Jump to Navigation

Mechatronics & Robotics

The Minor in Mechatronics & Robotics provides an opportunity for undergraduates at IUB to learn the principles and practice of robotics through theoretical studies and hands-on experience with robots. This minor serves as a focal point for CSE students who are interested in robotics. Students initially learn the basics of robotics, then move on to additional required courses that teach control systems and robotic manipulation. Students also choose from a wide selection of electives in robotics, perception and computer vision, cognition and cognitive science, or computer graphics. Students have a unique opportunity to undertake independent research projects, working under the guidance of faculty and research members, an excellent introduction to robotics research for those considering graduate studies.

CSE 420: Image Processing 3 credits
An introduction to the science of computer vision and image processing. Topics include: point operations, histograms, spatial operations, image rectification, interpolation, affine and other transformations, contrast enhancement, magnification, Fourier image transforms, edge and contour detection, boundary extraction and representation. Focus is mainly placed on the general principles of image processing. Other topics discussed include morphological image processing, wavelets, compression and convolution operations for the tasks of image classification, localization and detection.

Text Book:

  • Digital Image Processing (3rd Edition) Rafael C. Gonzalez, Richard E. Woods
  • Fundamentals of Digital Image Processing by A. K. Jain

CSE 421: Machine Learning 3 credits
Introduction to Machine Learning; Classification of learning: unsupervised and supervised learning, connectionist learning, reinforcement learning, machine discovery; Supervised learning: Information theoretic decision tree learner, best current hypothesis search, candidate elimination (version space) algorithm, learning in the first order Horn clause representation, inductive logic programming, applications; Unsupervised learning: hierarchical clustering, category utility, incremental and non-incremental algorithms for hierarchical clustering, applications; Connectionist learning: introduction to neural networks, Feed forward and recurrent networks, perception, multilayer feed forward networks, backpropagation algorithm for training a feed forward network, applications; Genetic algorithms: genetic operators, fitness function, genetic algorithm in supervised learning framework, applications.

Text Book:

  • Introduction to Machine Learning by Ethem Alpaydin
  • Pattern Recognition and Machine Learning by Chris Bishop
  • Machine Learning: a Probabilistic Perspective by Kevin Murphy

CSE 425: Artificial Intelligence 3 credits
Artificial Intelligence (AI) is the study of making optimal decisions given incomplete information and limited resources. This unit covers the foundational concepts and programming techniques of AI: search and problem solving methods, knowledge representation, reasoning, intelligent agents and natural language processing. Additional aspects of AI discussed include logic, uncertainty, puzzle solvers, simulative and cognitive process, expert systems and data processing.

Text Book:

  • Artificial Intelligence: A Modern Approach (3rd Edition) by Stuart Russell and Peter Norvig
  • The Elements of Statistical Learning by Hastie, Tibshirani, and Friedmanli>

CSC 426 Introduction to Robotics 3 credits
In addition to traditions rooted in mechanics and dynamics, geometrical reasoning, and artificial intelligence, the study of robot systems is growing to include many issues traditionally part of the computing sciences; distributed and adaptive control, architecture, software engineering, real-time systems, information processing and learning. In robotics, processing and its relationship to mechanical function are dependent on the target platform and the world in which it is situated. Designing an embedded computational system for sensory and motor processes requires that designers appreciate and understand all of these disciplines. This course is concerned with the design and analysis of adaptive, closed-loop physical systems. The focus will be sensory and motor systems that interpret and manipulate their environments. Toward this end, we will study mechanisms (kinematics and dynamics), actuators, sensors (with a focus on active vision), signal processing, associative memory, feedback control theory, supervised and unsupervised learning, and task planning. Interesting examples of integrated sensory, motor, and computational systems can be found in nature, so occasionally we will relate the subject matter to biological systems. Students will experiment with system identification and control, image processing, path planning, and learning on simulated platforms to reinforce the material presented in class. (Prerequisite: CSC 305, MAT 212, MAT 203)

Text Book:

  • Introduction to AI Robotics, by Robin Murphy, MIT Press.
  • The Robotics Primer by Maja J. Mataric, MIT Press.
  • Introduction to Robotics: Mechanics and Control by John J. Craig

CSE 441: Instrumentation and Measurements 3 credits
Single phase transformers; Principles of operation of DC, Induction and Stepper motors; Thyristor and microprocessor based speed control of motors. Introduction to amplifiers; Basic differential amplifiers; logarithmic amplifiers; Temperature compensation of Logarithmic amplifiers; Antilog amplifier; Chopper stabilized amplifier. Frequency and voltage measurements using digital techniques: Digital frequency meter, digital voltmeter. Recorders and display devices: Oscilloscope, Spectrum analyzers and logic analyzers. Data acquisition system and interfacing to microprocessor based systems. Transducers: terminology, types, principles and application of piezoelectric, photovoltaic, thermoelectric, variable reactance and opto-electronic transducers. Noise reduction in instrumentation.

