时间序列相似性度量的面积距离方法的研究

针对现有的一些时间序列相似性度量函数存在的问题,在时间序列分段线性表示的基础上,提出了一种新的基于面积的度量方法。分段后的时间序列,用对齐法解决时间序列模式之间长度可能不相等的问题,再通过平移,将相交的两线段所围成的面积,作为相似性度量的函数。该方法与现有的一些相似性度量方法进行比较,并且通过人工模拟数据和真实的股票数据进行实验,证明了该方法能够更好地进行相似性搜索,并且较其他的方法,更合理,有效。     

图谱在歌唱教学中的“活用”

图谱是指根据歌曲的结构,运用符号、图画、线条等编辑起来,绘制成幼儿所能认知的图。图谱可以帮助幼儿理解感受歌曲,是幼儿园歌唱教学中常用的一种教学策略。幼儿园歌唱活动中图谱设计与运用的实践研究,是指在幼儿园的歌唱教学活动中,对歌曲教学图谱设计原则及运用方法进行的实践研究。本文从多元化设计图谱、灵活运用图谱、有效体现图谱三个方面阐述图谱在歌唱活动中的灵活运用。     

“金奏”探

在周代的乐器分类中,＂金＂乃＂八音＂之首。＂金＂主要是指钟类乐器,＂金奏＂当是指敲击钟、镈乐器以奏乐。＂金奏＂是至礼备乐,一般场合是不能随便演奏的,它在中国古代是地位与权力的象征,与鼎有同样重要的意义。＂金奏＂乃周代的礼乐重器,在周代的音乐生活中占有十分重要的地位。本文拟在已有的文献资料和音乐考古资料的基础上对周代＂金奏＂的乐器种类与组合、形制演变、音乐性能等方面进行探索,以期进一步了解周代的用乐制度。     

动态时间弯曲技术支持下时序NDVI数据的耕地分布信息提取

我国耕地保护形势十分严峻,及时获取耕地现状信息对耕地保护工作的开展具有重要参考意义。文章探讨了动态时间弯曲技术在时序NDVI数据的耕地分布信息提取中的可行性,并以江苏省苏南地区为实验区,用2010年MODIS NDVI时间序列数据进行耕地提取实验。首先使用频域低通滤波对时序NDVI数据进行重构,抑制大气、光照等噪声的影响,接着选取耕地训练样本,构建耕地参考时间序列,然后根据动态时间弯曲（DTW）方法计算待分类像元时间序列与耕地参考时间序列的相似性程度,对计算结果使用阈值分割,得到研究区耕地信息。实验中耕地提取结果正确率达84.08%,完整率达85.68%,证实了该方法的适用性。研究表明,基于时序NDVI数据相似性分析可以快速有效提取大面积耕地信息,为农业政策的制定提供参考依据。     

Hearing the irrational: music and the development of the modern concept of number

Because the modern concept of number emerged within a quadrivium that included music alongside arithmetic, geometry, and astronomy, musical considerations affected mathematical developments. Michael Stifel embedded the then-paradoxical term "irrational numbers" (numerici irrationales) in a musical context (1544), though his philosophical aversion to the "cloud of infinity" surrounding such numbers finally outweighed his musical arguments in their favor. Girolamo Cardano gave the same status to irrational and rational quantities in his algebra (1545), for which his contemporaneous work on music suggested parallels and empirical examples. Nicola Vicentino's attempt to revive ancient "enharmonic" music (1555) required and hence defended the use of "irrational proportions" (proportiones inrationales) as if they were numbers. These developments emerged in richly interactive social and cultural milieus whose participants interwove musical and mathematical interests so closely that their intense controversies about ancient Greek music had repercussions for mathematics as well. The musical interests of Stifel, Cardano, and Vicentino influenced their respective treatments of "irrational numbers." Practical as well as theoretical music both invited and opened the way for the recognition of a radically new concept of number, even in the teeth of paradox.     

