检索结果-内蒙古大学图书馆

8th China High Resolution Earth Observation Conference, CHREOC 2022

作者： Zheng, Pengfei Fang, Panfei Liu, Peiwei Xu, Weiheng Wang, Guojun Wang, Leiguang Faculty of Forestry Southwest Forestry University Kunming China College of Big Data and Intelligent Engineering Southwest Forestry University Kunming China Key Laboratory of National Forestry and Grassland Administration on Forestry and Ecological Big Data Southwest Forestry University Kunming China Yunnan Tobacco Company Qujing Company Qujing China

ISBN: (纸本)9789811982019

Remote sensing technology provides an economical and efficient means for obtaining the distribution of dominant tree species. However, remote sensing mapping of dominant tree species have remained an ongoing challenge, such as massive data and low accuracy of a single machine learning method, especially over large-scale mountainous areas. In this study, the multi-source variables and multi-classifier decision fusion was used to separate the dominant tree species on the Google Earth Engine cloud computing platform. We combined with multi-source data such as Sentinel-2 satellite imagery, bioclimate, topography, and forest inventory data and constructed time series for NDVI and REP to evaluate different variables combinations. At the same time, tree species classification was carried out following two approaches: non-stratified and stratified. Four different Machine learning algorithms, Random Forest (RF), Support Vector Machine (SVM), XGBoost, and Maximum Entropy (MaxEnt) were used as component classifiers to construct two decision fusion models of serial integration and Bayesian parallel integration respectively and completed the spatial distribution of 10 main dominant tree species mapping in the mountainous areas of northwest Yunnan. The nine tree species were classified with an overall accuracy of 74.44% using serial integration of MaxEnt and RF. This study confirmed that combination of multi-source data multi-source variables and the decision fusion method can be used to provide a reference for the classification of dominant tree species in large-scale mountainous areas. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Engines

来源：评论

学校读者我要写书评

暂无评论

Agent Planning with World Knowledge Model

arXiv

引用

arXiv 2024年

作者： Qiao, Shuofei Fang, Runnan Zhang, Ningyu Zhu, Yuqi Chen, Xiang Deng, Shumin Jiang, Yong Xie, Pengjun Huang, Fei Chen, Huajun Zhejiang University China National University of Singapore NUS-NCS Joint Lab Singapore Alibaba Group China Zhejiang Key Laboratory of Big Data Intelligent Computing China

Recent endeavors towards directly using large language models (LLMs) as agent models to execute interactive planning tasks have shown commendable results. Despite their achievements, however, they still struggle with brainless trial-and-error in global planning and generating hallucinatory actions in local planning due to their poor understanding of the "real" physical world. Imitating humans’ mental world knowledge model which provides global prior knowledge before the task and maintains local dynamic knowledge during the task, in this paper, we introduce parametric World Knowledge Model (WKM) to facilitate agent planning. Concretely, we steer the agent model to self-synthesize knowledge from both expert and sampled trajectories. Then we develop WKM, providing prior task knowledge to guide the global planning and dynamic state knowledge to assist the local planning. Experimental results on three complex real-world simulated datasets with three state-of-the-art open-source LLMs, Mistral-7B, Gemma-7B, and Llama-3-8B, demonstrate that our method can achieve superior performance compared to various strong baselines. Other interesting findings include: 1) our instance-level task knowledge can generalize better to unseen tasks, 2) weak WKM can guide strong agent model planning, and 3) unified WKM training has promising potential for further development Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Multimodal Biological Knowledge Graph Completion via Triple Co-Attention Mechanism 39

Multimodal Biological Knowledge Graph Completion via Triple ...

引用

39th IEEE International Conference on data Engineering, ICDE 2023

作者： Xu, Derong Zhou, Jingbo Xu, Tong Xia, Yuan Liu, Ji Chen, Enhong Dou, Dejing University of Science and Technology of China State Key Laboratory of Cognitive Intelligence China Baidu Research Business Intelligence Lab Baidu Intelligent Healthcare Unit Baidu Research Big Data Lab BCG X

