检索结果-内蒙古大学图书馆

MAUN:Memory-Augmented Deep Unfolding Network for Hyperspectral Image Reconstruction

IEEE/CAA Journal of Automatica Sinica 2024年第5期11卷 1139-1150页

作者： Qian Hu Jiayi Ma Yuan Gao Junjun Jiang Yixuan Yuan Electronic Information School Wuhan UniversityWuhan 430072China School of Computer Science and Technology Harbin Institute of TechnologyHarbin 150001China Department of Electronic Engineering Chinese University of Hong KongHong Kong 999077China

Spectral compressive imaging has emerged as a powerful technique to collect the 3D spectral information as 2D *** algorithm for restoring the original 3D hyperspectral images(HSIs)from compressive measurements is pivotal in the imaging *** approaches painstakingly designed networks to directly map compressive measurements to HSIs,resulting in the lack of interpretability without exploiting the imaging *** some recent works have introduced the deep unfolding framework for explainable reconstruction,the performance of these methods is still limited by the weak information transmission between iterative *** this paper,we propose a Memory-Augmented deep Unfolding Network,termed MAUN,for explainable and accurate HSI ***,MAUN implements a novel CNN scheme to facilitate a better extrapolation step of the fast iterative shrinkage-thresholding algorithm,introducing an extra momentum incorporation step for each iteration to alleviate the information ***,to exploit the high correlation of intermediate images from neighboring iterations,we customize a cross-stage transformer(CSFormer)as the deep denoiser to simultaneously capture self-similarity from both in-stage and cross-stage features,which is the first attempt to model the long-distance dependencies between iteration *** experiments demonstrate that the proposed MAUN is superior to other state-of-the-art methods both visually and *** code is publicly available at https://***/HuQ1an/MAUN.

关键词： Deep folding iteration

来源：评论

学校读者我要写书评

暂无评论

Integrating Transformer and Bidirectional Long Short-Term Memory for Intelligent Breast Cancer Detection from Histopathology Biopsy Images

引用

computer Modeling in engineering & sciences 2024年第10期141卷 443-458页

作者： Prasanalakshmi Balaji Omar Alqahtani Sangita Babu Mousmi Ajay Chaurasia Shanmugapriya Prakasam Department of Computer Science College of Computer ScienceKing Khalid UniversityAbha61451Saudi Arabia College of Science and Arts in Rijal Alma King Khalid UniversityAbha61451Saudi Arabia Department of Information Technology Muffakham Jah College of Engineering and TechnologyHyderabad500034India Department of Computer Science and Business Systems Rajalakshmi Engineering CollegeThandalam602105India

Breast cancer is a significant threat to the global population,affecting not only women but also a threat to the entire *** recent advancements in digital pathology,Eosin and hematoxylin images provide enhanced clarity in examiningmicroscopic features of breast tissues based on their staining *** cancer detection facilitates the quickening of the therapeutic process,thereby increasing survival *** analysis made by medical professionals,especially pathologists,is time-consuming and challenging,and there arises a need for automated breast cancer detection *** upcoming artificial intelligence platforms,especially deep learning models,play an important role in image diagnosis and ***,the histopathology biopsy images are taken from standard data ***,the gathered images are given as input to the Multi-Scale Dilated Vision Transformer,where the essential features are ***,the features are subjected to the Bidirectional Long Short-Term Memory(Bi-LSTM)for classifying the breast cancer *** efficacy of the model is evaluated using divergent *** compared with other methods,the proposed work reveals that it offers impressive results for detection.

关键词： Bidirectional long short-term memory breast cancer detection feature extraction histopathology biopsy images multi-scale dilated vision transformer

来源：评论

学校读者我要写书评

暂无评论

A multi-strategy integrated improved YOLOv5 model and its application in target detection 4

A multi-strategy integrated improved YOLOv5 model and its ap...