旋律是音乐的灵魂

旋律亦称曲调,是音乐的基本要素,经过艺术构思而形成的若干乐音的有组织、有节奏的和谐运动。它是建立在一定的调式和节拍的基础上,按一定的音高、时值和音量构成的、具有逻辑因素的单声部进行的。     

Efficient customer segmentation in digital marketing using deep learning with swarm intelligence approach

Nowadays, Artificial Intelligence (AI) based modeling is the major consideration to build efficient, automated, and smart systems for our today's needs. Many companies are benefited from these modeling methods for their marketing efforts. Each firm has expected to increase its product development in an innovative way to improve its business growth. Successful firm marketing is to offer the right product to the right person at the right time. To market the product to the customer successfully, it is needed to segment the customer by finding their behavioral patterns. The customer behaviors and their purchasing patterns are used to generate profit for the company. Customer segmentation is the process of grouping customers based on commonalities. Developing an efficient AI-based customer segmentation to improve digital marketing growth is a challenging task. In this paper, an unsupervised deep learning model called a Self-organizing map with an Improved social spider optimization approach has been used for efficient customer segmentation. The customer data are analyzed by a feature engineering process using a swarm intelligence model called Modified social spider optimization to select the behavioral features of the customer. Then, the customers are clustered using Self Organizing neural network (SONN). Based on the clusters, the customers are classified using the Deep neural network (DNN) model. The experimental results prove the performance of the proposed model with high clustering and segmentation capability to improve the business profit in marketing.     

Mining movies for song sequences with video based music genre identification system

Musical sequences with actors dancing and lip-synching to songs sung by playback singers are integral parts, particularly of South Asian movies. Fans seek out movies for their songs and they often seek songs of a particular genre. In fact, song and dance sequence of South Asian movies are an industry of their own. Given the huge numbers of movies produced in South Asia over the past decades, most of which are in digital archives, it is an important problem to automatically extract and categorise their musical sequences. This paper proposes a system for musical sequences extraction from movies. Our method invokes an SVM-based classifier and makes as well a novel application of probabilistic timed automaton to distinguish musical sequences from non-musical. Our system analyses both audio and video signals to give a classifier that not only extracts musical sequences from movies but identifies their genre. We achieved a recall of 93.24% with precision of 87.34% in song extraction when applied on 10 popular Bollywood movies. An accuracy of 89.5% has been achieved on Bollywood song genre identification.     

Dependence measures for model selection in singular spectrum analysis

Selection of optimal dimension of trajectory matrix in singular spectrum analysis plays an important role in signal reconstruction from noisy time series. A noisy time series is embedded into a Hankel matrix and the dimension of this matrix depends on the window length considered for a time series. The window length requirement of a time series depends on its underlying data generating mechanism. Since the number of columns in a Hankel structured trajectory matrix is a function of number of rows (window length), dimension dependency occurs naturally in the trajectory matrix and this dependency is characterized by the statistical properties of a time series. In this paper, we develop an entropy based dimension dependency measure that accounts for changes in information content in the matrix in response to changes in window length for a time series. We examine the performance of this measure by using simulation experiments and analyzing real data sets. Results obtained from simulation experiments show that the dimension dependency measure finds reasonably meaningful dimension of the trajectory matrix and provides better forecasting outcome when applied to some popular climatic time series and production indices.     

图像的增强与分割方法研究

以图像增强与分割这两个计算机视觉中最具基础性质的研究方向为内容,深入研究了红外序列图像的增强,以及一般图像的分割问题.在图像增强方面,提出了一种基于模型的远红外序列图像自适应增强算法(ASTHF).该算法保持了原有算法的良好效果和计算效率,从而达到了视觉效果和运算速度的良好统一.在图像分割方面,提出了一种综合利用边缘和区域信息的图像分割方法--基于尺度空间的区域竞争一般框架(GSRC).通过将被误标记可能性小的像素作为种子,GSRC首先自动确定初始分割(粗分割),然后以能量泛函为工具,通过综合运用轮廊平滑、概率模型和区域竞争来确定最终的分割(精细分割).GSRC不仅能有效地利用图像特征,还为特征的知觉组织提供了一条简单的计算途径.     

