检索结果-内蒙古大学图书馆

Research on Multi-Scale Feature Fusion Network Algorithm Based on Brain Tumor Medical Image Classification

Computers, Materials & Continua 2024年第6期79卷 5313-5333页

作者： Yuting Zhou Xuemei Yang Junping Yin Shiqi Liu Graduate School China Academy of Engineering PhysicsBeijing100000China Department of Computational Mathematics Beijing Institute of Applied Physics and Computational MathematicsBeijing100000China National Key Laboratory of Computational Physics Beijing100088China Shanghai Zhangjiang Institute of Mathematics Shanghai201203China

Gliomas have the highest mortality rate of all brain *** classifying the glioma risk period can help doctors make reasonable treatment plans and improve patients’survival *** paper proposes a hierarchical multi-scale attention feature fusion medical image classification network(HMAC-Net),which effectively combines global features and local *** network framework consists of three parallel layers:The global feature extraction layer,the local feature extraction layer,and the multi-scale feature fusion layer.A linear sparse attention mechanism is designed in the global feature extraction layer to reduce information *** the local feature extraction layer,a bilateral local attention mechanism is introduced to improve the extraction of relevant information between adjacent *** the multi-scale feature fusion layer,a channel fusion block combining convolutional attention mechanism and residual inverse multi-layer perceptron is proposed to prevent gradient disappearance and network degradation and improve feature representation *** double-branch iterative multi-scale classification block is used to improve the classification *** the brain glioma risk grading dataset,the results of the ablation experiment and comparison experiment show that the proposed HMAC-Net has the best performance in both qualitative analysis of heat maps and quantitative analysis of evaluation *** the dataset of skin cancer classification,the generalization experiment results show that the proposed HMAC-Net has a good generalization effect.

关键词： Medical image classification feature fusion transformer

来源：评论

学校读者我要写书评

暂无评论

Onfire 2023 Contest: what did we learn about real time fire detection from cameras?

引用

Journal of Ambient Intelligence and Humanized Computing 2025年第1期16卷 253-264页

作者： Gragnaniello, Diego Greco, Antonio Sansone, Carlo Vento, Bruno Department of Information and Electrical Engineering and Applied Mathematics University of Salerno Fisciano Italy Department of Electrical Engineering and Information Technology University of Napoli Federico II Naples Italy

Several methods for fire detection from camera streams have been proposed in recent years. While traditional techniques often emphasize recall, they frequently neglect critical factors such as minimizing false positives, ensuring timely alarm notifications and optimizing performance for devices with limited computational resources. The ONFIRE 2023 contest evaluates various approaches for detecting fire using smart cameras and establishes new evaluation metrics to measure precision, recall, notification promptness, processing speed and resource utilization. The eight participating teams received a training set that integrated all publicly available video datasets and were evaluated on a private test set. The latter includes positive samples where fire is not present at the beginning of the clip, as well as negative samples featuring moving fire-like objects. In this paper, we provide an overview of the competition’s dataset and review the proposed solutions, highlighting the winning approach, the limitations of existing datasets and the evaluation metrics used. By analyzing the results of the competition, we propose possible design choices and future directions that may help to reduce the false positive rate while preserving accuracy. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Fires

来源：评论

学校读者我要写书评

暂无评论

Recent advances in multipactor physics and mitigation

引用

High Voltage 2023年第6期8卷 1095-1114页

作者： Asif Iqbal De‐Qi Wen John Verboncoeur Peng Zhang Department of Electrical and Computer Engineering Michigan State UniversityEast LansingMichiganUSA Department of Computational Mathematics Scienceand EngineeringMichigan State UniversityEast LansingMichiganUSA

Recent progress made in the prediction,characterisation,and mitigation of multipactor discharge is reviewed for single‐and two‐surface ***,an overview of basic concepts including secondary electron emission,electron kinetics under the force law,multipactor susceptibility,and saturation mechanisms is provided,followed by a discus-sion on multipactor mitigation *** strategies are categorised into two broad areas–mitigation by engineered devices and engineered radio frequency(rf)*** approach is useful in different *** advances in multipactor physics and engineering during the past decade,such as novel multipactor prediction methods,un-derstanding space charge effects,schemes for controlling multipacting particle trajec-tories,frequency domain analysis,high frequency effects,and impact on rf signal quality are *** addition to vacuum electron multipaction,multipactor‐induced ioni-zation breakdown is also reviewed,and the recent advances are summarised.

