Jose Enrique Munoz-Exposito

Adaptive network-based fuzzy inference system vs. other classification algorithms for warped LPC-based speech/music discrimination

Automatic discrimination of speech and music is an important tool in many multimedia applications. The paper presents an effective approach based on an adaptive network-based fuzzy inference system (ANFIS) for the classification stage required in a speech/music discrimination system. A new simple feature, called warped LPC-based spectral centroid (WLPC-SC), is also proposed. Comparison between WLPC-SC and the classical features proposed in the literature for audio classification is performed, aiming to assess the good discriminatory power of the proposed feature. The vector length used to describe the proposed psychoacoustic-based feature is reduced to a few statistical values (mean, variance and skewness). With the aim of increasing the classification accuracy percentage, the feature space is then transformed to a new feature space by LDA. The classification task is performed applying ANFIS to the features in the transformed space. To evaluate the performance of the ANFIS system for speech/music discrimination, comparison to other commonly used classifiers is reported. The classification results for different types of music and speech signals show the good discriminating power of the proposed approach.

Dynamic Voltage Frequency Scaling Simulator for Real Workflows Energy-Aware Management in Green Cloud Computing

Nowadays, the growing computational capabilities of Cloud systems rely on the reduction of the consumed power of their data centers to make them sustainable and economically profitable. The efficient management of computing resources is at the heart of any energy-aware data center and of special relevance is the adaptation of its performance to workload. Intensive computing applications in diverse areas of science generate complex workload called workflows, whose successful management in terms of energy saving is still at its beginning. WorkflowSim is currently one of the most advanced simulators for research on workflows processing, offering advanced features such as task clustering and failure policies. In this work, an expected power-aware extension of WorkflowSim is presented. This new tool integrates a power model based on a computing-plus-communication design to allow the optimization of new management strategies in energy saving considering computing, reconfiguration and networks costs as well as quality of service, and it incorporates the preeminent strategy for on host energy saving: Dynamic Voltage Frequency Scaling (DVFS). The simulator is designed to be consistent in different real scenarios and to include a wide repertory of DVFS governors. Results showing the validity of the simulator in terms of resources utilization, frequency and voltage scaling, power, energy and time saving are presented. Also, results achieved by the intra-host DVFS strategy with different governors are compared to those of the data center using a recent and successful DVFS-based inter-host scheduling strategy as overlapped mechanism to the DVFS intra-host technique.

New speech/music discrimination approach based on warping transformation and ANFIS

Abstract Automatic discrimination of speech and music is an important tool in many multimedia applications. The paper presents an effective approach based on an Adaptive Network-Based Fuzzy Inference System (ANFIS) for the classification stage required in a speech/music discrimination system. A new simple feature, called Warped LPC-based Spectral Centroid (WLPC-SC), is also proposed. Comparison between WLPC-SC and the classical features proposed in the literature for audio classification is performed, aiming to assess the good discriminatory power of the proposed feature. The length of the vector for describing the proposed psychoacoustic-based feature is reduced to a few statistical values (mean, variance and skewness), which are then transformed to a new feature space by LDA, with the aim of increasing the classification accuracy percentage. The classification task is performed applying ANFIS to the features in the transformed space. To evaluate the performance of the ANFIS system for speech/music discrimination, comparison to other commonly used classifiers is reported. The classification results for different types of music and speech signals show the good discriminating power of the proposed approach.

Fuzzy Rule-Based Systems for Optimizing Power Consumption in Data Centers

One of the most important aspects in cloud computing is the infraestructure as a service (IaaS). In the basic cloud service model, providers offers virtual machines and solutions based on virtualization. An user pays for consumption of resources (disk space, virtual local area networks, etc.). A data center is a facility used to house computer systems to provide IaaS. Large data centers consume a lot of electricity (high power consumption) and are a source of environmental pollution and costs, so it is important to improve their performance. In this paper a fuzzy rule-based system is proposed to schedule virtual machines in a data center based on Green Computing concepts: minimum power consumption as performance index is considered. This approach is compared to classic scheduling algorithms in literature.

