Filters








949 Hits in 2.0 sec

Internet Anomaly Detection based on Complex Network Path [article]

Jinfa Wang, Siyuan Jia, Hai Zhao, Jiuqiang Xu, Chuan Lin
2017 arXiv   pre-print
Detecting the anomaly behaviors such as network failure or Internet intentional attack in the large-scale Internet is a vital but challenging task. While numerous techniques have been developed based on Internet traffic in past years, anomaly detection for structured datasets by complex network have just been of focus recently. In this paper, a anomaly detection method for large-scale Internet topology is proposed by considering the changes of network crashes. In order to quantify the dynamic
more » ... anges of Internet topology, the network path changes coefficient(NPCC) is put forward which will highlight the Internet abnormal state after it is attacked continuously. Furthermore we proposed the decision function which is inspired by Fibonacci Sequence to determine whether the Internet is abnormal or not. That is the current Internet is abnormal if its NPCC is beyond the normal domain which structured by the previous k NPCCs of Internet topology. Finally the new Internet anomaly detection method was tested over the topology data of three Internet anomaly events. The results show that the detection accuracy of all events are over 97%, the detection precision of each event are 90.24%, 83.33% and 66.67%, when k = 36. According to the experimental values of the index F_1, we found the the better the detection performance is, the bigger the k is, and our method has better performance for the anomaly behaviors caused by network failure than that caused by intentional attack. Compared with traditional anomaly detection, our work may be more simple and powerful for the government or organization in items of detecting large-scale abnormal events.
arXiv:1710.06121v1 fatcat:7fxmod3f6rcjpboalp25wzatjq

Constrained Maximum Correntropy Adaptive Filtering [article]

Siyuan Peng, Badong Chen, Lei Sun, Zhiping Lin, Wee Ser
2016 arXiv   pre-print
Lin a linearly-constrained minimum-variance (LCMV) filtering problem in antenna array processing [6] .  ... 
arXiv:1610.01766v2 fatcat:z5jnuvvutnh27pzyoxzw7u3nn4

A Hardware-Oriented and Memory-Efficient Method for CTC Decoding [article]

Siyuan Lu, Jinming Lu, Jun Lin, Zhongfeng Wang
2019 arXiv   pre-print
The Connectionist Temporal Classification (CTC) has achieved great success in sequence to sequence analysis tasks such as automatic speech recognition (ASR) and scene text recognition (STR). These applications can use the CTC objective function to train the recurrent neural networks (RNNs), and decode the outputs of RNNs during inference. While hardware architectures for RNNs have been studied, hardware-based CTCdecoders are desired for high-speed CTC-based inference systems. This paper, for
more » ... first time, provides a low-complexity and memory-efficient approach to build a CTC-decoder based on the beam search decoding. Firstly, we improve the beam search decoding algorithm to save the storage space. Secondly, we compress a dictionary (reduced from 26.02MB to 1.12MB) and use it as the language model. Meanwhile searching this dictionary is trivial. Finally, a fixed-point CTC-decoder for an English ASR and an STR task using the proposed method is implemented with C++ language. It is shown that the proposed method has little precision loss compared with its floating-point counterpart. Our experiments demonstrate the compression ratio of the storage required by the proposed beam search decoding algorithm are 29.49 (ASR) and 17.95 (STR).
arXiv:1905.03175v1 fatcat:df44erzet5fktj6fs3goreh4ze

Sharp decay for Teukolsky equation in Kerr spacetimes [article]

Siyuan Ma, Lin Zhang
2021 arXiv   pre-print
In this work, we derive the global sharp decay, as both a lower and an upper bounds, for the spin ±𝔰 components, which are solutions to the Teukolsky equation, in the black hole exterior and on the event horizon of a slowly rotating Kerr spacetime. These estimates are generalized to any subextreme Kerr background under an integrated local energy decay estimate. Our results apply to the scalar field (𝔰=0), the Maxwell field (𝔰=1) and the linearized gravity (𝔰=2) and confirm the Price's law decay
more » ... that is conjectured to be sharp. Our analyses rely on a novel global conservation law for the Teukolsky equation, and this new approach can be applied to derive the precise asymptotics for solutions to semilinear wave equations.
arXiv:2111.04489v2 fatcat:o6cfes7p5ndo5k2iro7ctxxbku

Neural Rejuvenation: Improving Deep Network Training by Enhancing Computational Resource Utilization [article]