ISBN: (纸本)9798350322279

Biological Knowledge Graphs (BKGs) can help to model complex biological systems in a structural way to support various tasks. Nevertheless, the incompleteness problem may limit the performance of existing BKGs, which still deserves new methods to reveal the missing relations. Though great efforts have been made to knowledge graph completion, existing methods are not easy to be adapted to the multimodal biological information such as molecular structures and textual descriptions. To this end, we propose a novel co-attention-based multimodal embedding framework, named CamE, for the multimodal BKG completion task. Specifically, we design a Triple Co-Attention (TCA) operator to capture and highlight the same semantic features among different modalities. Based on TCA, we further propose two components to handle multimodal fusion and multimodal entity-relation interaction, respectively. One is the multimodal TCA fusion module to achieve a multimodal joint representation for each entity in the BKG. It aims to project different modal information into a common space by capturing the same semantic features and overcoming the modality gap. The other is the relation-aware interactive TCA module to learn interactive representation by modelling the deep interaction between multimodal entities and relations. Extensive experiments on two real-world multimodal BKG datasets demonstrate that our method significantly outperforms several state-of-the-art baselines, including 10.3% and 16.2% improvement w.r.t MRR and Hits@1 metrics over its best competitors on public DRKG-MM dataset. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Based User Scheduling for Real-Time Multimedia Tasks in Edge Devices 1

引用

3rd EAI International Conference on Edge computing and IoT, EAI ICECI 2022

作者： Wen, Wenkan Liu, Yiwen Gao, Yanxia Zhu, Zhirong Shi, Yuanquan Peng, Xiaoning School of Computer and Artificial Intelligence Huaihua University Huaihua418000 China Key Laboratory of Wuling-Mountain Health Big Data Intelligent Processing and Application in Hunan Province Universities Hunan Huaihua418000 China Key Laboratory of Intelligent Control Technology for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua418000 China

ISBN: (数字)9783031289903

ISBN: (纸本)9783031289897

Edge networks are highly volatile and the quality of device communication and computational resources change not only over time but also according to the movement of users. Current federation learning suffers from poor device network state and failure of devices to upload models in a timely manner. To address these problems, an intelligent scheduling mechanism that uses the predicted device state based on device information to select the appropriate device for federated learning is proposed in this paper. By focusing on information such as communication quality, computational resources, and location information, the information of edge devices is collected to analyze and predict the device network and computing resources to further analyze the state of devices in depth. Experiments are conducted on real datasets, and the experimental results show that the proposed scheduling method can make the global model fit faster than without the algorithm, which significantly improves the training efficiency of federated learning. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

TF-DTA: A Deep Learning Approach Using Transformer Encoder to Predict Drug-Target Binding Affinity

TF-DTA: A Deep Learning Approach Using Transformer Encoder t...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Li, Wenjun Zhou, Yiqiang Tang, Xiwei Changsha University of Science and Technology Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Hunan Changsha China Hunan First Normal University School of Computer Science Hunan Changsha China

ISBN: (纸本)9798350337488

Bioinformatics is a rapidly growing field that involves the application of computational methods to analyze and interpret biological data. One important task in bioinformatics is predicting the drug-target affinity (DTA), which plays a significant role in drug discovery through virtual screening. Effectively predicting the association between drug molecules and target molecules can speed up the drug discovery process. The DTA can be quantitatively measured. This quantifiable affinity is more precise than a simple binary relationship. In this study, we propose a deep learning model for DTA prediction that utilizes the encoder module of the Transformer architecture. Our proposed model utilizes Convolutional Neural Networks (CNNs) and the encoder module of Transformer to characterize protein and drug sequences. The model outperforms some methods such as KronRLS, SimBoost and DeepDTA as evidenced by superior evaluation metrics such as Mean Squared Error (MSE), Concordance Index (CI), and Regression toward the Mean Index (rm2). These results demonstrate the effectiveness of the Transformer's encoder in extracting meaningful representations from sequences, thereby improving the accuracy of DTA prediction. Deep learning models for DTA prediction can accelerate drug discovery by identifying drug candidates with high binding affinity to specific targets. Compared to traditional methods, the use of machine learning technology enables more effective and efficient drug discovery. © 2023 IEEE.

