1,579 Hits in 1.8 sec

Randomized Online CP Decomposition [article]

Congbo Ma, Xiaowei Yang, Hu Wang
2020 arXiv   pre-print
CANDECOMP/PARAFAC (CP) decomposition has been widely used to deal with multi-way data. For real-time or large-scale tensors, based on the ideas of randomized-sampling CP decomposition algorithm and online CP decomposition algorithm, a novel CP decomposition algorithm called randomized online CP decomposition (ROCP) is proposed in this paper. The proposed algorithm can avoid forming full Khatri-Rao product, which leads to boost the speed largely and reduce memory usage. The experimental results
more » ... n synthetic data and real-world data show the ROCP algorithm is able to cope with CP decomposition for large-scale tensors with arbitrary number of dimensions. In addition, ROCP can reduce the computing time and memory usage dramatically, especially for large-scale tensors.
arXiv:2007.10798v1 fatcat:p57kxnrnljacrdkxrhipootgni

Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation [article]

Xiaowei Xu, Qing Lu, Yu Hu, Lin Yang, Sharon Hu, Danny Chen, Yiyu Shi
2018 arXiv   pre-print
With pervasive applications of medical imaging in health-care, biomedical image segmentation plays a central role in quantitative analysis, clinical diagno- sis, and medical intervention. Since manual anno- tation su ers limited reproducibility, arduous e orts, and excessive time, automatic segmentation is desired to process increasingly larger scale histopathological data. Recently, deep neural networks (DNNs), par- ticularly fully convolutional networks (FCNs), have been widely applied to
more » ... edical image segmenta- tion, attaining much improved performance. At the same time, quantization of DNNs has become an ac- tive research topic, which aims to represent weights with less memory (precision) to considerably reduce memory and computation requirements of DNNs while maintaining acceptable accuracy. In this paper, we apply quantization techniques to FCNs for accurate biomedical image segmentation. Unlike existing litera- ture on quantization which primarily targets memory and computation complexity reduction, we apply quan- tization as a method to reduce over tting in FCNs for better accuracy. Speci cally, we focus on a state-of- the-art segmentation framework, suggestive annotation [22], which judiciously extracts representative annota- tion samples from the original training dataset, obtain- ing an e ective small-sized balanced training dataset. We develop two new quantization processes for this framework: (1) suggestive annotation with quantiza- tion for highly representative training samples, and (2) network training with quantization for high accuracy. Extensive experiments on the MICCAI Gland dataset show that both quantization processes can improve the segmentation performance, and our proposed method exceeds the current state-of-the-art performance by up to 1%. In addition, our method has a reduction of up to 6.4x on memory usage.
arXiv:1803.04907v1 fatcat:bi7liafp7jbetmadc2e77o4svq

Local Distribution in Neighborhood for Classification [article]

Chengsheng Mao, Bin Hu, Lei Chen, Philip Moore, Xiaowei Zhang
2018 arXiv   pre-print
• ChengshengMao, Bin Hu, Philip Moore and Xiaowei Zhang are with the School of Information Science and Engineering, Lanzhou University, Gansu, China. • Corresponding to Chengsheng Mao ( e-mail: chshmao  ... 
arXiv:1812.02934v1 fatcat:wj64obdyy5erbatsl4nz4edaii

DAC-SDC Low Power Object Detection Challenge for UAV Applications [article]

Xiaowei Xu, Xinyi Zhang, Bei Yu, X. Sharon Hu, Christopher Rowen, Jingtong Hu, Yiyu Shi
2018 arXiv   pre-print
The 55th Design Automation Conference (DAC) held its first System Design Contest (SDC) in 2018. SDC'18 features a lower power object detection challenge (LPODC) on designing and implementing novel algorithms based object detection in images taken from unmanned aerial vehicles (UAV). The dataset includes 95 categories and 150k images, and the hardware platforms include Nvidia's TX2 and Xilinx's PYNQ Z1. DAC-SDC'18 attracted more than 110 entries from 12 countries. This paper presents in detail
more » ... e dataset and evaluation procedure. It further discusses the methods developed by some of the entries as well as representative results. The paper concludes with directions for future improvements.
arXiv:1809.00110v1 fatcat:lfjf3gcwc5cr5egl5xkboy3jsu

Instance Shadow Detection [article]