Siyuan Qiao, Zhe Lin, Jianming Zhang, Alan Yuille
2018 arXiv   pre-print
In this paper, we study the problem of improving computational resource utilization of neural networks. Deep neural networks are usually over-parameterized for their tasks in order to achieve good performances, thus are likely to have underutilized computational resources. This observation motivates a lot of research topics, e.g. network pruning, architecture search, etc. As models with higher computational costs (e.g. more parameters or more computations) usually have better performances, we
more » ... udy the problem of improving the resource utilization of neural networks so that their potentials can be further realized. To this end, we propose a novel optimization method named Neural Rejuvenation. As its name suggests, our method detects dead neurons and computes resource utilization in real time, rejuvenates dead neurons by resource reallocation and reinitialization, and trains them with new training schemes. By simply replacing standard optimizers with Neural Rejuvenation, we are able to improve the performances of neural networks by a very large margin while using similar training efforts and maintaining their original resource usages.
arXiv:1812.00481v1 fatcat:f2it5tdqkvhqhaxifc44inhnoq

Training Deep Neural Networks Using Posit Number System [article]

Jinming Lu, Siyuan Lu, Zhisheng Wang, Chao Fang, Jun Lin, Zhongfeng Wang, Li Du
2019 arXiv   pre-print
With the increasing size of Deep Neural Network (DNN) models, the high memory space requirements and computational complexity have become an obstacle for efficient DNN implementations. To ease this problem, using reduced-precision representations for DNN training and inference has attracted many interests from researchers. This paper first proposes a methodology for training DNNs with the posit arithmetic, a type- 3 universal number (Unum) format that is similar to the floating point(FP) but
more » ... reduced precision. A warm-up training strategy and layer-wise scaling factors are adopted to stabilize training and fit the dynamic range of DNN parameters. With the proposed training methodology, we demonstrate the first successful training of DNN models on ImageNet image classification task in 16 bits posit with no accuracy loss. Then, an efficient hardware architecture for the posit multiply-and-accumulate operation is also proposed, which can achieve significant improvement in energy efficiency than traditional floating-point implementations. The proposed design is helpful for future low-power DNN training accelerators.
arXiv:1909.03831v1 fatcat:nj4ghktsb5hwxkf6m2z27ng2ye

SDM transmission of orbital angular momentum mode channels over a multi-ring-core fibre

Jingxing Zhang, Zhongzheng Lin, Jie Liu, Junyi Liu, Zhenrui Lin, Shuqi Mo, Shuqing Lin, Lei Shen, Lei Zhang, Yujie Chen, Xiaobo Lan, Siyuan Yu
2021 Nanophotonics  
Spatial division multiplexed optical transmission over a multi-ring-core orbital angular momentum (OAM) fibre is reported for the first time. The seven cores in the fibre each supports OAM modes belonging to mode groups (MGs) of topological charge |l| = 0–4. The MGs of |l| = 1–4 each contains four near-degenerate OAM modes that carry the combinations of opposite orbital and spin angular momenta. The weak coupling between these higher-order MGs as well as between the cores enables the
more » ... s transmission of 56 OAM mode channels (two MGs per core of the topological charges |l| = 2 and 3) over the 60-km span, while only requiring modular 4 × 4 multi-input multi-output (MIMO) signal processing to equalize the mixing among the four mode channels in each MG that are strongly coupled – a feature that also minimizes the number of filter taps. The mode channels are launched using seven-core single-mode fibre fan-in devices, with the light in all seven cores converted into OAM modes via specially designed plates that carry seven off-axis-compensated phase masks matching the hexagonal configuration of the multi-core fibres. Each mode channel carries 10 WDM wavelengths, equivalently aggregating to a capacity of 31.4 Tbit/s (net 25.1 Tb/s) and a spectral efficiency (SE) of 62.7 bit/s/Hz (net 50.2 bit/s/Hz) with 28-GBaud QPSK modulation per data channel.
doi:10.1515/nanoph-2021-0471 fatcat:yvmceiqkavg7jbsrkyq52efnqm

High performance distributed feedback quantum dot lasers with laterally coupled dielectric grating [article]

Zhuohui Yang, Zhengqing Ding, Lin Liu, Hancheng Zhong, Sheng Cao, Xinzhong Zhang, Shizhe Lin, Xiaoying Huang, Huadi Deng, Ying Yu, Siyuan Yu
2021 arXiv   pre-print
The combination of grating-based frequency-selective optical feedback mechanisms, such as distributed feedback (DFB) or distributed Bragg reflector (DBR) structures, with quantum dot (QD) gain materials is a main approach towards ultra-high-performance semiconductor lasers for many key novel applications, either as stand-alone sources or as on-chip sources in photonic integrated circuits. However, the fabrication of conventional buried Bragg grating structures on GaAs, GaAs/Si, GaSb and other
more » ... terial platforms have been met with major material regrowth difficulties. We report a novel and universal approach of introducing laterally coupled dielectric Bragg gratings to semiconductor lasers that allows highly controllable, reliable and strong coupling between the grating and the optical mode. We implement such a grating structure in a low-loss amorphous silicon material alongside GaAs lasers with InAs/GaAs QD gain layers. The resulting DFB laser arrays emit at pre-designed 0.8 THz LWDM frequency intervals in the 1300 nm band with record performance parameters, including side mode suppression ratios as high as 52.7 dB, continuous-wave output power of 27.7 mW (room-temperature) and 10 mW (at 70C), and ultra-low relative intensity noise (RIN) of < -165 dB/Hz (2.5-25 GHz). The devices are also capable of operating isolator-free under very high external reflection levels of up to -12.3 dB whilst maintaining the high spectral and ultra-low RIN qualities. These results validate the novel laterally coupled dielectric grating as a technologically superior and potentially cost-effective approach for fabricating DFB and DBR lasers free of their semiconductor material constraints, thus universally applicable across different material platforms and wavelength bands.
arXiv:2110.14186v1 fatcat:xmwwbadk3ngl3jojheo5r23axm

