检索结果-内蒙古大学图书馆

NeurDB: an AI-powered autonomous data system

science China(Information sciences) 2024年第10期67卷 129-150页

作者： Beng Chin OOI Shaofeng CAI Gang CHEN Yanyan SHEN Kian-Lee TAN Yuncheng WU Xiaokui XIAO Naili XING Cong YUE Lingze ZENG Meihui ZHANG Zhanhao ZHAO School of Computing National University of Singapore College of Computer Science and Technology Zhejiang University Department of Computer Science and Engineering Shanghai Jiao Tong University School of Information Renmin University of China School of Computer Science and Technology Beijing Institute of Technology

In the wake of rapid advancements in artificial intelligence(AI), we stand on the brink of a transformative leap in data systems. The imminent fusion of AI and DB(AI×DB) promises a new generation of data systems, which will relieve the burden on end-users across all industry sectors by featuring AI-enhanced functionalities, such as personalized and automated in-database AI-powered analytics, and selfdriving capabilities for improved system performance. In this paper, we explore the evolution of data systems with a focus on deepening the fusion of AI and DB. We present NeurDB, an AI-powered autonomous data system designed to fully embrace AI design in each major system component and provide in-database AI-powered analytics. We outline the conceptual and architectural overview of NeurDB, discuss its design choices and key components, and report its current development and future plan.

关键词： AI$\times$DB in-database AI intelligent data system

来源：评论

学校读者我要写书评

暂无评论

Preparation of excellent building materials using geopolymer instead of traditional cement

引用

Particuology 2024年第12期95卷 333-342页

作者： Yuanchuan Ren Shanqisong Huang Yan Hu Nanqi Ren Lingrui Kuang Fenghui Wu Dandan Chen Xuejun Zhu Qiang Niu College of Biological and Chemical Engineering(College of Agriculture) Panzhihua UniversityPanzhihua617000China Faculty of Environmental Science and EngineeringKunming University of Science and Technology Kunming650500China School of Environment Harbin Institute of TechnologyHarbin150090China

In order to improve the resource utilization rate of aluminum ash,high-quality building materials were prepared by replacing traditional cement with aluminum ash,and the performance of building materials under different conditions and factors was *** experimental results show that when the pressure was 300 MPa and the natural curing time was 3 days,the comprehensive performance of the brick reaches its optimum(compressive strength of 60 MPa,flexural strength of 1.3 MPa,and softening coefficient of about 0.9),far superior to other reported methods for preparing building ***-EDS,Particle size analysis and XRD confirmed that the crystal structure in aluminum ash undergoes a transformation under high-intensity mechanical pressure,forming cement-based active *** study not only obtained a new method for preparing building materials,but also further promoted the research on the resource utilization of aluminum ash,providing a new approach for the treatment and disposal of hazardous waste.

关键词： Aluminum ash Hazardous solid waste Extreme high value Densification Super building materials

来源：评论

学校读者我要写书评

暂无评论

Scale-CoT: Integrating LLM with Psychiatric Scales for Analyzing Mental Health Issues on Social Media

Scale-CoT: Integrating LLM with Psychiatric Scales for Analy...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Bichen Sun, Yixin Zi, Yuzhe Zhao, Yanyan Qin, Bing Harbin Institute of Technology School of Computer Science and Technology Harbin China

ISBN: (纸本)9798350386226

Mental health issues pose significant challenges worldwide, leading researchers to utilize computing techniques to analyze social media posts for early detection. Currently, Large Language Models (LLMs) represent advanced AI systems with exceptional language processing capabilities. However, their effectiveness depends on the use of appropriate prompts. The design of suitable prompts specifically for analyzing mental health issues remains underexplored. Drawing inspiration from psychiatrists who use psychiatric scales to assess mental health, we have developed scale-based chains of thought (Scale-CoT) prompts. These not only enhance the LLMs' ability to detect mental health issues but also increase clarity and explainability by integrating professional scales. Furthermore, we demonstrate that the knowledge generated by LLMs can be effectively transferred to smaller models, resulting in a better-performing and more lightweight system. Our approach, which leverages psychiatric scales, outperforms existing methods. Our experiments indicate that combining traditional psychiatry with computational techniques is worthwhile and deserving of further research and exploration. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Attentive Large Kernel Network with Mixture of Experts for Video Deblurring

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5575-5588页

作者： Zhang, Chaopeng Xiong, Ruiqin Fan, Xiaopeng Zhao, Debin Peking University Institute of Digital Media School of Electronic Engineering and Computer Science Beijing100871 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China Peng Cheng Laboratory Shenzhen519055 China

