适用于不确定类标签数据学习的迁移支持向量机

为了解决包含不确定信息的分类学习问题,提出一种新的适用于不确定类标签数据的迁移支持向量机。该方法基于结构风险最小化模型,同时将源领域中所学知识、领域间的共享数据、目标领域中已标定的和不确定的数据纳入学习框架中,进而实现了源领域和目标领域的知识迁移。在多种真实数据集上的实验结果表明了所提出方法的有效性。     

极限学习机类不平衡数据学习算法研究

尽管极限学习机因具有快速、简单、易实现及普适的逼近能力等特点被广泛应用于分类、回归及特征学习问题,但是,极限学习机同其他标准分类方法一样将最大化各类总分类性能作为算法的优化目标,因此,在实际应用中遇到数据样本分布不平衡时,算法对大类样本具有性能偏向性。针对极限学习机类不平衡学习问题的研究起步晚,算法少的问题,在介绍了极限学习机类不平衡数据学习研究现状,极限学习机类不平衡数据学习的典型算法-加权极限学习机及其改进算法的基础上,提出一种不需要对原始不平衡样本进行处理的Adaboost提升的加权极限学习机,通过在15个UCI不平衡数据集进行分析实验,实验结果表明提出的算法具有更好的分类性能。     

A new multi-view learning machine with incomplete data

Pattern Analysis and Applications - Multi-view learning with incomplete views (MVL-IV) is a reliable algorithm to process incomplete datasets which consist of instances with missing views or...     

Knowledge acquisition from questionnaire data using simulated breeding and inductive learning methods

Marketing decision making tasks require the acquisition of efficient decision rules from noisy questionnaire data. Unlike popular learning-from-example methods, in such tasks, we must interpret the characteristics of the data without clear features of the data nor pre-determined evaluation criteria. The problem is how domain experts get simple, easy-to-understand, and accurate knowledge from noisy data.

This paper describes a novel method to acquire efficient decision rules from questionnaire data using both simulated breeding and inductive learning techniques. The basic ideas of the method are that simulated breeding is used to get the effective features from the questionnaire data and that inductive learning is used to acquire simple decision rules from the data. The simulated breeding is one of the Genetic Algorithm based techniques to subjectively or interactively evaluate the qualities of offspring generated by genetic operations.

The proposed method has been qualitatively and quantitatively validated by a case study on consumer product questionnaire data: the acquired rules are simpler than the results from the direct application of inductive learning; a domain expert admits that they are easy to understand; and they are at the same level on the accuracy compared with the other methods.

Furthermore, we address three variations of the basic interactive version of the method: (i) with semiautomated GA phases, (ii) with the relatively evaluation phase via AHP, and (iii) with an automated multiagent learning method.     

Urban areas extraction from multi sensor data based on machine learning and data fusion

Accurate urban areas information is important for a variety of applications, especially city planning and natural disaster prediction and management. In recent years, extraction of urban structures from remotely sensed images has been extensively explored. The key advantages of this imaging modality are reduction of surveying expense and time. It also elevates restrictions on ground surveys. Thus far, much research typically extracts these structures from very high resolution satellite imagery, which are unfortunately of relatively poor spectral resolution, resulting in good precision yet moderate accuracy. Therefore, this paper investigates extraction of buildings from middle and high resolution satellite images by using spectral indices (Normalized Difference Building Index: NDBI, Normalized Difference Vegetation Index: NDVI, Soil Adjustment Vegetation Index: SAVI, Modified Normalized Difference Index: MNDWI, and Global Environment Monitoring Index: GEMI) by means of various Machine Learning methods (Artificial Neural Network: ANN, K-Nearest Neighbor: KNN, and Support Vector Machine: SVM) and Data Fusion (i.e., Majority Voting). Herein empirical results suggested that suitable learning methods for urban areas extraction are in preferring order Data Fusion, SVM, KNN, and ANN. Their accuracies were 85.46, 84.86, 84.66, and 84.91%, respectively.     

用机器学习方法解码脑图像数据

特征选择和分类是脑功能磁共振成像（fMRI）数据分析的核心问题。针对fMRI高维数据,特征选择分两步,选取感兴趣脑区,选择最能区分刺激任务体素。该方法简单,稳定,符合人的思维逻辑。分类器选择高斯朴素贝叶斯（GNB）和支持向量机（SVM）,评估该特征选择方法。实验结果表明,该方法有效提高了分类速度,分类准确度也得到很大提高。对分类方法进行比较,SVM总体上优于GNB。     

Supervised machine learning using encrypted training data

International Journal of Information Security - Preservation of privacy in data mining and machine learning has emerged as an absolute prerequisite in many practical scenarios, especially when the...     

Estimating city-level poverty rate based on e-commerce data with machine learning

Electronic Commerce Research - There are many big data sources in Indonesia, for example, data from social media, financial transactions, transportation, call detail records, and e-commerce. These...     

