检索结果-内蒙古大学图书馆

Question Answering Over Knowledge Base: A Scheme for Integrating Subject and the Identified Relation to Answer Simple Questions

引用

SN Computer Science 2021年第1期2卷 25页

作者： Buzaaba, Happy Amagasa, Toshiyuki Systems and Information Engineering University of Tsukuba Tsukuba Japan Center for Computational Sciences University of Tsukuba Tsukuba Japan

Answering natural language question over a knowledge base is an important and challenging task with a wide range of application in natural language processing and information retrieval. Several existing knowledge-based question answering systems exploit complex end-to-end neural network approaches that are computationally expensive and take long to execute when training the neural network. More importantly, such an end-to-end approach makes it difficult to examine the process of query processing. In this study, we decompose the question answering problem in a three-step pipeline of entity detection, entity linking, and relation prediction, and solve each component separately. We explore basic neural network and non-neural network methods for entity detection and relation prediction plus a few heuristics for entity linking. We also introduce a method to identify ambiguity in the data and show that ambiguity in the data bounds the performance of the question answering system. The experiment on the SimpleQuestions benchmark data set shows that a combination of basic LSTMs, GRUs, and non-neural network techniques achieve reasonable performance while providing an opportunity to understand the question answering problem structure. © 2021, The Author(s).

关键词： Knowledge base Neural networks Question answering Simple questions

来源：评论

学校读者我要写书评

暂无评论

Temporal phase characterization of picosecond pulsed squeezed vacuum

Temporal phase characterization of picosecond pulsed squeeze...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Xu, Zicong Nitanai, Sho Ozeki, Yasuyuki Research Center of Advanced Science and Technology The University of Tokyo 4-6-1 Komaba Meguro-ku Tokyo153-8904 Japan Department of Electrical Engineering and Information Systems The University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan

We propose a method to measure the temporal phase of ultrashort pulsed squeezed vacuum. We verified that the temporal chirp has limited influence on pulsed squeezing level. © Optica Publishing Group 2024 © 2... 详细信息

ISBN: (纸本)9781957171395

关键词： Fiber lasers

来源：评论

学校读者我要写书评

暂无评论

DCU: Unidimensional Data Prediction with Graphical Model 6

DCU: Unidimensional Data Prediction with Graphical Model

引用

6th IEEE International Conference on Civil Aviation Safety and information Technology, ICCASIT 2024

作者： Yin, Jiazhi Xiao, Ming Shen, Binnan Liao, Xufei Aviation Safety Institute China Academy of Civil Aviation Science and Technology Beijing China Engineering and Technical Research Center of Civil Aviation Safety Analysis and Prevention of Beijing Beijing China Beijing Research Institute of Automation for Machinery Industry Co. Ltd. Beijing China Specialized Systems and Electronic Technology Engineering Division Beijing China

ISBN: (纸本)9798350389418

In view of the limited number of available models for one-dimensional data prediction tasks at present and in the past, and the underlying problems of RNN-like networks in most general models, we propose a new data prediction method. This method utilizes a two-dimensional model with a larger sampling area and more extensive branches to carry out the prediction task of one-dimensional time series data from the image level. We integrate one-dimensional data according to the time nodes and transform it into two-dimensional multi-channel images. We enhance the traditional encoding-decoding network structure by replacing part of the convolutional layers with Tokenized MLP. This modification ensures more accurate weight calculation of the model on a specific coordinate axis. Additionally, we improve the training mode of the traditional network architecture, and add a custom penalty mechanism on top of the loss function. This mechanism directly impacts the weight of the model nodes beyond the learning process, enhancing the controllability of the network training process. Through comparative experiments, our method demonstrates an 8.4 % improvement in MAE, a 7.8 % improvement in 12 fitting, and a 51.3 % improvement in test time compared with the traditional methods. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

User Models for Connected Personalized Avatars for Cultural Heritage Experiences 25

User Models for Connected Personalized Avatars for Cultural ...

