Optimization techniques for improving power quality data mining using wavelet packet based support vector machine

This paper aims at automatic classification of power quality events using Wavelet Packet Transform (WPT) and Support Vector Machines (SVM). The features of the disturbance signals are extracted using WPT and given to the SVM for effective classification. Recent literature dealing with power quality establishes that support vector machine methods generally outperform traditional statistical and neural methods in classification problems involving power disturbance signals. However, the two vital issues namely the determination of the most appropriate feature subset and the model selection, if suitably addressed, could pave way for further improvement of their performances in terms of classification accuracy and computation time. This paper addresses these issues through a classification system using two optimization techniques, the genetic algorithms and simulated annealing. This system detects the best discriminative features and estimates the best SVM kernel parameters in a fully automatic way. Effectiveness of the proposed detection method is shown in comparison with the conventional parameter optimization methods discussed in literature like grid search method, neural classifiers like Probabilistic Neural Network (PNN), fuzzy k-nearest neighbor classifier (FkNN) and hence proved that the proposed method is reliable as it produces consistently better results.     

Multiple comparator classifier framework for accelerometer-based fall detection and diagnostic

There are a significant number of high fall risk individuals who are susceptible to falling and sustaining severe injuries. An automatic fall detection and diagnostic system is critical for ensuring a quick response with effective medical aid based on relative information provided by the fall detection system. This article presents and evaluates an accelerometer-based multiple classifier fall detection and diagnostic system implemented on a single wearable Shimmer device for remote health monitoring. Various classifiers have been utilised within literature, however there is very little current work in combining classifiers to improve fall detection and diagnostic performance within accelerometer-based devices. The presented fall detection system utilises multiple classifiers with differing properties to significantly improve fall detection and diagnostic performance over any single classifier and majority voting system. Additionally, the presented multiple classifier system utilises comparator functions to ensure fall event consistency, where inconsistent events are outsourced to a supervisor classification function and discrimination power is considered where events with high discrimination power are evaluated to further improve the system response. The system demonstrated significant performance advantages in comparison to other classification methods, where the proposed system obtained over 99% metrics for fall detection recall, precision, accuracy and F-value responses.     

Power quality time series data mining using S-transform and fuzzy expert system

This paper presents a new approach for power quality time series data mining using S-transform based fuzzy expert system (FES). Initially the power signal time series disturbance data are pre-processed through an advanced signal processing tool such as S-transform and various statistical features are extracted, which are used as inputs to the fuzzy expert system for power quality event detection. The proposed expert system uses a data mining approach for assigning a certainty factor for each classification rule, thereby providing robustness to the rule in the presence of noise. Further to provide a very high degree of accuracy in pattern classification, both the Gaussian and trapezoidal membership functions of the concerned fuzzy sets are optimized using a fuzzy logic based adaptive particle swarm optimization (PSO) technique. The proposed hybrid PSO-fuzzy expert system (PSOFES) provides accurate classification rates even under noisy conditions compared to the existing techniques, which show the efficacy and robustness of the proposed algorithm for power quality time series data mining.     

Power quality disturbance detection and classification using wavelet and RBFNN

This paper introduces a novel approach to detect and classify power quality disturbance in the power system using radial basis function neural network (RBFNN). The proposed method requires less number of features as compared to conventional approach for the identification. The feature extracted through the wavelet is trained by a radial basis function neural network for the classification of events. After training the neural network, the weight obtained is used to classify the Power Quality (PQ) problems. For the classification, 20 types of disturbances are taken into account. The classification performance of RBFNN is compared with feed forward multilayer network (FFML), learning vector quantization (LVQ), probabilistic neural network (PNN) and generalized regressive neural network (GRNN). The classification accuracy of the RBFNN network is improved, just by rewriting the weights and updating the weights with the help of cognitive as well as the social behavior of particles along with fitness value. The simulation results possess significant improvement over existing methods in signal detection and classification.     

