检索结果-内蒙古大学图书馆

Enhancing Medical Image Classification with BSDA-Mamba:Integrating Bayesian Random Semantic Data Augmentation and Residual Connections

引用

computers, Materials & Continua 2025年第6期83卷 4999-5018页

作者： Honglin Wang Yaohua Xu Cheng Zhu School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science Nanjing University of Information Science and TechnologyNanjing210044China Electrical&Computer Engineering University of Illinois at Urbana ChampaignUrbanaIL 61801USA

Medical image classification is crucial in disease diagnosis,treatment planning,and clinical *** introduced a novel medical image classification approach that integrates Bayesian Random Semantic Data Augmentation(BSDA)with a Vision Mamba-based model for medical image classification(MedMamba),enhanced by residual connection blocks,we named the model *** augments medical image data semantically,enhancing the model’s generalization ability and classification ***,a deep learning-based state space model,excels in capturing long-range dependencies in medical *** incorporating residual connections,BSDA-Mamba further improves feature extraction *** comprehensive experiments on eight medical image datasets,we demonstrate that BSDA-Mamba outperforms existing models in accuracy,area under the curve,and *** results highlight BSDA-Mamba’s potential as a reliable tool for medical image analysis,particularly in handling diverse imaging modalities from X-rays to *** open-sourcing of our model’s code and datasets,will facilitate the reproduction and extension of our work.

关键词： Deep learning medical image classification data augmentation visual state space model

来源：评论

学校读者我要写书评

暂无评论

An Improved Hybrid Deep Learning Approach for Security Requirements Classification

引用

computers, Materials & Continua 2025年第3期82卷 4041-4067页

作者： Shoaib Hassan QianmuLi Muhammad Zubair Rakan AAlsowail Muhammad Umair School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing210094China Faculty of Information Technology and Computer Science University of Central PunjabLahore5400Pakistan Computer Skills Self-Development Skills DevelopmentDeanship of Common First YearKing Saud UniversityRiyadh11362Saudia Arabia

As the trend to use the latestmachine learning models to automate requirements engineering processes continues,security requirements classification is tuning into the most researched field in the software engineering *** literature studies have proposed numerousmodels for the classification of security ***,adopting those models is constrained due to the lack of essential datasets permitting the repetition and generalization of studies employing more advanced machine learning ***,most of the researchers focus only on the classification of requirements with security *** did not consider other nonfunctional requirements(NFR)directly or indirectly related to *** has been identified as a significant research gap in security requirements *** major objective of this study is to propose a security requirements classification model that categorizes security and other relevant security *** use PROMISE_exp and DOSSPRE,the two most commonly used datasets in the software engineering *** proposed methodology consists of two *** the first step,we analyze all the nonfunctional requirements and their relation with security *** found 10 NFRs that have a strong relationship with security *** the second step,we categorize those NFRs in the security requirements *** proposedmethodology is a hybridmodel based on the ConvolutionalNeural Network(CNN)and Extreme Gradient Boosting(XGBoost)***,we evaluate the model by updating the requirement type column with a binary classification column in the dataset to classify the requirements into security and non-security *** performance is evaluated using four metrics:recall,precision,accuracy,and F1 Score with 20 and 28 epochs number and batch size of 32 for PROMISE_exp and DOSSPRE datasets and achieved 87.3%and 85.3%accuracy,*** proposed study shows an enhancement in metrics

关键词： Requirements engineering security requirements deep learning CNN XGBoost classification

来源：评论

学校读者我要写书评

暂无评论

Stress Distribution Characteristics and Energy Evolution Law of Drilling Pressure Relief 43

Stress Distribution Characteristics and Energy Evolution Law...

引用

43rd International Conference on Ground Control in Mining, ICGCM 2024, held at the 2024 SME Annual Conference and Expo

作者： Zhang, Kai Li, Yingming Chi, Xiaolou Yang, Ke Zhang, Xiangyang School of Mining Engineering Anhui University of Science and Technology China

ISBN: (纸本)9798331300487

Based on the research background of 1303 working face return air roadway in Jinyuan Zhaoxian Mine, Shaanxi Province, a method of determining the reasonable spacing of boreholes is proposed based on the stress transfer degree of coal above and between boreholes, combined with the law of plastic zone and energy evolution by theoretical analysis and numerical simulation. After drilling pressure relief, the average daily energy of microseismic events decreased by 70%, and those with microseismic energy greater than 104 J decreased by 99.2%. The research has a strong guiding significance and research value for determining the reasonable distance of borehole pressure relief. © ICGCM 2024 . All rights reserved.

