Splitting and placement of data-intensive applications with machine learning for power system in cloud computing

Aiming to meet the growing demand for observation and analysis in power systems that based on Internet of Things (IoT), machine learning technology has been adopted to deal with the data-intensive power electronics applications in IoT. By feeding previous power electronic data into the learning model, accurate information is drawn, and the quality of IoT-based power services is improved. Generally, the data-intensive electronic applications with machine learning are split into numerous data/control constrained tasks by workflow technology. The efficient execution of this data-intensive Power Workflow (PW) needs massive computing resources, which are available in the cloud infrastructure. Nevertheless, the execution efficiency of PW decreases due to inappropriate sub-task and data placement. In addition, the power consumption explodes due to massive data acquisition. To address these challenges, a PW placement method named PWP is devised. Specifically, the Non-dominated Sorting Differential Evolution (NSDE) is used to generate placement strategies. The simulation experiments show that PWP achieves the best trade-off among data acquisition time, power consumption, load distribution and privacy preservation, confirming that PWP is effective for the placement problem.     

An evaluation of contrast enhancement techniques for mammographic breast masses.

The main aim of this paper is to propose a novel set of metrics that measure the quality of the image enhancement of mammographic images in a computer-aided detection framework aimed at automatically finding masses using machine learning techniques. Our methodology includes a novel mechanism for the combination of the metrics proposed into a single quantitative measure. We have evaluated our methodology on 200 images from the publicly available digital database for screening mammograms. We show that the quantitative measures help us select the best suited image enhancement on a per mammogram basis, which improves the quality of subsequent image segmentation much better than using the same enhancement method for all mammograms.     

On the reliability of Landsat TM for estimating forest variables byregression techniques: a methodological analysis

In order to build models that relate thematic mapper (TM) imagery to field forest variables, several regression techniques, such as the ones based on the Mallows' C_p and the adjusted R² statistics, were applied. Nevertheless, although the best created models had good fittings (R²>0.65) apparently supported by a clear statistical significance (p<0.0001), later trials tested with additional plots showed that these models were, in fact, nonrobust models (models with very low-predictive capabilities). Two factors were pointed out as causes of these inconsistencies between predicted and observed values: a relatively small number of available field plots and a relatively high number of possible independent variables. Actually, different trials suggested much lower fittings for the expected “really” predictive models. Some restrictions of TM satellite data, such as its radiometric, spectral, and spatial limitations, together with restrictions arising from gathering and processing of field data, might have led to these poor relations. This study shows the need for guarantees stronger than the usual ones before concluding that there is a clear possibility of using satellite information to estimate forest parameters by means of regression techniques     

A method for dynamics identification for haptic display of the operating feel in virtual environments

Realistic dynamics models are important for haptic display for virtual reality systems. Such dynamic models are desirably obtained via experimental identification. However, traditional dynamics identification methods normally require large sized training data sets, which maybe difficult to meet in many practical applications. To obtain the dynamics models, we present, in this paper, an identification method using support vector machines regression algorithm which is more effective than traditional methods for sparse training data. This method can be used as a generic learning machine or as a special learning technique that can make full use of the available knowledge about the dynamics structure. The experimental results show the application of our method for identifying friction models for haptic display.     

以风险投资促进卫星数据通信行业的发展

卫星数据业务可分为“卫星专网业务”、“卫星模式数据包分发业务”、“卫星模式网站推送业务”和“卫星互联网接入业务”等。卫星数据业务具有许多自己的特点和优势，但面临着投资不足和经营规模偏小的问题。风险投资作为一种在我国较新的投资模式．将为卫星数据业务的发展注入活力。     

S/X/Ka频段天伺馈系统关键技术分析

采用Ka频段进行星地数据传输是解决数据传输频带资源紧张的有效技术途径,将成为星地数据传输的发展方向。针对目前国内外对S/X/Ka地面接收系统缺乏深入的技术研究和工程化产品的问题,分析研究了S/X/Ka天伺馈系统的关键技术,提出了主要技术指标需求及关键技术实现途径。研究结果可为系统的设计、研制加工等提供技术参考。     

