检索结果-内蒙古大学图书馆

computer Information science and Application Technology (CISAT), International Conference on

作者： Ruilin Su Wanshan Zhang Dunhui Yu Hubei University Wuhan China Wuhan China School of Computer Science and Information Engineering Hubei University Wuhan China Hubei Key Laboratory of Big Data Intelligent Analysis and Application Hubei University Wuhan China Engineering and Technical Research Center of Hubei Province in Software Engineering Wuhan China

ISBN: (数字)9798350375107

ISBN: (纸本)9798350375114

Multi-hop Knowledge Reasoning is a task that involves generating an answer given a query and a knowledge graph. Existing sequence-to-sequence reasoning models use the Transformer to encode and decode sequences, but these models have some flaws, such as the inability to effectively handle long-sequence reasoning and susceptibility to exposure bias. To address these issues, we provides a sequence-to-sequence reasoning model named STSR, which is based on Retentive Network. Aiming at improving training efficiency through parallel training, this model leverages the advantages in Retentive Network, reduce time overhead, and enhance reasoning efficiency through iterative reasoning. It effectively mitigates the problems of high spatial overhead and low efficiency in long-sequence reasoning faced by the Transformer. Moreover, it retains and updates historical information during the encoding and decoding process, enhancing the model’s memory and generalization capabilities. Additionally, the Scheduled Sampling method is adopted to alleviate the exposure bias introduced during reasoning, which involves using the model’s own output as the input for the next moment with a certain probability during training, instead of using the true label. We conduct the experiment on six public datasets, with the results showing that the proposed model outperforms existing baseline models in terms of precision and generation quality. This paper provides a new solution for the task of sequence-to-sequence multihop knowledge reasoning and also demonstrates the potential application of the Retentive Network in natural language processing.

关键词： Training Knowledge engineering Accuracy Spread spectrum communication Knowledge graphs Transformers Sampling methods Cognition Natural language processing Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

A Low Self-Noise Fiber Optic Gyroscope Based on Dual-polarization Configuration for Geophysical Rotation Sensing

A Low Self-Noise Fiber Optic Gyroscope Based on Dual-polariz...

引用

2021 Asia Communications and Photonics Conference, ACP 2021

作者： Chen, Yanjun Cao, Yuwen Wang, Wenbo He, Yan Zhou, Tong Li, Zhengbin State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Engineering and Computer Science Peking University Beijing100871 China School of Software and Microelectronics Peking University Beijing102600 China

A fiber optic gyroscope based on dual-polarization configuration_is designed and realized. The 24-hour stability test shows aself-noise level of 3 × 10−9 rad/s/√Hz within the frequency range of 0.001Hz to 1Hz. &... 详细信息

ISBN: (纸本)9781957171005

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Multi-Swarm Genetic Gray Wolf Optimizer with Embedded Autoencoders for High-Dimensional Expensive Problems

SSRN

引用

SSRN 2023年

作者： Zhai, Jiahui Bi, Jing Yuan, Haitao Zhou, Mengchu School of Software Engineering Faculty of Information Technology Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

High-dimensional expensive problems are often encountered in the design and optimization of complex robotic and automated systems and distributed computing systems, and they suffer from a time-consuming fitness evaluation process. It is extremely challenging and difficult to produce promising solutions in high-dimensional search space. This work proposes an evolutionary optimization framework with embedded autoencoders that effectively solve optimization problems with high-dimensional search spaces. Autoencoders provide strong dimension reduction and feature extraction abilities that compress a high-dimensional space to an informative low-dimensional one. Search operations are performed in a low-dimensional space, thereby guiding a whole population to converge to the optimal solution more efficiently. Multiple subpopulations coevolve iteratively in a distributed manner. One subpopulation is embedded by an autoencoder, and the other one is guided by a proposed Multi-swarm Gray wolf optimizer based on Genetic learning (MGG). Thus, the proposed multi-swarm framework is named Autoencoder-based MGG (AMGG). AMGG consists of three proposed strategies that well balance exploration and exploitation abilities, i.e., a Dynamic subgroup Number Strategy for reducing the number of subpopulations, a Subpopulation Reorganization Strategy for sharing useful information about each subpopulation, and a Purposeful Detection Strategy for jumping out of local optima and improving exploration ability. AMGG is compared with several widely used algorithms by using typical benchmark functions and a real-life optimization problem. Extensive experimental results prove that AMGG outperforms its peers in terms of search accuracy and convergence efficiency. © 2023, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

arXiv

引用

arXiv 2023年

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao The School of Software Engineering South China University of Technology Guangzhou510640 China The Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China The School of Computer Science and Engineering Nanyang Technological University Singapore The Pazhou Lab Guangzhou China

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

Joint Learning Neuronal Skeleton and Brain Circuit Topology with Permutation Invariant Encoders for Neuron Classification

arXiv

引用

arXiv 2023年

作者： Liao, Minghui Wan, Guojia Du, Bo National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Institute of Artificial Intelligence Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

