Search

University timetabling is a real-world problem frequently encountered in higher education institutions. It has been studied by many researchers who have proposed a wide variety of solutions. Measuring the variation of the performance of solution approaches across instance spaces is a critical factor for algorithm selection and algorithm configuration, but because of the diverse conditions that define the problem within different educational contexts, measurement has not been formally addressed within the university timetabling context. In this paper, we propose a set of metrics to predict the performance of combinatorial optimization algorithms that generate initial solutions for university timetabling instances. These metrics, derived from the fields of enumerative combinatorics and graph coloring, include size-related instance properties, counting functions, feature ratios and constraint indexes evaluated through a feature selection methodology that, based on regression algorithms, characterizes the empirical hardness of a subspace of synthetically generated instances. The results obtained with this methodology show the current need not only to develop solution strategies for particular cases of the problem, but also to produce a formal description of the conditions that make instance spaces hard to solve, in order to improve and integrate the available solution approaches.

Recent advances in computational and electronic technologies, and the application of artificial intelligence algorithms could make it possible to automate the patient monitoring process in order to improve their care and safety. Patient monitoring involves three main procedures: data gathering, data analysis, and feedback generation. On the other hand, artificial intelligence is a computer science field that makes use of mathematical, statistical, and probabilistic techniques in order to classify, learn, plan, or deduce information. This chapter describes the patient monitoring process and presents current research about how artificial intelligence techniques and computational technologies are able to produce care providers or the same patient with information that could be useful for the patient’s health care.

Payment of fruits or vegetables in retail stores normally require them to be manually identified. This paper presents an image classification method, based on lightweight Convolutional Neural Networks (CNN), with the goal of speeding up the checkout process in stores. A new dataset of images is introduced that considers three classes of fruits, inside or without plastic bags. In order to increase the classification accuracy, different input features are added into the CNN architecture. Such inputs are, a single RGB color, the RGB histogram, and the RGB centroid obtained from K-means clustering. The results show an overall 95% classification accuracy for fruits with no plastic bag, and 93% for fruits in a plastic bag .

In this paper, we present the construction process of a per-instance algorithm selection model to improve the initial solutions of Curriculum-Based Course Timetabling (CB-CTT) instances. Following the meta-learning framework, we apply a hybrid approach that integrates the predictions of a classifier and linear regression models to estimate and compare the performance of four meta-heuristics across different problem sub-spaces described by seven types of features. Rather than reporting the average accuracy, we evaluate the model using the closed SBS-VBS gap, a performance measure used at international algorithm selection competitions. The experimental results show that our model obtains a performance of 0.386, within the range obtained by per-instance algorithm selection models in other combinatorial problems. As a result of the process, we conclude that the performance variation between the meta-heuristics has a significant role in the effectiveness of the model. Therefore, we introduce statistical analyses to evaluate this factor within per-instance algorithm portfolios.

Honeybees, as social insects, follow a modular strategy applied to dynamic environments to provide reasonable opportunities for partial solutions to evolve in the form of interacting coadapted subcomponents. The honeybee search algorithm combines concepts from the areas of evolutionary algorithms and swarm intelligence to solve optimization problems. This algorithm is mainly based on the foraging behavior of honeybees and the search power of evolution strategies, a type of evolutionary algorithm used for real-valued problems. This paper shows the integration between an automaton and the honeybee search algorithm to formalize the algorithm mathematically. The combination mentioned above is tested here with the innovative applications of three-dimensional scene reconstruction and video tracking. The experimental results for both applications show evidence that the honeybee search algorithm can be used to improve time costs in challenging computer vision tasks through controlled experiments and objective comparisons. Also, the validation of results demonstrates that the measured accuracy ranks top-tier among other algorithms in the ALOV++ benchmark.

Service robots are expected to help us in different tasks in various environments such as homes, hospitals and offices. This work presents the first steps towards building a service robot at our university. The robot is provided with a topological map of a building floor (environmental map). Using this map the robot learns a path from one location to another by means of reinfocerment learning. During execution the robot is provided with a navigation map, related to the environmental map. We make use of a comercial Roomba robot and show how to create an interface in order to control it. Service robots are expected to help us in different tasks in various environments such as homes, hospitals and offices. This work presents the first steps towards building a service robot at our university. The robot is provided with a topological map of a building floor (environmental map). Using this map the robot learns a path from one location to another by means of reinfocerment learning. During execution the robot is provided with a navigation map, related to the environmental map. We make use of a comercial Roomba robot and show how to create an interface in order to control it.

One of the most basic tasks for any autonomous mobile robot is that of safely navigating from one point to another e.g. service robots should be able to find their way in different kinds of environments. Typically, vision is used to find landmarks in that environment to help the robot localise itself reliably. However, some environments may lack of these landmarks and the robot would need to be able to find its way in a featureless environment. This paper presents a topological vision-based approach for navigating through a featureless maze-like environment using a NAO humanoid robot, where all processing is performed by the robot's embedded computer. We show how our approach allows the robot to reliably navigate in this kind of environment in real-time.

In this work we present principled methods for the coordination of a robot's oculomotor system with the rest of its body motor systems. The problem is to decide which physical actions to perform next and where the robot's gaze should be directed in order to gain information that is relevant to the success of its physical actions. Previous work on this problem has shown that a reward-based coordination mechanism provides an efficient solution. However, that approach does not allow the robot to move its gaze to different parts of the scene, it considers the robot to have only one motor system, and assumes that the actions have the same duration. The main contributions of our work are to extend that previous reward-based approach by making decisions about where to fixate the robot's gaze, handling multiple motor systems, and handling actions of variable duration. We compare our approach against two common baselines: random and round robin gaze allocation. We show how our method provides a more effective strategy to allocate gaze where it is needed the most.

Findings from eye movement research in humans have demonstrated that the task determines where to look. One hypothesis is that the purpose of looking is to reduce uncertainty about properties relevant to the task. Following this hypothesis, we define a model that poses the problem of where to look as one of maximising task performance by reducing task relevant uncertainty. We implement and test our model on a simulated humanoid robot which has to move objects from a table into containers. Our model outperforms and is more robust than two other baseline schemes in terms of task performance whilst varying three environmental conditions, reach/grasp sensitivity, observation noise and the camera’s field of view.