arXiv subjects

Chen Li

Publications and source records attributed to Chen Li.

At least 379 records · Page 21Linked to original sources

arXiv2022

Predictive Edge Caching through Deep Mining of Sequential Patterns in User Content Retrievals

Edge caching plays an increasingly important role in boosting user content retrieval performance while reducing redundant network traffic. The effectiveness of caching ultimately hinges on the accuracy of predicting content popularity in the near future. However, at the network edge, content popularity can be extremely dynamic due to diverse user content retrieval behaviors and the low-degree of user multiplexing. It's challenging for the traditional reactive caching systems to keep up with the dynamic content popularity patterns. In this paper, we propose a novel Predictive Edge Caching (PEC) system that predicts the future content popularity using fine-grained learning models that mine sequential patterns in user content retrieval behaviors, and opportunistically prefetches contents predicted to be popular in the near future using idle network bandwidth. Through extensive experiments driven by real content retrieval traces, we demonstrate that PEC can adapt to highly dynamic content popularity, and significantly improve cache hit ratio and reduce user content retrieval latency over the state-of-art caching policies. More broadly, our study demonstrates that edge caching performance can be boosted by deep mining of user content retrieval behaviors.

cs.NI↗

arXiv2022

Quasi-supervised Learning for Super-resolution PET

Low resolution of positron emission tomography (PET) limits its diagnostic performance. Deep learning has been successfully applied to achieve super-resolution PET. However, commonly used supervised learning methods in this context require many pairs of low- and high-resolution (LR and HR) PET images. Although unsupervised learning utilizes unpaired images, the results are not as good as that obtained with supervised deep learning. In this paper, we propose a quasi-supervised learning method, which is a new type of weakly-supervised learning methods, to recover HR PET images from LR counterparts by leveraging similarity between unpaired LR and HR image patches. Specifically, LR image patches are taken from a patient as inputs, while the most similar HR patches from other patients are found as labels. The similarity between the matched HR and LR patches serves as a prior for network construction. Our proposed method can be implemented by designing a new network or modifying an existing network. As an example in this study, we have modified the cycle-consistent generative adversarial network (CycleGAN) for super-resolution PET. Our numerical and experimental results qualitatively and quantitatively show the merits of our method relative to the state-ofthe-art methods. The code is publicly available at https://github.com/PigYang-ops/CycleGAN-QSDL.

eess.IV↗

arXiv2022

A Multi-Channel Next POI Recommendation Framework with Multi-Granularity Check-in Signals

Current study on next POI recommendation mainly explores user sequential transitions with the fine-grained individual-user POI check-in trajectories only, which suffers from the severe check-in data sparsity issue. In fact, coarse-grained signals (i.e., region- and global-level check-ins) in such sparse check-ins would also benefit to augment user preference learning. Specifically, our data analysis unveils that user movement exhibits noticeable patterns w.r.t. the regions of visited POIs. Meanwhile, the global all-user check-ins can help reflect sequential regularities shared by the crowd. We are, therefore, inspired to propose the MCMG: a Multi-Channel next POI recommendation framework with Multi-Granularity signals categorized from two orthogonal perspectives, i.e., fine-coarse grained check-ins at either POI/region level or local/global level. Being equipped with three modules (i.e., global user behavior encoder, local multi-channel encoder, and region-aware weighting strategy), MCMG is capable of capturing both fine- and coarse-grained sequential regularities as well as exploring the dynamic impact of multi-channel by differentiating the region check-in patterns. Extensive experiments on four real-world datasets show that our MCMG significantly outperforms state-of-the-art next POI recommendation approaches.

cs.IR↗

arXiv2022

Segmentation of Weakly Visible Environmental Microorganism Images Using Pair-wise Deep Learning Features

The use of Environmental Microorganisms (EMs) offers a highly efficient, low cost and harmless remedy to environmental pollution, by monitoring and decomposing of pollutants. This relies on how the EMs are correctly segmented and identified. With the aim of enhancing the segmentation of weakly visible EM images which are transparent, noisy and have low contrast, a Pairwise Deep Learning Feature Network (PDLF-Net) is proposed in this study. The use of PDLFs enables the network to focus more on the foreground (EMs) by concatenating the pairwise deep learning features of each image to different blocks of the base model SegNet. Leveraging the Shi and Tomas descriptors, we extract each image's deep features on the patches, which are centered at each descriptor using the VGG-16 model. Then, to learn the intermediate characteristics between the descriptors, pairing of the features is performed based on the Delaunay triangulation theorem to form pairwise deep learning features. In this experiment, the PDLF-Net achieves outstanding segmentation results of 89.24%, 63.20%, 77.27%, 35.15%, 89.72%, 91.44% and 89.30% on the accuracy, IoU, Dice, VOE, sensitivity, precision and specificity, respectively.

