检索结果-内蒙古大学图书馆

ieee International Conference on Robotics and Automation (ICRA)

作者： Leibovich, Gal Jacob, Guy Endrawis, Shadi Novik, Gal Tamar, Aviv Intel Labs Santa Clara CA 95052 USA Technion Israel Inst Technol Haifa Israel

ISBN: (纸本)9781728196817

A practical approach to learning robot skills, often termed sim2real, is to train control policies in simulation and then deploy them on a real robot. Popular sim2real techniques build on domain randomization (DR) - training the policy on diverse randomly generated domains for better generalization to the real world. Due to the large number of hyper-parameters in both the policy learning and DR algorithms, one often ends up with a large number of trained policies, where choosing the best policy among them demands costly evaluation on the real robot. In this work we ask - can we rank the policies without running them in the real world? Our main idea is that a predefined set of real world data can be used to evaluate all policies, using out-of-distribution detection (OOD) techniques. In a sense, this approach can be seen as a 'unit test' to evaluate policies before any real world execution. However, we find that by itself, the OOD score can be inaccurate and very sensitive to the particular OOD method. Our main contribution is a simple-yet-effective policy score that combines OOD with an evaluation in simulation. We show that our score - VSDR - can significantly improve the accuracy of policy ranking without requiring additional real world data. We evaluate the effectiveness of VSDR on sim2real transfer in a robotic grasping task with image inputs. We extensively evaluate different DR parameters and OOD methods, and show that VSDR improves policy selection across the board. More importantly, our method achieves significantly better ranking, and uses significantly less data compared to baselines. Project website is at https: //***/view/vsdr/home

关键词： Training visualization Automation Friction Grasping Robot sensing systems Task analysis

来源：评论

学校读者我要写书评

暂无评论

Weakly-Supervised Semantic Space Structuring: Cardiac Cycle Position for Cerebral Emboli visualization Using Contrastive Learning

Weakly-Supervised Semantic Space Structuring: Cardiac Cycle ...

引用

ieee International symposium on Biomedical Imaging

作者： Mathilde Dupouy Yamil Vindas Marilys Almar Blaise Kévin Guépié Philippe Delachartre CREATIS UMR 5220 U1294 Univ Lyon INSA-Lyon Université Claude Bernard Lyon 1 CNRS Inserm LYON France Inria INSA Lyon CITI UR3720 Villeurbanne France Atys Medical 17 Parc Arbora Soucieu-en-Jarrest France Laboratoire Informatique et Société Numérique Université de Technologie de Troyes Troyes France

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Transcranial Doppler (TCD) is an important tool for monitoring cerebral emboli, a primary cause of ischemic stroke, by detecting high-intensity transient signals (HITS). The link between HITS and their position in the cardiac cycle is emphasized in the literature, but little exploited for microemboli characterization. We therefore propose to integrate this information directly into the structure of latent spaces derived from unsupervised deep learning models toward a more interpretable data visualization. Specifically, we combine autoencoders (AEs) with a contrastive learning framework, where HITS with the same cardiac cycle position are brought closer together, while those with different positions are pushed apart. This weakly-supervised approach facilitates a guided semantic structuring of the latent space, while preserving the underlying data structure. We evaluate our method on a TCD HITS dataset and demonstrate a 11.85% improvement in the local structuring of latent spaces with respect to cardiac cycle position continuity. This trend is further validated in a more complex scenario where the latent space is structured based on both HITS type and cardiac cycle position, outperforming the AE baseline by 5.92% in terms of category continuity in the latent space. These results validate the use of cardiac cycle positioning of HITS for their characterization and demonstrate its benefits for structuring latent representations. The code is available at https://***/MathildeDupouy/contrastive-cardiac-cycle/.

关键词： Representation learning Semantics data visualization Contrastive learning Information representation Market research Doppler effect Transient analysis Unsupervised learning Monitoring

来源：评论

学校读者我要写书评

暂无评论

Medxchat: A Unified Multimodal large Language Model Framework Towards CXRS Understanding and Generation

Medxchat: A Unified Multimodal Large Language Model Framewor...

