高效学习的透过未知散射介质的相位恢复方法

透过散射介质对目标进行准确的重建仍然是阻碍人们对深层生物组织成像分析和深空天文观测的主要挑战之一。基于深度学习的散射计算成像方法虽然在成像质量和效率等方面取得了很大的进展,但是针对实际系统中散射介质状态不固定,目标结构具有较高复杂度以及可获取的训练散射数据有限的情况下,单纯利用数据驱动的方法已无法进行准确高效的重建。将散斑相关原理和卷积神经网络强大的数据挖掘和映射能力进行有效的结合,进一步挖掘和利用散斑所包含的冗余信息,实现了仅利用一块薄散射介质对应的散斑数据即可实现透过具有不同统计特性散射介质的复杂目标重构。该方法针对实际散射场景复杂多变和训练样本数据有限的情况,实现了对复杂目标的高质量恢复,有力地推动了基于物理感知的学习方法在实际散射场景中的应用。     

Editorial: Machine Learning and Intelligent Communications (MLICOM 2018)

Mobile Networks and Applications -     

Physical Violence Detection Based on Distributed Surveillance Cameras

Mobile Networks and Applications - In recent years, physical violence detection has become a research hotspot in the area of human activity recognition. With the improvement and full coverage of...     

In Situ Management of Ions Migration to Control Hysteresis Effect for Planar Heterojunction Perovskite Solar Cells

As one of the most promising photovoltaic materials, the efficiency of inorganic–organic hybrid halide perovskite solar cells (PSCs) has reached 25.5% in 2020. However, the stability and hysteresis remain primary challenges before it can become a commercial photovoltaic technology. Therefore, those issues have drawn significant attention for photovoltaic applications. In this work, a study of the PSCs hysteresis improvement is presented based on a combination of first-principles simulations, scanning electron microscopy images, and time-dependent photocurrent measurements. It indicates the hysteresis led by the ion migration and accumulation is mainly localized at the two interfaces: one is between electron transport layer and active layer, and the other is between active layer and hole transport layer. Considering the massive defects at the grain boundaries (GBs), they lower the potential barriers significantly. The defect density at GBs is therefore reduced via the in situ passivation of PbI₂ crystals. The hysteresis index is decreased from 22.43% down to 1.04%, and results in an improvement in efficiency from 17.12% up to 20.10%. Following the understanding of defect-induced hysteresis, an approach to improve the hysteresis is provided, which can be integrated into the fabrication process and widely applied to enhance the performance of PSCs.     

Photonic Crystal Palette of Binary Block Copolymer Blends for Full Visible Structural Color Encryption

Structural color (SC) arising from a periodically ordered self-assembled block copolymer (BCP) photonic crystal (PC) is useful for reflective-mode sensing displays owing to its capability of stimuli-responsive structure alteration. However, a set of PC inks, each providing a precisely addressable SC in the full visible range, has rarely been demonstrated. Here, a strategy for developing BCP PC inks with tunable structures is presented. This involves solution-blending of two lamellar-forming BCPs with different molecular weights. By controlling the mixing ratio of the two BCPs, a thin 1D BCP PC film is developed with alternating in-plane lamellae whose periodicity varies linearly from ≈46 to ≈91 nm. Subsequent preferential swelling of one-type lamellae with either solvent or non-volatile ionic liquid causes the photonic band gap of the films to red-shift, giving rise to full-visible-range SC correlated with the pristine nanostructures of the blended films in both liquid and solid states. The BCP PC palette of solution-blended binary solutions is conveniently employed in various coating processes, allowing facile development of BCP SC on the targeted surface. Furthermore, full-color SC paintings are realized with their transparent PC inks, facilitating low-power pattern encryption.     

Personalized Convolution for Face Recognition

International Journal of Computer Vision - Face recognition has been significantly advanced by deep learning based methods. In all face recognition methods based on convolutional neural network...     

