检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Zhang, Xiongtao Yin, Zezong Jiang, Yunliang Jiang, Yizhang Sun, Danfeng Liu, Yong School of Information Engineering Huzhou University Huzhou31300 China Zhejiang Key Laboratory of Intelligent Education Technology and Application Zhejiang Normal University Jinhua321004 China School of Computer Science and Technology Zhejiang Normal University Jinhua321004 China School of Artificial Intelligence and Computer Science Jiangnan University Wuxi 214122 China Key Laboratory of Image Processing and Intelligent Control Huazhong University of Science and Technology Ministry of Education Wuhan430074 China School of Computer Science Hangzhou Dianzi University Hangzhou310018 China College of Control Science and Engineering Zhejiang University Hangzhou310027 China

In order to enpower the hight performance as well as interpretability of low-order TSK fuzzy classifier, a born-again TSK fuzzy classier embedded with decoupled fuzzy dark knowledge distillation called HTSK-LLM-DKD is proposed in this study. HTSK-LLM DKD achieves the following distinctive characteristics: 1) It takes high-order TSK as teacher model and low-order TSK fuzzy classifier as student model, and leverages the proposed Least Learning Machine based Decoupling Knowledge Distillation to distill the fuzzy dark knowledge from high-order TSK fuzzy classifier to low-order TSK fuzzy classifier, which resulting in low-order TSK fuzzy classifier endowed with enhanced performance surpassing or at least comparable to high-order TSK fuzzy classifier;specifically 2) The Negative Euclidean distance between the output of teacher model and each class is employed to obtain the teacher logits, and then it computes teacher/student soft labels by the softmax function with distilling temperature parameter;3) By reformulating the Kullback Leibler divergence, it decouples fuzzy dark knowledge into target class knowledge and non-target class knowledge, and transfers them to student model, which taking HTSK-LLM-DKD with outstanding performance and relatively fast running speed. Extensive experiment results on UCI benchmarking datasets and real-world dataset Cleveland Heart Disease demonstrate the effectiveness of the proposed HTSK-LLM-DKD. © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Weakly Supervised Text-based Person Re-Identification

Weakly Supervised Text-based Person Re-Identification

引用

International Conference on Computer Vision (ICCV)

作者： Shizhen Zhao Changxin Gao Yuanjie Shao Wei-Shi Zheng Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Sun Yat-sen University

ISBN: (纸本)9781665428132

The conventional text-based person re-identification methods heavily rely on identity annotations. However, this labeling process is costly and time-consuming. In this paper, we consider a more practical setting called weakly supervised text-based person re-identification, where only the text-image pairs are available without the requirement of annotating identities during the training phase. To this end, we propose a Cross-Modal Mutual Training (CMMT) framework. Specifically, to alleviate the intra-class variations, a clustering method is utilized to generate pseudo labels for both visual and textual instances. To further re-fine the clustering results, CMMT provides a Mutual Pseudo Label Refinement module, which leverages the clustering results in one modality to refine that in the other modality constrained by the text-image pairwise relationship. Mean-while, CMMT introduces a Text-IoU Guided Cross-Modal Projection Matching loss to resolve the cross-modal matching ambiguity problem. A Text-IoU Guided Hard Sample Mining method is also proposed for learning discriminative textual-visual joint embeddings. We conduct extensive experiments to demonstrate the effectiveness of the proposed CMMT, and the results show that CMMT performs favorably against existing text-based person re-identification methods. Our code will be available at https://***/X-BrainLab/WS_Text-ReID.

关键词： Training Visualization Computer vision Codes Annotations Computational modeling Clustering methods

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Composite Stochastic Resonance In Enhancement Detection

SSRN

引用

SSRN 2023年

作者： Gao, Rui Jiao, Shangbin Xue, Qiongjie Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology Xi’an710048 China School of Electronic and Electrical Engineering Baoji University of Arts and Sciences Baoji721016 China

Aiming at the problem that the intermediate potential part of the traditional tristable method cannot be adjusted independently, a new composite stochastic resonance (NCSR) model is proposed by combining the Woods Saxon (WS) model and the improved piecewise bistable model. All the parameters in the new model have no coupling characteristics. Moreover, the model retains the characteristics of the independent parameters of WS model and the improved piecewise model has no output saturation. Understable noise environment, the new model is used to detect periodic signal and aperiodic signal, the detection results indicate that the new model has better noise utilization and better detection effect. Finally, through image denoising experiments, the output signal-to-noise ratio (SNR) and correlation number of NCSR method is higher than that of other commonly used linear denoising methods and classical SR methods under the same conditions, the effectiveness of the new model is verified. © 2023, The Authors. All rights reserved.

