Collection

2024 ASEE North Central Section Conference

Authors

Joseph George, Western Michigan University; Ajay Gupta, Western Michigan University; Alvis Fong, Western Michigan University

save time in defining the accurate model for the data chosen. Theexperiment was run on a Michigan State University cluster having one NVIDIA A100GPU, Intel XEON CPU with 36GB of allocated memory. Amino acid Accuracy Time duration A 0.706 00h 47m 06s R 0.564 01h 53m 16s N 0.654 03h 07m 00s D 0.651 01h 31m 36s C 0.939 01h 28m 31s Q

Collection

2024 ASEE North Central Section Conference

Authors

Bin Chen, Purdue University Fort Wayne

Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningAugust (2016) 785–79412. Wang C., Wu Q., Weimer M., Zhu E.. FLAML: A Fast and Lightweight AutoML Library. (2019). https://arxiv.org/abs/1911.0470613. Ke G., Meng K., Finley T., Wang T., Chen W., Ma W., Ye Q., Liu TY. LightGBM: a highly efficient gradient boosting decision tree. NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems. (2017) 3149–315714. Prokhorenkova L., Gusev G., Vorobev A., Dorogush AV, Gulin A. CatBoost: unbiased boosting with categorical features. NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems

Collection

2024 ASEE North Central Section Conference

Authors

Elin Jensen, Lawrence Technological University

Non-Learning Deep Learning New concepts and cross links XI Absent - - - - -The statistical analysis presented in the following section is for the purpose of visualizing trends,only. The results may not be representative of a larger study group. Future work will includerepetition and validation. Figure 5 shows probability density functions for the mind map scoresassuming that the mind map scores can be represented by a theoretical normal distribution. Themind map score is a positive value. Both Q-Q tests and Chi-tests indicate that the (limited) datasets can be represented by either a normal or lognormal distribution. The addition of data fromfuture semesters will be used to

Collection

2024 ASEE North Central Section Conference

Authors

John William Lynch, University of Cincinnati; Sheryl A. Sorby, University of Cincinnati; Betsy M. Aller, Western Michigan University; Teri J Murphy, University of Cincinnati

Tagged Topics

Diversity

. Reviewers were offered a comment box area where theycould elaborate on why they decided on specific scores for each question.Table 1. Working version of Communication Task Rubric distributed to reviewers Q. # General Specific details for question Description 1. Overall design • “Big picture” of robot design project is shown. project and goals • Problems to be solved are provided. identified. 2. Purpose / task of • Robot’s specific goals / tasks to be accomplished are identified. the robot provided.• Precise tasks to perform are clearly described. Proceedings of the 2024 ASEE North Central Section Conference Copyright @2024

Collection

2024 ASEE North Central Section Conference

Authors

Ethan O'Neill, Geneva College; Christopher Charles Jobes P.E., Geneva College

4 Proceedings of the 2024 ASEE North Central Section Conference Copyright © 2024, American Society for Engineering EducationThe rest of the variables used in the analysis of the steering geometry are presented in Figure 2, acomplete diagram of steering components and their associated geometry. Where: x = steering arm length y = tie rod length p = rack casing length q = lateral travel of rack d = distance between front axis and rack center axis β = Ackerman angleNote: the point of intersection of the two extrapolated steering arm lines must lie on the rear axleto constitute Ackerman steering.Using the variables defined in Figure 2, the following three

Collection

2024 ASEE North Central Section Conference

Authors

Nicholas Brown, Western Michigan University; Johan Fanas Rojas, Western Michigan University; Alyssa K. Moon, Western Michigan University; Ali Alhawiti, Western Michigan University; Pritesh Yashaswi Patil, Western Michigan University; Parth Kadav, Western Michigan University; Kira Hamelink, Western Michigan University; Wendy R. Swalla, Western Michigan University; Zachary D. Asher, Western Michigan University

- Final Project Q&A Physical Vehicle Control Example and Vehicle Integration Applying ISO 26262 Lab 13 walk-through EEAV Lab Student’s Final Project Reports and Lecture 14 Chapter 5 - AV system - Presentations Final Algorithms Test Run Autonomous Vehicle Operation Final GitHub and LinkedIn Profile Capstone Problem

Collection

2024 ASEE North Central Section Conference

Authors

Joseph Carpenter Sheils, Marshall University; David A Dampier, Marshall University; Haroon Malik, Marshall University

Arabia and the effect of gender bias in student evaluations.7,8 In other applications, topicmodeling has been used to construct recommendation systems in Q&A sites, analyze developerdiscussions on Stack Overflow, explore posts on Twitter and Instagram, and understand the diningexperience of tourists.9-13Similar to numeric clustering methods, topic models discover patterns in unlabeled data. To findword clusters, various techniques can be used. In this paper, we study four topic models that usedifferent implementation methods: (1) Latent Dirichlet Allocation, (2) Nonnegative MatrixFactorization, (3) BERTopic, and (4) Top2Vec.2.3.1. Latent Dirichlet AllocationLatent Dirichlet Allocation (LDA) is a generative probabilistic model for collections