Failure Prediction for Scientific Workflows Using Nature-Inspired Machine Learning Approach

Scientific workflows have gained the emerging attention in sophisti-cated large-scale scientific problem-solving environments.The pay-per-use model of cloud,its scalability and dynamic deployment enables it suited for executing scientific workflow applications.Since the cloud is not a utopian environment,failures are inevitable that may result in experiencingfluctuations in the delivered performance.Though a single task failure occurs in workflow based applications,due to its task dependency nature,the reliability of the overall system will be affected drastically.Hence rather than reactive fault-tolerant approaches,proactive measures are vital in scientific workflows.This work puts forth an attempt to con-centrate on the exploration issue of structuring a nature inspired metaheuristics-Intelligent Water Drops Algorithm(IWDA)combined with an efficient machine learning approach-Support Vector Regression(SVR)for task failure prognostica-tion which facilitates proactive fault-tolerance in the scheduling of scientific workflow applications.The failure prediction models in this study have been implemented through SVR-based machine learning approaches and the precision accuracy of prediction is optimized by IWDA and several performance metrics were evaluated on various benchmark workflows.The experimental results prove that the proposed proactive fault-tolerant approach performs better compared with the other existing techniques.

Hybrid Approach for Privacy Enhancement in Data Mining Using Arbitrariness and Perturbation

Imagine numerous clients,each with personal data;individual inputs are severely corrupt,and a server only concerns the collective,statistically essential facets of this data.In several data mining methods,privacy has become highly critical.As a result,various privacy-preserving data analysis technologies have emerged.Hence,we use the randomization process to reconstruct composite data attributes accurately.Also,we use privacy measures to estimate how much deception is required to guarantee privacy.There are several viable privacy protections;however,determining which one is the best is still a work in progress.This paper discusses the difficulty of measuring privacy while also offering numerous random sampling procedures and statistical and categorized data results.Further-more,this paper investigates the use of arbitrary nature with perturbations in privacy preservation.According to the research,arbitrary objects(most notably random matrices)have"predicted"frequency patterns.It shows how to recover crucial information from a sample damaged by a random number using an arbi-trary lattice spectral selection strategy.Thisfiltration system's conceptual frame-work posits,and extensive practicalfindings indicate that sparse data distortions preserve relatively modest privacy protection in various situations.As a result,the research framework is efficient and effective in maintaining data privacy and security.

Energy-Efficient Routing Protocol with Multi-Hop Fuzzy Logic for Wireless Networks

A Wireless Sensor Network(WSN)becomes a newer type of real-time embedded device that can be utilized for a wide range of applications that make regular networking which appears impracticable.Concerning the energy produc-tion of the nodes,WSN has major issues that may influence the stability of the system.As a result,constructing WSN requires devising protocols and standards that make the most use of constrained capacity,especially the energy resources.WSN faces some issues with increased power utilization and an on going devel-opment due to the uneven energy usage between the nodes.Clustering has proven to be a more effective strategy in this series.In the proposed work,a hybrid meth-od is used for reducing the energy consumption among CHs.A Fuzzy Logic-based clustering protocol FLUC(unequally clustered)and Fuzzy Clustering with Energy-Efficient Routing Protocol(FCERP)are used.A Fuzzy Clustering with Energy Efficient Routing Protocol(FCERP)reduces the WSN power usage and increases the lifespan of the network.FCERP has created a novel cluster-based fuzzy routing mechanism that uses a limit value to combine the clustering and multi-hop routing capabilities.The technique creates uneven groups by using fuz-zy logic with a competitive range to choose the Cluster Head(CH).The input variables include the distance of the nodes from the ground station,concentra-tions,and remaining energy.The proposed FLUC-FCERP reduces the power usage and improves the lifetime of the network compared with the existing algorithms.

Optimized ANFIS Model for Stable Clustering in Cognitive Radio Network

With the demand for wireless technology,Cognitive Radio(CR)technology is identified as a promising solution for effective spectrum utilization.Connectivity and robustness are the two main difficulties in cognitive radio networks due to their dynamic nature.These problems are solved by using clustering techniques which group the cognitive users into logical groups.The performance of clustering in cognitive network purely depends on cluster head selection and parameters considered for clustering.In this work,an adaptive neuro-fuzzy inference system(ANFIS)based clustering is proposed for the cognitive network.The performance of ANFIS improved using hybrid particle swarm and whale optimization algorithms for parameter tuning called PSWO.The consequent and antecedent parameters of ANFIS model are tuned by PSWO.The proper cluster heads from the network are identified using optimized ANFIS.The proposed optimized ANFIS based clustering model is analyzed in terms of number of clusters,number of common channels,reclustering rate and stability period.Simulation results indicate that proposed clustering effectively increase the stability of cluster with reduced communication overhead compared to other conventional clustering algorithms.

