检索结果-内蒙古大学图书馆

International Conference on Asian Language processing (IALP)

作者： Aihong Huang Feilong Bao Guanglai Gao Yu Shan Rui Liu National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Provincial Key Laboratory of Mongolian Information Processing Technology School of Computer Science Inner Mongolia University Hohhot China

ISBN: (纸本)9781665483124

In recent years, end-to-end speech synthesis based on attention has achieved better performance than traditional speech synthesis models, and the technology of end-to-end Mongolian speech synthesis has reached the application standard. However, due to the sparse training corpus, the research on Mongolian emotional speech synthesis is still far from perfect. In response to these problems, we established a Mongolian emotional corpus and constructed an emotionally controllable Mongolian speech synthesis system for the first time. Through combining transfer learning and emotional embedding, the Mongolian emotional speech synthesis system with 8 kinds of emotions (happy, angry, sadness, surprise, fear, disgust, boredom and neutral) has been achieved. We proposed the method that emotional labels are used as the input of the emotional embedding layer to generate emotional vectors, which are spliced with the output vectors of the bidirectional LSTM layer, so that the text representation vectors contain information about emotional category, thereby synthesize a variety of different emotional voices. Experiments show that our method can synthesize high-quality Mongolian emotional speech.

关键词： Training Transfer learning Speech enhancement Controllability Speech synthesis Standards

来源：评论

学校读者我要写书评

暂无评论

Strain-Mediated Magnetization Switching Behavior in a Bicomponent Nanomagnet

引用

Physical Review Applied 2023年第1期19卷 014003-014003页

作者： Jia-Hui Yuan Xiao-Kuo Yang Bo Wei Ya-Bo Chen Huan-Qing Cui Jia-Hao Liu Shu-Qing Dou Ming-Xu Song Li Fei Fundamentals Department Air Force Engineering University Xi’an 710051 China College of Computer National University of Defense Technology Changsha 410005 China College of Advanced Interdisciplinary Studies & Hunan Provincial Key Laboratory of Novel Nano-Optoelectronic Information Materials and Devices National University of Defense Technology Changsha 410005 China Aeronautics Engineering College Air Force Engineering University Xi’an 710051 China

The strain-mediated method is considered to be a promising solution for implementing energy-efficient magnetization rotation. However, current methods strictly require a voltage clock. Here, a multiferroic nanomagnet composed of bicomponent magnetic materials (Terfenol-D:Ni = 1:2) is developed to study strain-mediated magnetization switching behavior. With micromagnetic simulations, what is demonstrated is that the strict requirements for a precise applied voltage period can be overcome in such a bicomponent nanomagnet, where the threshold of the square-wave voltage pulse width required for complete and repeated magnetization reversal is only 0.42 ns if the amplitude of the voltage is 1 V. Besides deterministic magnetization switching, further study shows that the unique strain-mediated stochastic magnetization reversal behavior of the designed device can be used to mimic the biological neuron. With the application of the derived neural device parameters, a three-layer artificial neural network is further constructed to recognize a handwritten dataset, based on which, an accuracy of more than 98% can be achieved. Overall, these results open an intriguing way toward straintronic memory and neuromorphic systems.

关键词： Magnetization switching Magnetoelastic effect Spintronics Artificial neural networks Devices for digital logic, storage & processing Multiferroics Nanostructures Landau-Lifschitz-Gilbert equation

来源：评论

学校读者我要写书评

暂无评论

A New Finite Element Model with Manufactured Error for Additive Manufacturing

引用

computer Modeling in Engineering & Sciences 2020年第8期124卷 703-720页

作者： Zhaohui Xia Zhihao He Qifu Wang Yingjun Wang National Enterprise Information Software Engineering Research Center School of Mechanical Science and EngineeringHuazhong University of Science and TechnologyWuhan430074China National Engineering Research Center of Novel Equipment for Polymer Processing The Key Laboratory of Polymer Processing Engineering of the Ministry of Education(South China University of Technology)Guangdong Provincial Key Laboratory of Technique and Equipment for Macromolecular Advanced ManufacturingSouth China University of TechnologyGuangzhou510641China

