检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Shih-Cheng Wang, Pei-Hwa Su, Jheng-Wei Chiang, Wei-Yin Huang, Shih-Hsien Lin, Yen-Chu Ou, Chia-Ho Chen, Chih-Yu Insilico Medicine Taiwan Ltd. Taipei City110208 Taiwan Department of Chemical Engineering Massachusetts Institute of Technology CambridgeMA02139 United States Quantum Information Center Chung Yuan Christian University Taoyuan City320314 Taiwan Master Program in Intelligent Computing and Big Data Chung Yuan Christian University Taoyuan City320314 Taiwan Department of Computer Science and Information Engineering National Pingtung University Pingtung City900392 Taiwan

Finding appropriate reaction conditions that yield high product rates in chemical synthesis is crucial for the chemical and pharmaceutical industries. However, due to the vast chemical space, conducting experiments for each possible reaction condition is impractical. Consequently, models such as QSAR (Quantitative Structure-Activity Relationship) or ML (Machine Learning) have been developed to predict the outcomes of reactions and illustrate how reaction conditions affect product yield. Despite these advancements, inferring all possible combinations remains computationally prohibitive when using a conventional CPU. In this work, we explore using a Digital Annealing Unit (DAU) to tackle these large-scale optimization problems more efficiently by solving Quadratic Unconstrained Binary Optimization (QUBO). Two types of QUBO models are constructed in this work: one using quantum annealing and the other using ML. Both models are built and tested on four high-throughput experimentation (HTE) datasets and selected Reaxys datasets. Our results suggest that the performance of models is comparable to classical ML methods (i.e., Random Forest and Multilayer Perceptron (MLP)), while the inference time of our models requires only seconds with a DAU. Additionally, in campaigns involving active learning and autonomous design of reaction conditions to achieve higher reaction yield, our model demonstrates significant improvements by adding new data, showing promise of adopting our method in the iterative nature of such problem settings. Our method can also accelerate the screening of billions of reaction conditions, achieving speeds millions of times faster than traditional computing units in identifying superior conditions. Therefore, leveraging the DAU with our developed QUBO models has the potential to be a valuable tool for innovative chemical synthesis. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

An Algorithm for Detecting Surface Defects in Industrial Strip Steel based on Receptive Field and Feature Information Supplementation

An Algorithm for Detecting Surface Defects in Industrial Str...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Qingyu Xu Jiguo Yu Anming Dong Zihao Shang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Data Intelligence Information Technology Co. Ltd. Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In the context of Industry 4.0 and the rise of intelligent manufacturing, the quality of industrial products is becoming more and more important. Strip steel surface defect detection, as a key link in industrial production, is crucial to ensure the quality of industrial products. However, due to the irregularity of the defect scale and the inconspicuous defect features in the surface defect image of strip steel, it is difficult for the existing detection algorithms to realize the effective detection of defects. In order to better extract the features of defects and improve the network’s ability to detect defects, this paper proposes an algorithm for detecting surface defects on industrial strip steel based on receptive field and feature information supplementation. First, we design a receptive field (RF) module to replace the residual structure in the C3 module, which we name C3RF. This module can effectively increase the network’s receptive field, allowing the network to fully capture irregular defect features without increasing the cost. Second, for the characteristics that defective features are not obvious and tend to lose detail information as the network deepens, an extra information supplemental branching feature fusion pyramid (EFPN) is proposed on the basis of the original PAFPN architecture to compensate for the detail information that is lost by the fragile features in deeper layers. Finally, convolutional block attention module (CBAM) is introduced to replace the spatial pooling pyramid (SPPF) in the baseline network, which enhances the contrast between defects and backgrounds, and improves the classification and localization ability of the network. Our network achieves an accuracy of 82.2% on the publicly available strip steel defect detection dataset, which is a 4.0% improvement over the baseline. The results show that the network constructed in this paper can realize effective defect detection.

关键词： Radio frequency Location awareness Strips Production Feature extraction Real-time systems Hardware

来源：评论

学校读者我要写书评

暂无评论

A Diverse Biases Non-negative Latent Factorization of Tensors Model for Dynamic Network Link Prediction

A Diverse Biases Non-negative Latent Factorization of Tensor...

