A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.

Implementing statistical learning methods through Bayesian networks (Part 2): bayesian evaluations for results of black toner analyses in forensic document examination

This paper presents and discusses the use of Bayesian procedures - introduced through the use of Bayesian networks in Part I of this series of papers - for 'learning' probabilities from data. The discussion will relate to a set of real data on characteristics of black toners commonly used in printing and copying devices. Particular attention is drawn to the incorporation of the proposed procedures as an integral part in probabilistic inference schemes (notably in the form of Bayesian networks) that are intended to address uncertainties related to particular propositions of interest (e.g., whether or not a sample originates from a particular source). The conceptual tenets of the proposed methodologies are presented along with aspects of their practical implementation using currently available Bayesian network software.

Learning design twofold strategies for teacher-led inquiry andstudent active learning

This workshop paper states that fostering active student participation both in face-to-face lectures / seminars and outside the classroom (personal and group study at home, the library, etc.) requires a certain level of teacher-led inquiry. The paper presents a set of strategies drawn from real practice in higher education with teacher-led inquiry ingredients that promote active learning. Thesepractices highlight the role of the syllabus, the importance of iterative learning designs, explicit teacher-led inquiry, and the implications of the context, sustainability and practitioners’ creativity. The strategies discussed in this paper can serve as input to the workshop as real cases that need to be represented in design and supported in enactment (with and without technologies).

Applying machine learning methods to avalanche forecasting

Avalanche forecasting is a complex process involving the assimilation of multiple data sources to make predictions over varying spatial and temporal resolutions. Numerically assisted forecasting often uses nearest neighbour methods (NN), which are known to have limitations when dealing with high dimensional data. We apply Support Vector Machines to a dataset from Lochaber, Scotland to assess their applicability in avalanche forecasting. Support Vector Machines (SVMs) belong to a family of theoretically based techniques from machine learning and are designed to deal with high dimensional data. Initial experiments showed that SVMs gave results which were comparable with NN for categorical and probabilistic forecasts. Experiments utilising the ability of SVMs to deal with high dimensionality in producing a spatial forecast show promise, but require further work.

Implementing statistical learning methods through Bayesian networks. Part 1: a guide to Bayesian parameter estimation using forensic science data

As a thorough aggregation of probability and graph theory, Bayesian networks currently enjoy widespread interest as a means for studying factors that affect the coherent evaluation of scientific evidence in forensic science. Paper I of this series of papers intends to contribute to the discussion of Bayesian networks as a framework that is helpful for both illustrating and implementing statistical procedures that are commonly employed for the study of uncertainties (e.g. the estimation of unknown quantities). While the respective statistical procedures are widely described in literature, the primary aim of this paper is to offer an essentially non-technical introduction on how interested readers may use these analytical approaches - with the help of Bayesian networks - for processing their own forensic science data. Attention is mainly drawn to the structure and underlying rationale of a series of basic and context-independent network fragments that users may incorporate as building blocs while constructing larger inference models. As an example of how this may be done, the proposed concepts will be used in a second paper (Part II) for specifying graphical probability networks whose purpose is to assist forensic scientists in the evaluation of scientific evidence encountered in the context of forensic document examination (i.e. results of the analysis of black toners present on printed or copied documents).

Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.

Cluster-based active learning for compact image classification

In this paper, we consider active sampling to label pixels grouped with hierarchical clustering. The objective of the method is to match the data relationships discovered by the clustering algorithm with the user's desired class semantics. The first is represented as a complete tree to be pruned and the second is iteratively provided by the user. The active learning algorithm proposed searches the pruning of the tree that best matches the labels of the sampled points. By choosing the part of the tree to sample from according to current pruning's uncertainty, sampling is focused on most uncertain clusters. This way, large clusters for which the class membership is already fixed are no longer queried and sampling is focused on division of clusters showing mixed labels. The model is tested on a VHR image in a multiclass classification setting. The method clearly outperforms random sampling in a transductive setting, but cannot generalize to unseen data, since it aims at optimizing the classification of a given cluster structure.