Determining the types of neurons within a nervous system plays a significant role in the analysis of brain connectomics and the investigation of neurological diseases. However, the efficiency of utilizing anatomical, physiological, or molecular characteristics of neurons is relatively low and costly. With the advancements in electron microscopy imaging and analysis techniques for brain tissue, we are able to obtain whole-brain connectome consisting neuronal high-resolution morphology and connectivity information. However, few models are built based on such data for automated neuron classification. In this paper, we propose NeuNet, a framework that combines morphological information of neurons obtained from skeleton and topological information between neurons obtained from neural circuit. Specifically, NeuNet consists of three components, namely Skeleton Encoder, Connectome Encoder, and Readout Layer. Skeleton Encoder integrates the local information of neurons in a bottom-up manner, with a one-dimensional convolution in neural skeleton’s point data;Connectome Encoder uses a graph neural network to capture the topological information of neural circuit;finally, Readout Layer fuses the above two information and outputs classification results. We reprocess and release two new datasets for neuron classification task from volume electron microscopy(VEM) images of human brain cortex and Drosophila brain. Experiments on these two datasets demonstrated the effectiveness of our model with accuracy of 0.9169 and 0.9363, respectively. Code and data are available at: https://***/WHUminghui/NeuNet. Copyright © 2023, The Authors. All rights reserved.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

Illuminate Low-Light Image via Coarse-to-fine Multi-level Network 27th

Illuminate Low-Light Image via Coarse-to-fine Multi-level Ne...

引用

27th International Conference on MultiMedia Modeling, MMM 2021

作者： Qiu, Yansheng Chen, Jun Wang, Xiao Jang, Kui National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China

ISBN: (纸本)9783030678319

Images under low light or against light are of low readability and visibility which in turn cause performance degradation of many computer vision tasks. As the crucial research objects for low-brightness image enhancement, reflectance as an invariant has color information, and illuminance as a variable has brightness information. Existing technologies prefer to represent the reflectance and illumination in the same network depth directly, which ignores the internal discrepancy and correlation of these two components, further causing the details vanished and artifacts noises. Consequently, we propose coarse-to-fine multi-level decouple and fusion network (CMDFN) to decompose the restoration tasks into two sub-tasks, and use decouple network (CMDN) to learn the joint features of reflectance and illumination at different network depths. To refine the joint representation and revise color information, fusion network (CMFN) is applied to promote the illuminations map by extracting the complementary and redundant information from the reflectance map. Finally, we integrate the refined illumination and reflectance to reproduce the predicted image. Especially, in CMFN, we introduce a process based on discriminate attention mechanism to balance the noise. Experimental results have demonstrated that our proposed network is superior other state of the art methods, both visually and quantitatively. © 2021, Springer Nature Switzerland AG.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

Goal-Conflict Identification Based on Local Search and Fast Boundary-Condition Verification Based on Incremental Satisfiability Filter

SSRN

引用

SSRN 2022年

作者： Luo, Weilin Wan, Hai Zhong, Hongzhen Cai, Shaowei Xiao, Zhanhao Chen, Polong School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Ministry of Education China State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences China School of Computer Science Guangdong Polytechnic Normal University Guangzhou China

Identifying boundary conditions (BCs) is of fundamental importance for goal-oriented requirements engineering. A BC can capture a divergence, a particular combination of circumstances in which the goals of the requirement cannot be satisfied as a whole. Existing approaches only handle small-scale cases and ignore the general BC, a higher quality BC, because of the complex definition of BC and high computational *** observe an interesting phenomenon that some pairs of BCs are similar in structural. It inspires us to develop a local search algorithm, named LOGION, to identify general BCs on large-scale specifications. Specifically, we utilize the structural similarity of BCs to construct the neighborhood relation of local search algorithm. Besides, we design strengthening and weakening operators of formula to capture the semantic of general BCs in local searching. In order to boost up the BC verification, we propose a lasso-based incremental satisfiability filter (LISF). LISF is to use trace checking as a light-weight pre-checking. We conduct extensive experiments to evaluate LOGION, comparing against state-of-the-art approaches. Experimental results show that LOGION produces one order of magnitude more general BCs and is the first one to handle industrial cases. It is also shown that LISF significantly boosts up the performance. © 2022, The Authors. All rights reserved.

关键词： Boundary conditions

来源：评论

学校读者我要写书评

暂无评论

Logic Path Identified Hierarchical (LPIH) Routing for LEO Satellite Network

Logic Path Identified Hierarchical (LPIH) Routing for LEO Sa...