引用

ieee International symposium on Biomedical Imaging

作者： Ling Yang Zhanyu Wang Zhenghao Chen Xinyu Liang Luping Zhou School of Electrical and Computer Engineering The University of Sydney Australia School of Information and Physical Sciences The University of Newcastle Australia The First Hospital Attached to Guangzhou University of Chinese Medicine

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Multimodal large Language Models (MLLMs) have shown promise in general image tasks, but their application in medical imaging remains limited. This study explores MLLMs for Chest X-Rays (CXRs) through MedXChat, a unified framework enabling seamless interaction for tasks such as text report generation, visual question-answering (VQA), and Text-to-CXR generation. Our MLLM, which uses natural language as input, breaks task boundaries and simplifies medical professional training to the maximum extent by allowing diverse tasks within a single environment. To understand CXRs, we employ visual encoders (e.g.,ViT) and LLMs (e.g., mPLUG-Owl), which we refine using visual adapters and delta-tuning. For CXR generation, we introduce an innovative synthesis approach that leverages the instruction-following capabilities of the Stable Diffusion (SD) architecture to produce fine-grained medical images without additional parameters. Through comprehensive experiments, our model demonstrates exceptional cross-task adaptability, showcasing proficiency across all three tasks.

关键词： Training visualization Adaptation models large language models Biological system modeling Natural languages data models X-ray imaging Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Topological Simplifcation of Jacobi Sets for Piecewise-Linear Bivariate 2D Scalar Fields with Adjustment of the Underlying data

Topological Simplifcation of Jacobi Sets for Piecewise-Linea...

引用

Topological data analysis and visualization (TopoInVis)

作者： Felix Raith Gerik Scheuermann Christian Heine Leipzig University Leipzig University & ScaDS.AI

ISBN: (数字)9798331528447

ISBN: (纸本)9798331528454

Jacobi sets are an important tool to study the relationship between functions. Defined as the set of all points where the function’s gradients are linearly dependent, Jacobi sets extend the notion of critical point to multifields. In practice, Jacobi sets for piecewise-linear approximations of smooth functions can become very complex and large due to noise and numerical errors. Existing methods that simplify Jacobi sets exist, but either do not address how the functions’ values have to change in order to have simpler Jacobi sets or remain purely theoretical. In this paper, we present a method that modifies 2D bivariate scalar fields such that Jacobi set components that are due to noise are removed, while preserving the essential structures of the fields. The method uses the Jacobi set to decompose the domain, stores the and weighs the resulting regions in a neighborhood graph, which is then used to determine which regions to join by collapsing the image of the region’s cells. We investigate the influence of different tie-breaks when building the neighborhood graphs and the treatment of collapsed cells. We apply our algorithm to a range of datasets, both analytical and real-world and compare its performance to simple data smoothing.

关键词： Jacobian matrices Smoothing methods data analysis Noise Buildings data visualization

来源：评论

学校读者我要写书评

暂无评论

LLMs for the Post-Hoc Creation of Provenance

LLMs for the Post-Hoc Creation of Provenance

引用

ieee European symposium on Security and Privacy Workshops

作者： Abdullah Hamed Almuntashiri Luis-Daniel Ibàńez Adriane Chapman University of Southampton Southampton UK Najran University Najran KSA

ISBN: (数字)9798350367294

ISBN: (纸本)9798350367324

Provenance information is an essential component that facilitates the reproduction of scientific experiments, the assessment of data quality, and other related tasks. However, provenance capture at observation is sometimes difficult, and post-hoc methods are needed. In this paper, we explore the ability of large language models (LLMs) to access and extract provenance information from scientific papers through a set of specially designed prompts. We then identify and suggest the most effective prompt for provenance extraction from papers. Our findings confirm the capability of ChatGPT-4 in accessing and extracting provenance information from biomedical research papers.

