检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Laskar, Md Tahmid Rahman Hoque, Enamul Huang, Jimmy Xiangji Department of Electrical Engineering and Computer Science York University Toronto Canada Information Retrieval & Knowledge Management Research Lab York University Toronto Canada School of Information Technology York University Toronto Canada

Pre-training a transformer-based model for the language modeling task in a large dataset and then fine-tuning it for downstream tasks has been found very useful in recent years. One major advantage of such pre-trained language models is that they can effectively absorb the context of each word in a sentence. However, for tasks such as the answer selection task, the pre-trained language models have not been extensively used yet. To investigate their effectiveness in such tasks, in this paper, we adopt the pre-trained Bidirectional Encoder Representations from Transformer (BERT) language model and fine-tune it on two Question Answering (QA) datasets and three Community Question Answering (CQA) datasets for the answer selection task. We find that fine-tuning the BERT model for the answer selection task is very effective and observe a maximum improvement of 13.1% in the QA datasets and 18.7% in the CQA datasets compared to the previous state-of-the-art. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Prior-guided dual-stage diabetic retinopathy grading model based on feature collaboration of lesion and vascular structure

引用

Expert Systems with Applications 2025年 285卷

作者： Guo, Xiaoxin Yang, Guangqi Xu, Chenfangqian Dong, Hongliang Hu, Xiaoying Che, Songtian Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University 2699 Qianjin Street Changchun130012 China College of Computer Science and Technology Jilin University 2699 Qianjin Street Changchun130012 China Ophthalmology Department Bethune First Hospital of Jilin University Changchun Jilin130021 China Ophthalmology Department Bethune Second Hospital of Jilin University Changchun Jilin130041 China

In order to fully utilize lesion features and vascular structure and solve the problem of class imbalance, diabetes retinopathy (DR) grading is modeled as a dual-stage task, and the prior-guided dual-stage diabetes retinopathy grading model is proposed by designing an end-to-end hierarchical framework, consisting of XE-Net and MFC-Net. The former uses vascular structure from color fundus images as prior knowledge to guide the classification of proliferative diabetic retinopathy (PDR) and non-PDR;the latter further classifies non-PDR images using color fundus images with four types of segmented lesions. The core of MFC-Net is the feature collaboration block (FCB) for multi-classification tasks, which is proposed to facilitate effective collaboration between global and local features. In addition, a class-balanced (CB) loss weight is also introduced to address the common class imbalance problem in DR datasets. The experimental results on two publicly available datasets, DDR and IDRiD show that the proposed model has significant advantages. © 2025 Elsevier Ltd

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Distributed Representations of Entities in Open-World knowledge Graphs

arXiv

引用

arXiv 2020年

作者： Guo, Lingbing Chen, Zhuo Chen, Jiaoyan Zhang, Yichi Sun, Zequn Bo, Zhongpu Fang, Yin Liu, Xiaoze Chen, Huajun Zhang, Wen College of Computer Science and Technology Zhejiang University China Zhejiang University Ant Group Joint Laboratory of Knowledge Graph China Donghai Laboratory China Department of Computer Science The University of Manchester United Kingdom Department of Computer Science and Technology Nanjing University China Ant Group China Elmore Family School of Electrical and Computer Engineering Purdue University United States School of Software Technology Zhejiang University China

Graph neural network (GNN)-based methods have demonstrated remarkable performance in various knowledge graph (KG) tasks. However, most existing approaches rely on observing all entities during training, posing a challenge in real-world knowledge graphs where new entities emerge frequently. To address this limitation, we introduce Decentralized Attention Network (DAN). DAN leverages neighbor context as the query vector to score the neighbors of an entity, thereby distributing the entity semantics only among its neighbor embeddings. To effectively train a DAN, we introduce self-distillation, a technique that guides the network in generating desired representations. Theoretical analysis validates the effectiveness of our approach. We implement an end-to-end framework and conduct extensive experiments to evaluate our method, showcasing competitive performance on conventional entity alignment and entity prediction tasks. Furthermore, our method significantly outperforms existing methods in open-world settings. © 2020, CC0.

