March 18, 2022
March 18, 2022
April 4, 2022
This paper discusses the integration of broad background knowledge into an introductory course on applied artificial intelligence. The engineering programs at universities across the world must adapt to the rapidly changing engineering technology and the needs of the global workforce. The engineering students who enroll at these universities expect to be educated and trained with the latest industry-approved tools in order to function effectively in the engineering industry. In recent years, artificial intelligence (AI), machine learning, and deep learning have burgeoned to successfully reduce or eliminate human interaction while yet processing large amounts of data. AI offers computational tools that replace the need for humans to perform certain repetitive tasks. The industries which already use AI include health care, retail, manufacturing, and banking.
The broad description of the introductory course in applied artificial intelligence is to design physical systems requiring a background in digital signal and image processing, artificial neural network architectures, and specific programming skills in C/C++/Python. The students will have individual and team responsibilities as they function on project teams tackling real-world applications of AI. In addition, possessing the knowledge and skills to design and implement models in the framework of the internet of things is highly valued from the standpoint of assembling a physical system or a product which integrates the functional aspects of traditional subjects with modern tools to deliver tangible outcomes in the real world.
The paper will list the measurable outcomes of the course, the outline of course activities, and the course assessment methods. The course is taught over fourteen weeks with a total of twenty eight class sessions, each of duration eighty minutes. First, the student hones his/her skills in Python with exercises designed to yield results based on the application of the concepts related to image processing and image understanding. The student learns to apply stages of convolution and pooling operations to filter image frames and extract feature maps. Thereafter, the student learns how to design and train the neural network for the targeted application such as object detection and/or recognition and/or classification.
The course also prepares the student to participate on the integrated project platform for co-curricular and research project activities. The integrated platform was designed to test and implement the next generation of intelligent ground vehicles. The platform comprises modules for training data sets using the neural network, performing object detection and classification, followed by collision avoidance. In addition to course and curriculum development, the platform supports the active participation of the student, undergraduate and graduate, in design competitions related to intelligent and autonomous vehicles.
Sundaram, R. (2022, March), Integrating Broad Background Content into an Introductory Course on Applied Artificial Intelligence Paper presented at 2022 ASEE - North Central Section Conference, Pittsburgh, Pennsylvania. https://peer.asee.org/39249
ASEE holds the copyright on this document. It may be read by the public free of charge. Authors may archive their work on personal websites or in institutional repositories with the following citation: © 2022 American Society for Engineering Education. Other scholars may excerpt or quote from these materials with the same citation. When excerpting or quoting from Conference Proceedings, authors should, in addition to noting the ASEE copyright, list all the original authors and their institutions and name the host city of the conference. - Last updated April 1, 2015