Search

We study various discrete nonlinear combinatorial optimization problems in an online learning framework. In the first part, we address the computational complexity of designing vanishing regret (and vanishing approximate regret) algorithms. We provide a general reduction showing that many (min-max) polynomial time solvable problems not only do not have a vanishing regret, but also no vanishing approximation α -regret, for some α , unless N P = R P. In particular, for the min-max version of the vertex cover problem, which is solvable in polynomial time in the offline case, our reduction implies that there is no (2 − ϵ) -regret online randomized algorithm unless Unique Game is in RP. Besides, we prove that the bound is tight by providing an online efficient algorithm based on the online gradient descent method. In the second part, we turn our attention to online learning algorithms that are based on an offline optimization oracle that, given a set of multiple instances of the problem, is able to compute the optimum static solution that performs best on the set of instances overall. We show that for several min-max (nonlinear) discrete optimization problems, it is strongly NP -hard to solve the offline optimization oracle, even for problems that can be solved in polynomial time in the single-instance static case (e.g. min-max vertex cover, min-max perfect matching, etc.). This also provides a useful insight into the connection between the non-linear nature of some problems and the drastic change of their computational hardness when moved to an online learning setting. [ABSTRACT FROM AUTHOR]

Objective: To determine the response to a virtual educational curriculum in reconstructive urology presented during the COVID-19 pandemic. To assess learner satisfaction with the format and content of the curriculum, including relevance to learners' education and practice.Materials and Methods: A webinar curriculum of fundamental reconstructive urology topics was developed through the Society of Genitourinary Reconstructive Surgeons and partnering institutions. Expert-led sessions were broadcasted. Registered participants were asked to complete a survey regarding the curriculum. Responses were used to assess the quality of the curriculum format and content, as well as participants' practice demographics.Results: Our survey yielded a response rate of 34%. Survey responses showed >50% of practices offer reconstructive urologic services, with 37% offered by providers without formal fellowship training. A difference in self-reported baseline knowledge was seen amongst junior residents and attendings (P < .05). Regardless of level of training, all participants rated the topics presented as relevant to their education/practice (median response = 5/5). Responders also indicated that the curriculum supplemented their knowledge in reconstructive urology (median response = 5/5). The webinar format and overall satisfaction with the curriculum was highly rated (median response = 5/5). Participants also stated they were likely to recommend the series to others.Conclusion: We demonstrate success of an online curriculum in reconstructive urology. Given >50% of practices surveyed offer reconstruction, we believe the curriculum's educational benefits (increasing access and collaboration while minimizing the risk of in-person contact) will continue beyond the COVID-19 pandemic and that this will remain a relevant educational platform for urologists moving forward. [ABSTRACT FROM AUTHOR]

• A dynamic clustering algorithm for tracking evolving environments is presented. • It is able to handle non-convex, overlapping, multi-density distributions. • Input data can be processed in batch or in stream mode to adapt to the process. Evolving environments challenge researchers with non stationary data flows where the concepts – or states – being tracked can change over time. This requires tracking algorithms suited to represent concept evolution and in some cases, e.g. real industrial environments, also suited to represent time dependent features. This paper proposes a unified approach to track evolving environments that uses a two-stages distance-based and density-based clustering algorithm. In this approach data samples are fed as input to the distance based clustering stage in an incremental, online fashion, and they are then clustered to form μ -clusters. The density-based algorithm analyses the micro-clusters to provide the final clusters: thanks to a forgetting process, clusters may emerge, drift, merge, split or disappear, hence following the evolution of the environment. This algorithm has proved to be able to detect high overlapping clusters even in multi-density distributions, making no assumption about cluster convexity. It shows fast response to data streams and good outlier rejection properties. [ABSTRACT FROM AUTHOR]

Abstract Do students understand the potentially detrimental effects of mind wandering as they are watching a lecture online? To answer this question, we combined methods used to assess mind wandering and metacognitive methods used to assess student's judgments of learning. In two studies, college students watched a video lecture from an online course, and while watching it, responded to standard mind wandering prompts. They then judged how well they would perform on a quiz over the material they had just viewed. Analyses focused on answering two specific questions. Would students' judgments be higher when they reported being on-task than when they reported having task-unrelated thoughts? And, would their judgments be higher when they reported being on-task than when they reported having thoughts about whether they understand the material or reported elaborating on it (which we refer to as task-related thoughts)? Across two studies, students' judgments of learning were higher when they reported being on-task than when they reported having task-unrelated thoughts. Judgment magnitude was also greater when students reported task-related thoughts (e.g., assessing their understanding) than task-unrelated thoughts, even though performance did not differ after these two kinds of report. Relevant to instructional applications, students understand that mind wandering may be potentially detrimental to quiz performance, which suggests they may be open to interventions aimed at reducing mind wandering. Highlights • Participants responded to thought probes while watching an online video lecture. • After each thought probe, participants provided a judgment of learning regarding the material just prior to the probe. • Higher levels of mind wandering were related to lower judgments of learning (JOLs). • Participants' JOLs were lower following off-task thoughts as compared to task-related thoughts and on-task thoughts. [ABSTRACT FROM AUTHOR]