ANOMALY DETECTION IN DISTRIBUTED COMPUTER COMMUNICATION SYSTEMS

Anomaly detection is a basic functionality of intrusion detection systems. The aim of such systems in distributed computer communication systems is to recognize and notify about various events that influence a system's security. In a gain to assure efficiency, flexibility, and a quality of detection of systems security violation in a distributed environment, required detection systems should be responsive, adaptive, proactive, and less centralized than those currently deployed. Such required properties are offered by agents and multiagent systems, i.e., agent-based technology has the continuously increasing potential to offer a solution to the growing problem of designing intelligent, efficient, and flexible management systems. An agent-based approach offers the potential to develop advanced and effective distributed, network-based strategies replacing traditional node-based approaches by more perspective network-based approaches.

This article is devoted to present various architectures of anomaly detection systems, which may be implemented as multiagent systems supporting the classification of observed activities as normal or abnormal. Some simple example presents hierarchical architecture of a distributed anomaly detection system, which may be implemented in the form of a multiagent decision supporting system.     

Evolutionary algorithm based optimization for power quality disturbances classification using support vector machines

Classification and detection of power signal disturbances are most essential to ensure the good power quality. The power disturbance signals are non-stationary in nature. Non-stationary signal classification is a complex problem and equally a difficult task. In this paper we present a new method for accurate classification of power quality signals using Support Vector Machines (SVM) with Optimized Time-Frequency Kernels by a stochastic genetic algorithm. The Cohen’s class of time-frequency-transformation has been chosen as the Kernel for the SVM. An Evolutionary Algorithm has been used to optimize the parameters of the Kernels. The proposed classification method with optimized parameters is promising for classification of such non-stationary signals. Comparative simulation results demonstrate a significant improvement in the classification accuracy in case of these optimized Kernels. The important contribution of the paper is the optimization of the Kernels for the power system signal classification problem.     

短时电能质量扰动分类方法研究

为了准确检测短时电能质量扰动问题,提出了一种基于K-L变换和支持向量机多值分类器的短时电能质量扰动分类方法。采用离散小波变换获得信号在不同分解尺度下的能量分布作为原始特征空间;运用K-L变换进行模式识别特征空间的提取;设计了适用于短时电能质量扰动的支持向量机多值分类器。实验结果表明,对原始能量特征进行K-L变换后,可以提高分类准确率;支持向量机多值分类器的分类结果优于BP神经网络。     

Power quality diagnosis using time frequency analysis and rule based techniques

Diagnosing a power quality disturbance means identifying the type and cause of the disturbance. Fast diagnosis of power quality disturbances is important so as to assist network operators in performing counter measures and implementing suitable power quality mitigation actions. In this study a novel method for performing power quality diagnosis is presented by using the S-transform and rule based classification techniques. The proposed power quality diagnosis method was evaluated for its functionality in detecting the type of short duration voltage disturbances and identifying the cause of the disturbances which may be due to permanent or non permanent faults. Based on the results, this new method has the potential to be used in the existing real time power quality monitoring system in Malaysia to expedite the diagnosis on the recorded voltage disturbances.     

A dual‐tree complex wavelet transform‐based approach for recognition of power system transients

The present paper proposes a dual‐tree complex wavelet transform (DTCWT) based approach for recognition of power system transients. Several researchers, all over the world, have so far attempted to solve the problems of recognition of power system transients, hybridizing transform‐based techniques with popular computational intelligence based tools, for example, using wavelet transform and S‐transform for feature extraction, followed by artificial neural networks (ANN) or fuzzy logic‐based classifiers. The proposed method of hybridizing DTCWT‐based feature extraction with ANN‐based classification could efficiently detect several commonly occurring power quality (PQ) disturbance events. The PQ disturbance events considered include four different transient conditions, namely transients due to capacitor switching, transformer inrush currents, transients due to motor switching and transients due to short circuit faults. A detailed performance comparison with several contemporary, competing methods existing in the literatures for similar problems aptly demonstrates the suitability of the proposed method.     

