Shakespeare vs. fletcher: A stylometric analysis by radial basis functions

In this paper we show, for the first time, how Radial Basis Function (RBF) network techniques can be used to explore questions surrounding authorship of historic documents. The paper illustrates the technical and practical aspects of RBF's, using data extracted from works written in the early 17th century by William Shakespeare and his contemporary John Fletcher. We also present benchmark comparisons with other standard techniques for contrast and comparison.David Lowe is Professor of Neural Computing at Aston University, UK. His research interests span from the theoretical aspects of dynamical systems theory and statistical pattern processing, to a wide range of application domains, from financial market analysis (Novel Exploitation of Neural Network Methods in Financial Markets, invited paper,World Conference on Computational Intelligence, vol. VI, pp. 3623–28, 1994) to the artificial nose (Novel Topographic Nonlinear Feature Extraction using Radial Basis Functions for Concentration Coding in the Artificial Nose,3 ^rd IEE International Conference on Artificial Neural Networks, pp. 95–99, Conference Publication number 372, The Institute of Electrical Engineers, 1993).Robert Matthews is a visiting research fellow at Aston University. His research interests include probability, number theory and astronomy. His recent paper inNature (vol. 374, pp. 681–82, 1995) somehow managed to combine all three.     

电动汽车串联型电弧故障检测方法

电弧故障是引发电气火灾的主要原因之一。在电动汽车电气系统中,直流串联电弧故障通常发生在接触点松动或线路连接损坏处,会引起火灾、爆炸等严重事故。为快速、准确地检测电动汽车串联型电弧故障,搭建了电动汽车故障电弧实验平台,采集不同工况下干路电流时间序列并建立了样本库。通过轻量化卷积神经网络,建立了基于改进Mobilenet网络的串联故障电弧检测模型。通过对比分析学习率、网络层数、样本长度,对模型进行了优化。该优化模型通过干路电流可实现电动汽车串联型故障电弧的检测和故障选线,检测准确率达到96.39%,论文为电动汽车电气系统电弧故障检测提供了一种可行性方案。     

基于自注意力机制和CycleGAN的高分三号ScanSAR图像的扇贝效应抑制

高分三号卫星是我国首颗分辨率达到1 m的C波段 多极化合成孔径雷达(synthetic aperture radar,SAR) 卫星,其中扫描 式合成孔径雷达(scan synthetic aperture radar,ScanSAR)模式是高分三号卫星重要的工 作模式之一,由于该模式的工作机制导致生成的图像可能发生扇贝效应,一般呈现为明暗相 间的条纹。本文针对高分三号卫星ScanSAR模式下存在的扇贝效应,提出自注意力机制与循 环一致对抗网络(cycle-consistent adversarial networks,CycleGAN)结合的模型对Scan S AR图像进行处理,从而抑制扇贝效应产生的条纹现象。本文所示方法与传统扇贝效应抑制方 法和深度学习相关算法进行比较,并通过亮度均值、平均梯度等指标进行分析。实验结果表 明,本文方法可以对高分三号ScanSAR图像存在的扇贝效应进行较好的处理,有效抑制图像 的条纹现象,使得图像质量得到提升,具有较大的实用意义。     

A fixed clustering protocol based on random relay strategy for EHWSN

In Energy Harvesting Wireless Sensor Networks (EHWSN), the communication protocol will directly affect the final performance of the network, so it is necessary to study the communication protocol based on EHWSN. In this paper, for the low-cost fixed clustering problem, a fixed clustering protocol RRCEH is based on random relaying. Our proposed RRCEH abandons the inefficient inter-cluster communication method of the traditional fixed clustering protocol. To coordinate the data upload of the cluster head, RRCEH allocates different random relay vectors to each ring area of the network, and combines all the random relay vectors into a random relay matrix of RRCEH. In each communication round, the cluster head node randomly selects its relay target node to send data according to the probability distribution in the random relay vector in the area. For two different cluster head configuration scenarios, by optimizing the random relay matrix, RRCEH can effectively reduce the network's configuration requirements for cluster head energy harvesting capability, thus reducing the deployment cost of EHWSN.     

Face Editing Using Part-Based Optimization of the Latent Space

We propose an approach for interactive 3D face editing based on deep generative models. Most of the current face modeling methods rely on linear methods and cannot express complex and non-linear deformations. In contrast to 3D morphable face models based on Principal Component Analysis (PCA), we introduce a novel architecture based on variational autoencoders. Our architecture has multiple encoders (one for each part of the face, such as the nose and mouth) which feed a single decoder. As a result, each sub-vector of the latent vector represents one part. We train our model with a novel loss function that further disentangles the space based on different parts of the face. The output of the network is a whole 3D face. Hence, unlike part-based PCA methods, our model learns to merge the parts intrinsically and does not require an additional merging process. To achieve interactive face modeling, we optimize for the latent variables given vertex positional constraints provided by a user. To avoid unwanted global changes elsewhere on the face, we only optimize the subset of the latent vector that corresponds to the part of the face being modified. Our editing optimization converges in less than a second. Our results show that the proposed approach supports a broader range of editing constraints and generates more realistic 3D faces.     

