Earticle

Music Information Retrieval (MIR) is a crucial topic in the domain of information retrieval. According to the major characteristics of music, the Query-by-Humming system retrieves interesting music by finding melodies that contains similar or equal melodies to the humming query. Basing on the fuzzy inference model designed in this paper, a novel Query-by- Humming/Singing system is proposed to extract pitch contour information from WAV and MIDI files. To verify the effectiveness of the presented work, the MIREX QBSH Database is employed as our experimental database and a large amount of human vocal data is used as queries to test the robustness of the MIR. Then, the Longest Common Subsequence (LCS) is used as an approximate matching algorithm to identify the top 5 music samples as an evaluation standard for the system. Experimental results show that the proposed system achieves 85% accuracy in the top 5 retrievals.

To date there has been no evidence of a suitable cloud computing digital forensics framework. This is due to the fact that each framework is dependent on the type of data cloud investigations involved, and each framework is tailored to the specific virtualised data cloud being examined as potential evidence. This paper describes a basic model for using the computer’s virtual machine (VM) history based on finite state machine (FSM) automata theory. This theoretical model abstracts the low level (primitive) events of the VM, which in turn can later be used to define the categories and classes of VM investigation analysis required by law enforcement for establishing higher level frameworks relevant to pursuing potential cases. The model motivates this framework context by making a high-level mapping of the VM’s complex event histories as recorded by the VM-hosted operating system (hypervisor) kernel logs.

This paper presents an architecture proposal for mobile services. It covers server-side and terminal-side components for the simple creation, provision and consumption of mobile services. The specific characteristics of mobile services are reflected in this approach. In particular the role of the prosumer, who not only consumes mobile services but also modifies them or creates services of his own, is within the focus of this design. The paper concludes with a proof-of-concept that has been carried out in a European research project.

Traditional E-Commerce applications have evolved in the last few years due to the growth in the mobile environment, creating a new research area known as U-Commerce. The application of these techniques in the banking environment has been a direct outcome of the desire to enhance services offered to end users. In this article, we present a context-aware mobile recommender system based on real banking data provided by a well-known Spanish bank. The data were composed of customer profiles, credit card transactions and information about places where bank clients have previously spent their money. The system model and its architecture are described, taking into account social, mobility and ubiquitous requisites to generate personalised recommendations. The mobile prototype deployed in the bank was evaluated in a survey among 100 users, with good results regarding trust, usefulness and effectiveness.