Search for: All records

In today’s world, augmented reality and virtual reality (AR/VR) technologies have become more accessible to the public than ever. This brings the possibility of immersive learning to the forefront of education for future generations. However, there is still much to discover and improve in using these technologies to analyze and understand learning. This paper explores the utilization of data captured through AR/VR headsets during an immersive training program for industrial robotics. This includes data on time spent, eye gaze, and hand movement during a range of activities to track a learner’s understanding of the content and intelligently estimate learner confidence within these environments using deep learning. Leveraging a dataset that comprises responses and confidence levels from 10 individuals across 35 questions, we aim to improve the uses and applicability of confidence estimation. We explore the possibility of training a model using learners’ data to dynamically fine-tune lessons and activities for each individual, thereby improving performance. We demonstrate that a pre-trained compact LSTM classification model can be fine-tuned with relatively small data, for enhanced performance on an individual basis for better personalized learning. 

Abstract The F-box protein Coronatine Insensitive (COI) is a receptor for the jasmonic acid signaling pathway in plants. To investigate the functions of the 6 maize (Zea mays) COI proteins (COI1a, COI1b, COI1c, COI1d, COI2a, and COI2b), we generated single, double, and quadruple loss-of-function mutants. The pollen of the coi2a coi2b double mutant was inviable. The coi1 quadruple mutant (coi1-4x) exhibited shorter internodes, decreased photosynthesis, leaf discoloration, microelement deficiencies, and accumulation of DWARF8 and/or DWARF9, 2 DELLA family proteins that repress the gibberellic acid (GA) signaling pathway. Coexpression of COI and DELLA in Nicotiana benthamiana showed that the COI proteins trigger proteasome-dependent DELLA degradation. Many genes that are downregulated in the coi1-4x mutant are GA-inducible. In addition, most of the proteins encoded by the downregulated genes are predicted to be bundle sheath- or mesophyll-enriched, including those encoding C4-specific photosynthetic enzymes. Heterologous expression of maize Coi genes in N. benthamiana showed that COI2a is nucleus-localized and interacts with maize jasmonate zinc-finger inflorescence meristem domain (JAZ) proteins, the canonical COI repressor partners. However, maize COI1a and COI1c showed only partial nuclear localization and reduced binding efficiency to the tested JAZ proteins. Together, these results show the divergent functions of the 6 COI proteins in regulating maize growth and defense pathways. 

Despite the significant advancements in the field of Natural Language Processing (NLP), Large Language Models (LLMs) have shown limitations in performing complex tasks that require arithmetic, commonsense, and symbolic reasoning. Reasoning frameworks like ReAct, Chain-of-thought (CoT), Tree-of-thoughts (ToT), etc. have shown success but with limitations in solving long-form complex tasks. To address this, we propose a knowledge-sharing and collaborative multi-agent assisted framework on LLMs that leverages the capabilities of existing reasoning frameworks and the collaborative skills of multi-agent systems (MASs). The objectives of the proposed framework are to overcome the limitations of LLMs, enhance their reasoning capabilities, and improve their performance in complex tasks. It involves generating natural language rationales and in-context few-shot learning via prompting, and integrates the reasoning techniques with efficient knowledge-sharing and communication driven agent networks. The potential benefits of the proposed framework include saving time and money, improved efficiency for computationally intensive reasoning, and the ability to incorporate multiple collaboration strategies for dynamically changing environments. 

Abstract Homophily, the tendency for individuals to preferentially interact with others similar to themselves is typically documented via self-report and, for children, adult report. Few studies have investigated homophily directly using objective measures of social movement. We quantified homophily in children with developmental disabilities (DD) and typical development (TD) using objective measures of position/orientation in preschool inclusion classrooms, designed to promote interaction between these groups of children. Objective measurements were collected using ultra-wideband radio-frequency tracking to determine social approach and social contact, measures of social movement and interaction. Observations of 77 preschoolers (47 with DD, and 30 TD) were conducted in eight inclusion classrooms on a total of 26 days. We compared DD and TD groups with respect to how children approached and shared time in social contact with peers using mixed-effects models. Children in concordant dyads (DD-DD and TD-TD) both moved toward each other at higher velocities and spent greater time in social contact than discordant dyads (DD-TD), evidencing homophily. DD-DD dyads spent less time in social contact than TD-TD dyads but were comparable to TD-TD dyads in their social approach velocities. Children’s preference for similar peers appears to be a pervasive feature of their naturalistic interactions. 

The COVID-19 pandemic has resulted in more than 440 million confirmed cases globally and almost 6 million reported deaths as of March 2022. Consequently, the world experienced grave repercussions to citizens’ lives, health, wellness, and the economy. In responding to such a disastrous global event, countermeasures are often implemented to slow down and limit the virus’s rapid spread. Meanwhile, disaster recovery, mitigation, and preparation measures have been taken to manage the impacts and losses of the ongoing and future pandemics. Data-driven techniques have been successfully applied to many domains and critical applications in recent years. Due to the highly interdisciplinary nature of pandemic management, researchers have proposed and developed data-driven techniques across various domains. However, a systematic and comprehensive survey of data-driven techniques for pandemic management is still missing. In this article, we review existing data analysis and visualization techniques and their applications for COVID-19 and future pandemic management with respect to four phases (namely, Response, Recovery, Mitigation, and Preparation) in disaster management. Data sources utilized in these studies and specific data acquisition and integration techniques for COVID-19 are also summarized. Furthermore, open issues and future directions for data-driven pandemic management are discussed. 

P4Cub is a new intermediate representation (IR) for the P4 programming language. It has been designed with the goal of facilitating development of certified tools. To achieve this, P4Cub is organized around a small set of core constructs and avoids side effects in expressions, which avoids mutual recursion between the semantics of expressions and statements. Still, it retains the essential domain-specific features of P4 itself. P4Cub has a front-end based on Petr4, and has been fully mechanized in Coq including big-step and small-step semantics and a type system. As case studies, we have engineered several certified tools with P4Cub including proofs of type soundness, a verified compilation pass, and an automated verification tool.