arXiv subjects

Kaigui Bian

Publications and source records attributed to Kaigui Bian.

At least 37 records · Page 2Linked to original sources

arXiv2021

MetaSketch: Wireless Semantic Segmentation by Metamaterial Surfaces

Semantic segmentation is a process of partitioning an image into multiple segments for recognizing humans and objects, which can be widely applied in scenarios such as healthcare and safety monitoring. To avoid privacy violation, using RF signals instead of an image for human and object recognition has gained increasing attention. However, human and object recognition by using RF signals is usually a passive signal collection and analysis process without changing the radio environment, and the recognition accuracy is restricted significantly by unwanted multi-path fading, and/or the limited number of independent channels between RF transceivers in uncontrollable radio environments. This paper introduces MetaSketch, a novel RF-sensing system that performs semantic recognition and segmentation for humans and objects by making the radio environment reconfigurable. A metamaterial surface is incorporated into MetaSketch and diversifies the information carried by RF signals. Using compressive sensing techniques, MetaSketch reconstructs a point cloud consisting of the reflection coefficients of humans and objects at different spatial points, and recognizes the semantic meaning of the points by using symmetric multilayer perceptron groups. Our evaluation results show that MetaSketch is capable of generating favorable radio environments and extracting exact point clouds, and labeling the semantic meaning of the points with an average error rate of less than 1% in an indoor space.

eess.SP↗

arXiv2021

Wireless Indoor Simultaneous Localization and Mapping Using Reconfigurable Intelligent Surface

Indoor wireless simultaneous localization and mapping (SLAM) is considered as a promising technique to provide positioning services in future 6G systems. However, the accuracy of traditional wireless SLAM system heavily relies on the quality of propagation paths, which is limited by the uncontrollable wireless environment. In this paper, we propose a novel SLAM system assisted by a reconfigurable intelligent surface (RIS) to address this issue. By configuring the phase shifts of the RIS, the strength of received signals can be enhanced to resist the disturbance of noise. However, the selection of phase shifts heavily influences the localization and mapping phase, which makes the design very challenging. To tackle this challenge, we formulate the RIS-assisted indoor SLAM optimization problem and design an error minimization algorithm for it. Simulations show that the RIS assisted SLAM system can decrease the positioning error by at least 31% compared with benchmark schemes.

eess.SP↗

arXiv2021

Characterizing Impacts of Heterogeneity in Federated Learning upon Large-Scale Smartphone Data

Federated learning (FL) is an emerging, privacy-preserving machine learning paradigm, drawing tremendous attention in both academia and industry. A unique characteristic of FL is heterogeneity, which resides in the various hardware specifications and dynamic states across the participating devices. Theoretically, heterogeneity can exert a huge influence on the FL training process, e.g., causing a device unavailable for training or unable to upload its model updates. Unfortunately, these impacts have never been systematically studied and quantified in existing FL literature. In this paper, we carry out the first empirical study to characterize the impacts of heterogeneity in FL. We collect large-scale data from 136k smartphones that can faithfully reflect heterogeneity in real-world settings. We also build a heterogeneity-aware FL platform that complies with the standard FL protocol but with heterogeneity in consideration. Based on the data and the platform, we conduct extensive experiments to compare the performance of state-of-the-art FL algorithms under heterogeneity-aware and heterogeneity-unaware settings. Results show that heterogeneity causes non-trivial performance degradation in FL, including up to 9.2% accuracy drop, 2.32x lengthened training time, and undermined fairness. Furthermore, we analyze potential impact factors and find that device failure and participant bias are two potential factors for performance degradation. Our study provides insightful implications for FL practitioners. On the one hand, our findings suggest that FL algorithm designers consider necessary heterogeneity during the evaluation. On the other hand, our findings urge system providers to design specific mechanisms to mitigate the impacts of heterogeneity.

cs.LG↗

arXiv2020

TSSRGCN: Temporal Spectral Spatial Retrieval Graph Convolutional Network for Traffic Flow Forecasting

