303 Hits in 2.1 sec

Nonlinear Regression Color Correction Method for RGBN Cameras

Zhenghao Han, Weiqi Jin, Li Li, Xia Wang, Xiaofeng Bai, Hailin Wang
2020 IEEE Access  
XIA WANG received the Ph.D. degree in automation from the China University of Mining and Technology, in 1999.  ...  HAILIN WANG received the B.S. degree in optoelectronics information science and engineering from the Beijing Institute of Technology, Beijing, China, in 2018.  ... 
doi:10.1109/access.2020.2971423 fatcat:3nxxaqy4bfc23jtsaow77zh4xi

Cracking the cocktail party problem by multi-beam deep attractor network [article]

Zhuo Chen, Jinyu Li, Xiong Xiao, Takuya Yoshioka, Huaming Wang, Zhenghao Wang, Yifan Gong
2018 arXiv   pre-print
While recent progresses in neural network approaches to single-channel speech separation, or more generally the cocktail party problem, achieved significant improvement, their performance for complex mixtures is still not satisfactory. In this work, we propose a novel multi-channel framework for multi-talker separation. In the proposed model, an input multi-channel mixture signal is firstly converted to a set of beamformed signals using fixed beam patterns. For this beamforming, we propose to
more » ... e differential beamformers as they are more suitable for speech separation. Then each beamformed signal is fed into a single-channel anchored deep attractor network to generate separated signals. And the final separation is acquired by post selecting the separating output for each beams. To evaluate the proposed system, we create a challenging dataset comprising mixtures of 2, 3 or 4 speakers. Our results show that the proposed system largely improves the state of the art in speech separation, achieving 11.5 dB, 11.76 dB and 11.02 dB average signal-to-distortion ratio improvement for 4, 3 and 2 overlapped speaker mixtures, which is comparable to the performance of a minimum variance distortionless response beamformer that uses oracle location, source, and noise information. We also run speech recognition with a clean trained acoustic model on the separated speech, achieving relative word error rate (WER) reduction of 45.76\%, 59.40\% and 62.80\% on fully overlapped speech of 4, 3 and 2 speakers, respectively. With a far talk acoustic model, the WER is further reduced.
arXiv:1803.10924v1 fatcat:tfijy4ujn5cjxjcuga73mhcvci

Approximate Random Dropout [article]

Zhuoran Song, Ru Wang, Dongyu Ru, Hongru Huang, Zhenghao Peng, Jing Ke, Xiaoyao Liang, Li Jiang
2018 arXiv   pre-print
The training phases of Deep neural network (DNN) consumes enormous processing time and energy. Compression techniques utilizing the sparsity of DNNs can effectively accelerate the inference phase of DNNs. However, it can be hardly used in the training phase because the training phase involves dense matrix-multiplication using General Purpose Computation on Graphics Processors (GPGPU), which endorse regular and structural data layout. In this paper, we propose the Approximate Random Dropout that
more » ... replaces the conventional random dropout of neurons and synapses with a regular and predefined patterns to eliminate the unnecessary computation and data access. To compensate the potential performance loss we develop a SGD-based Search Algorithm to produce the distribution of dropout patterns. We prove our approach is statistically equivalent to the previous dropout method. Experiments results on MLP and LSTM using well-known benchmarks show that the proposed Approximate Random Dropout can reduce the training time by 20%-77% (19%-60%) when dropout rate is 0.3-0.7 on MLP (LSTM) with marginal accuracy drop.
arXiv:1805.08939v2 fatcat:dyhsbg2xkvdvvmcwkz2ynrch54

On Stage Ordering in Staged Computation [chapter]

