检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Robotics and Biomimetics, ROBIO 2024

作者： Lan, Tianbo Ding, Jiang Li, Jingyu Xie, Fengran He, Kai Zuo, Qiyang School of Mechanical Engineering Guangxi University Guangxi Key Laboratory of Manufacturing System and Advanced Manufacturing Technology Nanning530004 China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Guangxi University State Key Laboratory of Featured Metal Materials and Life-cycle Safety for Composite Structures Nanning530004 China School of Artificial Intelligence Shenzhen Polytechnic University Shenzhen518055 China

ISBN: (纸本)9781665481090

This paper presents a novel biomimetic rudder-controlled autonomous underwater vehicle (BRCAUV) that is capable of operating at all speed range (i.e. including high, medium, low, and even zero speeds) for both wide-area cruising and localized fine observation tasks. This AUV integrates a top rudder, a propeller, and two-degree-of-freedom (DOF) biomimetic rudder wings on both sides of the aft section, enabling it to perform various tasks in a single underwater operation. These tasks include wide-area cruising at medium to high speeds and fine observation at low and even zero speeds. The prototype is equipped with a propeller, a biomimetic dorsal fin, two pectoral fins(i.e. two-DOF biomimetic rudder wings), and a buoyancy regulation system. At medium to high speeds, the AUV utilizes a combination of the propeller and pectoral fin movements for ascent and descent. At low or zero speeds, the biomimetic pectoral fins are used for complex maneuvers such as buoyancy adjustment, roll, and pitch. This paper develops a dynamic model of the pectoral fins based on quasi-steady theory, elucidating the principles of low-speed steering. Experimental were carried out and the results validate the prototype's low-speed steering capabilities, so that new approaches were presented to enhance the maneuverability, multifunctionality, and practicality for underwater vehicles. © 2024 IEEE.

关键词： Buoyancy

来源：评论

学校读者我要写书评

暂无评论

Polarimetric CSAR Image Quality Enhancement Using Joint Sub-aperture Processing 7

Polarimetric CSAR Image Quality Enhancement Using Joint Sub-...

引用

7th International Conference on Signal and Image Processing, ICSIP 2022

作者： Zheng, Yiying Cui, Xingchao Wu, Guoqing Chen, Siwei National University of Defense Technology The State Key Lab. of Complex Electromagnetic Environ. Effects on Electronics and Information System Changsha China

ISBN: (数字)9781665495639

ISBN: (纸本)9781665495639

Polarimetric circular synthetic aperture radar (CSAR) can obtain the 360° full-azimuth polarization information of target. Due to the anisotropy of most manmade targets, there are great differences in the polarization scattering characteristics at different observation angles. However, full-aperture processing is the coherent accumulation imaging of the full-azimuth polarimetric data directly, which may result in the failure of obtaining the target's polarization characteristics at each azimuth. Focus on this issue, a polarimetric CSAR imaging method using joint sub-aperture processing is proposed. The proposed method mainly contains three steps. Firstly, the polarimetric data is divided into multiple sub-aperture data since manmade targets usually exhibit scattering anisotropic properly. Then, the sub-aperture images are obtained using the back projection (BP) algorithm. Finally, the joint processing image is obtained via combining the maximum SPAN value among all sub-aperture images. The effectiveness of the proposed method is validated using the simulated data of civilian vehicle. Compared with the full-aperture images, the sub-aperture images achieve better image contrast and lower image entropy. In this vein, the image quality of the polarimetric CSAR from the proposed method is enhanced. © 2022 IEEE.

关键词： Synthetic aperture radar

来源：评论

学校读者我要写书评

暂无评论

Interpretable Deep Learning Model for Identifying the Immediate Risk of Myocardial Infarction Complications 9

Interpretable Deep Learning Model for Identifying the Immedi...

引用

9th International Conference on Fuzzy systems and Data Mining, FSDM 2023

作者： Wang, Mengxiao Jin, Yanrui Li, Zhiyuan Wei, Xiaoyang Liu, Chengliang Yang, Xiaoxue State Key Laboratory of Mechanical System and Vibration School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China MoE Key Lab of Artificial Intelligence Ai Institute Shanghai Jiao Tong University Shanghai200240 China Shanghai University of Finance and Economics Shanghai200433 China

ISBN: (纸本)9781643684703

Electronic health records (EHR) encompass extensive personal information, diagnostic records, and medical history, enabling the prediction of disease occurrence and mortality risk. The objective of this study is to predict myocardial infarction complications and assess the risk of death by comparing the performance of various deep learning models and traditional machine learning approaches. The findings demonstrate similar performance between two kinds of models in predicting complication. The DeepFM model is commonly employed for Click-through rate (CTR) prediction. To the best of our knowledge, this is the first application of the DeepFM model to the EHR domain, and we have demonstrated its exceptional predictive performance, achieving the accuracy of 93.95%. Moreover, we further classify samples into low, intermediate, and high- risk categories with high confidence. To comprehend these results, we conduct an interpretability analysis of the models' predictions employing SHAP values. This analysis involves ranking the significant features, and summarizing ECG-related features, which hold clinical decision-making revelance for clinicians. © 2023 The authors and IOS Press.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Pulse Signal Denoising Method Based on Frequency Domain Wavelet Transform

