User Modeling for Adaptive News Access

We present a framework for adaptive news access, based on machine learning techniques specifically designed for this task. First, we focus on the system's general functionality and system architecture. We then describe the interface and design of two deployed news agents that are part of the described architecture. While the first agent provides personalized news through a web-based interface, the second system is geared towards wireless information devices such as PDAs (personal digital assistants) and cell phones. Based on implicit and explicit user feedback, our agents use a machine learning algorithm to induce individual user models. Motivated by general shortcomings of other user modeling systems for Information Retrieval applications, as well as the specific requirements of news classification, we propose the induction of hybrid user models that consist of separate models for short-term and long-term interests. Furthermore, we illustrate how the described algorithm can be used to address an important issue that has thus far received little attention in the Information Retrieval community: a user's information need changes as a direct result of interaction with information. We empirically evaluate the system's performance based on data collected from regular system users. The goal of the evaluation is not only to understand the performance contributions of the algorithm's individual components, but also to assess the overall utility of the proposed user modeling techniques from a user perspective. Our results provide empirical evidence for the utility of the hybrid user model, and suggest that effective personalization can be achieved without requiring any extra effort from the user.     

Machine learning: A tool to support usability?

One problem facing designers of interactive systems is catering to the wide range of users who will use a particular application. Understanding the user is critical to designing a usable interface. There are a number of ways of addressing this problem, including improved design methodologies using ''intuitive'' interface styles, adaptive interfaces, and better training and user support materials. In this article, we argue that each of these solutions involves pattern recognition in one form or another and that machine learning can therefore aid designers of interactive systems in these areas. We report on experiments that demonstrate the potential of machine learning to user modeling that has application to two of these areas in particular: adaptive systems and design methodologies.     

基于SVM用户建模的核函数选择研究

用户建模是从用户偏好数据中建立用户偏好模型的过程,用户偏好数据具有系统运行初期的稀疏性和非线形的特点。支持向量机(Support Vector Machine,简称SVM)具有小样本学习、非线形处理的能力,是合适的用户建模工具。SVM的非线形处理能力主要依赖于核函数,采用不同的核函数进行建模对模型的预测效果有重大影响。本文重点研究核函数的选择对基于SVM建模方法的影响,从中选取了表现较优的小波核函数,构建性能突出的SVM进行用户建模。实验证明该建模方法可以有效地从小样本数据中学习用户偏好信息,建立反映用户真实偏好的用户模型。     

QUESTO: Interactive Construction of Objective Functions for Classification Tasks

Building effective classifiers requires providing the modeling algorithms with information about the training data and modeling goals in order to create a model that makes proper tradeoffs. Machine learning algorithms allow for flexible specification of such meta-information through the design of the objective functions that they solve. However, such objective functions are hard for users to specify as they are a specific mathematical formulation of their intents. In this paper, we present an approach that allows users to generate objective functions for classification problems through an interactive visual interface. Our approach adopts a semantic interaction design in that user interactions over data elements in the visualization are translated into objective function terms. The generated objective functions are solved by a machine learning solver that provides candidate models, which can be inspected by the user, and used to suggest refinements to the specifications. We demonstrate a visual analytics system QUESTO for users to manipulate objective functions to define domain-specific constraints. Through a user study we show that QUESTO helps users create various objective functions that satisfy their goals.     

Efficient and non-parametric reasoning over user preferences

We consider the problem of modeling and reasoning about statements of ordinal preferences expressed by a user, such as monadic statement like “X is good,” dyadic statements like “X is better than Y,” etc. Such qualitative statements may be explicitly expressed by the user, or may be inferred from observable user behavior. This paper presents a novel technique for efficient reasoning about sets of such preference statements in a semantically rigorous manner. Specifically, we propose a novel approach for generating an ordinal utility function from a set of qualitative preference statements, drawing upon techniques from knowledge representation and machine learning. We provide theoretical evidence that the new method provides an efficient and expressive tool for reasoning about ordinal user preferences. Empirical results further confirm that the new method is effective on real-world data, making it promising for a wide spectrum of applications that require modeling and reasoning about user preferences.     