引用

2020 IEEE International Conference on Networking, Sensing and Control, ICNSC 2020

作者： Wu, Xuke Gou, Hang Wu, Hao Wang, Juan Chen, Minzhi Lai, Siyu Computer School China West Normal University Nanchong Sichuan637002 China Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China University of Chinese Academy of Sciences Beijing100049 China Department of Medical Imaging North Sichuan Medical College Nanchong Sichuan637000 China

ISBN: (纸本)9781728168531

Dynamic networks vary over time, making it vital to capture networks temporal patterns for predicting missing links with high accuracy. A biased non-negative latent factorization of tensors (BNLFT) model is very effective in extracting such patterns from dynamic data. However, a BNLFT model only integrates single bias, which cannot adequately represents the volatility of the dynamic data. To address this issue, this paper presents a Diverse Biases Non-negative Latent Factorization of Tensors (DBNT) model for accurate prediction of missing links in dynamic networks. Meanwhile, for further prediction accuracy improvement, the preprocessing bias is integrated into the DBNT model. Empirical studies on two dynamic networks datasets from real applications show that compared with state of the art predictors, a DBNT model achieves higher prediction accuracy. © 2020 IEEE.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean Label

arXiv

引用

arXiv 2022年

作者： Hu, Shengshan Zhou, Ziqi Zhang, Yechao Zhang, Leo Yu Zheng, Yifeng He, Yuanyuan Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China School of Information Technology Deakin University VIC3216 Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security HUST Wuhan430074 China Cluster and Grid Computing Lab HUST Wuhan430074 China

Due to its powerful feature learning capability and high efficiency, deep hashing has achieved great success in large-scale image retrieval. Meanwhile, extensive works have demonstrated that deep neural networks (DNNs) are susceptible to adversarial examples, and exploring adversarial attack against deep hashing has attracted many research efforts. Nevertheless, backdoor attack, another famous threat to DNNs, has not been studied for deep hashing yet. Although various backdoor attacks have been proposed in the field of image classification, existing approaches failed to realize a truly imperceptive backdoor attack that enjoys invisible triggers and clean label setting simultaneously, and they also cannot meet the intrinsic demand of image retrieval backdoor. In this paper, we propose BadHash, the first generative-based imperceptible backdoor attack against deep hashing, which can effectively generate invisible and input-specific poisoned images with clean label. Specifically, we first propose a new conditional generative adversarial network (cGAN) pipeline to effectively generate poisoned samples. For any given benign image, it seeks to generate a natural-looking poisoned counterpart with a unique invisible trigger. In order to improve the attack effectiveness, we introduce a label-based contrastive learning network LabCLN to exploit the semantic characteristics of different labels, which are subsequently used for confusing and misleading the target model to learn the embedded trigger. We finally explore the mechanism of backdoor attacks on image retrieval in the hash space. Extensive experiments on multiple benchmark datasets verify that BadHash can generate imperceptible poisoned samples with strong attack ability and transferability over state-of-the-art deep hashing schemes. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

MalScan: Android Malware Detection Based on Social-Network Centrality Analysis

引用

IEEE Transactions on Dependable and Secure computing 2025年

作者： Wu, Yueming Suo, Wenqi Feng, Siyue Zou, Deqing Yang, Wei Liu, Yang Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Jinyinhu Laboratory Wuhan430074 China University of Texas at Dallas United States Nanyang Technological University Singapore Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China

Malware scanning of an app market is expected to be scalable and effective. However, existing approaches use syntax-based features that can be evaded by transformation attacks or semantic-based features which are usually extracted by expensive program analysis. Therefore, to address the scalability challenges of traditional heavyweight static analysis, we propose a graph-based lightweight approach MalScan for Android malware detection. MalScan considers the function call graph as a complex social network and employs centrality analysis on sensitive application program interfaces (APIs) to express the semantic characteristics of the graph. On this basis, machine learning algorithms and ensemble learning algorithms are applied to classify the extracted features. We evaluate MalScan on datasets of 104,892 benign apps and 108,640 malwares, and the results of experiments indicate that MalScan outperforms six state-of-the-art detectors and can quickly detect Android malware with an f-value as high as 99%. In addition, there are also significant improvements in the robustness of Android app evolution and robustness to obfuscation. Finally, we conduct an exhaustive statistical study of over one million applications in the Google-Play app market and successfully identify 498 zero-day malware, which further validates the feasibility of MalScan on market-wide malware scanning. © 2004-2012 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Syntax-enhanced pre-trained model 59

