arXiv subjects

Feng Xue

Publications and source records attributed to Feng Xue.

79 records · Page 5Linked to original sources

arXiv2019

Occlusion-shared and Feature-separated Network for Occlusion Relationship Reasoning

Occlusion relationship reasoning demands closed contour to express the object, and orientation of each contour pixel to describe the order relationship between objects. Current CNN-based methods neglect two critical issues of the task: (1) simultaneous existence of the relevance and distinction for the two elements, i.e, occlusion edge and occlusion orientation; and (2) inadequate exploration to the orientation features. For the reasons above, we propose the Occlusion-shared and Feature-separated Network (OFNet). On one hand, considering the relevance between edge and orientation, two sub-networks are designed to share the occlusion cue. On the other hand, the whole network is split into two paths to learn the high-level semantic features separately. Moreover, a contextual feature for orientation prediction is extracted, which represents the bilateral cue of the foreground and background areas. The bilateral cue is then fused with the occlusion cue to precisely locate the object regions. Finally, a stripe convolution is designed to further aggregate features from surrounding scenes of the occlusion edge. The proposed OFNet remarkably advances the state-of-the-art approaches on PIOD and BSDS ownership dataset. The source code is available at https://github.com/buptlr/OFNet.

cs.CV↗

arXiv2019

Water-based Reconfigurable Frequency Selective Rasorber with Thermally Tunable Absorption Band

In this paper, a novel water-based reconfigurable frequency selective rasorber (FSR) at microwave band is proposed, which has a thermally tunable absorption band above the transmission band. The water-based FSR consists of a bandpass type frequency selective surface (FSS) and a 3D printing container. The water substrate is filled into the sealed space constructed by the above two structures. The numerical simulation results show that the FSR can achieve absorption with high absorptivity from 8.3 to 15.2 GHz, and obtain a transmission band of 5.2 to 7.0 GHz. The minimum insertion loss of the transmission band reaches 0.72 dB at 6.14 GHz. In addition, the FSR has the reconfigurable characteristics of absorbing or reflecting electromagnetic waves by filling with water or not. The proposed water-based FSR shows its good transmission/absorption performance under different polarizations and oblique incident angles. Due to the Debye model of water, the absorption band can be adjusted by water temperature, while the passband remains stable. At last, prototype of the FSR based on water has been fabricated, and the experimental results are presented to demonstrate the validity of the proposed structure.

physics.app-ph↗

arXiv2019

Full-duplex in 5G Small Cell Access: SystemDesign and Performance Aspects

Recent achievement in self-interference cancellation algorithms enables potential application of full-duplex (FD) in 5G radio access systems. The exponential growth of data traffic in 5G can be supported by having more spectrum and higher spectral efficiency. FD communication promises to double the spectral efficiency by enabling simultaneous uplink and downlink transmissions in the same frequency band. Yet for cellular access network with FD base stations (BS) serving multiple users (UE), additional BS-to-BS and UE-to-UE interferences due to FD operation could diminish the performance gain if not tackled properly. In this article, we address the practical system design aspects to exploit FD gain at network scale. We propose efficient reference signal design, low-overhead channel state information feedback and signalling mechanisms to enable FD operation, and develop low-complexity power control and scheduling algorithms to effectively mitigate new interference introduced by FD operation. We extensively evaluate FD network-wide performance in various deployment scenarios and traffic environment with detailed LTE PHY/MAC modelling. We demonstrate that FD can achieve not only appreciable throughput gains (1.9x), but also significant transmission latency reduction~(5-8x) compared with the half-duplex system.

