Addressing data complexity for imbalanced data sets: analysis of SMOTE-based oversampling and evolutionary undersampling

In the classification framework there are problems in which the number of examples per class is not equitably distributed, formerly known as imbalanced data sets. This situation is a handicap when trying to identify the minority classes, as the learning algorithms are not usually adapted to such characteristics. An usual approach to deal with the problem of imbalanced data sets is the use of a preprocessing step. In this paper we analyze the usefulness of the data complexity measures in order to evaluate the behavior of undersampling and oversampling methods. Two classical learning methods, C4.5 and PART, are considered over a wide range of imbalanced data sets built from real data. Specifically, oversampling techniques and an evolutionary undersampling one have been selected for the study. We extract behavior patterns from the results in the data complexity space defined by the measures, coding them as intervals. Then, we derive rules from the intervals that describe both good or bad behaviors of C4.5 and PART for the different preprocessing approaches, thus obtaining a complete characterization of the data sets and the differences between the oversampling and undersampling results.     

A non-intrusive estimation for high-quality Internet TV services

This paper presents a non-intrusive estimator for Internet TV services based on streaming technology. Analyzing the video packets received by the client application, the estimator is capable of selecting the most suitable encoding bitrate for the available bandwidth in the end-to-end path. The estimator has been integrated in a real client/server architecture and evaluated with different network traffic situations. The results of the performed evaluation have revealed the stability and adaptation speed as the best qualities of our proposal.     

SENFIS: a Sensor Node File System for increasing the scalability and reliability of Wireless Sensor Networks applications

In the last years the Wireless Sensor Networks’ (WSN) technology has been increasingly employed in various application domains. The extensive use of WSN posed new challenges in terms of both scalability and reliability. This paper proposes Sensor Node File System (SENFIS), a novel file system for sensor nodes, which addresses both scalability and reliability concerns. SENFIS can be mainly used in two broad scenarios. First, it can transparently be employed as a permanent storage for distributed TinyDB queries, in order to increase the reliability and scalability. Second, it can be directly used by a WSN application for permanent storage of data on the WSN nodes. The experimental section shows that SENFIS implementation makes an efficient use of resources in terms of energy consumption, memory footprint, flash wear levelling, while achieving execution times similarly with existing WSN file systems.     

An adaptive, real-time, traffic monitoring system

In this paper we describe a computer vision-based traffic monitoring system able to detect individual vehicles in real-time. Our fully integrated system first obtains the main traffic variables: counting, speed and category; and then computes a complete set of statistical variables. The objective is to investigate some of the difficulties impeding existing traffic systems to achieve balanced accuracy in every condition; i.e. day and night transitions, shadows, heavy vehicles, occlusions, slow traffic and congestions. The system we present is autonomous, works for long periods of time without human intervention and adapts automatically to the changing environmental conditions. Several innovations, designed to deal with the above circumstances, are proposed in the paper: an integrated calibration and image rectification step, differentiated methods for day and night, an adaptive segmentation algorithm, a multistage shadow detection method and special considerations for heavy vehicle identification and treatment of slow traffic. A specific methodology has been developed to benchmark the accuracy of the different methods proposed.     

Two-stage cascaded classification approach based on genetic fuzzy learning for speech/music discrimination

Automatic discrimination of speech and music is an important tool in many multimedia applications. The paper presents a robust and effective approach for speech/music discrimination, which relies on a two-stage cascaded classification scheme. The cascaded classification scheme is composed of a statistical pattern recognition classifier followed by a genetic fuzzy system. For the first stage of the classification scheme, other widely used classifiers, such as neural networks and support vector machines, have also been considered in order to assess the robustness of the proposed classification scheme. Comparison with well-proven signal features is also performed. In this work, the most commonly used genetic learning algorithms (Michigan and Pittsburgh) have been evaluated in the proposed two-stage classification scheme. The genetic fuzzy system gives rise to an improvement of about 4% in the classification accuracy rate. Experimental results show the good performance of the proposed approach with a classification accuracy rate of about 97% for the best trial.     

A technique for defining agent-oriented engineering processes with tool support

The formalization of engineering processes is necessary for guaranteeing the quality and cost of the products involved. Agent-oriented engineering has already proposed development processes that still need to be further formalized to be applicable by non-researchers. This paper proposes a technique to instantiate processes for specific agent-oriented methodologies. This technique is based on three orthogonal views that are respectively related with lifecycles, disciplines and guidances. In addition, processes are modeled with a tool, which is automatically generated from a process metamodel inspired by the software & systems process engineering metamodel. Accordingly, engineers can choose the methodology–process pair best-suited for the characteristics of their project. The paper illustrates the approach based on the unified development process and the scrum process for the INGENIAS methodology and compares the results with other existing alternatives.     