Computationally replicating the behaviour of the cerebral cortex to perform the control tasks of daily life in a human being is a challenge today. First, it is necessary to know the structure and connections between the elements of the neural network that perform movement control. Next, a mathematical neural model that adequately resembles biological neurons has to be developed. Finally, a suitable learning model that allows adapting neural network response to changing conditions in the environment is also required. Spiking Neural Networks (SNN) are currently the closest approximation to biological neural networks. SNNs make use of temporal spike trains to deal with inputs and outputs, thus allowing a faster and more complex computation. In this paper, a controller based on an SNN is proposed to perform the control of an anti-lock braking system (ABS) in vehicles. To this end, two neural networks are used to regulate the braking force. The first one is devoted to estimating the optimal slip while the second one is in charge of setting the optimal braking pressure. The latter resembles biological reflex arcs to ensure stability during operation. This neural structure is used to control the fast regulation cycles that occur during ABS operation. Furthermore, an algorithm has been developed to train the network while driving. On-line learning is proposed to update the response of the controller. Hence, to cope with real conditions, a control algorithm based on neural networks that learn by making use of neural plasticity, similar to what occurs in biological systems, has been implemented. Neural connections are modulated using Spike-Timing-Dependent Plasticity (STDP) by means of a supervised learning structure using the slip error as input. Road-type detection has been included in the same neural structure. To validate and to evaluate the performance of the proposed algorithm, simulations as well as experiments in a real vehicle were carried out. The algorithm proved to be able to adapt to changes in adhesion conditions rapidly. This way, the capability of spiking neural networks to perform the full control logic of the ABS has been verified. [ABSTRACT FROM AUTHOR]

This article reports on responses from an online survey designed to explore the before, during and after lockdown experiences of higher education teacher educators in Vietnam (n = 145) who were required to use digital technologies and pedagogies exclusively in their teaching during the 2020/21 lockdown. The data is interpreted using the TPACK framework (Koehler & Mishra, 2009) which enables analysis of the participants' technological, pedagogical and content knowledge in relation to teaching online using digital tools. The findings indicate mixed responses and experiences of teacher educators during this period with many having struggled with new technologies and unfamiliar pedagogical strategies whilst others enjoyed the opportunity to develop new approaches to their teaching. The paper concludes with key recommendations for best practice in this sector going forward post pandemic including the development of national and institutional e-learning policies, improvements in IT infrastructure and increased provision of professional training. [ABSTRACT FROM AUTHOR]

Abstract This paper proposes a method to allow users to select target species for detection, generate an initial detection model by selecting a small piece of image sample and as the movie plays, continue training this detection model automatically. This method has noticeable detection results for several types of objects. The framework of this study is divided into two parts: the initial detection model and the online learning section. The detection model initialization phase use a sample size based on the proportion of users of the Haar-like features to generate a pool of features, which is used to train and select effective classifiers. Then, as the movie plays, the detecting model detects the new sample using the NN Classifier with positive and negative samples and the similarity model calculates new samples based on the fusion background model to calculate a new sample and detect the relative similarity to the target. From this relative similarity-based conservative classification of new samples, the conserved positive and negative samples classified by the video player are used for automatic online learning and training to continuously update the classifier. In this paper, the results of the test for different types of objects show the ability to detect the target by choosing a small number of samples and performing automatic online learning, effectively reducing the manpower needed to collect a large number of image samples and a large amount of time for training. The Experimental results also reveal good detection capability. [ABSTRACT FROM AUTHOR]

Recently, incremental and on-line learning gained more attention especially in the context of big data and learning from data streams, conflicting with the traditional assumption of complete data availability. Even though a variety of different methods are available, it often remains unclear which of them is suitable for a specific task and how they perform in comparison to each other. We analyze the key properties of eight popular incremental methods representing different algorithm classes. Thereby, we evaluate them with regards to their on-line classification error as well as to their behavior in the limit. Further, we discuss the often neglected issue of hyperparameter optimization specifically for each method and test how robustly it can be done based on a small set of examples. Our extensive evaluation on data sets with different characteristics gives an overview of the performance with respect to accuracy, convergence speed as well as model complexity, facilitating the choice of the best method for a given application. [ABSTRACT FROM AUTHOR]

In this paper the classic momentum algorithm for stochastic optimization is considered. A method is introduced that adjusts coefficients for this algorithm during its operation. The method does not depend on any preliminary knowledge of the optimization problem. In the experimental study, the method is applied to on-line learning in feed-forward neural networks, including deep auto-encoders, and outperforms any fixed coefficients. The method eliminates coefficients that are difficult to determine, with profound influence on performance. While the method itself has some coefficients, they are ease to determine and sensitivity of performance to them is low. Consequently, the method makes on-line learning a practically parameter-free process and broadens the area of potential application of this technology. [ABSTRACT FROM AUTHOR]

In this paper we exploit the use of synthetic data for on-line handwritten gesture commands recognition with an emphasis on the problem of forgetting unused classes. For on-line learning, one of the most crucial moments of the processing is the initialization. In some applications the data is available and these can be fed to the learning model. However, in applications such as user-friendly handwritten gesture recognition, this scenario is not possible. Since from the user perspective it is better to let the user define his own symbols, the learning model is lacking in the amount of data at the initialization. Some strategies have been proposed to acquire synthetic handwritten gesture commands and use these for on-line learning. In this paper we exploit this technique further and focus on the forgetting of unused classes by applying a random buffer and Elastic Memory Learning (EML) to avoid this from happening. In the experiments we search for the proper amount of synthetic data produced for each sample as well as exploit the most appropriate time to stop the generation of synthetic data for learning purposes. We also investigate the influence of synthetic data on forgetting when using the proposed EML. We base the generation of synthetic gesture commands on Kinematic Theory. [ABSTRACT FROM AUTHOR]

