The main goal of the work presented in the paper is to introduce the use of fuzzy logic in the Grey Wolf Optimizer (GWO) algorithm specifically for dynamic simultaneous adaptation of the key parameters, which are crucial in the performance of the metaheuristic. The proposed approach for this modification of GWO using fuzzy logic is presented. In addition, a brief comparison between the traditional GWO algorithm and the Grey Wolf Optimizer using fuzzy logic for dynamic adaptation of parameters is reported. This research shows the individual dynamic adjustment of two parameters and then a proposal of how to simultaneously adjust both parameters and finally we present the performance of these methods when they are tested with a set of benchmark functions, showing the advantage of using the strategy of simultaneous adaptation of parameters.

The main goal of the paper is the use of fuzzy logic for dynamic parameter adaptation in the Grey Wolf Optimizer (GWO) algorithm. The proposed approach of a fuzzy GWO is compared with the traditional GWO algorithm with a set of benchmark functions. Simulation results show that there is a significant advantage of the proposed fuzzy GWO.

One of the most important tasks in computer vision systems is the description of the local neighborhood around interest points. In RGB-D images, this task is usually performed by computing descriptors encoded as real-value vectors. The use of binary descriptors, like BRISK, BRIEF or ORB, has proven to be adequate to address this task accurately and efficiently. In this paper, we propose a novel binary pattern that encodes the shape around a given point in a RGB-D image with invariance to rotation and scale. This descriptor is contrasted to well-known state-of-the-art 3D descriptors, namely FPFH, Spin Images, SHOT, PFHRGB and CSHOT in order to test its actual performance on the RGB-D Objects dataset. The experiments performed show that the proposed binary pattern descriptor equals and even outperforms state-of-the-art 3D descriptors with a higher computational efficiency.

This paper presents an exploratory study about two language learning MOOCs deployed in the UNED COMA platform. The study identifies three research questions: a) How does activity evolve in these MOOCs? b) Are all learning activities relevant?, and c) Does the use of the target language influence?. We conclude that the MOOC activity drops not only due to the drop-outs. When students skips around 10% of the proposed activities, the percentage of passing the course decrease in a 25%. Forum activity is a useful indicator for success, however the participation in active threads is not. Finally, the use of the target language course is not an indicator to predict success.

This paper is concerned with combining models for decoding an optimum translation for a dictation based machine aided human translation (MAHT) task. Statistical language model (SLM) probabilities in automatic speech recognition (ASR) are updated using statistical machine translation (SMT) model probabilities. The effect of this procedure is evaluated for utterances from human translators dictating translations of source language documents. It is shown that computational complexity is significantly reduced while at the same time word error rate is reduced by 30%.

Interactive machine translation (IMT) is an increasingly popular paradigm for semi-automated machine translation, where a human expert is integrated into the core of an automatic machine translation system. The human expert interacts with the IMT system by partially correcting the errors of the system's output. Then, the system proposes a new solution. This process is repeated until the output meets the desired quality. In this scenario, the interaction is typically performed using the keyboard and the mouse. However, speech is also a very interesting input modality since the user does not need to abandon the keyboard to interact with it.

To date, automatic handwriting recognition systems are far from being perfect and often they need a post editing where a human intervention is required to check and correct the results of such systems. We propose to have a new interactive, on-line framework which, rather than full automation, aims at assisting the human in the proper recognition- transcription process; that is, facilitate and speed up their transcription task of handwritten texts. This framework combines the efficiency of automatic handwriting recognition systems with the accuracy of the human transcriptor. The best result is a cost-effective perfect transcription of the handwriting text images.

Current machine translation systems are far from being perfect. However, such systems can be used in computer-assisted translation to increase the productivity of the (human) translation process. The idea is to use a text-to-text translation system to produce portions of target language text that can be accepted or amended by a human translator using text or speech. These user-validated portions are then used by the text-to-text translation system to produce further, hopefully improved suggestions. There are different alternatives of using speech in a computer-assisted translation system: From pure dictated translation to simple determination of acceptable partial translations by reading parts of the suggestions made by the system. In all the cases, information from the text to be translated can be used to constrain the speech decoding search space. While pure dictation seems to be among the most attractive settings, unfortunately perfect speech decoding does not seem possible with the current speech processing technology and human error-correcting would still be required. Therefore, approaches that allow for higher speech recognition accuracy by using increasingly constrained models in the speech recognition process are explored here. All these approaches are presented under the statistical framework. Empirical results support the potential usefulness of using speech within the computer-assisted translation paradigm.

In this paper, a novel approach for video sequence compression using Cellular Neural Networks (CNN's) is presented. CNN's are nets characterized by local interconnections between neurons (usually called cells), and can be modeled as dynamical systems. From among many different types, a CNN model operating in discrete-time (DT-CNN) has been chosen, its parameters being defined so that they are shared among all the cells in the network. The compression process proposed in this work is based on the possibility of replicating a given video sequence as a trajectory generated by the DT-CNN. In order for the CNN to follow a prescribed trajectory, a supervised training algorithm is implemented. Compression is achieved due to the fact that all the information contained in the sequence can be stored into a small number of parameters and initial conditions once training is stopped. Different improvements upon the basic formulation are analyzed and issues such as feasibility and complexity of the compression problem are also addressed. Finally, some examples with real video sequences illustrate the applicability of the method.