检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Xu, Ancheng Yang, Di Li, Renhao Zhu, Jingwei Tan, Minghuan Yang, Min Qiu, Wanxin Ma, Mingchen Wu, Haihong Li, Bingyu Sha, Feng Li, Chengming Hu, Xiping Qu, Qiang Wong, Derek F. Xu, Ruifeng Shenzhen Key Laboratory for High Performance Data Mining Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China University of Science and Technology of China China University of Macau China Shenzhen University China Shenzhen MSU-BIT University China Harbin Institute of Technology Shenzhen China

Traditional in-person psychological counseling remains primarily niche, often chosen by individuals with psychological issues, while online automated counseling offers a potential solution for those hesitant to seek help due to feelings of shame. Cognitive Behavioral Therapy (CBT) is an essential and widely used approach in psychological counseling. The advent of large language models (LLMs) and agent technology enables automatic CBT diagnosis and treatment. However, current LLM-based CBT systems use agents with a fixed structure, limiting their self-optimization capabilities, or providing hollow, unhelpful suggestions due to redundant response patterns. In this work, we utilize Quora-like1 and YiXinLi2 single-round consultation models to build a general agent framework that generates high-quality responses for single-turn psychological consultation scenarios. We use a bilingual dataset to evaluate the quality of single-response consultations generated by each framework. Then, we incorporate dynamic routing and supervisory mechanisms inspired by real psychological counseling to construct a CBT-oriented autonomous multi-agent framework, demonstrating its general applicability. Experimental results indicate that AutoCBT can provide higher-quality automated psychological counseling services. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Bio-Inspired Visual Neural Network for Moving Pedestrian Detection

SSRN

引用

SSRN 2023年

作者： Zhao, Qingqing Dai, Kunyu Hu, Bin Yang, Kai State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China College of Computer Science and Technology Guizhou University Guiyang550025 China Department of Information Engineering Guizhou Communications Polytechnic Guiyang550025 China

Reliably detecting pedestrian objects is crucial for building advanced intelligent surveillance systems in the future. In natural environments, traditional pedestrian detection methods are challenged by the irregular features of pedestrian objects in the field of view, such as varying scales, postures, and positions. Inspired by the mammalian visual layered structures and invariant object recognition mechanisms in biological vision systems, a novel feedforward visual neural network is investigated to detect moving pedestrian objects. The proposed model consists of two neural parts: the presynaptic and postsynaptic networks. The former captures visual signals, representing low-level features of a moving object, based on the significant convex and concave regions of the object’s contour;the latter processes these captured signals to form an invariant representation on behalf of a moving object, utilizing the invariant object recognition with sparse representation of biological recognition mechanism. Experimentally, the effectiveness and reliability of the proposed model are sufficiently verified by pedestrian videos in different realistic scenes, and comparative experimental results demonstrate that it outperforms existing state-of-the-art models. This research is a critical step towards the construction of an artificial vision system for pedestrian object perception. © 2023, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Effect of Ni Interlayer on Cavitation Erosion Resistance of NiTi Cladding by Tungsten Inert Gas(TIG)Surfacing Process

引用

Acta Metallurgica Sinica(English Letters) 2020年第3期33卷 415-424页

作者： Zhen-Ping Shi Zheng-Bin Wang Ji-Qiang Wang Yan-Xin Qiao Huai-Ning Chen Tian-Ying Xiong Yu-Gui Zheng CAS Key Laboratory of Nuclear Materials and Safety Assessment Institute of Metal ResearchChinese Academy of SciencesShenyang 110016China School of Materials Science and Engineering University of Science and Technology of ChinaShenyang 110016China School of Materials Science and Engineering Jiangsu University of Science and TechnologyZhenjiang 212003China

The NiTi cladding with/without Ni interlayer was prepared on stainless steel(SS) by tungsten inert gas(TIG) surfacing process,aiming at achieving good cavitation erosion *** ranking according to the cavitation erosion resistance is NiTi plate> NiTi-Ni-TIG cladding> NiTi-TIG cladding> *** better cavitation erosion resistance of NiTi-TIG and NiTi-Ni-TIG claddings than SS substrate is due to their higher micro-hardness and ***,the existence of Ni interlayer can decrease the amount of brittle intermetallic compounds,such as Fe2 Ti,and inhibit the crack generation,which results in the higher cavitation erosion resistance of NiTi-Ni-TIG compared with NiTi-TIG ***,the cavitation erosion resistance of NiTi cladding prepared by TIG surfacing process can be improved by employing Ni interlayer.

