An emergency event detection approach in real-time for efficient vehicle safety in Smart City

Multimedia Tools and Applications - Nowadays, the Internet of things (IoT) provides various services to drivers by equipped with smart devices. In this regard, the next generation of vehicles...     

RADS: a real-time anomaly detection model for software-defined networks using machine learning

International Journal of Information Security - Software-defined networks (SDN) are no more a new technology as many industries are adopting it in a hybrid or full stack mode. SDN has already...     

An evolving approach to unsupervised and Real-Time fault detection in industrial processes

Fault detection in industrial processes is a field of application that has gaining considerable attention in the past few years, resulting in a large variety of techniques and methodologies designed to solve that problem. However, many of the approaches presented in literature require relevant amounts of prior knowledge about the process, such as mathematical models, data distribution and pre-defined parameters. In this paper, we propose the application of TEDA – Typicality and Eccentricity Data Analytics – , a fully autonomous algorithm, to the problem of fault detection in industrial processes. In order to perform fault detection, TEDA analyzes the density of each read data sample, which is calculated based on the distance between that sample and all the others read so far. TEDA is an online algorithm that learns autonomously and does not require any previous knowledge about the process nor any user-defined parameters. Moreover, it requires minimum computational effort, enabling its use for real-time applications. The efficiency of the proposed approach is demonstrated with two different real world industrial plant data streams that provide “normal” and “faulty” data. The results shown in this paper are very encouraging when compared with traditional fault detection approaches.     

Visual dynamic model based on self-organizing maps for supervision and fault detection in industrial processes

Visual data mining techniques have experienced a growing interest for processing and interpretation of the large amounts of multidimensional data available in current industrial processes. One of the approaches to visualize data is based on self-organizing maps (SOM), which define a projection of the input space onto a 2D or 3D space that can be used to obtain visual representations. Although these techniques have been usually applied to visualize static relations among the process variables, they have proven to be very useful to display dynamic features of the processes. In this work, an approach based on the SOM to model the dynamics of multivariable processes is presented. The proposed method identifies the process conditions (clusters) and the probabilities of transition among them, using the trajectory followed by the input data on the 2D visualization space. Furthermore, a new method of residual computation for fault detection and identification that uses the dynamic information provided by the model of transitions is proposed. The proposed method for modeling and fault identification has been applied to supervise a real industrial plant and the results are included.     

An efficient abstract machine for Safe Ambients

Safe Ambients (SA) are a variant of the Ambient Calculus (AC) in which types can be used to avoid certain forms of interferences among processes called grave interferences.An abstract machine, called GcPan, for a distributed implementation of typed SA is presented and studied. Our machine improves over previous proposals for executing AC, or variants of it, mainly through a better management of special agents (the forwarders), created upon code migration to transmit messages to the target location of the migration. Well-known methods (such as reference counting and union-find) are applied in order to garbage collect forwarders, thus avoiding long – possibly distributed – chains of forwarders, as well as avoiding useless persistent forwarders.We present the proof of correctness of GcPan w.r.t. typed SA processes. We describe a distributed implementation of the abstract machine in OCaml.More broadly, this study is a contribution towards understanding issues of correctness and optimisations in implementations of distributed languages encompassing mobility.     

An artificial neural-network model for impact properties in X70 pipeline steels

An artificial neural-network (ANN) model has been developed for the analysis and simulation of the correlation between the mechanical properties and composition and thermomechanical treatment parameters of high strength, low alloy steels. The input parameters of the model consist of alloy compositions (C, Si, Mn, P, S, Cu, Ni, Cr, Mo, Ti, V, Nb, Ca, Al, B) and tensile test results (yield strength, ultimate tensile strength, percentage elongation). The outputs of the ANN model include impact energy (?10 °C). The model can be used to calculate the properties of low alloy steels as a function of alloy composition and thermomechanical treatment variables. The current study achieved a good performance of the ANN model, and the results are in agreement with experimental knowledge.     

An efficient motion magnification system for real-time applications

The human eye cannot see subtle motion signals that fall outside human visual limits, due to either limited resolution of intensity variations or lack of sensitivity to lower spatial and temporal frequencies. Yet, these invisible signals can be highly informative when amplified to be observable by a human operator or an automatic machine vision system. Many video magnification techniques have recently been proposed to magnify and reveal these signals in videos and image sequences. Limitations, including noise level, video quality and long execution time, are associated with the existing video magnification techniques. Therefore, there is value in developing a new magnification method where these issues are the main consideration. This study presents a new magnification method that outperforms other magnification techniques in terms of noise removal, video quality at large magnification factor and execution time. The proposed method is compared with four methods, including Eulerian video magnification, phase-based video magnification, Riesz pyramid for fast phase-based video magnification and enhanced Eulerian video magnification. The experimental results demonstrate the superior performance of the proposed magnification method regarding all video quality metrics used. Our method is also 60–70% faster than Eulerian video magnification, whereas other competing methods take longer to execute than Eulerian video magnification.     

