检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Sun, Qinhua Jenny Vo, Khuong Lui, Kitty Nunez, Michael Vandekerckhove, Joachim Srinivasan, Ramesh Department of Cognitive Sciences University of California Irvine IrvineCA United States Department of Computer Science University of California Irvine IrvineCA United States Department of Psychiatry University of California La Jolla San DiegoCA United States Psychological Methods Group University of Amsterdam Amsterdam Netherlands

Human decision making behavior is observed with choice-response time data during psychological experiments. Drift-diffusion models of this data consist of a Wiener first-passage time (WFPT) distribution and are described by cognitive parameters: drift rate, boundary separation, and starting point. These estimated parameters are of interest to neuroscientists as they can be mapped to features of cognitive processes of decision making (such as speed, caution, and bias) and related to brain activity. The observed patterns of RT also reflect the variability of cognitive processes from trial to trial mediated by neural dynamics. We adapted a SincNet-based shallow neural network architecture to fit the Drift-Diffusion model using EEG signals on every experimental trial. The model consists of a SincNet layer, a depthwise spatial convolution layer, and two separate fully connected layers that predict drift rate and boundary for each trial in-parallel. The SincNet layer parametrized the kernels in order to directly learn the low and high cutoff frequencies of bandpass filters that are applied to the EEG data to predict drift and boundary parameters. During training, model parameters were updated by minimizing the negative log likelihood function of WFPT distribution given trial RT. We developed separate decision SincNet models for each participant performing a two-alternative forced-choice task. Our results showed that single-trial estimates of drift and boundary performed better at predicting RTs than the median estimates in both training and test data sets, suggesting that our model can successfully use EEG features to estimate meaningful single-trial Diffusion model parameters. Furthermore, the shallow SincNet architecture identified time windows of information processing related to evidence accumulation and caution and the EEG frequency bands that reflect these processes within each participant. © 2022, CC BY-SA.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Who Said What? An Automated Approach to Analyzing Speech in Preschool Classrooms

arXiv

引用

arXiv 2024年

作者： Sun, Anchen Londono, Juan J. Elbaum, Batya Estrada, Luis Lazo, Roberto Jose Vitale, Laura Villasanti, Hugo Gonzalez Fusaroli, Riccardo Perry, Lynn K. Messinger, Daniel S. Department of Electrical and Computer Engineering University of Miami Coral GablesFL United States Department of Psychology University of Miami Coral GablesFL United States Department of Teaching Learning University of Miami Coral GablesFL United States Department of Mechanical Engineering University of Michigan Ann ArborMI United States Department of Linguistics Cognitive Science and Semiotics Aarhus University Nordre Ringgade 1 Aarhus C8000 Denmark

Young children spend substantial portions of their waking hours in noisy preschool classrooms. In these environments, children’s vocal interactions with teachers are critical contributors to their language outcomes, but manually transcribing these interactions is prohibitive. Using audio from child- and teacher-worn recorders, we propose an automated framework that uses open source software both to classify speakers (ALICE) and to transcribe their utterances (Whisper). We compare results from our framework to those from a human expert for 110 minutes of classroom recordings, including 85 minutes from child-word microphones (n=4 children) and 25 minutes from teacher-worn microphones (n=2 teachers). The overall proportion of agreement, that is, the proportion of correctly classified teacher and child utterances, was .76, with an error-corrected kappa of .50 and a weighted F1 of .76. The word error rate for both teacher and child transcriptions was .15, meaning that 15% of words would need to be deleted, added, or changed to equate the Whisper and expert transcriptions. Moreover, speech features such as the mean length of utterances in words, the proportion of teacher and child utterances that were questions, and the proportion of utterances that were responded to within 2.5 seconds were similar when calculated separately from expert and automated transcriptions. The results suggest substantial progress in analyzing classroom speech that may support children’s language development. Future research using natural language processing is under way to improve speaker classification and to analyze results from the application of the automated framework to a larger dataset containing classroom recordings from 13 children and 3 teachers observed on 17 occasions over one year. © 2024, CC BY-NC-ND.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Point-Snamae: Att-Masked Autoencoder Based on Self-Distillation And Normal Vector Estimation for Self-Supervised Point Cloud Representation Learning

SSRN

引用

SSRN 2024年

作者： Liu, Jie Yang, Mengna Tian, Yu Li, Yancui Song, Da Li, Kang Cao, Xin College of Computer and Information Engineering Henan Normal University Henan Xinxiang453007 China Big Data Engineering Laboratory for Teaching Resources & Assessment of Education Quality Henan Xinxiang453007 China School of Information Science and Technology Northwest University Shaanxi Xi’an China National and Local Joint Engineering Research Center for Cultural Heritage Digitization Shaanxi Xi’an710127 China Bioresource Engineering Department McGill University MontrealQC Canada

