- Browse by Subject
Browsing by Subject "algorithms"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Clustering Algorithm Based Straight and Curved Crop Row Detection Using Color Based Segmentation(ASME, 2021-02) Khan, Nazmuzzaman; Rajendran, Veera P.; Al Hasan, Mohammad; Anwar, Sohel; Mechanical and Energy Engineering, School of Engineering and TechnologyAutonomous navigation of agricultural robot is an essential task in precision agriculture, and success of this task critically depends on accurate detection of crop rows using computer vision methodologies. This is a challenging task due to substantial natural variations in crop row images due to various factors, including, missing crops in parts of a row, high and irregular weed growth between rows, different crop growth stages, different inter-crop spacing, variation in weather condition, and lighting. The processing time of the detection algorithm also needs to be small so that the desired number of image frames from continuous video can be processed in real-time. To cope with all the above mentioned requirements, we propose a crop row detection algorithm consisting of the following three linked stages: (1) color based segmentation for differentiating crop and weed from background, (2) differentiating crop and weed pixels using clustering algorithm and (3) robust line fitting to detect crop rows. We test the proposed algorithm over a wide variety of scenarios and compare its performance against four different types of existing strategies for crop row detection. Experimental results show that the proposed algorithm perform better than the competing algorithms with reasonable accuracy. We also perform additional experiment to test the robustness of the proposed algorithm over different values of the tuning parameters and over different clustering methods, such as, KMeans, MeanShift, Agglomerative, and HDBSCAN.Item Optimal Design for Deployable Structures Using Origami Tessellations(ASME, 2020-01) Cardona, Carolina; Tovar, Andres; Anwar, Sohel; Mechanical and Energy Engineering, School of Engineering and TechnologyThis work presents innovative origami optimization methods for the design of unit cells for complex origami tessellations that can be utilized for the design of deployable structures. The design method used to create origami tiles utilizes the principles of discrete topology optimization for ground structures applied to origami crease patterns. The initial design space shows all possible creases and is given the desired input and output forces. Taking into account foldability constraints derived from Maekawa’s and Kawasaki’s theorems, the algorithm designates creases as active or passive. Geometric constraints are defined from the target 3D object. The periodic reproduction of this unit cell allows us to create tessellations that are used in the creation of deployable shelters. Design requirements for structurally sound tessellations are discussed and used to evaluate the effectiveness of our results. Future work includes the applications of unit cells and tessellation design for origami inspired mechanisms. Special focus will be given to self-deployable structures, including shelters for natural disasters.Item Teaching Algorithmic Literacy within a Media Literacy Program(International Council for Media Literacy, 2022) Morris, Pamela; IUPUC School of Liberal ArtsThe prevalence of algorithms in daily life and the growing role of algorithms in societal decision making and governance has led to a call for teaching algorithmic literacy as a specific part of media and digital literacy. Several researchers have recently attempted to define algorithmic literacy and proposed scales to measure algorithmic knowledge; initial results indicate a widespread lack of awareness of and knowledge about algorithms, even in high-technology countries. Thus, teachers and instructors need to develop lesson plans that inform about algorithms and engage critical thinking and discussion about their role in our lives. However, this is a challenging topic. This article reviews literature on the need for and definition of algorithmic literacy and suggests steps instructors and teachers can take learn and teach about algorithms, including a list of recommended resources.Item The VITAL project: Visual Information Translation Analysis & Learning in Life Sciences(Office of the Vice Chancellor for Research, 2011-04-08) Tsechpenakis, Gavriil; Chang, XiaoIn many disciplines of science, especially in life sciences, research proceeds in a top-down approach, in which domain experts formulate hypotheses that are tested on relevant data. In contrast, research in Computer Science and Engineering often follows a data-driven bottom-up approach. In the bottom-up approach, various algorithms and computational tools are designed and utilized to perform unstructured knowledge discovery such as finding patterns and structure in data. In this presentation we give an overview of our research activities, namely how we combine novel bottom-up Computer Vision and Machine Learning methods with top-down domain knowledge in Physiology, Neuroscience and clinical Medicine to engender knowledge discovery. Specifically, we present our efforts towards answering the following questions: does brain control breathing? do genes control locomotion and touch sensation? can we reconstruct a model brain at single-cell resolution? how can we model protein-protein interactions in neurons, in situ? can we predict the biological effect of growth factor-delivering scaffolds for promoting angiogenesis? can we combine Magnetic Resonance imagery and biochemical spectroscopy for brain tumor radiation treatment planning? The VITAL project (PI: Tsechpenakis - web.mac.com/gavriil ) is a new research group, part of the Center for Visual Information Sensing and Computing (visc.cs.iupui.edu) at the Computer Science Department of IUPUI. The core theoretical background of our modeling and analysis methods is in Computer Vision, applied Machine Learning, Imaging and Signal Processing. Currently our research is funded by two NIH grants and the IUPUI School of Science; the PI’s research has been previously funded by NIH, NSF, NOAA, and the Wallace H. Coulter Foundation.