检索结果-内蒙古大学图书馆

Improving Interpretability of Radiology Report-based Pediatric Brain Tumor Pathology Classification and Key-phrases Extraction Using Large Language Models

Improving Interpretability of Radiology Report-based Pediatr...

引用

2024 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2024

作者： Zhao, Chen Kudus, Kareem Ketabi, Sara Namdar, Khashayar Wagner, Matthias W. Ertl-Wagner, Birgit B. Khalvati, Farzad University of Toronto Department of Mechanical and Industrial Engineering TorontoON Canada Neurosciences & Mental Health Research Program Research Institute The Hospital for Sick Children TorontoON Canada Institute of Diagnostic and Interventional Neuroradiology University Hospital Augsburg Germany The Hospital for Sick Children Department of Diagnostic & Interventional Radiology TorontoON Canada University of Toronto Department of Medical Imaging TorontoON Canada University of Toronto Department of Computer Science TorontoON Canada Institute of Medical Science University of Toronto TorontoON Canada

ISBN: (纸本)9798350351552

Radiology reports are crucial for bridging the expertise of radiologists and other clinicians. Machine Learning models trained on these reports have shown promising performance in various downstream clinical tasks, such as predicting the necessity of future follow-up procedures, based on past radiology reports. However, for clinicians to adopt these models and for radiologists to validate the results, interpretability of the model is essential. In this study, we train BERT models on radiology reports to classify pediatric brain tumor pathologies. These large language models enable accurate report-level classification, without the need for costly word-level annotations. To identify and extract keywords and key-phrases related to distinct pathologies from radiology reports, we used a modified Term Frequency-Inverse Document Frequency to determine phrase importance based on prevalence and attributions scores. We achieved an overall multiclass Area Under Receiver Operating Characteristic Curve (AUROC) of 79.57% using ClinicaiBERT. Moreover, the per-class AUROC values were 86%, 71.2%, and 81.5%, for 'Pilocytic Astrocytoma', 'Low-Grade Astrocytoma', and 'Other' pathologies, respectively. Our explainability analysis identified hypotonia and mesencephalon as the most important terms for 'Pilocytic Astrocytoma' and 'Low-Grade Astrocytoma', respectively. © 2024 IEEE.

关键词： Radiology

来源：评论

学校读者我要写书评

暂无评论

Bayesian and Neural Inference on LSTM-based Object Recognition from Tactile and Kinesthetic Information

arXiv

引用

arXiv 2023年

作者： Pastor, Francisco García-González, Jorge Gandarias, Juan M. Medina, Daniel Closas, Pau García-Cerezo, Alfonso J. Gómez-De-Gabriel, Jesús M. The Robotics and Mechatronics Group University of Málaga Spain The Department of Computer Languages and Computer Science University of Málaga Spain Germany The Department of Electrical and Computer Engineering Northeastern University BostonMA02115 United States

Recent advances in the field of intelligent robotic manipulation pursue providing robotic hands with touch sensitivity. Haptic perception encompasses the sensing modalities encountered in the sense of touch (e.g., tactile and kinesthetic sensations). This letter focuses on multimodal object recognition and proposes analytical and data-driven methodologies to fuse tactile- and kinesthetic-based classification results. The procedure is as follows: a three-finger actuated gripper with an integrated high-resolution tactile sensor performs squeeze-and-release Exploratory Procedures (EPs). The tactile images and kinesthetic information acquired using angular sensors on the finger joints constitute the time-series datasets of interest. Each temporal dataset is fed to a Long Short-term Memory (LSTM) Neural Network, which is trained to classify in-hand objects. The LSTMs provide an estimation of the posterior probability of each object given the corresponding measurements, which after fusion allows to estimate the object through Bayesian and Neural inference approaches. An experiment with 36-classes is carried out to evaluate and compare the performance of the fused, tactile, and kinesthetic perception systems. The results show that the Bayesian-based classifiers improves capabilities for object recognition and outperforms the Neural-based approach. Copyright © 2023, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction and Recommendation Approach Based on Machine Learning 4

Stock Price Prediction and Recommendation Approach Based on ...

引用

4th IEEE Eurasia Conference on IoT, Communication and engineering, ECICE 2022

作者： Chang, Chin-Chih Luo, Kei-Wen Hsiao, Sean Chung Hua University Bachelor's Program in Applied Foreign Language and Smart Commerce Hsinchu Taiwan Chung Hua University Department of Computer Science and Information Engineering Hsinchu Taiwan