Analysis of Power Quality for Distribution Networks Using Active Compensator

This paper concentrates on compensating the power quality issues which have been increased in day-to-day life due to the enormous usage of loads with power electronic control.One such solution is compensating devices like Pension Protection Fund(PPF),Active power filter(APF),hybrid power filter(HPF),etc.,which are used to overcome Power Quality(PQ)issues.The proposed method used here is an active compensator called unified power quality condi-tioner(UPQC)which is a combination of shunt and series type active filter con-nected via a common DC link.The primary objective is to investigate the behavior of the compensators in the distribution networks.The performance of two configurations of UPQC,Right Shunt UPQC(RS-UPQC)and Left Shunt UPQC(LS-UPQC)are tested in the distribution networks under various load con-ditions by connecting them at the source side of harmonic generation using a spe-cially constructed transformer called inductively filtered converter transformer which adopts special wiring scheme at the secondary side.PSCAD(Power Sys-tems Computer Aided Design)/EMTDC(Electromagnetic Transients with DC Analysis)software is used to model the compensators connected to the nonlinear load.Both RS-UPQC and LS-UPQC are tested at the distribution side of the sup-ply system with Hysteresis current controller for shunt and Sinusoidal pulse with modulation controller for series at various locations of power system network and their results are compared.

Wireless Sensor Network-based Detection of Poisonous Gases Using Principal Component Analysis

This work utilizes a statistical approach of Principal Component Ana-lysis(PCA)towards the detection of Methane(CH_(4))-Carbon Monoxide(CO)Poi-soning occurring in coal mines,forestfires,drainage systems etc.where the CH_(4) and CO emissions are very high in closed buildings or confined spaces during oxi-dation processes.Both methane and carbon monoxide are highly toxic,colorless and odorless gases.Both of the gases have their own toxic levels to be detected.But during their combined presence,the toxicity of the either one goes unidentified may be due to their low levels which may lead to an explosion.By using PCA,the correlation of CO and CH_(4) data is carried out and by identifying the areas of high correlation(along the principal component axis)the explosion suppression action can be triggered earlier thus avoiding adverse effects of massive explosions.Wire-less Sensor Network is deployed and simulations are carried with heterogeneous sensors(Carbon Monoxide and Methane sensors)in NS-2 Mannasim framework.The rise in the value of CO even when CH_(4) is below the toxic level may become hazardous to the people around.Thus our proposed methodology will detect the combined presence of both the gases(CH_(4) and CO)and provide an early warning in order to avoid any human losses or toxic effects.

Data Mining with Privacy Protection Using Precise Elliptical Curve Cryptography

Protecting the privacy of data in the multi-cloud is a crucial task.Data mining is a technique that protects the privacy of individual data while mining those data.The most significant task entails obtaining data from numerous remote databases.Mining algorithms can obtain sensitive information once the data is in the data warehouse.Many traditional algorithms/techniques promise to provide safe data transfer,storing,and retrieving over the cloud platform.These strategies are primarily concerned with protecting the privacy of user data.This study aims to present data mining with privacy protection(DMPP)using precise elliptic curve cryptography(PECC),which builds upon that algebraic elliptic curve infinitefields.This approach enables safe data exchange by utilizing a reliable data consolidation approach entirely reliant on rewritable data concealing techniques.Also,it outperforms data mining in terms of solid privacy procedures while maintaining the quality of the data.Average approximation error,computational cost,anonymizing time,and data loss are considered performance measures.The suggested approach is practical and applicable in real-world situations according to the experimentalfindings.

Secured Data Storage Using Deduplication in Cloud Computing Based on Elliptic Curve Cryptography

The tremendous development of cloud computing with related technol-ogies is an unexpected one.However,centralized cloud storage faces few chal-lenges such as latency,storage,and packet drop in the network.Cloud storage gets more attention due to its huge data storage and ensures the security of secret information.Most of the developments in cloud storage have been positive except better cost model and effectiveness,but still data leakage in security are billion-dollar questions to consumers.Traditional data security techniques are usually based on cryptographic methods,but these approaches may not be able to with-stand an attack from the cloud server's interior.So,we suggest a model called multi-layer storage(MLS)based on security using elliptical curve cryptography(ECC).The suggested model focuses on the significance of cloud storage along with data protection and removing duplicates at the initial level.Based on divide and combine methodologies,the data are divided into three parts.Here,thefirst two portions of data are stored in the local system and fog nodes to secure the data using the encoding and decoding technique.The other part of the encrypted data is saved in the cloud.The viability of our model has been tested by research in terms of safety measures and test evaluation,and it is truly a powerful comple-ment to existing methods in cloud storage.

