检索结果-内蒙古大学图书馆

A cascade transformer-based model for 3D dose distribution prediction in head and neck cancer radiotherapy

PHYSICS IN MEDICINE AND BIOLOGY 2024年第4期69卷 045010-045010页

作者： Gheshlaghi, Tara Nabavi, Shahabedin Shirzadikia, Samireh Moghaddam, Mohsen Ebrahimi Rostampour, Nima Shahid Beheshti Univ Fac Comp Sci & Engn Tehran Iran Kermanshah Univ Med Sci Sch Med Dept Med Phys Kermanshah Iran

Objective. Radiation therapy is one of the primary methods used to treat cancer in the clinic. Its goal is to deliver a precise dose to the planning target volume while protecting the surrounding organs at risk (OARs). However, the traditional workflow used by dosimetrists to plan the treatment is time-consuming and subjective, requiring iterative adjustments based on their experience. Deep learning methods can be used to predict dose distribution maps to address these limitations. Approach. The study proposes a cascade model for OARs segmentation and dose distribution prediction. An encoder-decoder network has been developed for the segmentation task, in which the encoder consists of transformer blocks, and the decoder uses multi-scale convolutional blocks. Another cascade encoder-decoder network has been proposed for dose distribution prediction using a pyramid architecture. The proposed model has been evaluated using an in-house head and neck cancer dataset of 96 patients and OpenKBP, a public head and neck cancer dataset of 340 patients. Main results. The segmentation subnet achieved 0.79 and 2.71 for Dice and HD95 scores, respectively. This subnet outperformed the existing baselines. The dose distribution prediction subnet outperformed the winner of the OpenKBP2020 competition with 2.77 and 1.79 for dose and dose-volume histogram scores, respectively. Besides, the end-to-end model, including both subnets simultaneously, outperformed the related studies. Significance. The predicted dose maps showed good coincidence with ground-truth, with a superiority after linking with the auxiliary segmentation task. The proposed model outperformed state-of-the-art methods, especially in regions with low prescribed doses. The codes are available at https://***/GhTara/Dose_Prediction.

关键词： radiation therapy dose distribution prediction deep learning transformer neural network multi-scale convolutional neural network head and neck cancer

来源：评论

学校读者我要写书评

暂无评论

multi-view domain adaption based multi-scale convolutional conditional invertible discriminator for cross-subject electroencephalogram emotion recognition

引用

COGNITIVE NEURODYNAMICS 2025年第1期19卷 1-19页

作者： Babu, S. Sivasaravana Venkatesan, Prabhu Velusamy, Parthasarathy Ganesan, Saravana Kumar Vel Tech High Tech Dr Rangarajan Dr Sakunthala Eng Dept Elect & Commun Engn Chennai 600062 Tamil Nadu India Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala En Dept Elect & Commun Engn Chennai 600062 Tamil Nadu India Karpagam Acad Higher Educ Dept Comp Sci & Engn Coimbatore 641021 Tamil Nadu India Karpagam Coll Engn Dept Elect & Commun Engn Coimbatore 641032 Tamil Nadu India

Cross subject Electroencephalogram (EEG) emotion recognition refers to the process of utilizing electroencephalogram signals to recognize and classify emotions across different individuals. It tracks neural electrical patterns, and by analyzing these signals, it's possible to infer a person's emotional state. The objective of cross-subject recognition is to create models or algorithms that can reliably detect emotions in both the same person and several other people. Accurately predicting emotions poses challenges due to dynamic traits. Models struggle with feature extraction, convergence, and negative transfer issues, hindering cross subject emotion recognition. The proposed model employs thorough signal preprocessing, Short-Time Geodesic Flow Kernel Fourier Transform (STGFKFT) for feature extraction, enhancing classifiers' accuracy. multi-view sheaf attention improves feature discrimination, while the multi-scale convolutional Conditional Invertible Puma Discriminator neural network (MSCCIPDNN) framework ensures generalization. Efficient computational techniques and the puma optimization algorithm enhance model robustness and convergence. The suggested framework demonstrates extraordinary success with high accuracy, of 99.5%, 99% and 99.50% for SEED, SEED-IV, and DEAP dataset sequentially. By incorporating these techniques, the proposed method aims to precisely recognition emotions, and accurately captures the features, thereby overcoming the limitations of existing methodologies.