Automatic CRP mapping using nonparametric machine learning approaches

This paper studies an uneven two-class unsupervised classification problem of satellite imagery, i.e., the mapping of U.S. Department of Agriculture's (USDA) Conservation Reserve Program (CRP) tracts. CRP is a nationwide program that encourages farmers to plant long-term, resource conserving covers to improve soil, water, and wildlife resources. With recent payments of nearly US $1.6 billion for new enrollments (2002 signup), it is imperative to obtain accurate digital CRP maps for management and evaluation purposes. CRP mapping is a complex classification problem where both CRP and non-CRP areas are composed of various cover types. Two nonparametric machine learning approaches, i.e., decision tree classifier (DTC) and support vector machine (SVMs) are implemented in this work. Specifically, considering the importance of CRP classification sensitivity, a new DTC pruning method is proposed to increase recall. We also study two SVM relaxation approaches to increase recall. Moreover, a localized and parallel framework is suggested in order to efficiently deal with the large-scale CRP mapping need. Simulation results validate the applicability of the suggested framework and proposed techniques.     

基于复述增广的医疗领域机器翻译

医疗机器翻译对于跨境医疗、医疗文献翻译等应用具有重要价值.汉英神经机器翻译依靠深度学习强大的建模能力和大规模双语平行数据取得了长足的进步.神经机器翻译通常依赖于大规模的平行句对训练翻译模型.目前,汉英翻译数据主要以新闻、政策等领域数据为主,缺少医疗领域的数据,导致医疗领域的汉英机器翻译效果不佳.针对医疗垂直领域机器翻译...     

Geometric versus geographic models for the estimation of an FTTH deployment

Optical access networks provide a future proof platform for a wide range of services, and today, several operators are deploying fibre to the home (FTTH) networks. Installing an FTTH infrastructure, however, involves very high investment cost. Therefore, a good estimation of the investment cost is important for building a successful business strategy and, consequently, to speed up the FTTH penetration. In this paper, for calculating the amount of cable and fibre in the outside plant together with the associated civil works, and the number of required network elements, two different approaches are investigated: (1) geometric modelling of the fibre plant based on approximate mathematical models and (2) geographic modelling of the fibre plant based on map-based geospatial data. The results obtained from these two approaches can then be used as input for preliminary investment cost calculations and/or techno-economic evaluations. Compared to more complex and accurate geographic modelling, we verify that especially with uneven population density and irregular street system, simple geometric models do not provide accurate results. However, if no geospatial data is available or a fast calculation is desired for a first estimation, geometric models definitely have their relevance. Based on the case studies presented in this paper, we propose some important guidelines to improve the accuracy of the geometric models by eliminating their main distortion factors.     

A "Reef-Up" approach to classifying coral habitats from IKONOS imagery

Monitoring coral reef benthos with satellites has typically followed a "sensor-down" approach, with the classification algorithm driven by statistics derived from the imagery. I adopt a "reef-up" method, drawing on statistics derived from hyperspectral optical field measurements of substrate reflectance to train image classification. In order to calibrate the satellite data with direct physical measurements of reflectivity, it is necessary to process both the imagery and in situ data to common units of albedo. Building upon a proof-of-concept study conducted by the author in the Red Sea, the link is made by correcting the remote sensing data for the effect of varying bathymetry using in situ measurement of water column optical properties and a digital elevation model constructed from a vessel-based acoustic survey, thereby yielding units of substrate reflectance. Extensive ground verification of the predictive benthic habitat map resulting from image classification showed that eight substrate classes were resolved with an overall accuracy of 69% down to a depth of 6 m, including live and dead coral framework. As compared to conventional from-image classification techniques, the reef-up method offers the potential for higher thematic accuracy while maintaining a greater degree of flexibility for repeat survey using platforms of higher spectral and spatial resolution, expected to come online in the near future. The fact that image acquisition and optical ground-truthing did not occur concurrently, is of particular relevance in confirming that in situ measurements can be made independent of image acquisition and retrospectively linked to appropriate substrate classes. Considering the wealth of hyperspectral data already acquired for shallow reef facies, the work highlights the potential of the reef-up approach for quantifying substrate distribution in coral environments using both air- and spaceborne platforms.     