关键词： multip kinetics susceptibility

来源：评论

学校读者我要写书评

暂无评论

Optimizing Crowd Counting in Dense Environments Through Curriculum Learning Training Strategy

引用

SN Computer Science 2024年第6期5卷 683页

作者： Fotia, Lidia Percannella, Gennaro Saggese, Alessia Vento, Mario Department of Information Engineering Electrical Engineering and Applied Mathematics (DIEM) University of Salerno Fisciano Italy

Counting individuals in highly crowded environments, characterized by thousands of people, has garnered significant attention in recent years, due to the high number of vertical markets wherein such algorithms can prove beneficial, ranging from smart city and transportation to retail sectors, among others. Within this context, in this paper we introduce a novel training methodology tailored for estimating the number of people, ensuring precise counting accuracy in both moderately and highly crowded scenarios. The proposed approach exploits a formulation of the problem based on point detection, where each point represents an individual’s head. Our innovative contributions center around the designing of a novel training strategy employing Curriculum Learning (CL), which aims to replicate the gradual learning process observed in human cognition, training on simpler tasks at the beginning and tackling more complex tasks as the training evolves. In order to evaluate the complexity of each sample image, we propose a novel indicator taking into account both the number of people and their distribution within the image. The experimentation phase encompassed 18 publicly available datasets;the obtained results validate the effectiveness of the proposed approach, surpassing the baseline state-of-the-art point detection by 71% and 70% in terms of Mean Absolute Error (MAE) and Mean Squared Error (MSE), respectively. © The Author(s) 2024.

关键词： Curriculum Learning High density crowd counting Point detection

来源：评论

学校读者我要写书评

暂无评论

Optimizations and applications in large-scale scenes of Monte Carlo geometry conversion code CMGC

引用

Nuclear Science and Techniques 2025年第4期36卷 220-232页

作者： Xin Wang Ling-Yu Zhang Xue-Ming Shi Zhen Wu Jun-Li Li Gui-Ming Qin Yuan-Guang Fu CAEP Software Center for High Performance Numerical Simulation Beijing 100088China Institute of Applied Physics and Computational Mathematics Beijing 100088China Department of Engineering Physics Tsinghua UniversityBeijing 100084China

In response to the demand for rapid geometric modeling in Monte Carlo radiation transportation calculations for large-scale and complex geometric scenes,functional improvements,and algorithm optimizations were performed using CAD-to-Monte Carlo geometry conversion(CMGC)*** representation(BRep)to constructive solid geometry(CSG)conversion and visual CSG modeling were combined to address the problem of non-convertible geometries such as spline *** splitting surface assessment method in BRep-to-CSG conversion was optimized to reduce the number of Boolean operations using an Open ***,in turn,reduced the probability of CMGC conversion *** auxiliary surface generation algorithm was optimized to prevent the generation of redundant auxiliary surfaces that cause an excessive decomposition of CAD geometry *** optimizations enhanced the usability and stability of the CMGC model *** was applied successfully to the JMCT transportation calculations for the conceptual designs of five China Fusion engineering Test Reactor(CFETR)*** rapid replacement of different blanket schemes was achieved based on the baseline CFETR *** geometric solid number of blankets ranged from hundreds to tens of *** correctness of the converted CFETR models using CMGC was verified through comparisons with the MCNP calculation *** CMGC supported radiation field evaluations for a large urban scene and detailed ship *** enabled the rapid conversion of CAD models with thousands of geometric solids into Monte Carlo CSG *** analysis of the JMCT transportation simulation results further demonstrated the accuracy and effectiveness of the CMGC.