Multimedia and machine learning approaches for data analytics

Multimedia Tools and Applications -     

面向贯序不均衡分类的粒度极限学习机

针对现有算法对贯序到达的密度型不均衡数据分类效果不佳的缺陷, 提出一种基于粒度划分的在线贯序极限学习机算法. 离线阶段,根据数据分布特性对多类样本进行粒度划分, 用粒心代替原有样本, 建立初始模型; 在线阶段, 根据更新后的分布特性对多类边界数据进行二次粒度划分, 替换原有边界数据, 并动态更新网络权值. 理论分析证明该算法存在信息损失上界. 实验结果表明, 该算法能有效提高贯序不均衡数据上的整体泛化性能和分类效率.     

Parallelized extreme learning machine for online data classification

Applied Intelligence - The challenges raised by the massive data are being managed by the community through the advancements of infrastructure and algorithms, and now the processing of fast data is...     

Evaluation and classification of otoneurological data with new data analysis methods based on machine learning

We improved the classification ability of multilayer perceptron networks by constructing a set of networks of as many as output classes and investigated the influence of different input variables on the classification. We have developed methods named scattering, spectrum and response analysis to express the classification complexity, especially the overlap of output classes, to disentangle the relation between the input variables and output classes of perceptron neural networks, and to establish the importance of input variables. The methods were tested by exploring complicated otoneurological data. In contrast to the variable selection problem, our methods characterize the importance of variables for classification and also describe the importance of the different values of each variable for output (disease) classes. When complex data is distributed in a biased manner between disease classes, we improved classification accuracy by developing a network set called NetSet, which increased average sensitivity and positive predictive value for at least 10% up to 85% and 83% respectively, compared to our earlier neural network classifications with the same data, which clarified class distribution effects and supported our comprehension of the significance of input.     

A framework for machine learning based on dynamic physical fields

Despite recent successes and advancements in artificial intelligence and machine learning, this domain remains under continuous challenge and guidance from phenomena and processes observed in natural world. Humans remain unsurpassed in their efficiency of dealing and learning from uncertain information coming in a variety of forms, whereas more and more robust learning and optimisation algorithms have their analytical engine built on the basis of some nature-inspired phenomena. Excellence of neural networks and kernel-based learning methods, an emergence of particle-, swarms-, and social behaviour-based optimisation methods are just few of many facts indicating a trend towards greater exploitation of nature inspired models and systems. This work intends to demonstrate how a simple concept of a physical field can be adopted to build a complete framework for supervised and unsupervised learning methodology. An inspiration for artificial learning has been found in the mechanics of physical fields found on both micro and macro scales. Exploiting the analogies between data and charged particles subjected to gravity, electrostatic and gas particle fields, a family of new algorithms has been developed and applied to classification, clustering and data condensation while properties of the field were further used in a unique visualisation of classification and classifier fusion models. The paper covers extensive pictorial examples and visual interpretations of the presented techniques along with some comparative testing over well-known real and artificial datasets.

Incremental and accurate computation of machine learning models with smart data summarization

Journal of Intelligent Information Systems - Nowadays, data scientists prefer “easy” high-level languages like R and Python, which accomplish complex mathematical tasks with a few lines...     

Efficient data aggregation with node clustering and extreme learning machine for WSN

The Journal of Supercomputing - Wireless sensor network is effective for data aggregation and transmission in IoT environment. Here, the sensor data often contain a significant amount of noises or...     

基于机器学习的TLS恶意加密流量检测方案

首先介绍了安全传输层（TLS,transport layer security）协议的特点、流量识别方法;然后给出了一种基于机器学习的分布式自动化的恶意加密流量检测体系;进而从 TLS 特征、数据元特征、上下文数据特征3个方面分析了恶意加密流量的特征;最后,通过实验对几种常见机器学习算法的性能进行对比,实现了对恶意加密流量的高效检测。     

A study of learning likely data structure properties using machine learning models

International Journal on Software Tools for Technology Transfer - Data structure properties are important for many testing and analysis tasks. For example, model checkers use these properties to...     

Annotating mobile phone location data with activity purposes using machine learning algorithms

Individual human travel patterns captured by mobile phone data have been quantitatively characterized by mathematical models, but the underlying activities which initiate the movement are still in a less-explored stage. As a result of the nature of how activity and related travel decisions are made in daily life, human activity-travel behavior exhibits a high degree of spatial and temporal regularities as well as sequential ordering. In this study, we investigate to what extent the behavioral routines could reveal the activities being performed at mobile phone call locations that are captured when users initiate or receive a voice call or message.Our exploration consists of four steps. First, we define a set of comprehensive temporal variables characterizing each call location. Feature selection techniques are then applied to choose the most effective variables in the second step. Next, a set of state-of-the-art machine learning algorithms including Support Vector Machines, Logistic Regression, Decision Trees and Random Forests are employed to build classification models. Alongside, an ensemble of the results of the above models is also tested. Finally, the inference performance is further enhanced by a post-processing algorithm.Using data collected from natural mobile phone communication patterns of 80 users over a period of more than one year, we evaluated our approach via a set of extensive experiments. Based on the ensemble of the models, we achieved prediction accuracy of 69.7%. Furthermore, using the post processing algorithm, the performance obtained a 7.6% improvement. The experiment results demonstrate the potential to annotate mobile phone locations based on the integration of data mining techniques with the characteristics of underlying activity-travel behavior, contributing towards the semantic comprehension and further application of the massive data.