检索结果-内蒙古大学图书馆

IEEE International Conference on Electronic Information and Communication Technology (ICEICT)

作者： Zhikai Gong Yingsong Li Baohe Pang Xueyan Li Wudang Xiao Liping Li Nikola Zlatanov College of Information and Communication Engineering Harbin Engineering University Harbin China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China Faculty of Computer and Engineering Sciences Innopolis University Russia

ISBN: (数字)9798350384437

ISBN: (纸本)9798350384444

In this paper, we propose two new subband adaptive filtering (SAF) algorithms based on the cost function of the logistic distance metric cost function and use the proportionate proximal gradient algorithm to exploit the sparsity of the system fully. Compared with prior works, the proposed algorithms can handle many different situations better. Through computer simulations, we prove that the algorithm performs excellently in sparse systems disturbed by impulse noises. The algorithm can be used in areas like system identifications.

关键词： Measurement Adaptive systems Computer simulation Noise Filtering algorithms Cost function Information filters

来源：评论

学校读者我要写书评

暂无评论

Open-vocabulary 3D Semantic Understanding via Affinity Neural Radiance Fields

Open-vocabulary 3D Semantic Understanding via Affinity Neura...

引用

Next Generation Data-driven Networks (NGDN), International Conference on

作者： Yujie Fan Huan Luo Computer and Data Science Fuzhou University Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China

ISBN: (数字)9798350388374

ISBN: (纸本)9798350388381

Three-dimensional semantic understanding using only several multi-view images can largely reduce the communication burden on the network. In addition, while point clouds are extensively studied for 3D scene understanding, utilization of multi-view image data offers rich visual details and texture information. However, challenges persist in lifting 2D semantic features to 3D space and leveraging language for segmentation. Inspired by recent advancements, this paper proposes a method that combines CLIP features and SAM masks to create a feature field capable of segmenting objects via natural language text across 2D multi-view and 3D Gaussian splatting. It offers a promising function for extracting 3D assets for game engines and the metaverse. Our method involves mask generation from video frames, extracting physical scales via RGB Nerf with masks, and organizing hierarchical information for semantic comprehension. In the training process, affinity features maintain scale properties and guide CLIP feature generation with auto weights blending for semantic robustness. A straightforward 3D splatting CLIP feature approach and canonical text methodology enhance query robustness across 2D multi-view and 3D splatting through relevance score calculation based on text CLIP features for inference. Experimental results demonstrate promising improvements in semantic understanding of 3D scenes.

关键词： Training Image segmentation Vocabulary Visualization Three-dimensional displays Semantics Natural languages Neural radiance field Feature extraction Robustness

来源：评论

学校读者我要写书评

暂无评论

Y-Mol: A Multiscale Biomedical Knowledge-Guided Large Language Model for Drug Development

arXiv

引用

arXiv 2024年

作者： Ma, Tengfei Lin, Xuan Li, Tianle Li, Chaoyi Chen, Long Zhou, Peng Cai, Xibao Yang, Xinyu Zeng, Daojian Cao, Dongsheng Zeng, Xiangxiang College of Computer Science and Electronic Engineering Hunan University China Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Xiangtan University China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University China Xiangya School of Pharmaceutical Sciences Central South University China