Traffic flow forecasting is of great significance for improving the efficiency of transportation systems and preventing emergencies. Due to the highly non-linearity and intricate evolutionary patterns of short-term and long-term traffic flow, existing methods often fail to take full advantage of spatial-temporal information, especially the various temporal patterns with different period shifting and the characteristics of road segments. Besides, the globality representing the absolute value of traffic status indicators and the locality representing the relative value have not been considered simultaneously. This paper proposes a neural network model that focuses on the globality and locality of traffic networks as well as the temporal patterns of traffic data. The cycle-based dilated deformable convolution block is designed to capture different time-varying trends on each node accurately. Our model can extract both global and local spatial information since we combine two graph convolutional network methods to learn the representations of nodes and edges. Experiments on two real-world datasets show that the model can scrutinize the spatial-temporal correlation of traffic data, and its performance is better than the compared state-of-the-art methods. Further analysis indicates that the locality and globality of the traffic networks are critical to traffic flow prediction and the proposed TSSRGCN model can adapt to the various temporal traffic patterns.

cs.LG↗

arXiv2020

MetaSensing: Intelligent Metasurface Assisted RF 3D Sensing by Deep Reinforcement Learning

Using RF signals for wireless sensing has gained increasing attention. However, due to the unwanted multi-path fading in uncontrollable radio environments, the accuracy of RF sensing is limited. Instead of passively adapting to the environment, in this paper, we consider the scenario where an intelligent metasurface is deployed for sensing the existence and locations of 3D objects. By programming its beamformer patterns, the metasurface can provide desirable propagation properties. However, achieving a high sensing accuracy is challenging, since it requires the joint optimization of the beamformer patterns and mapping of the received signals to the sensed outcome. To tackle this challenge, we formulate an optimization problem for minimizing the cross-entropy loss of the sensing outcome, and propose a deep reinforcement learning algorithm to jointly compute the optimal beamformer patterns and the mapping of the received signals. Simulation results verify the effectiveness of the proposed algorithm and show how the sizes of the metasurface and the target space influence the sensing accuracy.

eess.SP↗

arXiv2020

Differentiable Feature Aggregation Search for Knowledge Distillation

Knowledge distillation has become increasingly important in model compression. It boosts the performance of a miniaturized student network with the supervision of the output distribution and feature maps from a sophisticated teacher network. Some recent works introduce multi-teacher distillation to provide more supervision to the student network. However, the effectiveness of multi-teacher distillation methods are accompanied by costly computation resources. To tackle with both the efficiency and the effectiveness of knowledge distillation, we introduce the feature aggregation to imitate the multi-teacher distillation in the single-teacher distillation framework by extracting informative supervision from multiple teacher feature maps. Specifically, we introduce DFA, a two-stage Differentiable Feature Aggregation search method that motivated by DARTS in neural architecture search, to efficiently find the aggregations. In the first stage, DFA formulates the searching problem as a bi-level optimization and leverages a novel bridge loss, which consists of a student-to-teacher path and a teacher-to-student path, to find appropriate feature aggregations. The two paths act as two players against each other, trying to optimize the unified architecture parameters to the opposite directions while guaranteeing both expressivity and learnability of the feature aggregation simultaneously. In the second stage, DFA performs knowledge distillation with the derived feature aggregation. Experimental results show that DFA outperforms existing methods on CIFAR-100 and CINIC-10 datasets under various teacher-student settings, verifying the effectiveness and robustness of the design.

cs.LG↗

arXiv2020

A New Perspective for Flexible Feature Gathering in Scene Text Recognition Via Character Anchor Pooling

Irregular scene text recognition has attracted much attention from the research community, mainly due to the complexity of shapes of text in natural scene. However, recent methods either rely on shape-sensitive modules such as bounding box regression, or discard sequence learning. To tackle these issues, we propose a pair of coupling modules, termed as Character Anchoring Module (CAM) and Anchor Pooling Module (APM), to extract high-level semantics from two-dimensional space to form feature sequences. The proposed CAM localizes the text in a shape-insensitive way by design by anchoring characters individually. APM then interpolates and gathers features flexibly along the character anchors which enables sequence learning. The complementary modules realize a harmonic unification of spatial information and sequence learning. With the proposed modules, our recognition system surpasses previous state-of-the-art scores on irregular and perspective text datasets, including, ICDAR 2015, CUTE, and Total-Text, while paralleling state-of-the-art performance on regular text datasets.