A Product Line Systems Engineering Process for Variability Identification and Reduction [article]

Mole Li, Alan Grigg, Charles Dickerson, Lin Guan, Siyuan Ji
2018 arXiv   pre-print
A Product Line Systems Engineering Process for Variability Identification and Reduction Mole Li, Alan Grigg, Charles Dickerson, Senior Member, IEEE  , Lin Guan and Siyuan Ji, Member, IEEE T This paper  ...  Mole Li and Lin Guan are with the Department of Computer Science, Loughborough University, UK(e-mail: m.li@ lboro.ac.uk; l.guan@ lboro.ac.uk).  ... 
arXiv:1806.04705v1 fatcat:yvdsxw62uzgvpp3wmbmh2j44zm

Scalable Modulation for Scalable Wireless Videocast

Lin Cai, Yuanqian Luo, Siyuan Xiang, Jianping Pan
2010 2010 Proceedings IEEE INFOCOM  
In conventional wireless systems with layered architectures, the physical layer treats all data streams from upper layers equally and apply the same modulation and coding schemes. Newer systems such as Digital Video Broadcast start to introduce hierarchical modulation schemes with SuperPosition Coding (SPC) and support data streams of different priorities. However, SPC requires specialized hardware and has high complexity beyond most existing handheld devices. We thus propose scalable
more » ... (s-mod) by reusing the current mainstream modulation schemes with software-based bit-remapping. In this paper, we study how to optimize the configuration of the physical layer s-mod and coding schemes to maximize the utility of videocast with Scalable Video Coding (SVC). Simulation results demonstrate significant performance gains using s-mod and the cross-layer optimization, indicating s-mod and SVC is a good combination for wireless video multicast and unicast.
doi:10.1109/infcom.2010.5462237 dblp:conf/infocom/CaiLXP10 fatcat:p4kzfrhmargyrl74g3mnspxco4

Invertible Manifold Learning for Dimension Reduction [article]

Siyuan Li, Haitao Lin, Zelin Zang, Lirong Wu, Jun Xia, Stan Z. Li
2021 arXiv   pre-print
Acknowledgments This work was performed during the internship of Siyuan Li and Haitao Lin at Westlake University.  ... 
arXiv:2010.04012v2 fatcat:nhncdhml65fdlfqsfoyygvosam

Suggestive Annotation: A Deep Active Learning Framework for Biomedical Image Segmentation [article]

Lin Yang, Yizhe Zhang, Jianxu Chen, Siyuan Zhang, Danny Z. Chen
2017 arXiv   pre-print
Image segmentation is a fundamental problem in biomedical image analysis. Recent advances in deep learning have achieved promising results on many biomedical image segmentation benchmarks. However, due to large variations in biomedical images (different modalities, image settings, objects, noise, etc), to utilize deep learning on a new application, it usually needs a new set of training data. This can incur a great deal of annotation effort and cost, because only biomedical experts can annotate
more » ... effectively, and often there are too many instances in images (e.g., cells) to annotate. In this paper, we aim to address the following question: With limited effort (e.g., time) for annotation, what instances should be annotated in order to attain the best performance? We present a deep active learning framework that combines fully convolutional network (FCN) and active learning to significantly reduce annotation effort by making judicious suggestions on the most effective annotation areas. We utilize uncertainty and similarity information provided by FCN and formulate a generalized version of the maximum set cover problem to determine the most representative and uncertain areas for annotation. Extensive experiments using the 2015 MICCAI Gland Challenge dataset and a lymph node ultrasound image segmentation dataset show that, using annotation suggestions by our method, state-of-the-art segmentation performance can be achieved by using only 50% of training data.
arXiv:1706.04737v1 fatcat:ck6xwf6axjagvnu3lsyefcrubu

