智能变电站设备管控大数据分析系统研究

结合数据挖掘、大数据技术在电力系统中的应用现状，分析和设计了一种智能变电站设备管控大数据分析系统。对变电站设备运行状态的大数据特征及基本框架进行了分析，并重点阐述了变电站设备运行状态大数据分析系统的数据集成与预处理、数据存储与处理、设备状态评估模型以及数据可视化展示。实验结果表明，所设计的大数据分析系统能够大幅度提升变电站设备数据分析智能化水平，为变电站管控稳定运行提供更加有效和实用性的技术支撑。     

A two-stage vision-based method for measuring the key parameters of ball screws

Ball screws are crucial for improving the reliability and interchangeability of transmission mechanical systems; however, existing contact measurement methods that utilise stylus contact are not efficient, which precludes their use for rapid in-situ geometry evaluation. This paper presents a vision-based two-stage method for rapid measurement of key parameters (raceway arc radii and centre distance) of ball screws. The edge contour information is extracted from the acquired image using the dual-tree complex wavelet transform and non-maximal suppression. In the matching stage, a shape-matching algorithm is used for detecting approximate geometrical centres of raceway arcs. The refinement stage, on the other hand, is implemented for acquiring precise dimensional results. Furthermore, the method of averaging multiple measurements is performed to suppress random noise. A comparative experiment is presented to validate the robustness of the proposed method. Based on experimental results, the calculated mean absolute errors in the measurement of the two raceway arc radii and the centre distance are found to be 0.0082 mm, 0.0079 mm and 0.0055 mm, respectively. This study therefore paves the way for key parameter measurement without removing ball screws.     

Anti-Inflammatory Treatment with FTY720 Starting after Onset of Symptoms Reverses Synaptic Deficits in an AD Mouse Model

Therapeutic approaches providing effective medication for Alzheimer’s disease (AD) patients after disease onset are urgently needed. Previous studies in AD mouse models suggested that physical exercise or changed lifestyle can delay AD-related synaptic and memory dysfunctions when treatment started in juvenile animals long before onset of disease symptoms, while a pharmacological treatment that can reverse synaptic and memory deficits in AD mice was thus far not identified. Repurposing food and drug administration (FDA)-approved drugs for treatment of AD is a promising way to reduce the time to bring such medication into clinical practice. The sphingosine-1 phosphate analog fingolimod (FTY720) was approved recently for treatment of multiple sclerosis patients. Here, we addressed whether fingolimod rescues AD-related synaptic deficits and memory dysfunction in an amyloid precursor protein/presenilin-1 (APP/PS1) AD mouse model when medication starts after onset of symptoms (at five months). Male mice received intraperitoneal injections of fingolimod for one to two months starting at five to six months. This treatment rescued spine density as well as long-term potentiation in hippocampal cornu ammonis-1 (CA1) pyramidal neurons, that were both impaired in untreated APP/PS1 animals at six to seven months of age. Immunohistochemical analysis with markers of microgliosis (ionized calcium-binding adapter molecule 1; Iba1) and astrogliosis (glial fibrillary acid protein; GFAP) revealed that our fingolimod treatment regime strongly down regulated neuroinflammation in the hippocampus and neocortex of this AD model. These effects were accompanied by a moderate reduction of Aβ accumulation in hippocampus and neocortex. Our results suggest that fingolimod, when applied after onset of disease symptoms in an APP/PS1 mouse model, rescues synaptic pathology that is believed to underlie memory deficits in AD mice, and that this beneficial effect is mediated via anti-neuroinflammatory actions of the drug on microglia and astrocytes.     

神经网络全局势函数在多相催化中的应用

当今的多相催化研究需要新的技术和方法从原子尺度上表征活性中心结构和反应中间体。本文作者课题组近期开发了理论模拟新技术来探索催化剂活性位点结构，即基于神经网络势函数的大规模原子模拟（LASP）软件中实现的全局神经网络势函数计算方法。本文介绍了该方法可以显著降低催化体系的计算代价，而维持与密度泛函理论同一级别的计算精度，从而解决多相催化中的许多复杂问题。本文对神经网络势函数方法的实现细节和目前已实现的应用场景进行了详细介绍。神经网络势函数可以用来预测材料晶体结构，理解高压氢化条件下TiO₂表面的结构演化和确定三元氧化物ZnCrO晶相中合成气制甲醇活性位点。最后文章分析了神经网络势函数的局限性和今后可能的三个研究方向，即材料性质预测、多元素体系神经网络势函数构造和化学反应拟合。     

Arabic sign language intelligent translator

ABSTRACT

Arabic sign language (ArSL) is method of communication between deaf communities in Arab countries; therefore, the development of systemsthat can recognize the gestures provides a means for the Deaf to easily integrate into society. In this research we implemented a computational structurefor an intelligent interpreter that automatically recognizes the isolated dynamic gestures. The proposed system recognizes and translates gesturesperformed with one or both hands. It comprises five subsystems, building dataset, video processing, feature extraction, mapping between ArSL and Arabictext, and text generation. To apply the system, 100-signs of ArSL was used, which was applied on 1500 video files. It's were divided into five classes:alphabet, numbers, "prepositions, pronouns and question words", Arabic life expressions, and "nouns and verbs". The evaluation indicated that thesystem automatically recognizes and translates isolated dynamic ArSL gestures by highly accurate manner. The results showed that the system accuracy is 95.8%.     

