检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第7期5卷 3384-3392页

作者： Alkhouri, Ismail R. Jha, Sumit Beckus, Andre Atia, George Jha, Susmit Ewetz, Rickard Velasquez, Alvaro OrlandoFL32816 United States Michigan State University Computational Mathematics Science and Engineering Department East LansingMI48824 United States University of Michigan Electrical Engineering and Computer Science Department Ann ArborMI48109 United States Florida International University Knights Foundation School of Computing and Information Sciences MiamiFL33199 United States Air Force Research Laboratory Rome Information Directorate NY13441 United States Department Computer Science Department OrlandoFL32816 United States SRI International Computer Science Laboratory Menlo ParkCA94025 United States Electrical and Computer Engineering Department OrlandoFL32816 United States University of Colorado Computer Science Department BoulderCO80309 United States

Protein folding neural networks (PFNNs) such as AlphaFold predict remarkably accurate structures of proteins compared to other approaches. However, the robustness of such networks has heretofore not been fully explored. This is particularly relevant given the broad social implications of such technologies and the fact that biologically small perturbations to noncritical residues of a protein sequence do not typically lead to drastic changes in the protein structure. Our study demonstrates that, similar to adversarial methods in machine learning, small changes to protein sequences can result in significant differences in the predicted protein structures using AlphaFold as determined by large distance measures. Despite this, our findings using multiple protein sequences suggest that AlphaFold is able to accurately predict the domain structure and folding regions of a protein. To gauge structural differences, we employ two alignment-based measures [root-mean-square deviation (RMSD) and the global distance test (GDT) similarity], and one alignment-free measure, which is an effective graph-based structure representation (GraSR) method. We prove that the problem of minimally perturbing protein sequences is NP-complete. Based on the well-established block substitution matrices (BLOSUM62) sequence alignment scoring matrix, we generate adversarial sequences. In our experimental evaluation, we consider 111 proteins (including 29 COVID-19 sequences) in the Universal Protein resource (UniProt), a central resource for protein data. Our findings suggest that, despite the high RMSD values returned by AlphaFold, it is capable of handling the BLOSUM adversarial sequences considered in our analysis, as evidenced by the preservation of the folded regions and the GraSR results. © 2020 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

A Continual Learning System with Self Domain Shift Adaptation for Fake News Detection 10

A Continual Learning System with Self Domain Shift Adaptatio...

引用

10th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2023

作者： Basterrech, Sebastian Kasprzak, Andrzej Platos, Jan Wozniak, Michal Technical University of Denmark Department of Applied Mathematics and Computer Science Kongens Lyngby Denmark Wroclaw University of Science and Technology Department of Systems and Computer Networks Wroclaw Poland VŠB-Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Ostrava Czech Republic

ISBN: (纸本)9798350345032

Detecting fake news is currently one of the critical challenges facing modern societies. The problem is particularly relevant, as disinformation is readily used for political warfare but can also cause significant harm to the health of citizens, such as by promoting false data on the harmfulness of selected therapies. One way to combat disinformation is to treat fake news detection as a machine learning task. This paper presents such an approach, which additionally addresses an important problem related to the non-stationarity characteristics of the fake news. We elaborated a stream data with the simulation of domain shift based on two popular benchmark datasets dedicated to the fake news classification problem (Kaggle Fake News and Constraint@AAAI2021-COVID19 Fake News Detection). The proposed learning system works in a Continual Learning (CL) framework and integrates a self domain shift adaptation in a machine learning scheme. The method was built following state-of-the-art techniques, that includes Word2Vec as a feature extractor and the LSTM model as a classifier. The performance of the approach has been evaluated over the generated data stream. The convenience of our approach is showed in the results, where the accuracy gain with respect to a CL approach without domain adaptation is observed to be significant. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Closure equation and higher-order moment relations in the Gauss-Hermite lattice Boltzmann method

引用

Physical Review E 2024年第5期110卷 055301页

作者： Mahyar Madadi Joseph T. Johnson Yong Shi John E. Sader Department of Materials Physics Research School of Physics School of Mathematics and Statistics The Department of Mechanical Materials and Manufacturing Engineering Graduate Aerospace Laboratories and Department of Applied Physics

Moment methods are often used to solve transport problems involving the Boltzmann-BGK equation. Because the moment equations are underdetermined, these methods require an additional "closure equation" that relates higher to lower-order moments. Here, we examine the closure equation and higher-order moment relations implicit in the lattice Boltzmann method (LBM) that use Gauss-Hermite quadrature for their discrete velocity sets. It is shown that the discrete-velocity-set itself defines the closure equation and higher-order moment relations, the precise forms of which are yet to be reported. The general formula we present facilitates the efficient computational evaluation of higher-order moments and provides insight into the operation of LBM that is anticipated to be useful in theoretical analyses of its performance. Derived formulas for two different velocity sets are validated against numerical implementations of the LBM for steady Couette flow.