ISBN: (纸本)9781665482080

Investment is a lifetime work. Investing in stocks is a popular measure. However, investing in stocks is not easy, and losing money is not uncommon. We investigate if there is a systematic way to find buyable stocks and more importantly when to buy and sell them. Nowadays, with the progress of hardwarel, artificial intelligence (AI) has become a feasible solution to many issues. Machine learning and deep learning are two widely adopted methods in AI. In this study, we show how to apply machine learning to stock prediction and recommendation. After trials, we found that LightGBM shows its potential to predict and recommend stocks. We used the data of the Taiwan stock market to validate the method. We compared the prediction and recommendation with the wellknown Taiwan ETFs 0050 and 0056. The results show that the method is feasible, effective, efficient, and has better performance than Taiwan ETFs 0050 and 0056. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Flickr30K-CFQ: A Compact and Fragmented Query Dataset for Text-image Retrieval

arXiv

引用

arXiv 2024年

作者： Liu, Haoyu Song, Yaoxian Wang, Xuwu Zhu, Xiangru Li, Zhixu Song, Wei Li, Tiefeng Research Center for Intelligent Robotics Zhejiang Lab China Department of Engineering Mechanics Center for X-Mechanics Zhejiang University China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China

With the explosive growth of multi-modal information on the Internet, unimodal search cannot satisfy the requirement of Internet applications. Text-image retrieval research is needed to realize high-quality and efficient retrieval between different modalities. Existing text-image retrieval research is mostly based on general vision-language datasets (e.g. MS-COCO, Flickr30K), in which the query utterance is rigid and unnatural (i.e. verbosity and formality). To overcome the shortcoming, we construct a new Compact and Fragmented Query challenge dataset (named Flickr30K-CFQ) to model text-image retrieval task considering multiple query content and style, including compact and fine-grained entity-relation corpus. We propose a novel LLM-based Query-enhanced method using prompt engineering based on LLM. Experiments show that our proposed Flickr30-CFQ reveals the insufficiency of existing vision-language datasets in realistic text-image tasks. Our LLM-based Query-enhanced method applied on different existing text-image retrieval models improves query understanding performance both on public dataset and our challenge set Flickr30-CFQ with over 0.9% and 2.4% respectively. Our project can be available anonymously in https://***/view/Flickr30K-cfq. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Direct Drive System Applied to a Small Size League Robot

Direct Drive System Applied to a Small Size League Robot

引用

2024 Brazilian Symposium on robotics (SBR), and 2024 Workshop on robotics in Education (WRE)

作者： Henrique Barros Simões Flavio Tonidandel Department of Robotics Engineering Centro Universitário FEI São Bernardo do Campo Brazil Department of Computer Science Centro Universitário FEI São Bernardo do Campo Brazil

ISBN: (数字)9798350391084

ISBN: (纸本)9798350391091

This paper compares a new transmission system and a new set of powertrains for robots in the Small Size League category of the RoboCup Soccer competition. The goal is to improve their speed and movement, leading to better performance and engine efficiency. Additionally, the study aims to optimize the robot's lower internal space to facilitate future improvements and integration of new technologies. The best types of powertrains in various arrangements, shapes, sizes, and the optimal motor/wheel system are studied, presenting a direct drive system that suits the league's evolution.

关键词： Shape Robot vision systems Education Wheels Mechanical power transmission Software Trajectory Mobile robots Engines Sports

来源：评论

学校读者我要写书评

暂无评论

Customer Service Chatbot Enhanced with Conversational Language Understanding and Knowledge Base 4

Customer Service Chatbot Enhanced with Conversational Langua...

引用

4th IEEE Eurasia Conference on IoT, Communication and engineering, ECICE 2022

作者： Chang, Chin-Chih Cheng, Wen-Shing Hsiao, Sean Chung Hua University Bachelor's Program in Applied Foreign Language and Smart Commerce Hsinchu Taiwan Chung Hua University Department of Computer Science and Information Engineering Hsinchu Taiwan

ISBN: (纸本)9781665482080

A customer service chatbot enhanced with conversational language understanding and knowledge base is developed. Here, we explore LUIS and QnA Maker which are unified as Azure cognitive service for language. LUIS is a cloudbased conversational AI service that responds a user intelligence. QnA maker is a knowledge base for custom question answering. This question-and-answer knowledge base is especially useful for customer dialogs. Hence, by combining the services, we provide a smart response and provide a knowledge base to understand and improve the service. We implement this chatbot on the LINE Bot platform. Users easily access it by simply adding the representative of this chatbot on LINE. In addition, we put marketing information through this chatbot. The experiments are conducted, and the results show the chatbot is feasible and has a high user acceptance. © 2022 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

An Efficient Scene Coordinate Encoding and Relocalization Method

arXiv

引用

arXiv 2024年

作者： Xu, Kuan Jiang, Zeyu Cao, Haozhi Yuan, Shenghai Wang, Chen Xie, Lihua School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue 639798 Singapore Spatial AI & Robotics Lab Department of Computer Science and Engineering University at Buffalo BuffaloNY14260 United States

Scene Coordinate Regression (SCR) is a visual localization technique that utilizes deep neural networks (DNN) to directly regress 2D-3D correspondences for camera pose estimation. However, current SCR methods often face challenges in handling repetitive textures and meaningless areas due to their reliance on implicit triangulation. In this paper, we propose an efficient scene coordinate encoding and relocalization method. Compared with the existing SCR methods, we design a unified architecture for both scene encoding and salient keypoint detection, enabling our system to focus on encoding informative regions, thereby significantly enhancing efficiency. Additionally, we introduce a mechanism that leverages sequential information during both map encoding and relocalization, which strengthens implicit triangulation, particularly in repetitive texture environments. Comprehensive experiments conducted across indoor and outdoor datasets demonstrate that the proposed system outperforms other state-of-the-art (SOTA) SCR methods. Our single-frame relocalization mode improves the recall rate of our baseline by 6.4% and increases the running speed from 56Hz to 90Hz. Furthermore, our sequence-based mode increases the recall rate by 11% while maintaining the original efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Triangulation

来源：评论

学校读者我要写书评

暂无评论

Soft Sensing Brace for Monitoring Knee Joint Kinetics and Kinematics During Squatting

Soft Sensing Brace for Monitoring Knee Joint Kinetics and Ki...

