The-Hien Dang-Ha

The-Hien Dang-Ha

Deep learning and deep architectures are emerging as the best machine learning methods so far in many practical applications such as reducing the dimensionality of data, image classification, speech recognition or object segmentation. In fact, many leading technology companies such as Google, Microsoft or IBM are researching and using deep architectures in their systems to replace other traditional models. Therefore, improving the performance of these models could make a strong impact in the area of machine learning. However, deep learning is a very fast-growing research domain with many core methodologies and paradigms just discovered over the last few years. This thesis will first serve as a short summary of deep learning, which tries to include all of the most important ideas in this research area. Based on this knowledge, we suggested, and conducted some experiments to investigate the possibility of improving the deep learning based on automatic programming (ADATE). Although our experiments did produce good results, there are still many more possibilities that we could not try due to limited time as well as some limitations of the current ADATE version. I hope that this thesis can promote future work on this topic, especially when the next version of ADATE comes out. This thesis also includes a short analysis of the power of ADATE system, which could be useful for other researchers who want to know what it is capable of.

Anh-Vu Dinh-Duc, The-Hien Dang-Ha, Ngoc-An Lam

In a Wireless Sensor Network (WSN), data manipulation and representation is a crucial part and can take a lot of time to be developed from scratch. Although various visualization tools have been created for certain projects so far, these tools can only be used in certain scenarios, due to their hard-coded packet formats and network's properties. To speed up the development process, a visualization tool which can adapt to any kind of WSN is essentially necessary. For this purpose, a general-purpose visualization tool - NViz, which can represent and visualize data for any kind of WSN, is proposed. NViz allows users to set their network's properties and packet formats through XML files. Based on properties defined, users can choose the meaning of them and let NViz represents the data respectively. Furthermore, a better Replay mechanism, which lets researchers and developers debug their WSN easily, is also integrated in this tool. NViz is designed based on a layered architecture which allows for clear and well-defined interrelationships and interfaces between each component.

The-Hien Dang-Ha, Davide Roverso, Roland Olsson

With the emergence of cloud computing and sensor technologies, Big Data analytics for the Internet of Things (IoT) has become the main force behind many innovative solutions for our society's problems. This paper provides practical explanations for the question "why is the number of Big Data applications that succeed and have an effect on our daily life so limited, compared with all of the solutions proposed and tested in the literature?", with examples taken from Smart Grids. We argue that "noninvariants" are the most challenging issues in IoT applications, which can be easily revealed if we use the term "invariant" to replace the more common terms such as "information", "knowledge", or "insight" in any Big Data for IoT research. From our experience with developing Smart Grid applications, we produced a list of "noninvariants", which we believe to be the main causes of the gaps between Big Data in a laboratory and in practice in IoT applications. This paper also proposes Graph of Virtual Actors (GOVA) as a Big Data analytics architecture for IoT applications, which not only can solve the noninvariants issues, but can also quickly scale horizontally in terms of computation, data storage, caching requirements, and programmability of the system.

Steinar Kristoffersen, The-Hien Dang-Ha, Thien-Phuc Nguyen

This paper defines a new domain for collaborative systems and technologies research: inter-organizational lean-interactive systems engineering. It departs from the problems pertaining to large-scale, technically demanding one-off construction projects, such as in our case studies, the building of specialized offshore service vessels. The requirements are unique, as are the explicit ambitions to be "lean", in other words, avoid waste and re-engineering by making sure that the process is customer-driven and rational. Emphasis is on efficiency rather than effectiveness. This set-up poses new demands to the collaborative systems and technologies, which we in this paper have addressed with the design of a new type of Documentation-emtric ERP, which we have called "Paperstack". The ambition is to support inter-organizational lean-interactive systems engineering in an integrated platform, and the next step for our research, naturally, is to put the systems into factual use. This paper summarizes the design ideas.