Using electroencephalogram to continuously discriminate feelings of personal thermal comfort between uncomfortably hot and comfortable environments

Thermal comfort is an important factor for the design of buildings. Although it has been well recognized that many physiological parameters are linked to the state of thermal comfort or discomfort of humans, how to use physiological signal to judge the state of thermal comfort has not been well studied. In this paper, the feasibility of continuously determining feelings of personal thermal comfort was discussed by using electroencephalogram (EEG) signals in private space. In the study, 22 subjects were exposed to thermally comfortable and uncomfortably hot environments, and their EEG signals were recorded. Spectral power features of the EEG signals were extracted, and an ensemble learning method using linear discriminant analysis or support vector machine as a sub-classifier was used to build the discriminant model. The results show that an average discriminate accuracy of 87.9% can be obtained within a detection window of 60 seconds. This study indicates that it is feasible to distinguish whether a person feels comfortable or too hot in their private space by multi-channel EEG signals without interruption and suggests possibility for further applications in neuroergonomics.     

Solving the small sample size problem in face recognition using generalized discriminant analysis

The goal of face recognition is to distinguish persons via their facial images. Each person's images form a cluster, and a new image is recognized by assigning it to the correct cluster. Since the images are very high-dimensional, it is necessary to reduce their dimension. Linear discriminant analysis (LDA) has been shown to be effective at dimension reduction while preserving the cluster structure of the data. It is classically defined as an optimization problem involving covariance matrices that represent the scatter within and between clusters. The requirement that one of these matrices be nonsingular restricts its application to datasets in which the dimension of the data does not exceed the sample size. For face recognition, however, the dimension typically exceeds the number of images in the database, resulting in what is referred to as the small sample size problem. Recently, the applicability of LDA has been extended by using the generalized singular value decomposition (GSVD) to circumvent the nonsingularity requirement, thus making LDA directly applicable to face recognition data. Our experiments confirm that LDA/GSVD solves the small sample size problem very effectively as compared with other current methods.     

Extensions of LDA by PCA mixture model and class-wise features

Linear discriminant analysis (LDA) is a data discrimination technique that seeks transformation to maximize the ratio of the between-class scatter and the within-class scatter. While it has been successfully applied to several applications, it has two limitations, both concerning the underfitting problem. First, it fails to discriminate data with complex distributions since all data in each class are assumed to be distributed in the Gaussian manner. Second, it can lose class-wise information, since it produces only one transformation over the entire range of classes. We propose three extensions of LDA to overcome the above problems. The first extension overcomes the first problem by modelling the within-class scatter using a PCA mixture model that can represent more complex distribution. The second extension overcomes the second problem by taking different transformation for each class in order to provide class-wise features. The third extension combines these two modifications by representing each class in terms of the PCA mixture model and taking different transformation for each mixture component. It is shown that all our proposed extensions of LDA outperform LDA concerning classification errors for synthetic data classification, hand-written digit recognition, and alphabet recognition.     

Generalized null space uncorrelated Fisher discriminant analysis for linear dimensionality reduction

We propose a generalized null space uncorrelated Fisher discriminant analysis (GNUFDA) technique integrating the uncorrelated discriminant analysis and weighted pairwise Fisher criterion. The GNUFDA can effectively deal with the small sample-size problem and perform satisfactorily when the dimensionality of the null space decreases with increase in the number of training samples per class and/or classes, C. The proposed GNUFDA can extract at most C-1 optimal uncorrelated discriminative vectors without being influenced by the null-space dimensionality.     

基于双正交小波和加权NLDA的人脸识别

文章针对基于零空间线性判别分析方法在高维多类别的人脸识别应用中存在的“次优性”和“效率低”两个问题,提出了一种改进方法.该方法用加权函数重新定义类间离散矩阵以减弱边缘类带来的不良影响来改善次优性问题;并对图像进行双正交小波分解来降低分辨率以到达提高效率的目的.最后在ORL人脸库上进行了实验,通过实验确定了最优加权系数和小波分解的最佳层数,并验证了该方法比基于零空间线性判别分析方法有更高的效率和识别率.     

完全判别分析

针对现有的线性判别分析算法中存在的降维舍弃空间的判别信息丢失问题,以及秩空间和零空间的判别信息难以兼顾的问题,本文提出了一种完全判别分析算法.算法通过新构建一个子空间以及其中的判别矩阵,实现了可以充分使用全空间的判别信息;且新空间的维数较低,算法流程简单,计算代价较小.相关实验结果证实了本文算法较传统判别分析算法有更好的性能和效率.     

光学遥感舰船目标识别方法

提出一种基于粗糙集理论和分层判别回归技术的光学遥感舰船目标识别方法。该方法首先提出新的光学遥感舰船识别特征———面积比编码,并与四类特征组合作为备选特征;然后基于粗糙集理论按同可区分度来计算各备选特征的重要性权值,自动选择出对正确识别贡献较大的特征组合;最后根据分层判别回归原理生成分类判决树来识别光学遥感舰船目标。实验结果表明,本文方法在识别精度和速度方面优于最近邻和支持向量机方法,且通用可行。     

Incorporating statistical information into expert classification systems to reduce classification costs

Interactive expert systems seek relevant information from a user in order to answer a query or to solve a problem that the user has posed. A fundamental design issue for such a system is therefore itsinformation-seeking strategy, which determines the order in which it asks questions or performs experiments to gain the information that it needs to respond to the user. This paper examines the problem of optimal knowledge acquisition through questioning in contexts where it is expensive or time-consuming to obtain the answers to questions. An abstract model of an expert classification system — considered as a set of logical classification rules supplemented by some statistical knowledge about attribute frequencies — is developed and applied to analyze the complexity and to present constructive algorithms for doing probabilistic question-based classification. New heuristics are presented that generalize previous results for optimal identification keys and questionnaires. For an important class of discrete discriminant analysis problems, these heuristics find optimal or near-optimal questioning strategies in a small fraction of the time required by an exact solution algorithm.     

Weighted principal component extraction with genetic algorithms

Pattern recognition techniques have been widely used in a variety of scientific disciplines including computer vision, artificial intelligence, biology, and so forth. Although many methods present satisfactory performances, they still have several weak points, thus leaving a lot of space for further improvements. In this paper, we propose two performance-driven subspace learning methods by extending the principal component analysis (PCA) and the kernel PCA (KPCA). Both methods adopt a common structure where genetic algorithms are employed to pursue optimal subspaces. Because the proposed feature extractors aim at achieving high classification accuracy, enhanced generalization ability can be expected. Extensive experiments are designed to evaluate the effectiveness of the proposed algorithms in real-world problems including object recognition and a number of machine learning tasks. Comparative studies with other state-of-the-art techniques show that the methods in this paper are capable of enhancing generalization ability for pattern recognition systems.