Synchronously tracking entities and relations in a syntax-aware parallel architecture for aspect-opinion pair extraction

Aspect-Opinion Pair Extraction (AOPE) task aims to capture each aspect with its corresponding opinions in user reviews. Entity recognition and relation detection are two fundamental subtasks of AOPE. Although recent works take interaction into account, the two subtasks are still relatively independent during calculation. Furthermore, since AOPE task has not been formally proposed for a long time, syntactic information does not attract much attention in the current deep learning models for AOPE. In this paper, we propose a model for Synchronously Tracking Entities and Relations (STER) to deal with AOPE. Specifically, we design a network consisting of a bank of gated RNNs, where we can track all entities of a review sentence in parallel. STER utilizes three features, i.e., context, syntax and relation, to learn the representation of each tracked entity and calculate the correlated degree between all entities synchronously at each time step. The entity representation and the correlated degree are highly dependent during calculation. Finally, they will be used for entity recognition and relation detection, respectively. Therefore, in STER, the two subtasks of AOPE can achieve sufficient interaction, which enhances their mutual heuristic effect heavily. To verify the effectiveness and adaptiveness of our model, we conduct experiments on two annotation versions of SemEval datasets. The results demonstrate that STER not only achieves advanced performances but adapts to different annotation strategies well.

     

Analysis of Internet Financial Risks Based on Deep Learning and BP Neural Network

Computational Economics - The study aims to analyze and forecast Internet financial risks based on the model based on deep learning and the Back Propagation Neural Network (BPNN). First, the theory...     

中国健康服务业发展战略研究

为落实健康中国发展战略,推进中国健康服务业的发展,中国工程院于2015年启动"中国健康服务业发展战略研究"重大咨询项目。课题自启动以来,组织了28位院士和150余位专家,对京上广深等一至三线共12个城市进行了广泛的社会调查。本文在大量社会调查的基础上,从健康服务业的概念、内涵、发展特点入手,深入分析了国内健康服务业的发展现状;以全方位、全覆盖、全过程建立健康服务保障体系为目标,对健康服务业的定位、发展思路,城乡理想模式等进行了深入探讨;并针对健康管理体系建设、养生养老、医养结合、健康保险、社会办医、金融保障等重点问题,提出了为顺应中国健康服务业发展战略顺畅实施的保障措施和相关建议。     

Mechanical behaviour analysis of buried pressure pipeline crossing ground settlement zone

Numerical simulation model of buried pipeline crossing ground settlement zone was established considering pipeline–soil interaction. Mechanical behaviour of the buried pipeline was investigated, and effects of ground settlement, pipeline parameters and surrounding soil parameters on mechanical behaviour of the buried pipeline were discussed. These results show that there are two high stress areas on both sides of the dividing plane. High stress areas are oval on the top and bottom of the pipeline. Z-shape bending deformation appears under the action of ground settlement. In ground settlement zone, axial strain on the top of the pipeline is compression strain, and axial strain on the bottom of the pipeline is tension strain. On the contrary, they are tension strain and compression strain respectively in no settlement zone. Bending deformation, axial strain and plastic strain of the buried pipeline increase with the increase in ground settlement. Von Mises stress, high stress area, axial strain and plastic strain of the buried pipeline increase with the increasing diameter-thick ratio and internal pressure, but they decrease with the increase in buried depth. Diameter-thick ratio and internal pressure have a small effect on the bending deformation of the buried pipeline. Bending deformation decreases with the increase in buried depth in ground settlement zone. Von Mises stress and high stress area increase with the increasing surrounding soil’s elasticity modulus and cohesion, but they increase first and then decrease with the increase in Poisson’s ratio. Bending deformation of the pipeline in no settlement zone increases with the increase in elasticity modulus and Poisson’s ratio, but it is affected little by the cohesion. Axial strain and plastic strain have a bigger relationship with the elasticity modulus and Poisson’s ratio. Axial strain and plastic strain of the buried pipeline increase with the increase in cohesion, and the change rates increase with the increase in ground settlement.