关键词： Electroencephalogram Emotion recognition Geodesic flow kernel multi-scale convolutional neural network Puma optimizer

来源：评论

学校读者我要写书评

暂无评论

A novel deep learning approach to online quality control for multiple time series process

引用

COMPUTERS & INDUSTRIAL ENGINEERING 2025年 204卷

作者： Tian, Guangjie Liu, Yumin Xue, Li Wang, Ning Liang, Xiaoying Sun, Jingjing Zhengzhou Univ Sch Business Zhengzhou 450001 Henan Peoples R China Zhengzhou Univ Aeronaut Sch Management Engn Zhengzhou 450015 Henan Peoples R China Zhengzhou Univ Sch Management Zhengzhou 450001 Henan Peoples R China

The imbalance of abnormal data in the manufacturing process remains a challenge for applying deep learning methods in the quality control domain. The existing shallow machine learning methods for quality control of multivariate nonlinear manufacturing process have some problems, such as low monitoring efficiency and poor real-time performance. This paper introduces a novel deep learning approach for online quality control of multiple time-series processes with imbalanced data. The original process data is initially transformed into grayscale quality images to address imbalanced data and visualize the status of abnormal processes. Next, a convolutional block attention module (CBAM) is integrated into the adversarial classifier generative adversarial network (ACGAN) to tackle the issue of imbalanced data by augmenting the minority abnormal images. By utilizing a balanced dataset, a SA-MCNN recognition model is established, which consists of a multi-scale convolutional neural network (MCNN) with self-attention(SA) module to extract multi-scale features from multiple time series processes. Subsequently, a comprehensive quality control framework is proposed for online monitoring of multiple time series processes with imbalanced data and diagnosing root causes in the manufacturing process. An empirical study is conducted using data from an actual pasting process to validate the augmented images, assess the discrimination ability of the SA-MCNN model, evaluate the performance enhancement of the attention module, and measure the effectiveness of online quality control. The results of the study demonstrate that the proposed method effectively monitors abnormal processes with high accuracy and outperforms other imbalanced time series classification methods.

关键词： Quality control multiple time-series process Adversarial Classifier Generative Adversarial network multi-scale convolutional neural network Attention Mechanism

来源：评论

学校读者我要写书评

暂无评论

Dual Channel Residual Learning for Denoising Path Tracing

引用

INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS 2025年第1期25卷

作者： Liu, Ping Ji, Hangyu Commun Univ Zhejiang Sch Animat & Digital Art Hangzhou 310018 Peoples R China Xian Conservatory Mus Contemporary Mus Acad Xian 710061 Peoples R China

In this paper, we present a denoising method for path tracing using residual learning with convolutional neural networks (CNNs). Noisy artifacts in path tracing are inherited from insufficient sampling, which often generates over- or under-exposed values when integrating the limited bright or dark samples in a pixel. In this paper, we introduce a dual channel residual learning CNNs which separates the over and under-exposed signals in order to provide an efficient denoising filter for the path tracing rendering. Furthermore, we present an advanced CNN comprised of variable-sized kernels in each convolutional layer. Our CNN detects features in different scales providing an adaptive denoising filter capability which is optimal for extracting various contextual details in a complex scene. The experiments demonstrate that our method generates better visual quality than other compared approaches across various rendering effects.

关键词： Path tracing image denoising residual learning multi-scale convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

A method for constructing rolling bearing lifetime health indicator based on multi-scale convolutional neural networks

引用

JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING 2019年第11期41卷 1-11页

作者： Wu, Chunzhi Feng, Fuzhou Wu, Shoujun Jiang, Pengcheng Wang, Jie Acad Army Armored Forces Dept Vehicle Engn Beijing 100072 Peoples R China

The degradation of rolling bearings is complex, and traditional methods of degenerating feature degradation are highly dependent on previous research and expertise. However, the traditional methods' ability for learning the complex relationship between degraded features and large amounts of measured data is limited. So, it is difficult to construct a single health indicator (HI) to predict the degradation state of the bearing. In order to solve this problem, a multi-scale convolutional neural network (MSCNN) is proposed, which uses the frequency signal as input to construct HI. In combination with the "bathtub curve," the HI we proposed is constructed by the inverse hyperbolic tangent function (atanh) method which is different from the proportional HI construction method. Five kinds of processing methods, such as original vibration signal, frequency signal and three kinds of modal decomposition preprocessed signals, are tested with PHM 2012 bearing lifetime data. And the proposed method is compared with other three HI construction methods. The experimental results show that under the HI construction method of atanh, the MSCNN model with the input of frequency signal can better represent the degradation state of the bearing compared with other methods. Meanwhile, the remaining life prediction is more accurate compared.