Video deblurring is a fundamental problem in low-level vision, and many methods have employed designs based on CNNs and transformers. Traditional CNNs often require deeper architectures to achieve a larger receptive field, which may not be optimal for spatially non-uniform blurs and intense motion blurs. While transformers offer a large receptive field, their quadratic complexity due to attention designs typically imposes a significant computational burden. In addressing these issues, we present an Attentive Large Kernel Network with Mixture of Experts (ALK-MoE). In ALK-MoE, an attentive large kernel backbone network is proposed. On one hand, it inherently extends the network's receptive field through its large kernel design. On the other hand, it addresses the quadratic complexity of attention by employing a sophisticated attention design, thus maintaining its ability to capture long-range dependencies. Furthermore, to achieve more precise and robust alignment of inter-frame features using optical flow for better utilization of clear frames, a mixture of experts model is proposed. It involves integrating optical flow updates between different experts in a residual manner. Our ablation experiments and experiments on multiple datasets indicate that ALK-MoE achieves comparable or superior performance compared to Transformer-based methods, with lower complexity. © 1991-2012 IEEE.

关键词： Multimedia systems

来源：评论

学校读者我要写书评

暂无评论

Focus Your Attention: Multiple Instance Learning with Attention Modification for Whole Slide Pathological Image Classification

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年第6期35卷 5791-5804页

作者： Cheng, Hailun Huang, Shenjin Cai, Linghan Xu, Yangfan Wang, Runming Zhang, Yongbing Tsinghua University Institute of Biopharmaceutical and Health Engineering Shenzhen International Graduate School Shenzhen518055 China Harbin Institute of Technology Faculty of Computing Harbin150001 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China

computer-aided pathology diagnosis based on whole slide images, which is often formulated as a weakly supervised multiple instance learning (MIL) paradigm. Current approaches generally employ attention mechanisms to aggregate instance-level features. However, the weakly supervised signal and the imbalanced instance distribution often lead to inaccurate attention localization, compromising the performance and generalization capability of the MIL framework. To address these problems, this paper presents a novel MIL framework called FAMIL that focuses on inaccurate attention and refines them. FAMIL adopts a dual-branch structure and incorporates two innovative online data augmentation strategies: attention-based Mixup (ABMix) and attention-based Masking (ABMask). ABMix emphasizes the significance of positive instances, generalizing Mixup in the MIL scenarios, while ABMask flexibly identifies challenging positive instances to optimize the feature representation. Moreover, these two methods are plug-and-play and can be easily embedded into attention-based MIL methods. Extensive experiments on three public benchmarks demonstrate the superiority of our FAMIL, outperforming current state-of-the-art methods. The test AUC for the binary tumor classification can be up to 92.61% over CAMELYON16. And the AUC over the cancer subtype classification can be up to 93.81% and 98.41% on TCGA-NSCLC and TCGA-RCC datasets, respectively. © 1991-2012 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

MFTEP: A Multimodal Fusion Deep Learning Framework for T Cell Receptor-epitope Interaction Prediction

MFTEP: A Multimodal Fusion Deep Learning Framework for T Cel...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Wang, Haoyan Huang, Yifei Zang, Tianyi Harbin Institute of Technology School of Computer Science and Technology Harbin China

ISBN: (纸本)9798350386226

Accurately predicting immunogenic peptides recognized by T cell receptors (TCR) is a crucial step toward personalized immunotherapy. However, prediction of TCR-epitope interactions is still a challenging task. Early works, like molecular dynamics simulation-based methods, suffer from slow speed and poor generalization capabilities. It is necessary to develop novel computational methods to predict TCR-epitope interactions precisely. With the development of high-throughput sequencing technologies, more and more TCR-epitope interaction data have been recorded in public databases. With the help of these databases, many in silico predictive methods have shown promising performance. However, current methods still perform poorly on unseen TCRs and epitopes. Moreover, most current models still accept single-modal information about TCRs and epitopes, such as sequences or physicochemical information. Effectively utilizing the multimodal information of TCRs and epitopes, such as molecular graphs and 3D structure, may enhance the model's prediction performance. To address the above issues, we presented MFTEP, a multimodal fusion method to predict TCR-epitope interactions by fusing the sequence features, molecular graph features, and 3D structure features of TCRs and epitopes. The ablation study highlights the importance of the multi-modal fusion module in enhancing the model's performance. Several datasets were collected and utilized to evaluate the generality and robustness of the proposed model. According to the experimental results, MFTEP performs better than other state-of-the-art methods, indicating its high predictive power. Overall, the results demonstrate that MFTEP can learn general TCR-epitope interaction patterns and is a powerful prediction tool to apply to real-world scenarios. All the data and code are available at: https://***/skybluewhy/MFTEP © 2024 IEEE.