关键词： Cavitation erosion NiTi Cladding Tungsten inert gas surfacing process Ni interlayer

来源：评论

学校读者我要写书评

暂无评论

Jointly Part-of-Speech Tagging and Semantic Role Labeling Using Auxiliary Deep Neural Network Model

引用

Computers, Materials & Continua 2020年第10期65卷 529-541页

作者： Yatian Shen Yubo Mai Xiajiong Shen Wenke Ding Mengjiao Guo School of Computer Science and Engineering Southeast UniversityNanjing210000China Henan Key Laboratory of Big Data Analysis and Processing Henan UniversityKaifeng475000China Swinburne Data Science Research Institute Swinburne University of TechnologyVictoria3122Australia

Previous studies have shown that there is potential semantic dependency between part-of-speech and semantic *** the same time,the predicate-argument structure in a sentence is important information for semantic role labeling *** this work,we introduce the auxiliary deep neural network model,which models semantic dependency between part-of-speech and semantic roles and incorporates the information of predicate-argument into semantic role *** on the framework of joint learning,part-of-speech tagging is used as an auxiliary task to improve the result of the semantic role *** addition,we introduce the argument recognition layer in the training process of the main task-semantic role labeling,so the argument-related structural information selected by the predicate through the attention mechanism is used to assist the main *** the model makes full use of the semantic dependency between part-of-speech and semantic roles and the structural information of predicate-argument,our model achieved the F1 value of 89.0%on the WSJ test set of CoNLL2005,which is superior to existing state-of-the-art model about 0.8%.

关键词： Part-of-speech tagging semantic role labeling multi-task learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Particle YOLO Detector for Urine Sediment Detection 4th

An Efficient Particle YOLO Detector for Urine Sediment Dete...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Chen, Zejian Hu, Rong Chen, Fukun Fan, Haoyi Ching, Fum Yew Li, Zuoyong Su, Shimei Fujian Provincial Key Laboratory of Big Data Mining and Applications School of Computer Science and Mathematics Fujian University of Technology Fujian Fuzhou350118 China School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou450001 China School of Computer Sciences Universiti Sains Malaysia Penang11800 Malaysia Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fujian Fuzhou350121 China School of Electrical Engineering Zhengzhou University Henan Zhengzhou450001 China

ISBN: (纸本)9783031201011

Urine sediment detection is an essential aid in assessing kidney health. Traditional machine learning approaches treat urine sediment particle detection as an image classification task, segmenting particles for detection based on information such as edges or thresholds. However, the segmentation of sediment particles is complex due to the low contrast and weak edge characteristics of urine sediment images. In this paper, we consider urine sediment particle detection as a object detection task and propose the YOLOv5s-CBL, a detector dedicated to particle detection. Specifically, to mitigate the impact of background noise on detection accuracy, we inherit CBAM on the YOLOv5s model to help the network filter useless noise information and find regions of interest to extract target features. Then, we expand the original three-scale feature layer to improve the sensitivity of the model to larger-scale target sediment particles. Finally, we use the BiFPN structure instead of the original PANet combined with the FPN structure, which can more effectively fuse multiple different scales of information to improve the detection performance of the model. We compared state-of-the-art methods on two real-world datasets, and the experimental results demonstrated the effectiveness of YOLOv5s-CBL. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Drone-Assisted Behavior Recognition via key Frame Extraction for Efficient 5G Communication

Drone-Assisted Behavior Recognition via Key Frame Extraction...