Additive manufacturing(AM),adding materials layer by layer,can be used to produce objects of almost any shape or ***,AM techniques cannot accurately build parts with large overhangs,especially for the large features close to horizontal,hanging over the *** overhangs will make the manufactured model deviate from the design model,which will result in the performance of the manufactured model that cannot satisfy the design *** this paper,we will propose a new finite element(FE)analysis model that includes the manufacturing errors by mimicking the AM layer by layer construction *** such FE model,an overhang coefficient is introduced to each FE,which is defined by the support elements in the lower *** mimicking the AM process from the bottom layer to the top layer,all the FE properties are updated based on their overhang coefficients,which makes the computational model be able to predict the manufactured model with manufacturing *** proposed model can be used to predict the performance of the AM objects in the design stage,which will help the designers to improve their design by the simulation results.

关键词： Additive manufacturing manufacturing error finite element analysis overhangs 3D printing

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning

arXiv

引用

arXiv 2024年

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3DAD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. Copyright © 2024, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Image Definition Evaluation Function Based on Improved Maximum Local Variation and Focusing Window Selection 1

引用

6th International Conference on Data Mining and Big Data, DMBD 2021

作者： Li, Shiyun Chen, Jian Wan, Jiaze Li, Zuoyong Lin, Li School of Electronic Electrical Engineering and Physics Fujian University of Technology Xueyuan Road Fujian Fuzhou350118 China College of Computer and Control Engineering Minjiang University No. 200 Xiyuangong Road Fujian Fuzhou350121 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (数字)9789811675027

ISBN: (纸本)9789811675010

Aiming at the problem that commonly used image definition evaluation functions in the focusing process are sensitive to noise, we propose a new image definition evaluation function based on improved maximum local variation and focusing window selection. Firstly, the focusing window is selected by gradient accumulation of a 4-directional Scharr operator in order to reduce the calculation complexity and improve the accuracy of evaluation results. Secondly, an improved 3-neighbors method based on the maximum local variation is proposed to decrease the change in scores for noisy images. Finally, the standard deviation of the improved maximum local variation distribution is used as the measure of clarity. The experimental results show that compared with the method using maximum local variation, the proposed method has better unbiasedness and sensitivity. Compared with the commonly used evaluation functions, the proposed method has better noise immunity and high sensitivity. Compare with other no-reference image quality assessment algorithms, it has better monotonicity, unimodality, unbiasedness, sensitivity and real-time performance as well. The proposed method is suitable for the fine focusing stage with high real-time performance. © 2021, Springer Nature Singapore Pte Ltd.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Neural Network-Assisted Hybrid Model Based Message Passing for Parametric Holographic MIMO Near Field Channel Estimation

引用

IEEE Transactions on Wireless Communications 2025年

作者： Yuan, Zhengdao Guo, Yabo Gao, Dawei Guo, Qinghua Wang, Zhongyong Huang, Chongwen Jin, Ming Wong, Kai-Kit Henan Open University Artificial Intelligence Technology Engineering Research Center Zhengzhou450002 China University of Wollongong School of Electrical Computer and Telecommunications Engineering WollongongNSW2522 Australia Zhengzhou University School of Information Engineering Zhengzhou450002 China Xidian University Hangzhou Institute of Technology Hangzhou311200 China University of Wollongong School of Electrical Computer and Telecommunications Engineering NSW2522 Australia Zhejiang University College of Information Science and Electronic Engineering Hangzhou310027 China Zhejiang Provincial Key Laboratory of Multi-Modal Communication Networks and Intelligent Information Processing Hangzhou310027 China Ningbo University Faculty of Electrical Engineering and Computer Science Ningbo315211 China University College London Department of Electronic and Electrical Engineering Torrington Place WC1E 7JE United Kingdom Yonsei University Yonsei Frontier Lab Seoul Korea Republic of