An important question in self-learning robots is how robots can autonomously learn about and act in their environment in an on-line and unsupervised manner. This paper introduces and evaluates Context Recognition in Data Streams (CoRDS), a method that enables a robot to identify and recognise different situations in its environment. CoRDS achieves this by processing the data stream from the robot’s sensors to distinguish different patterns that identify different environmental situations. We evaluated the CoRDS method by means of quantitative and qualitative analysis on three different data streams: one synthetic and two data sets with actual sensor data generated by Thymio II robots. Our analyses showed that CoRDS created active cluster patterns that, for all three data streams, corresponded with the experimenters’ expectations. Experiments varying the parameters of the CoRDS method indicated a consistent response over all three data streams. These findings suggest that CoRDS may provide a basis for data stream clustering techniques that can be applied for the task of situation recognition. [ABSTRACT FROM AUTHOR]

Background Nursing students need to be prepared for the increasingly culturally diverse health care. Therefore, providing students with international perspectives remains the mission of higher education. However, given the logistic and financial constraints, not all students will be able to travel overseas for their international experiences. A feasible alternative to study abroad is internationalisation-at-home where intercultural dimensions are incorporated into curriculum, without students leaving their home universities. This paper presents findings from a collaboration between nursing programmes in Sweden and Hong Kong. The aim of the project was to explore how undergraduate nursing students' perceived achieved learning outcomes after participating in a web-based intercultural peer-learning intervention. [ABSTRACT FROM AUTHOR]

Previous research has indicated that instructor immediacy is associated with student satisfaction, motivation, and improved learning outcomes. Few studies have examined instructor immediacy on retention rates and student success in the on-line setting, specifically within on-line RN-to-BSN programs. The purpose of this study is to determine if perceived instructor immediacy behaviors impact student retention rates and academic success in an on-line RN-to-BSN program in a rural central Pennsylvania university. The Student Perception Appraisal of Retention scale and an immediacy scale were administered via Internet survey to undergraduate nursing students in an on-line RN-to-BSN program. The current study found that instructor immediacy impacts both academic success and retention in an on-line RN-to-BSN program. Results of this study provide educators another tool for increasing retention and academic success. Increased levels of student success and retention as a result of instructor immediacy would provide institutions of higher education with active teaching strategies to ensure success for the RN-to-BSN on-line student resulting in improved retention and higher graduation rates. [ABSTRACT FROM AUTHOR]

Although wikis appear to have been reported as effective tools for educators, uncertainty exists as to their effectiveness in achieving student learning outcomes. The aim of this integrative review was to examine the current evidence on the impact of wikis on student learning in courses requiring collaborative or co-developed assignments or activities. The authors searched several electronic databases for relevant articles and used R. Whittemore and K. Knafl's (2005) integrative review method to analyze and synthesize the evidence. Twenty-five articles met the selection criteria for this review, and four major themes for wiki use were identified: (a) writing skills, (b) collaboration, (c) knowledge acquisition, and (d) centralized repository. Although wikis have been found useful in improving student learning outcomes and hold great potential as an instructional strategy to aid students in learning various skills and gaining new knowledge, more research is needed on their effectiveness, especially in the area of nursing education. [ABSTRACT FROM AUTHOR]

Are comprehension and production a single, integrated skill, or are they separate processes drawing on a shared abstract knowledge of language? We argue that a fundamental constraint on memory, the Now-or-Never bottleneck, implies that language processing is incremental and that language learning occurs on-line. These properties are difficult to reconcile with the ‘abstract knowledge’ viewpoint, and crucially suggest that language comprehension and production are facets of a unitary skill. This viewpoint is exemplified in the Chunk-Based Learner, a computational acquisition model that processes incrementally and learns on-line. The model both parses and produces language; and implements the idea that language acquisition is nothing more than learning to process. We suggest that the Now-or-Never bottleneck also provides a strong motivation for unified perception–production models in other domains of communication and cognition. [ABSTRACT FROM AUTHOR]

This paper presents a recurrent neural network based novelty filter where a Scitos G5 mobile robot explored the environment and built dynamic models of observed sensory–motor values, then the acquired models of normality are used to predict the expected future values of sensory–motor inputs during patrol. Novelties could be detected whenever the prediction error between models-predicted values and actual observed values exceeded a local novelty threshold. The network is trained on-line; it grows by inserting new nodes when abnormal observation is perceived from the environment; and also shrinks when the learned information is not necessary anymore. In addition, the network is also capable of learning region-specific novelty thresholds on-line continuously. To evaluate the proposed algorithm, real-world robotic experiments were conducted by fusing sensory perceptions (vision and laser sensors) and the robot motor control outputs (translational and rotational velocities). Experimental results showed that all of the novelty cases were highlighted by the proposed algorithms and it produced reliable local novelty thresholds while the robot patrols in the noisy environment. The statistical analysis showed that there was a strong correlation between the novelty filter responses and the actual novelty status. Furthermore, the filter was also compared with another novelty filter and the results showed that the proposed system performed better novelty detection. [ABSTRACT FROM AUTHOR]

By and large, the interpretation of learning as a computational process taking place in both humans and machines is primarily provided in the framework of statistics. In this paper, we propose a radically different perspective in which the emergence of learning is regarded as the outcome of laws of nature that govern the interactions of intelligent agents with their own environment. We introduce a natural learning theory based on the principle of least cognitive action , which is inspired to the related mechanical principle, and to the Hamiltonian framework for modeling the motion of particles. The introduction of the kinetic and of the potential energy leads to a surprisingly natural interpretation of learning as a dissipative process. The kinetic energy reflects the temporal variation of the synaptic connections, while the potential energy is a penalty that describes the degree of satisfaction of the environmental constraints. The theory gives a picture of learning in terms of the energy balancing mechanisms, where the novel notions of boundary and bartering energies are introduced. Finally, as an example of application of the theory, we show that the supervised machine learning scheme can be framed in the proposed theory and, in particular, we show that the Euler–Lagrange differential equations of learning collapse to the classic gradient algorithm on the supervised pairs. [ABSTRACT FROM AUTHOR]