关键词： Boreholes

来源：评论

学校读者我要写书评

暂无评论

Improved Set Algebra-Based Heuristic Technique for Training Multiplicative Functional Link Artificial Neural Networks for Financial Time Series Forecasting

引用

SN computer science 2024年第5期5卷 567页

作者： Behera, Sudersan Kumar, AVS Pavan Nayak, Sarat Chandra Department of Computer Science and Engineering School of Engineering & amp Technology GIET University Gunupur India Department of Computer Science and Engineering School of Technology GITAM University Hyderabad India

The current study is defined by two main aims. An effective strategy for improving local search is to combine the Set Algebra-Based Heuristic Algorithm (SAHA) algorithm with the Nelder-Mead simplex method. The approach outlined above, referred to as the Improved SAHA (ISAHA), and has the ability to produce superior outcomes. The multiplicative functional link artificial neural network (MFLANN) is an improved version of the functional link artificial neural network that promotes exploration by replacing the summing unit in the output layer with a multiplication unit. Moreover, the combination of ISAHA and MFLANN results in the development of ISAHA-MFLANN, a sophisticated hybrid forecasting model. The main assessment of the hybrid model rests on its ability to forecast complex and dynamic financial time series. It's possible to get around the problems that come with traditional learning-based MFLANN techniques by using MFLANN's advanced approximation features and ISAHA's resilient global search features together. Experimental verification using two stock market datasets and three currency exchange rates demonstrates the validity of the idea. The results show that the suggested improved SAHA hybrid learning works well at improving six standard benchmark functions. The ISAHA-MFLANN model is also statistically significant at accurately capturing the volatility that is inherent in the financial time series. In addition, it surpasses other models such as SAHA-MFLANN, Monarch Butterfly Optimization-MFLANN, Particle Swarm Optimization-MFLANN, Genetic Algorithm-MFLANN, Gradient Descent-MFLANN, Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Auto Regressive Integrated Moving Average (ARIMA). © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Exchange rate forecasting Improved Set Algebra-Based Heuristic Algorithm Multiplicative functional link artificial neural network Stock market forecasting

来源：评论

学校读者我要写书评

暂无评论

Constructing a stable interface on Ni-rich LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2) cathode via lactic acid-assisted engineering strategy

引用

Journal of Energy Chemistry 2024年第3期90卷 412-422,I0010页

作者： Weijian Tang Chengzhi Hu AFei Li Xiaoqin Huang Zhangxian Chen Jianhui Su Weixin Zhang Institute of Energy Hefei Comprehensive National Science CenterHefei 230031AnhuiChina School of Chemistry and Chemical Engineering Hefei University of Technology and Anhui Key Laboratory of Controllable Chemical Reaction&Material Chemical EngineeringHefei 230009AnhuiChina School of Electrical Engineering and Automation Hefei University of TechnologyHefei 230009AnhuiChina

Ni-rich layered oxides are potential cathode materials for next-generation high energy density Li-ion batteries due to their high capacity and low ***,the inherently unstable surface properties,including high levels of residual Li compounds,dissolution of transition metal cations,and parasitic side reactions,have not been effectively addressed,leading to significant degradation in their electrochemical *** this study,we propose a simple and effective lactic acid-assisted interface engineering strategy to regulate the surface chemistry and properties of Ni-rich LiNi_(0.8)Co_(0.1)Mr_(0.1)O_(2) *** novel surface treatment method successfully eliminates surface residual Li compounds,inhibits structural collapse,and mitigates cathode-electrolyte interface film *** a result,the lactic acidtreated LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2) achieved a remarkable capacity retention of 91.7% after 100 cycles at 0.5 C(25℃) and outstanding rate capability of 149.5 mA h g^(-1) at 10 C,significantly outperforming the pristine ***,a pouch-type full cell incorporating the modified LiNi_(0.8)Co_(0.1)Mn_(0.1)O_(2) cathode demonstrates impressive long-term cycle life,retaining 81.5% of its capacity after 500 cycles at 1 *** importantly,the thermal stability of the modified cathode is also dramatically *** study offers a valuable surface modification strategy for enhancing the overall performance of Ni-rich cathode materials.