引用

IEEE Conference on Computer Communications Workshops, INFOCOM Wksps

作者： Hui Li Tongao Ge Ruidi Ma Ying Guo Guowei Zhao Jiaming Pei Lukun Wang Lingwei Xu Qingdao University of Science and Technology Qingdao China State Oceanic Administration of China Qingdao China University of Sydney Sydney Australia Shandong University of Science and Technology Qingdao China Fujian Key Laboratory of Big Data Application and Intellectualization for Tea Industry Wuyishan China

Video behavior recognition based on drone + 5G technology has important research value in public security, intelligent transportation, telemetry and remote sensing, etc. However, the high redundancy of videos taken by drones leads to a large amount of calculation for its auxiliary behavior recognition algorithm, the current drone platform has limited computational power and cannot process data well. Therefore, we propose drone-assisted behavior recognition via key frame extraction based on AFCN, V-Stream and S-Stream (AFVS) for efficient 5G communication. Firstly, a key frame extraction algorithm of full convolutional Network and attention mechanism, named AFCN is proposed to quickly extract important information from drone video. Secondly, VS-Stream with dual stream architecture is designed to process both video stream and skeleton stream. In the video stream, we designed the fast and slow path network to obtain the deep features that affect the target behavior, finally achieve high-accuracy behavior recognition. Our experiment results demonstrate that AFVS solves the defects of the drone-assisted behavior recognition algorithm in natural scenes, and greatly improves its performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identifying functional evolution processes of cancer according to regression residuals network

Identifying functional evolution processes of cancer accordi...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Cheny, Bolin Yang, Manting Shang, Xuequn Northwestern Polytechnical University School of Computer Science Xi'an China Key Laboratory of Big Data Storage and Management Ministry of Industry and Information Technology Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9781665401265

The occurrence and development of cancer is a complex biological process, which usually requires further research by constructing a network. The existing methods of constructing networks are usually based on similarity to construct co-expression networks for analysis, but this similarity-based method usually ignores the data whose expression level increases or decreases at the same time in different groups. Gene pairs may also be related to the evolution of cancer, and that may cause part of the information to be lost. Therefore, we propose a new method of constructing a network based on regression residuals. Then, the module is identified based on the regression residual network according to different stages of cancer. A module network between cancer stages is obtained through the similarity between the modules. Finally, based on the size and density of the subnets in the modular network, enjoy the screening, and finally selected 3 subnets for functional analysis and Veen diagram analysis, and found some biological functions and genes that have been confirmed to be related to cancer. © 2021 IEEE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Ray computational ghost imaging based on rotational modulation method

arXiv

引用

arXiv 2023年

作者： Zhou, Zhi Li, Sangang Liao, Shan Gong, Sirun Su, Rongrong Zhao, Chuxiang Yang, Li Liu, Qi Yan, Yucheng Liu, Mingzhe Cheng, Yi College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China Applied Nuclear Technology in Geosciences Key Laboratory of Sichuan Province Chengdu University of Technology Chengdu610059 China Institute of Plasma Physics Hefei Institutes of Physical Science Chinese Academy of Science Hefei230031 China Sichuan University of Science and Engineering Zigong643000 China The Engineering & Technical College of Chengdu University of Technology Leshan614000 China

The CGI (CGI) has the potential of low cost, low dose, and high resolution, which is very attractive for the development of radiation imaging field. However, many sub-coding plates must be used in the modulation process, which greatly affects the development of CGI technology. In order to reduce the coding plates, we refer to the rotation method of computed tomography (CT), then propose a novel CGI method based on rotational modulation method of a single-column striped coding plate. This method utilizes the spatial variation of a single sub-coding plate (rotation) to realize multiple modulation of the ray field and improves the utilization rate of a single sub-coding plate. However, for this rotation scheme of CGI, the traditional binary modulation matrix is no longer applicable. To obtain the system matrix of the rotated striped coding plate, an area model based on beam boundaries is established. Subsequently, numerical and Monte Carlo simulations were conducted. The results reveal that our scheme enables high-quality imaging of N×N resolution objects using only N sub-coding plates, under both full-sampling and under-sampling scenarios. Moreover, our scheme demonstrates superiority over the Hadamard scheme in both imaging quality and the number of required sub-coding plates, whether in scenarios of full-sampling or under-sampling. Finally, an α ray imaging platform was established to further demonstrate the feasibility of the rotational modulation method. By employing our scheme, a mere 8 sub-coding plates were employed to achieve CGI of the radiation source intensity distribution, achieving a resolution of 8×8. Therefore, the novel ray CGI based on rotational modulation method can achieve high-quality imaging effect with fewer sub-coding plates, which has important practical value and research significance for promoting single-pixel radiation imaging technology. © 2023, CC BY.

