检索结果-内蒙古大学图书馆

DMFVAE:miRNA-disease associations prediction based on deep matrix factorization method with variational autoencoder

Frontiers of Computer Science 2024年第6期18卷 259-270页

作者： Pijing WEI Qianqian WANG Zhen GAO Ruifen CAO Chunhou ZHENG Information Materials and Intelligent Sensing Laboratory of Anhui Province Institutes of Physical Science and Information TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and TechnologyAnhui UniversityHefei 230601China Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial IntelligenceAnhui UniversityHefei 230601China

MicroRNAs(miRNAs)are closely related to numerous complex human diseases,therefore,exploring miRNA-disease associations(MDAs)can help people gain a better understanding of complex disease *** increasing number of computational methods have been developed to predict ***,the sparsity of the MDAs may hinder the performance of many *** addition,many methods fail to capture the nonlinear relationships of miRNA-disease network and inadequately leverage the features of network and neighbor *** this study,we propose a deep matrix factorization model with variational autoencoder(DMFVAE)to predict potential *** first decomposes the original association matrix and the enhanced association matrix,in which the enhanced association matrix is enhanced by self-adjusting the nearest neighbor method,to obtain sparse vectors and dense vectors,***,the variational encoder is employed to obtain the nonlinear latent vectors of miRNA and disease for the sparse vectors,and meanwhile,node2vec is used to obtain the network structure embedding vectors of miRNA and disease for the dense ***,sample features are acquired by combining the latent vectors and network structure embedding vectors,and the final prediction is implemented by convolutional neural network with channel *** evaluate the performance of DMFVAE,we conduct five-fold cross validation on the HMDD v2.0 and HMDD v3.2 datasets and the results show that DMFVAE performs ***,case studies on lung neoplasms,colon neoplasms,and esophageal neoplasms confirm the ability of DMFVAE in identifying potential miRNAs for human diseases.

关键词： miRNA-disease association deep matrix factorization self-adjusted nearest neighbor variational encoder network structure

来源：评论

学校读者我要写书评

暂无评论

Inductive Relation Prediction by Disentangled Subgraph Structure

引用

Tsinghua Science and technology 2024年第5期29卷 1566-1579页

作者： Guiduo Duan Rui Guo Wenlong Luo Guangchun Luo Tianxi Huang Laboratory of Intelligent Collaborative Computing University of Electronic Science and Technology of ChinaChengdu 611731Chinaand also with Trusted Cloud Computing and Big Data Key Laboratory of Sichuan ProvinceChengdu 611731China School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731China Hangzhou NetEase Cloud Music Technology Co. Ltd.Hangzhou 310052China Department of Fundamental Courses Chengdu Textile CollegeChengdu 611700China

Currently,most existing inductive relation prediction approaches are based on subgraph structures,with subgraph features extracted using graph neural networks to predict ***,subgraphs may contain disconnected regions,which usually represent different semantic *** not all semantic information about the regions is helpful in relation prediction,we propose a relation prediction model based on a disentangled subgraph structure and implement a feature updating approach based on relevant semantic *** indirectly achieve the disentangled subgraph structure from a semantic perspective,the mapping of entity features into different semantic spaces and the aggregation of related semantics on each semantic space are *** disentangled model can focus on features having higher semantic relevance in the prediction,thus addressing a problem with existing approaches,which ignore the semantic differences in different subgraph ***,using a gated recurrent neural network,this model enhances the features of entities by sorting them by distance and extracting the path information in the ***,it is shown that when there are numerous disconnected regions in the subgraph,our model outperforms existing mainstream models in terms of both Area Under the Curve-Precision-Recall(AUC-PR)and Hits@*** prove that semantic differences in the knowledge graph can be effectively distinguished and verify the effectiveness of this method.

