Browsing by Author "Recabarren, Matias"

Now showing 1 - 8 of 8
  • Thumbnail Image
    Item
    Challenges for computer vision as a tool for screening urban trees through street-view images
    (2024) Arevalo-Ramirez, Tito; Alfaro, Anali; Figueroa, Jose; Ponce-Donoso, Mauricio; Saavedra, Jose M.; Recabarren, Matias; Delpiano, Jose
    Urban forests play a fundamental and irreplaceable role within cities through the ecosystem services they provide, such as carbon capture. However, inadequate management of urban trees can heighten the risks they pose to society. For instance, mechanical failures of tree components, such as branches, can cause harm to individuals and property. Regular assessments of tree conditions are necessary to mitigate these tree-related hazards, yet such evaluations are labor-intensive and currently lack automation. Previous studies have proposed utilizing street view images to alleviate tree inspection and shown the feasibility of visually inspecting trees. However, only a limited number of studies have addressed the automatic evaluation of urban trees, a challenge that can potentially be addressed using deep learning networks. Particularly in urban environments, there is a pressing need for increased automation in unresolved computer vision tasks. Therefore, this research presents a comprehensive analysis of neural networks and publicly available datasets that can aid arborists in automatically identifying urban trees. Specifically, we investigate the potential of deep learning networks in classifying tree genera and segmenting individual trees and their trunks. We emphasize the utilization of transfer learning strategies to enhance tree identification. The results demonstrate that neural networks can be considered practical tools for assisting arborists in tree recognition. Nevertheless, there are still gaps that remain and require attention in future research endeavors.
  • Thumbnail Image
    Item
    Collaborative robotic instruction: A graph teaching experience
    (PERGAMON-ELSEVIER SCIENCE LTD, 2009) Mitnik, Ruben; Recabarren, Matias; Nussbaum, Miguel; Soto, Alvaro
    Graphing is a key skill in the study of Physics. Drawing and interpreting graphs play a key role in the understanding of science, while the lack of these has proved to be a handicap and a limiting factor in the learning of scientific concepts. It has been observed that despite the amount of previous graph-working experience, students of all ages experience a series of difficulties when trying to comprehend graphs or when trying to relate them with physical concepts such as position, velocity and acceleration. Several computational tools have risen to improve the students' understanding of kinematical graphs; however, these approaches fail to develop graph construction skills. On the other hand, Robots have opened new opportunities in learning. Nevertheless, most of their educational applications focus on Robotics related subjects, such as robot programming, robot construction, and artificial intelligence. This paper describes a robotic activity based on face-to-face computer supported collaborative learning. By means of a set of handhelds and a robot wirelessly interconnected, the aim of the activity is to develop graph construction and graph interpretation skills while also reinforcing kinematics concepts. Results show that students using the robotic activity achieve a significant increase in their graph interpreting skills. Moreover, when compared with a similar computer-simulated activity, it proved to be almost twice as effective. Finally, the robotic application proved to be a highly motivating activity for the students, fostering collaboration among them. (C) 2009 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Cultural divide and the Internet
    (PERGAMON-ELSEVIER SCIENCE LTD, 2008) Recabarren, Matias; Nussbaum, Miguel; Leiva, Claudia
    The aim of this paper is to Study the relationship between Culture and Internet usage. In the light of studies showing the existence of subcultures within a Country, an experiment was designed and conducted based on the Hofstede Cultural model and Tiwana's expert knowledge model to determine how social differences affect the Internet usage of first-year University Students. Data-mining techniques were then used to find relationships between culture and Internet usage. We conclude that abilities and performance relating to Internet use differs among subcultures not only because of the digital divide but also because of cultural differences. We also show that subcultures tend to converge over time when placed in the same context. (C) 2008 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Cultural illiteracy and the Internet
    (MARY ANN LIEBERT, INC, 2007) Recabarren, Matias; Nussbaum, Miguel; Leiva, Claudia
    The Internet has created different expectations regarding its possibilities as a tool for including groups that have heretofore been excluded from the modern world. But mere access to information does not necessarily imply correct and effective use of it. Despite the great increase in Internet access in previously excluded areas, expectations of inclusion have not been fulfilled. Research suggests that the effectiveness of Internet use varies among cultures, but all such studies analyze countries as a whole with no further breakdown. Yet it is known that within a given country there co-exist subcultures that differ both in language and social context. This paper presents a study that shows the correlation between different social subcultures and their Internet knowledge.
