Flocking based approach for data clustering

Data clustering is a process of extracting similar groups of the underlying data whose labels are hidden. This paper describes different approaches for solving data clustering problem. Particle swarm optimization (PSO) has been recently used to address clustering task. An overview of PSO-based clustering approaches is presented in this paper. These approaches mimic the behavior of biological swarms seeking food located in different places. Best locations for finding food are in dense areas and in regions far enough from others. PSO-based clustering approaches are evaluated using different data sets. Experimental results indicate that these approaches outperform K-means, K-harmonic means, and fuzzy c-means clustering algorithms.     

On Effective Dual Use of Auxiliary Information in Variability Control Charts

During the last decade, variance control charts based on different sampling schemes have attracted research interest in the field of statistical process control. These charts used extra (auxiliary) information either for ranking of units or estimation rather than using it for both. The effectiveness of a control chart can be increased by utilizing the auxiliary information for dual purposes. This article is focused on developing a generalized structure of variance control charts based on dual use of auxiliary information under different sampling strategies and runs rules. The generalized structure mainly depends on three auxiliary information‐based estimators with dual use of auxiliary information, three bivariate process distributions, and variety of sampling schemes. The performance of the proposed control charts is investigated by assessing the power curve. We have observed that the proposals of the study perform better than its complement. An application example is also provided for practitioners' concerns to monitor the stability of physicochemical parameter of groundwater. Copyright © 2015 John Wiley & Sons, Ltd.     

On Modified Successive Sampling Based Control Charting Schemes

The presence of variation cannot be avoided in different kinds of manufacturing and non‐manufacturing processes. A better understanding of the causes of variability in any process is necessary to improve the process. Control chart is a very frequently used tool for checking whether the process parameters are stable or not. The current study devises a sampling technique, named as modified successive sampling scheme, that is not only cost‐effective but also efficient as compared with the simple random sampling scheme. A number of Shewhart‐type control charts are proposed based on the said sampling scheme, and average run length is used as a performance indicator. Based on the average run length values, all the proposed charts are compared with existing Shewhart control chart for both positive and negative shifts in the process. Finally, the new proposals are applied to a real dataset where the variable of interest is an inner diameter of automobile engine piston rings made of steel. Copyright © 2015 John Wiley & Sons, Ltd.     

On designing a progressive mean chart for efficient monitoring of process location

Variation is an important phenomenon of the output of every manufacturing and production process. To deal with the natural and special cause variations in the process, quality practitioners mostly apply control charts. There have been regular advancements over time in the design structures of these charts such as runs rules, fast initial response, sampling mechanisms among many others. In this article, auxiliary-information-based progressive mean (AIB-PM) control chart has been proposed, in which study variable is found correlated with another auxiliary variable. The development of the proposed AIB-PM structure utilises both the study and auxiliary variables. It is based on the regression estimator to introduce an unbiased and efficient estimate of the location parameter of the study variable. The performance assessment is carried out using average run length as a metric under zero-state and steady-state modes. The proposed AIB-PM chart is compared with some existing competitors and found that it performs uniformly superior than the existing competitors at small and persistent shifts in the process mean. An illustrative example using a real data set is presented to show the implementation of the proposed method.     

On developing an exponentially weighted moving average chart under progressive setup: An efficient approach to manufacturing processes

The exponentially weighted moving average (EWMA) control chart is a memory chart that is widely used in process monitoring to spot small and persistent disturbances in the process parameter(s). This chart requires normality of the quality characteristic(s) of interest and a smaller choice of smoothing parameter. Any deviations from these conditions affect its performance in terms of efficiency and robustness. For the said two concerns, this study develops a new mixed EWMA chart under progressive setup (mixed EWMA–progressive mean [MEP] chart). The proposed MEP chart combines the advantages of robustness (under nonnormal scenarios) and high sensitivity to small and persistent shifts in the process mean. The performance of the proposed MEP control chart is evaluated in terms of average run length and some other characteristics of run length distribution. The assessment of the proposed chart is made under standard normal, student's t, gamma, Laplace, logistic, exponential, contaminated normal and lognormal distributions. The performance of the proposed MEP chart is also compared with some existing competitors including the classical EWMA, the classical cumulative sum (CUSUM), the homogenously weighted moving average, the mixed EWMA–CUSUM, the mixed CUSUM–EWMA and the double EWMA charts. The analysis reveals that the proposal of this study offers a superior design structure relative to its competing counterparts. An application from substrates manufacturing process (in which flow width of the resist is the key quality characteristic) is also provided in the study.     

A Fused Machine Learning Approach for Intrusion Detection System

The rapid growth in data generation and increased use of computer network devices has amplified the infrastructures of internet. The interconnectivity of networks has brought various complexities in maintaining network availability, consistency, and discretion. Machine learning based intrusion detection systems have become essential to monitor network traffic for malicious and illicit activities. An intrusion detection system controls the flow of network traffic with the help of computer systems. Various deep learning algorithms in intrusion detection systems have played a prominent role in identifying and analyzing intrusions in network traffic. For this purpose, when the network traffic encounters known or unknown intrusions in the network, a machine-learning framework is needed to identify and/or verify network intrusion. The Intrusion detection scheme empowered with a fused machine learning technique (IDS-FMLT) is proposed to detect intrusion in a heterogeneous network that consists of different source networks and to protect the network from malicious attacks. The proposed IDS-FMLT system model obtained 95.18% validation accuracy and a 4.82% miss rate in intrusion detection.     

