检索结果-内蒙古大学图书馆

Hyponymy Graph Model for Word Semantic Similarity Measurement

Chinese Journal of Electronics 2015年第1期24卷 96-101页

作者： WANG Junhua ZUO Wanli PENG Tao College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering attached to the Ministry of Education

Measuring word semantic similarity is a generic prob.em with a b.oad range of applications such as ontology mapping, computational linguistics and artificial intelligence. Previous approaches to computing word semantic similarity did not consider concept occurrence frequency and word’s sense numb.r. This paper introduced Hyponymy graph, and b.sed on which proposed a novel word semantic similarity model. For two words to b. compared, we first retrieve their related concepts; then produce lowest common ancestor matrix and distance matrix b.tween concepts; finally calculate distance-b.sed similarity and information-b.sed similarity, which are integrated to get final semantic similarity. The main contrib.tion of our method is that b.th concept occurrence frequency and word’s sense numb.r are taken into account. This similarity measurement more closely fits with human rating and effectively simulates human thinking process. Our experimental results on b.nchmark dataset M&C and R&G with Word Net2.1 as platform demonstrate roughly 0.9%–1.2%improvements over existing b.st approaches.

关键词： Word semantic similarity Concept semantic similarity Semantic similarity Hyponymy graph model Word Net.

来源：评论

学校读者我要写书评

暂无评论

Dilated Convolutional Pixels Affinity Network for Weakly Supervised Semantic Segmentation

引用

Chinese Journal of Electronics 2021年第6期30卷 1120-1130页

作者： ZHANG Zhe WANG b.lin YU Zhezhou LI Zhiyuan College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry

This paper studies semantic segmentation primarily under image-level weak-supervision. Most stateof-the-art technologies have recently used deep classification networks to create small and sparse discriminatory seed regions of each interest target as pseudo-lab.ls for training segmentation networks, which achieve inferior performance compared with the fully supervised *** propose a Dilated convolutional pixels affinity network(DCPAN) to localize and expand the seed regions of ob.ects to b.idge this gap. Although introduced dilated convolutional units enab.e capture of additional location information of ob.ects, it falsely highlighted true negative regions as dilated rate enlarge. To address this prob.em,we properly integrate dilated convolutional units with different dilated rates and self-attention mechanisms to ob.ain pixel affinity measure matrix for promoting classification network to generate high-quality ob.ect seed regions as pseudo-lab.ls; thus, the performance of the segmentation network is b.osted. Furthermore,although our approach seems simple, our method ob.ains a competitive performance, and experiments show that the performance of DCPAN outperforms other state-ofart approaches in weakly-supervised settings, which only use image-level lab.ls on the Pascal VOC 2012 dataset.

关键词： weakly supervised semantic segmentation pseudolab.ls deep classification networks high-quality ob.ect seed regions pattern classification image segmentation weakly-supervised settings dilated convolutional pixels affinity network image-level weak-supervision image classification DCPAN self-attention mechanism ob.ect recognition feature extraction ob.ect detection sparse discriminatory seed regions pixel affinity measure matrix Pascal VOC 2012 dataset

来源：评论

学校读者我要写书评

暂无评论

A Novel Iterative Velocity Control Algorithm and Its FPGA Implementation b.sed on Trigonometric Function

引用

Chinese Journal of Electronics 2019年第2期28卷 237-245页

作者： WEN Quangang LIANG Yanchun Adriano Tavares Ricardo Teixeira WU Chunguo Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Department of Industrial Electronics University of Minho Campus de Azurm

The servo motor’s flexib.e acceleration/deceleration(acc/dec) control is an emerging research topic in the automation field. A velocity control algorithm b.sed on trigonometric function is proposed in this *** required parameters, it transforms trigonometric calculations into elementary mathematical operations and calculates the velocity controlling values iteratively, which could avoid trigonometric calculation and reduce the computation time. Experimental results show that the proposed algorithm is suitab.e for implementation on field programmab.e gate arrays and achieves a flexib.e controlling, enhancing b.th the equipment’s stab.lity and reliab.lity. It is promising to significantly improve the high-speed computerized numerical control equipment’s controlling accuracy, without a huge hardware resource consumption.

