Cluster kernels for semisupervised classification of VHR urban images

In this paper, we present and apply a semisupervised support vector machine based on cluster kernels for the problem of very high resolution image classification. In the proposed setting, a base kernel working with labeled samples only is deformed by a likelihood kernel encoding similarities between unlabeled examples. The resulting kernel is used to train a standard support vector machine (SVM) classifier. Experiments carried out on very high resolution (VHR) multispectral and hyperspectral images using very few labeled examples show the relevancy of the method in the context of urban image classification. Its simplicity and the small number of parameters involved make it versatile and workable by unexperimented users.

Hybrid coordination of reinforcement learning-based behaviors for AUV control

This paper proposes a hybrid coordination method for behavior-based control architectures. The hybrid method takes advantages of the robustness and modularity in competitive approaches as well as optimized trajectories in cooperative ones. This paper shows the feasibility of applying this hybrid method with a 3D-navigation to an autonomous underwater vehicle (AUV). The behaviors are learnt online by means of reinforcement learning. A continuous Q-learning implemented with a feed-forward neural network is employed. Realistic simulations were carried out. The results obtained show the good performance of the hybrid method on behavior coordination as well as the convergence of the behaviors

Efficient learning of reactive robot behaviors with a Neural-Q_learning approach

The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

A behavior-based scheme using reinforcement learning for autonomous underwater vehicles

This paper presents a hybrid behavior-based scheme using reinforcement learning for high-level control of autonomous underwater vehicles (AUVs). Two main features of the presented approach are hybrid behavior coordination and semi on-line neural-Q_learning (SONQL). Hybrid behavior coordination takes advantages of robustness and modularity in the competitive approach as well as efficient trajectories in the cooperative approach. SONQL, a new continuous approach of the Q_learning algorithm with a multilayer neural network is used to learn behavior state/action mapping online. Experimental results show the feasibility of the presented approach for AUVs

Policy gradient based Reinforcement Learning for real autonomous underwater cable tracking

This paper proposes a field application of a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot in cable tracking task. The learning system is characterized by using a direct policy search method for learning the internal state/action mapping. Policy only algorithms may suffer from long convergence times when dealing with real robotics. In order to speed up the process, the learning phase has been carried out in a simulated environment and, in a second step, the policy has been transferred and tested successfully on a real robot. Future steps plan to continue the learning process on-line while on the real robot while performing the mentioned task. We demonstrate its feasibility with real experiments on the underwater robot ICTINEU AUV

Autonomous underwater vehicle control using reinforcement learning policy search methods

Autonomous underwater vehicles (AUV) represent a challenging control problem with complex, noisy, dynamics. Nowadays, not only the continuous scientific advances in underwater robotics but the increasing number of subsea missions and its complexity ask for an automatization of submarine processes. This paper proposes a high-level control system for solving the action selection problem of an autonomous robot. The system is characterized by the use of reinforcement learning direct policy search methods (RLDPS) for learning the internal state/action mapping of some behaviors. We demonstrate its feasibility with simulated experiments using the model of our underwater robot URIS in a target following task

Towards Direct Policy Search Reinforcement Learning for Robot Control

This paper proposes a high-level reinforcement learning (RL) control system for solving the action selection problem of an autonomous robot. Although the dominant approach, when using RL, has been to apply value function based algorithms, the system here detailed is characterized by the use of direct policy search methods. Rather than approximating a value function, these methodologies approximate a policy using an independent function approximator with its own parameters, trying to maximize the future expected reward. The policy based algorithm presented in this paper is used for learning the internal state/action mapping of a behavior. In this preliminary work, we demonstrate its feasibility with simulated experiments using the underwater robot GARBI in a target reaching task

Improvement of antibiotic prescription in outpatient care: a cluster-randomized intervention study using a sentinel surveillance network of physicians.

OBJECTIVES: To assess the effectiveness of implementing guidelines, coupled with individual feedback, on antibiotic prescribing behaviour of primary care physicians in Switzerland. METHODS: One hundred and forty general practices from a representative Swiss sentinel network of primary care physicians participated in this cluster-randomized prospective intervention study. The intervention consisted of providing guidelines on treatment of respiratory tract infections (RTIs) and uncomplicated lower urinary tract infections (UTIs), coupled with sustained, regular feedback on individual antibiotic prescription behaviour during 2 years. The main aims were: (i) to increase the percentage of prescriptions of penicillins for all RTIs treated with antibiotics; (ii) to increase the percentage of trimethoprim/sulfamethoxazole prescriptions for all uncomplicated lower UTIs treated with antibiotics; (iii) to decrease the percentage of quinolone prescriptions for all cases of exacerbated COPD (eCOPD) treated with antibiotics; and (iv) to decrease the proportion of sinusitis and other upper RTIs treated with antibiotics. The study was registered at ClinicalTrials.gov (NCT01358916). RESULTS: While the percentage of antibiotics prescribed for sinusitis or other upper RTIs and the percentage of quinolones prescribed for eCOPD did not differ between the intervention group and the control group, there was a significant increase in the percentage of prescriptions of penicillins for all RTIs treated with antibiotics [57% versus 49%, OR=1.42 (95% CI 1.08-1.89), P=0.01] and in the percentage of trimethoprim/sulfamethoxazole prescriptions for all uncomplicated lower UTIs treated with antibiotics [35% versus 19%, OR=2.16 (95% CI 1.19-3.91), P=0.01] in the intervention group. CONCLUSIONS: In our setting, implementing guidelines, coupled with sustained individual feedback, was not able to reduce the proportion of sinusitis and other upper RTIs treated with antibiotics, but increased the use of recommended antibiotics for RTIs and UTIs, as defined by the guidelines.