SPEECH/MUSIC DISCRIMINATION BASED ON WARPING TRANSFORMATION AND FUZZY LOGIC FOR INTELLIGENT AUDIO CODING

Automatic discrimination of speech and music is an important tool in many multimedia applications. This article presents an evolutionary, fuzzy, rules-based speech/music discrimination approach for intelligent audio coding, which exploits only one simple feature, called Warped LPC-based Spectral Centroid (WLPC-SC). Comparison between WLPC-SC and the classical features proposed in the literature for audio classification is performed, aiming to assess the good discriminatory power of the proposed feature. The length of the vector for describing the proposed psychoacoustic-based feature is reduced to a few statistical values (mean, variance, and skewness), which are then transformed to a new feature space, applying linear discriminant analysis (LDA), with the aim of increasing the classification accuracy percentage. The classification task is performed applying a support vector machine (SVM) to the features in the transformed space. The final decision is made by a fuzzy expert system, which improves the accuracy rate provided by the SVM, taking into account the audio labels assigned by this classifier to past audio frames. The accuracy rate improvement due to the fuzzy expert system is also reported. Experimental results reveal that our speech/music discriminator is robust and fast, making it suitable for intelligent audio coding.

A wiki as a common framework for promoting autonomous learning among university students

The process of adapting methodologically to European Credit Transfer System suffers from a lack in practical evaluations within the engineering field. One of the main competencies within the studies of telematics engineering is the development of skills related to behaving as technical consultants. This competency has been traditionally developed via publishing additional material through learning management systems; however, the approach followed within this study has promoted its development through the creation of practical guides within a wiki. The evaluation of this activity with students of different courses is presented herein, providing certain guidelines about its use as a support system for autonomous learning.

Acceleration of Genome Sequencing with Intelligent Cloud Brokers

Workflows from DNA sequencing applications have an extensive number of jobs which are reliant and that require parallel execution if high levels of performance are desired. In this work, a novel workflow broker based on expert systems is presented to accelerate workflows for DNA sequencing in cloud computing datacenters. The broker is based on the adaptation of Fuzzy Rule-Based Systems (FRBSs), which are inspired by Fuzzy Logic (FL) and rule-based systems, and as shown by simulation results, it is able to accelerate the processing of genome sequencing more efficiently than a wide range of scheduling strategies.

Energy-aware scheduling in clouc computing systems

The main objective of this work is to reduce power consumption and energy of a datacenter. There are various power saving techniques. A fuzzy system-based scheduler has been used, comparing its results with other well-known algorithms. The methods used in this paper are based on a combination of the DVFS algorithm and the development of a rule-based expert system to provide power-based planners for task planning domains. The parameters considered in the system are explained in detail and the results obtained are analyzed.

Power Consumption Optimization in Datacenters Using PSO Tuning in Fuzzy Rule-Based Systems

This paper presents a strategy for reducing power consumption in a data centers in cloud computing. A more efficient use of resources using optimal scheduling of tasks is proposed. The scheduling strategy uses a fuzzy rule-based system (FRBS) with automatic learning for knowledge adquisition. The learning strategy is inspired on Particle Swarm Optimization algorithm and it allows the tuning of fuzzy sets of the FRBS without the need for obtaining new rules in a way that the initial rule base introduced by an expert is maintained through the whole performance of the scheduler.

Analysis and Real Implementation of a Cloud Infraestructure for Computing Laboratories Virtualization

In this work , a cloud infrastructure is analysed and deployed to virtualize computing laboratories. Virtualization of computing resources allows the user to face a single computing interface whose capabilities are really offered by a cloud system that makes use of its processing capability on demand. The use of this proposed infrastructure reduces the cost of equipment investments as well as maintenance of real laboratories and further, it makes a more efficient use of available resources with a transparent user experience.