Jefferson Morais

Data Mining Applied to the Electric Power Industry: Classification of Short-Circuit Faults in Transmission Lines

Data mining can play a fundamental role in modern power systems. However, the companies in this area still face several difficulties to benefit from data mining. A major problem is to extract useful information from the currently available non-labeled digitized time series. This work focuses on automatic classification of faults in transmission lines. These faults are responsible for the majority of the disturbances and cascading blackouts. To circumvent the current lack of labeled data, the alternative transients program (ATP) simulator was used to create a public comprehensive labeled dataset. Results with different preprocessing (e.g., wavelets) and learning algorithms (e.g., decision trees and neural networks) are presented, which indicate that neural networks outperform the other methods.

A Framework for Evaluating Automatic Classification of Underlying Causes of Disturbances and Its Application to Short-Circuit Faults

Most works in power systems event classification concern classifying an event according to the morphology of the corresponding waveform. An important and even more difficult problem is the classification of the event underlying cause. However, the lack of labeled data is more problematic in this second scenario. This paper proposes a framework based on frame-based sequence classification (FBSC), the Alternative Transient Program (ATP), and a public dataset to advance research in this area. As a proof of concept, a thorough evaluation of automatic classification of short circuits in transmission lines is discussed. Simulations with different preprocessing (e.g., wavelets) and learning algorithms (e.g., support vector machines) are presented. The results can be reproduced at other sites and elucidate several tradeoffs when designing the front end and pattern recognition stages of a sequence classifier. For example, when considering the whole event in an offline scenario, the combination of the raw front end and a decision tree is competitive with wavelets and a neural network.

An Overview of Data Mining Techniques Applied to Power Systems

The growth of available data in the electric power industry motivates the adoption of data mining techniques. However, the companies in this area still face several difficulties to benefit from data mining. One of the reasons is that mining power systems data is an interdisciplinary task. Typically, electrical and computer engineers (or scientists) need to work together in order to achieve breakthroughs, interfacing power systems and data mining at a mature level of cooperation. Another reason is the lack of freely available and standardized benchmarks. Because of that, most previous research in this area used proprietary datasets, which makes difficult to compare algorithms and reproduce results. This chapter has two mains goals and, consequently, is divided in two parts. In the first part, the goal is to present a brief overview on ho w data mining techniques have been used in power systems. There are several works, such as (Mori, 2002), that introduce data mining techniques to people with background in power systems. In contrast, this text assumes previous knowledge of data mining, describes some fundamental concepts of power systems and illustrates the kind of problems that the electric industry tries to solve with data mining. The second part of the work presents a thor ough investigation of a specific problem: classifying time series that represent short-circuit faults in transmission lines. Studies show that these faults are responsible for 70% of the disturbances and cascading blackouts (Kezunovic & Zhang, 2007). Besides, there is a large and growing number of publications about this problem. Two types of fault classification systems are discussed: on-line and post-fault. On-line fault classification must be performed on a very short time span, with the analysis segment (or frame) being located approximately at the instant the fault begins. Post-fault classification can be performed off-line and its input consists of a multivariate time series with variable length (duration). Post-fault is a sequence classification problem, while in on-line classification the input is a fixed-length vector. Both fault classification systems (and most data mining applications) require a preprocessing or front end stage that converts the raw

Guidelines for Graphical User Interface Design in Mobile Augmented Reality Applications

The technological advancement of mobile devices allowed the entry of innovative technologies in users’ daily lives, due to miniaturization and advancement of sensors, cameras and computer resources. These technologies make it possible to increase the user’s interaction and perception about places and objects around him, allowing, for example, the use of augmented reality. However, this opportunity presents new challenges, such as application design and development, aspects to this new context of ubiquitous devices, heterogeneity of mobile devices, and how the user interacts with these applications. Thus, this paper aims to present the results of Mobile Augmented Reality application usability evaluation, identifying a list of problems in the application Graphical User Interface and propose some guidelines for building Graphical User Interfaces to avoid these problems. The chosen usability evaluation is the Think Aloud protocol, which was performed with 20 participants in the Mobile Augmented Reality application named ARguide.