关键词： Accuracy large language models data integrity Memory management Complexity theory data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

Visual analysis of Public Opinion Based on Keywords

Visual Analysis of Public Opinion Based on Keywords

引用

2021 ieee International Conference on Power Electronics, Computer Applications, ICPECA 2021

作者： Zhang, Dongjiao Guo, Qi Ning, Zenan Zhang, Lei Wan, Fucheng Northwest Minzu University Key Laboratory of China's Ethnic Languages and Information Technology of Ministry of Education Lanzhou China

ISBN: (纸本)9781728190037

With the development of social media, the development of large-scale social media has become the main platform for public opinion today. Visual analysis of public opinion for keywords under specific conditions uses data mining technology, data cleaning technology and data visualization technology. Through keyword reviews and content mining under specific conditions, discrete data is denoised, cleaned, keyword events and geographic information of interest are extracted. Through the visual expression of the geographical distribution of the focus area, the tag cloud and the geographical map are combined to obtain the public opinion dynamics of keyword events, which opens up ideas for the visualization of public opinion analysis of keywords under specific conditions. © 2021 ieee.

关键词： data visualization

来源：评论

学校读者我要写书评

暂无评论

Open-Source Cellular IoT Technologies Coverage data Collection System for Precision Agriculture

Open-Source Cellular IoT Technologies Coverage Data Collecti...

引用

ieee Latin American symposium on Circuits and Systems (LASCAS)

作者： Sebastián Maldonado Gonzalo Escuder Andrés Seré Leonardo Steinfeld Instituto de Ingeniería Eléctrica Facultad de Ingeniería Universidad de la República Montevideo Uruguay Mobile Network Operations Administración Nacional de Telecomunicaciones (ANTEL) Montevideo Uruguay

In remote rural areas, cellular IoT coverage remains limited and exhibits geographical variations, often leading to unreliable connectivity or even complete lack thereof. Mobile operators cannot afford comprehensive coverage assessments conducted through drive testing to provide coverage maps, hindering a wider adoption of IoT solutions for precision agriculture. However, system integrators and farmers could conduct on-demand field coverage assessments to evaluate the feasibility of embracing cellular as a Low Power Wide Area Network (LPWAN) communication technology in their production units if an affordable tool were accessible. This work proposes an open-source tool for cellular IoT coverage analysis. The system comprises a low-cost, portable, and autonomous device with a Global Navigation Satellite System (GNSS) chip and a cellular modem. Constructed using affordable, interconnectable kits (Arduino Zero and a Quectel BG96 modem board) powered by a power bank, it offers several hours of energy autonomy. The device collects network information and transmits it in georeferenced form via MQTT (Message Queuing Telemetry Transport) to a server for storage and user-friendly visualization. The server side is composed of four open-source systems. Eclipse Mosquitto serves as the system's core, implementing the MQTT protocol. Telegraf, a server-based agent, subscribes to Mosquitto topics, extracts data from JSON-formatted messages, and sends it to InfluxDB, a time-series database, for storage. Finally, Grafana serves as a powerful web-based data visualization system, retrieving and displaying InfluxDB data through a color-coded map. Experimental results demonstrate the exceptional potential and effectiveness of the proposed solution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explaining noise effects in CNN: a practical case study on volcano signals 35

Explaining noise effects in CNN: a practical case study on v...

引用

35th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)

作者： Canario, Joao Paulo Ribeiro, Otavio Rios, Ricardo Univ Fed Bahia Inst Comp Salvador Brazil

ISBN: (数字)9781665453851

ISBN: (纸本)9781665453851

The study presented in this work was devoted to understanding the effect of noises in classifiers created to model signals, a particular case of data analysis characterized for presenting temporal dependencies. In this sense, we have considered a real-world application related to predicting seismic volcano events based on its temporal monitoring. Firstly, we created a convolutional neural network (CNN) to model and predict such signals. Then, we have used statistical tests to confirm the noise influence on our network. Finally, we have used an eXplainable AI (XAI) approach to describe the noise behavior visually. Besides developing a CNN with an outstanding performance to deal with this real-world application, the theoretical contribution of our work is twofold: firstly, the adoption of an XAI approach, originally designed to explain image classification, to describe the influence of noise in signals;and, secondly, we show an approach to reconstruct signals after this explaining process to smooth their observations in the time domain.