cs.CV↗

arXiv2022

Artificial Neural Networks for Finger Vein Recognition: A Survey

Finger vein recognition is an emerging biometric recognition technology. Different from the other biometric features on the body surface, the venous vascular tissue of the fingers is buried deep inside the skin. Due to this advantage, finger vein recognition is highly stable and private. They are almost impossible to be stolen and difficult to interfere with by external conditions. Unlike the finger vein recognition methods based on traditional machine learning, the artificial neural network technique, especially deep learning, it without relying on feature engineering and have superior performance. To summarize the development of finger vein recognition based on artificial neural networks, this paper collects 149 related papers. First, we introduce the background of finger vein recognition and the motivation of this survey. Then, the development history of artificial neural networks and the representative networks on finger vein recognition tasks are introduced. The public datasets that are widely used in finger vein recognition are then described. After that, we summarize the related finger vein recognition tasks based on classical neural networks and deep neural networks, respectively. Finally, the challenges and potential development directions in finger vein recognition are discussed. To our best knowledge, this paper is the first comprehensive survey focusing on finger vein recognition based on artificial neural networks.

cs.CV↗

arXiv2022

Reshape: Adaptive Result-aware Skew Handling for Exploratory Analysis on Big Data

The process of data analysis, especially in GUI-based analytics systems, is highly exploratory. The user iteratively refines a workflow multiple times before arriving at the final workflow. In such an exploratory setting, it is valuable to the user if the initial results of the workflow are representative of the final answers so that the user can refine the workflow without waiting for the completion of its execution. Partitioning skew may lead to the production of misleading initial results during the execution. In this paper, we explore skew and its mitigation strategies from the perspective of the results shown to the user. We present a novel framework called Reshape that can adaptively handle partitioning skew in pipelined execution. Reshape employs a two-phase approach that transfers load in a fine-tuned manner to mitigate skew iteratively during execution, thus enabling it to handle changes in input-data distribution. Reshape has the ability to adaptively adjust skew-handling parameters, which reduces the technical burden on the users. Reshape supports a variety of operators such as HashJoin, Group-by, and Sort. We implemented Reshape on top of two big data engines, namely Amber and Flink, to demonstrate its generality and efficiency, and report an experimental evaluation using real and synthetic datasets.

cs.DC↗

arXiv2022

A Transistor Operations Model for Deep Learning Energy Consumption Scaling Law

Deep Learning (DL) has transformed the automation of a wide range of industries and finds increasing ubiquity in society. The high complexity of DL models and its widespread adoption has led to global energy consumption doubling every 3-4 months. Currently, the relationship between the DL model configuration and energy consumption is not well established. At a general computational energy model level, there is both strong dependency to both the hardware architecture (e.g. generic processors with different configuration of inner components- CPU and GPU, programmable integrated circuits - FPGA), as well as different interacting energy consumption aspects (e.g., data movement, calculation, control). At the DL model level, we need to translate non-linear activation functions and its interaction with data into calculation tasks. Current methods mainly linearize nonlinear DL models to approximate its theoretical FLOPs and MACs as a proxy for energy consumption. Yet, this is inaccurate (est. 93\% accuracy) due to the highly nonlinear nature of many convolutional neural networks (CNNs) for example. In this paper, we develop a bottom-level Transistor Operations (TOs) method to expose the role of non-linear activation functions and neural network structure in energy consumption. We translate a range of feedforward and CNN models into ALU calculation tasks and then TO steps. This is then statistically linked to real energy consumption values via a regression model for different hardware configurations and data sets. We show that our proposed TOs method can achieve a 93.61% - 99.51% precision in predicting its energy consumption.

cs.LG↗

arXiv2022

Frustration-induced diffusive scattering anomaly and dimension change in $\rm FeGe_2$

Magnetic frustration, arising from the competition of exchange interactions, has received great attention because of its relevance to exotic quantum phenomena in materials. In the current work, we report an unusual checkerboard-shaped scattering anomaly in $\rm FeGe_2$, far from the known incommensurate magnetic satellite peaks, for the first time by inelastic neutron scattering. More surprisingly, such phenomenon appears as spin dynamics at low temperature, but it becomes prominent above Néel transition as elastic scattering. A new model Hamiltonian that includes an intraplane next-nearest neighbor was proposed and attributes such anomaly to the near-perfect magnetic frustration and the emergence of unexpected two-dimensional magnetic order in the quasi-one-dimensional $\rm FeGe_2$.

cond-mat.mtrl-sci↗

arXiv2022

An application of Pixel Interval Down-sampling (PID) for dense tiny microorganism counting on environmental microorganism images