关键词： Rolling bearing Degradation prediction multi-scale convolutional neural network Bathtub curve

来源：评论

学校读者我要写书评

暂无评论

MSCNN-LSTM Model for Predicting Return Loss of the UHF Antenna in HF-UHF RFID Tag Antenna

引用

Computers, Materials & Continua 2023年第5期75卷 2889-2904页

作者： Zhao Yang Yuan Zhang Lei Zhu Lei Huang Fangyu Hu Yanping Du Xiaowei Li School of Mechanical and Electrical Engineering Beijing Institute of Graphic CommunicationBeijing102600China Postal Industry Technology R&D Center Beijing Institute of Graphic CommunicationBeijing102600China Collage of Electronic Information and Automation Civil Aviation University of ChinaTianjin300300China

High-frequency(HF)and ultrahigh-frequency(UHF)dual-band radio frequency identification(RFID)tags with both near-field and farfield communication can meet different application ***,it is time-consuming to calculate the return loss of a UHF antenna in a dualband tag antenna using electromagnetic(EM)*** overcome this,the present work proposes a model of a multi-scale convolutional neural network stacked with long and short-term memory(MSCNN-LSTM)for predicting the return loss of UHF antennas instead of EM *** the proposed MSCNN-LSTM,the MSCNN has three branches,which include three convolution layers with different kernel sizes and ***,MSCNN can extract fine-grain localized information of the antenna and overall *** LSTM can effectively learn the EM characteristics of different structures of the antenna to improve the prediction accuracy of the *** results show that the mean absolute error(0.0073),mean square error(0.00032),and root mean square error(0.01814)of theMSCNNLSTM are better than those of other prediction *** predicting the return loss of 100UHFantennas,compared with the simulation time of 4800 s for High Frequency Structure Simulator(HFSS),MSCNN-LSTM takes only 0.927519 s under the premise of ensuring prediction accuracy,significantly reducing the calculation time,which provides a basis for the rapid design of HF-UHF RFID tag ***-LSTM is used to determine the dimensions of the UHF antenna *** return loss of the designed dualband RFID tag antenna is−58.76 and−22.63 dB at 13.56 and 915 MHz,respectively,achieving the desired goal.

关键词： HF-UHF RFID tag antenna multi-scale convolutional neural network long-short term memory return loss

来源：评论

学校读者我要写书评

暂无评论

A deep learning approach using temporal-spatial data of computational fluid dynamics for fast property prediction of gas-solid fluidized bed

引用

KOREAN JOURNAL OF CHEMICAL ENGINEERING 2023年第1期40卷 57-66页

作者： Qin, Pengfei Xia, Zhaojie Guo, Li Chinese Acad Sci Inst Proc Engn State Key Lab Multiphase Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Chem Engn Beijing 100049 Peoples R China Chinese Acad Sci Innovat Acad Green Manufacture Beijing 100190 Peoples R China

To deal with the critical issue of long computational time in practical application of computational fluid dynamics (CFD), this paper presents a new approach of deep learning for voidage prediction (DeepVP) that couples short time CFD simulations (limited CFD iterations) with the deep learning method to accelerate the 2D voidage distribution prediction for a gas-solid fluidized bed at steady state. Short time CFD simulations are first performed to obtain a sequence of voidage distribution images containing the temporal-spatial property of a gas-solid fluidized bed of the early period. A deep learning model is built to predict the voidage distribution at steady state, which is achieved by implementing multi-scale convolutional neural networks based on the sequence of voidage images. The case study results for a bubbling bed show that the voidage distribution at steady state for the bubbling bed can be predicted with comparable accuracy of conventional CFD simulations at about 1/30th computational cost. Moreover, the DeepVP method exhibits better extrapolation capability than the deep learning approach merely based on CFD condition parameters.

关键词： Gas-solid Fluidized Bed CFD Surrogate Model Deep Learning multi-scale convolutional neural network Voidage Distribution Prediction

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid heuristic adopted ensemble of deep learning models for COVID-19 detection framework using CT and X-Ray images

引用

COMPUTER METHODS IN BIOMECHANICS AND BIOMEDICAL ENGINEERING-IMAGING AND VISUALIZATION 2023年第6期11卷 2457-2478页

作者： Shiba, C. Mary Navaneethakrishnan, M. Kalaipriya, V Jothi, E. Gowsalya, S. RMK Engn Coll Dept Comp Sci & business Syst Chennai India St Joseph Coll Engn Dept Comp Sci & Engn Chennai India RMK Coll Engn & Technol Dept Comp Sci & Engn Tiruvallur India New Prince Shri Bhavani Coll Engn & Technol Dept Informat technol Chennai India Hindustan Inst technol & Sci Dept Comp Sci & Engn Gowrivakkam India