Being complex, non-linear and coupled system, the robotic manipulator cannot be effectively controlled using classical proportional-integral-derivative (PID) controller. To enhance the effectiveness of the conventional PID controller for the nonlinear and uncertain systems, gains of the PID controller should be conservatively tuned and should adapt to the process parameter variations. In this work, a mix locally recurrent neural network (MLRNN) architecture is investigated to mimic a conventional PID controller which consists of at most three hidden nodes which act as proportional, integral and derivative node. The gains of the mix locally recurrent neural network based PID (MLRNNPID) controller scheme are initialized with a newly developed cuckoo search algorithm (CSA) based optimization method rather than assuming randomly. A sequential learning based least square algorithm is then investigated for the on-line adaptation of the gains of MLRNNPID controller. The performance of the proposed controller scheme is tested against the plant parameters uncertainties and external disturbances for both links of the two link robotic manipulator with variable payload (TL-RMWVP). The stability of the proposed controller is analyzed using Lyapunov stability criteria. A performance comparison is carried out among MLRNNPID controller, CSA optimized NNPID (OPTNNPID) controller and CSA optimized conventional PID (OPTPID) controller in order to establish the effectiveness of the MLRNNPID controller. [ABSTRACT FROM AUTHOR]

The success of SVM in solving pattern recognition problems has encouraged researcher to extend the development of different versions. They are well-known for their robustness and good generalization performance. In many real-world applications, the data to be trained are available on-line in a sequential fashion and because of space and time requirements, batch training methods are not suitable. This paper proposes a new fast on-line algorithm called OTWISVM. It defines two optimization problems and incremental learning is done based of them. Two hyperplanes are generated as decision functions thus each of them is closer to one of the two classes and is as far as possible from the other. The solution is constructed via two subsets of linearly independent samples seen so far, and is always bounded. Good accuracy and notable speed of the method was tested and affirmed both on ordinary and noisy data sets as opposed to similar algorithms. [ABSTRACT FROM AUTHOR]

This article highlights the commitment of the American Association of Colleges of Nursing to engage nursing schools to support the Joining Forces initiative by enhancing the education and preparation of the nation's nurses to care for veterans, service members, and their families. The progress toward meeting the Joining Forces pledge and integrating veteran-centered learning in an on-line registered nurse-to-bachelor of science in nursing program is described. [ABSTRACT FROM AUTHOR]

Background The receptive field (RF) represents the signal preferences of sensory neurons and is the primary analysis method for understanding sensory coding. While it is essential to estimate a neuron's RF, finding numerical solutions to increasingly complex RF models can become computationally intensive, in particular for high-dimensional stimuli or when many neurons are involved. New method Here we propose an optimization scheme based on stochastic approximations that facilitate this task. The basic idea is to derive solutions on a random subset rather than computing the full solution on the available data set. To test this, we applied different optimization schemes based on stochastic gradient descent (SGD) to both the generalized linear model (GLM) and a recently developed classification-based RF estimation approach. Results and comparison with existing method Using simulated and recorded responses, we demonstrate that RF parameter optimization based on state-of-the-art SGD algorithms produces robust estimates of the spectro-temporal receptive field (STRF). Results on recordings from the auditory midbrain demonstrate that stochastic approximations preserve both predictive power and tuning properties of STRFs. A correlation of 0.93 with the STRF derived from the full solution may be obtained in less than 10% of the full solution's estimation time. We also present an on-line algorithm that allows simultaneous monitoring of STRF properties of more than 30 neurons on a single computer. Conclusions The proposed approach may not only prove helpful for large-scale recordings but also provides a more comprehensive characterization of neural tuning in experiments than standard tuning curves. [ABSTRACT FROM AUTHOR]

On-line portfolio selection, a fundamental problem in computational finance, has attracted increasing interest from artificial intelligence and machine learning communities in recent years. Empirical evidence shows that stock's high and low prices are temporary and stock prices are likely to follow the mean reversion phenomenon. While existing mean reversion strategies are shown to achieve good empirical performance on many real datasets, they often make the single-period mean reversion assumption, which is not always satisfied, leading to poor performance in certain real datasets. To overcome this limitation, this article proposes a multiple-period mean reversion , or so-called “Moving Average Reversion” (MAR), and a new on-line portfolio selection strategy named “On-Line Moving Average Reversion” (OLMAR), which exploits MAR via efficient and scalable online machine learning techniques. From our empirical results on real markets, we found that OLMAR can overcome the drawbacks of existing mean reversion algorithms and achieve significantly better results, especially on the datasets where existing mean reversion algorithms failed. In addition to its superior empirical performance, OLMAR also runs extremely fast, further supporting its practical applicability to a wide range of applications. Finally, we have made all the datasets and source codes of this work publicly available at our project website: http://OLPS.stevenhoi.org/ . [ABSTRACT FROM AUTHOR]