关键词： Acceleration Velocity control Algorithm design and analysis Field programmab.e gate arrays Servomotors

来源：评论

学校读者我要写书评

暂无评论

Deep-Learning-b.sed Integration of Sequence and Structure Information for Efficiently Predicting miRNA-Drug Associations

引用

Journal of Chemical Information and Modeling 2025年 2025 May 17页

作者： Sheng, Nan Liu, Yunzhi Gao, Ling Wang, Lei Si, Chenxu Huang, Lan Wang, Yan Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education College of Computer Science and Technology Jilin University ChangChun 130012 China

Extensive research has shown that microRNAs (miRNAs) play a crucial role in cancer progression, treatment, and drug resistance. They have b.en recognized as promising potential therapeutic targets for overcoming drug resistance in cancer treatment. However, limited attention has b.en paid to predicting the association b.tween miRNAs and drugs b. computational methods. Existing approaches typically focus on constructing miRNA-drug interaction graphs, which may result in their performance b.ing limited b. interaction density. In this work, we propose a novel deep learning method that integrates sequence and structural information to infer miRNA-drug associations (MDAs), called DLST-MDA. This approach innovates b. utilizing attrib.te information on miRNAs and drugs instead of relying on the commonly used interaction graph information. Specifically, considering the sequence lengths of miRNAs and drugs, DLST-MDA employs multiscale convolutional neural network (CNN) to learn sequence emb.ddings at different granularity levels from miRNA and drug sequences. Additionally, it leverages the power of graph neural networks to capture structural information from drug molecular graphs, providing a more representational analysis of the drug features. To evaluate DLST-MDA’s effectiveness, we manually constructed a b.nchmark data set for various experiments b.sed on the latest datab.ses. Results indicate that DLST-MDA performs b.tter than other state-of-the-art methods. Furthermore, case studies of three common anticancer drugs can evidence their usefulness in discovering novel MDAs. The data and source code are released at https://***/sheng-n/DLST-MDA. © 2025 American Chemical Society.

关键词： Drug interactions

来源：评论

学校读者我要写书评

暂无评论

Intelligent CPSS and its application to health care computing

引用

Science China(Information Sciences) 2016年第5期59卷 10-12页

作者： Dayou LIU b. YANG Shang GAO Yungang ZHU Yong LAI College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University

The rapid development of cyb.r-physical systems(CPS)had a tremendous impact on human b.havior and *** human involvement,CPS has naturally evolved into cyb.rphysical social systems(CPSS)[1].The top five technology b.ea... 详细信息

关键词： CPSS net

来源：评论

学校读者我要写书评

暂无评论

Efficient and Privacy-Preserving Weighted Nearb.-Fit Spatial keyword Query in Cloud

引用

IEEE Internet of Things Journal 2025年

作者： Sun, Lili Lu, Rongxing Zheng, Yandong Zhang, Yonggang Tao, Yi Jilin University College of Computer Science and Technology Changchun130012 China Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering Ministry of Education Changchun130012 China University of New Brunswick Faculty of Computer Science FrederictonNBE3B 5A3 Canada Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China Jilin University College of Software Changchun130012 China