引用

Adjunct Proceedings of the 33rd ACM Conference on User Modeling, Adaptation and Personalization

作者： Alan Jay Wecker Antonio Origlia Tsvi Kuflik Information Systems The University of Haifa Haifa Israel URBAN/ECO Research Center Dept. of Electrical Engineering and Information Technology Federico II University Naples Italy

来源：评论

学校读者我要写书评

暂无评论

Fault Diagnosis of Chiller Based on ALSTM-FCN

Fault Diagnosis of Chiller Based on ALSTM-FCN

引用

2024 International Conference on Artificial Intelligence and Power systems, AIPS 2024

作者： Gao, Xuejin Jiang, Yiwei Han, Huayun Faculty of Information Technology Beijing University of Technology Beijing100124 China Engineering Research Center of Ministry of Education Beijing100124 China Beijing Laboratory of Association of Metros Beijing100124 China Beijing Key Laboratory of Computational Intelligence and Intelligent Systems Beijing100124 China

ISBN: (纸本)9798350392210

Maintaining the effective operation of chillers depends heavily on prompt and precise fault diagnosis. A chiller fault diagnosis method based on attention and long and short-term memory fully convolutional neural network (ALSTM-FCN) was proposed in light of the nonlinearity of chillers' operation data and the challenge of fault diagnosis models in identifying effective features, which results in low model accuracy. First, an FCN fault diagnosis model was established according to the feature selection results, and the proposed Lastly, the attention mechanism was included to the model with the intention of emphasizing the significance of features and enhancing the accuracy of chiller problem diagnosis. Furthermore, the ASHRAE 1043-RP dataset was used to confirm the efficacy of the suggested approach. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

S3M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving

arXiv

引用

arXiv 2024年

作者： Wu, Zhiyuan Feng, Yi Liu, Chuang-Wei Yu, Fisher Chen, Qijun Fan, Rui College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China Department of Information Technology and Electrical Engineering ETH Zürich Sternwartstrasse 7 Zürich8092 Switzerland

Semantic segmentation and stereo matching are two essential components of 3D environmental perception systems for autonomous driving. Nevertheless, conventional approaches often address these two problems independently, employing separate models for each task. This approach poses practical limitations in real-world scenarios, particularly when computational resources are scarce or real-time performance is imperative. Hence, in this article, we introduce S3M-Net, a novel joint learning framework developed to perform semantic segmentation and stereo matching simultaneously. Specifically, S3M-Net shares the features extracted from RGB images between both tasks, resulting in an improved overall scene understanding capability. This feature sharing process is realized using a feature fusion adaption (FFA) module, which effectively transforms the shared features into semantic space and subsequently fuses them with the encoded disparity features. The entire joint learning framework is trained by minimizing a novel semantic consistency-guided (SCG) loss, which places emphasis on the structural consistency in both tasks. Extensive experimental results conducted on the vKITTI2 and KITTI datasets demonstrate the effectiveness of our proposed joint learning framework and its superior performance compared to other state-of-the-art single-task networks. Our project webpage is accessible at ***/S3M-Net. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Temporal phase characterization of picosecond pulsed squeezed vacuum

Temporal phase characterization of picosecond pulsed squeeze...

引用

CLEO: Science and Innovations in CLEO 2024, CLEO: S and I 2024 - Part of Conference on Lasers and Electro-Optics

关键词： Ultrahigh vacuum

来源：评论

学校读者我要写书评

暂无评论

Playing to Vision Foundation Model's Strengths in Stereo Matching

arXiv

引用

arXiv 2024年

作者： Liu, Chuang-Wei Chen, Qijun Fan, Rui The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems China Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China

