Adaptive unsupervised learning of human actions

Automatic detection of suspicious activities in CCTV camera feeds is crucial to the success of video surveillance systems. Such a capability can help transform the dumb CCTV cameras into smart surveillance tools for fighting crime and terror. Learning and classification of basic human actions is a precursor to detecting suspicious activities. Most of the current approaches rely on a non-realistic assumption that a complete dataset of normal human actions is available. This paper presents a different approach to deal with the problem of understanding human actions in video when no prior information is available. This is achieved by working with an incomplete dataset of basic actions which are continuously updated. Initially, all video segments are represented by Bags-Of-Words (BOW) method using only Term Frequency-Inverse Document Frequency (TF-IDF) features. Then, a data-stream clustering algorithm is applied for updating the system's knowledge from the incoming video feeds. Finally, all the actions are classified into different sets. Experiments and comparisons are conducted on the well known Weizmann and KTH datasets to show the efficacy of the proposed approach.

Toward a fuzzy domain ontology extraction method for adaptive e-learning

With the widespread applications of electronic learning (e-Learning) technologies to education at all levels, increasing number of online educational resources and messages are generated from the corresponding e-Learning environments. Nevertheless, it is quite difficult, if not totally impossible, for instructors to read through and analyze the online messages to predict the progress of their students on the fly. The main contribution of this paper is the illustration of a novel concept map generation mechanism which is underpinned by a fuzzy domain ontology extraction algorithm. The proposed mechanism can automatically construct concept maps based on the messages posted to online discussion forums. By browsing the concept maps, instructors can quickly identify the progress of their students and adjust the pedagogical sequence on the fly. Our initial experimental results reveal that the accuracy and the quality of the automatically generated concept maps are promising. Our research work opens the door to the development and application of intelligent software tools to enhance e-Learning.

An Adaptive Machine Learning Decision System for Flexible Predictive Maintenance

Process monitoring and Predictive Maintenance (PdM) are gaining increasing attention in most manufacturing environments as a means of reducing maintenance related costs and downtime. This is especially true in industries that are data intensive such as semiconductor manufacturing. In this paper an adaptive PdM based flexible maintenance scheduling decision support system, which pays particular attention to associated opportunity and risk costs, is presented. The proposed system, which employs Machine Learning and regularized regression methods, exploits new information as it becomes available from newly processed components to refine remaining useful life estimates and associated costs and risks. The system has been validated on a real industrial dataset related to an Ion Beam Etching process for semiconductor manufacturing.

Cost dependent strategy for electricity markets bidding based on adaptive reinforcement learning

Electricity markets are complex environments, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. MASCEM is a multi-agent electricity market simulator to model market players and simulate their operation in the market. Market players are entities with specific characteristics and objectives, making their decisions and interacting with other players. MASCEM provides several dynamic strategies for agents’ behavior. This paper presents a method that aims to provide market players with strategic bidding capabilities, allowing them to obtain the higher possible gains out of the market. This method uses a reinforcement learning algorithm to learn from experience how to choose the best from a set of possible bids. These bids are defined accordingly to the cost function that each producer presents.

A framework for adaptive e-learning for continuum mechanics and structural analysis

This paper presents a project for providing the students of Structural Engineering with the flexibility to learn outside classroom schedules. The goal is a framework for adaptive E-learning based on a repository of open educational courseware with a set of basic Structural Engineering concepts and fundamentals. These are paramount for students to expand their technical knowledge and skills in structural analysis and design of tall buildings, arch-type structures as well as bridges. Thus, concepts related to structural behaviour such as linearity, compatibility, stiffness and influence lines have traditionally been elusive for students. The objective is to facilitate the student a teachinglearning process to acquire the necessary intuitive knowledge, cognitive skills and the basis for further technological modules and professional development in this area. As a side effect, the system is expected to help the students improve their preparation for exams on the subject. In this project, a web-based open-source system for studying influence lines on continuous beams is presented. It encompasses a collection of interactive user-friendly applications accessible via Web, written in JavaScript under JQuery and Dygraph Libraries, taking advantage of their efficiency and graphic capabilities. It is performed in both Spanish and English languages. The student is enabled to set the geometric, topologic, boundary and mechanic layout of a continuous beam. While changing the loading and the support conditions, the changes in the beam response prompt on the screen, so that the effects of the several issues involved in structural analysis become apparent. This open interaction with the user allows the student to simulate and virtually infer the structural response. Different levels of complexity can be handled, whereas an ongoing help is at hand for any of them. Students can freely boost their experiential learning on this subject at their own pace, in order to further share, process, generalize and apply the relevant essential concepts of Structural Engineering analysis. Besides, this collection is being added to the "Virtual Lab of Continuum Mechanics" of the UPM, launched in 2013 (http://serviciosgate.upm.es/laboratoriosvirtuales/laboratorios/medios-continuos-en-construcci%C3%B3n)

Prototyping Adaptive Online Learning Courses

This article describes the process of prototyping adaptive online learning using the authoring tool for developers, which is based on ontologies. The article also gives a brief overview of contemporary situation and describes modern trends of evolution e-learning courses and present standards in this area. It also describes architecture of system VITA II.

Adaptive E-learning Content Design and Delivery Based on Learning Styles and Knowledge Level

ACM Computing Classification System (1998): K.3.1, K.3.2.