引用

Satellite Computing (Satellite), IEEE International Conference on

作者： Fei Yan Peng Lian Hongbin Luo Zhiyuan Wang Shan Zhang School of Computer Science and Engineering Beihang University Beijing China National Laboratory for Software Developmnet Environment Beihang University Beijing China

The mobility of LEO satellites renders the routing design highly challenging for a large-scale constellation. This paper proposes a Logic Path Identified Hierarchical (LPIH) routing to overcome the challenge. LPIH is an information-centric routing scheme capable of mitigating the routing dynamics in LEO satellite networks. The key idea of LPIH consists of constellation partition and logic path identification, which enable an efficient and reliable hierarchical routing. Specifically, LPIH partitions the constellation into multiple satellite groups and keeps the link state advertisement (LSA) updated within each satellite group. Moreover, LPIH uses a unique logic path identifier (PID) to represent multiple physical links between adjacent satellite groups, which will be used in the inter-group forwarding. This way, LPIH will deliver content according to the inter-group PIDs recorded by the request packet (i.e., the PID sequence). The packet forwarding within a group is based on the inner-group routing table. Overall, LPIH appropriately decouples the inner-group and inter-group routing, which stabilizes the routing dynamics and facilitates the efficiency of forwarding in large-scale LEO constellation. We compare the performance of LPIH to the traditional information-centric approach (i.e., NLSR) via packet-level simulation on OMNET++. Results show that LPIH reduces the messaging overhead by 64.37% and improves the packet delivery ratio by 16% compared to NLSR.

关键词： Satellites Computational modeling Low earth orbit satellites Routing Reliability Object recognition

来源：评论

学校读者我要写书评

暂无评论

Next-Generation Human Activity Recognition Using Locality Constrained Linear Coding Combined With Machine Learning (NG-HAR-LCML)

引用

Healthcare Technology Letters 2025年第1期12卷

作者： Shabbir, Maryam Ahmad, Fahad Alanazi, Saad Awadh Khan, Muhammad Hassan Li, Jianqiang Mahmood, Tariq Naseem, Shahid Anwar, Muhammad Department of Computer Sciences Bahria University Punjab Lahore Pakistan Department of Computer Science Faculty of Computing & Information Technology University of the Punjab Lahore Pakistan School of Computing Faculty of Technology University of Portsmouth Portsmouth United Kingdom University of Portsmouth Portsmouth United Kingdom Department of Computer Science College of Computer and Information Sciences Jouf University Aljouf Sakaka Saudi Arabia The School of Software Engineering Beijing University of Technology Beijing China Lab CCIS Prince Sultan University Riyadh Saudi Arabia Department of Information Sciences University of Education Vehari Pakistan Faculty of Information Sciences Division Science &Technology University of Education Lahore Pakistan

Accurate Human Activity Recognition (HAR) is a critical challenge with wide-ranging applications in healthcare, assistive technologies, and human-computer interaction. Traditional feature extraction methods often struggle to capture the complex spatial and temporal dynamics of human movements, leading to suboptimal classification performance. To address this limitation, this study introduces a novel encoding approach using Locality-Constrained Linear Coding (LLC) to enhance the discriminative power of hand-crafted features extracted from low-cost wearable sensors—an accelerometer and a gyroscope. The proposed LLC-based encoding scheme enables robust feature representation, improving the accuracy of HAR models. The encoded features are classified using a diverse set of Machine Learning (ML) and Deep Learning (DL) algorithms, including Support Vector Machine (SVM), Logistic Regression (LR), Naive Bayes (NB), K-Nearest Neighbours (KNN), AdaBoost, Gradient Boosting Machine (GBM), and Deep Belief Network (DBN). Extensive quantitative evaluations demonstrate that LLC significantly outperforms conventional feature encoding techniques, leading to improved classification accuracy. Among the tested models, DBN achieves a state-of-the-art accuracy of 99%, highlighting its superiority for HAR tasks. The contributions of this research are threefold: (1) it establishes the necessity of an advanced encoding scheme (LLC) for feature enhancement in HAR, (2) it provides a rigorous comparative analysis of multiple ML and DL classifiers, and (3) it introduces a scalable and cost-effective HAR framework suitable for real-world applications. Performance is comprehensively assessed using robust evaluation metrics such as Area Under the Curve (AUC), Classification Accuracy (CA), F1 Score, Precision, Recall, and Matthews Correlation Coefficient (MCC). The findings of this study offer new insights into feature encoding for HAR, setting a foundation for future advancements in sensor-based act

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Improving Complex Reasoning over Knowledge Graph with Logic-Aware Curriculum Tuning

arXiv

引用

arXiv 2024年

作者： Xia, Tianle Ding, Liang Wan, Guojia Zhan, Yibing Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia JD Explore Academy China College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

Answering complex queries over incomplete knowledge graphs (KGs) is a challenging task. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However, they are bottlenecked by the inability to share world knowledge to improve logical reasoning, thus resulting in suboptimal performance. In this paper, we propose a complex reasoning schema over KG upon large language models (LLMs), containing a curriculum-based logical-aware instruction tuning framework, named LACT. Specifically, we augment the arbitrary first-order logical queries via binary tree decomposition, to stimulate the reasoning capability of LLMs. To address the difficulty gap among different types of complex queries, we design a simple and flexible logic-aware curriculum learning framework. Experiments across widely used datasets demonstrate that LACT has substantial improvements (brings an average +5.5% MRR score) over advanced methods, achieving the new state-of-the-art. Copyright © 2024, The Authors. All rights reserved.

关键词： Binary trees

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：