基于对比学习的多模态序列推荐算法

针对如何利用商品的多模态信息提高序列推荐算法准确性的问题,提出一种基于对比学习技术的多模态序列推荐算法。该算法首先通过改变商品颜色和截取商品图片中心区域等手段进行数据增强,并把增强后的数据与原数据进行对比学习,以提取到商品的颜色和形状等视觉模态信息;其次对商品的文本模态信息进行低维空间嵌入,从而得到商品多模态信息的完整表达;最后根据商品的时序性,采用循环神经网络（RNN）建模多模态信息的序列交互特征,得到用户的偏好表达,从而进行商品推荐。在两个公开的数据集上进行实验测试的结果表明,与现有的序列推荐算法LESSR相比,所提算法排序性能有所提升,且该算法在特征维度值到达50后,推荐性能基本保持不变。     

联合多层注意力网络矩阵分解的推荐算法

许多推荐算法如基于矩阵分解因无法充分挖掘用户对项目的偏好信息而无法取得令人满意的推荐效果.为了解决上述问题,该文设计了两个模块,首先,利用多层感知机技术学习输入的信息以获得较好的特征表示,在原始输入时通过点积操作得到关系信息,并将其命名为深度矩阵分解(DeepMF);其次,在多层感知机中加入多层注意力网络,这样能够得到...     

Product information visualization and augmentation in collaborative design

In this paper, a collaborative system for product information visualization and augmentation is presented. The developed system allows the users, who can be remotely distributed, to view a product model, which is a geometric representation of the product, from different perspectives. They can choose to view design and product history, such as previous modification processes and feature information of the product independently. The product models displayed to the users are immediately updated after any design modifications have been made to the CAD model. Product features being discussed can be highlighted to draw the users’ attention. In addition, modifications can be displayed dynamically for the users to evaluate the design effect. The product history document module in the system provides a user-friendly interface for retrieving design records. After a specific record has been chosen, the related product model is displayed, and it can be aligned with the current product model for the ease of comparison and evaluation. The feature information of the product is displayed using virtual “floating” annotations linked to the related features. A user interface to enter annotations is provided, and the annotations entered by different users can be shared in real time. A cluster-based greedy algorithm is implemented to avoid overlapping annotations in the field of view.     

离群点挖掘技术在交通事件检测中的应用

交通事件的检测与确认是交通事件管理中的首要问题。基于线圈和视频数据的检测方法由于成本高,检测效果不明显,在实际应用中受到限制。提出了一种基于离群点挖掘的交通事件检测算法。该算法通过使用浮动车（floatingcardata,FcD）技术得到路况信息,并提取交通事件特征,建立特征向量。算法简单、高效、易于部署。实验结果表明,同模式识别方法相比,该算法具有较高的准确度,能有效区分常规拥堵与交通事件。     

Land surface phenology from MODIS: Characterization of the Collection 5 global land cover dynamics product

Information related to land surface phenology is important for a variety of applications. For example, phenology is widely used as a diagnostic of ecosystem response to global change. In addition, phenology influences seasonal scale fluxes of water, energy, and carbon between the land surface and atmosphere. Increasingly, the importance of phenology for studies of habitat and biodiversity is also being recognized. While many data sets related to plant phenology have been collected at specific sites or in networks focused on individual plants or plant species, remote sensing provides the only way to observe and monitor phenology over large scales and at regular intervals. The MODIS Global Land Cover Dynamics Product was developed to support investigations that require regional to global scale information related to spatio-temporal dynamics in land surface phenology. Here we describe the Collection 5 version of this product, which represents a substantial refinement relative to the Collection 4 product. This new version provides information related to land surface phenology at higher spatial resolution than Collection 4 (500-m vs. 1-km), and is based on 8-day instead of 16-day input data. The paper presents a brief overview of the algorithm, followed by an assessment of the product. To this end, we present (1) a comparison of results from Collection 5 versus Collection 4 for selected MODIS tiles that span a range of climate and ecological conditions, (2) a characterization of interannual variation in Collections 4 and 5 data for North America from 2001 to 2006, and (3) a comparison of Collection 5 results against ground observations for two forest sites in the northeastern United States. Results show that the Collection 5 product is qualitatively similar to Collection 4. However, Collection 5 has fewer missing values outside of regions with persistent cloud cover and atmospheric aerosols. Interannual variability in Collection 5 is consistent with expected ranges of variance suggesting that the algorithm is reliable and robust, except in the tropics where some systematic differences are observed. Finally, comparisons with ground data suggest that the algorithm is performing well, but that end of season metrics associated with vegetation senescence and dormancy have higher uncertainties than start of season metrics.     

