Application of artificial intelligence techniques in building economic-financial forecast models on high dimensional data sets.

Forecasting in the economic-financial field plays a very important role for the direction and regulation of the government, the development and implementation of business-production strategies of enterprises, investment and consumption of people. So far, the econometric approach based on a combination of mathematics, economic theory and statistical prediction with regression techniques, remains the most popular and important one to make forecasts in the field of economics and finance.
With the increasing economic globalization and the rapid development of science and technology, each event in the field of economics – finance is affected by many other economic-financial and social factors in the country as well as abroad. The current econometric approach to build economic-financial forecasting models is not applicable to input data sets with high dimensions and it is a very big challenge for the implementation of economic-financial forecasts.
The purpose of this report is to present some approachs of application of artificial intelligence techniques in building economic-financial forecasting models on huge input data sets. Artificial intelligence techniques are very useful for dimensionality reduction of input data sets and to improve the quality of forecasting models built under the econometric approach. Some forecasting models in the economic – financial field built arcoding to the mentioned approachs on the real data sets of the economy show that the forecast accuracy by the models is not only increased but also can use these models for evaluation of the impact of economic-financial shocks as well as of many other external factors. Some new researchs by author and some open issues will also be presented and discussed in this report.

Assoc. Prof. Do Van Thanh – Nguyen Tat Thanh University (Vietnam)

Assoc. Prof. PhD. Do Van Thanh was a senior researcher, deputy director of the National Center for Socio-Economic Information and Forecasts, Ministry of Planning and Investment, and a part – time lecturer of the Information Technology Department, University of Technology, Hanoi National University. Now he is a full time lecturer, the Information Technology Department, Nguyen Tat Thanh University. He received PhD’s degree in Information Technology in 1996 from the Vietnamese Academy of Science and Technology. His research interests include Data Analysis and Data Mining, Knowledge representation and automatic reasoning, Economic – Financial Analysis and Forecast. He is the author and co-authors of more than 70 peer – reviewed publications concerning the all fields above. He has strong experience in knowledge discovery in databases and building economic-financial forecast models.

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

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

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

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)