Tianyu Wang, Xiaowei Hu, Qiong Wang, Pheng-Ann Heng, Chi-Wing Fu
2020 arXiv   pre-print
Hu et al. [16, 19] and Zhu et al. [54] explored the spatial context via the direction-aware spatial context module and recurrent attention residual module, respectively. Wang et al.  ... 
arXiv:1911.07034v2 fatcat:47kdmlx5zfbyjmmjzqnwzuuxre

Detection of Long Noncoding RNA Expression by Nonradioactive Northern Blots [chapter]

Xiaowen Hu, Yi Feng, Zhongyi Hu, Youyou Zhang, Chao-Xing Yuan, Xiaowei Xu, Lin Zhang
2016 Msphere  
With the advances in sequencing technology and transcriptome analysis, it is estimated that up to 75% of the human genome is transcribed into RNAs. This finding prompted intensive investigations on the biological functions of non-coding RNAs and led to very exciting discoveries of microRNAs as important players in disease pathogenesis and therapeutic applications. Research on long non-coding RNAs (lncRNAs) is in its infancy, yet a broad spectrum of biological regulations has been attributed to
more » ... ncRNAs. As a novel class of RNA transcripts, the expression level and splicing variants of lncRNAs are various. Northern blot analysis can help us learn about the identity, size, and abundance of lncRNAs. Here we describe how to use northern blot to determine lncRNA abundance and identify different splicing variants of a given lncRNA.
doi:10.1007/978-1-4939-3378-5_14 pmid:26721491 pmcid:PMC4773203 fatcat:gemeeroaifbt5nzp67isspphc4

Scaling for edge inference of deep neural networks

Xiaowei Xu, Yukun Ding, Sharon Xiaobo Hu, Michael Niemier, Jason Cong, Yu Hu, Yiyu Shi
2018 Nature Electronics  
Hu et al. 98 adopted hashing and Leng et al. 99 squeezed the last bit out for training to further improve the accuracy of binary weight networks, while Ko et al. 100, 101 determined the optimal pair  ... 
doi:10.1038/s41928-018-0059-3 fatcat:g6oezqmezbhcjbli6pxbvnrihm

Robust Anomaly Detection for Time-series Data [article]

Min Hu, Yi Wang, Xiaowei Feng, Shengchen Zhou, Zhaoyu Wu, Yuan Qin
2022 arXiv   pre-print
Time-series anomaly detection plays a vital role in monitoring complex operation conditions. However, the detection accuracy of existing approaches is heavily influenced by pattern distribution, existence of multiple normal patterns, dynamical features representation, and parameter settings. For the purpose of improving the robustness and guaranteeing the accuracy, this research combined the strengths of negative selection, unthresholded recurrence plots, and an extreme learning machine
more » ... der and then proposed robust anomaly detection for time-series data (RADTD), which can automatically learn dynamical features in time series and recognize anomalies with low label dependency and high robustness. Yahoo benchmark datasets and three tunneling engineering simulation experiments were used to evaluate the performance of RADTD. The experiments showed that in benchmark datasets RADTD possessed higher accuracy and robustness than recurrence qualification analysis and extreme learning machine autoencoder, respectively, and that RADTD accurately detected the occurrence of tunneling settlement accidents, indicating its remarkable performance in accuracy and robustness.
arXiv:2202.02721v1 fatcat:vtpda4fgvfeajdipra2bib2dvy

ColluEagle: Collusive review spammer detection using Markov random fields [article]

Zhuo Wang, Runlong Hu, Qian Chen, Pei Gao, Xiaowei Xu
2019 arXiv   pre-print
Product reviews are extremely valuable for online shoppers in providing purchase decisions. Driven by immense profit incentives, fraudsters deliberately fabricate untruthful reviews to distort the reputation of online products. As online reviews become more and more important, group spamming, i.e., a team of fraudsters working collaboratively to attack a set of target products, becomes a new fashion. Previous works use review network effects, i.e. the relationships among reviewers, reviews, and
more » ... products, to detect fake reviews or review spammers, but ignore time effects, which are critical in characterizing group spamming. In this paper, we propose a novel Markov random field (MRF)-based method (ColluEagle) to detect collusive review spammers, as well as review spam campaigns, considering both network effects and time effects. First we identify co-review pairs, a review phenomenon that happens between two reviewers who review a common product in a similar way, and then model reviewers and their co-review pairs as a pairwise-MRF, and use loopy belief propagation to evaluate the suspiciousness of reviewers. We further design a high quality yet easy-to-compute node prior for ColluEagle, through which the review spammer groups can also be subsequently identified. Experiments show that ColluEagle can not only detect collusive spammers with high precision, significantly outperforming state-of-the-art baselines --- FraudEagle and SpEagle, but also identify highly suspicious review spammer campaigns.
arXiv:1911.01690v1 fatcat:6h7qwkzxbnby7ojxzexiobsnz4