引用

4th IEEE International Conference on Electronic technology, Communication and Information, ICETCI 2024

作者： Li, Jia Liu, Ziyan Song, Yuxin Harbin Engineering University College of Computer Science and Technology Harbin China Hunan University of Technology and Business College of Intelligent Engineering and Intelligent Manufacturing Changsha China Jiangnan University School of Artificial Intelligence and Computer Science Wuxi China

ISBN: (纸本)9798350361643

Deep learning techniques have the potential to significantly improve target detection speed and detection accuracy in autonomous driving. Most existing target detection algorithms have poor real-time performance and poor accuracy. Moreover, the algorithm is difficult to be deployed. Based on analysis of the existing problems of target detection in autonomous driving, this paper puts forward an improved YOLOv5 algorithm. First, the extract feature network of YOLOv5 is replaced with the FasterNet-T0 model to reduce model parameters. Next, in the fusion part (Neck) of the network, the attention mechanism CBAM is introduced to improve the accuracy of the target detection. Then, the Slim-Neck framework is presented to improve the computational efficiency of the model. Finally, considering that CIoU may be replaced by Inner-IoU to improve the accuracy and generalization of the model, in order to verify the effect of the improved model, this paper uses the improved YOLOv5 algorithm model to extract the specific categories from VOC2007 dataset and DOTA dataset. After experimentation. The results show that the model we made, the improved YOLOv5 algorithm model is capable of getting a 0.848 and 0.748mAP @ 0.5 of the VOC2007 dataset and DOTA dataset for the specific category extraction, which verifies its effectiveness. Compared with other algorithms, the improved YOLOv5s algorithm is more competitive. On the VOC2007 data set, mAP live/voc, 0.5 increased by 5.1% for a specific category acquisition, and mAP live/voc, 0.5:0.95 increased by 6.4% relative to the original YOLOv5s algorithm, and the number of parameters reduced by 39.2% from 7035811 to 4276490. On the DOTA dataset, mAP@0.5 increased by 0.9% for a specific category acquisition, and mAP@ 0.5:0.95 increased by 0.4%, which demonstrates that this method improves the accuracy and efficiency of vehicle detection to some extent. In this study, DOTA dataset was used as an experimental dataset to verify the performance of YOL

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

Spatial attention-based hybrid VGG-SVM and VGG-RF frameworks for improved cotton leaf disease detection

引用

Neural Computing and Applications 2025年第14期37卷 8309-8329页

作者： Pandiyaraju, V. Anusha, B. Senthil Kumar, A.M. Jaspin, K. Venkatraman, Shravan Kannan, A. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India Department of Computer Science and Engineering Marian Engineering College Trivandram Kerala Trivandrum India Department of Computer Science and Engineering St. Joseph’s Institute of Technology Tamil Nadu Chennai India Department of Information Science and Technology College of Engineering Guindy Anna University Tamil Nadu Chennai India

The agriculture industry's production and food quality have been impacted by plant leaf diseases in recent years. Hence, it is vital to have a system that can automatically identify and diagnose diseases at an initial stage for enhancing the quality of agricultural output and also for stopping the overall plant extinction. Most state-of-the-art methods do not provide appropriate accuracy of identification when the similarity among different diseases is higher and the input leaf images have complex background. In this work, a transfer learning-based automated crop disease recognition system is proposed to handle this problem. The cotton leaf disease detection framework being proposed here includes two key stages: (1) the feature extraction stage, where the convolutional neural network (CNN) model from the visual geometry group (VGG-16) is employed to obtain the deep features from cotton leaf images with complex background. (2) Cotton leaf disease detection stage: Here, the extracted optimal features are input to the machine learning classifiers, namely random forest (RF) and nonlinear support vector machine (SVM), for the initial classification of the diseases. For providing an optimal cotton crop disease detection performance, Kaggle’s four-class cotton disease dataset with complex background is chosen in this work. For the final decision making and analysis, two hybrid models named spatial attention-based hybrid VGG-RF and hybrid VGG-SVM have been proposed in this work for enhancing the decision accuracy. These hybrid models offered an average accuracy of approximately 98.29% and 99.31%, respectively, which is higher than the accuracy provided by the related work. This proved that the proposed hybrid model, namely spatial attention-based VGG-SVM and VGG-RF models, with spatial attention outperformed the state-of-the-art classifiers. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Uncovering the degradation mechanism induced by ion-diffusion kinetics in large-format lithium-ion pouch cells

引用

Journal of Energy Chemistry 2023年第8期83卷 98-105,I0005页

作者： Shi Zhou Xiaohong Zhang Cong Chen Ming Chen Fanpeng Kong Yingjie Qiao Jiajun Wang Key Laboratory of Superlight Materials and Surface Technology Ministry of EducationCollege of Materials Science and Chemical EngineeringHarbin Engineering University Harbin 150001HeilongjiangChina Chongqing Research Institute of Harbin Institute of Technology Chongqing 401135China