基于智能Agent的电子商务知识管理

通过运用智能Agent技术解决了客户知识获取的问题.建立了基于智能Agent的电子商务知识管理框架,运用买方Agent获取客户知识,卖方Agent检索相匹配的产品信息;还运用ontology对产品和客户进行建模,并构造了基于ontology的产品分类学习算法.最后,通过原型的验证证明智能Agent技术能够有效地获取客户知识,也提高了产品信息检索的精度与速度.研究结果为电子商务环境下的客户知识管理提供了新思路.     

基于监督局部线性嵌入的中药材分类鉴别研究*

电子鼻所采集的中药材气味信息往往具有高维性和非线性。针对气味信息的这种特性,提出一种基于监督局部线性嵌入(SLLE)和线性判别分析(LDA)的气味数据分析方法。首先利用SLLE对所采集的高维非线性气味信息进行降维,目的是提取出气味数据内在的低维流行特征,并增大类别间的辨别信息。然后,在低维空间中,利用LDA进行特征分类判别。通过实验,分别将该方法与单独使用SLLE方法及PCA LDA方法进行对比分析,结果表明,该方法可以很好地对五种不同种类的中药材及三种不同产地的何首乌进行分类鉴别,其个体识别率和整体识别率均可达到100%,为使用电子鼻对中药材进行分类鉴别提供了一种行之有效的方法。     

The illumination-invariant matching of deterministic localstructure in color images

The availability of multiple spectral measurements at each pixel in an image provides important additional information for recognition. Spectral information is of particular importance for applications where spatial information is limited. Such applications include the recognition of small objects or the recognition of small features on partially occluded objects. We introduce a feature matrix representation for deterministic local structure in color images. Although feature matrices are useful for recognition, this representation depends on the spectral properties of the scene illumination. Using a linear model for surface spectral reflectance with the same number of parameters as the number of color bands, we show that changes in the spectral content of the illumination correspond to linear transformations of the feature matrices, and that image plane rotations correspond to circular shifts of the matrices. From these relationships, we derive an algorithm for the recognition of local surface structure which is invariant to these scene transformations. We demonstrate the algorithm with a series of experiments on images of real objects     

A parallel system for text inference using marker propagations

This paper presents a possible solution for the text inference problem-extracting information unstated in a text, but implied. Text inference is central to natural language applications such as information extraction and dissemination, text understanding, summarization, and translation. Our solution takes advantage of a semantic English dictionary available in electronic form that provides the basis for the development of a large linguistic knowledge base. The inference algorithm consists of a set of highly parallel search methods that, when applied to the knowledge base, find contexts in which sentences are interpreted. These contexts reveal information relevant to the text. Implementation, results, and parallelism analysis are discussed     

Multi-subregion based correlation filter bank for robust face recognition

In this paper, we propose an effective feature extraction algorithm, called Multi-Subregion based Correlation Filter Bank (MS-CFB), for robust face recognition. MS-CFB combines the benefits of global-based and local-based feature extraction algorithms, where multiple correlation filters corresponding to different face subregions are jointly designed to optimize the overall correlation outputs. Furthermore, we reduce the computational complexity of MS-CFB by designing the correlation filter bank in the spatial domain and improve its generalization capability by capitalizing on the unconstrained form during the filter bank design process. MS-CFB not only takes the differences among face subregions into account, but also effectively exploits the discriminative information in face subregions. Experimental results on various public face databases demonstrate that the proposed algorithm provides a better feature representation for classification and achieves higher recognition rates compared with several state-of-the-art algorithms.     