关键词： Lattice-Boltzmann methods

来源：评论

学校读者我要写书评

暂无评论

Farsi Optical Character Recognition Using a Transformer-based Model 13

Farsi Optical Character Recognition Using a Transformer-base...

引用

13th International Conference on computer and Knowledge engineering, ICCKE 2023

作者： Asadi-Zeydabadi, Fatemeh Shabaninia, Elham Nezamabadi-Pour, Hossein Shojaee, Melika Shahid Bahonar University of Kerman Department of Electrical Engineering Kerman Iran Graduate University of Advanced Technology Faculty of Sciences and Modern Technologies Department of Applied Mathematics Kerman Iran Shahid Bahonar University of Kerman Department of Computer Engineering Kerman Iran

ISBN: (纸本)9798350330151

Optical Character Recognition (OCR) techniques have made significant advances in recent years using new approaches such as Transformers for Latin languages. However, research on low-resource languages like Farsi is still relatively scarce. One of the reasons for this is the complex nature of Farsi script, which poses unique challenges for OCR. Farsi OCR is essential for various applications, such as document management, digital archiving, and automated data entry. In the context of this investigation, we presents a deep neural network that utilizes transformer architecture for the recognition of Farsi words, yielding promising results. Additionally, we assess the effectiveness of our method through a comparison with state-of-the-art techniques on two datasets namely, Shotor and Sadri, achieving accuracy rates of 99.75% and 99.23%, respectively. Our results outperform previous methods and highlight the potential of transformer-based approaches for Farsi OCR. © 2023 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

To the Issue of the Comparison of 2D and 3D Modeling of Mechanical-engineering Parts 7

To the Issue of the Comparison of 2D and 3D Modeling of Mech...

引用

7th International Conference on Information Technologies in engineering Education, Inforino 2024

作者： Rudnitskaya, Anastasia V. Sokolov, Semeon A. Fedotov, Gennady V. National Research University 'MPEI' Institute of Power Machinery and Mechanics Moscow Russia National Research University 'MPEI' Faculty of Radio-Electronic Systems and Complexes Moscow Russia National Research University 'MPEI' Department of Applied Mathematics and Artificial Intelligence Power Engineering Design Department Moscow Russia

ISBN: (纸本)9798350371369

The article provides a comparison of two methods for designing mechanical engineering parts using 2D and 3D modeling according to the following criteria:•speed of creating models. •responsibilities for creating models. •project editing capabilities. •information content of the model. •methods of manufacturing parts. As examples, assignments from the course "engineering and computer Graphics"of the department of Modeling and Design of Power Installations (MDPI) of the National research University "MPEI"were used, which the authors, students of this article, completed on the nanoCAD system. The authors believe that the course program "engineering and computer Graphics"of the department of MDPI National researching University "MPEI"is effective and relevant;the use of 3D modeling without mastering 2D modeling is not the right method of specialist education, because the latter provides the necessary skills in engineering graphics of complex mechanical-engineering parts. © 2024 IEEE.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

A MULTI-OBJECTIVE APPROACH BASED ON MARKOWITZ AND DEA CROSS-EFFICIENCY MODELS FOR THE INTUITIONISTIC FUZZY PORTFOLIO SELECTION PROBLEM

Decision Making: Applications in Management and Engineering

引用

Decision Making: Applications in Management and engineering 2022年第2期5卷 241-259页

作者： Rasoulzadeh, Mehrdad Edalatpanah, Seyyed Ahmad Fallah, Mohammad Najafi, Seyyed Esmaeil Department of Industrial Engineering Central Tehran Branch Islamic Azad University Tehran Iran Department of Applied Mathematics Ayandegan Institute of Higher Education Tonekabon Iran Department of Industrial Engineering Science and Research Branch Islamic Azad University Tehran Iran

