检索结果-内蒙古大学图书馆

2011 IEEE International conference on intelligent Computation and Bio-Medical Instrumentation, ICBMI 2011

作者： Chen, Wanjun Ding, Mingyue Miao, Yalin Luo, Lei Department of Information Science Xi'an University of Technology Xi'an Shannxi 710048 China College of Life Science and Technology Lmage Processing and Intelligent Control Key Laboratory of Education Ministry of China Huazhong University of Science and Technology Wuhan Hubei 430074 China

ISBN: (纸本)9780769546230

The Non-Local Means (NLM) filter uses the redundancy of information in the image to remove noise, this scheme gives some of the best results among other powerful methods such as wavelet based approaches or diffusion techniques. Though simple to implement and efficient in practice, the classical NLM suffers from ringing artifacts around edges when using square patches, due to an abrupt lack of redundancy of the image. This paper presents an extended NLM based on Multi-Shape Patches Aggregation (NLM-MSPA) to overcome this problem, and uses it to remove medical ultrasound images corrupted by multiplicative speckle noise. We have incorporated a preprocessing step to make the speckle noise much closer to the real additive white Gaussian noise, hence more amenable to a denoising algorithm such as NLM-MSPA. Results on real images and artificially speckled images show that the proposed scheme outperforms several classical methods chosen for comparison in its ability to reduce speckle and preserve edge details. © 2011 IEEE.

关键词： Speckle

来源：评论

学校读者我要写书评

暂无评论

ICT: A system combination for Chinese semantic dependency parsing 1

ICT: A system combination for Chinese semantic dependency pa...

引用

1st Joint Conference on Lexical and Computational Semantics, *SEM 2012

作者： Xiong, Hao Liu, Qun Key Lab. of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences P.O. Box 2704 Beijing100190 China

ISBN: (纸本)9781937284220

The goal of semantic dependency parsing is to build dependency structure and label semantic relation between a head and its modifier. To attain this goal, we concentrate on obtaining better dependency structure to predict better semantic relations, and propose a method to combine the results of three state-of-The-Art dependency parsers. Unfortunately, we made a mistake when we generate the final output that results in a lower score of 56.31%in term of Labeled Attachment Score (LAS), reported by organizers. After giving golden testing set, we fix the bug and rerun the evaluation script, this time we obtain the score of 62.8% which is consistentwith the results on developing set. We will report detailed experimental results with correct program as a comparison standard for further research. © 2012 Association for Computational Linguistics.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Image matching based on analysis of reliability in Log-Polar field

引用

2012 2nd International Conference on Materials Science and information technology, MSIT 2012

作者： Xu, Yiping Tan, Jing Li, Hongping Tian, Yan Department of Electronics and Information Engineering Huazhong University of Science and Technology Wuhan 430074 China National Key Laboratory of Science and Technology on Multi-spectral Information Processing Wuhan 430074 China

ISBN: (纸本)9783037854389

Due to the invariance to scale and rotation, image matching method based on Log-Polar transformation has been extensively applied in target detection and location. This paper analyses the effect on image matching accuracy from variation of scale and rotation, and proposes a modified image matching method based on analysis of data reliability for matching, this method can eliminate the interference from invalid data and improve the image matching performance. Experiments show that this method has better performance in accuracy. © (2012) Trans Tech Publications, Switzerland.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

Breast Tissue Classification Method Based on Machine Learning

引用

Recent Patents on Engineering 2024年第1期18卷 18-27页

作者： Li, Yong Tang, Zhiling Zhang, Liangxi College of Information Engineering Chengdu Vocational & Technical College of Industry Sichuan Chengdu China Guangxi Key Laboratory of Wireless Broadband Communication and Signal Processing Guilin University of Electronic Technology Guangxi Guilin China

Early detection and treatment of breast cancer are very necessary, and effective classification of breast tissue is helpful for the diagnosis of breast cancer;so, a classification method named FT_GA_GBDT is proposed. First, the correlations between the features and classification labels of breast tissue samples were determined, and features with higher correlation were analyzed statistically and combined by weight. Thus, feature transformation (FT) is realized. The datasets were then enhanced by calculating the mean and root mean square of the feature attributes of each adjacent odd-and even-row sample with both belonging to the same class. Finally, the genetic algorithm (GA) was used to search the optimal parameters of the gradient boosting decision tree (GBDT) model, and the optimal parameters were substituted into the GBDT to classify the breast tissue. In addition, the K-nearest-neighbor (KNN), support-vector-machine (SVM) and GBDT methods were also used to test the breast tissue classification. Results of 6-fold cross validation on three breast tissue datasets showed that the average Precision, Recall, and F1 score obtained by the FT_GA_GBDT method were better than those obtained by the KNN, SVM and GBDT methods. The results further show that the FT algorithm and searching for the optimal hyper-parameters by the GA were helpful in improving the performance of the breast tissue classification model, which is more obvious when the correlations between features and classification labels are generally not high. © 2024 Bentham Science Publishers.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Laser polishing of a high-entropy alloy manufactured by selective laser melting