Pulse Signal Denoising Method Based on Frequency Domain Wave...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Liu, Zhao Ruan, Guangxin Liu, Zheng National University of Defense Technology State Key Lab. of Complex Electromagnetic Environment Effects on Electronics and Information System College of Electronic Science and Technology Changsha China

ISBN: (纸本)9781665452366

Bandpass filtering and time-domain wavelet threshold denoising methods do not perform well in pulse signal denoising, which are not effective for Specific Emitter Identification (SEI). Base on this problem, we propose a frequency-domain wavelet threshold denoising method, and improve the threshold estimation method as well as threshold function. Simulation results show that the proposed method is more superior than traditional methods in restoring the envelope and instantaneous frequency of the single-frequency pulse signals, which proves that our method has the potential to improve the accuracy of SEI. © 2022 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Automated Design of Complex Analog Circuits with Multiagent based Reinforcement Learning

Automated Design of Complex Analog Circuits with Multiagent ...

引用

Design Automation Conference

作者： Jinxin Zhang Jiarui Bao Zhangcheng Huang Xuan Zeng Ye Lu State Key Lab. of ASIC & System School of Information Science and Technology Frontier Institute of Chip and System State Key Lab. of ASIC & System Microelectronics Department Fudan University Shanghai China

Despite the effort of analog circuit design automation, currently complex analog circuit design still requires extensive manual iterations, making it labor intensive and time-consuming. Recently, reinforcement learning (RL) algorithms have been demonstrated successfully for the analog circuit design optimization. However, a robust and highly efficient RL method to design analog circuits with complex design space has not been fully explored yet. In this work, inspired by multiagent planning theory as well as human expert design practice, we propose a multiagent based RL (MA-RL) framework to tackle this issue. Particularly, we (i) partition the complex analog circuits into several sub-blocks based on topology information and effectively reduce the complexity of design search space; (ii) leverage MA-RL for the circuit optimization, where each agent corresponds to a single sub-block, and the interactions between agents delicately mimic the best design tradeoffs between circuit sub-blocks by human experts; (iii) introduce the multiagent twin-delayed techniques to further boost training stability and accomplish higher performances. Experiments on two different analog circuit topologies and knowledge transfers between two technology nodes are demonstrated. It’s shown that MA-RL framework can achieve the best FoM for complex analog circuits design. This work shines the light for future large scale analog circuit system design automation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recognition of Continuous Phase Modulation Signals Based on Synchrosqueezing Wavelet Transform

Recognition of Continuous Phase Modulation Signals Based on ...

引用

2022 International Applied Computational Electromagnetics Society Symposium, ACES-China 2022

作者： Ruan, Guangxin Zhao, Liu Liu, Zheng College of Electronic Science and Technology National University of Defense Technology State Key Lab. of Complex Electromagnetic Environment Effects on Electronics and Information System Changsha China

ISBN: (纸本)9781665452366

We present a new algorithm that can solve the problem of recognition of continuous phase modulation (CPM) signals to phase shift keying (PSK) signals. The algorithm uses synchrosqueezing wavelet transform (SWT) to extract the instantaneous frequency (IF) of the signal. On this basis, a recognition characteristic parameter is proposed. This paper verifies the parameter is suitable for PSK and CPM signals with different modulation parameters. Finally, the simulation shows that the algorithm can fully recognize CPM signals to BPSK and QPSK signals when signal-to-noise ratio (snr) is above 6dB. Compared with the existing algorithms, the algorithm proposed in this paper has a higher recognition rate in the low snr environment. © 2022 IEEE.

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Rethinking the membrane dynamics and optimization objectives of spiking neural networks 24

Rethinking the membrane dynamics and optimization objectives...

引用

Proceedings of the 38th International Conference on Neural Information Processing systems

作者： Hangchi Shen Qian Zheng Huamin Wang Gang Pan College of Artificial Intelligence Southwest University and Chongqing Key Laboratory of Brain Inspired Computing and Intelligent Chips The State Key Lab of Brain-Machine Intelligence and College of Computer Science and Technology Zhejiang University

ISBN: (纸本)9798331314385

Despite spiking neural networks (SNNs) have demonstrated notable energy efficiency across various fields, the limited firing patterns of spiking neurons within fixed time steps restrict the expression of information, which impedes further improvement of SNN performance. In addition, current implementations of SNNs typically consider the firing rate or average membrane potential of the last layer as the output, lacking exploration of other possibilities. In this paper, we identify that the limited spike patterns of spiking neurons stem from the initial membrane potential (IMP), which is set to 0. By adjusting the IMP, the spiking neurons can generate additional firing patterns and pattern mappings. Furthermore, we find that in static tasks, the accuracy of SNNs at each time step increases as the membrane potential evolves from zero. This observation inspires us to propose a learnable IMP, which can accelerate the evolution of membrane potential and enables higher performance within a limited number of time steps. Additionally, we introduce the last time step (LTS) approach to accelerate convergence in static tasks, and we propose a label smooth temporal efficient training (TET) loss to mitigate the conflicts between optimization objective and regularization term in the vanilla TET. Our methods improve the accuracy by 4.05% on ImageNet compared to baseline and achieve state-of-the-art performance of 87.80% on CIFAR10-DVS and 87.86% on N-Caltech101. The code is available at https://***/StephenTaylor1998/IMP-SNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MOLECULE GENERATION FOR TARGET PROTEIN BINDING WITH STRUCTURAL MOTIFS 11