Large Language Models (LLMs) have recently demonstrated remarkable performance in general tasks across various fields. However, their effectiveness within specific domains such as drug development remains challenges. To solve these challenges, we introduce Y-Mol, forming a well-established LLM paradigm for the flow of drug development. Y-Mol is a multiscale biomedical knowledge-guided LLM designed to accomplish tasks across lead compound discovery, pre-clinic, and clinic prediction. By integrating millions of multiscale biomedical knowledge and using LLaMA2 as the base LLM, Y-Mol augments the reasoning capability in the biomedical domain by learning from a corpus of publications, knowledge graphs, and expert-designed synthetic data. The capability is further enriched with three types of drug-oriented instructions: description-based prompts from processed publications, semantic-based prompts for extracting associations from knowledge graphs, and template-based prompts for understanding expert knowledge from biomedical tools. Besides, Y-Mol offers a set of LLM paradigms that can autonomously execute the downstream tasks across the entire process of drug development, including virtual screening, drug design, pharmacological properties prediction, and drug-related interaction prediction. Our extensive evaluations of various biomedical sources demonstrate that Y-Mol significantly outperforms general-purpose LLMs in discovering lead compounds, predicting molecular properties, and identifying drug interaction events. The source code is available at https://***/r/Y-Mol. © 2024, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Using Rough Sets to Improve the High-dimensional Data Anomaly Detection Method Based on Extended Isolation Forest 26

Using Rough Sets to Improve the High-dimensional Data Anomal...

引用

26th International Conference on Computer Supported Cooperative Work in Design, CSCWD 2023

作者： Liu, Hanlin Zhou, Jiantao Li, Hua Inner Mongolia University College of Computer Science Hohhot China Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Anomaly detection refers to the identification of data objects that deviate from the general data distribution. One of the important challenges in anomaly detection is handling high-dimensional data, especially when it contains a large number of redundant attributes. Although traditional Isolation Forest (iForest) and Extended Isolation Forest (EIF) have performed well in anomaly detection, the detection accuracy is still extremely influenced by redundant attributes. In this paper, we propose a two-tier architecture named RS-EIF, to alleviate the negative impact of redundant attributes. Specifically, the RS-EIF combines the rough set theory and EIF algorithm and provides an effective basis for the EIF-based anomaly detection method by removing redundant attributes with rough set theory. Experimental results show that the RS-EIF algorithm performs better than the iForest and EIF algorithms in terms of anomaly detection rate, and the results of the combination of rough set theory and EIF are more prominent compared to the other combination methods. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Leveraging Slot-Aware Enhancements for Improved Zero-Shot Dialogue State Tracking

Leveraging Slot-Aware Enhancements for Improved Zero-Shot Di...

引用

Frontiers Technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Tianhang Song Haolei Hu Xinxin Chen Kangli Zi Henan Institute of Advanced Technology Zhengzhou University Zhengzhou China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Beijing China

ISBN: (数字)9798331541750

ISBN: (纸本)9798331541767

Task-oriented dialogue systems (TOD) aim to help users complete specific tasks through multiple rounds of dialogue, in which Dialogue State Tracking (DST) is a key component. The training of DST models typically necessitates the availability of a substantial corpus of dialogue data with turn-level annotations. However, the collection of such data is both costly and inefficient. Despite the impressive performance of systems based on advanced large language models (LLMs), their closed-source nature restricts the potential for local deployment. To address this challenge, this paper proposes a new zero-shot slot-aware enhanced model (SAE), which introduces a novel coded prompting framework to enhance the DST capability of small parameter models in new domains and task scenarios. In particular, we have devised a prompting framework that employs code to refine task instructions. Furthermore, we have proposed a slot-aware question generation mechanism that generates slot-aware questions based on contextual details in accordance with the dialogue context, thereby enhancing the model's perception and matching capabilities for slots. In order to verify the effectiveness of the model, we conducted experiments on the MultiWOZ dataset. The results show that the SAE model has achieved significant performance improvements in zero-shot DST tasks.

