检索结果-内蒙古大学图书馆

Classification and structural characteristics of amorphous materials based on interpretable deep learning

Chinese Physics B 2023年第9期32卷 356-363页

作者：崔佳梅李韵洁赵偲郑文 Institute of Public Safety and Big Data College of Data ScienceTaiyuan University of TechnologyJinzhong 030600China Shanxi Engineering Research Center for Intelligent Data Assisted Treatment Changzhi Medical CollegeChangzhi 046000China

Defining the structure characteristics of amorphous materials is one of the fundamental problems that need to be solved urgently in complex materials because of their complex structure and long-range *** this study,we develop an interpretable deep learning model capable of accurately classifying amorphous configurations and characterizing their structural *** results demonstrate that the multi-dimensional hybrid convolutional neural network can classify the two-dimensional(2D)liquids and amorphous solids of molecular dynamics *** classification process does not make a priori assumptions on the amorphous particle environment,and the accuracy is 92.75%,which is better than other convolutional neural ***,our model utilizes the gradient-weighted activation-like mapping method,which generates activation-like heat maps that can precisely identify important structures in the amorphous configuration *** obtain an order parameter from the heatmap and conduct finite scale analysis of this *** findings demonstrate that the order parameter effectively captures the amorphous phase transition process across various *** results hold significant scientific implications for the study of amorphous structural characteristics via deep learning.

关键词： amorphous interpretable deep learning image classification finite scale analysis

来源：评论

学校读者我要写书评

暂无评论

Accelerating BERT inference with GPU-efficient exit prediction

引用

Frontiers of Computer Science 2024年第3期18卷 31-42页

作者： Lei LI Chengyu WANG Minghui QIU Cen CHEN Ming GAO Aoying ZHOU Shanghai Engineering Research Center of Big Data Management School of Data Science and EngineeringEast China Normal UniversityShanghai 200062China Alibaba Group Hangzhou 311121China KLATASDS-MOE School of StatisticsEast China Normal UniversityShanghai 200062China

BERT is a representative pre-trained language model that has drawn extensive attention for significant improvements in downstream Natural Language Processing(NLP)*** complex architecture and massive parameters bring BERT competitive performance but also result in slow speed at model inference *** speed up BERT inference,FastBERT realizes adaptive inference with an acceptable drop in accuracy based on knowledge distillation and the early-exit ***,many factors may limit the performance of FastBERT,such as the teacher classifier that is not knowledgeable enough,the batch size shrinkage and the redundant computation of student *** overcome these limitations,we propose a new BERT inference method with GPU-Efficient Exit Prediction(GEEP).GEEP leverages the shared exit loss to simplify the training process of FastBERT from two steps into only one step and makes the teacher classifier more knowledgeable by feeding diverse Transformer outputs to the teacher *** addition,the exit layer prediction technique is proposed to utilize a GPU hash table to handle the token-level exit layer distribution and to sort test samples by predicted exit *** this way,GEEP can avoid batch size shrinkage and redundant computation of student *** results on twelve public English and Chinese NLP datasets prove the effectiveness of the proposed *** source codes of GEEP will be released to the public upon paper acceptance.

关键词： BERT FastBERT inference acceleration model distillation early exit text classification

来源：评论

学校读者我要写书评

暂无评论

Resource investment for DDoS attack resistant SDN: a practical assessment

引用

Science China(Information Sciences) 2023年第7期66卷 112-129页

作者： Bin YUAN Fan ZHANG Jun WAN Huan ZHAO Shui YU Deqing ZOU Qiangsheng HUA Hai JIN School of Cyber Science and Engineering 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 Shenzhen Huazhong University of Science and Technology Research Institute School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab School of Computer Science University of Technology Sydney

Software-defined networks(SDNs) present a novel network architecture that is widely used in various datacenters. However, SDNs also suffer from many types of security threats, among which a distributed denial of service(DDoS) attack, which aims to drain the resources of SDN switches and controllers,is one of the most common. Once the switch or controller is damaged, the network services can be *** defense schemes against DDoS attacks have been proposed from the perspective of attack detection;however, such defense schemes are known to suffer from a time consuming and unpromising accuracy, which could result in an unavailable network service before specific countermeasures are taken. To address this issue through a systematic investigation, we propose an elaborate resource-management mechanism against DDoS attacks in an SDN. Specifically, by considering the SDN topology, we leverage the M/M/c queuing model to measure the resistance of an SDN to DDoS attacks. Network administrators can therefore invest a reasonable number of resources into SDN switches and SDN controllers to defend against DDoS attacks while guaranteeing the quality of service(QoS). Comprehensive analyses and empirical data-based experiments demonstrate the effectiveness of the proposed approach.