MOLECULE GENERATION FOR TARGET PROTEIN BINDING WITH STRUCTUR...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Zhang, Zaixi Min, Yaosen Zheng, Shuxin Liu, Qi Anhui Province Key Lab of Big Data Analysis and Application School of Computer Science and Technology University of Science and Technology of China China State Key Laboratory of Cognitive Intelligence Anhui Hefei China Institute of Interdisciplinary Information Sciences Tsinghua University China Microsoft Research United States

Designing ligand molecules that bind to specific protein binding sites is a fundamental problem in structure-based drug design. Although deep generative models and geometric deep learning have made great progress in drug design, existing works either sample in the 2D graph space or fail to generate valid molecules with realistic substructures. To tackle these problems, we propose a Fragment-based LigAnd Generation framework (FLAG), to generate 3D molecules with valid and realistic substructures fragment-by-fragment. In FLAG, a motif vocabulary is constructed by extracting common molecular fragments (i.e., motif) in the dataset. At each generation step, a 3D graph neural network is first employed to encode the intermediate context information. Then, our model selects the focal motif, predicts the next motif type, and attaches the new motif. The bond lengths/angles can be quickly and accurately determined by cheminformatics tools. Finally, the molecular geometry is further adjusted according to the predicted rotation angle and the structure refinement. Our model not only achieves competitive performances on conventional metrics such as binding affinity, QED, and SA, but also outperforms baselines by a large margin in generating molecules with realistic substructures. Our code is publicly available at https://***/zaixizhang/FLAG. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Logical Negation Augmenting and Debiasing for Prompt-based Methods

arXiv

引用

arXiv 2024年

作者： Li, Yitian Tian, Jidong He, Hao Jin, Yaohui MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China State Key Lab of Advanced Optical Communication System and Network Shanghai Jiao Tong University China

Prompt-based methods have gained increasing attention on NLP and shown validity on many downstream tasks. Many works have focused on mining these methods' potential for knowledge extraction, but few explore their ability to make logical reasoning. In this work, we focus on the effectiveness of the prompt-based methods on first-order logical reasoning and find that the bottleneck lies in logical negation. Based on our analysis, logical negation tends to result in spurious correlations to negative answers, while propositions without logical negation correlate to positive answers. To solve the problem, we propose a simple but effective method, Negation Augmenting and Negation Debiasing (NAND), which introduces negative propositions to prompt-based methods without updating parameters. Specifically, these negative propositions can counteract spurious correlations by providing "not" for all instances so that models cannot make decisions only by whether expressions contain a logical negation. Experiments on three datasets show that NAND not only solves the problem of calibrating logical negation but also significantly enhances prompt-based methods of logical reasoning without model retraining. Copyright © 2024, The Authors. All rights reserved.

关键词： Formal logic

来源：评论

学校读者我要写书评

暂无评论

Do LLMs Overcome Shortcut Learning? An Evaluation of Shortcut Challenges in Large Language Models

arXiv

引用

arXiv 2024年

作者： Yuan, Yu Zhao, Lili Zhang, Kai Zheng, Guangting Liu, Qi State Key Lab of Cognitive Intelligence University of Science and Technology of China China School of Computer Science and Technology University of Science and Technology of China China

Large Language Models (LLMs) have shown remarkable capabilities in various natural language processing tasks. However, LLMs may rely on dataset biases as shortcuts for prediction, which can significantly impair their robustness and generalization capabilities. This paper presents Shortcut Suite, a comprehensive test suite designed to evaluate the impact of shortcuts on LLMs’ performance, incorporating six shortcut types, five evaluation metrics, and four prompting strategies. Our extensive experiments yield several key findings: 1) LLMs demonstrate varying reliance on shortcuts for downstream tasks, significantly impairing their performance. 2) Larger LLMs are more likely to utilize shortcuts under zero-shot and few-shot in-context learning prompts. 3) Chain-of-thought prompting notably reduces shortcut reliance and outperforms other prompting strategies, while few-shot prompts generally underperform compared to zero-shot prompts. 4) LLMs often exhibit overconfidence in their predictions, especially when dealing with datasets that contain shortcuts. 5) LLMs generally have a lower explanation quality in shortcut-laden datasets, with errors falling into three types: distraction, disguised comprehension, and logical fallacy. Our findings offer new insights for evaluating robustness and generalization in LLMs and suggest potential directions for mitigating the reliance on shortcuts. The code is available at https://***/yyhappier/***. Copyright © 2024, The Authors. All rights reserved.

关键词： Zero-shot learning

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：