Syntax-enhanced pre-trained model

引用

Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021

作者： Xu, Zenan Guo, Daya Tang, Duyu Su, Qinliang Shou, Linjun Gong, Ming Zhong, Wanjun Quan, Xiaojun Jiang, Daxin Duan, Nan School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Microsoft Research Asia Beijing China Microsoft Search Technology Center Asia Beijing China Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou China Key Lab. of Machine Intelligence and Advanced Computing Ministry of Education China

ISBN: (纸本)9781954085527

We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. Such a problem would lead to the necessity of having human-annotated syntactic information, which limits the application of existing methods to broader scenarios. To address this, we present a model that utilizes the syntax of text in both pre-training and fine-tuning stages. Our model is based on Transformer with a syntax-aware attention layer that considers the dependency tree of the text. We further introduce a new pre-training task of predicting the syntactic distance among tokens in the dependency tree. We evaluate the model on three downstream tasks, including relation classification, entity typing, and question answering. Results show that our model achieves state-of-the-art performance on six public benchmark datasets. We have two major findings. First, we demonstrate that infusing automatically produced syntax of text improves pre-trained models. Second, global syntactic distances among tokens bring larger performance gains compared to local head relations between contiguous tokens. © 2021 Association for Computational Linguistics

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

Ultrafast all-optical manipulation of the charge-density wave in VTe2

引用

Physical Review research 2023年第4期5卷 043276-043276页

作者： Manuel Tuniz Davide Soranzio Davide Bidoggia Denny Puntel Wibke Bronsch Steven L. Johnson Maria Peressi Fulvio Parmigiani Federico Cilento Dipartimento di Fisica Università degli Studi di Trieste 34127 Trieste Italy Institute for Quantum Electronics Eidgenössische Technische Hochschule (ETH) Zürich 8093 Zurich Switzerland Elettra - Sincrotrone Trieste S.C.p.A. Strada Statale 14 km 163.5 34149 Trieste Italy ICSC - Italian Research Center on High Performance Computing Big Data and Quantum Computing 40121 Bologna Italy International Faculty University of Cologne Albertus-Magnus-Platz 50923 Cologne Germany

The charge-density-wave (CDW) phase in the layered transition-metal dichalcogenide VTe2 is strongly coupled to the band inversion involving vanadium and tellurium orbitals. In particular, this coupling leads to a selective disappearance of the Dirac-type states that characterize the normal phase, when the CDW phase sets in. Here, we investigate the broadband time-resolved reflectivity variations caused by collective and single-particle excitations in the CDW ground state of VTe2. With the aid of density functional perturbation theory simulations we unveil the presence of two collective amplitude modes of the CDW ground state. By applying a double-pulse excitation scheme, we show the possibility to manipulate these modes, gaining insights into the coupling between these two collective excitations and demonstrating a more efficient way to perturb the CDW phase in VTe2.

关键词： Carrier dynamics Charge density waves Coherent control Electronic structure of atoms & molecules First-principles calculations Lattice dynamics Topological materials Ultrafast optics Ultrafast phenomena

来源：评论

学校读者我要写书评

暂无评论

Post-Quantum Blockchain over Lattice

引用

Computers, Materials & Continua 2020年第5期63卷 845-859页

作者： Xiao Zhang Faguo Wu Wang Yao Wenhua Wang Zhiming Zheng School of Mathematics and Systems Science Beihang Universityand Key Laboratory of MathematicsInformatics and Behavioral SemanticsMinistry of EducationBeijing100191China Peng Cheng Laboratory Shenzhen518055China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang UniversityBeijing100191China Aviation Industry Development Research Center of China BeijingChina

Blockchain is an emerging decentralized architecture and distributed computing paradigm underlying Bitcoin and other cryptocurrencies,and has recently attracted intensive attention from governments,financial institutions,high-tech enterprises,and the capital *** cryptographic security relies on asymmetric cryptography,such as ECC,***,with the surprising development of quantum technology,asymmetric cryptography schemes mentioned above would become ***,lattice-based cryptography scheme was proposed to be secure against attacks in the quantum *** 2018,with the aid of Bonsai Trees technology,Yin et al.[Yin,Wen,Li et al.(2018)]proposed a lattice-based authentication method which can extend a lattice space to multiple lattice spaces accompanied by the corresponding *** their scheme has theoretical significance,it is unpractical in actual situation due to extremely large key size and signature *** this paper,aiming at tackling the critical issue of transaction size,we propose a post quantum blockchain over *** using SampleMat and signature without trapdoor,we can reduce the key size and signature size of our transaction authentication approach by a significant *** of using a whole set of vectors as a basis,we can use only one vector and rotate it enough times to form a *** on the hardness assumption of Short Integer Solution(SIS),we demonstrate that the proposed anti-quantum transaction authentication scheme over lattice provides existential unforgeability against adaptive chosen-message attacks in the random *** compared to the Yin et al.[Yin,Wen,Li et al.(2018)]scheme,our scheme has better performance in terms of energy consumption,signature size and signing key *** the underlying lattice problem is intractable even for quantum computers,our scheme would work well in the quantum age.