关键词： disentangled subgraph structure knowledge graph completion Gated Recurrent Unit(GRU) feature updating

来源：评论

学校读者我要写书评

暂无评论

ProXplore: A GPU-Enhanced Protein Discovery Engine

ProXplore: A GPU-Enhanced Protein Discovery Engine

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Sun, Zewen Zhang, Peiheng Fu, Xingzhuo Li, Xueqi Cas Institute of Intelligent Computing Technology Suzhou China University of Chinese Academy of Sciences China Cas State Key Lab of Processors Institute of Computing Technology China

ISBN: (纸本)9798350386226

Language models have achieved unprecedented success in natural language processing tasks and have recently been adapted for biological sequences. However, GPUs still encounter significant performance bottlenecks when running BERT-style natural language models. Moreover, due to the vastly greater number of tokens in protein sequences compared to human languages (as illustrated in Figure 1), directly transferring language models from human languages to proteins results in significant changes in runtime behavior. Consequently, optimizations designed for short-input BERT models are less effective for protein language *** this paper, we propose a novel GPU-based cross-layer optimization strategy. From an architectural perspective, our approach leverages intra- and inter-operator parallelism, multilevel data computation and warp parallelism to fully utilize GPU features. From an algorithmic perspective, we address the issue of varying lengths in protein input sequences and reduce memory overhead through padding removal. Experimental results demonstrate that ProXplore achieves a 1.8× increase in inference speed on the TAPE benchmark without a significant loss in prediction accuracy. This improvement effectively overcomes performance bottlenecks and provides substantial benefits for protein sequence analysis and other bioinformatics applications. © 2024 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Non-uniform Compressive Sensing Imaging Based on Image Saliency

引用

Chinese Journal of Electronics 2023年第1期32卷 159-165页

作者： LI Hongliang DAI Feng ZHAO Qiang MA Yike CAO Juan ZHANG Yongdong University of Chinese Academy of Sciences Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences University of Science and Technology of China

For more effective image sampling, compressive sensing(CS) imaging methods based on image saliency have been proposed in recent years. Those methods assign higher measurement rates to salient regions,but lower measurement rate to non-salient regions to improve the performance of CS imaging. However, those methods are block-based, which are difficult to apply to actual CS sampling, as each photodiode should strictly correspond to a block of the scene. In our work, we propose a non-uniform CS imaging method based on image saliency, which assigns higher measurement density to salient regions and lower density to non-salient regions,where measurement density is the number of pixels measured in a unit size. As the dimension of the signal is reduced, the quality of reconstructed image will be improved theoretically, which is confirmed by our experiments. Since the scene is sampled as a whole, our method can be easily applied to actual CS sampling. To verify the feasibility of our approach, we design and implement a hardware sampling system, which can apply our non-uniform sampling method to obtain measurements and reconstruct the images. To our best knowledge, this is the first CS hardware sampling system based on image saliency.

关键词： Measurement units Density measurement Imaging Image sampling Size measurement Hardware Sensors

来源：评论

学校读者我要写书评

暂无评论

TransCaller: An End-to-end Accelerated Transformer-based Nanopore Basecaller on GPUs

TransCaller: An End-to-end Accelerated Transformer-based Nan...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Xu, Di Zhang, Peiheng Zhang, Yang Shi, Shunchen Li, Xueqi Institute of Computing Technology State Key Lab of Processors China University of Chinese Academy of Sciences China Institute of Intelligent Computing Technology Suzhou China

ISBN: (纸本)9798350337488

Basecalling is a crucial step in nanopore sequencing as it transforms the raw electrical signal obtained from the nanopore into a readable sequence. The accuracy of basecalling directly affects the quality and reliability of the sequenced data. Various algorithms and models are employed to perform accurate basecalling, with advancements in deep learning techniques. However, due to the difficulty of combining feature extraction capability, high parallelism and long sequence modeling capability of existing models, the accuracy and speed of basecalling model are still bottlenecks in data *** this paper, we present TransCaller, an end-to-end accelerated transformer-based nanopore basecaller model. TransCaller comprises a low-parameter electrical signal sampler, a fully transformer-based encoder integrating multiple algorithm-specific modules, and a CTC decoder enhanced with a filter. To further refine and enhance the TransCaller model, we introduce a three-stage pyramid model structure and leverage knowledge distillation techniques to balance the accuracy and speed. Experimental results on 9 datasets demonstrate that TransCaller achieves an average accuracy of 92.95%, surpassing the state-of-the-art Bonito sup model by a margin of 0.65% to 2.34%. Moreover, the distilled TransCallermodel showcases a remarkable 2.97× acceleration in inference speed compared to the original model, effectively catering to the variegated requirements of distinct inference speeds and precision levels across a wide spectrum of scenarios. © 2023 IEEE.