Decision fusion systems for fault detection and identification in industrial processes

Numerous fault detection and identification methods have been developed in recent years, whereas, each method works under its own assumption, which means a method works well in one condition may not provide a satisfactory performance in another condition. In this paper, we intend to design a fusion system by combining results of various methods. To increase the diversity among different methods, the resampling strategy is introduced as a data preprocessing step. A total of six conventionally used methods are selected for building the fusion system in this paper. Decisions generated from different models are combined together through the Dempster-Shafer evidence theory. Furthermore, to improve the computational efficiency and reliability of the fusion system, a new diversity measurement index named correlation coefficient is defined for model pruning in the fusion system. Fault detection and identification performances of the decision fusion system are evaluated through the Tennessee Eastman process.     

Towards precise real-time 3D difference detection for industrial applications

3D difference detection is the task to verify whether the 3D geometry of a real object exactly corresponds to a 3D model of this object. We present an approach for 3D difference detection with a hand-held depth camera. In contrast to previous approaches, with the presented approach geometric differences can be detected in real-time and from arbitrary viewpoints. The 3D difference detection accuracy is improved by two approaches: first, the precision of the depth camera's pose estimation is improved by coupling the depth camera with a high precision industrial measurement arm. Second, the influence of the depth measurement noise is reduced by integrating a 3D surface reconstruction algorithm. The effects of both enhancements are quantified by a ground-truth based quantitative evaluation, both for a time-of-flight (SwissRanger 4000) and a structured light depth camera (Kinect). With the proposed enhancements, differences of few millimeters can be detected from 1 m measurement distance.     

Improved canonical correlation analysis-based fault detection methods for industrial processes

Recent research has emphasized the successful application of canonical correlation analysis (CCA) to perform fault detection (FD) in both static and dynamic processes with additive faults. However, dealing with multiplicative faults has not been as successful. Thus, this paper considers the application of CCA to deal with the detection of incipient multiplicative faults in industrial processes. The new approaches incorporate the CCA-based FD with the statistical local approach. It is shown that the methods are effective in detecting incipient multiplicative faults. Experiments using a continuous stirred tank heater and simulations on the Tennessee Eastman process are provided to validate the proposed methods.     

A computationally efficient technique for real-time detection of particular-slope edges

Identification of oblique lines of a particular slope is needed for various applications such as motion tracking for smart cameras. Wavelets and gradient-based techniques, such as Sobel and Canny, do not classify edges based on their slopes. The Hough transform (HT) does classify edges based on their slopes but with high computational complexity, even using its most improved versions. This paper presents a computationally efficient technique for detecting edges of a particular slope. The angle of the required edges is converted into pixel increments over rows and columns. Using these two simple parameters, parallel, oblique lines of a particular slope are formed. A first-order, orthonormal Haar low-pass filter (LPF) is used over the formed lines to filter out undesired edges. The hardware architecture of the proposed technique is fully described, including processing time, based on the number of clock cycles, and fixed-point implementation. A line-based memory mechanism was used to minimize the memory requirements to two simple registers. To demonstrate the computational advantage of the proposed technique, it is compared to the Sobel, Canny and HT detectors.     

Evolving neuro-fuzzy network for real-time high impedance fault detection and classification

Neural Computing and Applications - This paper concerns the application of a neuro-fuzzy learning method based on data streams for high impedance fault (HIF) detection in medium-voltage power...     

A framework for real-time fault detection and diagnosis using temporal data

Successful real-time sensor-based fault detection and diagnosis in large and complex systems is seldom achieved by operators. The lack of an effective method for handling temporal data is one of several key problems in this area. A methodology is introduced which advantageously uses temporal data in performing fault diagnosis in a subsystem of a Navy ship propulsion system. The methodology is embedded in a computer program designed to be used as a decision aid to assist the operator. It utilizes machine learning, is able to cope with uncertainty at several levels, and works in real-time. Program performance data is presented and analysed. The approach illustrates how relatively simple existing techniques can be assembled into more powerful real-time diagnostic tools.     

An efficient dynamic system for real-time robot-path planning.