关键词： Monte Carlo CAD BRep to CSG CMGC

来源：评论

学校读者我要写书评

暂无评论

Computer-Aided Diagnostic System for Brain Tumor Classification using Explainable AI 2

Computer-Aided Diagnostic System for Brain Tumor Classificat...

引用

2nd IEEE International Conference on Interdisciplinary Approaches in Technology and Management for Social Innovation, IATMSI 2024

作者： Padmapriya, S.T. Devi, M.S. Gayathri Department of Applied Mathematics and Computational Science Thiagarajar College of Engineering TamilNadu Madurai India

ISBN: (纸本)9798350360523

The field of computer-aided diagnosis (CAD) of brain tumors has been transformed by developments in medical imaging and artificial intelligence. The accuracy and interpretability of brain tumor classification are improved in this research using Explainable AI (XAI) techniques. A timely and correct diagnosis of brain tumors is essential for the best possible care and treatment of the patient. In contrast, traditional machine learning models often lack transparency and interpretability, making it difficult for clinicians to rely on their judgment. This study uses a Grad-Cam algorithm to create an understandable and interpretable CAD system for classifying brain tumors. Our approach not only achieves high classification accuracy, but also provides physicians with insights into the decision-making process, improving their understanding and confidence in the system's recommendations. We evaluate our model using a large and diverse dataset and compare it to modern deep learning models and traditional CAD systems. The results show that our CAD system with XAI extensions not only achieves improved accuracy but also provides useful insights into the decision-making process. Using this method, doctors may be able to diagnose patients more accurately. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning: Driven Strategies for Enhancing Student Academic Performance

Machine Learning: Driven Strategies for Enhancing Student Ac...

引用

2024 IEEE International Conference on Intelligent Computing and Emerging Communication Technologies, ICEC 2024

作者： Sakthipriya, D. Chandrakumar, T. Johnson, B. Thiagaraiar College of Engineering Department of Applied Mathematics and Computational Science Tamilnadu Madurai India

ISBN: (数字)9798331508432

ISBN: (纸本)9798331508432

In order to improve learning outcomes and reduce dropouts, educational institutions must anticipate students' academic performance. This study focuses on identifying effective prediction models and employing a wrapper feature selection method to estimate students' performance in final examinations. Utilizing a well-established dataset from diverse engineering departments, comprising 3560 data samples, the research aims to select the optimal algorithm and feature selection technique for predicting the number of course arrears for each student. Regression predictive modeling, specifically for numerical value prediction, is employed along with relevant metrics to assess model performance. The study employs various machine learning approaches to forecast students' academic performance based on acquired data, including ongoing assessments and examinations. A comparative evaluation of ML techniques using different metrics is presented. This information empowers students to monitor their academic progress and adapt their study strategies for improved performance. Additionally, five feature selection strategies are applied to identify the most accurate predictor. The study incorporates regression algorithms and wrapper feature selection methods to enhance student performance outcomes. Experimental results highlight the effectiveness of the Variance Inflation Factor (VIF) with adaptive Decision Tree regression as the superior approach. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Enhancing IoT Network Security with Graph Neural Networks for Node Anomaly Detection

Enhancing IoT Network Security with Graph Neural Networks f...

引用

Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition and Structural and Syntactic Pattern Recognition, S+SSPR 2024

作者： Carletti, Vincenzo Foggia, Pasquale Rosa, Francesco Vento, Mario Department of Information Engineering Electrical Engineering and Applied Mathematics University of Salerno Fisciano Italy