关键词： image denoising

来源：评论

学校读者我要写书评

暂无评论

OadTR: Online Action Detection with Transformers

OadTR: Online Action Detection with Transformers

引用

International Conference on Computer Vision (ICCV)

作者： Xiang Wang Shiwei Zhang Zhiwu Qing Yuanjie Shao Zhengrong Zuo Changxin Gao Nong Sang Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Alibaba Group China

ISBN: (纸本)9781665428132

Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In this paper, we propose a new encoder-decoder framework based on Transformers, named OadTR, to tackle these problems. The encoder attached with a task token aims to capture the relationships and global inter-actions between historical observations. The decoder extracts auxiliary information by aggregating anticipated future clip representations. Therefore, OadTR can recognize current actions by encoding historical information and predicting future context simultaneously. We extensively evaluate the proposed OadTR on three challenging datasets: HDD, TVSeries, and THUMOS14. The experimental results show that OadTR achieves higher training and inference speeds than current RNN based approaches, and significantly outperforms the state-of-the-art methods in terms of both mAP and mcAP. Code is available at https://***/wangxiang1230/OadTR.

关键词： Training Visualization Recurrent neural networks Streaming media Transformers Encoding Spatiotemporal phenomena

来源：评论

学校读者我要写书评

暂无评论

A pushing-grasping collaborative method based on deep q-network algorithm in dual perspectives

arXiv

引用

arXiv 2021年

作者： Gang, Peng Jinhu, Liao Shangbin, Guan Key Laboratory of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Aiming at the traditional grasping method for manipulators based on 2D camera, when faced with the scene of gathering or covering, it can hardly perform well in unstructured scenes that appear as gathering and covering, for the reason that can’t recognize objects accurately in cluster scenes from a single perspective and the manipulators can’t make the environment better for grasping. In this case, a novel method of pushing-grasping collaborative based on the deep Q-network in dual perspectives is proposed in this paper. This method adopts an improved deep Q-network algorithm, with an RGB-D camera to obtain the information of objects’ RGB images and point cloud from two perspectives, and combines the pushing and grasping actions, so that the trained manipulator can make the scenes better for grasping, so that it can perform well in more complicated grasping scenes. What’s more, we improved the reward function of the deep Q-network and propose the piecewise reward function to speed up the convergence of the deep Q-network. We trained different models and tried different methods in the V-REP simulation environment, and it drew a conclusion that the method proposed in this paper converges quickly and the success rate of grasping objects in unstructured scenes raises up to 83.5%. Besides, it shows the generalization ability and well performance when novel objects appear in the scenes that the manipulator has never grasped before. Copyright © 2021, The Authors. All rights reserved.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Online Identification of Boost Converter Components with Multiple Updating RLS Algorithm

Online Identification of Boost Converter Components with Mul...

引用

Chinese control Conference (CCC)

作者： Tong Zhou Zhicheng Zhang Zhiqiang Zuo Yijing Wang Peng Li Tianjin Key Laboratory of Intelligent Unmanned Swarm Technology and System School of Electrical and Information Engineering Tianjin University Tianjin P. R. China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai P. R. China

In this paper, component parameters of the boost converter are identified online using a multiple updating recursive least squares (MURLS) algorithm. The component parameters, such as resistance, inductor inductance and capacitor capacitance, are obtained directly through the identification procedure rather than transfer function coefficients. The MURLS algorithm is applied to improve the rapidity of system identification compared to the traditional recursive least squares (RLS) algorithm, which is verified by a comparative simulation between MURLS and RLS and the simulation of a load-switching scenario.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BoostTree and BoostForest for Ensemble Learning

Research Square

引用

Research Square 2021年

作者： Zhao, Changming Wu, Dongrui Huang, Jian Yuan, Ye Zhang, Hai-Tao Peng, Ruimin Shi, Zhenhua Guo, Chenfeng Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have been widely used in biology, engineering, healthcare, etc. This article proposes BoostForest, which is an ensemble learning approach using BoostTree as base learners and can be used for both classification and regression. BoostTree constructs a tree model by gradient boosting. It achieves high randomness (diversity) by sampling its parameters randomly from a parameter pool, and selecting a subset of features randomly at node splitting. BoostForest further increases the randomness by bootstrapping the training data in constructing different BoostTrees. BoostForest outperformed four classical ensemble learning approaches (Random Forest, Extra-Trees, XGBoost and LightGBM) on 34 classification and regression datasets. Remarkably, BoostForest has only one hyper-parameter (the number of BoostTrees), which can be easily specified. Our code is publicly available, and the proposed ensemble learning framework can also be used to combine many other base learners. © 2021, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Smartphone-based colorimetric detection of formaldehyde in the air