Architecture and implementation of a smart-pregnancy monitoring system using web-based application

Today, people use web-based technologies to meet their information needs, socialise, communicate, and deal with formal and informal processes. At the same time, mobile versions of these applications provide people with great convenience in daily life. These applications include blood-pressure monitors, blood-glucose monitors, body-analysis scales, pulse oximeters, and activity and sleep trackers. Many of these products sync directly with a free mobile app that makes monitoring, viewing, storing, and sharing of health vitals simple and comprehensive. The data collected from the user is stored in a cloud-based application, then trained by intelligent algorithms that use machine learning for health aims so that the user can instantly see his or her status and development. In this study, the aim was to construct a cloud-based application specific to women for monitoring pregnancy. In the web-based application working with membership logic, members can access machine learning assisted calculators of the baby percentile, period tracker, pregnancy calendar, and baby vaccination schedule. Moreover, they can access augmented/virtual-reality-assisted visual training.     

Semi-supervised learning with an imperfect supervisor

Real-life applications may involve huge data sets with misclassified or partially classified training data. Semi-supervised learning and learning in the presence of label noise have recently emerged as new paradigms in the machine learning community to cope with this kind of problems. This paper describes a new discriminant algorithm for semi-supervised learning. This algorithm optimizes the classification maximum likelihood (CML) of a set of labeled–unlabeled data, using a discriminant extension of the Classification Expectation Maximization algorithm. We further propose to extend this algorithm by modeling imperfections in the estimated class labels for unlabeled data. The parameters of this label-error model are learned together with the semi-supervised classifier parameters. We demonstrate the effectiveness of the approach using extensive experiments on different datasets. Massih R. Amini is currently assistant professor in the University of Pierre and Marie Curie (Paris 6). He received an engineering degree in computer science from the Ecole Supérieure d'Informatique (Computer science engineering school) in Paris in 1995. He then accomplished his master thesis in science in artificial intelligence in 1997 and obtained his PhD in 2001 at University of Pierre and Marie Curie. His research interests include Statistical Learning and Text-Mining. Patrick Gallinari is currently professor in the University of Pierre and Marie Curie (Paris 6) and head of the Computer Science laboratory (LIP6). His main research activity has been in the field of statistical machine learning for the last 15 years. He has also contributed in developing machine learning techniques for different application domains like information retrieval and text mining, user modelling, man–machine interaction and pen interfaces.     

Enhancing touch behavioral authentication via cost-based intelligent mechanism on smartphones

Due to the popularity of smartphones, there is a great need to deploy appropriate authentication mechanisms to safeguard users’ sensitive data. Touch dynamics-based authentication has been developed to verify smartphone users and detect imposters. These schemes usually employ machine learning techniques to detect behavioral anomalies by comparing current behavioral actions with the stored normal model. However, we notice that machine learning classifiers often have an unstable performance, which would greatly reduce the system usability, i.e., causing a high false rejection. In this work, we are motivated by this challenge and design a cost-based intelligent mechanism that can choose a less costly algorithm for user authentication. In the evaluation, we conduct a user study with a total of 60 users to investigate the performance of our mechanism with a lightweight touch gesture-based scheme on smartphones. Experimental results demonstrate that our approach can help achieve a relatively higher and more stable authentication accuracy, as compared to the use of a sole classifier.     

布料仿真建模研究进展

布料仿真一直是计算机动画中的研究热点与难点,对提高计算机动画质量以及用户体验具有重要意义,布料是一种非常经典的柔性材料物体,遍布于人们的日常生活中。虚拟世界中虚拟角色强烈的视觉真实感主要来源于逼真的虚拟人物的服装动画,这在很大程度上可以增强用户的体验感,在游戏娱乐、电影电视和动画制作等领域有着十分广泛的应用前景。布料仿真的质量与速度直接决定了计算机动画的整体水平,而布料的模拟水平则起着至关重要的作用。随着计算机软硬件的不断发展和计算机动画市场需求的提高,对布料仿真建模方法的研究受到越来越多的关注,布料仿真建模方法也因此有了较大发展。本文通过回顾布料仿真建模方法的相关工作,对国内外方法的研究进展进行综述,从布料仿真中数值积分方法的改进、多分辨率网格的改进和机器学习方法的使用等方面对布料仿真方法的发展进行简要阐述,并根据不同方法在布料模拟应用上的特性,对几大类改进方法进行了相应的总结与展望。同时选取几种算法进行对比,并给出建议。     