关键词： Basecalling GPUs Parallelism Transformer

来源：评论

学校读者我要写书评

暂无评论

Reversible Data Hiding for 3D Mesh Model Based on Block Modulus Encryption and Multi-MSB Prediction 10th

Reversible Data Hiding for 3D Mesh Model Based on Block Modu...

引用

10th International Conference of Pioneering Computer Scientists, Engineers and Educators, ICPCSEE 2024

作者： Fu, Zihao Gao, Yang Lyu, Wanli Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China

ISBN: (纸本)9789819787456

Reversible data hiding in encrypted domain (RDH-ED) fortifies data security and privacy safeguards while upholding the original data’s integrity and accessibility. Current research on RDH-ED focuses on 2D images, while research on 3D mesh models is still immature. This paper introduces an RDH-ED method using block modulus encryption and multi-MSB prediction. Initially, the original mesh model is partitioned into non-overlapping subblocks of equal size, and then the vertices in each subblock are encrypted with the same key for additive modulus encryption, ensuring that the spatial correlation present in the original mesh subblocks remains preserved within the encrypted subblocks. Subsequently, the subblocks are disrupted one by one using the 3D Arnold Transform to enhance security. The vertices in each embeddable subblock are divided into a reference vertex and several embeddable vertices, where the multi-MSB prediction strategy is employed to allocate embedding room for each embeddable vertex. Finally, the secret information is embedded into the allocated room. Since the proposed method almost completely preserves the spatial correlation within each subblock, the achieved embedding rate surpasses that of all previous outstanding methods that rely on vacating room after encryption (VRAE). The experimental findings demonstrate that the proposed approach achieves an average embedding rate of 45.55 bits per vertex (bpv), surpassing the state-of-the-art method that achieves 25.63 bpv. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Flexible TiO_(2)-WO_(3−x) hybrid memristorwith enhanced linearity and synaptic plasticity for precise weight tuning in neuromorphic computing

引用

npj Flexible Electronics 2024年第1期8卷 180-191页

作者： Jianyong Pan Hao Kan Zhaorui Liu Song Gao Enxiu Wu Yang Li Chunwei Zhang Shandong Provincial Key Laboratory of Network Based Intelligent Computing School of Information Science and EngineeringUniversity of JinanJinanChina State Key Lab of Transducer Technology Shanghai Institute of Microsystem and Information TechnologyChinese Academy of SciencesShanghaiChina School of Integrated Circuits Shandong UniversityJinanChina

Tungsten oxide(WO_(3))-based memristors show promising applications in neuromorphic ***,single-layer WO_(3) memristors suffer from issues such as weak memory performance and nonlinear conductance *** this work,a functional layer based on the hybrids of WO_(3−x) and TiO_(2) is proposed for constructing flexible memristors featuring outstanding synaptic *** diverse electrical stimulations to the memristor enables a range of synaptic functions,elucidating its conduction mechanism through the conductive filament *** incorporation of TiO_(2) not only enhances the memristor’s memory characteristics but makes its conductance more linear,symmetrical and uniform during the long-term ***,in view of the enhanced device performance by TiO_(2) doping,the potential of this device for simple behavioral simulation and processing of complex computing problems is ***“learning-forgetting-relearning”characteristics and device integrability are visually *** the device to a convolutional neural network,the recognition accuracy of MNIST handwritten digits reaches 98.7%.