Masked signal modeling (MSM) has gained considerable attention in self-supervised learning. Considering that the existing masked strategies may cause the model to damage the structural or semantic understanding of key regions, we present an improved masked auto-encoder based on self-distillation and normal vector prediction that can augment the capacity to recognize local regions. Firstly, given a point cloud with a normal vector, our approach involves the grouping and embedding of point clouds lacking a corresponding normal vector. Secondly, based on self-distillation, the teacher branch guides the student branch to perform regional masking according to an embedded self-attention matrix. Due to the point cloud’s redundancy, the encoder utilizes a high ratio as input and greatly alleviates the input. At the same time, to prevent the model learning difficulty caused by too few inputs from affecting the robustness of model learning, our method only retains a small number of high score regions. Finally, the feature representation of the teacher-student branches is supervised by patch and global losses to comprehensively evaluate the learning performance of the mask patches. Taking normal vector estimation as a supervisory signal to improve global representation. Extensive experiments have shown that our approach is effective and well-transferable to a variety of downstream tasks. Specifically, our model achieves an accuracy of 94.12% on ModelNet40 and 87.16% on the PB-T50-RS setting of ScanObjectNN, outperforming other self-supervised learning methods. Our method achieved a remarkable accuracy of 98.4% in the 5-way 20-shot setting of Few Shot Learning. For part segmentation, our method achieves competitive results with other self-supervised methods. © 2024, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

LLaVA-docent: Instruction tuning with multimodal large language model to support art appreciation education

arXiv

引用

arXiv 2024年

作者： Lee, Unggi Jeon, Minji Lee, Yunseo Byun, Gyuri Son, Yoorim Shin, Jaeyoon Ko, Hongkyu Kim, Hyeoncheol Department of Computer Science and Engineering Korea University Korea Republic of Teaching Learning and Teacher Education University of Nebraska-Lincoln United States Poongnap Elementary School Seoul Metropolitan Office of Education Korea Republic of Department of Education Seoul National University Korea Republic of Interdisciplinary Program in Art Education Art Education Major Seoul National University Korea Republic of Department of Elementary Art Education Seoul National University of Education Korea Republic of

Despite the development of various AI systems to support learning in various domains, AI assistance for art appreciation education has not been extensively explored. Art appreciation, often perceived as an unfamiliar and challenging endeavor for most students, can be more accessible with a generative AI enabled conversation partner that provides tailored questions and encourages the audience to deeply appreciate artwork. This study explores the application of multimodal large language models (MLLMs) in art appreciation education, with a focus on developing LLaVA-Docent, a model designed to serve as a personal tutor for art appreciation. Our approach involved design and development research, focusing on iterative enhancement to design and develop the application to produce a functional MLLM-enabled chatbot along with a data design framework for art appreciation education. To that end, we established a virtual dialogue dataset that was generated by GPT-4, which was instrumental in training our MLLM, LLaVA-Docent. The performance of LLaVA-Docent was evaluated by benchmarking it against alternative settings and revealed its distinct strengths and weaknesses. Our findings highlight the efficacy of the MMLM-based personalized art appreciation chatbot and demonstrate its applicability for a novel approach in which art appreciation is taught and experienced. © 2024, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Are deeper reflectors better goal-setters? AI-empowered analytics of reflective writing in pharmaceutical education

引用

computers and Education: Artificial Intelligence 2023年 5卷

作者： Li, Yuheng Raković, Mladen Dai, Wei Lin, Jionghao Khosravi, Hassan Galbraith, Kirsten Lyons, Kayley Gašević, Dragan Chen, Guanliang Centre for Learning Analytics Monash University Clayton 3168 VIC Australia Human-Computer Interaction Institute School of Computer Science Carnegie Mellon University Pittsburgh PA United States Institute for Teaching and Learning Innovation University of Queensland Brisband 4072 QLD Australia Experiential Development and Graduate Education Faculty of Pharmacy and Pharmaceutical Sciences Monash University Parkville 3052 VIC Australia Centre for Digital Transformation of Health University of Melbourne Parkville 3010 VIC Australia