cs.CV↗

arXiv2020

Transfer Heterogeneous Knowledge Among Peer-to-Peer Teammates: A Model Distillation Approach

Peer-to-peer knowledge transfer in distributed environments has emerged as a promising method since it could accelerate learning and improve team-wide performance without relying on pre-trained teachers in deep reinforcement learning. However, for traditional peer-to-peer methods such as action advising, they have encountered difficulties in how to efficiently expressed knowledge and advice. As a result, we propose a brand new solution to reuse experiences and transfer value functions among multiple students via model distillation. But it is still challenging to transfer Q-function directly since it is unstable and not bounded. To address this issue confronted with existing works, we adopt Categorical Deep Q-Network. We also describe how to design an efficient communication protocol to exploit heterogeneous knowledge among multiple distributed agents. Our proposed framework, namely Learning and Teaching Categorical Reinforcement (LTCR), shows promising performance on stabilizing and accelerating learning progress with improved team-wide reward in four typical experimental environments.

cs.AI↗

arXiv2019

Rethinking Irregular Scene Text Recognition

Reading text from natural images is challenging due to the great variety in text font, color, size, complex background and etc.. The perspective distortion and non-linear spatial arrangement of characters make it further difficult. While rectification based method is intuitively grounded and has pushed the envelope by far, its potential is far from being well exploited. In this paper, we present a bag of tricks that prove to significantly improve the performance of rectification based method. On curved text dataset, our method achieves an accuracy of 89.6% on CUTE-80 and 76.3% on Total-Text, an improvement over previous state-of-the-art by 6.3% and 14.7% respectively. Furthermore, our combination of tricks helps us win the ICDAR 2019 Arbitrary-Shaped Text Challenge (Latin script), achieving an accuracy of 74.3% on the held-out test set. We release our code as well as data samples for further exploration at https://github.com/Jyouhou/ICDAR2019-ArT-Recognition-Alchemy

cs.CV↗

arXiv2019

Symmetry-constrained Rectification Network for Scene Text Recognition

Reading text in the wild is a very challenging task due to the diversity of text instances and the complexity of natural scenes. Recently, the community has paid increasing attention to the problem of recognizing text instances with irregular shapes. One intuitive and effective way to handle this problem is to rectify irregular text to a canonical form before recognition. However, these methods might struggle when dealing with highly curved or distorted text instances. To tackle this issue, we propose in this paper a Symmetry-constrained Rectification Network (ScRN) based on local attributes of text instances, such as center line, scale and orientation. Such constraints with an accurate description of text shape enable ScRN to generate better rectification results than existing methods and thus lead to higher recognition accuracy. Our method achieves state-of-the-art performance on text with both regular and irregular shapes. Specifically, the system outperforms existing algorithms by a large margin on datasets that contain quite a proportion of irregular text instances, e.g., ICDAR 2015, SVT-Perspective and CUTE80.

cs.CV↗

arXiv2019

Reprojection R-CNN: A Fast and Accurate Object Detector for 360° Images

360° images are usually represented in either equirectangular projection (ERP) or multiple perspective projections. Different from the flat 2D images, the detection task is challenging for 360° images due to the distortion of ERP and the inefficiency of perspective projections. However, existing methods mostly focus on one of the above representations instead of both, leading to limited detection performance. Moreover, the lack of appropriate bounding-box annotations as well as the annotated datasets further increases the difficulties of the detection task. In this paper, we present a standard object detection framework for 360° images. Specifically, we adapt the terminologies of the traditional object detection task to the omnidirectional scenarios, and propose a novel two-stage object detector, i.e., Reprojection R-CNN by combining both ERP and perspective projection. Owing to the omnidirectional field-of-view of ERP, Reprojection R-CNN first generates coarse region proposals efficiently by a distortion-aware spherical region proposal network. Then, it leverages the distortion-free perspective projection and refines the proposed regions by a novel reprojection network. We construct two novel synthetic datasets for training and evaluation. Experiments reveal that Reprojection R-CNN outperforms the previous state-of-the-art methods on the mAP metric. In addition, the proposed detector could run at 178ms per image in the panoramic datasets, which implies its practicability in real-world applications.