关键词： knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Correction to: Multilayered-quality education ecosystem (MQEE): an intelligent education modal for sustainable quality education

引用

Journal of Computing in Higher Education 2021年第3期33卷 580-580页

作者： Verma, Anil Singh, Aman Lughofer, Edwin Cheng, Xiaochun Abualsaud, Khalid Department of Computer Science and Engineering Lovely Professional University Phagwara India Department of Knowledge-Based Mathematical Systems Johannes Kepler University Linz Linz Austria Department of Computer Science Middlesex University London UK Department of Computer Science Qatar University Doha Qatar

来源：评论

学校读者我要写书评

暂无评论

Dynamic anomaly detection based on recursive independent component analysis of multi-variate residual signals 33

Dynamic anomaly detection based on recursive independent com...

引用

33rd Annual European Simulation and Modelling Conference, ESM 2019

作者： Lughofer, Edwin Pratama, Mahardhika Eitzinger, Christian Radauer, Thomas Department of Knowledge-Based Mathematical Systems Johannes Kepler University Linz Austria School of Computer Science and Engineering Nanyang Technological University Singapore Profactor GmbH Steyr-Gleink Austria Stratec Consumables Anif Austria

ISBN: (纸本)9789492859099

We address the problem of anomaly detection in industrial facilities based on multi-sensor measurement systems. Any anomaly may point to an (early) indication of a fault in the system, which may turn latter into a severe failure and thus should be detected as early as possible. Our approach relies on causal relation networks gained from the measurements of process variables, whose influence weights between causes and effects are modelled by a specific non-linear fuzzy systems architecture comprising generalized rules. Residuals are extracted online from a bunch of (high-quality) causal relations and are analyzed over time through an advanced independent component analysis (ICA), which employs a specific strategy on dominant parts for automatically suppressing noise content in the data/residuals. A further important novelty aspect is that the mixing and demixing matrices which characterize the independent components are recursively updated in incremental and robust (converging) manner (thus, our approach is termed as RICA). The control signal extracted from the components is therefore also dynamically updated. The second dynamic aspect concerns the update of the causal relation models themselves through the usage of an evolving fuzzy systems approach. This integrates the possibility of structural changes by decreasing or increasing the models' non-linearity degree on demand and on the fly. RICA is compared with static ICA and with several (15) related state-of-the-art (SoA) methods based on data sets from a chip manufacturing system embedding two production stages. They comprise OK process phases with different machining parameters and NOT-OK (abnormal) phases. Results show improved detection capabilities with RICA while achieving lower false alarms rates than static ICA and than the SoA methods. Copyright © 2019 EUROSIS-ETI.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Sure: Screening Unlabeled Samples for Reliable Negative Samples Based on Reinforcement Learning

SSRN

引用

SSRN 2022年

作者： Li, Ying Sun, Hang Fang, Wensi Ma, Qin Han, Siyu Wang-Sattler, Rui Du, Wei Yu, Qiong Key Laboratory of Symbolic Computation and Knowledge Engineering College of Computer Science and Technology Jilin University Qianjin Street Jilin Changchun130012 China Department of Biomedical Informatics Ohio State University Lane Ave ColumbusOH43210 United States TUM School of Medicine Technical University of Munich Ismaninger Straße 22 Bavaria Munich81675 Germany Helmholtz Center Munich German Research Center for Environmental Health Ingolstadter Landstraße 1 Bavaria Neuherberg85764 Germany Department of Epidemiology and Biostatistics School of public health Jilin University Qianjin Street Jilin Changchun130012 China

