Generic Adaptive Sliding Mode Control for a Quadrotor UAV System Subject to Severe Parametric Uncertainties and Fully Unknown External Disturbance

International Journal of Control, Automation and Systems - This paper aims to provide a generic robust controller that is able to manipulate all kinds of quadrotor unmanned aerial vehicle (UAV)...     

Intelligent Machine Learning with Metaheuristics Based Sentiment Analysis and Classification

Sentiment Analysis (SA) is one of the subfields in Natural Language Processing (NLP) which focuses on identification and extraction of opinions that exist in the text provided across reviews, social media, blogs, news, and so on. SA has the ability to handle the drastically-increasing unstructured text by transforming them into structured data with the help of NLP and open source tools. The current research work designs a novel Modified Red Deer Algorithm (MRDA) Extreme Learning Machine Sparse Autoencoder (ELMSAE) model for SA and classification. The proposed MRDA-ELMSAE technique initially performs preprocessing to transform the data into a compatible format. Moreover, TF-IDF vectorizer is employed in the extraction of features while ELMSAE model is applied in the classification of sentiments. Furthermore, optimal parameter tuning is done for ELMSAE model using MRDA technique. A wide range of simulation analyses was carried out and results from comparative analysis establish the enhanced efficiency of MRDA-ELMSAE technique against other recent techniques.     

A systematic mapping of semi-formal and formal methods in requirements engineering of industrial Cyber-Physical systems

Journal of Intelligent Manufacturing - The requirements engineering of Industrial Cyber-Physical Systems is extremely challenging due to large system sizes, component heterogeneity, involvement of...     

Fracture toughness of eutectic Al-Si casting alloy with different microstructural features

The static fracture toughness of a series of eutectic Al-Si casting alloy with different microstructural features has been evaluated. The dominant influence of eutectic silicon in controlling the fracture toughness is thus clarified. The relationship between the fracture toughness and the microstructure was established. Fracture toughness was found to be strongly associated with the size and morphology of silicon particles. The other feature which greatly influences the fracture toughness is the ratio (/DE)_Si, i.e. the silicon particle spacing divided by the equivalent particle diameter, rather than the silicon particle spacing, _Si. Fracture toughness also correlates well with the void growth parameter, VGP (=_y (/DE)_Si), proposed by the authors. The results of the present work can be used to develop an understanding of the variation of fracture toughness with the microstructural features of eutectic Al-Si alloys.     

Learning from demonstration in robots: Experimental comparison of neural architectures

Robots have played an important role in the automation of computer aided manufacturing. The classical robot control implementation involves an expensive key step of model-based programming. An intuitive way to reduce this expensive exercise is to replace programming with machine learning of robot actions from demonstration where a (learner) robot learns an action by observing a demonstrator robot performing the same. To achieve this learning from demonstration (LFD) different machine learning techniques such as Artificial Neural Networks (ANN), Genetic Algorithms, Hidden Markov Models, Support Vector Machines, etc. can be used. This piece of work focuses exclusively on ANNs. Since ANNs have many standard architectural variations divided into two basic computational categories namely the recurrent networks and feed-forward networks, representative networks from each have been selected for study, i.e. Feed Forward Multilayer Perceptron (FF) network for feed-forward networks category and Elman (EL), and Nonlinear Autoregressive Exogenous Model (NARX) networks for the recurrent networks category. The main objective of this work is to identify the most suitable neural architecture for application of LFD in learning different robot actions. The sensor and actuator streams of demonstrated action are used as training data for ANN learning. Consequently, the learning capability is measured by comparing the error between demonstrator and corresponding learner streams. To achieve fairness in comparison three steps have been taken. First, Dynamic Time Warping is used to measure the error between demonstrator and learner streams, which gives resilience against translation in time. Second, comparison statistics are drawn between the best, instead of weight-equal, configurations of competing architectures so that learning capability of any architecture is not forced handicap. Third, each configuration's error is calculated as the average of ten trials of all possible learning sequences with random weight initialization so that the error value is independent of a particular sequence of learning or a particular set of initial weights. Six experiments are conducted to get a performance pattern of each architecture. In each experiment, a total of nine different robot actions were tested. Error statistics thus obtained have shown that NARX architecture is most suitable for this learning problem whereas Elman architecture has shown the worst suitability. Interestingly the computationally lesser MLP gives much lower and slightly higher error statistics compared to the computationally superior Elman and NARX neural architectures, respectively.     

On a new class of analytic functions associated with conic domain

The aim of this paper is to generalize the conic domain defined by Kanas and Wisniowska, and define the class of functions which map the open unit disk E onto this generalized conic domain. A brief comparison between these conic domains is the main motivation of this paper. A correction is made in selecting the range interval of order of conic domain.     

Crystal dislocation in SEM with image processing

Image processing algorithm is implemented to detect the grain boundary of the crystal using (SEM) Scanning Electron Microscopy. This paper presents a method for edge-detection in color image based on Sobel, Canny operator’s algorithm and discrete wavelet transform. The performance of these methods is effective and faster. Filtering is another approach to clear the noise of an image. Scanning Electron Microscopy (SEM) used to inspect semiconductor materials and devices for several decades, continues to increase in importance. Removal of noise is an important step in the image restoration process, but de-noising of the image has remained a challenging problem in recent research associated with image process. De-noising is used to remove the noise from corrupted images, while retaining the edges and other detailed features too are an essential part of de-noising.     

Fuzzy based multi-criteria vertical handover decision modeling in heterogeneous wireless networks

Vertical handover gain significant importance due to the enhancements in mobility models by the Fourth Generation (4G) technologies. However, these enhancements are limited to specific scenarios and hence do not provide support for generic mobility. Similarly, various schemes are proposed based on these mobility models but most of them are suffered from the high packet loss, frequent handovers, too early and late handovers, inappropriate network selection, etc. To address these challenges, a generic vertical handover management scheme for heterogeneous wireless networks is proposed in this article. The proposed scheme works in three phases. In the first phase, a handover triggering approach is designed to identify the appropriate place for initiating handover based on the estimated coverage area of a WLAN access point or cellular base station. In the second phase, fuzzy rule based system is designed to eliminate the inappropriate networks before deciding an optimal network for handover. In the third phase, a network selection scheme is developed based on the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) decision mechanism. Various parameters such as delay, jitter, Bit Error Rate (BER), packet loss, communication cost, response time, and network load are considered for selecting an optimal network. The proposed scheme is tested in a mobility scenario with different speeds of a mobile node ranging from very low to very high. The simulation results are compared with the existing decision models used for network selection and handover triggering approaches. The proposed scheme outperforms these schemes in terms of energy consumption, handover delay and time, packet loss, good put, etc.     

Regulation of Autophagy Machinery in Magnaporthe oryzae

Plant diseases cause substantial loss to crops all over the world, reducing the quality and quantity of agricultural goods significantly. One of the world’s most damaging plant diseases, rice blast poses a substantial threat to global food security. Magnaporthe oryzae causes rice blast disease, which challenges world food security by causing substantial damage in rice production annually. Autophagy is an evolutionarily conserved breakdown and recycling system in eukaryotes that regulate homeostasis, stress adaption, and programmed cell death. Recently, new studies found that the autophagy process plays a vital role in the pathogenicity of M. oryzae and the regulation mechanisms are gradually clarified. Here we present a brief summary of the recent advances, concentrating on the new findings of autophagy regulation mechanisms and summarize some autophagy-related techniques in rice blast fungus. This review will help readers to better understand the relationship between autophagy and the virulence of plant pathogenic fungi.