A Hybrid Strategy-Based Ultra-Narrow Stretchable Microelectrodes with Cell-Level Resolution

Stretchable ultra-narrow (e.g., 10 µm in width) microelectrodes are crucial for the electrophysiological monitoring of single cells providing the fundamental understanding to the working mechanism of neuro network or other electrically functional cells. Current fabrication strategies either focus on the preparation of normal stretchable electrodes with hundreds of micrometers or millimeters in width by using inorganic conductive materials or develop conductive organic polymer gel for ultra-narrow electrodes which suffer from low stretchability and instability for long-term implantation, therefore, it is still highly desirable to explore bio-interfacial ultra-narrow stretchable inorganic electrodes. Herein, a hybrid strategy is reported to prepare ultra-narrow multi-channel stretchable microelectrodes without using photolithography or laser-assisting etching. A 10 µm × 10 µm monitoring window is fabricated with enhanced interfacial impedance by the special rough surface. The stretchability achieves to 120% for this 10 µm-width stretchable electrode. Supported by these superior properties, it is demonstrated that the stretchable microelectrodes can detect electrophysiological signals of single cells in vitro and collect electrophysiological signals more precisely in vivo. The reported strategy will open up the accessible preparation of the fine-size stretchable microelectrode. It will significantly improve the resolution of monitoring and stimulation of inorganic stretchable electrodes.     

Functional Materials for Memristor-Based Reservoir Computing: Dynamics and Applications

The booming development of artificial intelligence (AI) requires faster physical processing units as well as more efficient algorithms. Recently, reservoir computing (RC) has emerged as an alternative brain-inspired framework for fast learning with low training cost, since only the weights associated with the output layers should be trained. Physical RC becomes one of the leading paradigms for computation using high-dimensional, nonlinear, dynamic substrates. Among them, memristor appears to be a simple, adaptable, and efficient framework for constructing physical RC since they exhibit nonlinear features and memory behavior, while memristor-implemented artificial neural networks display increasing popularity towards neuromorphic computing. In this review, the memristor-implemented RC systems from the following aspects: architectures, materials, and applications are summarized. It starts with an introduction to the RC structures that can be simulated with memristor blocks. Specific interest then focuses on the dynamic memory behaviors of memristors based on various material systems, optimizing the understanding of the relationship between the relaxation behaviors and materials, which provides guidance and references for building RC systems coped with on-demand application scenarios. Furthermore, recent advances in the application of memristor-based physical RC systems are surveyed. In the end, the further prospects of memristor-implemented RC system in a material view are envisaged.     

基于深度神经网络的多指灵巧手抓取手势优化

基于深度神经网络模型,提出了一种适用于多指灵巧手的抓取手势优化方法。首先,在仿真环境下构建了一个抓取数据集,并在此基础上训练了一个卷积神经网络,依据目标物体单目视觉信息和多指灵巧手抓取位形来预测抓取质量函数,由此可以将多指灵巧手的抓取规划问题转化为使抓取质量最大化的优化问题,进一步,基于深度神经网络中的反向传播和梯度上升算法实现多指灵巧手抓取手势的迭代与优化。在仿真环境中,比较该网络和仿真平台对同一抓取位形的抓取质量评估结果,再利用所提出的优化方法对随机搜索到的初始手势进行优化,比较优化前后手势的力封闭指标。最后,在实际机器人平台上验证本文方法的优化效果,结果表明,本文方法对未知物体的抓取成功率在80%以上,对于失败的抓取,优化后成功的比例达到90%。     

基于机器学习的超声造影分析综述

超声造影（Contrast-enhanced ultrasound, CEUS）通过外周静脉注入超声造影剂,显著增强来自肿瘤微血管的血流信号,便于临床医生以实时、动态的方式评估肿瘤血管生成、周边浸润等,广泛应用于多器官病变诊断、预后评估和治疗方案规划等方面。近年来,以深度学习为代表的机器学习方法快速发展,为动态超声造影智能分析带来新的机遇。深度学习方法很大程度上拓宽了超声造影临床应用范围,提高了其诊疗效能。但与常规超声影像类似,超声造影仍然存在斑点噪声、呼吸运动干扰和标准化程度低等问题,使得动态灌注时间、空间信息挖掘面临挑战。本文系统性回顾了近年来超声造影智能分析相关工作,涵盖良恶性鉴别、恶性分级、疗效预测和诊疗方案选择等方面应用,总结了当前影像组学及深度学习方法在超声造影分析领域的最新进展,并指出当前研究的局限性和未来发展方向。     