This paper proposes a novel pixel interval down-sampling network (PID-Net) for dense tiny object (yeast cells) counting tasks with higher accuracy. The PID-Net is an end-to-end convolutional neural network (CNN) model with an encoder--decoder architecture. The pixel interval down-sampling operations are concatenated with max-pooling operations to combine the sparse and dense features. This addresses the limitation of contour conglutination of dense objects while counting. The evaluation was conducted using classical segmentation metrics (the Dice, Jaccard and Hausdorff distance) as well as counting metrics. The experimental results show that the proposed PID-Net had the best performance and potential for dense tiny object counting tasks, which achieved 96.97\% counting accuracy on the dataset with 2448 yeast cell images. By comparing with the state-of-the-art approaches, such as Attention U-Net, Swin U-Net and Trans U-Net, the proposed PID-Net can segment dense tiny objects with clearer boundaries and fewer incorrect debris, which shows the great potential of PID-Net in the task of accurate counting.

cs.CV↗

arXiv2022

High-pressure control of optical nonlinearity in the polar Weyl semimetal TaAs

The transition metal monopnictide family of Weyl semimetals recently has been shown to exhibit anomalously strong second-order optical nonlinearity, which is theoretically attributed to a highly asymmetric polarization distribution induced by their polar structure. We experimentally test this hypothesis by measuring optical second harmonic generation (SHG) from TaAs across a pressure-tuned polar-to-nonpolar structural phase transition. Despite the high-pressure structure remaining noncentrosymmetric, the SHG yield is reduced by more than 60 % by 20 GPa as compared to the ambient pressure value. By examining the pressure dependence of distinct groups of SHG susceptibility tensor elements, we find that the yield is primarily controlled by a single element that governs the response along the polar axis. Our results confirm a connection between the polar axis and the giant optical nonlinearity of Weyl semimetals and demonstrate pressure as a means to tune this effect $in$ $situ$.

cond-mat.str-el↗

arXiv2022

Neutron Scattering Signature of Phonon Renormalization in Nickel (II) Oxide

The physics of mutual interaction of phonon quasiparticles with electronic spin degrees of freedom, leading to unusual transport phenomena of spin and heat, has been a subject of continuing interests for decades. Despite its pivotal role in transport processes, the effect of spin-phonon coupling on the phonon system, especially acoustic phonon properties, has so far been elusive. By means of inelastic neutron scattering and first-principles calculations, anomalous scattering spectral intensity from acoustic phonons was identified in the exemplary collinear antiferromagnetic nickel (II) oxide, unveiling strong spin-lattice correlations that renormalize the polarization of acoustic phonon. In particular, a clear magnetic scattering signature of the measured neutron scattering intensity from acoustic phonons is demonstrated by its momentum transfer and temperature dependences. The anomalous scattering intensity is successfully modeled with a modified magneto-vibrational scattering cross section, suggesting the presence of spin precession driven by phonon. The renormalization of phonon eigenvector is indicated by the observed "geometry-forbidden" neutron scattering intensity from transverse acoustic phonon. Importantly, the eigenvector renormalization cannot be explained by magnetostriction but instead, it could result from the coupling between phonon and local magnetization of ions.

cond-mat.mtrl-sci↗

arXiv2022

Deep Learning for Finger Vein Recognition: A Brief Survey of Recent Trend

Finger vein image recognition technology plays an important role in biometric recognition and has been successfully applied in many fields. Because veins are buried beneath the skin tissue, finger vein image recognition has an unparalleled advantage, which is not easily disturbed by external factors. This review summarizes 46 papers about deep learning for finger vein image recognition from 2017 to 2021. These papers are summarized according to the tasks of deep neural networks. Besides, we present the challenges and potential development directions of finger vein image recognition.

cs.CV↗

arXiv2022

High-responsivity MoS$_2$ hot-electron telecom-band photodetector integrated with microring resonator

We report a high-responsive hot-electron photodetector based on the integration of an Au-MoS$_2$ junction with a silicon nitride microring resonator (MRR) for detecting telecom-band light. The coupling of the evanescent field of the silicon nitride MRR with the Au-MoS$_2$ Schottky junction region enhances the hot-electron injection efficiency. The device exhibits a high responsivity of 154.6 mA W-1 at the wavelength of 1516 nm, and the moderately uniform responsivities are obtained over the wavelength range of 1500 nm-1630 nm. This MRR-enhanced MoS2 hot-electron photodetector offers possibilities for integrated optoelectronic systems.