多源适应多标签分类框架

多源适应学习是一种旨在提升目标学习性能的有效机器学习方法。针对多标签视觉分类问题,基于现有的研究进展,研究提出一种新颖的联合特征选择和共享特征子空间学习的多源适应多标签分类框架,在现有的图Laplacian正则化半监督学习范式中充分考虑目标视觉特征的优化处理,多标签相关信息在共享特征子空间的嵌入,以及多个相关领域的判别信息桥接利用等多个方面,并将其融为一个统一的学习模型,理论证明了其局部最优解只需通过求解一个广义特征分解问题便可分别获得,并给出了算法实现及其收敛性定理。在两个实际的多标签视觉数据分类上分别进行深入实验分析,证实了所提框架的鲁棒有效性和优于现有相关方法的分类性能。     

基于GDBN网络的文本情感倾向分类算法

情感倾向性分类是自然语言处理领域中的热门话题,它的一个重要应用是挖掘线上评论中的重要信息,掌握网络舆论走向,因此本文提出一种基于GDBN网络的文本情感倾向性分类算法.该算法通过引入遗传算法来改进深度置信网络模型中的隐层,使模型自行对隐单元个数寻优,取得当前模型的适宜值,并以此模型进行深层建模与特征提取.最后通过反向传播网络对提取到的特征进行情感倾向性分类.在多个文本数据集上进行实验验证,验证结果表明了本文算法的有效性.     

FEATURE SELECTION BASED ON COMPACTNESS AND SEPARABILITY: COMPARISON WITH FILTER‐BASED METHODS

Selecting a subset of salient features for performing clustering using a clustering learning algorithm has been explored extensively in many real‐world applications. To select salient features during training, the filter model evaluates the intrinsic characteristics of each individual feature but is not permitted to use a clustering learning algorithm that provides clustered information to train the features. In particular, the filter model aims to predict unobservable clusters and measure how the features help provide satisfactory within‐cluster and between‐cluster scatters to achieve a good clustering quality. However, it is generally difficult to achieve both scatters in the filter model. For example, a random variable with a large variance may raise only the between‐cluster scatter, whereas another variable following a uniform distribution may raise only the within‐cluster scatter. In this paper, we present a new filter‐based method to quantify features that consider feature compactness and separability to ensure that both scatters are raised. Moreover, our method adopts a new search strategy to locate the best feature salience vector instead of visiting the space of all the possible feature subsets. After the benchmark data sets are tested, the experimental results indicate that our method performs better than many benchmark filter‐based methods at selecting a feature subset to perform clustering.     

Feature-based ontological framework for semantic interoperability in product development

An essential requirement in integrating tasks in product development is to have a seamless exchange of product information through the entire product lifecycle. A key challenge in the integration is the exchange of shape semantics in terms of understandable labels and representations. A unified taxonomy is proposed to represent, classify, and extract shape features. This taxonomy is built using the Domain-Independent Form Feature (DIFF) model as the representation of features. All the shape features in a product model are classified under three main classes, namely, volumetric features, deformation features and free-form surface features. Shape feature ontology is developed using the unified taxonomy, which brings the shape features under a single reasoning framework. One-to-many reasoning framework is presented for mapping semantically equivalent information (label and representation) of the feature to be exchanged to target applications, and the reconstruction of the shape model automatically in that target application. An algorithm has been developed to extract the semantics of shape features and construct the model in the target application. The algorithm developed has been tested for shape models taken from literature and test cases are selected based on variations of topology and geometry. Results of exchanging product information are presented and discussed. Finally, the limitations of the proposed method for exchanging product information are explained.     

基于局部子空间的多标记特征选择算法*

在已有的特征选择算法中,常用策略是通过相关准则选择与标记集合相关性较强的特征,然而该策略不一定是最优选择,因为与标记集合相关性较弱的特征可能是决定某些类别标记的关键特征.基于这一假设,文中提出基于局部子空间的多标记特征选择算法.该算法首先利用特征与标记集合之间的互信息得到一个重要度由高到低的特征序列,然后将新的特征排序空间划分为几个局部子空间,并在每个子空间设置采样比例以选择冗余性较小的特征,最后融合各子空间的特征子集,得到一组合理的特征子集.在6个数据集和4个评价指标上的实验表明,文中算法优于一些通用的多标记特征选择算法.     