In 2019, Corona Virus Disease (COVID)-19 has created an important impact on people's health and economy because of its rapid spreading. Therefore, the earlier detection and diagnosis for handling the further spread is regarded as a significant factor. Computed Tomography (CT) images of the lungs are utilised for the detection process of COVID-19 infection. Chest X-Ray (CXR) and CT serves as the major source for the identification of COVID-19. Some of the classifiers have shown promising outcomes as well as better performance over various medical imaging applications and computer vision processes. Due COVID pandemic, researchers have utilised standard techniques for accurately identifying the coronavirus infection in lung images. Here, a new COVID-19 detection approach has been implemented with the adoption of ensemble classifiers to recognise the occurrence of COVID-19 infection at the starting phase. The required CT and the CXR images are garnered from publicly presented online sources. Meanwhile, the acquired images undergo the process of pre-processing using filtering methods and histogram equalisation techniques in order to ignore the unnecessary artifacts are presented in the images. Then, the detection of COVID-19 is made possible through Ensemble Classifiers (EC) such as multi-scale convolutional neural networks (CNN), Residual Attention networks (RAN), Visual Geometry Group (VGG), and Long Short Term Memory (LSTM), where the variables within the machine learning strategies are tuned by Modified Mexican Axolotl Shuffled Frog-Leaping Optimization (MMASFLO). The efficacy of the newly developed ensemble classifier-based COVID-19 detection approaches will be tested through various benchmark datasets, and is tested with several existing approaches and conventional COVID-19 detection approaches.

关键词： COVID-19 Detection ensemble classifiers visual geometry group long short term memory residual attention network multi-scale convolutional neural network Modified Mexican Axolotl Shuffled Frog-Leaping Optimization

来源：评论

学校读者我要写书评

暂无评论

The Construction of Campus network Public Opinion Analysis Model Based on T-GAN Model

引用

INTERNATIONAL JOURNAL OF ADVANCED COMPUTER SCIENCE AND APPLICATIONS 2023年第12期14卷 453-462页

作者： Zhang, Jianan Nantong Univ Sch Educ Sci Nantong 226019 Peoples R China

The advancement of information technology has made the internet and social media an indispensable part of modern life, but with it comes a flood of false information and rumors. The aim of this study is to develop a technology that can automatically identify campus network public opinion information, in order to protect student groups from the intrusion of erroneous information, maintain their mental health, and promote a clear campus public opinion environment. This study used the Scrapy framework to write web scraping scripts to collect campus public opinion data, and carried out cleaning and preprocessing. Then, a transformer based generative adversarial network (T-GAN) model was designed, combined with a multi-scale convolutional neural network (MCNN) structure, for public opinion analysis on campus networks. The results show that the accuracy of the dataset processed by the T-GAN model has been improved on LGBT, KNN, SVM, and RoBERTa, proving that the campus network public opinion analysis model based on the T-GAN model helps to automatically identify campus network public opinion, protect students' physical and mental health, and promote the healthy development of the campus network environment.

关键词： Public opinion analysis T-GAN feature extraction multi-scale convolutional neural network campus network

来源：评论

学校读者我要写书评

暂无评论

Improving Classification of Breast Cancer by Utilizing the Image Pyramids of Whole-Slide Imaging and multi-scale convolutional neural networks 43

Improving Classification of Breast Cancer by Utilizing the I...

引用

43rd IEEE-Computer-Society Annual International Computers, Software and Applications Conference (COMPSAC)

作者： Tong, Li Sha, Ying Wang, May D. Georgia Inst Technol Dept Biomed Engn Atlanta GA 30332 USA Emory Univ Atlanta GA 30332 USA Georgia Inst Technol Sch Biol Atlanta GA 30332 USA

ISBN: (纸本)9781728126074

Whole-slide imaging (WSI) is the digitization of conventional glass slides. Automatic computer-aided diagnosis (CAD) based on WSI enables digital pathology and the integration of pathology with other data like genomic biomarkers. Numerous computational algorithms have been developed for WSI, with most of them taking the image patches cropped from the highest resolution as the input. However, these models exploit only the local information within each patch and lost the connections between the neighboring patches, which may contain important context information. In this paper, we propose a novel multi-scale convolutional network (ConvNet) to utilize the built-in image pyramids of WSI. For the concentric image patches cropped at the same location of different resolution levels, we hypothesize the extra input images from lower magnifications will provide context information to enhance the prediction of patch images. We build corresponding ConvNets for feature representation and then combine the extracted features by 1) late fusion: concatenation or averaging the feature vectors before performing classification, 2) early fusion: merge the ConvNet feature maps. We have applied the multi-scale networks to a benchmark breast cancer WSI dataset. Extensive experiments have demonstrated that our multi-scale networks utilizing the WSI image pyramids can achieve higher accuracy for the classification of breast cancer. The late fusion method by taking the average of feature vectors reaches the highest accuracy (81.50%), which is promising for the application of multi-scale analysis of WSI.

关键词： Whole-Slide Imaging Breast Cancer Image Pyramid multi-scale convolutional neural network

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：