引用

International Conference on Ubiquitous Robots (UR)

作者： Junhwan Choi Eunseok Song Hyunkyu Park Kyoungchul Kong Jung Kim Department of Mechanical Engineering Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea Robotics Program Korea Advanced Institute of Science and Technology (KAIST) Daejeon Republic of Korea

Exoskeletons have been developed to increase joint performance by providing assistance torque. Soft exosuits, which use light and soft materials for human-robot interaction, are a growing trend in the orthosis. However, wearable motion capture technology for biomechanical data collection remains a challenge. Traditional measurement systems such as motion capture camera (Mocap), inertial measurement units (IMUs), and ground reaction force and moment (GRF&M) are computationally intensive and collected in restricted laboratory environments. To address this challenge, we propose a sensing brace to monitor knee joint kinetics using an elastic strain sensor and a pressure-based mechanomyography (pMMG) sensor. The pMMG sensor improves comfort, reliability, linearity, and durability, and does not need to attach directly to the skin. Linear regression model of knee angle and moment are conducted with high reliability which showed $p-value < 0.05$ and $R^{2}$ is over 0.98. We used a linear regression model to estimate knee angle and torque during squatting with $\text{RMSE} =4.4\ deg$ in knee angle estimation and $\text{RMSE}=3.4\ Nmm/kg$ in knee moment estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Particle Swarm Approach for Energy-Aware Location-Aided Routing in Mobile Ad-Hoc Network

An Improved Particle Swarm Approach for Energy-Aware Locatio...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Sandeep Kumar Khemraj Sharma P. M. Ashok Kumar Arpit Jain Sukesh Kumar Bhagat Pranita Singh Tula’s institute Dehradun U.K India Department of Business Administration Doctoral Program in Management Sciences Nanhua University Dalin Chiayi R.O.C Department of Computer Science Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India Department of Computer Science & Engineering Uttaranchal University Dehradun Uttarakhand India Department of Computer Science and Engineering Roorkee Institute of Technology Roorkee Uttarakhand India

ISBN: (数字)9798350350067

ISBN: (纸本)9798350350074

A network with no infrastructure, multiple hops, and dispersed nodes called a MANET. Nodes can communicate directly or through intermediaries without the need for permanent infrastructure. In dynamic networks like MANETs, routing procedures enhance the overall appearance of the network by ensuring Quality of Service (QoS). A routing protocol may use a composite routing measure to determine the best path for transferring data. Optimal location-based routing for MANETs based on energy-awareness is presented in this paper. Optimal routes are selected using this fast algorithm. Particle swarm optimization (PSO) is used instead of location-aided routing to select the normal data transmission route. Last but not least, the network is tested by simulating its packet delivery ratio, its energy level, its delay, and its overhead.

关键词： Scalability Transportation Quality of service Routing Particle measurements Routing protocols Real-time systems Delays Security Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

Non-invasive Feedback for Prosthetic Arms: A Conceptual Design of a Wearable Haptic Armband

Non-invasive Feedback for Prosthetic Arms: A Conceptual Desi...

引用

IEEE/ASME (AIM) International Conference on Advanced Intelligent Mechatronics

作者： Sudhir Solomon Zhuwawu Ahmed B. Zaki Mahmoud El-Samanty Victor Parque Haitham El-Hussieny Department of Mechatronics and Robotics Engineering Egypt-Japan University of Science and Technology Alexandria Egypt Department of Computer Science and Information Technology (CSIT) Egypt-Japan University of Science and Technology Alexandria Egypt Department of Modern Mechanical Engineering Waseda University Tokyo Japan

One of the main challenges users of prosthetic hands face is the lack of haptic feedback, which can make it difficult for them to accurately perceive the shape, texture, and other characteristics of objects they are touching, resulting in heavy reliance on visual feedback. This can limit the user’s ability to manipulate objects and interact with their environment effectively. In this research, we present a conceptual design of a mechanotactile haptic armband that has five fingers, each with two segments to provide different haptic profiles. The goal of this device is to provide haptic feedback to users of prosthetic hands, allowing them to experience a sense of touch and to more accurately perceive the shape, texture, and other characteristics of objects they are touching. To control the haptic armband, we have developed a control technique based on fuzzy logic, which maps the force sensed from a soft sensor to a force applied to the armband. Our results show that the haptic armband has the potential to improve the functionality and performance of prosthetic arms, enabling users to interact with their environment.

关键词：

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：