Department of Artificial Intelligence (Interdisciplinary program)
- Engineering Division, Graduate School of INU
- Doctorate Programs
Goals
To train highly qualified AI professionals with knowledge and skills necessary for the era of AI, the core of the Fourth Industrial Revolution.
Faculty
| Name | Position | Academic Area | |
|---|---|---|---|
| Kang, Seokhoon | Professor | Embedded S/W and platform | hana@inu.ac.kr |
| Jun, Kyunkoo | Professor | Embedded software | kjun@inu.ac.kr |
| Choi, Byoungjo | Professor | OFDM, MC-CDMA | bjc97r@inu.ac.kr |
| Lee, Youngsup | Professor | Embedded Control | ysl@inu.ac.kr |
| Hwang, Kwangil | Professor | Embedded networked system | hkwangil@inu.ac.kr |
| Jeon, Gwanggil | Professor | Image processing | gjeon@inu.ac.kr |
| Kang, Woochul | Professor | Real-Time Software | wchkang@inu.ac.kr |
| Kim Hyunbum | Professor | Internet of Things, Smart and Intelligent Systems, Algorithms | hyunbumkim@inu.ac.kr |
| Kang, ChangMook | Professor | Systems control, Advanced control Linear/nonlinear control, Machine learning Autonomous vehicle. Unmanned systems | mook@inu.ac.kr |
Principles
- Credit Requirements for completion : 36 credits. • Applications for classes are guided by an advisor and can be taken for all subjects provided by the Department of Artificial Intelligence.
- In principle, the department's operating rules should follow graduate school regulations.
Course
| Course | Course Overview |
|---|---|
| Next Generation System Design Methodology | This course studies next generation system design, analysis and related technologies and system components for applications. Also, the recent trends and issues, applicable areas, research papers, research problems, methodology for next generation system are introduced. |
| Data service platform | Students learn engineering theories and methodologies related to platform design and implementation for the purpose of systematizing and sharing or distributing collected and stored information. Theyalsolearnthelatesttechnologiesinnetworkingprotocols,cloud,front-endandback-endtechnologies,databaseandplatformimplementation. |
| Data pattern recognition | Students learn engineering methodology to find specific patterns in various linear and non-linear data such as pictures, sound sources, texts, etc. Also, they learn techniques such as image classification and recognition through the application of pattern recognition. |
| Advanced Communication Systems | Looking at the overall architecture of communication systems, the core compoents are identified and the corresponding techniques are investigated. A special emphasis is on OFDM and MIMO technology. The applciation of AI in communication systems is also explored. |
| Mobile Communication Systems | The recent advancement in mobile communication systems is introduced. Based on the current mobile communication standard, the PHY layer, the MAC layer and the RLC layer are investigated in detail. The latest technologoes applied in mobiles, basestations and core networks are also presented. |
| Robot Software | In this course, student will understand the overall eco system of robot software (especially ROS: Robot Operating System). Based on basic ROS Programming Framework, various algorithm analysis related to autonomous robot driving, and practical code analysis and practice, students acquire theoretical and practical knowledge and skills of robot autonomous driving. |
| Time Series Data Analysis | In this course, students learn how to understand time-changing data (time series data) used in various fields and predict future data through visualization and data analysis. This course includes various techniques for time series data transformation and evaluation of various predictive models. Students will also learn how to interpret the results of the traditional ARIMA model. |
| Algorithmic System Design | This course provides advanced techniques and methods for algorithmic system design and analysis. The essential algorithm schemes, graph modelling, various problems in regard to NP and approximation are introduced. Moreover, the problem formulation and design scheme using ILP for applicable embedded system are presented. |
| Advanced Network Systems | This course deals with network system technology, environment and recent advanced topics. Current internetworking protocols, P2P system construction are studied as well as wireless network system and emerging IoT-based embedded system application environment are analyzed. Also, the design of applicable systems including smart city and ocean-driven system is covered. |
| Embedded Deep Learning | Deep learning is providing intelligent services for many embedded systems such as autonomous vehicles, smartphones, and smart watches. However, embedded systems have limited computing resource, and, hence various optimization techniques are required to meet their resource constraints. In this class, we introduce both basic theory of deep learning and more advanced recent techniques for embedded deep learning. The class combines theory, practice, and presentation of the latest papers. |