On Neural Architecture Search for Resource-Constrained Hardware Platforms [article]

Qing Lu, Weiwen Jiang, Xiaowei Xu, Yiyu Shi, Jingtong Hu
2019 arXiv   pre-print
In the recent past, the success of Neural Architecture Search (NAS) has enabled researchers to broadly explore the design space using learning-based methods. Apart from finding better neural network architectures, the idea of automation has also inspired to improve their implementations on hardware. While some practices of hardware machine-learning automation have achieved remarkable performance, the traditional design concept is still followed: a network architecture is first structured with
more » ... cellent test accuracy, and then compressed and optimized to fit into a target platform. Such a design flow will easily lead to inferior local-optimal solutions. To address this problem, we propose a new framework to jointly explore the space of neural architecture, hardware implementation, and quantization. Our objective is to find a quantized architecture with the highest accuracy that is implementable on given hardware specifications. We employ FPGAs to implement and test our designs with limited loop-up tables (LUTs) and required throughput. Compared to the separate design/searching methods, our framework has demonstrated much better performance under strict specifications and generated designs of higher accuracy by 18\% to 68\% in the task of classifying CIFAR10 images. With 30,000 LUTs, a light-weight design is found to achieve 82.98\% accuracy and 1293 images/second throughput, compared to which, under the same constraints, the traditional method even fails to find a valid solution.
arXiv:1911.00105v1 fatcat:5pi4ac3ihncnxlutodo6fao5sa

FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis [article]

Yawen Wu, Dewen Zeng, Xiaowei Xu, Yiyu Shi, Jingtong Hu
2022 arXiv   pre-print
Many works have shown that deep learning-based medical image classification models can exhibit bias toward certain demographic attributes like race, gender, and age. Existing bias mitigation methods primarily focus on learning debiased models, which may not necessarily guarantee all sensitive information can be removed and usually comes with considerable accuracy degradation on both privileged and unprivileged groups. To tackle this issue, we propose a method, FairPrune, that achieves fairness
more » ... y pruning. Conventionally, pruning is used to reduce the model size for efficient inference. However, we show that pruning can also be a powerful tool to achieve fairness. Our observation is that during pruning, each parameter in the model has different importance for different groups' accuracy. By pruning the parameters based on this importance difference, we can reduce the accuracy difference between the privileged group and the unprivileged group to improve fairness without a large accuracy drop. To this end, we use the second derivative of the parameters of a pre-trained model to quantify the importance of each parameter with respect to the model accuracy for each group. Experiments on two skin lesion diagnosis datasets over multiple sensitive attributes demonstrate that our method can greatly improve fairness while keeping the average accuracy of both groups as high as possible.
arXiv:2203.02110v1 fatcat:c7e5cvtkcnghxdzilxraumipru

Deterministic circular self test path

Ke Wen, Yu Hu, Xiaowei Li
2007 Tsinghua Science and Technology  
CSTP (Circular Self Test Path) is an attractive technique for testing sequential circuits in the nanometer era because it can easily provide at-speed test. But the area overhead of CSTP is high if random-pattern-resistant faults need to be reliably tested. This paper presents a deterministic CSTP (DCSTP) structure that embeds pre-computed test data with predictable area overhead. Experimental results on ISCAS'89 benchmarks indicate that complete fault coverage can be obtained with low area overhead, especially for large circuit.
doi:10.1016/s1007-0214(07)70078-0 fatcat:lynjipzozfbt5gkkhhcm34ffhe

Local temporal Rac1-GTP nadirs and peaks restrict cell protrusions and retractions [article]