Battery electrochemistry in an actual cell is a complicated behavior influenced by the current density,uniformity,and ion-diffusion distance,*** anisotropism of the lithiation/delithiation degree is usually inevitable,and even worse,due to a trend of big-size cell design,typically such as 4680 and blade cells,which accelerated a battery failure during repeat lithiation and delithiation of *** by that,two big-size pouch cells with big sizes,herein,are selected to reveal the ion-diffusion dependency of the cathodes at different ***,we find that the LiCoO_(2) pouch cell exhibits ~5 A h loss after 120 charge-discharge cycles,but a 15 A h loss is verified in a LiNixMnyCO_(1-x)-yO_(2)(NCM) ***-based imaging analysis indicates that higher ion-diffusion rates in the LiCoO_(2)than that in the LiNixMnyCO_(1-x)-yO_(2)is the determined factor for the anisotropic cathode fading,which is responsible for a severe mechanical issue of particle damage,such as cracks and even pulverization,in the cathode ***,we verify the different locations at the near-tab and bottom of the electrode make it worse due to the ion-diffusion kinetics and temperature,inducing a spatially uneven electrochemistry in the big-size pouch *** findings give an in-depth insight into pouch cell failure and make a guideline for high-energy cell design and development.

关键词： Ah-level lithium-ion pouch cells Cathode materials lon-diffusion kinetics X-ray tomography

来源：评论

学校读者我要写书评

暂无评论

Reparameterized Importance Sampling for Robust Variational Bayesian Neural Networks 41

Reparameterized Importance Sampling for Robust Variational B...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Long, Yunfei Tian, Zilin Zhang, Liguo Xu, Huosheng College of Computer Science and Technology Harbin Engineering University Heilongjiang Harbin China Modeling and Emulation in E-Government National Engineering Laboratory Harbin Engineering University Heilongjiang Harbin China

Mean-field variational inference (MFVI) methods provide computationally cheap approximations to the posterior of Bayesian Neural Networks (BNNs) when compared to alternatives like MCMC. However, applying MFVI to BNNs encounters limitations due to the Monte Carlo sampling problem. This problem stems from two main issues. First, most samples do not accurately represent the most probable weights. Second, random sampling from variational distributions introduces high variance in gradient estimates, which can hinder the optimization process, leading to slow convergence or even failure. In this paper, we introduce a novel sampling method called Reparameterized Importance Sampling (RIS) to estimate the first moment in neural networks, reducing variance during feed-forward propagation. We begin by analyzing the generalized form of the optimal proposal distribution and presenting an inexpensive approximation. Next, we describe the sampling process from the proposal distribution as a transformation that combines exogenous randomness with the variational parameters. Our experimental results demonstrate the effectiveness of the proposed RIS method in three critical aspects: improved convergence, enhanced predictive performance, and successful uncertainty estimation for out-of-distribution data. Copyright 2024 by the author(s)

关键词： Importance sampling

来源：评论

学校读者我要写书评

暂无评论

Seizure Onset Zone Localization Method based on GNN Explanation

Seizure Onset Zone Localization Method based on GNN Explanat...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Feng, Shang Huang, Shaobin Lin, Zhiguo Harbin Engineering University College of Computer Science and Technology Harbin China The First Affiliated Hospital Harbin Medical University Department of Neurosurgery Harbin China

ISBN: (纸本)9798350386226

The localization of seizure onset zones from long term electrophysiological data is essential of epilepsy surgery, which demands significant effort and clinical knowledge to analysis long term electrophysiological data. In this study we proposed a Graph Neural Network (GNN)-based technique for automated localization of seizure onset zones in prolonged electrophysiological data. Initially, we established a Graph Convolutional Networks (GCN) model for epileptic stereo electroencephalography (SEEG) data classification. Then we used a GNN Explanation method to extract the magnitude of classification contribution from electrodes in the epilepsy SEEG data. The electrodes with most contribution would be considered as part of the seizure onset zone. The results revealed that the proposed method successfully identifies the primary seizure onset zones and estimates the impact of seizure foci on the other zones. This method applies graph neural networks explanation and offers novel perspectives for understanding the mechanisms of epilepsy. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimized Magnetic Gradient Tensor Array Algorithm for Enhanced Positioning Accuracy of Underwater Weak Magnetic Targets

