last few years. In this talk I just want to highlight two examples (spam and fraud detections) where we can use machine learning to solve the decision making in real-life problems.
The first one is how to use machine learning to detect spam traffics from huge data set (e.g., 1M records/second). The data size, however, is not only the main challenge but also the ambitious spam definition as well as quality of training data (if you can collect). The second one is focus on a challenge where your training data is not only low quality but also extremely unbalanced.

Dr. Le Sy Quang – Google (UK)

Quang Sy Le got Ph.D degree from Japan Advanced Institute of Science and Technology (JAIST, Japan). He has more than ten years working in different academia projects including e.g., Molecular Evolution, 1000 Genome Projects. He is now moving to Google (England) to work on machine learning projects for large data sets.

How to Make Chatbots Smarter: Computational Semantics Beyond Events and Roles

How to Make Chatbots Smarter: Computational Semantics Beyond Events and Roles

Current chatbot systems have mostly used a swallow semantic representation of text, which have focused on extracting propositional meaning, capturing “who does what to whom, how, when and where”. These chatbots tend to disregard significant meaning encoded in human language. For this reason, it is difficult for them to understand utterances such as “What is the tallest mountain in Vietnam?” or “What is the largest prime less than 2018?”. In this talk, I show that a deep understanding and reasoning of natural language is required in order for a chatbot to better understand an input utterance and produce an appropriate action. This goal can be achieved by semantic parsing, an area within the field of natural language processing. Chatbots can be made more intelligent only by computer scientists with a deep knowledge of computational semantics.

Dr. Le Hong Phuong – Vietnam National University (Vietnam)

Le Hong Phuong received his PhD in computer science at Université de Lorraine, France in 2010; master of information technology at Institut de la Francophonie pour l’Informatique (IFI) in 2005; bachelor of science in applied mathematics-informatics at Hanoi University of Science in 2002. He was a researcher and assistant professor at Ecole des Mines de Nancy and INRIA Lorraine, France from 2010 to 2011. He is currently the head of the Data Science Laboratory at Hanoi University of Science, Vietnam National University. He has been also an associate researcher at FPT Research & Development, FPT Corporation since 2013; a scientific counselor for several AI companies. He has been working in the fields of natural language processing and applied mathematics for nearly 20 years. He has published over 40 scientific papers and has been in programme committees of many national and international scientific conferences. He is the author of some softwares toolkits which are widely used in the Vietnamese text processing community. His website is at http://mim.hus.vnu.edu.vn/phuonglh/

Virtual and Augmented Reality: Applications and Issues in a Smart City context

Virtual and Augmented Reality: Applications and Issues in a Smart City context

Virtual and Augmented Reality has the potential revolutionise how we play, work and learn. In this talk we will consider the fundamentals of Virtual and Augmented Reality technologies including how these technologies can be applied to education, entertainment and data visualisation applications associated with the Smart Cities paradigm. There is a great potential to make use of Virtual and Augmented Reality technologies to enable Smart City applications, however we must solve a number of problems first. Solving these problems will require both an understanding of the data to be visualised and the physiology and psychology of the human user. We cannot afford to ignore either and so in this talk I will touch on the human aspects of Virtual and Augmented applications to Smart Cities and show how an understanding of human perception is crucial to building effective solutions to these problems.

Assoc. Prof. Perry Stuart – University of Technology Sydney (Australia)

Stuart Perry received the B.S. degree (first-class honors) in electrical engineering and the Ph.D. degree from the University of Sydney, Sydney, Australia, in 1995 and 1999, respectively. He has previously worked for the Commonwealth Science and Industrial Research Organisation, Australia (CSIRO), Australia, Defence Science and Technology Organization (DSTO), Australia and Canon Information Systems Research Australia (CiSRA). He is currently an Associate Professor at University of Technology Sydney in FEIT’s Perceptual Imaging Laboratory (PILab) conducting research into colour and perceptual quality in 3D environments. His research interests include virtual and augmented reality, image processing, and perceptual quality.

Deep Learning for Natural Language Processing and Beyond

Deep Learning for Natural Language Processing and Beyond

The Tutorial begins with the basic of feed-forward neural network and relevant fundamental knowledge for deep learning. We then introduce more specialized neural network models, including Convolutional Neural Network, Recurrent Neural Network, and attention-based models. In the second part, we will present how these models and techniques can be applied to some interesting problems of natural language processing including sentiment classification, textual entailment recognition, natural language generation, and question answering. The last part of the tutorial will show how we can adapt deep learning and natural language processing techniques for program analysis.

Assoc. Prof. Nguyen Le Minh – Japan Advanced Institute for Science and Technology (Japan)

Minh Le Nguyen is currently an Associate Professor of School of Information Science, JAIST. He leads the lab on Machine Learning and Natural language Understanding at JAIST. He received his B.Sc. degree in information technology from Hanoi University of Science, and M.Sc. degree in information technology from Vietnam National University, Hanoi in 1998 and 2001, respectively. He received his Ph.D. degree in Information Science from School of Information Science, Japan Advanced Institute of Science and Technology (JAIST) in 2004. He was an assistant professor at School of information science, JAIST from 2008-2013. His research interests include machine learning, natural language understanding, question answering, text summarization, machine translation, big data mining, and Deep Learning.