This paper presents a simple yet efficient dynamic-programming (DP) shortest path algorithm for real-time collision-free robot-path planning applicable to situations in which targets and barriers are permitted to move. The algorithm works in real time and requires no prior knowledge of target or barrier movements. In the case that the barriers are stationary, this paper proves that this algorithm always results in the robot catching the target, provided it moves at a greater speed than the target, and the dynamic-system update frequency is sufficiently large. Like most robot-path-planning approaches, the environment is represented by a topologically organized map. Each grid point on the map has only local connections to its neighboring grid points from which it receives information in real time. The information stored at each point is a current estimate of the distance to the nearest target and the neighbor from which this distance was determined. Updating the distance estimate at each grid point is done using only the information gathered from the point's neighbors, that is, each point can be considered an independent processor, and the order in which grid points are updated is not determined based on global knowledge of the current distances at each point or the previous history of each point. The robot path is determined in real time completely from the information at the robot's current grid-point location. The computational effort to update each point is minimal, allowing for rapid propagation of the distance information outward along the grid from the target locations. In the static situation, where both the targets and the barriers do not move, this algorithm is a DP solution to the shortest path problem, but is restricted by lack of global knowledge. In this case, this paper proves that the dynamic system converges in a small number of iterations to a state where the minimal distance to a target is recorded at each grid point and shows that this robot-path-planning algorithm can be made to always choose an optimal path. The effectiveness of this algorithm is demonstrated through a number of simulations.     

An FPGA implementation for real-time edge detection

The Hessian matrix-based edge detection algorithm of Dr. Carsten Steger has the advantages of high accuracy and versatility. However, this algorithm has a complex and time-consuming computation process. Large-scale Gaussian convolution also employs a large number of multipliers when implemented on a field programmable gate array (FPGA). To address these problems, an FPGA implementation for Steger’s edge detection algorithm is proposed. This implementation employs pipeline and parallel architectures at both task and data levels for data stream processing. The original kernels of Gaussian convolution are simplified with box-filter to convert the multiplication operation in the convolution into addition, subtraction, or shift operations with the concept of integral image, thereby minimizing the multiplier resources. The proposed FPGA implementation demonstrates a favorable accuracy and anti-noise capability when dealing with different degrees of blur and noise in an image. Therefore, the FPGA implementation can satisfy real-time edge detection requirements.     

Practical real-time intrusion detection using machine learning approaches

The growing prevalence of network attacks is a well-known problem which can impact the availability, confidentiality, and integrity of critical information for both individuals and enterprises. In this paper, we propose a real-time intrusion detection approach using a supervised machine learning technique. Our approach is simple and efficient, and can be used with many machine learning techniques. We applied different well-known machine learning techniques to evaluate the performance of our IDS approach. Our experimental results show that the Decision Tree technique can outperform the other techniques. Therefore, we further developed a real-time intrusion detection system (RT-IDS) using the Decision Tree technique to classify on-line network data as normal or attack data. We also identified 12 essential features of network data which are relevant to detecting network attacks using the information gain as our feature selection criterions. Our RT-IDS can distinguish normal network activities from main attack types (Probe and Denial of Service (DoS)) with a detection rate higher than 98% within 2 s. We also developed a new post-processing procedure to reduce the false-alarm rate as well as increase the reliability and detection accuracy of the intrusion detection system.     

基于LNS-DEWKECA算法的多模态工业过程故障检测

受市场需求主导,工业过程需要在多种工作模态下切换,数据往往呈现多模态复杂分布特性,研究多模态的故障检测技术对于保障工业过程的安全运行具有重要意义.为此,提出一种基于局部近邻标准化(LNS)和方向熵加权核熵成分分析(DEWKECA)的故障检测算法.利用LNS实现多模态数据的标准化,相比于全局标准化,LNS可以有效消除多模态特性;考虑到故障样本与正常样本在变化趋势上的差异,定义样本变化方向的信息熵为方向熵,用来衡量样本变化方向的无序程度,从而利用DEWKECA实现数据降维,可以更有效提取数据变化方向特征;考虑到多模态数据往往服从非高斯分布,采用局部离群因子(LOF)算法建立监控统计量,根据核密度估计确定其控制限.最后,通过数值例子及TE过程仿真验证所提出算法的有效性.     

Induction machine fault detection using clone selection programming

A clonal selection programming (CSP)-based fault detection system is developed for performing induction machine fault detection and analysis. Four feature vectors are extracted from power spectra of machine vibration signals. The extracted features are inputs of an CSP-based classifier for fault identification and classification. In this paper, the proposed CSP-based machine fault diagnostic system has been intensively tested with unbalanced electrical faults and mechanical faults operating at different rotating speeds. The proposed system is not only able to detect electrical and mechanical faults correctly, but the rules generated is also very simple and compact and is easy for people to understand, This will be proved to be extremely useful for practical industrial applications.