For many classification tasks, only experimentally validated positive samples are available, and experimentally validated negative samples are not recorded. The lack of negative samples poses a great challenge for using supervised machine learning. To address this problem, we propose a novel deep reinforcement learning based model to screen reliable negative samples from unlabeled samples, named SURE. SURE has two modules: sample selector and sample inspector. The sample selector screens reliable negative samples from unlabeled samples by two reinforcement strategies. The sample inspector classifies samples and provides rewards to the sample selector. In this paper, we focus on one popular issue in the field of bioinformatics: the ncRNA-protein interaction (NPI) prediction task, which lacks reliable negative samples. Thirty datasets for NPI prediction are used to test the screening effect of SURE. The Experimental results show that our model has a robust negative sample screening capability and is superior to all outstanding sample screening methods used in the NPI prediction task. In addition, we refine 5 NPI datasets containing reliable negative samples screened by SURE, and a webserver (***/sure) is available offering the NPI prediction refined by SURE. © 2022, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Malware Identification and Detection Method Using Mixture Correntropy-Based Deep Neural Network 3rd

A Malware Identification and Detection Method Using Mixture ...

引用

3rd International Conference on Cyberspace Data and Intelligence, Cyber DI 2019, and the International Conference on Cyber-Living, Cyber-Syndrome, and Cyber-Health, CyberLife 2019

作者： Luo, Xiong Li, Jianyuan Wang, Weiping Gao, Yang Zhao, Wenbing School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China Beijing Key Laboratory of Knowledge Engineering for Materials Science Beijing100083 China Beijing Intelligent Logistics System Collaborative Innovation Center Beijing101149 China Department of Electrical and Computer Engineering University of Pittsburgh PittsburghPA15261 United States China Information Technology Security Evaluation Center Beijing100085 China Department of Electrical Engineering and Computer Science Cleveland State University ClevelandOH44115 United States

ISBN: (纸本)9789811519215

With the rapid development of CPS technology, the identification and detection of malware has become a matter of concern in the industrial application of CPS. Currently, advanced machine learning methods such as deep learning are popular in the research of malware identification and detection, and some progress has been made so far. However, there are also some problems. For example, considering the existing noise or outliers in the datasets of malware, some methods are not robust enough. Therefore, the accuracy of classification of malware still needs to be improved. Aiming at it, we propose a novel method thought the combination of correntropy and deep neural network (DNN). In our proposed method for malware identification and detection, given the success of mixture correntropy as an effective similarity measure in addressing complex dataset with noise, it is therefore incorporated into a popular DNN, i.e., convolutional neural network (CNN), to reconstruct its loss function, with the purpose of further detecting the features of outliers. We present the detailed design process of our proposed method. Furthermore, the proposed method is tested both on a popular benchmark dataset and a real-world malware classification dataset, to verify its learning performance. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Mixtures

来源：评论

学校读者我要写书评

暂无评论

A vehicular network based intelligent transport system for smart cities using machine learning algorithms

引用

Scientific reports 2024年第1期14卷 468页

作者： J Prakash L Murali N Manikandan N Nagaprasad Krishnaraj Ramaswamy Computer Science and Engineering Hindusthan College of Engineering and Technology Coimbatore Tamil Nadu India. Department of Electronics and Communication Engineering P. A. College of Engineering Pollachi Coimbatore Tamil Nadu 642 002 India. Department of Mechanical Engineering P. A. College of Engineering and Technology Pollachi Tamil Nadu 642002 India. Department of Mechanical Engineering ULTRA College of Engineering and Technology Madurai Tamil Nadu 625104 India. Centre for Excellence-Indigenous Knowledge Innovative Technology Transfer and Entrepreneurship Dambi Dollo University Dambi Dolo Ethiopia. prof.dr.krishnaraj@dadu.edu.et. Department of Mechanical Engineering College of Engineering and Technology Dambi Dollo University Dambi Dolo Ethiopia. prof.dr.krishnaraj@dadu.edu.et.