Modeling of the intrinsic stress effect on the resonant frequency of NEMS resonators integrated by beams with variable cross-section

Nano-electro-mechanical systems (NEMS) resonators integrated by a double clamped beam with variable cross-section are used in several applications such as chemical and biological detectors, high-frequency filters, and signal processing. The structure of these resonators can experience intrinsic stresses produced during their fabrication process. We present an analytical model to estimate the first bending resonant frequency of NEMS resonators based on a double clamped beam with three cross-sections, which considers the intrinsic stress effect on the resonant structure. This model is obtained using the Rayleigh and Macaulay methods, as well as the Euler–Bernoulli beam theory. We applied the analytical model to a silicon carbide (SiC) resonator of 186 nm thickness reported in the literature. This resonator has a total length ranking from 80 to 258 μm and is subjected to a tensile intrinsic stress close to 110 MPa. Results from this model show good agreement with experimental results. The analytic frequencies have a maximum relative difference less than 6.3% respect to the measured frequencies. The tensile intrinsic stress on the resonant structure causes a significantly increase on its bending resonant frequency. The proposed model provides an insight into the study of the intrinsic stress influence on the resonant frequency of this nanostructure. In addition, this model can estimate the frequency shift due to the variations of the resonator geometrical parameters.     

Semi-formal transformation of secure business processes into analysis class and use case models: An MDA approach

ContextModel-Driven Development (MDD) is an alternative approach for information systems development. The basic underlying concept of this approach is the definition of abstract models that can be transformed to obtain models near implementation. One fairly widespread proposal in this sphere is that of Model Driven Architecture (MDA). Business process models are abstract models which additionally contain key information about the tasks that are being carried out to achieve the company’s goals, and two notations currently exist for modelling business processes: the Unified Modelling Language (UML), through activity diagrams, and the Business Process Modelling Notation (BPMN).ObjectiveOur research is particularly focused on security requirements, in such a way that security is modelled along with the other aspects that are included in a business process. To this end, in earlier works we have defined a metamodel called secure business process (SBP), which may assist in the process of developing software as a source of highly valuable requirements (including very abstract security requirements), which are transformed into models with a lower abstraction level, such as analysis class diagrams and use case diagrams through the approach presented in this paper.MethodWe have defined all the transformation rules necessary to obtain analysis class diagrams and use case diagrams from SBP, and refined them through the characteristic iterative process of the action-research method.ResultsWe have obtained a set of rules and a checklist that make it possible to automatically obtain a set of UML analysis classes and use cases, starting from SBP models. Our approach has additionally been applied in a real environment in the area of the payment of electrical energy consumption.ConclusionsThe application of our proposal shows that our semi-automatic process can be used to obtain a set of useful artifacts for software development processes.     

Assessment methodology for software process improvement in small organizations

ContextDiagnosing processes in a small company requires process assessment practices which give qualitative and quantitative results; these should offer an overall view of the process capability. The purpose is to obtain relevant information about the running of processes, for use in their control and improvement. However, small organizations have some problems in running process assessment, due to their specific characteristics and limitations.ObjectiveThis paper presents a methodology for assessing software processes which assist the activity of software process diagnosis in small organizations. There is an attempt to address issues such as the fact that: (i) process assessment is expensive and typically requires major company resources and (ii) many light assessment methods do not provide information that is detailed enough for diagnosing and improving processes.MethodTo achieve all this, the METvalCOMPETISOFT assessment methodology was developed. This methodology: (i) incorporates the strategy of internal assessments known as rapid assessment, meaning that these assessments do not take up too much time or use an excessive quantity of resources, nor are they too rigorous and (ii) meets all the requirements described in the literature for an assessment proposal which is customized to the typical features of small companies.ResultsThis paper also describes the experience of the application of this methodology in eight small software organizations that took part in the COMPETISOFT project. The results obtained show that this approach allows us to obtain reliable information about the strengths and weaknesses of software processes, along with information to companies on opportunities for improvement.ConclusionThe assessment methodology proposed sets out the elements needed to assist with diagnosing the process in small organizations step-by-step while seeking to make its application economically feasible in terms of resources and time. From the initial application it may be seen that this assessment methodology can be useful, practical and suitable for diagnosing processes in this type of organizations.     

A framework for the definition of metamodels for Computer-Aided Software Engineering tools

Computer-Aided Software Engineering (CASE) tools support modeling-related activities in development projects. Given the variety of tools and functionalities, it is quite common to work with several tools in the same project. However, data cannot usually be exchanged between these tools without loss of information. Recent approaches address this model interchange problem using metamodels to characterize the involved information and transformations to export/import it. Nevertheless, most of these solutions focus on the abstract syntax of models. They fail to consider aspects such as the presentation of models or tool-specific information, which are either disregarded or represented in ad-hoc ways that make difficult their processing. In order to overcome these limitations, this paper introduces a framework to define metamodels of CASE tools and a process to carry out the model interchange using them. The proposed metamodels have a modular organization with several internal metamodels. Each of them is aimed at describing some specific information about content, structure and presentation for both models and tools. The paper illustrates this approach with a case study used for comparison with existing works for this problem.