检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Shaokai Ji, Yixuan Song, Peng Sun, Haoqin Zheng, Wenming School of Computer and Control Engineering Yantai University Yantai264005 China Business School Xuzhou University of Technology Xuzhou221018 China College of Computer Science Nankai University Tianjin300350 China Key Laboratory of Child Development and Learning Science of Ministry of Education Southeast University Nanjing210096 China

In this paper, we propose a novel deep inductive transfer learning framework, named feature distribution adaptation network, to tackle the challenging multi-modal speech emotion recognition problem. Our method aims to use deep transfer learning strategies to align visual and audio feature distributions to obtain consistent representation of emotion, thereby improving the performance of speech emotion recognition. In our model, the pre-trained ResNet-34 is utilized for feature extraction for facial expression images and acoustic Mel spectrograms, respectively. Then, the cross-attention mechanism is introduced to model the intrinsic similarity relationships of multi-modal features. Finally, the multi-modal feature distribution adaptation is performed efficiently with feed-forward network, which is extended using the local maximum mean discrepancy loss. Experiments are carried out on two benchmark datasets, and the results demonstrate that our model can achieve excellent performance compared with existing ones. Our code is available at https://***/shaokai1209/FDAN. Copyright © 2024, The Authors. All rights reserved.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Multi-Discriminator Weighted Adversarial Network for Cross-Domain Unknown Wind Turbine Fault Diagnosis

A Multi-Discriminator Weighted Adversarial Network for Cross...

引用

IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia)

作者： Yinghua Han Huaiyuan Qi Fangyuan Si Kangping Li Qiang Zhao School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao China School of Control Engineering Notheastern University at Qinhuangdao Qinhuangdao China Department of Electrical Engineering Tsinghua University Beijing China The College of Smart Energy Shanghai Jiao Tong University Shanghai China

The practical cross-domain fault diagnosis methods in wind turbines based on transfer learning have been widely studied, where most of the existing transfer learning methods assume that test data and training data have the same label space. However, this assumption is not realistic in practical wind turbines because the data in the target domain wind turbine often presents new fault categories during the testing phase, which can affect the accuracy of the model. A multi-discriminator weighted adversarial network (MWAN) is proposed here to handle the above problem. The proposed method can automatically identify outliers in the source domain and unknown fault classes in the target domain by introducing a hybrid weighting balanced strategy and using an auxiliary discriminator to weigh source and target domain samples. Adversarial training is introduced to achieve shared class-level alignment in the two domains. Experiments verify that the proposed method outperforms state-of-the-art methods for wind turbine fault diagnosis applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved Machine Learning Technique with Effective Heart Disease Prediction System

引用

computers, Materials & Continua 2021年第12期69卷 4169-4181页

作者： Mohammad Tabrez Quasim Saad Alhuwaimel Asadullah Shaikh Yousef Asiri Khairan Rajab Rihem Farkh Khaled Al Jaloud College of Computing and Information Technology University of BishaBisha67714Saudi Arabia King Abdulaziz City for Science and Technology P.O.Box 6086Riyadh11442Saudi Arabia College of Computer Science and Information Systems Najran UniversityNajran61441Saudi Arabia College of Engineering Muzahimiyah BranchKing Saud UniversityRiyadh11451Saudi Arabia Department of Electrical Engineering Laboratory for AnalysisConception and Control of SystemsLR-11-ES20National Engineering School of TunisTunis El Manar University1002Tunisia

Heart disease is the leading cause of death *** heart disease is challenging because it requires substantial experience and *** research studies have found that the diagnostic accuracy of heart disease is *** coronary heart disorder determines the state that influences the heart valves,causing heart *** indications of coronary heart disorder are strep throat with a red persistent skin rash,and a sore throat covered by tonsils or strep *** work focuses on a hybrid machine learning algorithm that helps predict heart attacks and arterial *** first,we achieved the component perception measured by using a hybrid cuckoo search particle swarm optimization(CSPSO)*** this perception measure,characterization and accuracy were improved,while the execution time of the proposed model was *** CSPSO-deep recurrent neural network algorithm resolved issues that state-of-the-art methods *** proposed method offers an illustrative framework that helps predict heart attacks with high *** proposed technique demonstrates the model accuracy,which reached 0.97 with the applied dataset.

关键词： Machine learning deep recurrent neural network effective heart disease prediction framework

来源：评论

学校读者我要写书评

暂无评论

InterTracker: Discovering and Tracking General Objects Interacting with Hands in the Wild

arXiv

引用

arXiv 2023年

作者： Shao, Yanyan Ye, Qi Luo, Wenhan Zhang, Kaihao Chen, Jiming College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China College of Control Science and Engineering Zhejiang University Hangzhou310027 China School of Cyber Science and Technology Sun Yat-sen University Shenzhen518107 China College of Engineering Computing & Cybernetics Australian National University CanberraACT2601 Australia