Reflection and goal-setting are interrelated processes in well-established educational theories to promote in-depth self-reflection and self-regulated learning. Prior studies have considered reflection to be an important antecedent for meaningful goal-setting. Yet, there lacks empirical evidence to shed light on how students' abilities to reflect inform their abilities to set goals. Hence, in the present study, we aimed to quantify the connection between students' retrospective reflection and their subsequent goal-setting, and derive more in-depth insights to benefit educators in their teaching to promote deeper reflection, more specific goal-setting and better self-regulation. To this end, we utilised two fine-grained coding schemes, adapted from well-established reflection and goal-setting theories, respectively, as well as pertinent prior studies, to annotate the reflective and goal-setting elements within 600 student responses in pharmacy curricula. We visualised such elements as a network graph to study students' joint behavioural patterns in reflecting and setting goals. Then, we statistically analysed the correlation between students' reflective levels and the goal specificities using a Mann Whitney U test. We found that (1) descriptive reflection and goals that included content and actions with additional details more commonly presented jointly;(2) students who reflected deeply tended to set more specific goals. These findings are further summarised and discussed to guide educators to adopt reflective and goal-setting practices when designing teaching activities. Moreover, driven by these findings, we emphasised the significance of aiding instructors to provide timely assessment to students' written reflections so as to further ameliorate students' reflective abilities. Therefore, we attempted to automate such assessments using five traditional machine learning algorithms and one deep learning approach based on Bidirectional Encoder Representation of Transfo

关键词： BERT Deep learning Goal-setting Machine learning Reflective writing Self-regulated learning

来源：评论

学校读者我要写书评

暂无评论

Sequen-C: A multilevel overview of temporal event sequences

arXiv

引用

arXiv 2021年

作者： Castaneda, Jessica Gisela Magallanes Stone, Tony Morris, Paul D. Mason, Suzanne Wood, Steven Villa-Uriol, Maria-Cruz Department of Computer Science Centre for Urgent and Emergency Care Research Department of Infection Immunity and Cardiovascular Disease University of Sheffield United Kingdom Sheffield Teaching Hospitals NHS Foundation Trust

Building a visual overview of temporal event sequences with an optimal level-of-detail (i.e. simplified but informative) is an ongoing challenge - expecting the user to zoom into every important aspect of the overview can lead to missing insights. We propose a technique to build a multilevel overview of event sequences, whose granularity can be transformed across sequence clusters (vertical level-of-detail) or longitudinally (horizontal level-of-detail), using hierarchical aggregation and a novel cluster data representation Align-Score-Simplify. By default, the overview shows an optimal number of sequence clusters obtained through the average silhouette width metric - then users are able to explore alternative optimal sequence clusterings. The vertical level-of-detail of the overview changes along with the number of clusters, whilst the horizontal level-of-detail refers to the level of summarization applied to each cluster representation. The proposed technique has been implemented into a visualization system called Sequence Cluster Explorer (Sequen-C) that allows multilevel and detail-on-demand exploration through three coordinated views, and the inspection of data attributes at cluster, unique sequence, and individual sequence level. We present two case studies using real-world datasets in the healthcare domain: CUREd and MIMIC-III;which demonstrate how the technique can aid users to obtain a summary of common and deviating pathways, and explore data attributes for selected patterns. © 2021, CC BY.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Asymptotic Relaxation of Moment Equations for a Multi-species, Homogeneous BGK Model

arXiv

引用

arXiv 2023年

作者： Habbershaw, Evan Glasby, Ryan S. Haack, Jeffrey R. Hauck, Cory D. Wise, Steven M. Department of Mathematics The University of Tennessee KnoxvilleTN37996 United States Computational Sciences and Engineering Division Oak Ridge National Laboratory Oak RidgeTN37831 United States Computational Physics and Methods Group Los Alamos National Laboratory Los AlamosNM87545 United States Computer Science and Mathematics Division Oak Ridge National Laboratory Oak RidgeTN37831 United States

Multi-species BGK models describe the dynamics of rarefied gases with constituent particles of different elements or compounds with potentially non-trivial velocity distributions. In this paper, moment equations for the bulk velocities, energies, and temperatures of a spatially homogeneous multi-species BGK model are examined. A key challenge in analyzing these equations is the fact that the collision frequencies are allowed to depend on the species temperatures, which allows for more realistic simulations of dilute gas flow. Therefore, a positive lower bound is established for the species temperatures. With this lower bound, a global existence and uniqueness of solutions to the coupled velocity-energy ODE system is established. The lower bound also enables a proof of exponential decay to a unique steady-state solution. Numerical results are presented to demonstrate how the bulk velocities and temperatures relax for large *** Codes 37A60, 34A12, 82C40 © 2023, CC BY.

关键词： Velocity distribution

来源：评论

学校读者我要写书评

暂无评论

Improving Lagos State emergency medical services by analysing road traffic accident data, response time, and efficient allocation of ambulances

引用

The Lancet. Global health 2022年 10卷 S26-S26页

作者： Salam, Sayeed, PhD Mehta, Avirut Kim, Dohyeong, PhD Seyi-Olajide, Justina, PhD Allo, Nicholas, PhD Malolan, Chenchita, MPH Nwariaku, Fiemu, MD Khan, Latifur, PhD Department of Computer Science University of Texas at Dallas Richardson TX United States Department of Public Policy and Political Economy Geospatial Information Sciences University of Texas at Dallas Richardson TX United States Lagos University Teaching HospitalLagos Nigeria Visual Earth London United Kingdom University of Texas Southwestern Medical Center University of Texas Dallas United States Department of Computer Science University of Texas at Dallas Richardson TX United States