关键词： Rotation

来源：评论

学校读者我要写书评

暂无评论

A Microstructural Study of Ductile Martensitic Interface in a Multilayered Steel Composite

SSRN

引用

SSRN 2024年

作者： Xu, Chi Yang, Weitao Ma, Yixing Yang, Qi Wang, Kuaishe Key Laboratory of Beam Technology of Ministry of Education College of Nuclear Science and Technology Beijing Normal University Beijing100875 China Shanghai Research Institute of Materials Co. Ltd Shanghai200437 China Shanghai Key Laboratory of Engineering Materials Application and Evaluation Shanghai200437 China Institute of Radiation Technology Beijing Academy of Science and Technology Beijing100875 China School of Metallurgical Engineering National and Local Joint Engineering Research Center for Functional Materials Processing Xi’an University of Architecture and Technology Xi’an710055 China

A three-layered TWIP/IF/TWIP composite steel was fabricated through hot-rolling and tensile-tested at room temperature. The microstructures of the TWIP/IF interface before and after the deformation were characterized with transmission electron microscopy, electron-probe micro-analyzer and nano-indentation tests in detail. The pre-deformation interface is compact and shows two different transition zones. Lath martensites are found on the TWIP steel side, while a high density of deformation structures with carbide precipitates are present on the IF steel side. A spiking increase of hardness around the interface is identified due to the presence of the martensites. The martensitic transformation is related with the diffusion of Mn, C etc. alloying elements through the interface during the hot-rolling process, and a highly asymmetric C distribution through the interface is identified. Severe deformation structures are formed after the tensile deformation, where parallel deformation bands and ω-cementite phases are identified on the TWIP steel side, and fine-grained cell structures are formed on the IF steel side. The martensites have been plastic deformed through a large strain (~55%) without crack formation, which present a microstructure close to those of ductile deformations with a high density of dislocation tangles and deformation bands. The extraordinary high ductility of the martensites and the composite steel is attributed to the functioning of the interface structure which effectively balances the strain transfers on both sides of it. © 2024, The Authors. All rights reserved.

关键词： Martensitic transformations

来源：评论

学校读者我要写书评

暂无评论

Short-term traffic flow prediction based on BAS-VMD-CEEMDAN and IWOA-RF

Short-term traffic flow prediction based on BAS-VMD-CEEMDAN ...

引用

Information Systems and Computing technology (ISCTech), International Conference on

作者： Jia Tian Deyong Wang Yanyun Fn Xueyi Zhao Jian Fang Wenxi Shi School of Information Science and Engineering Xinjiang University Urumqi China Key Laboratory of Big Data of Xinjiang Social Security Risk Prevention and Control Xinjiang Lianhaichuangzhi Information Technology Co. Ltd Urumqi China Beijing Academy of Science and Technology Beijing China

Short-term traffic flow forecasting is crucial for intelligent traffic management. In view of the non-linear and random nature of short-term traffic flow, a prediction model based on BAS-VMD-CEEMDAN and IWOA-RF is proposed. Firstly, the parameters of the VMD, namely the modal number (K) and the value of the quadratic penalty term (α), are optimized using the BAS algorithm, and then the traffic flow is decomposed to obtain several VMF components and one RES component, which extracts the smooth information of the traffic flow. Subsequently, the RES component is decomposed using the decomposition completeness of CEEMDAN to obtain several IMF components, refining the complex information of the RES component. Then, the RF model is constructed according to the characteristics of each component, and then the parameters of RF models are optimized using IWOA. Finally, overlay the predictions of each component superimposed to obtain the final predictions. Experimental results show that the short-term traffic flow forecasting model basedon BAS-VMD-CEEMDAN-IWOA-RF has a high accuracy compared to other decomposition models.

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：