The development of an effective maximum power point tracking (MPPT) algorithm is important in order to achieve maximum power operation in a photovoltaic system (PV). In this study, a direct neural control (DNC) scheme is developed. The intelligent MPPT controller consists of a hybrid learning mechanism; an on-line learning rule based on gradient decent method and an off-line learning rule based on Big Bang–Big Crunch (BB–BC) algorithm. The effectiveness of the proposed system is tested under partial shading conditions by applying the cascaded converter topology. The feasibility of the DNC is evaluated by the simulation results and compared to the conventional perturbation and observation (P&O) method. [ABSTRACT FROM AUTHOR]

Abstract: This paper proposes a multiple kernel regression (MKr) to predict water demand in the presence of a continuous source of infor- mation. MKr extends the simple support vector regression (SVR) to a combination of kernels from as many distinct types as kinds of input data are available. In addition, two on-line learning methods to obtain real time predictions as new data arrives to the system are tested by a real-world case study. The accuracy and computational efficiency of the results indicate that our proposal is a suitable tool for making adequate management decisions in the smart cities environment. [Copyright &y& Elsevier]

Summary: Background: The learning of biosciences is well-documented to be problematic as students find the subjects amongst the most difficult and anxiety-provoking of their pre-registration programme. Studies suggest that learning consequently is not at the level anticipated by the profession. Curriculum innovations might improve the situation but the effectiveness of applied interventions has not been evaluated. Objective: To undertake an integrative review and narrative synthesis of curriculum interventions and evaluate their effect on the learning of biosciences by pre-registration student nurses. Review methods A systematic search of electronic databases CINAHL, Medline, British Nursing Index and Google Scholar for empirical research studies was designed to evaluate the introduction of a curriculum intervention related to the biosciences, published in 1990–2012. Studies were evaluated for design, receptivity of the intervention and impact on bioscience learning. Results: The search generated fourteen papers that met inclusion criteria. Seven studies introduced on-line learning packages, five an active learning format into classroom teaching or practical sessions, and two applied Audience Response Technology as an exercise in self-testing and reflection. Almost all studies reported a high level of student satisfaction, though in some there were access/utilization issues for students using on-line learning. Self-reporting suggested positive experiences, but objective evaluation suggests that impacts on learning were variable and unconvincing even where an effect on course progress was identified. Adjunct on-line programmes also show promise for supporting basic science or language acquisition. Conclusions: Published studies of curriculum interventions, including on-line support, have focused too heavily on the perceived benefit to students rather than objective measures of impact on actual learning. Future studies should include rigorous assessment evaluations within their design if interventions are to be adopted to reduce the ‘bioscience problem’. [Copyright &y& Elsevier]

Abstract: Incremental algorithms for fuzzy classifiers are studied in this paper. It is assumed that not all training patterns are given a priori for training classifiers, but are gradually made available over time. It is also assumed that the previously available training patterns can not be used afterwards. Thus, fuzzy classifiers should be modified by updating already constructed classifiers using the available training patterns. In this paper, a confidence-weighted (CW) learning algorithm is applied to fuzzy classifiers for this task. A series of computational experiments are conducted in order to examine the performance of the proposed method comparing that method with the conventional learning algorithm for fuzzy classifiers. [Copyright &y& Elsevier]

Abstract: This paper presents recurring concept drifts (RCD), a framework that offers an alternative approach to handle data streams that suffer from recurring concept drifts (on-line learning). It creates a new classifier to each context found and stores a sample of data used to build it. When a new concept drift occurs, the algorithm compares the new context to previous ones using a non-parametric multivariate statistical test to verify if both contexts come from the same distribution. If so, the corresponding classifier is reused. The RCD framework is compared with several algorithms (among single and ensemble approaches), in both artificial and real data sets, chosen from frequently used algorithms and data sets in the concept drift research area. We claim the proposed framework had better average ranks in data sets with abrupt and gradual concept drifts compared to both the single classifiers and the ensemble approaches that use the same base learner. [Copyright &y& Elsevier]

Abstract: This paper presents a novel incremental orthogonal projective non-negative matrix factorization (IOPNMF) algorithm, which is aimed to learn a parts-based subspace that reveals dynamic data streams. By assuming that the newly added samples only affect basis vectors but do not affect the coefficients of old samples, we propose an objective function for on-line learning and then present a multiplicative update rule to solve it. Compared with other non-negative matrix factorization (NMF) methods, our algorithm can guarantee to learn a linear parts-based subspace in an on-line fashion, which may facilitate some real applications. The facial analysis experiment shows that our IOPNMF method learns parts-based components successfully. In addition, we present an effective tracking method by integrating the IOPNMF method, the idea of sparse representation and the domain information of object tracking. The proposed tracker explicitly takes partial occlusion and mis-alignment into account for appearance model update and object tracking. The experimental results on some challenging image sequences demonstrate the proposed tracking algorithm performs favorably against several state-of-the-art methods. [Copyright &y& Elsevier]

Abstract: Objective: Blended learning is a relatively new technology-based teaching approach. Few attempts have been made to use this approach in medical education. The aim of this study was to assess the effectiveness of blended learning in studying family medicine as an example of a clinical medical science. Methods: This comparative cross-sectional study involved 121 fourth-year medical students, at the clinical phase of a family medicine course at the College of Medicine, Taibah University, Almadinah Almunawwarah, Kingdom of Saudi Arabia. The students were randomly divided into two groups: 61 taught by the traditional approach (face-to-face) and 60 taught by blended learning (both electronic and face-to-face). The effect of blended learning was evaluated from responses to the Dundee ‘ready education environment measure’ questionnaire. Clinical skills were assessed with the ‘objective structured clinical examination’; knowledge gain was assessed from a written multiple-choice examination; and problem-solving, critical thinking, decision-making skills and attitude were assessed in written and oral examinations based on clinical scenarios. Results: Blended learning was statistically significantly better than traditional learning in all domains of the educational environment, except for social perception, and in all types of examination: written, objective structured clinical and case scenarios. Conclusion: The findings suggest that medical students, as adult learners, are open to new methods of learning. The blended learning approach is an effective method for teaching family medicine and may be applicable to other clinical medical sciences. [Copyright &y& Elsevier]