Smart cities and the Internet of Things have enabled the integration of communicating devices for efficient decision-making. Notably, traffic congestion is one major problem faced by daily commuters in urban cities. In developed countries, specialized sensors are deployed to gather traffic information to predict traffic patterns. Any traffic updates are shared with the commuters via the Internet. Such solutions become impracticable when physical infrastructure and Internet connectivity are either non-existent or very limited. In case of developing countries, no roadside units are available and Internet connectivity is still an issue in remote areas. Internet traffic analysis is a thriving field of study due to the myriad ways in which it may be put to practical use. In the intelligent Internet-of-Vehicles (IOVs), traffic congestion can be predicted and identified using cutting-edge technologies. Using tree-based decision-tree, random-forest, extra-tree, and XGBoost machine learning (ML) strategies, this research proposes an intelligent-transport-system for the IOVs-based vehicular network traffic in a smart city set-up. The suggested system uses ensemble learning and averages the selection of crucial features to give high detection accuracy at minimal computational costs, as demonstrated by the simulation results. For IOV-based vehicular network traffic, the tree-based ML approaches with feature-selection (FS) outperformed those without FS. When contrasted to the lowest KNN accuracy of 96.6% and the highest SVM accuracy of 98.01%, the Stacking approach demonstrates superior accuracy as 99.05%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extraction and comparative study of green energy using different types of biowaste material

Extraction and comparative study of green energy using diffe...

引用

2020 National Conference on Functional Materials: Emerging Technologies and Applications in Materials science, NCFM 2020

作者： Singh, Palvinder Bhargava, Cherry Kumar, Manish Maturia, Abhilash Singh Singh, Pramod K. Sharma, Pardeep Kumar Sachdeva, Amit Department of Electronics IT Sanatan Dharma College Haryana Ambala133001 India Department of Computer Science and Engineering Symbiosis Institute of Technology Pune412115 India Experimental Research Laboratory Department of Physics ARSD College University of Delhi New Delhi110021 India Department of Life Sciences SBSR Sharda University Uttar Pradesh Greater Noida201310 India Department of Physics Sharda University Knowledge Park-III Uttar Pradesh Greater Noida201 306 India QC Analyst Cosmas Research Lab Ltd Punjab Hambran 141110 India School of Electronics and Electrical Engineering Lovely Professional University Punjab Phagwara144411 India

Wind and solar green energy sources have increasingly been widely used by businesses and researchers worldwide. In the literature, these energy sources have also been represented. For these developments to be universal, these energy sources need more construction costs, more maintenance costs, and more operating space. An energy storage system is to be built to solve these issues, allowing us to store energy during lean hours and supply energy at a low cost later. These technologies, such as the battery, cell, and supercapacitor, can very easily store energy and energy distribution speeds. This energy sources have a high current for a limited period. We need electrode material and electrolyte material mentioned in previous research papers to make these energy sources. Due to its excellent electrical conductivity, excellent stability, and high specific surface area, electrode materials such as carbon and carbon-based materials are generally used. In these energy sources, these materials serve as dielectric materials. Carbon and carbon-based materials have recently been derived from bio-waste materials. These bio-waste products are bio-waste for agriculture, bio-waste for tree leaves and bio-waste from fruits. The use of these biowaste products aids in the disposal of waste and turns waste into a vital resource. These products for bio-waste are readily available at no cost. The approaches used by researchers to obtain from biowaste are explored in this study research paper on the availability of different bio-waste materials. © 2021 Elsevier Ltd. All rights reserved.

关键词： Carbon

来源：评论

学校读者我要写书评

暂无评论

Correction: Fog computing network security based on resources management

引用

EURASIP Journal on Wireless Communications and Networking 2023年第1期2023卷 1-1页

作者： Daoud, Wided Ben Othmen, Salwa Hamdi, Monia Khdhir, Radhia Hamam, Habib NTS’Com Research Unit ENET’Com University of Sfax Sfax Tunisia Department of Computers and Information Technologies College of Sciences and Arts Turaif Northern Border University Arar Saudi Arabia Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh Saudi Arabia Department of Computer Science College of Science and Arts in Qurayyat Jouf University Al-Jouf Saudi Arabia Faculty of Engineering Uni de Moncton Moncton Canada International Institute of Technology and Management Libreville Gabon Spectrum of Knowledge Production & Skills Development Sfax Tunisia Department of Electrical and Electronic Engineering Science School of Electrical Engineering University of Johannesburg Johannesburg South Africa

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：