Automated analysis of feature models 20 years later: A literature review

Software product line engineering is about producing a set of related products that share more commonalities than variabilities. Feature models are widely used for variability and commonality management in software product lines. Feature models are information models where a set of products are represented as a set of features in a single model. The automated analysis of feature models deals with the computer-aided extraction of information from feature models. The literature on this topic has contributed with a set of operations, techniques, tools and empirical results which have not been surveyed until now. This paper provides a comprehensive literature review on the automated analysis of feature models 20 years after of their invention. This paper contributes by bringing together previously disparate streams of work to help shed light on this thriving area. We also present a conceptual framework to understand the different proposals as well as categorise future contributions. We finally discuss the different studies and propose some challenges to be faced in the future.     

代价敏感数据的多标记特征选择算法

在多标记学习中,特征选择是提升多标记学习分类性能的有效手段。针对多标记特征选择算法计算复杂度较大且未考虑到现实应用中数据的获取往往需要花费代价,本文提出了一种面向代价敏感数据的多标记特征选择算法。该算法利用信息熵分析特征与标记之间的相关性,重新定义了一种基于测试代价的特征重要度准则,并根据服从正态分布的特征重要度和特征代价的标准差,给出一种合理的阈值选择方法,同时通过阈值剔除冗余和不相关特征,得到低总代价的特征子集。通过在多标记数据的实验对比和分析,表明该方法的有效性和可行性。     

Template-Free Biometric-Key Generation by Means of Fuzzy Genetic Clustering

Biometric authentication is increasingly gaining popularity in a wide range of applications. However, the storage of the biometric templates and/or encryption keys that are necessary for such applications is a matter of serious concern, as the compromise of templates or keys necessarily compromises the information secured by those keys. In this paper, we propose a novel method, which requires storage of neither biometric templates nor encryption keys, by directly generating the keys from statistical features of biometric data. An outline of the process is as follows: given biometric samples, a set of statistical features is first extracted from each sample. On each feature subset or single feature, we model the intra and interuser variation by clustering the data into natural clusters using a fuzzy genetic clustering algorithm. Based on the modelling results, we subsequently quantify the consistency of each feature subset or single feature for each user. By selecting the most consistent feature subsets and/or single features for each user individually, we generate the key reliably without compromising its relative security. The proposed method is evaluated on handwritten signature data and compared with related methods, and the results are very promising.     

面向不平衡样本的物联网入侵检测方法

随着设备的迭代,网络流量呈现指数级别的增长,针对各种应用的攻击行为越来越多,从流量层面识别并对这些攻击流量进行分类具有重要意义。同时,随着物联网设备的激增,针对这些设备的攻击行为也逐渐增多,造成的危害也越来越大。物联网入侵检测方法可以从这些海量的流量中识别出攻击流量,从流量层面保护物联网设备,阻断攻击行为。针对现阶段各类攻击流量检测准确率低以及样本不平衡问题,提出了基于重采样随机森林（RF,random forest）的入侵检测模型——Resample-RF,共包含3种具体算法：最优样本选择算法、基于信息熵的特征归并算法、多分类贪心转化算法。在物联网环境中,针对不平衡样本问题,提出最优样本选择算法,增加小样本所占权重,从而提高模型准确率;针对随机森林特征分裂效率不高的问题,提出基于信息熵的特征归并算法,提高模型运行效率;针对随机森林多分类精度不高的问题,提出多分类贪心转化算法,进一步提高准确率。在两个公开数据集上进行模型的检验,在 IoT-23 数据集上 F1 达到0.99,在Kaggle数据集上F1达到1.0,均具有显著效果。从实验结果中可知,提出的模型具有非常好的效果,能从海量流量中有效识别出攻击流量,较好地防范黑客对应用的攻击,保护物联网设备,从而保护用户。