Rail transportation, especially, high-speed rails (HSR), is an important infrastructure for the development of national economy and the promotion of passenger experience. Due to the large bandwidth, millimeter wave (mmWave) communication is regarded
as a promising technology to meet the demand of high data rates. However, since mmWave communication has the characteristic of high attenuation, mobile relay (MR) is considered in this paper. Also, full-duplex (FD) communications have been proposed to improve the spectral efficiency. However, because of the high speed, as well as the problem of penetration loss, passengers on the train have a poor quality of service. Consequently, an effective user association scheme for HSR in mmWave band is necessary. In this paper, we investigate the user association optimization problem in mmWave mobilerelay systems where the MRs operate in the FD mode. To maximize the system capacity, we propose a cooperative user association approach based on coalition formation game, and develop a coalition formation algorithm to solve the challenging NP-hard problem. We also prove the convergence and Nashstable property of the proposed algorithm. Extensive simulations are done to show the system performance of the proposed scheme under various network settings. It is demonstrated that the proposed distributed low complexity scheme achieves a nearoptimal performance and outperforms two baseline schemes in terms of average system throughput.
Practical recommender systems experience a cold-start problem when observed user-item interactions in the history are insufficient. Meta learning, especially gradient based one, can be adopted to tackle this problem by learning initial parameters of
the model and thus allowing fast adaptation to a specific task from limited data examples. Though with significant performance improvement, it commonly suffers from two critical issues: the non-compatibility with mainstream industrial deployment and the heavy computational burdens, both due to the inner-loop gradient operation. These two issues make them hard to be applied in practical recommender systems. To enjoy the benefits of meta learning framework and mitigate these problems, we propose a recommendation framework called Contextual Modulation Meta Learning (CMML). CMML is composed of fully feed-forward operations so it is computationally efficient and completely compatible with the mainstream industrial deployment. CMML consists of three components, including a context encoder that can generate context embedding to represent a specific task, a hybrid context generator that aggregates specific user-item features with task-level context, and a contextual modulation network, which can modulate the recommendation model to adapt effectively. We validate our approach on both scenario-specific and user-specific cold-start setting on various real-world datasets, showing CMML can achieve comparable or even better performance with gradient based methods yet with much higher computational efficiency and better interpretability.
Federated learning (FL) emerged as a promising learning paradigm to enable a multitude of participants to construct a joint ML model without exposing their private training data. Existing FL designs have been shown to exhibit vulnerabilities which ca
n be exploited by adversaries both within and outside of the system to compromise data privacy. However, most current works conduct attacks by leveraging gradients on a small batch of data, which is less practical in FL. In this work, we consider a more practical and interesting scenario in which participants share their epoch-averaged gradients (share gradients after at least 1 epoch of local training) rather than per-example or small batch-averaged gradients as in previous works. We perform the first systematic evaluation of attribute reconstruction attack (ARA) launched by the malicious server in the FL system, and empirically demonstrate that the shared epoch-averaged local model gradients can reveal sensitive attributes of local training data of any victim participant. To achieve this goal, we develop a more effective and efficient gradient matching based method called cos-matching to reconstruct the training data attributes. We evaluate our attacks on a variety of real-world datasets, scenarios, assumptions. Our experiments show that our proposed method achieves better attribute attack performance than most existing baselines.
The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training. However, acquiring and manually labeling a large medical image set is resource-intensive, expensive, and sometimes impra
ctical due to data sharing and privacy issues. To address this challenge, we propose an adversarial data augmentation approach to improve the efficiency in utilizing training data and to enlarge the dataset via simulated but realistic transformations. Specifically, we present a generic task-driven learning framework, which jointly optimizes a data augmentation model and a segmentation network during training, generating informative examples to enhance network generalizability for the downstream task. The data augmentation model utilizes a set of photometric and geometric image transformations and chains them to simulate realistic complex imaging variations that could exist in magnetic resonance (MR) imaging. The proposed adversarial data augmentation does not rely on generative networks and can be used as a plug-in module in general segmentation networks. It is computationally efficient and applicable for both supervised and semi-supervised learning. We analyze and evaluate the method on two MR image segmentation tasks: cardiac segmentation and prostate segmentation. Results show that the proposed approach can alleviate the need for labeled data while improving model generalization ability, indicating its practical value in medical imaging applications.
In twisted bilayer graphene (TBG) a moire pattern forms that introduces a new length scale to the material. At the magic twist angle of 1.1{deg}, this causes a flat band to form, yielding emergent properties such as correlated insulator behavior and
superconductivity [1-4]. In general, the moire structure in TBG varies spatially, influencing the local electronic properties [5-9] and hence the outcome of macroscopic charge transport experiments. In particular, to understand the wide variety observed in the phase diagrams and critical temperatures, a more detailed understanding of the local moire variation is needed [10]. Here, we study spatial and temporal variations of the moire pattern in TBG using aberration-corrected Low Energy Electron Microscopy (AC-LEEM) [11,12]. The spatial variation we find is lower than reported previously. At 500{deg}C, we observe thermal fluctuations of the moire lattice, corresponding to collective atomic displacements of less than 70pm on a time scale of seconds [13], homogenizing the sample. Despite previous concerns, no untwisting of the layers is found, even at temperatures as high as 600{deg}C [14,15]. From these observations, we conclude that thermal annealing can be used to decrease the local disorder in TBG samples. Finally, we report the existence of individual edge dislocations in the atomic and moire lattice. These topological defects break translation symmetry and are anticipated to exhibit unique local electronic properties.