Abstract: Usually, vehicle applications need to use artificial intelligence techniques to implement control strategies able to deal with the noise in the signals provided by sensors, or with the impossibility of having full knowledge of the dynamics of a vehicle (engine state, wheel pressure, or occupants’ weight). This work presents a cruise control system which is able to manage the pedals of a vehicle at low speeds. In this context, small changes in the vehicle or road conditions can occur unpredictably. To solve this problem, a method is proposed to allow the on-line evolution of a zero-order TSK fuzzy controller to adapt its behaviour to uncertain road or vehicle dynamics. Starting from a very simple or even empty configuration, the consequents of the rules are adapted in real time, while the membership functions used to codify the input variables are modified after a certain period of time. Extensive experimentation in both simulated and real vehicles showed the method to be both fast and precise, even when compared with a human driver. [Copyright &y& Elsevier]

Abstract: Problem-based learning has been demonstrated as an effective methodology for developing analytical skills and critical thinking. The use of scenario-based learning incorporates problem-based learning whilst encouraging students to collaborate with their colleagues and dynamically adapt to their environment. This increased interaction stimulates a deeper understanding and the generation of new knowledge. The Victorian Space Science Education Centre (VSSEC) uses scenario-based learning in its Mission to Mars, Mission to the Orbiting Space Laboratory and Primary Expedition to the M.A.R.S. Base programs. These programs utilize methodologies such as hands-on applications, immersive-learning, integrated technologies, critical thinking and mentoring to engage students in Science, Technology, Engineering and Mathematics (STEM) and highlight potential career paths in science and engineering. The immersive nature of the programs demands specialist environments such as a simulated Mars environment, Mission Control and Space Laboratory, thus restricting these programs to a physical location and limiting student access to the programs. To move beyond these limitations, VSSEC worked with its university partners to develop a web-based mission that delivered the benefits of scenario-based learning within a school environment. The Robotic Mission to Mars allows students to remotely control a real rover, developed by the Australian Centre for Field Robotics (ACFR), on the VSSEC Mars surface. After completing a pre-mission training program and site selection activity, students take on the roles of scientists and engineers in Mission Control to complete a mission and collect data for further analysis. Mission Control is established using software developed by the ACRI Games Technology Lab at La Trobe University using the principles of serious gaming. The software allows students to control the rover, monitor its systems and collect scientific data for analysis. This program encourages students to work scientifically and explores the interaction between scientists and engineers. This paper presents the development of the program, including the involvement of university students in the development of the rover, the software, and the collation of the scientific data. It also presents the results of the trial phase of this program including the impact on student engagement and learning outcomes. [Copyright &y& Elsevier]

Abstract: This paper investigates the development and experimental implementation of an adaptive dynamic nonlinear model inversion control law for a Twin Rotor MIMO System (TRMS) using artificial neural networks. The TRMS is a highly nonlinear aerodynamic test rig with complex cross-coupled dynamics and therefore represents the control challenges of modern air vehicles. A highly nonlinear 1DOF mathematical model of the TRMS is considered in this study and a nonlinear inverse model is developed for the pitch channel of the system. An adaptive neural network element is integrated thereafter with the feedback control system to compensate for model inversion errors. The proposed on-line learning algorithm updates the weights and biases of the neural network using the error between the set-point and the real output. The real-time response of the method shows a satisfactory tracking performance in the presence of inversion errors caused by model uncertainty. The approach is therefore deemed to be suitable to apply real-time to other nonlinear systems with necessary modifications. [Copyright &y& Elsevier]

Abstract: Although Stochastic Context-Free Grammars (SCFGs) appear promising for the recognition and threat assessment of complex radar emitters in radar Electronic Support (ES) systems, techniques for learning their production rule probabilities are computationally demanding, and cannot efficiently reflect changes in operational environments. On-line learning techniques are needed in ES applications to adapt SCFG probabilities rapidly, as new training data are collected from the field. In this paper, an efficient on-line version of the fast learning technique known as the graphical Expectation-Maximization (gEM) technique – called on-line gEM (ogEM) – is proposed. A second technique called on-line gEM with discount factor (ogEM-df) expands ogEM to allow for tuning the learning rate. The performance of these new techniques has been compared to HOLA, the only other fast on-line learning technique, from several perspectives – perplexity, error rate, complexity, and convergence time – and using complex radar signals. The impact on performance of factors like the size of new data blocks, and the level of ambiguity of grammars has been observed. Results indicate that on-line learning of new training data blocks with ogEMand ogEM-df provides the same level of accuracy as batch learning with gEM using all cumulative data from the start, even for small data blocks. As expected, on-line learning significantly reduces the overall time and memory complexities associated with updating probabilities with new data in an operational environment. Finally, while the computational complexity and memory requirements of ogEM and ogEM-df may be greater than that of HOLA, they both provide a significantly higher level of accuracy. [Copyright &y& Elsevier]