关键词： SDN security DDoS attacks resource management queueing theory QoS

来源：评论

学校读者我要写书评

暂无评论

A Helmet Detection Algorithm Based on Transformers with Deformable Attention Module

引用

Chinese Journal of Electronics 2025年第1期34卷 229-241页

作者： Songle Chen Hongbo Sun Yuxin Wu Lei Shang Xiukai Ruan Engineering Research Center of Post Big Data Technology and Application of Jiangsu Province Nanjing University of Posts and Telecommunications State Key Lab for Novel Software Technology Nanjing University Institute of Intelligent Locks Wenzhou University

Wearing a helmet is one of the effective measures to protect workers' safety. To address the challenges of severe occlusion, multi-scale, and small target issues in helmet detection, this paper proposes a helmet detection algorithm based on deformable attention transformers. The main contributions of this paper are as follows. A compact end-to-end network architecture for safety helmet detection based on transformers is proposed. It cancels the computationally intensive transformer encoder module in the existing detection transformer(DETR) and uses the transformer decoder module directly on the output of feature extraction for query decoding, which effectively improves the efficiency of helmet detection. A novel feature extraction network named Swin transformer with deformable attention module(DSwin transformer) is proposed. By sparse cross-window attention, it enhances the contextual awareness of multi-scale features extracted by Swin transformer, and keeps high computational efficiency simultaneously. The proposed method generates the query reference points and query embeddings based on the joint prediction probabilities, and selects an appropriate number of decoding feature maps and sparse sampling points for query decoding, which further enhance the inference capability and processing speed. On the benchmark safety-helmet-wearing-dataset(SHWD), the proposed method achieves the average detection accuracy mAP@0.5 of 95.4% with 133.35G floating-point operations per second(FLOPs) and 20 frames per second(FPS), the state-of-the-art method for safety helmet detection.

关键词： Head Accuracy Network architecture Benchmark testing Transformers Feature extraction Safety Decoding Computational efficiency Detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Large Language Models are Good Annotators for Type-aware data Augmentation in Grammatical Error Correction 31

Large Language Models are Good Annotators for Type-aware Dat...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Li, Xinyuan Lan, Yunshi East China Normal University China Shanghai Engineering Research Center of Big Data Management China

ISBN: (纸本)9798891761964

Large Language Models (LLMs) have achieved outstanding performance across various NLP tasks. Grammatical Error Correction (GEC) is a task aiming at automatically correcting grammatical errors in text, but it encounters a severe shortage of annotated data. researchers have tried to make full use of the generalization capabilities of LLMs and prompt them to correct erroneous sentences, which however results in unexpected over-correction issues. In this paper, we rethink the role of LLMs in GEC tasks and propose a method, namely TypeDA, considering LLMs as the annotators for type-aware data augmentation in GEC tasks. Different from the existing data augmentation methods, our method prevents in-distribution corruption and is able to generate sentences with multi-granularity error types. Our experiments verify that our method can generally improve the GEC performance of different backbone models with only a small amount of augmented data. Further analyses verify the high consistency and diversity of the pseudo data generated via our method. Our code can be accessed via the provided URL. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

An Effective Hybridization of Quantum-based Avian Navigation and Bonobo Optimizers to Solve Numerical and Mechanical engineering Problems

引用

Journal of Bionic engineering 2023年第3期20卷 1361-1385页

作者： Mohammad H.Nadimi-Shahraki Faculty of Computer Engineering Najafabad BranchIslamic Azad UniversityNajafabad***Iran Big Data Research Center Najafabad BranchIslamic Azad UniversityNajafabad***Iran