Traditional classification for subclass of the Seyfert galaxies is visual inspection or using a quantity defined as a flux ratio between the Balmer line and forbidden line. One algorithm of deep learning is Convolution Neural Network (CNN) and has sh
own successful classification results. We building a 1-dimension CNN model to distinguish Seyfert 1.9 spectra from Seyfert 2 galaxies. We find our model can recognize Seyfert 1.9 and Seyfert 2 spectra with an accuracy over 80% and pick out an additional Seyfert 1.9 sample which was missed by visual inspection. We use the new Seyfert 1.9 sample to improve performance of our model and obtain a 91% precision of Seyfert 1.9. These results indicate our model can pick out Seyfert 1.9 spectra among Seyfert 2 spectra. We decompose H{alpha} emission line of our Seyfert 1.9 galaxies by fitting 2 Gaussian components and derive line width and flux. We find velocity distribution of broad H{alpha} component of the new Seyfert 1.9 sample has an extending tail toward the higher end and luminosity of the new Seyfert 1.9 sample is slightly weaker than the original Seyfert 1.9 sample. This result indicates that our model can pick out the sources that have relatively weak broad H{alpha} component. Besides, we check distributions of the host galaxy morphology of our Seyfert 1.9 samples and find the distribution of the host galaxy morphology is dominant by large bulge galaxy. In the end, we present an online catalog of 1297 Seyfert 1.9 galaxies with measurement of H{alpha} emission line.
The purpose of the PandaX experiments is to search for the possible events resulted from dark matter particles, neutrinoless double beta decay or other rare processes with xenon detectors. Understanding the energy depositions from backgrounds or cali
bration sources in these detectors is very important. The program of BambooMC is created to perform the Geant4-based Monte Carlo simulation, providing reference information for the experiments. We introduce the design and features of BambooMC in this report. The running of the program depends on a configuration file, which combines different detectors, event generators, physics lists and analysis packs together in one simulation. The program can be easily extended and applied to other experiments.
Deep learning-based segmentation methods are vulnerable to unforeseen data distribution shifts during deployment, e.g. change of image appearances or contrasts caused by different scanners, unexpected imaging artifacts etc. In this paper, we present
a cooperative framework for training image segmentation models and a latent space augmentation method for generating hard examples. Both contributions improve model generalization and robustness with limited data. The cooperative training framework consists of a fast-thinking network (FTN) and a slow-thinking network (STN). The FTN learns decoupled image features and shape features for image reconstruction and segmentation tasks. The STN learns shape priors for segmentation correction and refinement. The two networks are trained in a cooperative manner. The latent space augmentation generates challenging examples for training by masking the decoupled latent space in both channel-wise and spatial-wise manners. We performed extensive experiments on public cardiac imaging datasets. Using only 10 subjects from a single site for training, we demonstrated improved cross-site segmentation performance and increased robustness against various unforeseen imaging artifacts compared to strong baseline methods. Particularly, cooperative training with latent space data augmentation yields 15% improvement in terms of average Dice score when compared to a standard training method.
In this paper, we propose an orthogonal frequency division multiplexing (OFDM)-based generalized optical quadrature spatial modulation (GOQSM) technique for multiple-input multiple-output optical wireless communication (MIMO-OWC) systems. Considering
the error propagation and noise amplification effects when applying maximum likelihood and maximum ratio combining (ML-MRC)-based detection, we further propose a deep neural network (DNN)-aided detection for OFDM-based GOQSM systems. The proposed DNN-aided detection scheme performs the GOQSM detection in a joint manner, which can efficiently eliminate the adverse effects of both error propagation and noise amplification. The obtained simulation results successfully verify the superiority of the deep learning-aided OFDM-based GOQSM technique for high-speed MIMO-OWC systems.
87 -
Weichen Chen Collage ofn Information Engineering
, Zhejiang University of Technology
, Hangzhou
2021
Pedestrian attribute recognition in surveillance scenarios is still a challenging task due to inaccurate localization of specific attributes. In this paper, we propose a novel view-attribute localization method based on attention (VALA), which relies
on the strong relevance between attributes and views to capture specific view-attributes and to localize attribute-corresponding areas by attention mechanism. A specific view-attribute is composed by the extracted attribute feature and four view scores which are predicted by view predictor as the confidences for attribute from different views. View-attribute is then delivered back to shallow network layers for supervising deep feature extraction. To explore the location of a view-attribute, regional attention is introduced to aggregate spatial information of the input attribute feature in height and width direction for constraining the image into a narrow range. Moreover, the inter-channel dependency of view-feature is embedded in the above two spatial directions. An attention attribute-specific region is gained after fining the narrow range by balancing the ratio of channel dependencies between height and width branches. The final view-attribute recognition outcome is obtained by combining the output of regional attention with the view scores from view predictor. Experiments on three wide datasets (RAP, RAPv2, PETA, and PA-100K) demonstrate the effectiveness of our approach compared with state-of-the-art methods.