关键词： Residual Li Lactic acid Surface modification Carbon coating Layered cathode Ni-rich

来源：评论

学校读者我要写书评

暂无评论

Microstructure Characteristics and Elevated Temperature Mechanical Properties of a B Containedβ-solidifiedγ-TiAl Alloy

引用

Journal of Wuhan university of technology(Materials science) 2024年第3期39卷 738-746页

作者：王秀琦 GUO Ruiqi 刘国怀 LI Tianrui YANG Yuxuan CHEN Yang XIN Meiling WANG Zhaodong State Key Laboratory of Rolling and Automation Northeastern UniversityShenyang 110819China School of Materials Science and Engineering Harbin Institute of Technology at ShenzhenShenzhen 518055China School of Metallurgical Engineering Anhui University of TechnologyMaanshan 243000China

The improved microstructure and enhanced elevated temperature mechanical properties of Ti-44Al-5Nb-(Mo,V,B)alloys were obtained by vacuum arc re-melting(VAR)and primary annealing heat treatment(HT)of 1260℃/6 h/Furnace cooling(FC).The phase transformation,microstructure evolution and tensile properties for as-cast and HTed alloys were *** indicate that three main phase transformation points are determined,T_(eut)=1164.3℃,T_(γsolv)=1268.3℃and T_(βtrans)=1382.8℃.There are coarse lamellar colonies(300μm in length)and neighbor reticular B2 andγgrain(3-5μm)in as-cast alloy,while lamellar colonies are markedly refined and multi-oriented(20-50μm)as well as the volume fraction and grain sizes of equiaxedγand B2 phases(about 15μm)significantly increase in as-HTed *** transformations involvingα+γ→α+γ+β/B2 and discontinuousγcoarsening contribute to the above ***(1-3μm)act as nucleation sites forβ_(eutectic) and produce massiveβgrains with different orientations,thus effectively refining the lamellar colonies and forming homogeneous multi-phase *** curves show both the alloys exhibit suitable performance at 800℃.As-cast alloy shows a higher ultimate tensile stress of 647 MPa,while a better total elongation of more than 41%is obtained for as-HTed *** mechanical properties improvement is mainly attributed to fine,multi-oriented lamellar colonies,coordinated deformation of homogeneous multi-phase microstructure and borides within lamellar interface preventing crack propagation.

关键词： TiAl alloy phase transformation heat treatment boride microstructure mechanical properties

来源：评论

学校读者我要写书评

暂无评论

Ontology-Based Semantic Reasoning for Multi-Source Heterogeneous Industrial Devices Using OPC UA

引用

IEEE Internet of Things Journal 2025年第13期12卷 25020-25032页

作者： Bi, Jing Wu, Rina Yuan, Haitao Wang, Ziqi Zhang, Jia Zhou, MengChu Beijing University of Technology College of Computer Science Beijing100124 China Beihang University School of Automation Science and Electrical Engineering Beijing China Southern Methodist University Department of Computer Science Lyle School of Engineering DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

The advent of smart manufacturing in Industry 4.0 signifies the era of connections. As a communication protocol, Object linking and embedding for Process Control Unified Architecture (OPC UA) can address most semantic heterogeneity issues. However, its semantics are not formally defined at the application layer. To address the information silo problem caused by semantic heterogeneity, an integration framework named Querying of Ontology Mapping-based OPC UA (QOMOU) is proposed. QOMOU extracts information models of OPC UA servers into resource description framework triples and utilizes web ontology language for semantic enrichment and inference. Then, an Event Class Semantic Similarity Calculation (ECSSC) method is proposed for device type identification, enabling the classification of semantically heterogeneous OPC UA devices. The effectiveness of ECSSC is validated through queries with the RDF query language (SPARQL) protocol in Apache Jena. Experimental results demonstrate that ECSSC improves the accuracy of device identification by approximately 7% compared to benchmark device identification models. Specifically, compared with graph embedding-based methods, QOMOU’s query performance is approximately 13% higher, and its query efficiency is 5% higher on average compared to both structured query and extensible markup languages. Moreover, by employing a keyword-matching algorithm, the query accuracy of the existing heterogeneous data integration scheme is improved by 4% on average. This enhancement can boost the operational efficiency of Internet of Things systems based on the OPC UA architecture. © 2014 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Analyzing the performance of geometric mean optimization-based artificial neural networks for cryptocurrency forecasting