Hybrid metaheuristic algorithms play a prominent role in improving algorithms' searchability by combining each algorithm's advantages and minimizing any substantial shortcomings. The Quantum-based Avian Navigation Optimizer Algorithm (QANA) is a recent metaheuristic algorithm inspired by the navigation behavior of migratory birds. Different experimental results show that QANA is a competitive and applicable algorithm in different optimization fields. However, it suffers from shortcomings such as low solution quality and premature convergence when tackling some complex problems. Therefore, instead of proposing a new algorithm to solve these weaknesses, we use the advantages of the bonobo optimizer to improve global search capability and mitigate premature convergence of the original QANA. The effectiveness of the proposed Hybrid Quantum-based Avian Navigation Optimizer Algorithm (HQANA) is assessed on 29 test functions of the CEC 2018 benchmark test suite with different dimensions, 30, 50, and 100. The results are then statistically investigated by the Friedman test and compared with the results of eight well-known optimization algorithms, including PSO, KH, GWO, WOA, CSA, HOA, BO, and QANA. Ultimately, five constrained engineering optimization problems from the latest test suite, CEC 2020 are used to assess the applicability of HQANA to solve complex real-world engineering optimization problems. The experimental and statistical findings prove that the proposed HQANA algorithm is superior to the comparative algorithms.

关键词： Optimization Metaheuristic algorithms Evolutionary algorithm Quantum-based avian navigation optimizer algorithm engineering optimization problems,Bionic algorithm

来源：评论

学校读者我要写书评

暂无评论

Enhancing Tea Leaf Disease Identification with Lightweight MobileNetV2

引用

Computers, Materials & Continua 2024年第7期80卷 679-694页

作者： Zhilin Li Yuxin Li Chunyu Yan Peng Yan Xiutong Li Mei Yu Tingchi Wen Benliang Xie College of Big Data and Information Engineering Guizhou UniversityGuiyang550025China Power Semiconductor Device Reliability Engineering Center of the Ministry of Education Guiyang550025China State Key Laboratory of Public Big Data Guizhou UniversityGuiyang550025China The Mushroom Research Centre Guizhou UniversityGuiyang550025China The Engineering Research Center of Southwest Bio-Pharmaceutical Resources Ministry of EducationGuizhou UniversityGuiyang550025China

Diseases in tea trees can result in significant losses in both the quality and quantity of tea *** monitoring can help to prevent the occurrence of large-scale diseases in tea ***,existingmethods face challenges such as a high number of parameters and low recognition accuracy,which hinders their application in tea plantation monitoring *** paper presents a lightweight I-MobileNetV2 model for identifying diseases in tea leaves,to address these *** proposed method first embeds a Coordinate Attention(CA)module into the originalMobileNetV2 network,enabling the model to locate disease regions ***,a Multi-branch Parallel Convolution(MPC)module is employed to extract disease features across multiple scales,improving themodel’s adaptability to different disease ***,the AutoML for Model Compression(AMC)is used to compress themodel and reduce computational *** results indicate that our proposed algorithm attains an average accuracy of 96.12%on our self-built tea leaf disease dataset,surpassing the original MobileNetV2 by 1.91%.Furthermore,the number of model parameters have been reduced by 40%,making itmore suitable for practical application in tea plantation environments.

关键词： Disease identification coordinate attention mechanism multi-scale feature extraction model pruning

来源：评论

学校读者我要写书评

暂无评论

Intelligent proportioning model of converter scrap based on optimization algorithm

引用

Progress in Natural Science:Materials International 2024年第1期34卷 37-44页

作者： Chaojie Zhang Jinjun Cheng Liqiang Zhang Yingxue Wang Wei Zhang Jianwei Yuan Haichuan Wang School of Metallurgical Engineering Anhui University of Technology National Engineering Research Center for Public Safety Risk Perception and Control by Big Data(RPP) China Academic of Electronics and Information Technology Wuhu Xinxing Pipes Co. Ltd.