ISBN: (纸本)9783031805066

The widespread deployment of Internet of Things (IoT) devices in homes, industries, and public spaces presents significant cybersecurity challenges, particularly due to their limited computational capabilities and often insecure configurations. Detecting infected devices through network analysis presents a significant challenge given the diversity of network protocols and behaviors. Traditional methods, reliant on packet statistics or binary signatures, show their limits in these complex environments. Recent advancements in machine learning and deep learning offer promising alternatives, also through the use of graph-based representations that capture network topology and facilitate the detection of complex attack patterns. This paper presents a comprehensive analysis in a realistic setup of two state-of-the-art Graph Neural Networks (GNNs) designed for node anomaly detection, applied to a large-scale dataset of IoT network traffic. The dataset, comprising over 240,000 graphs extracted from IoT23, IoTID20, and IoT-Traces, includes both benign and malicious communications. In the analysis we take into account the impact of varying snapshot durations and graph-based representations on the performance achieved by the GNNs. The results suggest that using a state-of-the-art graph autoencoder (DOMINANT) with a computationally efficient representation (TDG) is the best trade-off among the considered constraints and variables. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Ion-focused propagation of a relativistic electron beam in the self-generated plasma in atmosphere

引用

Chinese Physics B 2022年第6期31卷 334-341页

作者： Jian-Hong Hao Bi-Xi Xue Qiang Zhao Fang Zhang Jie-Qing Fan Zhi-Wei Dong School of Electrical and Electronic Engineering Department North China Electric Power UniversityBeijing 102206China Institute of Applied Physics and Computational Mathematics Beijing 100094 China

It is known that ion-focused regime(IFR)can effectively suppress expansion of a relativistic electron beam(REB).Using the particle-in-cell Monte Carlo collision(PIC-MCC)method,we numerically investigate the propagation of an REB in neutral *** results demonstrate that the beam body is charge neutralization and a stable IFR can be *** a result,the beam transverse dimensions and longitudinal velocities keep close to the initial *** also calculate the charge and current neutralization factors of the *** with envelope equations,we obtain the variations of beam envelopes,which agree well with the PIC ***,both the energy loss and instabilities of the REB may lead to a low transport efficiency during long-range *** is proved that decreasing the initial pulse length of the REB can avoid the influence of electron *** parts of REB pulses to build a long-distance IFR in advance can improve the beam quality of subsequent ***,a long-distance IFR may contribute to the implementation of long-range propagation of the REB in space environment.

关键词： ion-focused regime(IFR) charge neutralization electron avalanche relativistic electron beam(REB) particle-in-cell Monte Carlo collision(PIC-MCC)

来源：评论

学校读者我要写书评

暂无评论

Combining Deep Networks with Model-Based Scene Segmentation for Reliably Detecting Rocks on Railway Tracks 8

Combining Deep Networks with Model-Based Scene Segmentation ...

引用

8th IEEE International Forum on Research and Technologies for Society and Industry Innovation, RTSI 2024

作者： Carletti, Vincenzo Foggia, Pasquale Ranieri, Speranza Saggese, Alessia Spingola, Camilla Vento, Mario University of Salerno Department of Information and Electrical Engineering and applied Mathematics Italy

ISBN: (纸本)9798350362138

Railway transportation is crucial to global mobility, serving as a sustainable conduit for transporting goods and passengers;unfortunately, it is vulnerable to different threats, like the presence of rocks on railway tracks. Accidents caused by rocks can disrupt transport schedules, damage infrastructure, and even lead to injuries or fatalities. Addressing these safety challenges is very important for ensuring the operation of rail networks, which in turn enhances overall mobility and minimizes delays, but also for protecting lives. In this paper, we propose a novel approach to detect rocks on the railway tracks using a camera mounted on the train's front-end. In particular, we exploit domain-specific knowledge regarding intrinsic characteristics of the camera, its positioning with respect to the rails and rail-track characteristics, together with the output of a deep neural network for semantic segmentation, to identify the railway track in the image. Once the track area is identified, it is partitioned into patches and a convolutional neural network is applied to analyze these patches and to detect the presence of rocks;furthermore, in order to enhance the robustness of the detection process, we employ a majority voting mechanism across a sequence of video frames. The experimentation, conducted over six videos augmented with the presence of rocks, confirm the effectiveness of the proposed approach. © 2024 IEEE.

关键词： Semantic Segmentation

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：