引用

Building Simulation 2024年第11期17卷 2007-2015页

作者： Meng Yang Jin Ye Tao Yu Ying Song Hua Qian Tianyi Liu Yang Chen Junqi Wang Shi-jie Cao Cong Liu School of Energy and Environment Southeast UniversityNanjing210096China School of Energy and Power Jiangsu University of Science and TechnologyZhenjiangJiangsu212100China Wuhan Second Ship Design and Research Institute Wuhan430205China Hubei Provincial Engineering and Technology Research Center for Food Quality and Safety Test Hubei Provincial Institute for Food Supervision and TestWuhan430075China Laboratory of Image Science and Technology the School of Computer Science and EngineeringSoutheast UniversityNanjingChina Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing Southeast UniversityNanjingChina School of Cyber Science and Engineering Southeast UniversityNanjingChina Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of EducationNanjingChina School of Architecture Southeast UniversityNanjingChina Jiangsu Province Engineering Research Center of Urban Heat and Pollution Control Southeast UniversityNanjingChina Global Centre for Clean Air Research(GCARE) University of SurreyGuildfordUK

Adverse impacts of exposure to formaldehyde on human health significantly increases attention in monitoring formaldehyde concentrations in the *** formaldehyde detection methods typically rely on large and costly instruments and requires high skills of expertise,preventing it from being widely accessible to *** study introduced a novel approach utilizing smartphone-based colorimetric *** of green channel signals of digital images by a smartphone successfully capture variation of purple color of 4-amino-3-hydrazino-5-mercapto-1,2,4-triazol solution,which is proportional to formaldehyde *** is because that green and purple are complimentary color pairs.A calibration curve was established between green channel signals and formaldehyde concentrations,with a correlation coefficient of *** limit of the smartphone-based method is 0.008 mg/m^(3).Measurement errors decrease as formaldehyde concentrations increase,with median relative errors of 34%,17%,and 6%for concentration ranges of 0–0.06 mg/m^(3),0.06–0.12 mg/m^(3),and 0.12–0.35 mg/m^(3),*** method replaced scientific instrumentation with ordinary items,greatly reducing cost and operation *** would provide an opportunity to realize onsite measurements for formaldehyde by occupants themselves and increase awareness of air quality for better health protection.

关键词： indoor air quality VOC RGB color identification machine vision

来源：评论

学校读者我要写书评

暂无评论

Condition Monitoring for Railway Point Machines Based on Sound Analysis and Support Vector Machine

引用

Chinese Journal of Electronics 2020年第4期29卷 786-792页

作者： SUN Yongkui CAO Yuan XIE Guo WEN Tao School of Electronic and Information Engineering Beijing Jiaotong University National Engineering Research Center of Rail Transportation Operation and Control System Beijing Jiaotong University Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an University of Technology

Railway point machines(RPMS) are one of the key equipments in the railway system to switch different routes for the *** monitoring for RPMs is a vital measure to keep train operation safe and *** convenience and low cost into consideration, a novel intelligent condition monitoring method for RPMs based on sound analysis is ***-domain and frequency-domain features are obtained,and normalized using z-score standardization method to eliminate the influences of different *** particle swarm optimization(BPSO) is utilized to select the most significant discrimination feature *** effects of the selected optimal features are verified using Support vector machine(SVM), 1-Nearest neighbor(1 NN), Random forest(RF), and Naive Bayes(NB).Experiment results indicate SVM performs best on identification accuracy and computing cost compared with the other three *** identification accuracies on normal switching and reverse switching processes reach100% and 99.67%, respectively, indicating the feasibility of the proposed method.

关键词： Condition monitoring Sound analysis Railway point machines(RPMs) Binary particle swarm optimization(BPSO) Support vector machine(SVM)

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Active Learning for Simultaneous Emotion Classification and Regression

Multi-Task Active Learning for Simultaneous Emotion Classifi...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Xue Jiang Lubin Meng Dongrui Wu Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781665442084

Emotion recognition, which aims to identify an individual’s emotional state from the acquired physiological or body signals, is very important in affective computing. Emotions have two common representations: categorical, e.g., happy, sad, etc., and dimensional (continuous), e.g., valence, arousal and dominance. Training a good emotion classification or regression model usually requires a large number of labeled data. However, the labeling process is very difficult. As emotions are subtle and uncertain, it usually requires multiple assessors to label each emotional instance to obtain the groundtruth categorical label or dimensional values. In this paper, we propose a multi-task active learning (MTAL) framework to query the most useful samples for labeling, which enables the efficient training of an emotion classification model and multiple emotion regression models simultaneously. This is novel and challenging, as all previous research considered only emotion classification or regression alone, but not simultaneously. Experimental results on the IEMOCAP dataset demonstrated that MTAL outperformed random selection and several state-of-the-art single task active learning approaches, i.e., with the same number of labeled samples, MTAL can obtain better emotion classification and regression models simultaneously.

关键词： Training Emotion recognition Conferences Multitasking Physiology Data models Classification algorithms

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：