physics.optics↗

arXiv2022

Mining Error Templates for Grammatical Error Correction

Some grammatical error correction (GEC) systems incorporate hand-crafted rules and achieve positive results. However, manually defining rules is time-consuming and laborious. In view of this, we propose a method to mine error templates for GEC automatically. An error template is a regular expression aiming at identifying text errors. We use the web crawler to acquire such error templates from the Internet. For each template, we further select the corresponding corrective action by using the language model perplexity as a criterion. We have accumulated 1,119 error templates for Chinese GEC based on this method. Experimental results on the newly proposed CTC-2021 Chinese GEC benchmark show that combing our error templates can effectively improve the performance of a strong GEC system, especially on two error types with very little training data. Our error templates are available at \url{https://github.com/HillZhang1999/gec_error_template}.

cs.CL↗

arXiv2022

Understanding Linearity of Cross-Lingual Word Embedding Mappings

The technique of Cross-Lingual Word Embedding (CLWE) plays a fundamental role in tackling Natural Language Processing challenges for low-resource languages. Its dominant approaches assumed that the relationship between embeddings could be represented by a linear mapping, but there has been no exploration of the conditions under which this assumption holds. Such a research gap becomes very critical recently, as it has been evidenced that relaxing mappings to be non-linear can lead to better performance in some cases. We, for the first time, present a theoretical analysis that identifies the preservation of analogies encoded in monolingual word embeddings as a necessary and sufficient condition for the ground-truth CLWE mapping between those embeddings to be linear. On a novel cross-lingual analogy dataset that covers five representative analogy categories for twelve distinct languages, we carry out experiments which provide direct empirical support for our theoretical claim. These results offer additional insight into the observations of other researchers and contribute inspiration for the development of more effective cross-lingual representation learning strategies.

cs.CL↗

arXiv2022

GasHis-Transformer: A Multi-scale Visual Transformer Approach for Gastric Histopathological Image Detection

In this paper, a multi-scale visual transformer model, referred as GasHis-Transformer, is proposed for Gastric Histopathological Image Detection (GHID), which enables the automatic global detection of gastric cancer images. GasHis-Transformer model consists of two key modules designed to extract global and local information using a position-encoded transformer model and a convolutional neural network with local convolution, respectively. A publicly available hematoxylin and eosin (H&E) stained gastric histopathological image dataset is used in the experiment. Furthermore, a Dropconnect based lightweight network is proposed to reduce the model size and training time of GasHis-Transformer for clinical applications with improved confidence. Moreover, a series of contrast and extended experiments verify the robustness, extensibility and stability of GasHis-Transformer. In conclusion, GasHis-Transformer demonstrates high global detection performance and shows its significant potential in GHID task.

cs.CV↗

arXiv2022

Adaptive Weighted Nonnegative Matrix Factorization for Robust Feature Representation

Nonnegative matrix factorization (NMF) has been widely used to dimensionality reduction in machine learning. However, the traditional NMF does not properly handle outliers, so that it is sensitive to noise. In order to improve the robustness of NMF, this paper proposes an adaptive weighted NMF, which introduces weights to emphasize the different importance of each data point, thus the algorithmic sensitivity to noisy data is decreased. It is very different from the existing robust NMFs that use a slow growth similarity measure. Specifically, two strategies are proposed to achieve this: fuzzier weighted technique and entropy weighted regularized technique, and both of them lead to an iterative solution with a simple form. Experimental results showed that new methods have more robust feature representation on several real datasets with noise than exsiting methods.

cs.LG↗

arXiv2022

Chip-integrated van der Waals PN heterojunction photodetector with low dark current and high responsivity

Two-dimensional materials are attractive for constructing high-performance photonic chip-integrated photodetectors because of their remarkable electronic and optical properties and dangling-bond-free surfaces. However, the reported chip-integrated two-dimensional material photodetectors were mainly implemented with the configuration of metal-semiconductor-metal, suffering from high dark currents and low responsivities at high operation speed. Here, we report a van der Waals PN heterojunction photodetector, composed of p-type black phosphorous and n-type molybdenum telluride, integrated on a silicon nitride waveguide. The built-in electric field of the PN heterojunction significantly suppresses the dark current and improves the responsivity. Under a bias of 1 V pointing from n-type molybdenum telluride to p-type black phosphorous, the dark current is lower than 7 nA, which is more than two orders of magnitude lower than those reported in other waveguide-integrated black phosphorus photodetectors. An intrinsic responsivity up to 577 mA/W is obtained. Remarkably, the van der Waals PN heterojunction is tunable by the electrostatic doping to further engineer its rectification and improve the photodetection, enabling an increased responsivity of 709 mA/W. Besides, the heterojunction photodetector exhibits a response bandwidth of ~1.0 GHz and a uniform photodetection over a wide spectral range, as experimentally measured from 1500 to 1630 nm. The demonstrated chip-integrated van der Waals PN heterojunction photodetector with low dark current, high responsivity and fast response has great potentials to develop high-performance on-chip photodetectors for various photonic integrated circuits based on silicon, lithium niobate, polymer, etc.

physics.optics↗