基于模糊C-均值聚类图像分割技术研究

主要研究了均值聚类图像分割问题。针对传统的聚类图像分割算法对图像地分割精度较低等问题,提出一种基于模糊控制的C-均值聚类快速图像分割新方法。本文采用快速模糊C-均值聚类算法对图像分割。实验结果表明,图像分割边缘清晰,分割效果明显优于传统的聚类图像分割算法。     

高分辨率SAR图像CFAR分割的改进方法

针对传统的基于韦布尔模型的恒虚警检测(CFAR)分割中误差大、精度低的缺点,提出了分割前对特定方向角样本进行垂直中值滤波、分割后采用区域生长滤波的改进方法.最后用区域间对比度和最终测量精度的分割评价准则,与传统CFAR分割和计数滤波的方法进行了比较.对运动和静止目标获取和识别(MSTAR)样本的实验结果表明,改进方法提高了分割精度,分割效果优于传统的CFAR分割方法.     

面向新时代的人民日报语料中文分词歧义分析

【目的/意义】对近几年的人民日报语料中文分词结果进行统计和分析有利于总结新时代的中文语料在分 词歧义方面的规律,提高分词效果,促进中文信息处理的相关研究和技术的发展。【方法/过程】本文以2015年以后 的共4个月新时代的人民日报分词语料为研究对象,通过统计词频、词长、从合度等信息,从名词、动词、数词、量词、 副词、形容词、区别词、方位词、处所词、时间词、代词、介词、连词、助词、习用语、否定词、前后缀等类型来讨论变异 词的切分规律。【结果/结论】结果发现新时代的人民日报语料中的切分变异大部分为假歧义,相同语法结构的二字 词要比三字词、四字词的切分变异从合度更高。【创新/局限】本文首次面向新时代的人民日报语料讨论了中文分词 歧义的问题,但缺少与旧语料的对比分析。     

Demand cycles and market segmentation in bicycle sharing

Consumers often display unique habitual behaviors, and knowledge of these behaviors is of great value in prediction of future demand. We investigated consumer behavior in bicycle sharing in Beijing, where demand prediction is critical for cost-effective rebalancing of bicycle locations (putting bikes where and when they will be rented) and supply (number of bicycles). We created baseline statistical demand models, borrowing methods from economics, signal processing and animal tracking to find consumption cycles of 7, 12, 24 h and 7-days. Lorenz curves of bicycle demand revealed significant stratification of consumer behavior and a long-tail of infrequent demand. To overcome the limits of traditional statistical models, we developed a deep-learning model to incorporate (1) weather and air quality, (2) time-series of demand, and (3) geographical location of demand. Customer segmentation was added at a later stage, to explore potential for improvement with customer demographics. Our final machine learning model with tuned hyperparameters yielded around 50% improvement in predictions over a discrete wavelet transform model, and 80–90% improvement in predictions over a naïve model the reflects some current industry practice. We assessed causality in the deep-learning model, finding that location and air quality had the strongest causal impact on demand. The extreme market segmentation of customer demand, and our relatively short time span of data combined to make it difficult to find sufficient data on all customers for a model fit based on segmentation. We reduced our model data to only the 10 most frequent to see whether such segmentation improves our model's predictive success. These results, though limited, suggest that customer behavior within market segments is more stable than across all customers, as was expected.     