Visuo-motor and cognitive procedural learning in children with basal ganglia pathology.

We investigated procedural learning in 18 children with basal ganglia (BG) lesions or dysfunctions of various aetiologies, using a visuo-motor learning test, the Serial Reaction Time (SRT) task, and a cognitive learning test, the Probabilistic Classification Learning (PCL) task. We compared patients with early (<1 year old, n=9), later onset (>6 years old, n=7) or progressive disorder (idiopathic dystonia, n=2). All patients showed deficits in both visuo-motor and cognitive domains, except those with idiopathic dystonia, who displayed preserved classification learning skills. Impairments seem to be independent from the age of onset of pathology. As far as we know, this study is the first to investigate motor and cognitive procedural learning in children with BG damage. Procedural impairments were documented whatever the aetiology of the BG damage/dysfunction and time of pathology onset, thus supporting the claim of very early skill learning development and lack of plasticity in case of damage.

Adaptive intelligent agent approach to guide the web navigation on the PLAN-G distance learning platform

Hypermedia systems based on the Web for open distance education are becoming increasinglypopular as tools for user-driven access learning information. Adaptive hypermedia is a new direction in research within the area of user-adaptive systems, to increase its functionality by making it personalized [Eklu 961. This paper sketches a general agents architecture to include navigationaladaptability and user-friendly processes which would guide and accompany the student during hislher learning on the PLAN-G hypermedia system (New Generation Telematics Platform to Support Open and Distance Learning), with the aid of computer networks and specifically WWW technology [Marz 98-1] [Marz 98-2]. The PLAN-G actual prototype is successfully used with some informatics courses (the current version has no agents yet). The propased multi-agent system, contains two different types of adaptive autonomous software agents: Personal Digital Agents {Interface), to interacl directly with the student when necessary; and Information Agents (Intermediaries), to filtrate and discover information to learn and to adapt navigation space to a specific student

Assessing the Precision of Compositional Data in a Stratified Double Stage Cluster Sample: Application to the Swiss Earnings Structure Survey

Precision of released figures is not only an important quality feature of official statistics,it is also essential for a good understanding of the data. In this paper we show a casestudy of how precision could be conveyed if the multivariate nature of data has to betaken into account. In the official release of the Swiss earnings structure survey, the totalsalary is broken down into several wage components. We follow Aitchison's approachfor the analysis of compositional data, which is based on logratios of components. Wefirst present diferent multivariate analyses of the compositional data whereby the wagecomponents are broken down by economic activity classes. Then we propose a numberof ways to assess precision

A teaching/learning support tool for introductory programming courses

In This work we present a Web-based tool developed with the aim of reinforcing teaching and learning of introductory programming courses. This tool provides support for teaching and learning. From the teacher's perspective the system introduces important gains with respect to the classical teaching methodology. It reinforces lecture and laboratory sessions, makes it possible to give personalized attention to the student, assesses the degree of participation of the students and most importantly, performs a continuous assessment of the student's progress. From the student's perspective it provides a learning framework, consisting in a help environment and a correction environment, which facilitates their personal work. With this tool students are more motivated to do programming

Effect of a general school-based physical activity intervention on bone mineral content and density: A cluster-randomized controlled trial.

Background: Specific physical loading leads to enhanced bone development during childhood. A general physical activity program mimicking a real-life situation was successful at increasing general physical health in children. Yet, it is not clear whether it can equally increase bone mineral mass. We performed a cluster-randomized controlled trial in children of both gender and different pubertal stages to determine whether a school-based physical activity (PA) program during one school-year influences bone mineral content (BMC) and density (BMD), irrespective of gender.Methods: Twenty-eight 1st and 5th grade (6-7 and 11-12 year-old) classes were cluster randomized to an intervention (INT, 16 classes, n = 297) and control (CON; 12 classes, n = 205) group. The intervention consisted of a multi-component PA intervention including daily physical education with at least 10 min of jumping or strength training exercises of various intensities. Measurements included anthropometry, and BMC and BMD of total body, femoral neck, total hip and lumbar spine using dual-energy X-ray absorptiometry (DXA). PA was assessed by accelerometers and Tanner stages by questionnaires. Analyses were performed by a regression model adjusted for gender, baseline height and weight, baseline PA, post-intervention pubertal stage, baseline BMC, and cluster.Results: 275 (72%) of 380 children who initially agreed to have DXA measurements had also post-intervention DXA and PA data. Mean age of prepubertal and pubertal children at baseline was 8.7 +/- 2.1 and 11.1 +/- 0.6 years, respectively. Compared to CON, children in INT showed statistically significant increases in BMC of total body, femoral neck, and lumbar spine by 5.5%, 5.4% and 4.7% (all p < 0.05), respectively, and BMD of total body and lumbar spine by 8.4% and 7.3% (both p < 0.01), respectively. There was no gender*group, but a pubertal stage*group interaction consistently favoring prepubertal children.Conclusion: A general school-based PA intervention can increase bone health in elementary school children of both genders, particularly before puberty. (C) 2010 Elsevier Inc. All rights reserved.