Holographic multiple-input and multiple-output (HMIMO) is a promising technology with the potential to achieve high energy and spectral efficiencies, enhance system capacity and diversity, etc. In this work, we address the challenge of HMIMO near field (NF) channel estimation, which is complicated by the intricate model introduced by the dyadic Green's function. Despite its complexity, the channel model is governed by a limited set of parameters. This makes parametric channel estimation highly attractive, offering substantial performance enhancements and enabling the extraction of valuable sensing parameters, such as user locations, which are particularly beneficial in mobile networks. However, the relationship between these parameters and channel gains is nonlinear and compounded by integration, making the estimation a formidable task. To tackle this problem, we propose a novel neural network (NN) assisted hybrid method. With the assistance of NNs, we first develop a novel hybrid channel model with a significantly simplified expression compared to the original one, thereby enabling parametric channel estimation. Using the readily available training data derived from the original channel model, the NNs in the hybrid channel model can be effectively trained offline. Then, building upon this hybrid channel model, we formulate the parametric channel estimation problem with a probabilistic framework and design a factor graph representation for Bayesian estimation. Leveraging the factor graph representation and unitary approximate message passing (UAMP), we develop an effective message passing-based Bayesian channel estimation algorithm. Extensive simulations demonstrate the superior performance of the proposed method. © 2025 IEEE.

关键词： Green's function

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Tongue Image Recognition for Diabetes Diagnosis 3rd

Machine Learning Based Tongue Image Recognition for Diabetes...

引用

3rd International Conference on Machine Learning for Cyber Security, ML4CS 2020

作者： Lin, Xiaohui Yu, Zhaochai Li, Zuoyong Liu, Weina Fujian Provincial Key Laboratory of Information Processing and Intelligent Control College of Computer and Control Engineering Minjiang University Fuzhou350121 China Department of Computer Engineering Fujian Polytechnic of Information Technology Fuzhou350003 China

ISBN: (纸本)9783030624620

Tongue diagnosis of Traditional Chinese Medicine (TCM) is of great significance in the diagnosis of diabetes. To reduce the subjectivity of doctors in clinical diagnosis, this paper proposes a method for diabetic tongue image recognition based on machine learning. Specifically, the proposed method first transforms an image from RGB (red, green and blue) color space to HSV (hue, saturation, and value) color space, and the hue component is transformed into an image with higher difference degree. Secondly, image thresholding and morphological operation are performed on the image to obtain the initial tongue body region. Thirdly, the proposed method performs image thresholding and morphological operations on the value component to achieve image binarization, and retains the largest connected region as the final tongue body region. Fourthly, iterative image thresholding is used to further segment the tongue body region into tongue coating and tongue nature. Finally, the proposed method extracts tongue color features, and uses SVM (support vector machine) and KNN (k-Nearest Neighbor) to achieve image recognition based diabetes diagnosis. Experimental results show that SVM achieves higher diabetic image recognition accuracy than KNN. © 2020, Springer Nature Switzerland AG.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

An edge enhancement-based fusion method of infrared and visible images in low light

An edge enhancement-based fusion method of infrared and visi...

引用

Signal, information and Data processing (ICSIDP), IEEE International Conference on

作者： Xiang Gao Xiyan Wang Hanbin Bao Qian Li Guohua Lv Faculty of Comupter Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Bresee Technology Co. Ltd. Jinan China Shandong Grain Group Co. Ltd. Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

The combination of infrared and visible images can result in the generation of a single image with a high degree of detail and important targets in a variety of scenes, which is beneficial for human recognition. However, in low-light environments, low-intensity visible images tend to blur valuable information, which is often overlooked. This results in the loss of important information. While existing methods address the issue of low illumination and highlight the illumination, a considerable amount of structural information is lost when adjusting illumination, resulting in the omission of texture details. To solve aforementioned problems, we proposes a method for edge enhancement in low-illumination scenes. This approach aims to minimise the loss of edge information while simultaneously enhancing the illumination, thereby producing fusion images with enhanced texture detail. The initial step involves the design of an illumination enhancement module, which is employed to segregate the compromised illumination present from the scene information. Given the fact that image edge information has the capacity for effective structural modeling, a low-light visible image edge extraction network is designed to model structural information, which can accurately highlight important structural information and insert it in fused images. The results produced by this method have better visual perception and minimize structural loss. Extensive experiments demonstrate that the method outperforms SOTA methods in term of visual quality and quantitative metrics.