| Data Programming | Students learn through programming practice to have the ability to analyze real-world data using machine learning techniques including deep learning. |
| Machine to Machine Communications(M2M) | Communication users are being shifted from only human to objects. Therefore, in this course, the basic concept of Machine to Machine communication is introduced, and the latest standards and researches are investigated. In particular, this course will provide useful knowledge and information with respect to various next generation internet protocols including 6LowPAN based on IPv6. |
| Embedded Networks | This course investigates wireless and wired embedded communication technologies. In particular, we are going to study about the basic concept and detailed specifications about not only popular wired communication technologies including UART, SPI, TWI, I2C, CAN, LAN, but also WPAN, WLAN, WRAN. Therefore, this course may provide a big contribution to design a network-based embedded system. |
| Embedded Video Coding Systems | Video coding technique has become an important part of modern computer technology. In this course, students will be introduced to principles and current technologies of video processing. Issues in effectively representing, processing, motion estimation and compensation, motion search, deinterlacing and demosaicking, and video format conversion algorithms will be introduced. The students will gain hands-on experience in those areas by implementing some components of a video coding system as their term project. |
| Parallel Processing | Parallel processing technology has been actively used in supercomputing domain. Recently, parallel processing technology is also being employed in desktops and embedded systems. This is because many modern embedded systems, such as autonomous vehicles, require massive computing power to process massive data in real-time. In particular, GPU and heterogeneous processors in modern embedded systems enable effective and energy-efficient parallel programming. In this course, we study the architecture of modern parallel processors, and we also does hands-on programming using state-of-art parallel programming tools and languages. |
| Real-Time Systems | Real-time embedded systems are everywhere, e.g., cell phones, PDA's, automobiles, medical systems, and aircraft, in these days, playing key roles in everyday life. This class will cover important issues regarding fundamental concepts of real-time embedded computing including (1) real-time scheduling, (2) Feedback Ctonrol of Software Systems (3) real-time databases. |
| Embedded Multimedia System | Multimedia has become an indispensable part of modern computer technology. In this course, students will be introduced to principles and current technologies of multimedia systems. Issues in effectively representing, processing, and retrieving multimedia data such as sound and music, graphics, image and video will be addressed. |
| Embedded Image Processing System | To introduce the student to various image processing techniques for embedded systems. The objectives are, (1) to study the image fundamentals and mathematical transforms necessary for image processing, (2) to study the image enhancement techniques, (3) to study image restoration procedures, (4) to study the image compression procedures, and (5) to study the image segmentation and representation techniques. |
| Embedded Computer Vision | Understanding various video signal processing algorithms used in embedded systems and the methodology for designing video systems. In particular, it covers the study of 3D video systems and discusses implementation methods based on parallel processing processors. |
| Topics of Embedded Systems | Analyzes the trends in the latest embedded systems and lectures on emerging technologies. |
| Advanced Artificial Intelligence | This course probes into artificial intelligence, focusing on heuristic search, and knowledge representation. It also covers intelligent agents, and neural networks. Selected papers on current topics in artificial intelligence are discussed. |
| Machine Learning | This course provides practical introduction to machine learning. Modules include regression, classification, clustering, retrieval, recommender systems, and deep learning, with a focus on an intuitive understanding grounded in real-world applications. Selected papers on current topics in artificial intelligence are discussed. |
| Thesis Research | This graduate-level course is designed for students preparing their thesis. Students will decide on a topic and conduct research for their topic under the guidance of a faculty member. |