Essential Computer Science for Global LeadersUm19S1011n
|Essential Computer Science for Global LeadersUm19S1011n
Essential Computer Science for Global LeadersU
||BASHAR Md Khayrul
|Theory and practice; discussion and explanation using board and PPT slides
|1. Computer Vision: Algorithm and Applications – Richard Szeliski
2. S. Haykin, Neural Networks: A comprehensive Foundation, MacMillan College Publishing Co. New York, 1994
3. C++ How to Program by Paul Deitel and Harvey Deitel
4. Arduino Sketches: Tools and Techniques for programming Wizardry – James A. Langbridge
6. Signal Processing for Neuroscientists – Wim van Drongelen
7 .Rajkumar Buyya: Internet of Things -- Principles and Paradigm, Morgan Kaufmann, Elsevier, USA, 2016.
8. Lecture materials will also be supplied whenever needed
|»ΜΌ=Tests (40%), Attendance (30%), Assignment (30%)
|Steady increase of the deployment of computer systems in many real world applications made computer science and engineering an inevitable discipline in the current epoch of human history. Along with electronics, it drives the information revolution following industrial and agricultural revolutions. Future progress and the ultimate shape of this planet will largely depend on how the next generation global leaders are going to be equipped with essential knowledge on computer science and engineering. In this course, light will be shed on some advanced topics involving information security, artificial intelligence, the design and control of electronic devices for some real world applications.
|(a) Data Explorations (Four (4) classes)
• Introduction to data science, data types, typical data analysis methods.
• Feature extraction from image data (Local Binary Pattern (LBP), Histogram of Oriented Gradient (HOG), Scale Invariant Feature Transform (SIFT) and other transforms (Fourier transform, wavelet transform etc.)
• Feature selection and related algorithms
• Practice sessions on data analysis (C++/Matlab/Python/R)
(b) Machine learning and applications (Six (6) classes)
• Introduction, Some machine learning algorithms: minimum distance to mean, k- Nearest Neighbor, Maximum Likelihood and Naive Bayes, linear discriminant analysis (LDA), Decision Tree, Support Vector Machine (SVM)).
• Basics of artificial neural network (ANN) ; Some neural network algorithms (single and multilayer perceptron (MLP), deep learning).
• Practice sessions on machine learning algorithms.
• Assignment / Test
(c) Internet-Of-Things (IoT) (Five (5) classes)
• Introduction, Brief history of IoT, How it works ?;
• Structure of IoT; Current status and future prospect;
• Examples of IoT (fruit quality detection; human face tracking using webcam; car detection and traffic analysis)
• Final test/report
NB: Contents may be revised or modified subject to necessity.
|Having general idea before each lecture may be useful.
|Lecture will be delivered in both Japanese and English. Simple English will be used. Inquiries can be sent to Md. Khayrul Bashar at
Email : firstname.lastname@example.org;
Tel : 03-5978-2557 ;
Office : Science Building – 3 (Room : in front of Elevator Door at 3rd Floor)
N.B. Contents or the extent of the topics may be refined subject to necessity