Zhenghao Wang, Richard R. Muntz
2003 Lecture Notes in Computer Science  
A staged computation is a computation organized in a cascade of stages: each stage produces code for its successive stage; the final stage produces the desired output. An off-line procedure called binding time analysis (BTA) is often used to pre-convert unstaged code into staged code, i.e., code annotated with stage labels, which can guide online staged computation. For dynamic re-optimization purposes, it is advantageous for the order of stages in the cascade to change during runtime; however,
more » ... the staged code may not support all permutations of stage sequences. Thus, it is both a and practical question to efficiently decide whether a specific stage sequence is valid for a staged code. Our approach is to encode the set of valid stage sequences for a staged code off-line in a stage ordering language (SOL) to facilitate fast online decision. Contrary to the intuition that we only need a single generic SOL (such as the language of posets of stage labels) to sufficiently and efficiently encode the set of valid stage sequences for any staged code in any staged language, we may need different SOLs for different staged languages. We analyze several staged languages and then present a metatheory on validating a SOL for a given staged language. Our result reveals the relationship between SOLs and semantic properties of staged languages, and can influence the design of staged languages and BTA.
doi:10.1007/978-3-540-39815-8_5 fatcat:aesqwwszkjghrppaftepihjwkm

How to improve the interpretability of kernel learning [article]

Jinwei Zhao, Qizhou Wang, Yufei Wang, Yu Liu, Zhenghao Shi, Xinhong Hei
2019 arXiv   pre-print
In recent years, machine learning researchers have focused on methods to construct flexible and interpretable prediction models. However, an interpretability evaluation, a relationship between generalization performance and an interpretability of the model and a method for improving the interpretability have to be considered. In this paper, a quantitative index of the interpretability is proposed and its rationality is proved, and equilibrium problem between the interpretability and the
more » ... zation performance is analyzed. Probability upper bound of the sum of the two performances is analyzed. For traditional supervised kernel machine learning problem, a universal learning framework is put forward to solve the equilibrium problem between the two performances. The condition for global optimal solution based on the framework is deduced. The learning framework is applied to the least-squares support vector machine and is evaluated by some experiments.
arXiv:1811.10469v2 fatcat:twlqizl4mfgkrdm75stwxbmqda

Tree Branching Reconstruction from Unilateral Point Clouds [chapter]

Yinghui Wang, Xin Chang, Xiaojuan Ning, Jiulong Zhang, Zhenghao Shi, Minghua Zhao, Qiongfang Wang
2012 Lecture Notes in Computer Science  
Trees are ubiquitous in natural environment and realistic models of tree are also indispensable in computer graphics and virtual reality domains. However, their complexity in geometry and topology make it a great challenge for photo-realistic tree reconstruction. Since tree trunk is the preliminary structure of trees, its modeling is a critical step which plays an important role in tree modeling. Many existing methods focus on the overall resemblance of tree branches but omit the local geometry
more » ... details. In this paper, we perform unilateral scanning of real-world trees and propose an approach that could reconstruct trees from incomplete point clouds. The core of our method contains four parts: local optimal segmentation of tree branch, skeletal point and lines extraction from unilateral branch, the cross-section construction of tree branch, and final tree branch surface generation. Experimental results demonstrate the effectiveness and robustness of our method which could keep realistic shape of trees.
doi:10.1007/978-3-642-31439-1_23 fatcat:qyvik6mxizdgre7zzhw5nl45jm

Enriching Query Semantics for Code Search with Reinforcement Learning [article]

Chaozheng Wang, Zhenghao Nong, Cuiyun Gao, Zongjie Li, Jichuan Zeng, Zhenchang Xing, Yang Liu
2021 arXiv   pre-print
Code search is a common practice for developers during software implementation. The challenges of accurate code search mainly lie in the knowledge gap between source code and natural language (i.e., queries). Due to the limited code-query pairs and large code-description pairs available, the prior studies based on deep learning techniques focus on learning the semantic matching relation between source code and corresponding description texts for the task, and hypothesize that the semantic gap
more » ... tween descriptions and user queries is marginal. In this work, we found that the code search models trained on code-description pairs may not perform well on user queries, which indicates the semantic distance between queries and code descriptions. To mitigate the semantic distance for more effective code search, we propose QueCos, a Query-enriched Code search model. QueCos learns to generate semantic enriched queries to capture the key semantics of given queries with reinforcement learning (RL). With RL, the code search performance is considered as a reward for producing accurate semantic enriched queries. The enriched queries are finally employed for code search. Experiments on the benchmark datasets show that QueCos can significantly outperform the state-of-the-art code search models.
arXiv:2105.09630v1 fatcat:jvbhpyr4ajax5k73p4jpjh2l5y