An Experimental Evaluation Of Automatic Classification Of Sequences Representing Short Circuits In Transmission Lines

This work concerns automatic classification of short circuits in transmission lines. These faults are responsible for the majority of the disturbances and cascading blackouts. Each short circuit is represented by a sequence (time-series) and both online (for each short segment) and offline (taking in account the whole sequence) classification are investigated. Results with different preprocessing (e.g., wavelets) and learning algorithms are presented, which indicate that decision trees and neural networks outperform the other methods. Another contribution of this work is to promote the adoption of a public and comprehensive labeled dataset with short circuit sequences, which allows to properly compare the algorithms and reproduce the results. Keywords— Fault classification, sequence classification, machine learning.

Data Mining Applied to Cognitive Radio Systems

Cognitive radio (CR) is a novel technology that allows to improve spectrum utilization by enabling opportunistic access to the licensed spectrum band by unlicensed users [2]. This is accomplished through heterogeneous architectures and techniques of dynamic spectrum access. The CR is defined as an intelligent wireless communication system that is aware of its environment and is capable to learn from the environment and adapt its transmission parameters, such as frequency, modulation, transmission power and communication protocols [14].

Categorizing Issues in Mid-air InfoVis Interaction

This paper presents a starting study on InfoVis interaction through mid-air gestures, using a vision based interaction device, the Leap Motion. We present the user tests conducted and the results gathered, using a 3D Scatterplot as visualization technique. These tests aim in identify and categorize issues that can compromise InfoVis mid-air gestural interaction as a whole, not focusing on the design of the developed tool. The test tasks and results are exposed and the issues found are categorized in Boundary Awareness, Granularity and Collision and Depth Perception.

A New Strategy Based on Feature Selection for Fault Classification in Transmission Lines

The transmission lines are the element most susceptible to faults on power systems, and the short circuit faults are the worst type of faults than can happen on this element. In order to avoid further problems due to these faults, a fault diagnostic is necessary, and the use of front ends is required. However, the selection process for choosing the front ends is not a simple one because it behaves differently for each. Therefore, this paper presents a new front end, called Concat front end, which integrates other front ends, such as wavelet, raw and Root Mean Square. Furthermore, we have applied feature selection techniques based on filter in order to decrease the dimension of the input data. Thus, we used the following classifiers: neural network, K-nearest neighbor, Random Forest and support vector machine. We used a public dataset called UFPAFaults to train and test the classifiers. As a result, the concatenation of front ends, on most cases, had achieved the lowest error rates. In addition, the feature selection techniques applied showed that it is possible to get higher accuracy using less features on the process.

Temporal Data Visualization Technique Based on Treemap

Many information visualization techniques and tools have been created to analyze and understand temporal data. However, it is noticeable that time dimension is underused in most techniques and tools, used only as an aid in the search for patterns and answers. Therefore, this paper proposes an adaptation of the treemap joined with the calendar metaphor, using time as main attribute to hierarchy configuration and drill down navigation. Time granularity is flexible on granularity levels, and a grouping configuration of one level is used to display the calendar visual representation of that same granularity level. Furthermore, user interaction breadcrumbs are applied in order to provide better linear analysis of temporal characteristics of data without losing data overview. It is also possible to compare multiple different views of various time subsets.

A Review of Ways and Strategies on How to Collaborate in Information Visualization Applications.

Design and develop collaborative methods in information visualization are a current challenge, hence understand, identify and define the current progress of developed methods to collaborate in information visualization are important. The aim of this work is to review the ways and strategies of how to collaborate in information visualization applications. We surveyed published works that present applications that implements collaborative information visualization techniques and methods. We present a micro level category of identified ways of how the InfoVis applications implements collaboration.