Understanding human interaction with objects is an important research topic for embodied Artificial Intelligence and identifying the objects that humans are interacting with is a primary problem for interaction understanding. Existing methods rely on frame-based detectors to locate interacting objects. However, this approach is subjected to heavy occlusions, background clutter, and distracting objects. To address the limitations, in this paper, we propose to leverage spatio-temporal information of hand-object interaction to track interactive objects under these challenging cases. Without prior knowledge of the general objects to be tracked like object tracking problems, we first utilize the spatial relation between hands and objects to adaptively discover the interacting objects from the scene. Second, the consistency and continuity of the appearance of objects between successive frames are exploited to track the objects. With this tracking formulation, our method also benefits from training on large-scale general object-tracking datasets. We further curate a video-level hand-object interaction dataset for testing and evaluation from 100DOH. The quantitative results demonstrate that our proposed method outperforms the state-of-the-art methods. Specifically, in scenes with continuous interaction with different objects, we achieve an impressive improvement of about 10% as evaluated using the Average Precision (AP) metric. Our qualitative findings also illustrate that our method can produce more continuous trajectories for interacting objects. Copyright © 2023, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Feature learning of image for unsupervised texture segmentation 5

Feature learning of image for unsupervised texture segmentat...

引用

5th International Conference on Communication and Electronics Systems, ICCES 2020

作者： Vikhe, P.S. Rajput, M.P. Kadu, C.B. Mandhare, V.V. Department of Instrumentation & Control Engineering Department of Computer Engineering Pravara Rural Engineering College Loni MS413637 India

ISBN: (纸本)9781728153711

Segmentation in specific image class, texture feature extraction plays a vital role. But is time consuming and difficult, to develop novel technique to select features manually. Adapting features automatically for particular class of images, will be helpful and effective. Thus, proposed work contributes in texture segmentation, in absence of large learning datasets for learning features. Cost function is used to develop, learning process for matching segmentation model (Mumford Shah model). The feature learning provides essential piecewise image with constraint feature set of compact jump. It is based on convolution feature learning and segmentation performance respectively. It has been reflected, it is possible to learn features of image patch. The approach is effective and produces better texture segmentation for natural images. © 2020 IEEE.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Image Enhancement using linear filters for Rectal Cancer Diagnosis using MR Images

Image Enhancement using linear filters for Rectal Cancer Dia...

引用

International Conference on Biosignals, Images and Instrumentation (ICBSII)

作者： Sonal Patreena D’Almeida Surekha Kamath K.V Rajagopal K.N Manjunath Department of Instrumentation and Control Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India Department of Radiodiagnosis and Imaging Kasturba Medical College Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

ISBN: (数字)9798331513863

ISBN: (纸本)9798331513870

computer-aided diagnosis (CAD) is an efficient tool in analyzing medical images for the diagnosis and staging of rectal cancer. Magnetic Resonance Imaging (MRI) plays a crucial role in the detection and evaluation of rectal cancer due to its high-resolution imaging capabilities. This paper discusses the pre-processing methods for MR images of rectal cancer, which facilitate further image analysis for diagnosing the stage of cancer. Pre-processing is a critical step for MR images, aiding in subsequent steps of segmentation and classification. This paper investigates the impact of widely used pre-processing techniques. Initially, pelvic DICOM images are provided as input. By combining three filters—mean, median, and adaptive median filters—the noise is removed from the image. Image enhancement techniques such as Adaptive Histogram Equalization (AHE) and Contrast Limited Adaptive Histogram Equalization (CLAHE) are used to enhance the quality of the image. Statistical parameters like Peak Signal-to-Noise Ratio (PSNR), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Structural Similarity Index Measure (SSIM) are used to evaluate performance. Results indicate that CLAHE provides superior outcomes.

关键词： Image quality Maximum likelihood detection PSNR Magnetic resonance imaging Noise Nonlinear filters computer aided diagnosis Medical diagnostic imaging Image enhancement Cancer

来源：评论

学校读者我要写书评

暂无评论

Consistent and Asymptotically Statistically-Efficient Solution to Camera Motion Estimation

arXiv

引用

arXiv 2024年

作者： Zeng, Guangyang Zeng, Qingcheng Li, Xinghan Mu, Biqiang Chen, Jiming Shi, Ling Wu, Junfeng The School of Data Science Chinese University of Hong Kong Shenzhen Shenzhen518172 China The College of Control Science and Engineering The State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Key Laboratory of Systems and Control Institute of Systems Science Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Given 2D point correspondences between an image pair, inferring the camera motion is a fundamental issue in the computer vision community. The existing works generally set out from the epipolar constraint and estimate the essential matrix, which is not optimal in the maximum likelihood (ML) sense. In this paper, we dive into the original measurement model with respect to the rotation matrix and normalized translation vector and formulate the ML problem. We then propose a two-step algorithm to solve it: In the first step, we estimate the variance of measurement noises and devise a consistent estimator based on bias elimination;In the second step, we execute a one-step Gauss-Newton iteration on manifold to refine the consistent estimate. We prove that the proposed estimate owns the same asymptotic statistical properties as the ML estimate: The first is consistency, i.e., the estimate converges to the ground truth as the point number increases;The second is asymptotic efficiency, i.e., the mean squared error of the estimate converges to the theoretical lower bound - Cramer-Rao bound. In addition, we show that our algorithm has linear time complexity. These appealing characteristics endow our estimator with a great advantage in the case of dense point correspondences. Experiments on both synthetic data and real images demonstrate that when the point number reaches the order of hundreds, our estimator outperforms the state-of-the-art ones in terms of estimation accuracy and CPU time. Copyright © 2024, The Authors. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