Automatic detection of learner-style for adaptive eLearning

The advent of modern wireless technologies has seen a shift in focus towards the design and development of educational systems for deployment through mobile devices. The use of mobile phones, tablets and Personal Digital Assistants (PDAs) is steadily growing across the educational sector as a whole. Mobile learning (mLearning) systems developed for deployment on such devices hold great significance for the future of education. However, mLearning systems must be built around the particular learner’s needs based on both their motivation to learn and subsequent learning outcomes. This thesis investigates how biometric technologies, in particular accelerometer and eye-tracking technologies, could effectively be employed within the development of mobile learning systems to facilitate the needs of individual learners. The creation of personalised learning environments must enable the achievement of improved learning outcomes for users, particularly at an individual level. Therefore consideration is given to individual learning-style differences within the electronic learning (eLearning) space. The overall area of eLearning is considered and areas such as biometric technology and educational psychology are explored for the development of personalised educational systems. This thesis explains the basis of the author’s hypotheses and presents the results of several studies carried out throughout the PhD research period. These results show that both accelerometer and eye-tracking technologies can be employed as an Human Computer Interaction (HCI) method in the detection of student learning-styles to facilitate the provision of automatically adapted eLearning spaces. Finally the author provides recommendations for developers in the creation of adaptive mobile learning systems through the employment of biometric technology as a user interaction tool within mLearning applications. Further research paths are identified and a roadmap for future of research in this area is defined.

Evaluation of a suitable learning style for iLearn: a personalised e-learning platform

Brusilovsky and Millan (2007) state that learning styles are typically defined as the way people prefer to learn. Learning styles and how we learn is a vast research area and many research projects (SMILE, INSPIRE, iWeaver amongst others) attempt to incorporate these learning styles into e-Learning systems. This paper describes commonly used learning styles and how they are currently being used within the area of adaptive e-Learning. This work also builds upon current research and evaluates learning styles using criteria proposed by Sampson and Karagiannidis (2004) in order to select a suitable learning methodology for the iLearn e-Learning platform. The Sampson and Karagiannidis (2004) criteria is adapted for the purpose of the research and describes the measurability, time effectiveness and descriptiveness and prescriptiveness of the specific learning style. A suitable learning style for the iLearn e-Learning platform is then proposed within the paper and finally the research briefly introduces how the chosen learning style will be used for the proposed e-Learning platform.

Learning styles, personalisation and adaptable e-learning

Common Learning Management Systems (for example Moodle [1] and Blackboard [2]) are limited in the amount of personalisation that they can offer the learner. They are used widely and do offer a number of tools for instructors to enable them to create and manage courses, however, they do not allow for the learner to have a unique personalised learning experience. The e-Learning platform iLearn offers personalisation for the learner in a number of ways and one way is to offer the specific learning material to the learner based on the learner's learning style. Learning styles and how we learn is a vast research area. Brusilovsky and Millan [3] state that learning styles are typically defined as the way people prefer to learn. Examples of commonly used learning styles are Kolb Learning Styles Theory [4], Felder and Silverman Index of Learning Styles [5], VARK [6] and Honey and Mumford Index of Learning Styles [7] and many research projects (SMILE [8], INSPIRE [9], iWeaver [10] amonst others) attempt to incorporate these learning styles into adaptive e-Learning systems. This paper describes how learning styles are currently being used within the area of adaptive e-Learning. The paper then gives an overview of the iLearn project and also how iLearn is using the VARK learning style to enhance the platform's personalisation and adaptability for the learner. This research also describes the system's design and how the learning style is incorporated into the system design and semantic framework within the learner's profile.

Towards Real-time Speech Emotion Recognition for Affective E-Learning

The original article is available as an open access file on the Springer website in the following link: http://link.springer.com/article/10.1007/s10639-015-9388-2

Incremental learning from stream data

Recent years have witnessed an incredibly increasing interest in the topic of incremental learning. Unlike conventional machine learning situations, data flow targeted by incremental learning becomes available continuously over time. Accordingly, it is desirable to be able to abandon the traditional assumption of the availability of representative training data during the training period to develop decision boundaries. Under scenarios of continuous data flow, the challenge is how to transform the vast amount of stream raw data into information and knowledge representation, and accumulate experience over time to support future decision-making process. In this paper, we propose a general adaptive incremental learning framework named ADAIN that is capable of learning from continuous raw data, accumulating experience over time, and using such knowledge to improve future learning and prediction performance. Detailed system level architecture and design strategies are presented in this paper. Simulation results over several real-world data sets are used to validate the effectiveness of this method.

Extensions to knowledge acquisition and effect of multimodal representation in unsupervised learning

The phenomenal behaviour and composition of human cognition is yet to be defined comprehensibly. Developing the same, artificially, is a foremost research area in artificial intelligence and related fields. In this chapter we look at advances made in the unsupervised learning paradigm (self organising methods) and its potential in realising artificial cognitive machines. The first section delineates intricacies of the process of learning in humans with an articulate discussion of the function of thought and the function of memory. The self organising method and the biological rationalisations that led to its development are explored in the second section. The next focus is the effect of structure restrictions on unsupervised learning and the enhancements resulting from a structure adapting learning algorithm. Generation of a hierarchy of knowledge using this algorithm will also be discussed. Section four looks at new means of knowledge acquisition through this adaptive unsupervised learning algorithm while the fifth examines the contribution of multimodal representation of inputs to unsupervised learning. The chapter concludes with a summary of the extensions outlined.