关键词： Training Adaptation models Codes Large language models Computational modeling Termination of employment Predictive models Question generation Data models Context modeling

来源：评论

学校读者我要写书评

暂无评论

Pseudo Multi-Source Domain Extension and Selective Pseudo-Labeling for Unsupervised Domain Adaptive Medical Image Segmentation

Pseudo Multi-Source Domain Extension and Selective Pseudo-La...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Xiaokang Liu Zhiqiang Wang Kai Hu Xieping Gao Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Xiangtan University Xiangtan China College of Medical Imaging Laboratory and Rehabilitation Xiangnan University Chenzhou China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha China

Unsupervised domain adaptation (UDA) attracts extra attention in medical image processing because no additional labels are required when adapting to different distributions. In this work, we propose a novel unsupervised domain adaptation framework named as Domain Expansion and PseudoLabeling (DEPL). We extend the domain of a labeled source domain data to four different distributed domains and use adversarial learning to align the image appearance level and feature level from the four different domains to the unlabeled target domain. In addition, we propose a selective pseudolabeling mechanism, namely using strong confidence pseudolabeling to boost model performance. We evaluate our model for the MR to CT adaptation segmentation task on the public dataset MMWHS. Compared to seven other state-of-the-art segmentation methods, our DEPL achieves the best Dice similarity coefficient by 82.4%, which is at least 3.9% higher than the other UDA segmentation methods.

关键词： Image segmentation Adaptation models Computed tomography Distributed databases signal processing Adversarial machine learning Biomedical image processing

来源：评论

学校读者我要写书评

暂无评论

EEG-Based Fatigue Detection Using PLI Brain Network and Relief Algorithm

EEG-Based Fatigue Detection Using PLI Brain Network and Reli...

引用

2022 International Conference on Networking and Network Applications, NaNA 2022

作者： He, Yan Wang, Zhongmin Zhao, Yupeng Xi'an University of Posts and Telecommunications Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi'an710121 China School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

EEG-based fatigue driving monitoring has important application value in road traffic safety, and the ultimate goal of the research is the development and use of wearable devices, and too many EEG channels in practical application scenarios is detrimental to device portability, and it will lead to problems such as large amount of data, complex calculation and long processing time, so it is especially important to study how to select the EEG channels highly correlated with fatigue. In this paper, a PLI-Relief-based channel selection algorithm by combining the PLI functional connectivity and the weighting idea of Relief algorithm is proposed, and it is applied to the channel selection of fatigue driving EEG. First, the PLI functional connectivity matrix is constructed for the EEG signals after preprocessing, and the binarized PLI matrix is mapped into a brain functional network, and the prime channels are selected by the degree property of the brain network. Then, the power spectral density features are extracted from the EEG signals of the prime channels, and the weights of each prime channel are obtained using the relief algorithm, then the number and the names of optimal channels are determined according to the recognition accuracy of different channel combinations. The proposed method was validated on the publicly available SEED-VIG dataset, and the data of the seven optimal channels is finally selected and obtains a classification accuracy of 81.25%. The framework proposed in this paper takes into account both the correlation between channels and the characteristics of the channel signals themselves in channel selection, which is a reference value for the development and application of wearable devices. © 2022 IEEE.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

A Novel Effectiveness Assessment Framework for Neoadjuvant Chemoradiotherapy of Locally Advanced Rectal Cancer Based on Multi-modal Intelligence

A Novel Effectiveness Assessment Framework for Neoadjuvant C...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Tian, Xiao Sui, Dong Liu, Weifeng Guo, Maozu Luo, Gongning Wang, Kuanquan Beijing Key Laboratory for Intelligent Processing Methods of Architectural Big Data Beijing China School of Electrical and Information Engineering Beijing University of Civil Engineering and Architecture Beijing China Perceptual Computing Research Center Harbin Institute of Technology Harbin China

ISBN: (纸本)9798350337488

Neoadjuvant chemoradiotherapy (nCRT) is the standard treatment for locally advanced rectal cancer (LARC). With the development of artificial intelligence, an increasing number of studies have begun to explore its application in cancer treatment prediction. However, the prior methods exhibit considerable variability even with slight modifications to the input data, which could potentially undermine the reliability of the results. In this paper, we proposed RP-Net, a novel multi-modal fusion-based framework that combines feature information from magnetic resonance imaging (MRI) and whole slide images (WSI), establishing a relationship to map the therapeutic effectiveness of nCRT for LARC. We investigated the relationship of the tumour region and its periphery tissues, and demonstrated the validity of the proposed framework that involving 11 different combinations of modalities. The experimental results revealed that it has achieved higher prediction accuracy compared to the four intra-categories single-modal combinations and outperformed the two intra-categories multi-modal combinations. When compared to the other four inter-categories multi-modal combinations, the fusion features get accuracy of 2% ∼ 6% improvement respectively. © 2023 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