关键词： visualization Time-frequency analysis Predictive models Volcanoes Safety Convolutional neural networks Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Automated Image Captioning Using Sparrow Search Algorithm With Improved Deep Learning Model

引用

ieee ACCESS 2023年 11卷 104633-104642页

作者： Arasi, Munya A. Alshahrani, Haya Mesfer Alruwais, Nuha Motwakel, Abdelwahed Ahmed, Noura Abdelaziz Mohamed, Abdullah King Khalid Univ Coll Sci & Arts Rijal Almaa Dept Comp Sci Abha 62529 Saudi Arabia Princess Nourah Bint Abdulrahman Univ Coll Comp & Informat Sci Dept Informat Syst POB 84428 Riyadh 11671 Saudi Arabia King Saud Univ Coll Appl Studies & Community Serv Dept Comp Sci & Engn POB 22459 Riyadh 11495 Saudi Arabia Prince Sattam Bin Abdulaziz Univ Coll Business Adm Hawtat Bani Tamim Dept Management Informat Syst Al Kharj 11942 Saudi Arabia Prince Sattam Bin Abdulaziz Univ Dept Comp & Self Dev Preparatory Year Deanship Al Kharj 11942 Saudi Arabia Future Univ Egypt Res Ctr New Cairo 11845 Egypt

Image captioning is a deep learning technique that intends to create and generate textual descriptions or captions for images. It integrates computer vision and natural language processing (NLP) to comprehend the visual content of an image and generate human-like descriptions. Deep learning (DL) based image captioning models can be trained on large-scale datasets, allowing them to generalize various types of images and generate captions that apply to a wide range of visual scenarios. By combining computer vision and natural language processing, DL-enabled image captioning models can understand both visual and textual information, which enables them to generate captions that not only describe the visual content but also incorporate contextual and semantic information. This study develops an Automated Image Captioning using Sparrow Search Algorithm with Improved Deep Learning (AIC-SSAIDL) technique. The major intention of the AIC-SSAIDL technique lies in the automated generation of textual captions for the input images. To accomplish this, the AIC-SSAIDL technique utilizes the MobileNetv2 model to generate feature descriptors of the input images and its hyperparameter tuning process takes place using SSA. For the image captioning process, the AIC-SSAIDL technique utilizes an attention mechanism with long short-term memory (AM-LSTM) network. Finally, the hyperparameter selection of the AM-LSTM model is performed by the fruit fly optimization (FFO) algorithm. A wide range of experiments has been conducted on benchmark data to depict the better performance of the AIC-SSAIDL method. The comprehensive result analysis highlighted the enhanced captioning results of the AIC-SSAIDL method with maximum CIDEr of 46.12, 61.89, and 137.45 on Flickr8k, Flickr30k, and MSCOCO datasets, respectively.

关键词： Convolutional neural networks visualization Feature extraction Convolution Deep learning Natural language processing Computational modeling Image capture Search methods Image captioning deep learning natural language processing sparrow search algorithm computer vision

来源：评论

学校读者我要写书评

暂无评论

Merits and Limits of Preregistration for visualization Research

Merits and Limits of Preregistration for Visualization Resea...

引用

Evaluation and Beyond - Methodological Approaches for visualization (BELIV)

作者： Lonni Besançon Brian A. Nosek Tamarinde Haven Miriah Meyer Cody Dunne Mohammad Ghoniem Linköping University Center for Open Science Inc. & University of Virginia Tilburg University Northeastern University Luxembourg Institute of Science and Technology

ISBN: (数字)9798331528461

ISBN: (纸本)9798331528478

The replication crisis has spawned a revolution in scientific methods, aimed at increasing the transparency, robustness, and reliability of scientific outcomes. In particular, the practice of preregistering study designs has shown important advantages. Preregistration can help limit questionable research practices, as well as increase the success rate of study replications. Many fields have now adopted preregistration as a default expectation for published studies. In 2022, we set up a panel “Merits and Limits of User Study Prereg-istration” with the overall goal of explaining the concept of prereg-istration to a wide VIS audience and discussing its suitability for visualization research. We report on the arguments and discussion of this panel in the hope that it can benefit the visualization com-munity at large. All materials and a copy of this paper are available on our OSF repository at https://***/wes57/.

关键词： Reviews Statistical analysis Interactive systems data visualization Robustness Open data

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：