Distributed Nash Equilibrium Seeking for General Networked Games With Bounded Disturbances

This paper is concerned with anti-disturbance Nash equilibrium seeking for games with partial information. First, reduced-order disturbance observer-based algorithms are proposed to achieve Nash equilibrium seeking for games with first-order and second-order players, respectively. In the developed algorithms, the observed disturbance values are included in control signals to eliminate the influence of disturbances, based on which a gradient-like optimization method is implemented for each player. Second, a signum function based distributed algorithm is proposed to attenuate disturbances for games with second-order integrator-type players. To be more specific, a signum function is involved in the proposed seeking strategy to dominate disturbances, based on which the feedback of the velocity-like states and the gradients of the functions associated with players achieves stabilization of system dynamics and optimization of players’ objective functions. Through Lyapunov stability analysis, it is proven that the players’ actions can approach a small region around the Nash equilibrium by utilizing disturbance observer-based strategies with appropriate control gains. Moreover, exponential (asymptotic) convergence can be achieved when the signum function based control strategy (with an adaptive control gain) is employed. The performance of the proposed algorithms is tested by utilizing an integrated simulation platform of virtual robot experimentation platform (V-REP) and MATLAB.      

阻尼累加离散GM(1,1)模型及其应用

基于阻尼累加生成算子和离散灰色预测模型的思想,提出一类新的阻尼累加离散GM (1,1)模型,并详细给出模型的推导过程,从理论上分析与经典GM (1,1)模型、离散GM (1,1)模型以及最近提出的阻尼累加GM (1,1)模型的关系,探讨模型的稳定性和数据适用类型分析,并利用量子粒子群优化算法计算出最优阻尼累加参数.最后将所提出模型应用于两个实际案例,结果表明所提出的阻尼累加离散GM (1,1)模型的拟合和预测误差均优于上述基准模型.     

基于自适应遗传学习粒子群算法的多无人机协同任务分配

研究救援场景下的多无人机协同任务分配问题,考虑幸存者所需援助类型的不同,建立更贴合实际的组合优化模型.针对该模型,提出一种自适应遗传学习粒子群算法(adaptive genetic learning particle swarm optimization, AGLPSO).首先,根据无人机与幸存者之间的救援关系,采用一种实向量编码机制处理决策变量约束,以简化模型求解.然后,通过两层级联结构提高算法搜索能力:第1层通过遗传学习策略生成高质量的精英粒子,并对进化停滞的粒子采用精英学习策略进行更新,以跳出局部最优;第2层利用精英粒子指导种群的搜索方向,并根据粒子群的进化速度和粒子的聚集程度,采用自适应进化策略提高算法在不同进化时期的寻优能力.仿真实验表明,所提出的AGLPSO算法能快速、有效地找到合理的救援分配方案.     

APPCorp: a corpus for Android privacy policy document structure analysis

With the increasing popularity of mobile devices and the wide adoption of mobile Apps, an increasing concern of privacy issues is raised. Privacy policy is identified as a proper medium to indicate the legal terms, such as the general data protection regulation (GDPR), and to bind legal agreement between service providers and users. However, privacy policies are usually long and vague for end users to read and understand. It is thus important to be able to automatically analyze the document structures of privacy policies to assist user understanding. In this work we create a manually labelled corpus containing 231 privacy policies (of more than 566,000 words and 7,748 annotated paragraphs). We benchmark our data corpus with 3 document classification models and achieve more than 82% on F1-score.     

考虑冗余系统时变故障率和更新过程的MMC可靠性建模及其应用

针对现有模块化多电平换流器(modular multi-level converter, MMC)可靠性计算中未充分考虑冗余系统故障率时变性和缺乏考虑更新过程,从而不能科学衡量MMC可靠性的问题,提出了一种考虑MMC冗余系统故障率时变性并引入N阶梯更新过程的MMC可靠性建模方法。首先,从冗余程度、冗余方式角度细化MMC冗余系统的分类,建立可靠度与故障率间的数学解析关系来量化表征冗余系统故障率时变的变化特性,分析传统马尔科夫模型所计算的冗余系统故障率过小而导致可靠性计算结果偏高的不合理问题;其次,利用N阶梯故障率取代传统MMC冗余系统的时变故障率,并同时引入更新过程理论推导MMC的平均无故障工作时间(mean time to failure, MTTF)和稳态可用度公式,以此修正传统MMC可靠性参数计算结果偏高的问题。最后,以半桥子模块的MMC为例,验证了所提方法的有效性和可行性。