NetPrompt: Neural Network Prompting Enhances Event Extraction in Large Language Models

引用

IEEE Transactions on Big Data 2025年

作者： Mu, Lin Cheng, Yide Shen, Jun Zhang, Yiwen Zhong, Hong School of Computer Science and Technology Anhui University Anhui Hefei230601 China The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education the Anhui Engineering Laboratory of IoT Security Technologies the School of Computer Science and Technology the Institute of Physical Science and Information Technology Anhui University Hefei230039 China

Event Extraction involves extracting event-related information such as event types and event arguments from context, which has long been tackled through well-designed neural networks or fine-tuned pre-trained language models. These approaches require substantial annotated data for tuning parameters and are resource-intensive. Recently, Prompting strategies with frozen parameters, such as Chain-of-Thought and Self-Consistency, have delivered success in NLP using LLMs by generating intermediate thought steps. However, they suffer from the challenge of error propagation and lack of interaction between different thoughts. In this paper, we propose Neural Network-based Prompting (NetPrompt), a novel network-structured prompting strategy for event extraction. The core idea behind NetPrompt is to imitate the excellent information integration capabilities of neural network structures. Specifically, we first decompose the event extraction problem into diverse intermediate subtasks, and each subtask is represented as a node in different layers of the network, the output of the nodes in the preceding layer is fed into the subsequent layer. Secondly, we propose pruning strategies to adapt the reasoning overhead to different problems. Finally, we have conducted extensive experiments on two widely used event extraction benchmarks to evaluate NetPrompt. The results demonstrated that NetPrompt significantly improved the event extraction performance compared to previous methods. ©2015 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

QoS Prediction based on the Low-rank Autoregressive Tensor Completion

QoS Prediction based on the Low-rank Autoregressive Tensor C...

引用

2022 International Conference on Networking and Network Applications, NaNA 2022

作者： Xia, Hong Dong, Qingyi Chen, Yanping Zheng, Jiahao Gao, Cong Wang, ZhongMin School of Computer Science and Technology Xi’an University of Posts and Telecommunications Shaanxi Xi’an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Shaanxi Xi’an710121 China Xi'an Key Laboratory of Big Data and Intelligent Computing Shaanxi Xi’an710121 China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

With the rapid development of network services and edge computing, Quality of Service (QoS) has become an important indicator to validate performances of a network. Recommend high-quality services to users based on QoS values. However, the high sparsity of QoS data is because users usually call certain services only at a given time. Missing QoS data is very common in various service recommendation systems. Therefore, it is essential to predict QoS data to accurately recommend high-quality services to users. For the QoS data prediction problem, we build a third-order data tensor 'User-Service-Time' for the time series characteristics of QoS data. And introduce time-series variation as a regularization term into third-order tensor Data prediction. We propose a QoS prediction framework using Low-Rank Autoregressive Tensor Completion (LATC). In particular, constructing a third-order tensor data model can better capture the global consistency of the data structure. Time regularization is introduced to take into account the local correlation of the data. Finally, in order to solve the constrained optimization problem, we use the general Alternating Direction Method of Multipliers (ADMM) to minimize the iterative optimization of variables and autoregressive parameters to obtain the final prediction result. Meanwhile, we conduct extensive research experiments on the real dataset WS-Dream. Experiments show that the QoS data prediction accuracy of our proposed QoS prediction method is higher than that of existing prediction methods under different degrees of data density. © 2022 IEEE.

关键词： Forecasting

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：