Scrap is one of the main raw materials in converter steelmaking. Due to the wide variety of scrap and the significant differences in its prices, the proportioning of scrap presents a challenge in converter steelmaking. This paper explores the optimal proportioning method of scrap for converters using an optimization mathematical model. Initially, the melting characteristics of scrap after being added to the converter's molten iron were investigated using finite element numerical simulations. The study found that when the weight of the scrap is fixed, both the shape and type of the scrap significantly influence the melting time. Subsequently, employing mathematical optimization methods and considering comprehensive process parameters of the 210t converter smelting, including the composition and unit price of the scrap, as well as the requirements of the converter steelmaking process for scrap, an optimization model for the proportioning of scrap in converters was *** model was solved using computer programming languages. Through this optimization model, it is possible to obtain the lowest cost per ton of molten steel in the converter smelting process by determining the optimal proportions of various types of scrap.

关键词： scrap proportioning Optimization model Converter steelmaking mathematical model numerical simulation

来源：评论

学校读者我要写书评

暂无评论

TD-LSTM: a time distributed and deep-learning-based architecture for classification of motor imagery and execution in EEG signals

引用

Neural Computing and Applications 2024年第25期36卷 15843-15868页

作者： Karimian-Kelishadrokhi, Morteza Safi-Esfahani, Faramarz Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran Big Data Research Center Najafabad Branch Islamic Azad University Najafabad Iran

One of the critical challenges in brain-computer interfaces is the classification of brain activities through the analysis of EEG signals. This paper seeks to improve the efficacy of deep learning-based rehabilitation systems, aiming to deliver superior services for individuals with physical disabilities. The research introduces the time distributed long short-term memory (TD-LSTM) framework, which incorporates an LSTM and a time distributed approach to classify brain activities. Learning in TD-LSTM is achieved by uncovering time-dependent semantic dependencies within EEG signals over time. By extracting all discriminative and relevant spatiotemporal dependencies via TD-LSTM, valuable information on different time steps in each sequence has been obtained. Time distributed approach shortens the input time series, making learning from long time series sequences easier, and the learning process of complex temporal and spatial dependencies in time series multi-channel EEG signals becomes more efficient. The main contributions in this paper can be outlined as follows: (1) implementation of brain activity binary classification of motor imagery/execution tasks using time distributed approach via RNN network for the first time, (2) evaluation of the performance and generalizability of the proposed method on four benchmark datasets, (3) dual-purpose classification which providing an efficient ways for classifying both types of motor imagery/execution brain activity. The experimental results show that the proposed method performs well compared to several baseline research works. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A map reduce-based big data clustering using swarm-inspired meta-heuristic algorithms

引用

Scientia Iranica 2024年第10期31卷 737-749页

作者： Tekieh, Razieh Beheshti, Zahra Faculty of Computer Engineering Najafabad Branch Islamic Azad University Najafabad Iran Big Data Research Center Najafabad Branch Islamic Azad University Najafabad Iran

Clustering is one of the important methods in data analysis. For big data, clustering is difficult due to the volume of data and the complexity of clustering algorithms. Therefore, methods that can handle a large amount of data clustering at the reasonable time are required. MapReduce is a powerful programming model that allows parallel algorithms to run in distributed computing environments. In this study, an improved artificial bee colony algorithm based on a MapReduce clustering model (MR-CWABC) is proposed. The weighted average without greedy selection of the results improves the local and global search of ABC. The improved algorithm is implemented in accordance with the MapReduce model on the Hadoop framework to allocate optimal samples to the clusters such that the compression and separation of the clusters are preserved. The proposed method is compared with some well-known bio-inspired algorithms such as particle swarm optimization (PSO), artificial bee colony (ABC) and gravitational search algorithm (GSA) implemented based on the MapReduce model on the Hadoop framework. The results showed that MR-CWABC is well-suited for big data, while maintaining clustering quality. The MR-CWABC demonstrates an improvement of 7.13%, 7.71% and 6.77% based on the average F-measure compared to MR-CABC, MR-CPSO, and MR-CGSA, respectively. © 2024 Sharif University of Technology. All rights reserved.

关键词： MapReduce

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：