Micro-genetic algorithms for detecting and classifying electric power disturbances

The power quality analysis represents an important aspect in the overall society welfare. The analysis of power disturbances in electrical systems is typically performed in two steps: disturbance detection and disturbance classification. Disturbance detection is usually made through space transform techniques, and their classification is usually performed through artificial intelligence methods. The problem with those approaches is the adequate selection of parameters for these techniques. Due to the advantages of a variant scheme known as the micro-genetic algorithms, in this investigation, a new methodology to directly detect and classify electrical disturbances in one step is developed. The proposed approach is validated through synthetic signals and experimental test on real data, and the obtained results are compared with the particle swarm optimization method in order to show the effectiveness of this methodology.

     

Hybrid signal processing and machine intelligence techniques for detection,quantification and classification of power quality disturbances

This paper presents an advanced signal processing technique known as S-transform (ST) to detect and quantify various power quality (PQ) disturbances. ST is also utilized to extract some useful features of the disturbance signal. The excellent time–frequency resolution characteristic of the ST makes it an attractive candidate for analysis of power system disturbance signals. The number of features required in the proposed approach is less than that of the wavelet transform (WT) for identification of PQ disturbances. The features extracted by using ST are used to train a support vector machine (SVM) classifier for automatic classification of the PQ disturbances. Since the proposed methodology can reduce the features of disturbance signal to a great extent without losing its original property, it efficiently utilizes the memory space and computation time of the processor. Eleven types of PQ disturbances are considered for the classification purpose. The simulation results show that the combination of ST and SVM can effectively detect and classify different PQ disturbances.     

电力系统中网络质量问题分析方法及实现

电力电网质量情况是关系到电网正常运行的关键,如何及时监测电力网络是目前亟待解决的技术问题,针对该问题,提出了新型的质量监测方法,该文基于.NET的浏览器/服务器(B/S)架构设计出系统总体架构,该系统包括监测设备层、数据库层服务层、Web服务层、客户端应用层等,通过电力网络质量检测模块监测电力网络系统中影响电力网络质量的数据,诸如网络正常稳态数据、网络参数、告警事件数据等,并且应用OneNet平台实现电力网络数据的准确、实时采集和传输,并采用随机矩阵理论模型对监测的数据进行深度的分析,揭示影响电力系统数据的因素。通过试验分析,该技术方案能够及时发现电网中的问题,有利于电力电网的稳定运行。     

A versatile hardware architecture for a constant false alarm rate processor based on a linear insertion sorter

Constant False Alarm Rate (CFAR) algorithms are used in digital signal processing applications to extract targets from background in noisy environments. Some examples of applications are target detection in radar environments, image processing, medical engineering, power quality analysis, features detection in satellite images, Pseudo-Noise (PN) code detectors, among others. This paper presents a versatile hardware architecture that implements six variants of the CFAR algorithm based on linear and nonlinear operations for radar applications. Since some implemented CFAR algorithms require sorting the input samples, a linear sorter based on a First In First Out (FIFO) schema is used. The proposed architecture, known as CFAR processor, can be used as a specialized module or co-processor for Software Defined Radar (SDR) applications. The results of implementing the CFAR processor on a Field Programmable Gate Array (FPGA) are presented and discussed.     

A low power and real-time hardware recurrent neural network for time series analysis on wearable devices

The research presented in this paper addresses the exploitation of Deep Learning methods on wearable devices. We propose a hardware architecture capable of analyzing time series signals through a Recurrent Neural Network implemented on FPGA technology. This architecture has been validated using a real dataset, which includes three-axial accelerometer data acquired by a wearable device used for fall detection. The experiments have been conducted considering different devices and demonstrates that the proposed hardware architecture outperforms the state of the art solutions both in terms of processing time and power consumption. Indeed, the proposed architecture is real-time compliant in the elaboration of the fall detection dataset adopted for the validation. The power consumption is in the order of dozens μW. Finally, futher functionalities could be added in the same chip since the resource usage is low.     