音乐检索现状及发展趋势研究

基于音乐的特征,分析目前主要的音频检索技术方法,并提出一个音乐检索系统模型,阐述音乐检索的发展前景。     

Studying emotion induced by music through a crowdsourcing game

One of the major reasons why people find music so enjoyable is its emotional impact. Creating emotion-based playlists is a natural way of organizing music. The usability of online music streaming services could be greatly improved by developing emotion-based access methods, and automatic music emotion recognition (MER) is the most quick and feasible way of achieving it. When resorting to music for emotional regulation purposes, users are interested in the MER method to predict their induced, or felt emotion. The progress of MER in this area is impeded by the absence of publicly accessible ground-truth data on musically induced emotion. Also, there is no consensus on the question which emotional model best fits the demands of the users and can provide an unambiguous linguistic framework to describe musical emotions. In this paper we address these problems by creating a sizeable publicly available dataset of 400 musical excerpts from four genres annotated with induced emotion. We collected the data using an online “game with a purpose” Emotify, which attracted a big and varied sample of participants. We employed a nine item domain-specific emotional model GEMS (Geneva Emotional Music Scale). In this paper we analyze the collected data and report agreement of participants on different categories of GEMS. We also analyze influence of extra-musical factors on induced emotion (gender, mood, music preferences). We suggest that modifications in GEMS model are necessary.     

Alfred Wallace and the anthropology of sound in Victorian culture

In the years after the publication of Darwin's On the Origin of Species, Alfred Russel Wallace became a prominent critic of the argument that evolution provided a sufficient account of human origins. Unbeknownst to many historians of science, Wallace partly based his case on his belief that man's musical sense and aesthetic powers could not have evolved by natural selection. Although he witnessed a variety of musical practices during his travels abroad, Wallace, like many contemporaries in Victorian England, assumed that music uniquely belonged to the ‘civilized’ world he inhabited. In the late 19th century, some evolutionists would challenge this view by reconceiving the nature of music itself.     

自动提取植物染色体特征的研究

植物染色体特征参量的提取是实现植物染色体计算机自动识别和分析的关键,本文首先对原始植物染色体图像进行图像分割、边界搜索、背景噪声滤除等处理,将各条染色体从图像中提取出来。然后,提出采用边界的高阶方向链码来判定染色体边界上明显凹凸点的分布,又根据染色体的细化中轴,自动判定出染色体着丝点的位置。进而,测量得到描述染色体特征的主要参量。经对植物染色体图像进行实验,其结果表明这一系列处理方法对植物染色体特征的自动提取是有效的。     

市场分割、创新要素流动与省域创新效率的空间相关性研究

本文运用动态空间计量模型对我国30个省（市、自治区）2003～2016年面板数据进行实证分析,旨在探究市场分割与省域创新效率的空间相关性,并揭示创新要素流动在两者中发挥的传导机制。研究发现：市场分割程度有下降的趋势,但其对创新效率依然有十分显著的抑制作用,这种抑制作用表现为中东西逐一递减。进一步探究发现创新要素流动的中介作用十分显著,其中市场分割通过阻碍R&D人员流动进而抑制创新效率的中介效应大于R&D资本;在东中西三大区域中,创新要素流动的中介作用具有差异性,呈现中-东-西的下降趋势。     

Subset selection for visualization of relevant image fractions for deep learning based semantic image segmentation

Semantic image segmentation is a challenging problem from image processing where deep convolutional neural networks (CNN) have been applied with great success in the recent years. It deals with pixel-wise classification of an input image, dividing it into regions of multiple object classes. However, CNNs are opaque models. Given a trained CNN, it is hard to tell which information encoded in the input image is important for the network to perform segmentation. Such information could be useful to judge whether a trained network learned to segment in a plausible way or how its performance can be improved.For a trained CNN, we formulate an optimization problem to extract relevant image fractions for semantic segmentation. We try to identify a subset of pixels that contain the relevant information for the segmentation of one selected object class. In experiments on the Cityscapes dataset, we show that this is an easy way to gain valuable insight into a CNN trained for semantic segmentation. Looking at the relevant image fractions, we can identify possible limits of a trained network and draw conclusions about possible improvements.