关键词： Blockchain post quantum lattice random oracle

来源：评论

学校读者我要写书评

暂无评论

A Hybrid MTS Anomaly Detection Method Based on Reconstruction and Adaptive Spatial-Temporal Graph Network

A Hybrid MTS Anomaly Detection Method Based on Reconstructio...

引用

data Driven Control and Learning Systems (DDCLS)

作者： X. Yuan Ke Ning K. Wei Yan-Lin He Qun-Xiong Zhu Ming-Qing Zhang Yi Luo Yang Zhang College of Information Science and Technology Beijing University of Chemical Technology Beijing P. R. China Engineering Research Center of Intelligent PSE Ministry of Education of China Beijing P. R. China Faculty of Applied Sciences Macao Polytechnic University Macao SAR P. R. China Research Institute of Mine Big Data Chinese Institute of Coal Science Beijing P. R. China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Effective anomaly detection of multivariate time series data is crucial for modern industrial applications. However, existing works usually ignore spatial and temporal dependencies of series. The data with complicated spatial-temporal feature put forward higher requirements for accurate detection of anomalies. In this paper, we propose an anomaly detection method for multivariate time series based on spatial-temporal network (STN). Firstly, the time series are reconstructed by Generative Adversarial Networks (GAN). The reconstruction block is used to amplify the influence of the abnormal state and prompt the anomalies more detectable, as poorly reconstructed data of abnormal state further worsen the quality of the final predicted value. Secondly, an adaptive learning graph structure layer is proposed. The graph structure is learned by adaptive method without any prior knowledge and is used for reconstructed data prediction. Thirdly, we use STN to extract spatial and temporal dependencies of series. Especially, attention mechanism is introduced into graph convolution network to enhance the prediction performance by focusing on more important neighbor node message. Finally, our model is tested on 3 public datasets to evaluate performance. The results demonstrate that our method performs better than baselines.

关键词： Learning systems Attention mechanisms Convolution Time series analysis Neural networks Focusing Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Stepdown SLOPE for Controlled Feature Selection

arXiv

引用

arXiv 2023年

作者： Liang, Jingxuan Zhang, Xuelin Chen, Hong Li, Weifu Tang, Xin College of Science Huazhong Agricultural University Wuhan430070 China College of Informatics Huazhong Agricultural University Wuhan430070 China Ping An Property & Casualty Insurance Company Shenzhen China Engineering Research Center of Intelligent Technology for Agriculture Ministry of Education Wuhan430070 China Key Laboratory of Smart Farming for Agricultural Animals Wuhan430070 China Hubei Engineering Technology Research Center of Agricultural Big Data Wuhan430070 China

Sorted L-One Penalized Estimation (SLOPE) has shown the nice theoretical property as well as empirical behavior recently on the false discovery rate (FDR) control of high-dimensional feature selection by adaptively imposing the non-increasing sequence of tuning parameters on the sorted 1 penalties. This paper goes beyond the previous concern limited to the FDR control by considering the stepdown-based SLOPE to control the probability of k or more false rejections (k-FWER) and the false discovery proportion (FDP). Two new SLOPEs, called k-SLOPE and F-SLOPE, are proposed to realize k-FWER and FDP control respectively, where the stepdown procedure is injected into the SLOPE scheme. For the proposed stepdown SLOPEs, we establish their theoretical guarantees on controlling k-FWER and FDP under the orthogonal design setting, and also provide an intuitive guideline for the choice of regularization parameter sequence in much general setting. Empirical evaluations on simulated data validate the effectiveness of our approaches on controlled feature selection and support our theoretical findings. Copyright © 2023, The Authors. All rights reserved.

关键词： Feature Selection

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：