引用

International Journal of Information technology (Singapore) 2024年 1-13页

作者： Behera, Sudersan Kumar, A V S Pavan Nayak, Sarat Chandra Department of Computer Science and Engineering School of Engineering and Technology GIET University Odisha Gunupur India Department of Computer Science and Engineering School of Technology GITAM University Hyderabad India

In this study, we utilize a recently proposed non-parametric metaheuristic algorithm known as geometric mean optimization (GMO) to adjust the hidden layer input weights and bias of six ANN variants, namely PSNN, SPNN, JPSNN, FLANN, RBFN, and MLP, thereby creating six hybrid models. Later on, we engage all these hybrid models to predict the closing price of four widely used cryptocurrencies. For comparison purposes, we also engage the widely popular traditional GD algorithm to fix the hidden layer input weights and biases of the same set of ANNs, creating six alternate models and employing those models for the same prediction task. In order to assess the effectiveness of each model, we employ the mean squared error (MSE), root mean square error (RMSE), and mean absolute percentage error (MAPE) statistics. The experimental result shows the superiority of GMO-based PSNN over others. We then compare the GMO-based PSNN's outcomes with some of the existing hybrid models in the literature. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： ANN Cryptocurrency forecasting Financial time series forecasting GMO Higher order neural networks

来源：评论

学校读者我要写书评

暂无评论

Addressing Transport Issues in Non‑Aqueous Li–air Batteries to Achieving High Electrochemical Performance

引用

Electrochemical Energy Reviews 2023年第1期6卷 187-233页

作者： Zhuojun Zhang Xu Xiao Xingbao Zhu Peng Tan Department of Thermal Science and Energy Engineering University of Science and Technology of China(USTC)Hefei 230026AnhuiChina School of Physics Harbin Institute of TechnologyHarbin 150080HeilongjiangChina

Li–air batteries are a promising type of energy storage technology because of the ultra-high theoretical specific *** advances are made in recent years,including the illustration of reaction mechanisms,development of effective catalyst materials,and design of battery structures accelerating species ***,the application still suffers from low rate capability,poor round-trip efficiency,and unsatisfactory cycling ***,we mainly focus on the species transport issues of non-aqueous Li–air batteries,including Li^(+) across the solid surfaces and the electrolyte,O_(2)solubility and diffusivity,distribution of intermediates and products,and side reactions by other components from the ***,considerable emphasis is paid to expound the approaches for enhancing species transport and accelerating reactions,among which the realization of well-designed electrode structures and flowing electrolytes is of great significance for the rapid migration of O_(2)and Li^(+)and mitigating the negative effects by solid insoluble Li_(2)O_(2).Moreover,optimizing reaction interfaces and operating conditions is an attractive alternative to promote reaction *** work aims to identify the mechanism of transport issues and corresponding challenges and perspectives,guiding the structure design and material selection to achieve high-performance Li–air batteries.

关键词： Li-air battery Solubility Species transport Key issues Enhancement

来源：评论

学校读者我要写书评

暂无评论

Knowledge Contrast-Enhanced Continuous Prompt Tuning for few-shot learning

引用

Neural Computing and Applications 2025年第19期37卷 14151-14169页

作者： Li, Fei Huang, Youzhi Wang, Yanyan Chen, Zhengyi Xu, Yin Li, Xiangyang School of Computer Science and Technology University of Science and Technology of China Fuxing Road 100 Anhui Hefei230031 China Innovation + Research Institute GuoChuang Cloud Technology Ltd. Wenqu Road 355 Anhui Hefei230031 China The CAS Key Laboratory of Wireless-Optical Communications University of Science and Technology of China Fuxing Road 100 Anhui Hefei230031 China

Prompt tuning for pre-trained language models (PLMs) has shown its effectiveness and superiority in few-shot learning. However, its success heavily depends on prompt engineering which designs different prompts for specific tasks. Continuous prompt templates can avoid this compared to discrete prompt templates, but how to obtain an optimal continuous prompt template is a question worth studying. In order to overcome this challenge, we focus on eliciting knowledge from PLMs and propose a novel Knowledge Contrast-Enhanced Continuous Prompt Tuning method (KCPT) based on contrastive learning. This method aims to obtain more meaningful and distinguishable prompt embeddings by introducing a contrastive learning strategy, enabling the model to better capture subtle differences between different prompts. Extensive experiments on 10 datasets demonstrate that our KCPT improves accuracy by 1–3% and stability by 26–40% on average compared to SOTA prompt tuning methods in low-resource settings. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Contrastive 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：