Nowadays, investors' main concerns are choosing the best portfolio so that the highest possible investment return can be achieved by accepting the least risk. In this regard, the classical Markowitz model is one of the most widely used models which helps investors get closer to their goals. Data envelopment analysis (DEA) is also a practical technique that can analyze the efficiency of firms. Few models can address companies' internal performance simultaneously in addition to considering the goals of Markowitz models. Also, we study the return and price fluctuations of assets in the market with the intuitionistic fuzzy numbers for the first time. Therefore, in this paper, we combine all these tools with returns of intuitionistic fuzzy numbers, proposing a new combined Markowitz and the cross DEA models. Furthermore, to get the best portfolio of assets, this model obtains the efficiency of all companies and, simultaneously, fully covers all constraints of the Markowitz model. To show the model's practicality, we studied a case study based on information from 50 active enterprises on Tehran Stock Exchange. We solved the proposed model using the Non-Dominated Sorting Genetic Algorithm II (NSGA-II). The obtained results and the comparisons made with the existing approaches show the effectiveness of the proposed model. © 2022 by the authors.

关键词： Data envelopment analysis

来源：评论

学校读者我要写书评

暂无评论

AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neural Activity 37

AMAG: Additive, Multiplicative and Adaptive Graph Neural Net...

引用

37th Conference on Neural Information Processing Systems, NeurIPS 2023

作者： Li, Jingyuan Scholl, Leo Le, Trung Rajeswaran, Pavithra Orsborn, Amy Shlizerman, Eli Department of Electrical & Computer Engineering University of Washington SeattleWA United States Department of Bioengineering University of Washington SeattleWA United States Department of Applied Mathematics University of Washington SeattleWA United States

ISBN: (纸本)9781713899921

Latent Variable Models (LVMs) propose to model the dynamics of neural populations by capturing low-dimensional structures that represent features involved in neural activity. Recent LVMs are based on deep learning methodology where a deep neural network is trained to reconstruct the same neural activity given as input and as a result to build the latent representation. Without taking past or future activity into account such a task is non-causal. In contrast, the task of forecasting neural activity based on given input extends the reconstruction task. LVMs that are trained on such a task could potentially capture temporal causality constraints within its latent representation. Forecasting has received less attention than reconstruction due to recording challenges such as limited neural measurements and trials. In this work, we address modeling neural population dynamics via the forecasting task and improve forecasting performance by including a prior, which consists of pairwise neural unit interaction as a multivariate dynamic system. Our proposed model-Additive, Multiplicative, and Adaptive Graph Neural Network (AMAG)-leverages additive and multiplicative message-passing operations analogous to the interactions in neuronal systems and adaptively learns the interaction among neural units to forecast their future activity. We demonstrate the advantage of AMAG compared to non-GNN based methods on synthetic data and multiple modalities of neural recordings (field potentials from penetrating electrodes or surface-level micro-electrocorticography) from four rhesus macaques. Our results show the ability of AMAG to recover ground truth spatial interactions and yield estimation for future dynamics of the neural population. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Gaussian Support Vector Machine Algorithm Based Air Pollution Prediction

引用

computers, Materials & Continua 2022年第4期71卷 683-695页

作者： K.S.Bhuvaneshwari J.Uma K.Venkatachalam Mehedi Masud Mohamed Abouhawwash T.Logeswaran Department of Computer Sceince and Engineering Karpagam College of EngineeringCoimbatore641032India Department of Electrical and Electronics Engineering M.Kumarasamy College of EngineeringKarur639113India Department of Applied Cybernetics Faculty of ScienceUniversity of Hradec KrálovéHradec Králové50003Czech Republic Department of Computer Science College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Department of Mathematics Faculty of ScienceMansoura UniversityMansoura35516Egypt Department of Computational Mathematics Scienceand Engineering(CMSE)Michigan State UniversityEast LansingMI48824USA Department of Electrical and Electronics Engineering Kongu Engineering CollegeErode638060India

