Reinforcement learning of pedagogical policies in adaptive and intelligent educational systems

In an adaptive and intelligent educational system (AIES), the process of learning pedagogical policies according the students needs fits as a Reinforcement Learning (RL) problem. Previous works have demonstrated that a great amount of experience is needed in order for the system to learn to teach properly, so applying RL to the AIES from scratch is unfeasible. Other works have previously demonstrated in a theoretical way that seeding the AIES with an initial value function learned with simulated students reduce the experience required to learn an accurate pedagogical policy. In this paper we present empirical results demonstrating that a value function learned with simulated students can provide the AIES with a very accurate initial pedagogical policy. The evaluation is based on the interaction of more than 70 Computer Science undergraduate students, and demonstrates that an efficient and useful guide through the contents of the educational system is obtained.     

Relational Learning with GPUs: Accelerating Rule Coverage

Relational learning algorithms mine complex databases for interesting patterns. Usually, the search space of patterns grows very quickly with the increase in data size, making it impractical to solve important problems. In this work we present the design of a relational learning system, that takes advantage of graphics processing units (GPUs) to perform the most time consuming function of the learner, rule coverage. To evaluate performance, we use four applications: a widely used relational learning benchmark for predicting carcinogenesis in rodents, an application in chemo-informatics, an application in opinion mining, and an application in mining health record data. We compare results using a single and multiple CPUs in a multicore host and using the GPU version. Results show that the GPU version of the learner is up to eight times faster than the best CPU version.     

Micromixing with spark-generated cavitation bubbles

The intrinsic laminarity of microfluidic devices impedes the mixing of multiple fluids over short temporal or spatial scales. Despite the existence of several mixers capable of stirring and stretching the flows to promote mixing, most approaches sacrifice temporal or spatial control, portability, or flexibility in terms of operating flow rates. Here, we report a novel method for rapid micromixing based on the generation of cavitation bubbles. By using a portable battery-powered electric circuit, we induce a localized electric spark between two tip electrodes perpendicular to the flow channel that results in several cavitation events. As a result, a vigorous stirring mechanism is induced. We investigate the spatiotemporal dynamics of the spark-generated cavitation bubbles and quantify the created flow disturbance. We demonstrate rapid (in the millisecond timescale) and efficient micromixing (up to 98%) within a length scale of only 200 µm and over a flow rate ranging from 5 to 40 µL/min.     

Microfluidic device with dual-channel fluorescence acquisition for quantification/identification of cancer cells

This paper presents an optofluidic device for cell discrimination with two independent interrogation regions. Pumping light is coupled to the device, and cell fluorescence is extracted from the two interrogation zones by using optical fibers embedded in the optofluidic chip. To test the reliability of this device, AU-565 cells—expressing EpCAM and HER2 receptors—and RAMOS cells were mixed in a controlled manner, confined inside a hydrodynamic focused flow in the microfluidic chip and detected individually so that they could be discriminated as positive (signal reception from fluorescently labeled antibodies from the AU-565 cells) or negative events (RAMOS cells). A correlation analysis of the two signals reduces the influence of noise on the overall data.     

Semantic-based authorization architecture for Grid

There are a few issues that still need to be covered regarding security in the Grid area. One of them is authorization where there exist good solutions to define, manage and enforce authorization policies in Grid scenarios. However, these solutions usually do not provide Grid administrators with semantic-aware components closer to the particular Grid domain and easing different administration tasks such as conflict detection or resolution. This paper defines a proposal based on Semantic Web to define, manage and enforce security policies in a Grid scenario. These policies are defined by means of semantic-aware rules which help the administrator to create higher-level definitions with more expressiveness. These rules also permit performing added-value tasks such as conflict detection and resolution, which can be of interest in medium and large scale scenarios where different administrators define the authorization rules that should be followed before accessing a resource in the Grid. The proposed solution has been also tested providing some reasonable response times in the authorization decision process.     

Proof Pearl: a Formal Proof of Higman��s Lemma in ACL2

Higman??s lemma is an important result in infinitary combinatorics, which has been formalized in several theorem provers. In this paper we present a formalization and proof of Higman??s Lemma in the ACL2 theorem prover. Our formalization is based on a proof by Murthy and Russell, where the key termination argument is justified by the multiset relation induced by a well-founded relation. To our knowledge, this is the first mechanization of this proof.     

Applying intelligent agents and semantic web services in eGovernment environments

The increasing volume of eGovernment‐related services is demanding new approaches for service integration and interoperability in this domain. Semantic web (SW) technologies and applications can leverage the potential of eGovernment service integration and discovery, thus tackling the problems of semantic heterogeneity characterizing eGovernment information sources and the different levels of interoperability. eGovernment services will therefore be semantically described in the foreseeable future. In an environment with semantically annotated services, software agents are essential as the entities responsible for exploiting the semantic content in order to automate some tasks, and so enhance the user's experience. In this paper, we present a framework that provides a seamless integration of semantic web services and intelligent agents technologies by making use of ontologies to facilitate their interoperation. The proposed framework can assist in the development of powerful and flexible distributed systems in complex, dynamic, heterogeneous, unpredictable and open environments. Our approach is backed up by a proof‐of‐concept implementation, where the breakthrough of integrating disparate eGovernment services has been tested.     

An Analysis of Edge Detection by Using the Jensen-Shannon Divergence

This work constitutes a theoretical study of the edge-detection method by means of the Jensen-Shannon divergence, as proposed by the authors. The overall aim is to establish formally the suitability of the procedure of edge detection in digital images, as a step prior to segmentation. In specific, an analysis is made not only of the properties of the divergence used, but also of the method's sensitivity to the spatial variation, as well as the detection-error risk associated with the operating conditions due to the randomness of the spatial configuration of the pixels. Although the paper deals with the procedure based on the Jensen-Shannon divergence, some problems are also related to other methods based on local detection with a sliding window, and part of the study is focused to noisy and textured images.     

Guidance of a mobile robot using an array of static cameras located in the environment

This paper presents a new proposal for positioning and guiding mobile robots in indoor environments. The proposal is based on the information provided by static cameras located in the movement environment. This proposal falls within the scope of what are known as intelligent environments; in this case, the environment is provided with cameras that, once calibrated, allow the position of the robots to be obtained. Based on this information, control orders for the robots can be generated using a radio frequency link. In order to facilitate identification of the robots, even under extremely adverse ambient lighting conditions, a beacon consisting of four circular elements constructed from infrared diodes is mounted on board the robots. In order to identify the beacon, an edge detection process is carried out. This is followed by a process that, based on the algebraic distance, obtains the estimated ellipses associated with each element of the beacon. Once the beacon has been identified, the coordinates of the centroids for the elements that make up the beacon are obtained on the various image planes. Based on these coordinates, an algorithm is proposed that takes into account the standard deviation of the error produced in the various cameras in ascertaining the coordinates of the beacon’s elements. An odometric system is also used in guidance that, in conjunction with a Kalman Filter, allows the position of the robot to be estimated during the time intervals required to process the visual information provided by the cameras.