DCGAN Based Spectrum Sensing Data Enhancement for Behavior Recognition in Self-Organized Communication Network

Communication behavior recognition is an issue with increasingly importance in the antiterrorism and national defense area.However,the sensing data obtained in actual environment is often not sufficient to accurately analyze the communication behavior.Traditional means can hardly utilize the scarce and crude spectrum sensing data captured in a real scene.Thus,communication behavior recognition using raw sensing data under smallsample condition has become a new challenge.In this paper,a data enhanced communication behavior recognition(DECBR)scheme is proposed to meet this challenge.Firstly,a preprocessing method is designed to make the raw spectrum data suitable for the proposed scheme.Then,an adaptive convolutional neural network structure is exploited to carry out communication behavior recognition.Moreover,DCGAN is applied to support data enhancement,which realize communication behavior recognition under small-sample condition.Finally,the scheme is verified by experiments under different data size.The results show that the DECBR scheme can greatly improve the accuracy and efficiency of behavior recognition under smallsample condition.

Spatiotemporal characteristics of the sea level anomaly in the Kuroshio Extension using a self-organizing map

Satellite altimeter SSH data in the Kuroshio Extension （KE） region gathered during the period January 1993 to December 2014 are analyzed using self-organizing map （SOM） analysis. Four spatial patterns （SOM1, SOM2, SOM3, and SOM4） are extracted, and the corresponding time series are used to characterize the variation of the sea level anomaly. Except in some individual months, SOM1 and SOM2 with single-branch jet structures appear alternately during the periods 1993-1998 and 2002-2011. However, during 1999-2001 and 2012-2014, SOM3 and SOM4 with double-branch jet structures are dominant.The sea level anomalies exhibit interannual variations, while the KE stream demonstrates decadal variation. For SOM1, the change in the KE path is less evident, although the KE jet is strong and narrow. For SOM2, the KE jet is weakened and widened and its jet axis moves towards the southwest. Compared with the SOM3, for SOM4 the trough and ridge in the upstream KE region are deeper in the northeast-southwest direction, and accompanied by a jet weakening and splitting.This study shows that SOM analysis is a useful approach for characterizing KE variability.

The State of the Kenyan Cotton Growing Industry

From the early 1960s to late 1980s, the Kenyan cotton growing industry played a vital role in the Kenyan economy in terms of provision of employment and creation of wealth in the rural areas. It also played a central role in the textile industry which was thriving during the above mentioned period. Over the years, cotton production in Kenya has fallen steadily, such that by the year 2000, the country experienced a severe cotton fiber deficit. This study was undertaken to investigate the trend of the cotton growing industry in Kenya. Selected aspects of the industry like cost of production, cotton seed distribution, the operation of cotton gins and the quality of cotton lint were considered. Kohonen Self Organizing Maps （SOM） and K-means clustering techniques were used in data analysis. The results of this study show that Kenyan cotton farmers produced seed cotton at a break-even price of US $ 0.31 per kilogram, while the price offered was US $ 0.29 per kilogram.

Advances in adaptive nonlinear manifolds and dimensionality reduction

Recent decades have witnessed a much increased demand for advanced,effective and efficient methods and tools for analyzing,understanding and dealing with data of increasingly complex,high dimensionality and large volume.Whether it is in biology,neuroscience,modern medicine and social sciences or in engineering and computer vision,data are being sampled,collected and cumulated in an unprecedented speed.It is no longer a trivial task to analyze huge amounts of high dimensional data.A systematic,automated way of interpreting data and representing them has become a great challenge facing almost all fields and research in this emerging area has flourished.Several lines of research have embarked on this timely challenge and tremendous progresses and advances have been made recently.Traditional and linear methods are being extended or enhanced in order to meet the new challenges.This paper elaborates on these recent advances and discusses various state-of-the-art algorithms proposed from statistics,geometry and adaptive neural networks.The developments mainly follow three lines:multidimensional scaling,eigen-decomposition as well as principal manifolds.Neural approaches and adaptive or incremental methods are also reviewed.In the first line,traditional multidimensional scaling(MDS)has been extended not only to be more adaptive such as neural scale,curvilinear component analysis(CCA)and visualization induced self-organizing map(ViSOM)for online learning,but also to be more local scaling such as Isomap for enhanced flexibility for nonlinear data sets.The second line extends linear principal component analysis(PCA)and has attracted a huge amount of interest and enjoyed flourishing advances with methods like kernel PCA(KPCA),locally linear embedding(LLE)and Laplacian eigenmap.The advantage is obvious:a nonlinear problem is transformed into a linear one and a unique solution can then be sought.The third line starts with the nonlinear principal curve and surface and links up with adaptive neural network approaches such as self-organizing map(SOM)and ViSOM.Many of these frameworks have been further improved and enhanced for incremental learning and mapping function generalization.This paper discusses these recent advances and their connections.Their application issues and implementation matters will also be briefly enlightened and commented on.