Air pollution is one of the major concerns considering detriments to human *** type of pollution leads to several health problems for humans,such as asthma,heart issues,skin diseases,bronchitis,lung cancer,and throat and eye *** pollution also poses serious issues to the *** from the vehicle industry is the cause of greenhouse effect and CO2 ***,real-time monitoring of air pollution in these areas will help local authorities to analyze the current situation of the city and take necessary *** monitoring process has become efficient and dynamic with the advancement of the Internet of things and wireless sensor *** is the main issue in WSNs;if the sensor node location is unknown,then coverage and power and routing are not *** study concentrates on localization-based air pollution prediction systems for real-time monitoring of smart *** systems comprise two phases considering the prediction as heavy or light traffic area using the Gaussian support vector machine algorithm based on the air pollutants,such as PM2.5 particulate matter,PM10,nitrogen dioxide(NO2),carbon monoxide(CO),ozone(O3),and sulfur dioxide(SO2).The sensor nodes are localized on the basis of the predicted area using the meta-heuristic algorithms called fast correlation-based elephant herding *** dataset is divided into training and testing parts based on 10 *** evaluation on predicting the air pollutant for localization is performed with the training *** error prediction in localizing nodes is 9.83 which is lesser than existing solutions and accuracy is 95%.

关键词： Air pollution monitoring air pollutant SVM Gaussian EHO fast correlation WSN localization

来源：评论

学校读者我要写书评

暂无评论

Privacy‐preserving remote sensing images recognition based on limited visual cryptography

引用

CAAI Transactions on Intelligence Technology 2023年第4期8卷 1166-1177页

作者： Denghui Zhang Muhammad Shafiq Liguo Wang Gautam Srivastava Shoulin Yin Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhouChina Department of New Networks Peng Cheng LaboratoryShenzhenChina College of Information and Communications Engineering Dalian Minzu UniversityDalianChina Department of Mathematics and Computer Science Brandon UniversityBrandonManitobaCanada Research Centre for Interneural Computing China Medical UniversityTaichungTaiwanChina Department of Computer Science and Math Lebanese American UniversityBeirutLebanon College of Information and Communications Engineering Harbin Engineering UniversityHarbinChina

With the arrival of new data acquisition platforms derived from the Internet of Things(IoT),this paper goes beyond the understanding of traditional remote sensing *** fusion of remote sensing and computer vision has hit the industrial world and makes it possible to apply Artificial intelligence to solve problems such as automatic extraction of information and image ***,due to the complex architecture of IoT and the lack of a unified security protection mechanism,devices in remote sensing are vulnerable to privacy leaks when sharing *** is necessary to design a security scheme suitable for computation‐limited devices in IoT,since traditional encryption methods are based on computational *** Cryptography(VC)is a threshold scheme for images that can be decoded directly by the human visual system when superimposing encrypted *** stacking‐to‐see feature and simple Boolean decryption operation make VC an ideal solution for privacy‐preserving recognition for large‐scale remote sensing images in *** this study,the secure and efficient transmission of high‐resolution remote sensing images by meaningful VC is *** diffusing the error between the encryption block and the original block to adjacent blocks,the degradation of quality in recovery images is *** fine‐tuning the pre‐trained model from large‐scale datasets,we improve the recognition performance of small encryption datasets for remote sensing *** experimental results show that the proposed lightweight privacy‐preserving recognition framework maintains high recognition performance while enhancing security.

关键词： activity recognition feature extraction image classification KNN privacy protection remote monitoring remote sensing

来源：评论

学校读者我要写书评

暂无评论

Automatic Identification of Table Contents in Electronic Component Specifications of EDA 28th

Automatic Identification of Table Contents in Electronic Com...

引用

28th International Conference on Technologies and Applications of Artificial Intelligence, TAAI 2023

作者： Hong, Tzung-Pei Xu, Yi-Zhen Huang, Shi-Feng Chen, Yi-Ting Lee, Ming-Han Department of Computer Science and Information Engineering National University of Kaohsiung Kaohsiung Taiwan Graduate Institute of Statistics National Central University Taoyuan Taiwan Footprintku Inc. Kaohsiung Taiwan Department of Applied Mathematics National University of Kaohsiung Kaohsiung Taiwan

ISBN: (纸本)9789819717132

With the rapid advancement of technology, the electronics industry has flourished in recent decades. Electronic products such as computers, mobile phones, and smart televisions are ubiquitous in our daily lives. In the design, manufacturing, and maintenance processes of electronic products, a large number of electronic components are required. The relevant information of these components is usually recorded in the tables of electronic component specifications. In this paper, we design methods to recognize and extract contents from tables, which typically contain vital information about electronic components, such as their characteristics and packaging methods. Our approach utilizes text processing techniques to structurally process and analyze the extracted table content, enabling us to obtain the specific information we need. We categorize tables in PDFs into different types and explore relevant information from them using the procedure of each type. The experimental results demonstrate that our method can achieve a high accuracy rate of over 90% in recognizing table contents. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Specifications

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：