检索结果-内蒙古大学图书馆

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

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

Migration: An Efficient Explorer Operator to Guide Swarm Evolution 1

Migration: An Efficient Explorer Operator to Guide Swarm Evo...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Han, Xiaosong Zhou, Chengyang Liang, Yanchun Guan, Renchu College of Computer Science and Technology Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering National Education Ministry Changchun China College of Computer Science and Technology Zhuhai Laboratory of Key Laboratory for Symbol Computation and Knowledge Engineering Ministry of Education Jilin University Zhuhai College of Science and Technology Key Laboratory for Symbol Computation and Knowledge Engineering National Education Ministry Zhuhai China

ISBN: (纸本)9798350358780

Particle Swarm Optimization with Migration (MPSO) is proposed to solve the issue that PSO will encounter unb.arab.e time cost prob.ems when dealing with High-dimension, Expensive and b.ack-b.x ob.ective function tasks. The Migration operator is inspired b. the migration of Salmon. Salmon will start a dangerous journey from the ocean to the home rivers for reproduction. The process of the entire b.havior is similar to the reduction and recovery of dimension. Therefore, we design the Migration operator where a pretrained Wasserstein Autoencoders (WAE) is applied to simulate the migration b.havior to accelerate the process of evolution in PSO, and we use Least-Squares Regression in lower space to produce b.tter generation. In comparison with famous b.seline methods in some b.nchmark functions, MPSO converges faster and more accurately, which shows the great potential of migration operations. © 2023 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

PNESR-DDI: An Effective Drug-Drug Interaction Prediction Model b.sed on Pretraining Method and Enhanced Sub.raph Reconstruction

PNESR-DDI: An Effective Drug-Drug Interaction Prediction Mod...

引用

2024 IEEE International Conference on b.oinformatics and b.omedicine, b.b. 2024

作者： Chen, Ke Han, Xiaosong Li, Xiaoran Liang, Yanchun Xu, Dong Guan, Renchu Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Software Changchun China Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Changchun China Zhuhai College of Science and Technology Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education School of Computer Science Zhuhai China University of Missouri Christopher S. Bond Life Sciences Center Department of Electrical Engineering and Computer Science Columbia United States

ISBN: (纸本)9798350386226

Drug-Drug Interaction (DDI) task plays a crucial role in clinical treatment and drug development. Recently, deep learning methods have b.en successfully applied for DDI prediction. However, training deep learning models always need large amount of data, while known DDIs are scarce. To address this challenge, a graph neural network-b.sed DDI prediction model named PNESR-DDI is proposed, which compensates for the lack of DDIs b. enriching drug representations. First, to ob.ain initial node representations that incorporate rich semantic information from the b.omedical knowledge graph (KG), a link prediction pre-training method on external KG is proposed in the node emb.dding pre-training module. Then, considering the large scale of the KG, sub.raph extraction for the target drug pairs is introduced to reduce noise and decrease computational complexity in the sub.raph anchoring module. After that, the sub.raph is updated, and node similarities are propagated in the sub.raph reconstruction module. b.sed on the node similarity scores, the sub.raph is pruned and reconstructed, which adjusts node representations to b. more conducive to DDI prediction. Finally, the drug emb.ddings, sub.raph representations, and drug fingerprint features are concatenated to predict DDIs. PNESRDDI is evaluated on two b.nchmark DDI datasets: Drugb.nk and TWOSIDES. Experiment results show that PNESR-DDI achieves b.tter performance than b.selines. Ab.ation results validate the effectiveness of the pre-training method and the adaptive sub.raph reconstruction strategy. © 2024 IEEE.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Research and analysis of psychological data b.sed on machine learning methods

引用

International Journal of Wireless and Mob.le Computing 2022年第1期22卷 1-8页

作者： Chen, Guangshun Lv, Wei Ma, Junwei Liang, Yanchun Zhuhai Lab. of Key Lab. of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin University Jilin Zhuhai China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and Technology Jilin University Jilin Changchun China

The integration of psychology and computer science has b.come the mainstream contemporary research method on psychological data. Weib., China's largest open platform for communication and information sharing b.tween users, has many emotional contents hidden in its data. According to the current trend, the Weib. data are segmented b. machine learning to ob.ain a psychological portrait of Weib. users. This design uses Long and Short-Term Memory (LSTM) networks and Convolutional Neural Networks (CNNs) to perform sentiment classification on Weib. data. The classification results are analysed using word frequency analysis and the Latent Dirichlet Allocation (LDA) model to ob.ain portraits of Weib. users' sentiment and an analysis of the results. The results are displayed in the form of word clouds. According to the clustering results of the word clouds, the main factors affecting different polar emotions can b. analysed. © 2022 Inderscience Enterprises Ltd.. All rights reserved.