  • Thumbnail Image
    Item
    Developing Cognition with Collaborative Robotic Activities
    (NATL TAIWAN NORMAL UNIV, TAIWAN, 2009) Mitnik, Ruben; Nussbaum, Miguel; Recabarren, Matias
    Cognition, faculty related to perception, imagination, memory, and problem solving, refers to internal mental processes through which sensorial input is acquired, elaborated, used, and stored. One of its importances relies on the fact that it affects in a direct way the learning potential. It has been shown that, even thou cognitive processes develop side by side with biological maturity, this cognitive development can be enhanced by means of mediated learning as signaled by Feuerstein's Mediated Learning theory. Based on this theory is that we propose an intervention model that addresses school academic issues using technologically assisted small group collaboration, pursuing a dual academic objective: to thrive students' cognitive processes while addressing school curriculum topics. The purpose, therefore, is to balance the students' cognitive differences by means of in-school content-filled classroom activities. Our aim is to make use of peer mediation in a real world setting with a virtual construction of it. In this paper, we describe this novel intervention model along with an in-school usage experience. For this, we present an activity designed for high school students, specifically aimed to assist the learning of kinematics, graph interpretation, and graph plotting. In this activity the students work in groups of three, using a robot and wirelessly interconnected Personal Digital Assistants (PDA). By means of a controlled experiment, we show how technologically-supported peer mediation promotes the students' enrichment of their cognitive processes in each of the different stages of the mental act (input-elaboration-output), favoring communication skills, insight, and reasoning, while also restraining impulsive conduct and trial-and-error answers.
  • No Thumbnail Available
    Item
    Exploring the feasibility of web form adaptation to users' cultural dimension scores
    (2010) Recabarren, Matias; Nussbaum, Miguel
    With many daily tasks now performed on the Internet, productivity and efficiency in working with web pages have become transversal necessities for all users. Many of these tasks involve the inputting of user information, obligating the user to interact with a webform. Research has demonstrated that productivity depends largely on users' personal characteristics, implying that it will vary from user to user. The webform development process must therefore, include modeling of its intended users to ensure the interface design is appropriate. Taking all potential users into account is difficult, however, primarily because their identity is unknown, and some may be effectively excluded by the final design. Such discrimination can be avoided by incorporating rules that allow webforms to adapt automatically to the individual user's characteristics, the principal one being the person's culture. In this paper we report two studies that validate this option. We begin by determining the relationships between a user's cultural dimension scores and their behavior when faced with a webform. We then validate the notion that rules based on these relationships can be established for the automatic adaptation of a webform in order to reduce the time taken to complete it. We conclude that the automatic webform adaptation to the cultural dimensions of users improves their performance.
  • No Thumbnail Available
    Item
    ShakerMaker: A framework that simplifies the simulation of seismic ground-motions
    (2022) Abell, Jose A.; Crempien, Jorge G. F.; Recabarren, Matias
    ShakerMaker is an open-source python framework which simplifies the generation of synthetic broad-band seismograms, produced by finite-fault kinematic representations of earthquake ruptures, using a 1-D layered model of the crust and the frequency-wavenumber (f-k) method. It is designed to bring closer the engineering seismology and earthquake engineering communities, by catering to the earthquake simulation needs of both disciplines. One particular goal of this framework is to provide a simple way to produce high-fidelity earthquake motions for use with the domain-reduction method, simplifying the setup of physically accurate finite-element simulations of multi-scale seismological and earthquake engineering problems through the use of a new specialized file format.
  • Thumbnail Image
    Item
    Teaching Communication, Interpersonal and Decision-Making Skills in Engineering Courses Supported by Technology
    (TEMPUS PUBLICATIONS, 2009) Alvarez, Claudio; Nussbaum, Miguel; Recabarren, Matias; Gomez, Florencia; Radovic, Darinka
    Communication, interpersonal and decision-making skills are essential for engineering work and should be explicitly incorporated in engineering curricula. We have tested a constructivist, technology-supported collaborative strategy in engineering courses that is aimed at supporting the teaching of regular subject matter as well as fostering the development of students' communication and social skills. In this strategy, students communicate face-to-face through a social network while supporting their work with handhelds interconnected through a wireless network. Information transfers from the social network to the handheld network and vice versa, meaning that collaborators maintain face-to-face interaction at all times while also being able to obtain and retrieve information. To implement this strategy, a technology tool named CollPad was created and applied in two computer science courses. The qualitative results of the experience show that students found the tool effective in creating an environment that promotes communication, interpersonal and decision-making skills.