BACKGROUND: Emergency medical services (EMS) play a critical role in the response to road traffic accidents (RTAs) by providing critical prehospital care to RTA victims, and thus helping to reduce the severity of injuries and casualties from RTAs. Analysing the efficiency of such systems and optimising the service (often with insufficient resources) would be highly beneficial to inform operating guidelines. In this study, we aimed to assess the ambulance utilisation rate for RTAs and provide insights about the system's efficiency and utilisation metrics in Lagos State, Nigeria. methods: We received hospital capacity information (type of hospital [eg, tertiary] and number of beds, nurses, operating rooms, and so on) from hospital survey data in Lagos. Additionally, we received RTA-specific intervention forms from the Lagos State Ambulance Service. With the limited amount of historical data, we highlighted methods to estimate the system parameters (eg, arrival rate, service rate, and so on) of RTA victims at various hospitals in Lagos. We also developed a parametric model and applied approximate dynamic programming approach for ambulance dispatch and location optimisation with a fixed number of base stations. Furthermore, our routing approach was accompanied by directions from OpenRouteService and queue analysis to determine the most appropriate hospital near an RTA for the EMS systems in Lagos. FINDINGS: Using patient-queue based wait-time analysis, we found that in over 80% of cases, one of the nearest three hospitals was the most appropriate recommendation for patient delivery. This exponentially decays with the next closest hospitals. Additionally, we found that optimising the ambulance relocation method, where the ambulance returns to a base selected by our model as opposed to its dedicated base or a random base, can reduce the average response time of the EMS system by 8%, or 3·5 min (from 41 min to 38 min). INTERPRETATION: Appropriate placement of mobile resour

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mathematical Modeling of the Orthotropy Effect in the Problems of DC Electrical Exploration by Boundary and Near-boundary Element methods 15

Mathematical Modeling of the Orthotropy Effect in the Proble...

引用

15th IEEE International Scientific and Technical Conference on computer sciences and Information Technologies, CSIT 2020

作者： Zhuravchak, Liubov Zabrodska, Nataliya Lviv Polytechnic National University Software Department Institute of Computer Science and Information Technologies Lviv Ukraine National Academy of Sciences Department of Geoelectromagnetic Methods Carpathian Branch of S.I. Subbotin Institute of Geophysics Lviv Ukraine

ISBN: (纸本)9781728174433

Mathematical models of the electric field distribution of direct current (DC) in 2D and 3D orthotropic piecewise-homogeneous half-infinite media, taking into account an ideal contact between components, have been constructed. To find solutions of the respective problems of potential theory, indirect methods of boundary and near-boundary elements have been used. The orthotropy effect in homogeneous and piecewise-homogeneous half-spaces has been investigated. A software implementation of the proposed approaches has been carried out. © 2020 IEEE.

关键词： Boundary element method

来源：评论

学校读者我要写书评

暂无评论

Multimodal Learning for Predicting Mortality in Patients with Pulmonary Arterial Hypertension

Multimodal Learning for Predicting Mortality in Patients wit...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mohammod N. I. Suvon Prasun C. Tripathi Samer Alabed Andrew J. Swift Haiping Lu Department of Computer Science The University of Sheffield Sheffield United Kingdom Department of Infection Immunity and Cardiovascular Disease The University of Sheffield Sheffield United Kingdom INSIGNEO Institute for in silico medicine The University of Sheffield Sheffield United Kingdom Department of Clinical Radiology Sheffield Teaching Hospitals Sheffield United Kingdom

ISBN: (数字)9781665468190

ISBN: (纸本)9781665468206

Pulmonary Arterial Hypertension (PAH) is a lifethreatening disorder. The prediction of mortality in PAH patients can play a crucial role in the clinical management of this disease. The prediction of mortality from one modality is a difficult task that may only provide limited performance. Therefore, we propose a multimodal learning approach in this work to predict one-year mortality in PAH patients. We have utilised three modalities, which include extracted numerical imaging features, echo report categorical features, and echo report text features from Electronic Health Records (EHRs) of patients. We have proposed a feature integration module to combine features from multiple modalities. The text features have been extracted from the echo reports using the Bidirectional Encoder Representations from Transformers (BERT). An attention mechanism and a weighted summation method are also adopted during the process of feature integration. We have performed different experiments to evaluate the performance of the proposed framework for mortality prediction. The experimental results indicate that we can achieve the best AUC score of 0.89 for predicting one-year mortality by combining all three modalities. The source code of this paper is available at https://***/Mdnaimulislam/MultimodalTab.

关键词： Hypertension Source coding Bit error rate Lung Imaging Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：