关键词： Reflectivity Measurement Visualization Target recognition Image edge detection Lighting Data mining Image reconstruction Image fusion Visual perception

来源：评论

学校读者我要写书评

暂无评论

A Cost-Efficient Approach to Storing Users'Data for Online Social Networks

引用

Journal of computer Science & technology 2019年第1期34卷 234-252页

作者： Jing-Ya Zhou Jian-Xi Fan Cheng-Kuan Lin Bao-Lei Cheng School of Computer Science and Technology Soochow UniversitySuzhou 215006China Provzncial Key Laboratory for Computer Information Processing Technology Soochow UniversitySuzhou 215006China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing University Nanjing 210023China

As users increasingly befriend others and interact online via their social media accounts,online social networks (OSNs)are expanding *** with the big data generated by users,it is imperative that data storage be distributed,scalable,and *** one of the most significant challenges about this topic is determining how to minimize the cost without deteriorating system *** many storage systems use the distributed key value store,it cannot be directly applied to OSN storage *** because users'data are highly correlated,hash storage leads to frequent inter-server communications,and the high inter-server traffic costs decrease the OSN storage system's scalability. Previous studies proposed conducting network partitioning and data replication based on social ***,data replication increases storage costs and impacts traffic ***,we consider how to minimize costs from the perspective of data storage,by combining partitioning and *** cost-efficient data storage approach supports scalable OSN storage *** proposed approach co-locates frequently interactive users together by conducting partitioning and replication simultaneously while meeting load-balancing *** experiments are undertaken on two real- world traces,and the results show that our approach achieves lower cost compared with state-of-the-art *** we conclude that our approach enables economic and scalable OSN data storage.

关键词： online social network inter-server traffic cost storage cost network partitioning data replication

来源：评论

学校读者我要写书评

暂无评论

DAM: Degradation-aware Model for Ultrasound Image Quality Assessment

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Liu, Tuo Zhang, Xuan Ma, Xiuzhu Chen, Shuang Wang, Xuejuan Zhou, Ping Chen, Yang Zhou, Guangquan Lv, Faqin Southeast University School of Biological Science and Medical Engineering Nanjing211189 China Chinese People's Liberation Army General Hospital Medical Center 3 Beijing100039 China Southeast University Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing the Laboratory of Image Science and Technology the School of Computer Science and Engineering Nanjing210096 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Application China Southeast University Jiangsu Key Laboratory of Biomaterials and Devices Nanjing211189 China Southeast University State Key Laboratory of Digital Medical Engineering Nanjing211189 China

One of the core challenges in ultrasound image quality assessment (IQA) is the entanglement of semantic content and quality-related information, such as blurring and shadows. Insufficient attention to the latter can easily lead to biased IQA results. Furthermore, fine-grained quality inconsistencies, i.e., subtle variations in ultrasound images that can impact quality interpretations, may further complicate the IQA tasks. To address these challenges, we propose a novel degradation-aware model (DAM) for the ultrasound IQA, which effectively perceives various and subtle variations of quality patterns, accurately assessing the quality of ultrasound images. The advanced degradation-derived augmentation (DDA) in DAM incorporates degradations that clinicians may focus on during IQA into the synthesis of appearance changes, promoting the disentanglement of quality-related representations from semantic contents. Subsequently, we present fine-grained degradation learning (FGDL), which encourages distinctions between image versions with diminishing quality inconsistencies, boosting the awareness of quality nuances from easy to hard for better ultrasound IQA performance. A universal boundary acquisition operator (UBAO) is also developed to suppress interferences from redundant information, achieving the standardization of ultrasound images from various devices. Extensive experimental results on an in-house ultrasound dataset demonstrate that DAM outperforms 14 baseline methods, achieving a PLCC of 0.760 and an SROCC of 0.766. © 2013 IEEE.

关键词： Damage detection

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：