Jianjiang Hu, Xiaowei Gong, Staffan Stromblad
2021 bioRxiv   pre-print
Spatiotemporal coordination of the GTP-binding activity of Rac1 and RhoA initiates and reinforces cell membrane protrusions and retractions during cell migration. However, while protrusions and retractions form cycles that cells use to efficiently probe their microenvironment, the control of their finite lifetime remains unclear. To examine if Rac1 or RhoA may also control protrusion and retraction lifetimes, we here define the relation of their spatiotemporal GTP-binding levels to key
more » ... n and retraction events, as well as to cell-ECM mechanical forces in fibrosarcoma cells grown on collagen of physiologically relevant stiffness. We identified temporal Rac1-GTP nadirs and peaks at the maximal edge velocity of local membrane protrusions and retractions, respectively, followed by declined edge velocity. Moreover, increased local Rac1-GTP consistently preceded increased cell-ECM traction force. This suggests that Rac1-GTP nadirs and peaks may restrain the lifetime of protrusions and retractions, possibly involving the regulation of local traction forces. Functional testing by optogenetics validated this notion, since local Rac1-GTP elevation applied early in the process prolonged protrusions and restrained retractions, while local Rac1-GTP inhibition acted in reverse. Optogenetics also defined Rac1-GTP as a promotor of local traction force. Together, we show that Rac1 plays a fundamental role in restricting the size and durability of protrusions and retractions, plausibly in part through controlling traction forces.
doi:10.1101/2021.06.23.449555 fatcat:7rv7jptfurdnrkdslhxp43vx5m

Quadratic fractional solitons [article]

Liangwei Zeng, Yongle Zhu, Boris A. Malomed, Dumitru Mihalache, Qing Wang, Hu Long, Yi Cai, Xiaowei Lu, Jingzhen Li
2021 arXiv   pre-print
We introduce a system combining the quadratic self-attractive or composite quadratic-cubic nonlinearity, acting in the combination with the fractional diffraction, which is characterized by its Lévy index α. The model applies to a gas of quantum particles moving by Lévy flights, with the quadratic term representing the Lee-Huang-Yang correction to the mean-field interactions. A family of fundamental solitons is constructed in a numerical form, while the dependence of its norm on the chemical
more » ... ential characteristic is obtained in an exact analytical form. The family of quasi-Townes solitons, appearing in the limit case of α =1/2, is investigated by means of a variational approximation. A nonlinear lattice, represented by spatially periodical modulation of the quadratic term, is briefly addressed too. The consideration of the interplay of competing quadratic (attractive) and cubic (repulsive) terms with a lattice potential reveals families of single-, double-, and triple-peak gap solitons (GSs) in two finite bandgaps. The competing nonlinearity gives rise to alternating regions of stability and instability of the GS, the stability intervals shrinking with the increase of the number of peaks in the GS.
arXiv:2111.00443v2 fatcat:4wcosk6eizgppezddzdznhxyx4

A Lightweight Job Submission Frontend and its Toolkits - HepJob

Xiaowei Jiang, Jingyan Shi, Jiaheng Zou, Ran Du, Qingbao Hu
2019 Zenodo  
In a HEP Computing Center, at least 1 batch systems are used. As an example, at IHEP, we've used 3 batch systems, PBS, HTCondor and Slurm. After running PBS as local batch system for 10 years, we replaced it by HTCondor (for HTC) and Slurm (for HPC). During that period, problems came up on both user and admin sides. On user side, the new batch systems bring a set of new commands, which users have to learn and remember more. In particular, some users would have to use HTCondor and Slurm in the
more » ... antime. Furthermore, HTCondor and Slurm provide more functions, which means more complicated usage mode, compared to the simple PBS commands. On admin side, HTCondor gives more freedom to users, which becomes a problem to admins. Admins have to find the solutions for many problems: preventing users from requesting the resources they are not allowed to use, checking if the required attributes are correct, deciding which site is requested (Slurm cluster, remote sites, virtual machine sites), etc. For the above requirements, HepJob was developed. HepJob provides a set of simple commands to users, hep_sub, hep_q, hep_rm, etc. In the submission procedure, HepJob checks all the attributes and ensure all attributes are correct; Assigns the proper resources to users, the user and group info is obtained from the management database; Routes jobs to the targeted site; Goes through the remaining steps. Users can start with HepJob very easily and admins can take many prevention actions in HepJob.
doi:10.5281/zenodo.3599404 fatcat:2idse7jnxvg7bfntiiq7xoge6y
« Previous Showing results 1 — 15 out of 1,579 results