关键词： deep learning drug-target affinity multi-head attention mechanism

来源：评论

学校读者我要写书评

暂无评论

引用

9th International Conference on Fuzzy Systems and data Mining, FSDM 2023

作者： Xu, Changlin Wu, Wenyuan School of Mathematics and Information Science North Minzu University Yinchuan750021 China The Key Laboratory of Intelligent Information and Big Data Processing of Ningxia Province North Minzu University Ningxia Yinchuan750021 China

ISBN: (纸本)9781643684703

The similarity of triangular fuzzy numbers could be served as a measurement of similarity between two triangular cloud models. However, it has been found that existing methods for describing the similarity of triangular cloud models has the drawbacks that can't make full use of utilizing graphic information and assigning inappropriate weights to distances through research and analysis. The method proposed in this literature has adjusted the weight of distance similarity aim to ensure that the characteristic information of the model will not be covered. In addition, the proposed method provides a measurement to describe geometric shape bases on the expected curve included angle of the triangular cloud model. On the foundation of taking abundantly the similarity of distance and shape into account, we provide the measurement to achieve better accuracy. The feasibility and effectiveness of the proposed method have been demonstrated through the time series of KNN algorithm. © 2023 The authors and IOS Press.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Transverse Velocity Field Measurements in High-resolution Solar Images Based on Deep Learning

引用

Research in Astronomy and Astrophysics 2023年第6期23卷 86-97页

作者： Zhen-Hong Shang Si-Yu Mu Kai-Fan Ji Zhen-Ping Qiang Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500China Yunnan Observatories Chinese Academy of SciencesKunming 650216China College of Big Data and Intelligent Engineering Southwest Forestry UniversityKunming 650224China

To address the problem of the low accuracy of transverse velocity field measurements for small targets in highresolution solar images,we proposed a novel velocity field measurement method for high-resolution solar images based on *** method transforms the transverse velocity field measurements into an optical flow field prediction *** evaluated the performance of the proposed method using the Hαand TiO data sets obtained from New Vacuum Solar Telescope *** experimental results show that our method effectively predicts the optical flow of small targets in images compared with several typical machine-and deeplearning *** the Hαdata set,the proposed method improves the image structure similarity from 0.9182 to0.9587 and reduces the mean of residuals from 24.9931 to 15.2818;on the TiO data set,the proposed method improves the image structure similarity from 0.9289 to 0.9628 and reduces the mean of residuals from 25.9908 *** optical flow predicted using the proposed method can provide accurate data for the atmospheric motion information of solar *** code implementing the proposed method is available on https://***/lygmsy123/transverse-velocity-field-measurement.

关键词： methods:data analysis techniques:image processing Sun:fundamental parameters

来源：评论

学校读者我要写书评

暂无评论

Three-Way Decision-Making Based on Incomplete Information System and Its Application 9

Three-Way Decision-Making Based on Incomplete Information Sy...

引用

9th International Conference on Fuzzy Systems and data Mining, FSDM 2023

作者： Xu, Changlin Mao, Songqian School of Mathematics and Information Science North Minzu University Yinchuan750021 China The Key Laboratory of Intelligent Information and Big Data Processing of Ningxia Province North Minzu University Ningxia Yinchuan750021 China

ISBN: (纸本)9781643684703

In order to avoid decision makers from making wrong decisions as much as possible and reduce the losses caused by wrong decisions, a new aggregation method of interval loss function is proposed based on incomplete information system. Firstly, the missing values are filled according to their characteristics and combined with probability, and on this basis, the measurement method of similarity is given, and the horizontal similarity class of each object is obtained according to the similarity between objects. Secondly, according to the number of times each object in the similar class appears in its corresponding horizontal similar class, the corresponding weight is obtained;Then the interval loss function of similar class is defined as the aggregation of interval loss functions of all objects in similar class, and each interval is weighted according to the weight, so that multiple intervals in similar class are aggregated into an interval, and then the aggregated interval is converted into a single value by using the conversion function. Finally, according to the aggregation method, three decision rules are given to make decisions, and the effectiveness of the method is verified by a case. © 2023 The authors and IOS Press.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Intersecting-Boundary-Sensitive Fingerprinting for Tampering Detection of DNN Models 41

Intersecting-Boundary-Sensitive Fingerprinting for Tampering...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Bai, Xiaofan He, Chaoxiang Ma, Xiaojing Zhu, Bin Benjamin Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Microsoft United States School of Computer Science and Technology Huazhong University of Science and Technology China Cluster and Grid Computing Lab China

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF. Copyright 2024 by the author(s)

关键词： HTTP

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：