Abstract: This paper introduces a collaborative personal speaker identification system to annotate conversations and meetings using speech-independent speaker modeling and one audio channel. This system can operate in standalone and collaborative modes, and learn about speakers online that were detected as unknown. In collaborative mode, the system exchanges current speaker information with personal systems of others to improve identification performance. Our collaboration concept is based on distributed personal systems only, hence it does not require a specific infrastructure to operate. We present a generalized description of collaboration situations and derive three use scenarios in which the system was subsequently evaluated. Compared to standalone operation, collaboration among four personal identification systems increased system performance by up to 9% for 4 relevant speakers and up to 21% for 24 relevant speakers. Allowing unknown speakers in a conversation did not impede performance gains of a collaboration. In a scenario where individual systems had nonidentical speaker sets, collaboration gains were 16% for 24 relevant speakers. [Copyright &y& Elsevier]

Abstract: Classifier grids have shown to be a considerable choice for object detection from static cameras. By applying a single classifier per image location the classifier’s complexity can be reduced and more specific and thus more accurate classifiers can be estimated. In addition, by using an on-line learner a highly adaptive but stable detection system can be obtained. Even though long-term stability has been demonstrated such systems still suffer from short-term drifting if an object is not moving over a long period of time. The goal of this work is to overcome this problem and thus to increase the recall while preserving the accuracy. In particular, we adapt ideas from multiple instance learning (MIL) for on-line boosting. In contrast to standard MIL approaches, which assume an ambiguity on the positive samples, we apply this concept to the negative samples: inverse multiple instance learning. By introducing temporal bags consisting of background images operating on different time scales, we can ensure that each bag contains at least one sample having a negative label, providing the theoretical requirements. The experimental results demonstrate superior classification results in presence of non-moving objects. [Copyright &y& Elsevier]

Abstract: Due to the widespread use of cameras, it is very common to collect thousands of personal photos. A proper organization is needed to make the collection usable and to enable an easy photo retrieval. In this paper, we present a method to organize personal photo collections based on “who” is in the picture. Our method consists in detecting the faces in the photo sequence and arranging them in groups corresponding to the probable identities. This problem can be conveniently modeled as a multi-target visual tracking where a set of on-line trained classifiers is used to represent the identity models. In contrast to other works where clustering methods are used, our method relies on a probabilistic framework; it does not require any prior information about the number of different identities in the photo album. To enable future comparison, we present experimental results on a public dataset and on a photo collection generated from a public face dataset. [Copyright &y& Elsevier]

Abstract: In this paper a novel architecture for implementing multi-layer perceptron (MLP) neural networks on field programmable gate arrays (FPGA) is presented. The architecture presents a new scalable design that allows variable degrees of parallelism in order to achieve the best balance between performance and FPGA resources usage. Performance is enhanced using a highly efficient pipelined design. Extensive analysis and simulations have been conducted on four standard benchmark problems. Results show that a minimum performance boost of three orders of magnitude (O 3) over software implementation is regularly achieved. We report performance of 2–67GCUPS for these simple problems, and performance reaching over 1TCUPS for larger networks and different single FPGA chips. To our knowledge, this is the highest speed reported to date for any MLP network implementation on FPGAs. [Copyright &y& Elsevier]

Abstract: In this study, we propose a dynamical memory strategy to efficiently control the size of the support set in a kernel-based Perceptron learning algorithm. The method consists of two operations, namely, the incremental and decremental projections. In the incremental projection, a new presented instance is either added to the support set or discarded depending on a predefined rule. To diminish information loss, we do not throw away those discarded examples cheaply, instead their impact to the discriminative function is sustained by a projection technique, which maps the modified discriminative function into the space spanned by the original support set. When a new example is added to the support set, the algorithm moves to the decremental projection. We evaluate the minimum information loss by deleting one instance from the support set. If this minimum information loss is less than a tolerable threshold, then the corresponding instance is removed, however, its contribution to the discriminative function is reserved by the projection technique. By this, our method can on one hand keep a relatively small size of the support set and on the other hand achieve a high classification accuracy. We also develop a method which sets a budget for the size of the support set. We test our approaches to four benchmark data sets, and find that our methods outperform others in either having higher classification accuracies when the sizes of their support sets are comparable or having smaller sizes of the support sets when their classification accuracies are similar. [Copyright &y& Elsevier]

Abstract: This paper considers on-line training of feedforward neural networks. Training examples are only available through sampling from a certain, possibly infinite, distribution. In order to make the learning process autonomous, one can employ Extended Kalman Filter or stochastic steepest descent with adaptively adjusted step-sizes. Here the latter is considered. A scheme of determining step-sizes is introduced that satisfies the following requirements: (i) it does not need any auxiliary problem-dependent parameters, (ii) it does not assume any particular loss function that the training process is intended to minimize, (iii) it makes the learning process stable and efficient. An experimental study with several approximation problems is presented. Within this study the presented approach is compared with Extended Kalman Filter and LFI, with satisfactory results. [Copyright &y& Elsevier]

Asynchronous communication has become the dominant mode of on-line instruction and has been incorporated into Flying Start NHS, an on-line programme for newly qualified NMAHPs in the transition phase from student to registered practitioner. On-line programmes have a number of objectives including the delivery of educational materials and the development of on-line communities. This study sought to provide a direct and objective understanding of the quality of the on-line community within Flying Start NHS and give an indication of areas of strength and weakness. The study used mixed methods including a Gricean analysis of on-line communication focusing on quantity, quality, relevance, and manner, and a thematic analysis of communication content. There was little evidence that students engaged in the type of interactive communication essential for creating on-line learning communities. The majority of postings related to progression through Flying Start. The small number of communications which did begin to engage with the learning materials were limited with little evidence of the development of critical debate. Analysis of the qualitative data indicates that the period of transition continues to be stressful with Flying Start NHS being undertaken concurrently with local CPD being seen as duplication of effort. [ABSTRACT FROM AUTHOR]