eess.SP↗

arXiv2018

Deep Item-based Collaborative Filtering for Top-N Recommendation

Item-based Collaborative Filtering(short for ICF) has been widely adopted in recommender systems in industry, owing to its strength in user interest modeling and ease in online personalization. By constructing a user's profile with the items that the user has consumed, ICF recommends items that are similar to the user's profile. With the prevalence of machine learning in recent years, significant processes have been made for ICF by learning item similarity (or representation) from data. Nevertheless, we argue that most existing works have only considered linear and shallow relationship between items, which are insufficient to capture the complicated decision-making process of users. In this work, we propose a more expressive ICF solution by accounting for the nonlinear and higher-order relationship among items. Going beyond modeling only the second-order interaction (e.g. similarity) between two items, we additionally consider the interaction among all interacted item pairs by using nonlinear neural networks. Through this way, we can effectively model the higher-order relationship among items, capturing more complicated effects in user decision-making. For example, it can differentiate which historical itemsets in a user's profile are more important in affecting the user to make a purchase decision on an item. We treat this solution as a deep variant of ICF, thus term it as DeepICF. To justify our proposal, we perform empirical studies on two public datasets from MovieLens and Pinterest. Extensive experiments verify the highly positive effect of higher-order item interaction modeling with nonlinear neural networks. Moreover, we demonstrate that by more fine-grained second-order interaction modeling with attention network, the performance of our DeepICF method can be further improved.

cs.IR↗

arXiv2017

A New Medical Diagnosis Method Based on Z-Numbers

How to handle uncertainty in medical diagnosis is an open issue. In this paper, a new decision making methodology based on Z-numbers is presented. Firstly, the experts' opinions are represented by Z-numbers. Z-number is an ordered pair of fuzzy numbers denoted as Z = (A, B). Then, a new method for ranking fuzzy numbers is proposed. And based on the proposed fuzzy number ranking method, a novel method is presented to transform the Z-numbers into Basic Probability Assignment (BPA). As a result, the information from different sources is combined by the Dempster' combination rule. The final decision making is more reasonable due to the advantage of information fusion. Finally, two experiments, risk analysis and medical diagnosis, are illustrated to show the efficiency of the proposed methodology.

cs.AI↗

arXiv2012

An upper bound on relaying over capacity based on channel simulation

The upper bound on the capacity of a 3-node discrete memoryless relay channel is considered, where a source X wants to send information to destination Y with the help of a relay Z. Y and Z are independent given X, and the link from Z to Y is lossless with rate $R_0$. A new inequality is introduced to upper-bound the capacity when the encoding rate is beyond the capacities of both individual links XY and XZ. It is based on generalization of the blowing-up lemma, linking conditional entropy to decoding error, and channel simulation, to the case with side information. The achieved upper-bound is strictly better than the well-known cut-set bound in several cases when the latter is $C_{XY}+R_0$, with $C_{XY}$ being the channel capacity between X and Y. One particular case is when the channel is statistically degraded, i.e., either Y is a statistically degraded version of Z with respect to X, or Z is a statistically degraded version of Y with respect to X. Moreover in this case, the bound is shown to be explicitly computable. The binary erasure channel is analyzed in detail and evaluated numerically.

cs.IT↗

arXiv2009

Network Coding with Two-Way Relaying: Achievable Rate Regions and Diversity-Multiplexing Tradeoffs

This paper addresses the fundamental characteristics of information exchange via multihop network coding over two-way relaying in a wireless ad hoc network. The end-to-end rate regions achieved by time-division multihop (TDMH), MAC-layer network coding (MLNC) and PHY-layer network coding (PLNC) are first characterized. It is shown that MLNC does not always achieve better rates than TDMH, time sharing between TDMH and MLNC is able to achieve a larger rate region, and PLNC dominates the rate regions achieved by TDMH and MLNC. An opportunistic scheduling algorithm for MLNC and PLNC is then proposed to stabilize the two-way relaying system for Poisson arrivals whenever the rate pair is within the Shannon rate regions of MLNC and PLNC. To understand the two-way transmission limits of multihop network coding, the sum-rate optimization with or without certain traffic pattern and the end-to-end diversity-multiplexing tradeoffs (DMTs) of two-way transmission over multiple relay nodes are also analyzed.

cs.IT↗