Improvement of Stochastic Competitive Learning for Social Network

As an unsupervised learning method, stochastic competitive learning is commonly used for community detection in social network analysis. Compared with the traditional community detection algorithms, it has the advantage of realizing the timeseries community detection by simulating the community formation process. In order to improve the accuracy and solve the problem that several parameters in stochastic competitive learning need to be pre-set, the author improves the algorithms and realizes improved stochastic competitive learning by particle position initialization, parameter optimization and particle domination ability self-adaptive. The experiment result shows that each improved method improves the accuracy of the algorithm, and the F1 score of the improved algorithm is 9.07% higher than that of original algorithm.     

Applying Feature-Weighted Gradient Decent K-Nearest Neighbor to Select Promising Projects for Scientific Funding

Due to its outstanding ability in processing large quantity and high-dimensional data, machine learning models have been used in many cases, such as pattern recognition, classification, spam filtering, data mining and forecasting. As an outstanding machine learning algorithm, K-Nearest Neighbor (KNN) has been widely used in different situations, yet in selecting qualified applicants for winning a funding is almost new. The major problem lies in how to accurately determine the importance of attributes. In this paper, we propose a Feature-weighted Gradient Decent K-Nearest Neighbor (FGDKNN) method to classify funding applicants in to two types: approved ones or not approved ones. The FGDKNN is based on a gradient decent learning algorithm to update weight. It updatesthe weight of labels by minimizing error ratio iteratively, so that the importance of attributes can be described better. We investigate the performance of FGDKNN with Beijing Innofund. The results show that FGDKNN performs about 23%, 20%, 18%, 15% better than KNN, SVM, DT and ANN, respectively. Moreover, the FGDKNN has fast convergence time under different training scales, and has good performance under different settings.     

Image Super-Resolution Based on Generative Adversarial Networks: A Brief Review

Single image super resolution (SISR) is an important research content in the field of computer vision and image processing. With the rapid development of deep neural networks, different image super-resolution models have emerged. Compared to some traditional SISR methods, deep learning-based methods can complete the superresolution tasks through a single image. In addition, compared with the SISR methods using traditional convolutional neural networks, SISR based on generative adversarial networks (GAN) has achieved the most advanced visual performance. In this review, we first explore the challenges faced by SISR and introduce some common datasets and evaluation metrics. Then, we review the improved network structures and loss functions of GAN-based perceptual SISR. Subsequently, the advantages and disadvantages of different networks are analyzed by multiple comparative experiments. Finally, we summarize the paper and look forward to the future development trends of GAN-based perceptual SISR.     

A Novel Beam Search to Improve Neural Machine Translation for English-Chinese

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, overcoming the weaknesses of conventional phrase-based translation systems. Although NMT based systems have gained their popularity in commercial translation applications, there is still plenty of room for improvement. Being the most popular search algorithm in NMT, beam search is vital to the translation result. However, traditional beam search can produce duplicate or missing translation due to its target sequence selection strategy. Aiming to alleviate this problem, this paper proposed neural machine translation improvements based on a novel beam search evaluation function. And we use reinforcement learning to train a translation evaluation system to select better candidate words for generating translations. In the experiments, we conducted extensive experiments to evaluate our methods. CASIA corpus and the 1,000,000 pairs of bilingual corpora of NiuTrans are used in our experiments. The experiment results prove that the proposed methods can effectively improve the English to Chinese translation quality.     

Image and Feature Space Based Domain Adaptation for Vehicle Detection

The application of deep learning in the field of object detection has experienced much progress. However, due to the domain shift problem, applying an off-the-shelf detector to another domain leads to a significant performance drop. A large number of ground truth labels are required when using another domain to train models, demanding a large amount of human and financial resources. In order to avoid excessive resource requirements and performance drop caused by domain shift, this paper proposes a new domain adaptive approach to cross-domain vehicle detection. Our approach improves the cross-domain vehicle detection model from image space and feature space. We employ objectives of the generative adversarial network and cycle consistency loss for image style transfer in image space. For feature space, we align feature distributions between the source domain and the target domain to improve the detection accuracy. Experiments are carried out using the method with two different datasets, proving that this technique effectively improves the accuracy of vehicle detection in the target domain.