引用

Frontiers of Mechanical Engineering 2024年第5期19卷 73-86页

作者： Xiaojun TAN Haibing XIAO Zihong WANG Wei ZHANG Zhijuan SUN Xuyun PENG Zhongmin LIU Liang GUO Qingmao ZHANG Intelligent Manufacturing and Equipment School Shenzhen Institute of Information TechnologyShenzhen 518172China Sino-German Intelligent Manufacturing School Shenzhen City PolytechnicShenzhen 518116China Guangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices School of Information and Optoelectronic Science and EngineeringSouth China Normal UniversityGuangzhou 510006China Guangdong Provincial Key Laboratory of Industrial Ultrashort Pulse Laser Technology Shenzhen 518055China College of Materials Science and Engineering Chongqing UniversityChongqing 400045China

The selective laser melting(SLM)technique applied to high-entropy alloys(HEAs)has attracted considerable attention in recent ***,its practical application has been restricted by poor surface *** this study,the capability of laser polishing on the rough surface of a Co-free HEA fabricated using SLM was *** show that the initial SLM-manufactured(as-SLMed)surface of the Co-free HEA,with a roughness exceeding 3.0μm,could be refined to less than 0.5μm by laser ***,the microstructure,microhardness,and wear resistance of the laser-polished(LP-ed)zone were *** indicate that compared with the microhardness and wear resistance of the as-SLMed layer,those of the LP-ed layer decreased by 4%and 11%,respectively,because of the increase in grain size and reduction of the BCC *** study shows that laser polishing has an excellent application prospect in surface improvement of HEAs manufactured by SLM.

关键词： laser polishing selective laser melting high-entropy alloy surface roughness mechanical performance

来源：评论

学校读者我要写书评

暂无评论

Slant split criterion random forests classification algorithm based on soft margin hyperplane 9

Slant split criterion random forests classification algorith...

引用

9th IEEE Joint International information technology and Artificial Intelligence Conference, ITAIC 2020

作者： Kan, Xueda Li, Tiansong Guilin University of Technology College of Information Science and Engineering Guilin China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin China

In order to further to improve the classification accuracy of the random forest algorithm, an Slant Split Criterion Random Forests based on Soft Margin Hyperplane (SSCRF) algorithm is proposed. In the decision tree node splitting process, consider using multiple attribute soft margin hyperplane of the decision tree to replace a single attribute splitting criterion, so that the splitting criterion becomes an inclined hyperplane in the data space, which effectively improves the accuracy of decision tree classification;In order to make the algorithm suitable for multi-classification problems, the 'one-to-many' strategy is adopted in the process of node splitting;in the process of transforming into leaf nodes, various adaptive weights are assigned to improve the algorithm's classification ability. The experimental results show that the SSCRF algorithm has higher classification accuracy than the random forest algorithm. © 2020 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Prosody Prediction with Discriminative Representation Method 3

Prosody Prediction with Discriminative Representation Method

引用

3rd International Conference on Pattern Recognition and Machine Learning, PRML 2022

作者： Zhang, Jipeng Yilahun, Hankiz Feng, Xiaoqin Chen, Yunlin Yang, Xipeng Hamdulla, Askar School of Information Science and Engineering Xinjiang University of China China Xinjiang Key Laboratory of Signal Detection and Processing China Xinjiang Key Laboratory of Multilingual Information Technology China Mobvoi Ai Lab Suzhou China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