关键词： computing tuning precise

来源：评论

学校读者我要写书评

暂无评论

Multi-user reinforcement learning based task migration in mobile edge computing

引用

Frontiers of Computer Science 2024年第4期18卷 161-173页

作者： Yuya CUI Degan ZHANG Jie ZHANG Ting ZHANG Lixiang CAO Lu CHEN Tianjin Key Lab of Intelligent Computing and Novel Software Technology Tianjin University of TechnologyTianjin 300384China School of Internet of Things Engineering Jiangsu Vocational College of Information TechnologyWuxi 214153China School of Electronic and Information Engineering Beijing Jiaotong UniversityBeijing 100044China School of Sports Economics and Management Tianjin University of SportTianjin 301617China

Mobile Edge computing(MEC)is a promising *** service migration is a key technology in *** order to maintain the continuity of services in a dynamic environment,mobile users need to migrate tasks between multiple servers in real *** to the uncertainty of movement,frequent migration will increase delays and costs and non-migration will lead to service ***,it is very challenging to design an optimal migration *** this paper,we investigate the multi-user task migration problem in a dynamic environment and minimizes the average service delay while meeting the migration *** order to optimize the service delay and migration cost,we propose an adaptive weight deep deterministic policy gradient(AWDDPG)*** distributed execution and centralized training are adopted to solve the high-dimensional *** show that the proposed algorithm can greatly reduce the migration cost and service delay compared with the other related algorithms.

关键词： mobile edge computing mobility service migration deep reinforcement learning deep deterministic policy gradient

来源：评论

学校读者我要写书评

暂无评论

Relation Reconstructive Binarization of word embeddings

引用

Frontiers of Computer Science 2022年第2期16卷 47-54页

作者： Feiyang PAN Shuokai LI Xiang AO Qing HE Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China University of Chinese Academy of Sciences Beijing 100049China

Word-embedding acts as one of the backbones of modern natural language processing(NLP).Recently,with the need for deploying NLP models to low-resource devices,there has been a surge of interest to compress word embeddings into hash codes or binary vectors so as to save the storage and memory ***,existing work learns to encode an embedding into a compressed representation from which the original embedding can be *** these methods aim to preserve most information of every individual word,they often fail to retain the relation between words,thus can yield large loss on certain *** this end,this paper presents Relation Reconstructive Binarization(R2B)to transform word embeddings into binary codes that can preserve the relation between *** its heart,R2B trains an auto-encoder to generate binary codes that allow reconstructing the wordby-word relations in the original embedding *** showed that our method achieved significant improvements over previous methods on a number of tasks along with a space-saving of up to 98.4%.Specifically,our method reached even better results on word similarity evaluation than the uncompressed pre-trained embeddings,and was significantly better than previous compression methods that do not consider word relations.

关键词： embedding compression variational auto-encoder binary word embedding

来源：评论

学校读者我要写书评

暂无评论

Exploring Trial-and-Error in Deep Learning:Initial Application to Isotope Detection in Mass Spectrometry

引用

Big Data Mining and Analytics 2024年第4期7卷 1251-1261页

作者： Qihong Jiao Yuxiao Wang Yongshuai Wang Shiwei Sun Xuefeng Cui School of Computer Science and Technology Shandong UniversityQingdao 266237China Key Lab of Intelligent Information Processing Institute of Computing TechnologyChinese Academy of SciencesBeijing 100190China

Mass spectrometry plays a crucial role in biomedicine by detecting isotopes,contributing significantly to research,diagnostics,and therapy *** study introduces IsoFusion,a deep learning model designed to address isotope detection in raw mass *** than directly applying convolutional layers to all signal and noise peaks,IsoFusion employs a trial-and-error ***,it investigates all potential charge states(trials)and collects signal peaks around expected m/z values for each ***,convolutional layers extract features from each trial,which are fused to identify the correct ***,the reparameterization trick predicts isotope features based on this correct trial.A key advantage of IsoFusion is shared model parameters across all trials,enhancing feature learning for less common charge states using data from prevalent *** results show a significant accuracy improvement for charge state 5,reaching 99.42%,compared to DeepIso’s 43.36%.Moreover,IsoFusion achieves a 97.33%detection accuracy for isotopes,with 2.4%of detected isotopes previously unidentified by four commonly used methods.

关键词： Liquid Chromatography-Mass Spectrometry(LC-MS) isotope detection retention time prediction charge state prediction deep learning

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：