cs.CV↗

arXiv2019

ImgSensingNet: UAV Vision Guided Aerial-Ground Air Quality Sensing System

Given the increasingly serious air pollution problem, the monitoring of air quality index (AQI) in urban areas has drawn considerable attention. This paper presents ImgSensingNet, a vision guided aerial-ground sensing system, for fine-grained air quality monitoring and forecasting using the fusion of haze images taken by the unmanned-aerial-vehicle (UAV) and the AQI data collected by an on-ground three-dimensional (3D) wireless sensor network (WSN). Specifically, ImgSensingNet first leverages the computer vision technique to tell the AQI scale in different regions from the taken haze images, where haze-relevant features and a deep convolutional neural network (CNN) are designed for direct learning between haze images and corresponding AQI scale. Based on the learnt AQI scale, ImgSensingNet determines whether to wake up on-ground wireless sensors for small-scale AQI monitoring and inference, which can greatly reduce the energy consumption of the system. An entropy-based model is employed for accurate real-time AQI inference at unmeasured locations and future air quality distribution forecasting. We implement and evaluate ImgSensingNet on two university campuses since Feb. 2018, and has collected 17,630 photos and 2.6 millions of AQI data samples. Experimental results confirm that ImgSensingNet can achieve higher inference accuracy while greatly reduce the energy consumption, compared to state-of-the-art AQI monitoring approaches.

eess.SY↗

arXiv2019

IoT-U: Cellular Internet-of-Things Networks over Unlicensed Spectrum

In this paper, we consider an uplink cellular Internet-of-Things (IoT) network, where a cellular user (CU) can serve as the mobile data aggregator for a cluster of IoT devices. To be specific, the IoT devices can either transmit the sensory data to the base station (BS) directly by cellular communications, or first aggregate the data to a CU through Machine-to-Machine (M2M) communications before the CU uploads the aggregated data to the BS. To support massive connections, the IoT devices can leverage the unlicensed spectrum for M2M communications, referred to as IoT Unlicensed (IoT-U). Aiming to maximize the number of scheduled IoT devices and meanwhile associate each IoT devices with the right CU or BS with the minimum transmit power, we first introduce a single-stage formulation that captures these objectives simultaneously. To tackle the NP-hard problem efficiently, we decouple the problem into two subproblems, which are solved by successive linear programming and convex optimization techniques, respectively. Simulation results show that the proposed IoT-U scheme can support more IoT devices than that only using the licensed spectrum.

cs.IT↗

arXiv2019

Real-Time Fine-Grained Air Quality Sensing Networks in Smart City: Design, Implementation and Optimization

Driven by the increasingly serious air pollution problem, the monitoring of air quality has gained much attention in both theoretical studies and practical implementations. In this paper, we present the architecture, implementation and optimization of our own air quality sensing system, which provides real-time and fine-grained air quality map of the monitored area. As the major component, the optimization problem of our system is studied in detail. Our objective is to minimize the average joint error of the established real-time air quality map, which involves data inference for the unmeasured data values. A deep Q-learning solution has been proposed for the power control problem to reasonably plan the sensing tasks of the power-limited sensing devices online. A genetic algorithm has been designed for the location selection problem to efficiently find the suitable locations to deploy limited number of sensing devices. The performance of the proposed solutions are evaluated by simulations, showing a significant performance gain when adopting both strategies.