Stability and Almost Disturbance Decoupling Analysis of Nonlinear System Subject to Feedback Linearization and Feedforward Neural Network Controller

This paper studies the tracking and almost disturbance decoupling problem of nonlinear system based on the feedback linearization and multilayered feedforward neural network approach. The feedback linearization and neural network controller guarantees exponentially global uniform ultimate bounded stability and the almost disturbance decoupling performance without using any learning or adaptive algorithms. The proposed approach provides the architecture of the neural network and the weights among the layers in order to guarantee stability of the system. Moreover, the new approach renders the system to be stable with the almost disturbance decoupling property at each step of selecting weights to enhance the performance if the proposed sufficient conditions are maintained. This study constructs a controller, under appropriate conditions, such that the resulting closed-loop system is valid for any initial condition and bounded tracking signal with the following characteristics: input-to-state stability with respect to disturbance inputs and almost disturbance decoupling performance. One example, which cannot be solved by the first paper on the almost disturbance decoupling problem, is proposed in this study to exploit the fact that the tracking and the almost disturbance decoupling performances are easily achieved by our proposed approach. In order to demonstrate the practical applicability, a famous ball-and-beam system has been investigated.      

基于db4提升小波的暂态电能质量的检测

暂态扰动是影响电能质量的重要因素之一,对电力用户和电力系统都会产生危害。针对暂态扰动信号具有非平稳性、突变性的特点,分析了db4提升小波变换的特性,提出了更新—预测—更新—预测—更新的结构,选择了合适的采样频率和分解层数,对暂态电能质量扰动信号进行检测与定位。在MATLAB仿真环境下,利用db4提升小波变换对电压暂降、暂升、中断以及暂态脉冲、振荡等几种暂态电能质量扰动信号进行检测与定位,仿真结果表明,该方法可以实现对扰动信号起止时刻更为准确的检测与定位,且计算速度快。     

Deep learning for vision‐based fall detection system: Enhanced optical dynamic flow

Accurate fall detection for the assistance of older people is crucial to reduce incidents of deaths or injuries due to falls. Meanwhile, vision‐based fall detection system has shown some significant results to detect falls. Still, numerous challenges need to be resolved. The impact of deep learning has changed the landscape of the vision‐based system, such as action recognition. The deep learning technique has not been successfully implemented in vision‐based fall detection system due to the requirement of a large amount of computation power and requirement of a large amount of sample training data. This research aims to propose a vision‐based fall detection system that improves the accuracy of fall detection in some complex environments such as the change of light condition in the room. Also, this research aims to increase the performance of the pre‐processing of video images. The proposed system consists of Enhanced Dynamic Optical Flow technique that encodes the temporal data of optical flow videos by the method of rank pooling, which thereby improves the processing time of fall detection and improves the classification accuracy in dynamic lighting condition. The experimental results showed that the classification accuracy of the fall detection improved by around 3% and the processing time by 40–50 ms. The proposed system concentrates on decreasing the processing time of fall detection and improving the classification accuracy. Meanwhile, it provides a mechanism for summarizing a video into a single image by using dynamic optical flow technique, which helps to increase the performance of image preprocessing steps.     

An optimized architecture for classification combining data fusion and data-mining

This paper presents a new architecture to integrate a library of feature extraction, Data-mining, and fusion techniques to automatically and optimally configure a classification solution for a given labeled set of training patterns. The most expensive and scarce resource in any detection problem (feature selection/classification) tends to be the acquiring of labeled training patterns from which to design the system. The objective of this paper is to present a new Data-mining architecture that will include conventional Data-mining algorithms, feature selection methods and algorithmic fusion techniques to best exploit the set of labeled training patterns so as to improve the design of the overall classification system. The paper describes how feature selection and Data-mining algorithms are combined through a Genetic Algorithm, using single source data, and how multi-source data are combined through several best-suited fusion techniques by employing a Genetic Algorithm for optimal fusion. A simplified version of the overall system is tested on the detection of volcanoes in the Magellan SAR database of Venus.     

POWER QUALITY DISTURBANCE CLASSIFICATION USING S-TRANSFORM AND RADIAL BASIS NETWORK

This article presents an artificial neural network (ANN)-based approach for power quality (PQ) disturbance classification. The input features of the ANN are extracted using S-transform. The features obtained from the S-transform are distinct, understandable, and immune to noise. These features after normalization are given to radial basis function (RBF) neural networks. The data required to develop the network are generated by simulating various faults in a test system. The proposed method requires a lesser number of features and less memory space without losing its original property. The simulation results show that the proposed method is effective and can classify the disturbance signals even under a noisy environment.