Computational functional genomics

The exponential growth of the publicly available data has transformed biology into an information rich science that provides new and interesting applications for the machine learning community. In this article, the author presents some specific examples regarding the possibility of representing biological data in a machine-learning framework as well as the contributions these representations impart to both the prediction and discovery of the biological function. The paper also illustrates the proper feature selection critical to the success of the of a particular computational functional genomics approach.     

基于卫星数据和深度学习方法预测京津冀地区地表 NO2浓度

二氧化氮 (NO2) 对人类健康和气候变化有着诸多负面影响, 随着中国城镇化和工业化进程加速, NO2污染成 为人们日益关注的问题。相关研究表明传统的单个站点监测结果只能代表数平方公里内的污染物水平, 无法提供大 尺度的污染物分布信息。相比于站点监测, 卫星遥感可以提供大尺度且时空连续的数据, 为研究大气污染提供了新 的角度。基于哨兵5P卫星的NO2柱浓度数据和气象、人口密度等其他辅助数据, 构建了对地表NO2进行预测的深度神 经网络 (DNN) 模型。并使用两种交叉验证方法对该模型进行验证。在基于样本的验证中, 模型的决定系数 R2、均方 根误差 (RMSE) 和平均预测误差 (MAE) 分别为0.80、7.72 μg/m3和 5.31 μg/m3;在基于站点的验证中, 模型的R2、RMSE 和MAE分别为 0.74、8.95 μg/m3和6.01 μg/m3, 两种验证结果都表明DNN模型具有较好的整体预测能力和空间泛化 性。此外, 与经典的地学统计和机器学习算法对比结果表明DNN预测性能优于其它方法。最后用训练好的模型获得 了京津冀地区 0.1° 的NO2分布图。     

Security from space

Satellites have gained a prominent role in the US's toughened homeland protection plan and many companies are set to benefit. Satellites have an important role in monitoring and protecting infrastructure and many companies are planning to capitalise on America's emergent homeland security market. According to an October 2002 study by the Electronics and IT Association, they could be competing for up to /spl divide/n-worth of business, which could grow to $12bn by 2008. Of course, only a small percentage of this would go to satellite companies, but this has not stemmed the flow of new ideas. As part of the Homeland Security initiative, NASA and the Department of Transportation are considering how commercial satellite imagery could be applied to other potential terrorist targets such as airports. By developing interactive digital maps, they hope to illustrate their use not only in planning airport security improvements, but also in guiding rescuers through the devastation following an incident. Eventually, it is envisaged that real-time ground radar data could be incorporated to help detect suspicious aircraft or vehicle movements.     

Deep learning methods for fingerprint-based indoor positioning: a review

ABSTRACT

Outdoor positioning systems based on the Global Navigation Satellite System have several shortcomings that have deemed their use for indoor positioning impractical. Location fingerprinting, which utilizes machine learning, has emerged as a viable method and solution for indoor positioning due to its simple concept and accurate performance. In the past, shallow learning algorithms were traditionally used in location fingerprinting. Recently, the research community started utilizing deep learning methods for fingerprinting after witnessing the great success and superiority these methods have over traditional/shallow machine learning algorithms. This paper provides a comprehensive review of deep learning methods in indoor positioning. First, the advantages and disadvantages of various fingerprint types for indoor positioning are discussed. The solutions proposed in the literature are then analyzed, categorized, and compared against various performance evaluation metrics. Since data is key in fingerprinting, a detailed review of publicly available indoor positioning datasets is presented. While incorporating deep learning into fingerprinting has resulted in significant improvements, doing so, has also introduced new challenges. These challenges along with the common implementation pitfalls are discussed. Finally, the paper is concluded with some remarks as well as future research trends.     