关键词： T-cells

来源：评论

学校读者我要写书评

暂无评论

MLRT-UNet:An Efficient Multi-Level Relation Transformer Based U-Net for Thyroid Nodule Segmentation

引用

computer Modeling in Engineering & sciences 2025年第4期143卷 413-448页

作者： Kaku Haribabu Prasath R Praveen Joe IR Department of Computer Science and Engineering RMK College of Engineering and TechnologyTiruvallur601206India School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India

Thyroid nodules,a common disorder in the endocrine system,require accurate segmentation in ultrasound images for effective diagnosis and ***,achieving precise segmentation remains a challenge due to various factors,including scattering noise,low contrast,and limited resolution in ultrasound *** existing segmentation models have made progress,they still suffer from several limitations,such as high error rates,low generalizability,overfitting,limited feature learning capability,*** address these challenges,this paper proposes a Multi-level Relation Transformer-based U-Net(MLRT-UNet)to improve thyroid nodule *** MLRTUNet leverages a novel Relation Transformer,which processes images at multiple scales,overcoming the limitations of traditional encoding *** transformer integrates both local and global features effectively through selfattention and cross-attention units,capturing intricate relationships within the *** approach also introduces a Co-operative Transformer Fusion(CTF)module to combine multi-scale features from different encoding layers,enhancing the model’s ability to capture complex patterns in the ***,the Relation Transformer block enhances long-distance dependencies during the decoding process,improving segmentation *** results showthat the MLRT-UNet achieves high segmentation accuracy,reaching 98.2% on the Digital Database Thyroid Image(DDT)dataset,97.8% on the Thyroid Nodule 3493(TG3K)dataset,and 98.2% on the Thyroid Nodule3K(TN3K)*** findings demonstrate that the proposed method significantly enhances the accuracy of thyroid nodule segmentation,addressing the limitations of existing models.

关键词： Thyroid nodules endocrine system multi-level relation transformer U-Net self-attention external attention co-operative transformer fusion thyroid nodules segmentation

来源：评论

学校读者我要写书评

暂无评论

Effect of Ti_(p) Content on the Work Hardening and Softening Behavior of Mg-Zn-Ca Alloy

引用

Acta Metallurgica Sinica(English Letters) 2024年第3期37卷 551-560页

作者： Jin-Kai Zhang Cui-Ju Wang Yi-Dan Fan Chao Xu Kai-Bo Nie Kun-Kun Deng Shanxi Key Laboratory of Advanced Magnesium-Based Materials College of Materials Science and EngineeringTaiyuan University of TechnologyTaiyuan 030024China School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China

The Ti_(p)/ZX60 composites with different Ti_(p) contents were prepared by semi-solid stirring *** extrusion,the microstructure,work hardening and softening behavior of the Ti_(p)/ZX60 composites were analyzed compared with the ZX60(Mg-6Zn-0.2Ca)*** results showed that the addition of Ti_(p) could not only promote the nucleation of dynamic recrystallized(DRXed)grains,but also be propitious to the refinement of DRXed *** increasing Ti_(p) content,the size of DRXed grains decreased accompanied with increasing volume fraction of DRXed *** the Ti_(p) content increased to 15 vol.%,the average size and volume fraction of DRXed grains reached to~0.32μm and 93.2%,***,both the strength and elongation were improved by the addition of Ti_(p).With increasing content of Ti_(p),a substantial increase in the strength was achieved with little change in the ***,the elongation decreased sharply when the Ti_(p) content further increased to 15 vol.%.The addition of Ti_(p) led to an increase in the work hardening rate,which gradually increased with increasing Ti_(p) ***,the softening rate did not demonstrate the same tendency with increasing Ti_(p) *** the conventional ceramic particles,the Ti_(p) can be deformed in coordination with the matrix alloy,which imparted a higher softening rate to the matrix *** though the softening rate improved as the Ti_(p) content increased from 5 to 10 vol.%,it dropped deeply as the Ti_(p) content increased to 15 vol.%owing to the fracture of Ti_(p) during extrusion.