The Impact of Automation on Air Traffic Controller's Behaviors

Yanjun Wang, Rongjin Hu, Siyuan Lin, Michael Schultz, Daniel Delahaye
2021 Aerospace (Basel)  
Air traffic controllers have to make quick decisions to keep air traffic safe. Their behaviors have a significant impact on the operation of the air traffic management (ATM) system. Automation tools have enhanced the ATM system's capability by reducing the controller's task-load. Much attention has been devoted to developing advanced automation in the last decade. However, less is known about the impact of automation on the behaviors of air traffic controllers. Here, we empirically tested the
more » ... fects of three levels of automation—including manual, attention-guided, and automated—as well as varying traffic levels on eye movements, situation awareness and mental workload. The results showed that there are significant differences in the gaze and saccade behaviors between the attention-guided group and automated group. Traffic affected eye movements under the manual mode or under the attention-guided mode, but had no effect on eye movements under the automated mode. The results also supported the use of automation for enhancing situation awareness while reducing mental workload. Our work has potential implications for the design of automation and operation procedures.
doi:10.3390/aerospace8090260 fatcat:6dryztdib5dcli5hvm2cqijzze

PFLD: A Practical Facial Landmark Detector [article]

Xiaojie Guo, Siyuan Li, Jinke Yu, Jiawan Zhang, Jiayi Ma, Lin Ma, Wei Liu, Haibin Ling
2019 arXiv   pre-print
Being accurate, efficient, and compact is essential to a facial landmark detector for practical use. To simultaneously consider the three concerns, this paper investigates a neat model with promising detection accuracy under wild environments e.g., unconstrained pose, expression, lighting, and occlusion conditions) and super real-time speed on a mobile device. More concretely, we customize an end-to-end single stage network associated with acceleration techniques. During the training phase, for
more » ... each sample, rotation information is estimated for geometrically regularizing landmark localization, which is then NOT involved in the testing phase. A novel loss is designed to, besides considering the geometrical regularization, mitigate the issue of data imbalance by adjusting weights of samples to different states, such as large pose, extreme lighting, and occlusion, in the training set. Extensive experiments are conducted to demonstrate the efficacy of our design and reveal its superior performance over state-of-the-art alternatives on widely-adopted challenging benchmarks, i.e., 300W (including iBUG, LFPW, AFW, HELEN, and XM2VTS) and AFLW. Our model can be merely 2.1Mb of size and reach over 140 fps per face on a mobile phone (Qualcomm ARM 845 processor) with high precision, making it attractive for large-scale or real-time applications. We have made our practical system based on PFLD 0.25X model publicly available at for encouraging comparisons and improvements from the community.
arXiv:1902.10859v2 fatcat:ofqjv44ivfajtkoeug7ew4hbmi

Bibliometric Study of Sodium Glucose Cotransporter 2 Inhibitors in Cardiovascular Research

Lu Chen, Siyuan Ma, Donghong Hu, Hairuo Lin, Yingqi Zhu, Kaitong Chen, Lin Chen, Cankun Zheng, Jichen Liu, Yulin Liao
2020 Frontiers in Pharmacology  
An increasing number of studies have shown that sodium glucose cotransporter 2 (SGLT2) inhibitors, initially used as antidiabetic agents, have cardiovascular (CV) benefits. However, few bibliometric analyses have examined this field systematically. Our study aimed to visualize the publications to determine the trends and hotspots in CV research on SGLT2 inhibitors. Publications on SGLT2 inhibitors in cardiovascular research were retrieved from the Web of Science Core Collection. Microsoft Excel
more » ... 2019, VOSviewer, and CiteSpace V were used to analyze and plot the references. On July 3, 2020, 1509 records of CV research on SGLT2 inhibitors published from 2013 to 2020 were retrieved. Nearly half were authored by American scholars, and most were published in Diabetes Obesity Metabolism, Cardiovascular Diabetology, and Diabetes Therapy. The USA was the leading driving force, with a strong academic reputation in this area. Inzucchi SE published the most related articles, while Neal B was cited the most frequently. All the top 10 co-cited references were in the leading co-cited journal, The New England Journal of Medicine. "Atherosclerotic cardiovascular event" was the leading research hotspot. The keywords "cardiac metabolism," "heart failure hospitalization," and "heart failure with preserved ejection fraction" appeared most recently as research frontiers. Most studies focused on clinical trial outcomes, such as cardiovascular death and heart failure (HF) hospitalization. The mechanisms of SGLT2 inhibitors, especially those related to cardiac metabolism, may soon become hotspots and should be closely monitored.
doi:10.3389/fphar.2020.561494 pmid:33041801 pmcid:PMC7522576 fatcat:vqlrlhg4rjcw5pj3fhywkoh2p4
« Previous Showing results 1 — 15 out of 949 results