基于机器学习的大视场星敏感器畸变在轨标定技术

随着遥感卫星在轨任务复杂性的不断提升,对卫星精度的要求也不断提高。星敏感器是星上精度最高态敏感器,因而其在轨标定是提高精度的有效手段。由于大视场星敏感器的镜头畸变复杂,目前广泛采用的基于星对角距的最小二乘法存在一定局限性。因此提出一种基于机器学习的星敏感器在轨标定算法,该方法结合机器学习预测建模思想,通过构造特征建立镜头畸变模型,并结合主成分分析方法进行冗余特征的消除,最后从星角距和模型泛化能力两方面对标定效果进行评价。仿真结果表明:算法对镜头畸变程度较大的星敏感器有良好的校正效果,标定精度始终能保持在0.8内,与目前几种主流算法相比,具有精度高,鲁棒性好等优点。     

Simulation of error sources in digital channels

A general approach to error-source simulation in digital channels is discussed. It is shown that the stochastic sequential machine (SSM) model is general enough to describe error-source statistics in digital communication channels. The SSM model is capable of describing both the correlation between errors in a channel (bursts of errors) and the correlation between errors in different channels (crosstalk). Physical causes of error burstiness in satellite channels are considered, and it is shown that the SSM model can account for differential encoding, scrambling, forward error correction, intersymbol interference, nonlinear signal distortion, adjacent channel interference, modem defects, etc. SSM models of the satellite channel with differential and convolutional codes are simulated. The results of simulation agree with the experimental data for the actual channels. Analytical methods for determining the performance characteristics of SSM-modeled systems are developed     

5G引领数字技术赋能农业互联网快速发展

随着“新基建”的发展，我国数字乡村建设迎来新高潮，建设数字乡村既是乡村振兴的战略方向，也是建设数字中国的重要内容。农业互联网是数字乡村建设的关键环节，伴随5G等数字技术不断深入农业生产的各个领域，我国农业互联网进入了快速发展的新阶段。重点围绕5G等数字技术为农业互联网带来的新变革，通过5G、卫星遥感、无人机、人工智能、机器视觉等推动农业生产经营数字化转型，对我国农业互联网未来的发展现状及趋势进行了深入探讨。     

Framework for TCAD augmented machine learning on multi-I-V characteristics using convolutional neural network and multiprocessing

In a world where data is increasingly important for making breakthroughs,microelectronics is a field where data is sparse and hard to acquire.Only a few entities have the infrastructure that is required to automate the fabrication and testing of semiconductor devices.This infrastructure is crucial for generating sufficient data for the use of new information technolo-gies.This situation generates a cleavage between most of the researchers and the industry.To address this issue,this paper will introduce a widely applicable approach for creating custom datasets using simulation tools and parallel computing.The multi-I-V curves that we obtained were processed simultaneously using convolutional neural networks,which gave us the abil-ity to predict a full set of device characteristics with a single inference.We prove the potential of this approach through two con-crete examples of useful deep learning models that were trained using the generated data.We believe that this work can act as a bridge between the state-of-the-art of data-driven methods and more classical semiconductor research,such as device en-gineering,yield engineering or process monitoring.Moreover,this research gives the opportunity to anybody to start experi-menting with deep neural networks and machine learning in the field of microelectronics,without the need for expensive experi-mentation infrastructure.     

Target-Centered Models and Information-Theoretic Segmentation for Automatic Target Recognition

We present an approach to automatic target recognition (ATR) from synthetic aperture radar (SAR) imagery which combines advantages of both model-based and template-based approaches. Prior observations are used to estimate the statistical properties of reflectance over regions in the training scene. These target-centered statistical models can then be used to estimate the statistical properties of sensor output for arbitrary pose. Two-sided hypothesis tests which are maximally powerful at the most likely alternative are developed in a information-theoretic framework to address target model segmentation and confuser rejection. Segmentation of target from clutter is performed in the target-centered coordinate system using all prior observations to produce a consistent segmentation over all poses. We present performance and computation complexity results as a function of segmentation threshold, confuser-rejection threshold, and operating conditions for publicly available SAR data.     

基于卫星参数预测的星载SAR图像定位方法研究

该文提出了一种基于卫星参数预测的无(少)地面控制点的星载SAR图像的定位方法。该方法利用待校正影像相邻景的成像参数,同时建立预测模型,内插或外推待校正SAR图像的成像参数,从而通过SAR共线方程模型实现无(少)地面控制点的星载SAR图像的定位。文中利用RADARSAT影像进行实验,取得了6～7个像元校正精度。