New kernel functions and learning methods for text and data mining

Recent advances in machine learning methods enable increasingly the automatic construction of various types of computer assisted methods that have been difficult or laborious to program by human experts. The tasks for which this kind of tools are needed arise in many areas, here especially in the fields of bioinformatics and natural language processing. The machine learning methods may not work satisfactorily if they are not appropriately tailored to the task in question. However, their learning performance can often be improved by taking advantage of deeper insight of the application domain or the learning problem at hand. This thesis considers developing kernel-based learning algorithms incorporating this kind of prior knowledge of the task in question in an advantageous way. Moreover, computationally efficient algorithms for training the learning machines for specific tasks are presented. In the context of kernel-based learning methods, the incorporation of prior knowledge is often done by designing appropriate kernel functions. Another well-known way is to develop cost functions that fit to the task under consideration. For disambiguation tasks in natural language, we develop kernel functions that take account of the positional information and the mutual similarities of words. It is shown that the use of this information significantly improves the disambiguation performance of the learning machine. Further, we design a new cost function that is better suitable for the task of information retrieval and for more general ranking problems than the cost functions designed for regression and classification. We also consider other applications of the kernel-based learning algorithms such as text categorization, and pattern recognition in differential display. We develop computationally efficient algorithms for training the considered learning machines with the proposed kernel functions. We also design a fast cross-validation algorithm for regularized least-squares type of learning algorithm. Further, an efficient version of the regularized least-squares algorithm that can be used together with the new cost function for preference learning and ranking tasks is proposed. In summary, we demonstrate that the incorporation of prior knowledge is possible and beneficial, and novel advanced kernels and cost functions can be used in algorithms efficiently.

Learning through role-playing games: an approach for active learning and teaching

This study evaluates the use of role-playing games (RPGs) as a methodological approach for teaching cellular biology, assessing student satisfaction, learning outcomes, and retention of acquired knowledge. First-year undergraduate medical students at two Brazilian public universities attended either an RPG-based class (RPG group) or a lecture (lecture-based group) on topics related to cellular biology. Pre- and post-RPG-based class questionnaires were compared to scores in regular exams and in an unannounced test one year later to assess students' attitudes and learning. From the 230 students that attended the RPG classes, 78.4% responded that the RPG-based classes were an effective tool for learning; 55.4% thought that such classes were better than lectures but did not replace them; and 81% responded that they would use this method. The lecture-based group achieved a higher grade in 1 of 14 regular exam questions. In the medium-term evaluation (one year later), the RPG group scored higher in 2 of 12 questions. RPG classes are thus quantitatively as effective as formal lectures, are well accepted by students, and may serve as educational tools, giving students the chance to learn actively and potentially retain the acquired knowledge more efficiently.

Working Together: Librarian and Student Collaboration Through Active Learning in a Library Eclassroom

Active learning strategies based on several learning theories were incorporated during instruction sessions for second year Biological Sciences students. The instructional strategies described in this paper are based primarily on sociocultural and collaborative learning theory, with the goal being to expand the relatively small body of literature currently available that discusses the application of these learning theories to library instruction. The learning strategies employed successfully involved students in the learning process ensuring that the experiences were appropriate and effective. The researchers found that, as a result of these strategies (e.g. teaching moments based on the emerging needs of students) students’ interest in learning information literacy was increased and students interacted with information given to them as well as with their peers. Collaboration between the Librarians, Co-op Student and Senior Lab Instructor helped to enhance the learning experience for students and also revealed new aspects of the active learning experiences. The primary learning objective, which was to increase the students’ information skills in the Biological Sciences, was realized. The advantages of active learning were realized by both instructors and students. Advantages for students attained during these sessions include having their diverse learning styles addressed; increased interaction with and retention of information; increased responsibility for their own learning; the opportunity to value not only the instructors, but also themselves and their peers as sources of authority and knowledge; improved problem solving abilities; increased interest and opportunities for critical thinking, as a result of the actively exchanging information in a group. The primary advantage enjoyed by the instructors was the opportunity to collaborate with colleagues to reduce the preparation required to create effective library instruction sessions. Opportunities for further research were also discovered, including the degree to which “social loafing” plays a role in collaborative, active learning.