Visual Analytics of Movement Pattern Based on Time-Spatial Data: A Neural Net Approach [article]

Zhenghao Chen, Jianlong Zhou, Xiuying Wang
2017 arXiv   pre-print
Time-Spatial data plays a crucial role for different fields such as traffic management. These data can be collected via devices such as surveillance sensors or tracking systems. However, how to efficiently an- alyze and visualize these data to capture essential embedded pattern information is becoming a big challenge today. Classic visualization ap- proaches focus on revealing 2D and 3D spatial information and modeling statistical test. Those methods would easily fail when data become mas-
more » ... Recent attempts concern on how to simply cluster data and perform prediction with time-oriented information. However, those approaches could still be further enhanced as they also have limitations for han- dling massive clusters and labels. In this paper, we propose a visualiza- tion methodology for mobility data using artificial neural net techniques. This method aggregates three main parts that are Back-end Data Model, Neural Net Algorithm including clustering method Self-Organizing Map (SOM) and prediction approach Recurrent Neural Net (RNN) for ex- tracting the features and lastly a solid front-end that displays the results to users with an interactive system. SOM is able to cluster the visiting patterns and detect the abnormal pattern. RNN can perform the predic- tion for time series analysis using its dynamic architecture. Furthermore, an interactive system will enable user to interpret the result with graph- ics, animation and 3D model for a close-loop feedback. This method can be particularly applied in two tasks that Commercial-based Promotion and abnormal traffic patterns detection.
arXiv:1707.02554v1 fatcat:6lgbbvoeyvbybp3ptdfy3yne34

Contrasting Thermoelectric Transport Behaviors of p-Type PbS Caused by Doping Alkali Metals (Li and Na)

Zhenghao Hou, Dongyang Wang, Jinfeng Wang, Guangtao Wang, Zhiwei Huang, Li-Dong Zhao
2020 Research  
PbS is a latent substitute of PbTe thermoelectric materials, which is on account of its superiority in low cost and earth abundance. Here, the thermoelectric transport properties of p-type PbS by doping alkali metals (Na and Li) are investigated and it is verified that Li is a more effective dopant than Na. By introducing Li, the electrical and thermal transport properties were optimized collectively. The electrical transport properties were boosted remarkably via adjusting carrier
more » ... , and the maximum power factor (PFmax) of ~11.5 μW/cmK2 and average power factor (PFave) ~9.9 μW/cmK2 between 423 and 730 K in Pb0.99Li0.01S were achieved, which are much higher than those (~9.5 and ~7.7 μW/cmK2) of Pb0.99Na0.01S. Doping Li and Na can weaken the lattice thermal conductivity effectively. Combining the enlarged PF with suppressed total thermal conductivity, a maximum ZT ~0.5 at 730 K and a large average ZT ~0.4 at 423-730 K were obtained in p-type Pb0.99Li0.01S, which are higher than ~0.4 and ~0.3 in p-type Pb0.99Na0.01S, respectively.
doi:10.34133/2020/4084532 pmid:33623904 pmcid:PMC7877382 fatcat:il2utlgrcrhsbhesvvfksg3iri

Association between Periodontitis and Carotid Artery Calcification: A Systematic Review and Meta-Analysis

Wenxuan Wang, Zhenghao Yang, Yue Wang, Hongyu Gao, Yan Wang, Qiong Zhang, Mauro Henrique Nogueira Guimarães Abreu
2021 BioMed Research International  
Wenxuan Wang, Zhenghao Yang, and Yue Wang performed data analysis and draft the manuscript. Hongyu Gao, Yan Wang, and Qiong Zhang provided critical revisions to the article.  ...  Authors' Contributions Wenxuan Wang, Zhenghao Yang, Yue Wang, Hongyu Gao, Yan Wang, and Qiong Zhang have directly participated in the planning, execution, and analysis of this review.  ... 
doi:10.1155/2021/3278351 pmid:34532500 pmcid:PMC8438587 fatcat:qpmu5p3aqfesxowja4mmquo5t4