Abstract: This work proposes an indirect adaptive nonlinear control scheme based on a recurrent neural network and the output regulation theory. The neural model is first trained off-line, being further improved by means of an on-line learning strategy using the Lyapunov and nonlinear observation theories. The regulation problem is solved by an iterative strategy, formulated as an eigenvalue assignment problem, ensuring the convergence of the regulation equations. The strategy was tested on a distributed collector field of a solar power plant (Plataforma Solar de Almería, Spain). Experimental results, collected on the solar power plant, show the effectiveness of the proposed approach. [Copyright &y& Elsevier]

Abstract: A semi-supervised learning method, the on-line accelerated kernel feature analysis (On-line AKFA) is presented. In On-line AKFA, features are extracted while data are being fed to the algorithm in small batches as the algorithm proceeds. The paper compares and contrasts the use of On-line AKFA and Off-line AKFA in CT colonography. On-line AKFA provides the flexibility to allow the feature space to dynamically adjust to changes in the input data with time during the training phase. The computational time, reconstruction accuracy, projection variance, and classification performance of the proposed method are experimentally evaluated for kernel principal component analysis (KPCA), Off-line AKFA, and On-line AKFA. Experimental results demonstrate a significant reduction in computation time for On-line AKFA compared to the other feature extraction methods considered in this paper. [Copyright &y& Elsevier]

Abstract: We consider the problem of learning to predict as well as the best in a group of experts making continuous predictions. We assume the learning algorithm has prior knowledge of the maximum number of mistakes of the best expert. We propose a new master strategy that achieves the best known performance for on-line learning with continuous experts in the mistake bounded model. Our ideas are based on drifting games, a generalization of boosting and on-line learning algorithms. We prove new lower bounds based on the drifting games framework which, though not as tight as previous bounds, have simpler proofs and do not require an enormous number of experts. We also extend previous lower bounds to show that our upper bounds are exactly tight for sufficiently many experts. A surprising consequence of our work is that continuous experts are only as powerful as experts making binary or no prediction in each round. [Copyright &y& Elsevier]

Abstract: Support vector machines (SVMs) are one of the most successful algorithms for classification. However, due to their space and time requirements, they are not suitable for on-line learning, that is, when presented with an endless stream of training observations. In this paper we propose a new on-line algorithm, called on-line independent support vector machines (OISVMs), which approximately converges to the standard SVM solution each time new observations are added; the approximation is controlled via a user-defined parameter. The method employs a set of linearly independent observations and tries to project every new observation onto the set obtained so far, dramatically reducing time and space requirements at the price of a negligible loss in accuracy. As opposed to similar algorithms, the size of the solution obtained by OISVMs is always bounded, implying a bounded testing time. These statements are supported by extensive experiments on standard benchmark databases as well as on two real-world applications, namely place recognition by a mobile robot in an indoor environment and human grasping posture classification. [Copyright &y& Elsevier]

Abstract: This paper proposes a web-based interactive speaking improvement system for EFL learners. Using fuzzy matching, the system automatically compares the learner’s and the system’s pronunciation and immediately provides corrective interaction whereby the student can improve speaking via continuous imitation and practice at the computer. The system, having been tested on Taiwanese students who needed to achieve a speaking proficiency equivalent to CEF Level A2, is found to be highly effective for the intended purpose. [Copyright &y& Elsevier]

Abstract: This paper investigates procedures for on-line learning and improvement with wave-nets utilizing a stream of data and then applies these methods to an experimental thermal process. Wave-nets are wavelet based neural networks with localized and hierarchical multi-resolution learning. The multi-resolution framework of wave-nets allows non-linear modeling of any complicated systems. The recently developed on-line features to wave-net learning have enhanced their capability in learning and adaptation of any non-linear time varying systems (with low dimensions). A real experimental time varying thermal process is modeled and the on-line learning was implemented to show the applicability of these algorithms. The platform used for the real-time implementation is MATLAB/Real-Time-Toolbox with a DAQ interface. The results show the effectiveness of the methods. [Copyright &y& Elsevier]

Abstract: There has been an increasing interest in the study of video based fire detection algorithms as video based surveillance systems become widely available for indoor and outdoor monitoring applications. A novel method explicitly developed for video based detection of wildfires at night (in the dark) is presented in this paper. The method comprises four sub-algorithms: (i) slow moving video object detection, (ii) bright region detection, (iii) detection of objects exhibiting periodic motion, and (iv) a sub-algorithm interpreting the motion of moving regions in video. Each of these sub-algorithms characterizes an aspect of fire captured at night by a visible range PTZ camera. Individual decisions of the sub-algorithms are combined together using a least-mean-square (LMS) based decision fusion approach, and fire/nofire decision is reached by an active learning method. [Copyright &y& Elsevier]

Abstract: The lack of an energy function is an important problem in many topographic map formation methods. This paper describes formation of a map, called linear manifold topographic map, based on minimization of an energy function. Using multiple low-dimensional linear manifolds as data representation elements, the data distributions of many problems with high-dimensional data spaces can be simply and parsimoniously modeled. Two sets of on-line adaptation rules are obtained based on stochastic gradient descent on the energy functions devised for a soft and a hard data assignment. Experimental results show good performance of the map in comparison to other relevant techniques. [Copyright &y& Elsevier]