关键词： Titanium particle content Particle reinforced magnesium matrix composites Work hardening Softening behavior Mechanical properties

来源：评论

学校读者我要写书评

暂无评论

Microstructure and Mechanical Properties of Al_(2)O_(3p)/AZ91 Magnesium Matrix Laminated Material Adjusted by Freezing Temperature

引用

Acta Metallurgica Sinica(English Letters) 2024年第11期37卷 1819-1829页

作者： Ze-Xin Bai Kun-Kun Deng Ze-Qi Du Kai-Bo Nie Chao Xu Quan-Xin Shi Shanxi Key Laboratory of Advanced Magnesium-based Materials College of Materials Science and EngineeringTaiyuan University of TechnologyTaiyuan 030024China School of Materials Science and Engineering Harbin Institute of TechnologyHarbin 150001China

The Al_(2)O_(3)laminated preforms with different layers thickness were prepared by freezing casting in present ***,the Al_(2)O_(3p)/AZ91 magnesium matrix laminated materials were obtained by infiltrating the AZ91 alloy melt into the Al_(2)O_(3)laminated preform based on pressure infiltration ***,the influence of freezing temperature on the microstructure,mechanical properties and fracture behavior of magnesium-based laminates was *** results indicated that with the decrease of freezing temperature,the thickness of Al_(2)O_(3)layers decreases gradually,the number of layers increases obviously,and the interlayers spacing *** with the decrease of interlayers spacing,the size of Mg17Al12 phase precipitated in the AZ91 alloy layers was refined,and the compression strength and strain were both improved *** micro-cracks initiated in Al_(2)O_(3)layers during loading process,while the AZ91 layers could effectively suppress the initiation and propagation of ***,the changing layers structure influenced by the decrease of freezing temperature had significant inhibiting effect on the initiation and propagation of micro-cracks,which endowed the Al_(2)O_(3p)/AZ91 magnesium matrix laminated materials with better strength and ***,the best compression properties of Al_(2)O_(3p)/AZ91 magnesium matrix laminated materials could be obtained at the freezing temperature of−50℃,the compression strength and elastic modulus of which were the 160%and 250%of monolithic AZ91 alloy,respectively.

关键词： Bio-inspired composites Freeze-casting Mechanical properties Metal matrix composites

来源：评论

学校读者我要写书评

暂无评论

A method for determining the spatial pattern of forest trees based on the uniformity theory

引用

Journal of Forestry Research 2024年第6期35卷 148-159页

作者： Yeqiong Shi Xiulong Gao Chunling Lang Chuanwen Luo College of Computer Science and Information Engineering Harbin Normal UniversityHarbin 150040People’s Republic of China College of Vocation and Technical Education Guangxi Science and Technology Normal UniversityLaibin 546199People’s Republic of China College of Mathematics and Computer Science Guangxi Science and Technology Normal UniversityLaibin 546199People’s Republic of China College of Forestry Northeast Forestry UniversityHarbin 150040People’s Republic of China

The spatial pattern of trees is an important feature of forests,and different spatial patterns of trees exhibit different ecological *** has confirmed that natural forests with random patterns have higher biodiversity and stronger resistance to unstable factors such as pests and *** if they are disturbed or destroyed by unstable factors such as pests and diseases,they can still recover and rescue themselves;while artificial forests with uniform and clustered patterns have lower biodiversity and are susceptible to unstable factors such as pests and *** once pests and diseases occur,it’s more difficult for them to *** order to promote the healthy and stable develop-ment of the forestry industry and protect the diversity of the biological environment,it is necessary to protect the random pattern of natural forests from being destroyed in the process of forest management,while effectively transforming the spatial pattern of artificial forests into a random ***,in order to ensure the convenient and accurate determination of the type of forest spatial pattern,research on methods for determining forest spatial pattern has become particularly *** on the theory of uniformity,this study proposes definitions and related theories of included exclusive sphere,included exclusive body,included random pattern,and included *** the guidance of the definition of inclusion uniformity and related theories,and by using mathematical method,it is proved that the uniformity of inclusion(CL)is asymptotically subject to the Eq.18,Therefore,the relationship between the included uniformity(CL)and the number of trees in the sample plot was established,and the corresponding relationship formula was obtained,and then the determination of the spatial pattern type of trees was completed by using the corresponding relationship *** rigorous reasoning and case verification,the determination method of forest spat

关键词： Uniformity Forest spatial pattern Contained exclusive sphere Co correlation coefficient Included Uniformity

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：