Insider Attack Detection Using Deep Belief Neural Network in Cloud Computing

Cloud computing is a high network infrastructure where users, owners, third users, authorized users, and customers can access and store their information quickly. The use of cloud computing has realized the rapid increase of information in every field and the need for a centralized location for processing efficiently. This cloud is nowadays highly affected by internal threats of the user. Sensitive applications such as banking, hospital, and business are more likely affected by real user threats. An intruder is presented as a user and set as a member of the network. After becoming an insider in the network, they will try to attack or steal sensitive data during information sharing or conversation. The major issue in today's technological development is identifying the insider threat in the cloud network. When data are lost, compromising cloud users is difficult. Privacy and security are not ensured, and then, the usage of the cloud is not trusted. Several solutions are available for the external security of the cloud network. However, insider or internal threats need to be addressed. In this research work, we focus on a solution for identifying an insider attack using the artificial intelligence technique. An insider attack is possible by using nodes of weak users’ systems. They will log in using a weak user id, connect to a network, and pretend to be a trusted node. Then, they can easily attack and hack information as an insider, and identifying them is very difficult. These types of attacks need intelligent solutions. A machine learning approach is widely used for security issues. To date, the existing lags can classify the attackers accurately. This information hijacking process is very absurd, which motivates young researchers to provide a solution for internal threats. In our proposed work, we track the attackers using a user interaction behavior pattern and deep learning technique. The usage of mouse movements and clicks and keystrokes of the real user is stored in a database. The deep belief neural network is designed using a restricted Boltzmann machine (RBM) so that the layer of RBM communicates with the previous and subsequent layers. The result is evaluated using a Cooja simulator based on the cloud environment. The accuracy and F-measure are highly improved compared with when using the existing long short-term memory and support vector machine.     

基于机器学习建模的航天器健康管理平台研究

近年来,随着深度学习等技术的快速发展和航天器系统数据量的不断增加,新型的机器学习平台凭借其友好的流程化分析框架、丰富的即插即用机器学习工具、分布式的服务等诸多优点,为航天器等领域复杂问题分析处理提出了新思路;在分析了航天器故障预测与健康管理方面存在的难点以及机器学习优势基础上,提出了面向机器学习建模的航天器健康管理平台设计方案与方法,分析了多语言融合的健康管理算法模型构建、基于分布式的健康管理计算服务引擎等关键技术,并以某卫星电源系统太阳电池阵功率预测等案例详细说明平台实际应用情况,验证结果表明研究成果能够为基于机器学习建模的航天器健康管理技术研究与应用提供技术参考,最终提高卫星、空间站等航天器的安全性。     

面向PHM的民机飞行数据分析及应用研究进展

针对现代飞机装备在可靠性、安全性、维修保障性和成本等方面存在的问题,探究了飞行数据在民机故障预测与健康管理领域的最新技术发展及应用。介绍了民机飞行数据采集和译码原理,针对民机智能运维应用场景,结合机器学习和数字孪生等技术,重点介绍了围绕机载系统健康监测与预测维修、发动机状态监控与寿命管理等应用场景的数据分析与建模方法,并结合实际工程问题给出了数据分析应用案例。开发的具有自主知识产权的民机飞行数据译码和智能化分析工具,可面向不同用户需求、不同机型开展客户化开发与部署,实现了民机的飞行安全监控和故障预警,可为民航运输安全、运营、保障等需求提供数字化、智慧化的关键理论与技术支撑。     

在线草图识别中的用户适应性研究

提出一种在线草图识别用户适应性解决方法，该方法分别采用支撑向量机主动式增量学习和动态用户建模技术进行笔划和复杂图形的识别．支撑向量机主动式增量学习方法通过主动“分析”用户增量数据，并根据用户反馈从中选择重要数据作为训练样本，可有效地鉴别用户手绘笔划特征，快速地识别用户输入笔划．动态用户建模技术则采用增量决策树记录草图的笔划构成及其手绘过程，有效捕捉用户的复杂图形手绘习惯，进而利用模糊匹配在草图绘制过程中预测和识别复杂图形．实验表明：该方法具有很好的效果，为解决在线草图识别及其用户适应性问题提供参考．     