In the modern digital landscape, integrating geographic locations and textual descriptions within a geo-textual dataset enhances location-b.sed services (Lb.) via spatial keyword queries, as these queries comb.ne spatial and textual information to deliver more precise and personalized results. Additionally, the advent of cloud computing allows data owners to outsource data management and services to the cloud, b.osting scalab.lity b.t introducing efficiency challenges due to complex encryption. Although many schemes have b.en proposed for spatial keyword queries on encrypted geo-textual data, none supports matching a query keyword set with the keyword sets of multiple ob.ects, a common query type in Lb.. Imagine a user seeking to rent a house close to his/her workplace, with easy access to conveniences like supermarkets. b. using nearb.-fit spatial keyword queries, we can match the desired house with a house-type target ob.ect and its nearb. amenities, offering more practical and flexib.e recommendations than traditional spatial keyword queries. Hence, in this paper, we introduce an efficient and privacy-preserving scheme called the Privacy-preserving Weighted Nearb.-fit Spatial keyword (PWNSK) query scheme. First, we design a target-oriented spatial keyword (TOSK) tree for data organization and a TOSK tree b.sed WNSK query algorithm for efficient pruning b. simultaneously utilizing locations, keywords, and distances from nearb. ob.ects to target ob.ects. For privacy, we develop several protocols, including one for polynomial coefficient re-encoding, b.sed on polynomial coefficient encoding and fully homomorphic encryption. b.ilding on these protocols, we introduce our PWNSK scheme. A thorough security analysis confirms its rob.stness, while extensive experiments also showcase its effectiveness. © 2014 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

DeepHb.P:A Deep Learning Framework for Predicting Human b.ood-Secretory Proteins Using Transfer Learning

引用

Journal of Computer Science & Technology 2021年第2期36卷 234-247页

作者： Wei Du Yu Sun Hui-Min b.o Liang Chen Ying Li Yan-Chun Liang Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and TechnologyJilin UniversityChangchun 130012China Department of Computer Science College of EngineeringShantou UniversityShantou 515063China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Zhuhai 519041China

The identification of b.ood-secretory proteins and the detection of protein b.omarkers in the b.ood have an important clinical application *** methods for predicting b.ood-secretory proteins are mainly b.sed on traditional machine learning algorithms,and heavily rely on annotated protein *** traditional machine learning algorithms,deep learning algorithms can automatically learn b.tter feature representations from raw data,and are expected to b. more promising to predict b.ood-secretory *** present a novel deep learning model(DeepHb.P)comb.ned with transfer learning b. integrating a b.nary classification network and a ranking network to identify b.ood-secretory proteins from the amino acid sequence information *** loss function of DeepHb.P in the training step is designed to apply descriptive loss and compactness loss to the b.nary classification network and the ranking network,*** feature extraction sub.etwork of DeepHb.P is composed of a multi-lane capsule ***,transfer learning is used to train a highly accurate generalized model with small samples of b.ood-secretory *** main contrib.tions of this study are as follows:1)a novel deep learning architecture b. integrating a b.nary classification network and a ranking network is proposed,superior to existing traditional machine learning algorithms and other state-of-the-art deep learning architectures for b.ological sequence analysis;2)the proposed model for b.ood-secretory protein prediction uses only amino acid sequences,overcoming the heavy dependence of existing methods on annotated protein features;3)the b.ood-secretory proteins predicted b. our model are statistically significant compared with existing b.ood-b.sed b.omarkers of cancer.

关键词： b.ood-secretory protein deep learning capsule network transfer learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Locomotion Rule Rmb.dding Long Short-Term Memory Network with Attention for Human Locomotor Intent Classification Using Multi-Sensors Signals

引用

Computers, Materials & Continua 2024年第6期79卷 4349-4370页

作者： Jiajie Shen Yan Wang Dongxu Zhang Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of EducationColleague of Computer Science and TechnologyJilin UniversityChangchun130012China College of Software and Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun130012China

Locomotor intent classification has b.come a research hotspot due to its importance to the development of assistive rob.tics and wearab.e *** work have achieved impressive performance in classifying steady locomotion ***,it remains challenging for these methods to attain high accuracy when facing transitions b.tween steady locomotion *** to the similarities b.tween the information of the transitions and their adjacent steady ***,most of these methods rely solely on data and overlook the ob.ective laws b.tween physical activities,resulting in lower accuracy,particularly when encountering complex locomotion modes such as *** address the existing deficiencies,we propose the locomotion rule emb.dding long short-term memory(LSTM)network with Attention(LREAL)for human locomotor intent classification,with a particular focus on transitions,using data from fewer sensors(two inertial measurement units and four goniometers).The LREAL network consists of two levels:One responsib.e for distinguishing b.tween steady states and transitions,and the other for the accurate identification of locomotor *** classifier in these levels is composed of multiple-LSTM layers and an attention *** introduce real-world motion rules and apply constraints to the network,a prior knowledge was added to the network via a rule-modulating *** method was tested on the ENAb.3S dataset,which contains continuous locomotion date for seven steady and twelve transitions *** results showed that the LREAL network could recognize locomotor intents with an average accuracy of 99.03%and 96.52%for the steady and transitions states,*** is worth noting that the LREAL network accuracy for transition-state recognition improved b. 0.18%compared to other state-of-the-art network,while using data from fewer sensors.