Optimized deep learning-based intrusion detection for wireless sensor networks

The technological innovations and wide use of Wireless Sensor Network (WSN) applications need to handle diverse data. These huge data possess network security issues as intrusions that cannot be neglected or ignored. An effective strategy to counteract security issues in WSN can be achieved through the Intrusion Detection System (IDS). IDS ensures network integrity, availability, and confidentiality by detecting different attacks. Regardless of efforts by various researchers, the domain is still open to obtain an IDS with improved detection accuracy with minimum false alarms to detect intrusions. Machine learning models are deployed as IDS, but their potential solutions need to be improved in terms of detection accuracy. The neural network performance depends on feature selection, and hence, it is essential to bring an efficient feature selection model for better performance. An optimized deep learning model has been presented to detect different types of attacks in WSN. Instead of the conventional parameter selection procedure for Convolutional Neural Network (CNN) architecture, a nature-inspired whale optimization algorithm is included to optimize the CNN parameters such as kernel size, feature map count, padding, and pooling type. These optimized features greatly improved the intrusion detection accuracy compared to Deep Neural network (DNN), Random Forest (RF), and Decision Tree (DT) models.     

Covalent Adaptable Microstructures via Combining Two-Photon Laser Printing and Alkoxyamine Chemistry: Toward Living 3D Microstructures

Manufacturing programmable materials, whose mechanical properties can be adapted on demand, is highly desired for their application in areas ranging from robotics, to biomedicine, or microfluidics. Herein, the inclusion of dynamic and living bonds, such as alkoxyamines, in a printable formulation suitable for two-photon 3D laser printing is exploited. On one hand, taking advantage of the dynamic covalent character of alkoxyamines, the nitroxide exchange reaction is investigated. As a consequence, a reduction of the Young´s Modulus by 50%, is measured by nanoindentation. On the other hand, due to its “living” characteristic, the chain extension becomes possible via nitroxide mediated polymerization. In particular, living nitroxide mediated polymerization of styrene results not only in a dramatic increase of the volume (≈8 times) of the 3D printed microstructure but also an increase of the Young's Modulus by two orders of magnitude (from 14 MPa to 2.7 GPa), while maintaining the shape including fine structural details. Thus, the approach introduces a new dimension by enabling to create microstructures with dynamically tunable size and mechanical properties.     

Light-Responsive Programmable Shape-Memory Soft Actuator Based on Liquid Crystalline Polymer/Polyurethane Network

Liquid crystalline polymers (LCPs), especially liquid crystalline elastomers (LCEs) can generate ultrahigh shape change amplitude but has lower mechanical strength. Although some attempts have been tried to improve the mechanical performance of LCE, there are still limitations including complicated fabrication and high actuation temperature. Here, a versatile method is reported to fabricate light-driven actuator by covalently cross-linking polyurethane (PU) into LCP networks (PULCN). This new scheme is distinct from the previous interpenetrating network strategy, the hydrogen bonds and covalent bonds are used in this study to improve the miscibility of non-liquid-crystalline PU and LCP materials and enhance the stability of the composite system. This material not only possesses the shape memory properties of PU but shows shape-changing behavior of LCPs. With a shrinkage ratio of 20% at the phase transition temperature, the prepared materials reached a maximum mechanical strength of 20 MPa, higher than conventional LCP. Meanwhile, the resulting film shows diverse and programmable initial shapes by constructing crosslinking density gradient across the thickness of the film. By integration of PULCN with near-infrared light-responsive polydopamine, local and sequential light control is achieved. This study may provide a new route for the fabrication of programmable and mechanically robust light-driven soft actuator.     

A Multi-Stage Secure IoT Authentication Protocol

The Internet of Things (IoT) is a network of heterogeneous and smart devices that can make decisions without human intervention. It can connect millions of devices across the universe. Their ability to collect information, perform analysis, and even come to meaningful conclusions without human capital intervention matters. Such circumstances require stringent security measures and, in particular, the extent of authentication. Systems applied in the IoT paradigm point out high-interest levels since enormous damage will occur if a malicious, wrongly authenticated device finds its way into the IoT system. This research provides a clear and updated view of the trends in the IoT authentication area. Among the issues covered include a series of authentication protocols that have remained research gaps in various studies. This study applies a comparative evaluation of authentication protocols, including their strengths and weaknesses. Thus, it forms the foundation in the IoT authentication field of study. In that direction, a multi authentication architecture that involves secured means is proposed for protocol authentication. Informal analysis can affect the security of the protocols. Burrows-Abadi-Needham (BAN) logic provides proof of the attainment of mutual authentication. NS3 simulator tool is used to compare the performance of the proposed protocol to verify the formal security offered by the BAN logic.     

多姿态图像生成的行人重识别算法研究

不同行人的高度相似性以及相同行人外观姿态的差异性,使得不同摄像头下的行人重识别面临严峻的挑战。生成对抗网络可以合成新的图像,被认为是解决行人姿态变化的主要技术手段。提出一种基于多姿态图像生成的行人重识别算法,利用生成对抗网络生成不同姿态的行人图像,通过归一化消除姿态的影响,从而大幅度提升行人重识别的整体性能。该行人重识别算法包括多姿态行人图像生成、不同姿态的行人特征提取与融合、距离度量和重排序三部分内容。在Market-1501数据集和DukeMTMC-ReID数据集上的实验证实了所提出算法的有效性,通过与state-of-the-art行人重识别方法比较,展示了多姿态图像生成方法在行人重识别任务中的优越性,同时表明生成行人图像的特征与原始图像的特征是相互补充的。