Stereo matching has become a key technique for 3D environment perception in intelligent vehicles. For a considerable time, convolutional neural networks (CNNs) have remained the mainstream choice for feature extraction in this domain. Nonetheless, there is a growing consensus that the existing paradigm should evolve towards vision foundation models (VFM), particularly those developed based on vision Transformers (ViTs) and pre-trained through self-supervision on extensive, unlabeled datasets. While VFMs are adept at extracting informative, general-purpose visual features, specifically for dense prediction tasks, their performance often lacks in geometric vision tasks. This study serves as the first exploration of a viable approach for adapting VFMs to stereo matching. Our ViT adapter, referred to as ViTAS, is constructed upon three types of modules: spatial differentiation, patch attention fusion, and cross-attention. The first module initializes feature pyramids, while the latter two aggregate stereo and multi-scale contextual information into fine-grained features, respectively. ViTAStereo, which combines ViTAS with cost volume-based stereo matching back-end processes, achieves the top rank on the KITTI Stereo 2012 dataset and outperforms the second-best network StereoBase by approximately 7.9% in terms of the percentage of error pixels, with a tolerance of 3 pixels. Additional experiments across diverse scenarios further demonstrate its superior generalizability compared to all other state-of-the-art approaches. We believe this new paradigm will pave the way for the next generation of stereo matching networks. Copyright © 2024, The Authors. All rights reserved.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

RadioModRec-l: A Large Scale Radio Frequency Dataset for Automatic Modulation Recognition Research 4

RadioModRec-l: A Large Scale Radio Frequency Dataset for Aut...

引用

4th International Conference on Emerging Trends in Networks and Computer Communications, ETNCC 2024

作者： Adetiba, Emmanuel Olasina, Jamiu R. Obiyemi, Obiseye Covenant University Covenant Applied Informatics and Communication Africa Center of Excellence Dept. of Electrical and Information Engineering Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban4001 South Africa Federal Polytechnic Ilaro Dept. of Computer Engineering Ilaro Nigeria Durban University of Technology Space Science Centre Dept. of Electrical Power Engineering Durban South Africa

ISBN: (纸本)9798350353266

Access to well-curated large datasets remains a significant bottleneck in AI-based research within wireless communication. Rapid advancements in neighbouring fields, such as computer vision and natural language processing, are largely due to the availability of extensive open-access datasets. However, similar progress has not been observed in wireless communication. To address this gap, we curated a comprehensive dataset for fifteen digital modulation schemes, including 4QAM, 16QAM, 64QAM, 256QAM, 8PSK, 16PSK, 32PSK, 64PSK, 128PSK, 256PSK, CPFSK, DBPSK, DQPSK, GFSK, and GMSK. Our dataset considers Rayleigh and Rician channel models under Additive White Gaussian Noise (A WGN) with SNRs ranging from -20dB to + 20dB in 5dB increments. The data samples were converted to constellation signal images and carefully pre-processed. Named RadioModRec, this dataset provides a valuable resource for researchers to train and evaluate AI models. It is freely accessible on Kaggle, promoting further innovation in the wireless communication domain. © 2024 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Numerical Simulation of a Novel Cargo Handling Strategy: Using a Centralized Cable-Linked Dual-Multirotor System

Numerical Simulation of a Novel Cargo Handling Strategy: Usi...

引用

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

作者： Tianhua Gao Xiao Han Kohji Tomita Akiya Kamimura Graduate School of Systems and Information Engineering University of Tsukuba Japan Department of Information Technology and Human Factors Industrial Cyber-Physical Systems Research Center National Institute of Advanced Industrial Science and Technology (AIST) Japan

ISBN: (数字)9798350355369

ISBN: (纸本)9798350355376

The cable-suspended transportation using multiple UAVs has gradually gained attention in UAV logistics fields over the past decade, owing to their greater efficiency compared to a single UAV transportation with heavy manipulators. This study further developed a centralized cable-linked dual-multirotor system prototype, which is expected to handle cargo of arbitrary shape and weight, attached with two hooks for loading, transporting, and unloading. To realize this, we proposed a novel Tug-of-War (ToW) method for loading/unloading and a modeling approach for transportation that treats the cargo as a disturbance. The control algorithm of the system adopted a hybrid control strategy formed by combining the model reference adaptive nonlinear model predictive control (MRA-NMPC) and the geometric control. The numerical simulation results successfully demonstrated the performance of the dualmultirotor system, and the feasibility of the ToW method was verified.

关键词： Adaptation models Shape Transportation Prototypes Predictive models Numerical simulation Autonomous aerial vehicles

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：