Rhythm affects the naturalness and intelligibility of Text-To-Speech (TTS). However, rhythm prediction remains a great challenge, usually in two aspects: 1) the united annotation is a relatively difficult task, which depends on expert's experience. 2) traditional methods based on conditional random field (CRF), which heavily rely on feature engineering, such as word segmentation, part of speech(pos) etc. For above problems, we propose a method to reduce the dependency for united annotation data and conduct the joint experiment which use one unified model on independent data. Meanwhile, we also propose an algorithm of Layer Look Up Table (LLUT): use an embedding layer to learn a discriminative representation for different level of prosody data without any feature engineering. By using this method, the classifier can share the parameters and predict for different prosody level separately, which reduces the number of trainable model parameters. In order to better represent the input text, we use the pre-training model, like BERT, to provide the semantic information. Our experiment shows that the method of LLUT, is better able to acquire the discriminative meaning of different prosody levels. And also, our algorithm is proved to be general for sequence annotation tasks thus we can do extra task, like polyphone-prosody prediction. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Adaptive tag selection for image annotation 15

Adaptive tag selection for image annotation

引用

15th Pacific-Rim Conference on Multimedia, PCM 2014

作者： He, Xixi Li, Xirong Yang, Gang Xu, Jieping Jin, Qin Key Lab of DEKE Renmin University of China 100872 China Multimedia Computing Lab Renmin University of China 100872 China Shanghai Key Laboratory of Intelligent Information Processing 200443 China

ISBN: (纸本)9783319131672

Not all tags are relevant to an image, and the number of relevant tags is image-dependent. Although many methods have been proposed for image auto-annotation, the question of how to determine the number of tags to be selected per image remains open. The main challenge is that for a large tag vocabulary, there is often a lack of ground truth data for acquiring optimal cutoff thresholds per tag. In contrast to previous works that pre-specify the number of tags to be selected, we propose in this paper adaptive tag selection. The key insight is to divide the vocabulary into two disjoint subsets, namely a seen set consisting of tags having ground truth available for optimizing their thresholds and a novel set consisting of tags without any ground truth. Such a division allows us to estimate how many tags shall be selected from the novel set according to the tags that have been selected from the seen set. The effectiveness of the proposed method is justified by our participation in the ImageCLEF 2014 image annotation task. On a set of 2,065 test images with ground truth available for 207 tags, the benchmark evaluation shows that compared to the popular top-k strategy which obtains an F-score of 0.122, adaptive tag selection achieves a higher Fscore of 0.223. Moreover, by treating the underlying image annotation system as a black box, the new method can be used as an easy plug-in to boost the performance of existing systems. © Springer International Publishing Switzerland 2014.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

A data clustering strategy for enhancing mutual privacy in healthcare system of IoT

A data clustering strategy for enhancing mutual privacy in h...

引用

2019 IEEE International Conferences on Ubiquitous Computing and Communications and Data Science and Computational Intelligence and Smart Computing, Networking and Services, IUCC/DSCI/SmartCNS 2019

作者： Guo, Xuancheng Lin, Hui Xu, Chuanfeng Lin, Wenzhong School of Mathematics and Computer Science Fujian Normal University Fuzhou China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou China

ISBN: (纸本)9781728152097

Recent advances in the healthcare system of Internet of Things (IoT) has led to a generation of a large amount of physic sensor data. Data analyst collects and analyzes these sensor data through wireless sensor network, so as to provide some treatment advices to physicians and patients. As a common data mining method, the k-means clustering algorithm is being applied to process large-scale sensor data. However, it also poses a threat of privacy leakage in the specific application process. To enhance the privacy in healthcare system of IoT, mutual privacypreserving k-means strategy (M-PPKS) based on homomorphic encryption is proposed in this paper, which neither discloses an individual's private information nor leaks the cluster center's characteristic data. An extension performance evaluation shows that, in the case of ensuring accurate clustering results, even if the analyst and individuals collude, the M-PPKS can prevent the disclosure of private information. © 2019 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Trajectory Planning of Launch Vehicle Orbital Injection Segment Under Engine Failure Based on DDPG Algorithm

Trajectory Planning of Launch Vehicle Orbital Injection Seg...

引用

Chinese intelligent Automation Conference, CIAC 2023

作者： Xiang, Zhuo Wang, Bo Liu, Lei Fan, Huijin National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9789819961863

Traditional methods for rocket orbiting have serious deficiencies in orbital accuracy and computational efficiency, and cannot handle engine failure which leads to thrust drop. Accordingly, this manuscript designs a trajectory planning algorithm based on DDPG for the launch vehicle into orbit, transforms the rocket orbiting into an MDP problem, and constructs reward functions that satisfy the flight process and terminal constraints. The simulation results show that this method has significantly improved the accuracy of orbiting and calculation efficiency, and has the ability to adjust to suitable orbit adaptively under failure. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Rockets

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：