Text Book:

  • Modern Electronic Instrumentation and Measurement Techniques by Albert D. Helfrick and William David Cooper

Big Data & Information Retrieval

Big data is a broad term for data sets so large or complex that traditional data processing applications are inadequate. Data sets grow in size in part because they are increasingly being gathered by cheap and numerous information-sensing mobile devices, and computer and sensor networks. Traditional database management systems and desktop statistics and visualization packages often have difficulty in handling big data.
The Minor in Big Data & Information Retrieval will train students in the analysis, capture, curation, search, sharing, storage, transfer, modeling and visualization of the Big Data. This includes the design of efficient and effective algorithms and systems to integrate the data and uncover large hidden values from datasets that are diverse, complex, and of a massive scale. This massive increase in data and information has created a high demand for skilled Big Data experts in all industries.

CSC 416 Distributed Database Systems 3 credits
A detailed study of advanced topics related to relational database theory, query processing and optimisation, recovery techniques, concurrency control. Crash recovery. Distributed database systems: security and integrity. Other database paradigms such as deductive and object oriented issues. Heterogeneous databases. (Prerequisite: CSC 306, CSC 401)

Text Book:

  • Principles of Distributed Database Systems by M. Tamer Özsu and Patrick Valduriez
  • Distributed Database Management Systems: A Practical Approach by Saeed K. Rahimi and Frank S. Haug
  • Distributed Systems: Principles and Paradigms (2nd Edition) by Andrew S. Tanenbaum and Maarten Van Steen

CSC 417 Data Mining and Warehouse 3 credits
Basic concept of data mining, issues and techniques. Data warehouse and OLTP technologies for data mining, Classification of data mining techniques and models, data pre-processing, data mining primitives, query languages and system architecture, characterization and comparison. Mining association rules in large database. Cluster analysis, multidimensional analysis and descriptive mining of complex data object. Data mining in distributed heterogeneous database systems. Data mining applications and future research issues. (Prerequisite: CSC 306, CSC 401)

Text Book:

  • Data Mining: Concepts and Techniques, Third Edition by Jiawei Han, Micheline Kamber and Jian Pei
  • Data Mining: Practical Machine Learning Tools and Techniques, Third Edition by Ian H. Witten, Eibe Frank and Mark A. Hall
  • Introduction to Data Mining by Pang-Ning Tan, Michael Steinbach and Vipin Kumar

CSC 470 Introduction to Parallel Computing 3 credits
Parallel architectures; linear, mesh, binary, and hypercube connections; routing mechanisms; communication models; scalability and efficiency; Principles of parallel algorithm design: Design approaches, design issues, performance measurement & analysis, complexities, anomalies in parallel algorithms; parallel searching, parallel sorting, parallel graph and parallel computational algorithms; parallel programming paradigms: message passing, shared memory and multi-core parallel programming.

Text Book:

  • Parallel Programming with Microsoft® .NET: Design Patterns for Decomposition and Coordination on Multicore Architectures by Colin Campbell, Ralph Johnson, Ade Miller and Stephen Toub
  • The Art of Multiprocessor Programming by Maurice Herlihy and Nir Shavitli>
  • Programming Massively Parallel Processors: A Hands-on Approach (2nd Edition) by David B. Kirk and Wen-mei W. Hwu
  • An Introduction to Parallel Programming by Peter Pacheco
  • Parallel and Concurrent Programming in Haskell: Techniques for Multicore and Multithreaded Programming by Simon Marlow

CSE 471 Introduction to High Performance Computing 3 credits
Basic principles and techniques in the design of high performance computer architecture. Memory architecture: cache structure and design, virtual memory structures. Pipelined processor architecture. Pipeline control and hazard resolution, pipelined memory structures, interrupt, evaluation techniques; vector processing, RISC and CISC architecture. VLSI architecture issues.

CSC 472 Cloud Computing 3 credits