Entorhinal Principal Neurons Mediate Brain-stimulation Treatments for Epilepsy

Zhenghao Xu, Yi Wang, Bin Chen, Cenglin Xu, Xiaohua Wu, Ying Wang, Shihong Zhang, Weiwei Hu, Shuang Wang, Yi Guo, Xiangnan Zhang, Jianhong Luo (+2 others)
2016 EBioMedicine  
., 2007) , cerebellum (Wang et al., 2008) , or white matter (Koubeissi et al., 2013) , reduced seizure severity in TLE.  ...  Dysfunctions of the EC are frequently observed in epileptic brains, including atrophy (Bartolomei et al., 2005) , hypometabolism (Goffin et al., 2009; Guo et al., 2009; Wang et al., 2014) and cell loss  ... 
doi:10.1016/j.ebiom.2016.11.027 pmid:27908611 pmcid:PMC5161446 fatcat:q2e5sooaw5akrk6sqcnbqjyyci

Effects of diuretic administration on outcomes of extracorporeal shockwave lithotripsy: A systematic review and meta-analysis

Zhenghao Wang, Yunjin Bai, Jia Wang, Federico Bilotta
2020 PLoS ONE  
Author Contributions Conceptualization: Zhenghao Wang, Yunjin Bai.  ...  Z, Bai Y, Wang J (2020) Effects of diuretic administration on outcomes of extracorporeal shockwave lithotripsy: A systematic review and meta-analysis.  ...  invasive procedure with PLOS ONE PLOS ONE | 0230059 March 5, 2020 1 / 8 a1111111111 a1111111111 a1111111111 a1111111111 a1111111111 OPEN ACCESS Citation: Wang  ... 
doi:10.1371/journal.pone.0230059 pmid:32134993 fatcat:qa66lkjhnzaotfb2z7i77czsu4

Recent Advances in Mechanochromism of Metal-Organic Compounds

Xiao-Yan Wang, Liqiang Lv, Li Sun, Yue Hou, Zhenghao Hou, Zhao Chen
2022 Frontiers in Chemistry  
Wang et al. designed a gold(I)-isocyanide complex demonstrating interesting tricolor mechanochromism feature (Wang et al., 2018) .  ...  ., 2018; Wang et al., 2021; Jackson et al., 2021; Yin et al., 2021; Min et al., 2022) .  ... 
doi:10.3389/fchem.2022.865198 pmid:35308787 pmcid:PMC8931262 fatcat:bhh53cmgmbh75kzxibfowmvpju

An overview of bond behavior of recycled coarse aggregate concrete with steel bar

Tian Su, Chenxia Wang, Fubo Cao, Zhenghao Zou, Chunguang Wang, Jun Wang, Haihe Yi
2021 Reviews on Advanced Materials Science  
: Writing -Original Draft preparation; Fubo Cao: Investigation; Zhenghao Zou: Writing -Review & Editing; Chunguang Wang: Visualization; Jun Wang: Supervision; Haihe Yi: Methodology, Formal analysis.  ...  Wang et al.  ... 
doi:10.1515/rams-2021-0018 fatcat:odw3gpn7obf5peaqc2zq4u6fyq

Small Object Detection in Traffic Scenes Based on Attention Feature Fusion

Jing Lian, Yuhang Yin, Linhui Li, Zhenghao Wang, Yafu Zhou
2021 Sensors  
Non-local neural networks were proposed by Wang et al. in one of the important works on attention mechanisms in the field of computer vision [23] .  ... 
doi:10.3390/s21093031 pmid:33925864 fatcat:weapqf6fu5b7dl2abvksam3v24
« Previous Showing results 1 — 15 out of 303 results