A high performance parallel Radon based OFDM transceiver design and simulation

A major goal of the next-generation wireless communication systems is the development of a reliable high-speed wireless communication system that supports high user mobility. They must focus on increasing the link throughput and the network capacity. In this paper a novel, spectral efficient system is proposed for generating and transmitting two-dimensional (2-D) orthogonal frequency division multiplexing (OFDM) symbols through 2-D inter-symbol interference (ISI) channel. Instead of conventional data mapping techniques, discrete finite Radon transform (FRAT) is used as a data mapping technique due to the increased orthogonality offered. As a result, the proposed structure gives a significant improvement in bit error rate (BER) performance. The new structure was tested and a comparison of performance for serial one-dimensional (1-D) Radon based OFDM and parallel 2-D Radon based OFDM is made under additive white Gaussian noise (AWGN), flat, and multi-path selective fading channels conditions. It is found that Radon based parallel 2-D OFDM has better speed and performance than serial 1-D Radon based OFDM.     

Hydrogen decrepitation as a method of powder preparation of a 2:17-type,Sm(Co,Cu, Fe,Zr)8.92 magnetic alloy

The present work has shown that hydrogen decrepitation of a 2:17-type Sm (Co_0.673 Cu_0.080Fe_0.222Zr_0.025)_8.92 alloy is a very rapid and convenient means of producing powdered material for the production of polymer-bonded permanent magnets. The magnets made from the hydrogen decrepitated powder (average particle size 100m) exhibited improved demagnetization loop shapes, higher intrinsic coercivities and improved elevated temperature stability when compared with the magnets produced from the standard milled powder material (average particle size 40m). These differences in properties have been related to the differences in the character of the powders produced by the two methods of decrepitation.     

A mixed finite element formulation for shells through a reduced Reissner's principle in elastodynamics

Summary The use of Mixed models based in Reissner's principle in statics has been found to lead to some desirable simplifications in Finite Element formulations, in particular in plates and shells. Reduced formulations of Reissner's principle such as the one used by Prato have proved to be even more successful. In this paper, a reduction similar to that of Prato is attempted on a mixed elastodynamic variational principle by Karnopp.

---

Eine gemischte finite Elemente-Formulierung für Schalen durch ein reduziertes Reissnersches Prinzip der Elastodynamik

Zusammenfassung Die Verwendung von gemischten Modellen basiert auf Reissners Prinzip der Statik führt zu erwünschten Vereinfachungen bei der Formulierung von finiten Elementen im speziellen bei Untersuchungen von Platten und Schalen. Reduzierungen des Reissnerschen Prinzips, wie sie von Prato angewendet worden sind, haben sich sogar als noch erfolgreicher erwiesen. In dieser Untersuchung wird eine Reduktion, ähnlich der von Prato, für ein gemischtes elastodynamisches Variationsprinzip nach Karnopp, vorgenommen.

---

Symbol Table A Domain of integration of the Functional. Also area of the triangle - b Second fundamental form of the shell middle surface - C ^ijkl Elastic Constants - E ₁,E ₁ ^* Strain Energy and Co-Energy density - e _ij Elastic strain tensor - f _i Body force density tensor - I _ks Karnopp's functional, specialized to shells - I _ksc Contracted Karnopp's functional, specialized to shells - i, j, k Index 1, 2, 3 - K ₁,K ₁ ^* Kinetic Energy and Co-Energy density - K ^* Kinetic co-energy density for shell - m Moment tensor defined at the mid-surface - n In-plane stress tensor defined at the middle surface - n Qualifier for the boundary normal - p ,p ³ Boundary forces - Prescribed boundary forces - p Shear force tensor defined at the mid-surface - R Position vector of a point in the volume of the shell - r Position vector of a point on the mid-surface - r _i Net impulse density tensor - S _u Portion of the boundary where displacements are preseribed - S Portion of the boundary where forces are prescribed - s Qualifier for the direction tangent to the boundary - t Time variable - t ^ij Stress tensor - u ,u ₃ Mid-surface displacements - Mid-surface velocities - V Volume - v _i Displacement tensor - , Indices. Range 1, 2 - Shear strain tensor for the middle surface - Variation operator - Mid-surface strain tensor - Mid-surface curvature strain tensor - Direction cosine tensor for boundary normal - Mid-surface rotation tensor - Mid-surface angular velocity tensor - _M Strain energy density - _M * Strain co-energy density - _B * Bending strain co-energy density - _TS ^* Transverse shear strain co-energy density - | Covariant differentiation with respect tox , etc - Partial differentiation with respect tox , etc - .(dot) Time differentiation - -(bar) Prescribed quantities