A Bayesian k-vector estimation method for electromagnetic waves in magnetized cold plasma

引用

URSI Radio Science Bulletin 2023年第378期2021卷 77-82页

作者： Yuji Tanaka Mamoru Ota Shoya Matsuda Yoshiya Kasahara Division of Electrical Engineering Graduate School of Engineering Kyoto University Kyotodaigaku-Katsura Nishikyo-ku Kyoto Kyoto Japan Department of Electrical and Control Systems Engineering National Institute of Technology Toyama College 13 Hongo-machi Toyama Toyama Japan Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology Kanazawa University Kakuma Kanazawa Ishikawa Japan

Using the plasma wave characteristics and remote sensing technology, the k-vector direction of plasma waves can provide important information for understanding the global features of space plasma. In this study, we proposed a Bayesian k-vector estimation method in magnetized cold plasma based on the wave distribution function method. The proposed method can be applied to various types of sensors with easy visualization and calculation of the estimation accuracy. We verified the effectiveness of the proposed method through simulations.

关键词： Estimation Plasmas Electromagnetics Mathematical models Magnetic sensors Bayes methods Plasma waves

来源：评论

学校读者我要写书评

暂无评论

NAS-WFPN: Neural Architecture Search Weighted Feature Pyramid Networks for Object Detection 13th

NAS-WFPN: Neural Architecture Search Weighted Feature Pyrami...

引用

13th International Conference on Security, Privacy, and Anonymity in Computation, Communication, and Storage, SpaCCS 2020

作者： Li, Xiaohan Xie, Ziyan Lai, Taotao Zhao, Fusheng Xu, Haiyin Chen, Riqing School of Computer Science Fujian Agriculture and Forestry University Fuzhou350002 China School of Computer and Control Engineering Minjiang University Fuzhou350108 China School of Mathematics and Computer Science Quanzhou Normal University Quanzhou362000 China Department of Information Engineering Hebei Vocational and Technical College of Building Materials Qinhuangdao066000 China

ISBN: (纸本)9783030688837

As we known, most of convolution neural architectures are manually designed. However, they cannot obtain the optimal structures. To address this problem, based on Weighted Feature Pyramid Networks (WFPN), in this paper, we use gaussian kernel to calculate the weight to design a novel method called the Neural Architecture Search Weighted Feature Pyramid Networks (i.e., NAS-WFPN). NAS-WFPN mainly consists of three parts (i.e., top-down pathway, bottom-up pathway and lateral connections) to fuse features across different scales. Experimental results show that NAS-WFPN achieves higher accuracy compared with the existing object detection methods. Specifically, NAS-WFPN increases accuracy by 2.3 AP compared to SSDLite with MobileNetV2 model and gets 49.1 AP, which exceeds NAS-FPN and Mask R-CNN. © 2021, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Payment System for Electric Vehicles Charging and Peer-to-Peer Energy Trading 7

A Payment System for Electric Vehicles Charging and Peer-to-...

引用

7th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2023

作者： Kaushal, Rajanish Kumar Jain, Shubhi Shankar Rao, R Gowri Thirumalaimuthu, Babu Rawat, Ruchira Natrayan, L. Chandigarh University Department of Electrical Engineering Punjab Mohali Gharuan India Swami Keshvanand Institute of Technology Management and Gramothan Department of Electronics and Communication Rajasthan Jaipur302018 India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Physics Tamil Nadu Chennai600062 India St. Joseph's College of Engineering Department of Instrumentation and Control Engineering Tamil Nandu Chennai600119 India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Saveetha School of Engineering Simats Department of Mechanical Engineering Tamil Nadu Chennai602105 India

ISBN: (纸本)9798350341485

The popularity of vehicles based on electricity is increasing as they are considered a sustainable mode of transportation. The charging infrastructure for electric vehicles are suffering various issues. There are limited availability of public charging stations, the high costs associated with installing private charging stations, and the high variability of electricity prices. The peer-to-peer (P2P) energy stability will be seen as a potential solution to facilitate electric vehicle (EV) charging in a manner that is both cost-effective and environmentally sustainable. The paper presents a novel system energy trading and charging payment for electric vehicles (EVs). The desired system enables EV owners to exchange surplus electricity with other EV owners in their location. The system being proposed utilizes blockchain technology to guarantee secure and transparent transactions. Additionally, it incorporates a smart contract to automate the trading and charging process. The system utilizes a dynamic pricing mechanism that adjusts in real-time to reflect the current electricity prices. This feature is designed to encourage electric vehicle owners to engage in energy stabilization during maximum usage hours. The Optimistic results shows that the described system has the efficacy on minimising the cost of vehicle charging and to decrease peak demand on the grid. Additionally, the system encourages the utilization of renewable energy sources. © 2023 IEEE.

关键词： Electric vehicles

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：