引用

IEEE Sensors Journal 2025年第11期25卷 20297-20308页

作者： Ma, Dingyi Yu, Qiang Li, Dan Meng, Xiangchao Harbin Engineering University National Key Laoratory of Underwater Acoustic Technology Harbin150001 China Ministry of Industry and Information Technology Key Laoratory of Marine Information Acquisition and Security Harbin Engineering University Harbin150001 China Harbin Engineering University College of Underwater Acoustic Engineering Harbin150001 China Harbin Engineering University College of Intelligent Systems Science and Engineering Harbin150001 China Design Institute Hull Room Dalian Shipbuilding Industry Group Co. Ltd Dalian China

This research utilized an 8-fluxgate array, based on the magnetic gradient tensor method (MGT), to perform positioning trials within a controlled aquatic environment. The experiment featured five designated locations and targeted marginal magnetic signals of approximately 2-3 nT, which are resolvable by the sensors. The standard deviation of the positioning outcomes ranged from 0.0724 to 0.0764, while the root mean square error (RMSE) was confined within 0.0921 to 0.1468. At a detection distance of about 6 m, the discrepancies in the x and y axes were comparatively minor, whereas the z-axis exhibited a more significant deviation in positioning. By comparing with STAR, which is also based on the MGT algorithm, and incorporating the averaging method from their approach, we have optimized the original MGT algorithm. This enhancement has led to improved positioning accuracy, with the RMSE reduced to a range of 0.0219 to 0.0734, resulting in superior localization performance. © 2001-2012 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Torque estimation for robotic joint with harmonic drive transmission based on system dynamic characteristics

引用

Journal of Systems engineering and Electronics 2022年第6期33卷 1320-1331页

作者： ZHU Minghong XIAO Shu YU Fei Faculty of Electrical Engineering and Computer Science Ningbo UniversityNingbo 315211China College of Intelligent Systems Science and Engineering Harbin Engineering UniversityHarbin 150001China College of Mathematical Sciences Harbin Engineering UniversityHarbin 150001China

In the applications of joint control and robot movement,the joint torque estimation has been treated as an effective technique and widely *** are made to analyze the kinematic and compliance model of the robot joint with harmonic drive to acquire high precision torque *** analyzing the structures of the harmonic drive and experiment apparatus,a scheme of the proposed joint torque estimation method based on both the dynamic characteristics and unscented Kalman filter(UKF)is designed and *** on research and scheme,torque estimation methods in view of only harmonic drive compliance model and compliance model with the Kalman filter are simulated as guidance and reference to promote the research on the torque estimation ***,a promoted torque estimation method depending on both harmonic drive compliance model and UKF is designed,and simulation results compared with the measurements of a commercial torque sensor,have verified the effectiveness of the proposed method.

关键词： harmonic drive torque estimation compliance model unscented Kalman filter(UKF)

来源：评论

学校读者我要写书评

暂无评论

From light sensing to adaptive learning:hafnium diselenide reconfigurable memcapacitive devices in neuromorphic computing

引用

Light(science & Applications) 2025年第1期14卷 215-226页

作者： Bashayr Alqahtani Hanrui Li Abdul Momin Syed Nazek El-Atab Electrical and Computer Engineering Program Computer Electrical Mathematical Science and Engineering DivisionKing Abdullah University of Science and Technology(KAUST)ThuwalSaudi Arabia Electrical Engineering Department College of EngineeringPrincess Nourah Bint Abdulrahman University(PNU)RiyadhSaudi Arabia

Advancements in neuromorphic computing have given an impetus to the development of systems with adaptive behavior,dynamic responses,and energy efficiency *** charge-based or emerging memory technologies such as memristors have been developed to emulate synaptic plasticity,replicating the key functionality of neurons—integrating diverse presynaptic inputs to fire electrical impulses—has remained *** this study,we developed reconfigurable metal-oxide-semiconductor capacitors(MOSCaps)based on hafnium diselenide(HfSe2).The proposed devices exhibit(1)optoelectronic synaptic features and perform separate stimulus-associated learning,indicating considerable adaptive neuron emulation,(2)dual light-enabled charge-trapping and memcapacitive behavior within the same MOSCap device,whose threshold voltage and capacitance vary based on the light intensity across the visible spectrum,(3)memcapacitor volatility tuning based on the biasing conditions,enabling the transition from volatile light sensing to non-volatile optical data *** reconfigurability and multifunctionality of MOSCap were used to integrate the device into a leaky integrate-and-fire neuron model within a spiking neural network to dynamically adjust firing patterns based on light stimuli and detect exoplanets through variations in light intensity.

关键词： integrate volatile integrating

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：