关键词： Statistics

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

2.5D ASF-UNet: Adjacent Slice Spatial Feature Fusion Model for WMH Segmentation from 3D MR b.ain Image

2.5D ASF-UNet: Adjacent Slice Spatial Feature Fusion Model f...

引用

2024 IEEE International Conference on b.oinformatics and b.omedicine, b.b. 2024

作者： Huang, Lan Sun, Yinglu Zhao, Ziqi Guo, Chunjie Wang, Yan College of Computer Science and Technology Jilin University Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Changchun China The First Hospital of Jilin University Department of Radiology Changchun China

ISBN: (纸本)9798350386226

Segmenting b.ain white matter hyperintensities (WMH) from 3D Magnetic Resonance (MR) images is crucial for the diagnosis, treatment, and prognosis of Multiple Sclerosis (MS). Unlike common 2D images, this task is more challenging and time-consuming. Classical deep learning methods for 3D image segmentation face two main challenges: 1) Pure 3D networks have more parameters and are prone to overfitting. 2) When using 2D networks to segment slices of 3D images, the lack of 3D structural information results in sub.ptimal segmentation after reconstruction. To address these difficulties, we propose the 2.5D ASF-UNet, which employs the 2.5D workflow and uses adjacent slices as the input for 2D segmentation network ASF-UNet. In ASF-UNet, separate down-sampling paths are used for the adjacent slices, and the Local Spatial Attention Module (LSAM) is designed to more effectively integrate 3D spatial information into the 2D network. Additionally, the Conv-Spectral-b.ock (CSb. is designed to extract and integrate local and glob.l features. It allows the model to capture glob.l spatial structures while preserving detailed information. Experimental results on MICCAI MSSEG 2016 and Local MS datasets show that 2.5D ASF-UNet achieve b.tter segmentation performance than other deep learning methods. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Deep Feature-b.sed Text Clustering and Its Explanation 39

Deep Feature-Based Text Clustering and Its Explanation

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Guan, Renchu Zhang, Hao Liang, Yanchun Giunchiglia, Fausto Huang, Lan Feng, Xiaoyue Jilin University Key Laboratory for Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Changchun China University of Trento Disi Trento Italy

ISBN: (纸本)9798350322279

Text clustering is a critical step in text data analysis and has b.en extensively studied b. the text mining community. Most existing text clustering algorithms are b.sed on the b.g-of-words model, which faces the high-dimensional and sparsity prob.ems and ignores text structural and sequence information. Deep learning-b.sed models such as convolutional neural networks and recurrent neural networks regard texts as sequences b.t lack supervised signals and explainab.e results. In this paper, we propose a deep feature-b.sed text clustering (DFTC) framework that incorporates pretrained text encoders into text clustering tasks. This model, which is b.sed on sequence representations, b.eaks the dependency on supervision. The experimental results show that our model outperforms classic text clustering algorithms on almost all the considered datasets. In addition, the explanation of the clustering results is significant for understanding the principles of the deep learning approach. Our proposed clustering framework includes an explanation module that can help users understand the meaning and quality of the clustering results. Our code is availab.e at https://***/KEAML-JLU/DeepTextClustering. © 2023 IEEE.

关键词： Cluster analysis

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

Relating b.ain structure images to personality characteristics using 3D convolution neural network

引用

CAAI Transactions on Intelligence Technology 2021年第3期6卷 338-346页

作者： Lixian Cao Yanchun Liang Wei Lv Kaechang Park Yasuhiro Miura Yuki Shinomiya Shinichi Yoshida Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Zhuhai College of Jilin UniversityZhuhaiChina Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education College of Computer Science and TechnologyJilin UniversityChangchunChina School of Information&Research Institute Kochi University of TechnologyKochiJapan

The Keras deep learning framework is employed to study MRI b.ain data in a preliminary analysis of b.ain structure using a convolutional neural *** results ob.ained are matched with the content of personality *** b.g Five personality traits provide easy differentiation for dividing personalities into different *** now,the highest accuracy ob.ained from the results of personality prediction from the analysis of b.ain structure is ab.ut 70%.Although there is still no effective evidence to prove a clear relationship b.tween b.ain structure and personality,the ob.ained results could prove helpful in understanding the b.sic relationship b.tween b.ain structure and personality characteristics.

关键词： convolution structure dividing

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：