cs.OH↗

arXiv2019

Heterogeneous Coexistence of Cognitive Radio Networks in TV White Space

Wireless standards (e.g., IEEE 802.11af and 802.22) have been developed for enabling opportunistic access in TV white space (TVWS) using cognitive radio (CR) technology. When heterogeneous CR networks that are based on different wireless standards operate in the same TVWS, coexistence issues can potentially cause major problems. Enabling collaborative coexistence via direct coordination between heterogeneous CR networks is very challenging, due to incompatible MAC/PHY designs of coexisting networks, requirement of an over-the-air common control channel for inter-network communications, and time synchronization across devices from different networks. Moreover, such a coexistence scheme would require competing networks or service providers to exchange sensitive control information that may raise conflict of interest issues and customer privacy concerns. In this paper, we present an architecture for enabling collaborative coexistence of heterogeneous CR networks over TVWS, called Symbiotic Heterogeneous coexistence ARchitecturE (SHARE). Define "indirect coordination" first before using it. Because coexistence cannot avoid coordination By mimicking the symbiotic relationships between heterogeneous organisms in a stable ecosystem, SHARE establishes an indirect coordination mechanism between heterogeneous CR networks via a mediator system, which avoids the drawbacks of direct coordination. SHARE includes two spectrum sharing algorithms whose designs were inspired by well-known models and theories from theoretical ecology, viz, the interspecific competition model and the ideal free distribution model.

cs.NI↗

arXiv2018

Real-Time Prediction for Fine-Grained Air Quality Monitoring System with Asynchronous Sensing

Due to the significant air pollution problem, monitoring and prediction for air quality have become increasingly necessary. To provide real-time fine-grained air quality monitoring and prediction in urban areas, we have established our own Internet-of-Things-based sensing system in Peking University. Due to the energy constraint of the sensors, it is preferred that the sensors wake up alternatively in an asynchronous pattern, which leads to a sparse sensing dataset. In this paper, we propose a novel approach to predict the real-time fine-grained air quality based on asynchronous sensing. The sparse dataset and the spatial-temporal-meteorological relations are modeled into the correlation graph, in which way the prediction procedures are carefully designed. The advantage of the proposed solution over existing ones is evaluated over the dataset collected by our air quality monitoring system.

eess.SP↗

arXiv2018

UAV Aided Aerial-Ground IoT for Air Quality Sensing in Smart City: Architecture, Technologies and Implementation

As air pollution is becoming the largest environmental health risk, the monitoring of air quality has drawn much attention in both theoretical studies and practical implementations. In this article, we present a real-time, fine-grained and power-efficient air quality monitoring system based on aerial and ground sensing. The architecture of this system consists of four layers: the sensing layer to collect data, the transmission layer to enable bidirectional communications, the processing layer to analyze and process the data, and the presentation layer to provide graphic interface for users. Three major techniques are investigated in our implementation, given by the data processing, the deployment strategy and the power control. For data processing, spacial fitting and short-term prediction are performed to eliminate the influences of the incomplete measurement and the latency of data uploading. The deployment strategies of ground sensing and aerial sensing are investigated to improve the quality of the collected data. The power control is further considered to balance between power consumption and data accuracy. Our implementation has been deployed in Peking University and Xidian University since February 2018, and has collected about 100 thousand effective data samples by June 2018.

cs.OH↗

arXiv2018

Mobile Social Big Data: WeChat Moments Dataset, Network Applications, and Opportunities

In parallel to the increase of various mobile technologies, the mobile social network (MSN) service has brought us into an era of mobile social big data, where people are creating new social data every second and everywhere. It is of vital importance for businesses, government, and institutes to understand how peoples' behaviors in the online cyberspace can affect the underlying computer network, or their offline behaviors at large. To study this problem, we collect a dataset from WeChat Moments, called WeChatNet, which involves 25,133,330 WeChat users with 246,369,415 records of link reposting on their pages. We revisit three network applications based on the data analytics over WeChatNet, i.e., the information dissemination in mobile cellular networks, the network traffic prediction in backbone networks, and the mobile population distribution projection. Meanwhile, we discuss the potential research opportunities for developing new applications using the released dataset.

cs.SI↗