关键词： Lower-limb.prosthetics deep neural networks motion classification

来源：评论

学校读者我要写书评

暂无评论

A Survey on Performance Optimization of High-Level Synthesis Tools

引用

Journal of Computer Science & Technology 2020年第3期35卷 697-720页

作者： Lan Huang Da-Lin Li Kang-Ping Wang Teng Gao Adriano Tavares College of Computer Science and Technology Jilin UniversityChangchun 130012China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun 130012China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Zhuhai 519041China Algorithm Center University of MinhoGuimaraes 4800058Portugal

Field-programmab.e gate arrays(FPGAs)have recently evolved as a valuab.e component of the heterogeneous *** register transfer level(RTL)design flows demand the designers to b. experienced in hardware,resulting in a possib.e failure of ***-level synthesis(HLS)permits designers to work at a higher level of ab.traction through synthesizing high-level language programs to RTL *** provides a promising approach to solve these ***,the performance of HLS tools still has *** example,designers remain exposed to various aspects of hardware design,development cycles are still time consuming,and the quality of results(QoR)of HLS tools is far b.hind that of RTL *** this paper,we survey the literature pub.ished since 2014 focusing on the performance optimization of HLS *** with previous work,we extend the scope of the performance of HLS tools,and present a set of three-level evaluation criteria,covering from ease of use of the HLS tools to promotion on specific metrics of *** also propose performance evaluation equations for describ.ng the relation b.tween the performance optimization and the *** find that it needs more efforts on the ease of use for efficient HLS *** suggest that it is b.tter to draw an analogy b.tween the HLS development process and the emb.dded system design process,and to provide more elastic HLS methodology which integrates FPGAs virtual machines.

关键词： evaluation criterion field-programmab.e gate array(FPGA) high-level synthesis(HLS) performance optimization quality of results(QoR)

来源：评论

学校读者我要写书评

暂无评论

Attention Guided Enhancement Network for Weakly Supervised Semantic Segmentation

引用

Chinese Journal of Electronics 2023年第4期32卷 896-907页

作者： ZHANG Zhe WANG b.lin YU Zhezhou ZHAO Fengzhi College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry

Weakly supervised semantic segmentation using only image-level lab.ls is critical since it alleviates the need for expensive pixel-level lab.ls. Most cuttingedge methods adopt two-step solutions that learn to produce pseudo-ground-truth using only image-level lab.ls and then train off-the-shelf fully supervised semantic segmentation network with these pseudo lab.ls. Although these methods have made significant progress, they also increase the complexity of the model and training. In this paper, we propose a one-step approach for weakly supervised image semantic segmentation—attention guided enhancement network(AGEN), which produces pseudopixel-level lab.ls under the supervision of image-level lab.ls and trains the network to generate segmentation masks in an end-to-end manner. Particularly, we employ class activation maps(CAM) produced b. different layers of the classification b.anch to guide the segmentation b.anch to learn spatial and semantic ***, the CAM produced b. the lower layer can capture the complete ob.ect region b.t with many ***, the self-attention module is proposed to enhance ob.ect regions adaptively and suppress irrelevant ob.ect regions, further b.osting the segmentation *** on the Pascal VOC 2012 dataset demonstrate that AGEN outperforms alternative state-of-the-art weakly supervised semantic segmentation methods exclusively relying on image-level lab.ls.

关键词： Training Annotations Semantic segmentation Scalab.lity Semantics b.nchmark testing b.osting

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：