一种基于RNN的社交消息爆发预测模型

社交网络中,消息的爆发预测属于社交网络流行动态分析的范畴,是社会计算领域的研究热点之一.通过利用基于深度循环神经网络对社交消息的传播过程进行建模,提出了SMOP（social messages outbreak prediction model based on recurrent neural network）模型.与传统的基于机器学习的模型相比,SMOP直接对消息转发的到达过程进行建模,避免了传统方法中繁琐的特征工程;与基于点随机过程的模型相比,SMOP可以自动学习消息传播过程的速率函数,不需要手动定义消息传播速率的特征函数,具有较强的数据场景适应性.另外,SMOP采用了时间向量和用户向量的输入表示方法,将时间的周期性和用户的兴趣偏好建模到传播过程之中,提升了SMOP的预测效果.在Twitter和新浪微博数据集上的实验结果均表明,SMOP具有优良的数据适应能力,可以在消息传播的早期（0.5h）,以较高的F1值预测某条社交消息是否爆发,验证了模型的有效性.     

User sensitive research in e-learning: exploring the role of individual user characteristics

The increasing need for active and accessible learning in the inclusive knowledge society drives the demand for e-learning that engages users much more effectively than ever before. In this context, it is crucial to conduct research that embraces innovation in user sensitive design, or else influential individual user differences may be overlooked. The objective of this paper is to explore the creation of successful e-learning systems that are able to increase users’ learning performance and enhance their personal learning experiences. The paper reports two converging and complimentary approaches, namely case studies and experimentation. First, case studies are used to explore the extent to which effective e-learning systems comply with eight specific factors. Of the eight, accessibility, individual differences and student modeling turn out to be the weakest points in current practice. Second, an empirical study investigates the influences of user individual user differences on users’ learning outcomes in an e-learning environment. The experiment found that individual differences in motivation to learn and expectations about e-learning significantly impacted users’ learning achievements. Third, based on these studies, improvements in research methodology are identified towards greater consideration of user sensitive research issues, thus enabling us to outline improved experimental procedures. Further experiment results should provide us with better insights into the arguments needed to carefully assess benefits of developing and involving a user model in an e-learning application. Consequently, evaluation and justification could now encompass both system performance as well as user performance.     

ONTOLOGY-BASED USER MODELING AND E-PORTFOLIO GRID LEARNING SERVICES

Several challenges need to be met by a new generation of learning services. On one hand, they need to fit into a ubiquitous and serendipitous learning vision, to adapt to different types of users with different backgrounds and needs. On the other hand, they need to integrate modern pedagogical approaches of learning. These services will probably rely on the cooperation of different distributed, autonomous, goal-oriented entities, and they can be Grid- or Web-Oriented. In this paper, we show how core technologies can contribute to the development of a next generation of learning services. In particular, we focus our attention on personalized services delivery for learning by employing an ontological perspective and user modeling techniques. This paper presents some preliminary results obtained within Elegi FP6 project.     

PrDB: managing and exploiting rich correlations in probabilistic databases

Due to numerous applications producing noisy data, e.g., sensor data, experimental data, data from uncurated sources, information extraction, etc., there has been a surge of interest in the development of probabilistic databases. Most probabilistic database models proposed to date, however, fail to meet the challenges of real-world applications on two counts: (1) they often restrict the kinds of uncertainty that the user can represent; and (2) the query processing algorithms often cannot scale up to the needs of the application. In this work, we define a probabilistic database model, PrDB, that uses graphical models, a state-of-the-art probabilistic modeling technique developed within the statistics and machine learning community, to model uncertain data. We show how this results in a rich, complex yet compact probabilistic database model, which can capture the commonly occurring uncertainty models (tuple uncertainty, attribute uncertainty), more complex models (correlated tuples and attributes) and allows compact representation (shared and schema-level correlations). In addition, we show how query evaluation in PrDB translates into inference in an appropriately augmented graphical model. This allows us to easily use any of a myriad of exact and approximate inference algorithms developed within the graphical modeling community. While probabilistic inference provides a generic approach to solving queries, we show how the use of shared correlations, together with a novel inference algorithm that we developed based on bisimulation, can speed query processing significantly. We present a comprehensive experimental evaluation of the proposed techniques and show that even with a few shared correlations, significant speedups are possible.