A Survey on Modeling and Enhancing Reliability of Wireless Sensor Network

Design of reliable wireless sensor network (WSN) needs to address the failure of single or multiple network components and implementation of the techniques to tolerate the faults occurred at various levels. The issues and requirements of reliability improvement mechanism depend on the available resources and application for which the WSN is deployed. This paper discusses the different modeling approaches to evaluate the reliability and classification of the approaches to improve it. Also the paper analyzes reliability enhancement by existing fault tolerant methods in WSN and compares the performance of these techniques with the technique we developed. From the results of the analysis we highlight the challenges and the characteristics of the sensor network affects the reliability and give some scope of future research directions in order to enhance reliability.

Fault Diagnostics on Steam Boilers and Forecasting System Based on Hybrid Fuzzy Clustering and Artificial Neural Networks in Early Detection of Chamber Slagging/Fouling

The slagging/fouling due to the accession of fireside deposits on the steam boilers decreases boiler efficiency and availability which leads to unexpected shut-downs. Since it is inevitably associated with the three major factors namely the fuel characteristics, boiler operating conditions and ash behavior, this serious slagging/fouling may be reduced by varying the above three factors. The research develops a generic slagging/fouling prediction tool based on hybrid fuzzy clustering and Artificial Neural Networks (FCANN). The FCANN model presents a good accuracy of 99.85% which makes this model fast in response and easy to be updated with lesser time when compared to single ANN. The comparison between predictions and observations is found to be satisfactory with less input parameters. This should be capable of giving relatively quick responses while being easily implemented for various furnace types.

Optimal Adaptive Genetic Algorithm Based Hybrid Signcryption Algorithm for Information Security

The functions of digital signature and public key encryption are simultaneously fulfilled by signcryption,which is a cryptographic primitive.To securely communicate very large messages,the cryptographic primitive called signcryption efficiently implements the same and while most of the public key based systems are suitable for small messages,hybrid encryption(KEM-DEM)provides a competent and practical way.In this paper,we develop a hybrid signcryption technique.The hybrid signcryption is based on the KEM and DEM technique.The KEM algorithm utilizes the KDF technique to encapsulate the symmetric key.The DEM algorithm utilizes the Adaptive Genetic Algorithm based Elliptic curve cryptography algorithm to encrypt the original message.Here,for the security purpose,we introduce the three games and we proved the attackers fail to find the security attributes of our proposed signcryption algorithm.The proposed algorithm is analyzed with Daniel of Service(DOS),Brute Force attack and Man In Middle(MIM)attacks to ensure the secure data transaction.

A Hybrid Artificial Intelligence Model for Skin Cancer Diagnosis

Melanoma or skin cancer is the most dangerous and deadliest disease.As the incidence and mortality rate of skin cancer increases worldwide,an automated skin cancer detection/classification system is required for early detection and prevention of skin cancer.In this study,a Hybrid Artificial Intelligence Model(HAIM)is designed for skin cancer classification.It uses diverse multi-directional representation systems for feature extraction and an efficient Exponentially Weighted and Heaped Multi-Layer Perceptron(EWHMLP)for the classification.Though the wavelet transform is a powerful tool for signal and image processing,it is unable to detect the intermediate dimensional structures of a medical image.Thus the proposed HAIM uses Curvelet(CurT),Contourlet(ConT)and Shearlet(SheT)transforms as feature extraction techniques.Though MLP is very flexible and well suitable for the classification problem,the learning of weights is a challenging task.Also,the optimization process does not converge,and the model may not be stable.To overcome these drawbacks,EWHMLP is developed.Results show that the combined qualities of each transform in a hybrid approach provides an accuracy of 98.33%in a multi-class approach on PH2 database.

Mammogram Learning System for Breast Cancer Diagnosis Using Deep Learning SVM

The most common form of cancer for women is breast cancer.Recent advances in medical imaging technologies increase the use of digital mammograms to diagnose breast cancer.Thus,an automated computerized system with high accuracy is needed.In this study,an efficient Deep Learning Architecture(DLA)with a Support Vector Machine(SVM)is designed for breast cancer diagnosis.It combines the ideas from DLA with SVM.The state-of-the-art Visual Geometric Group(VGG)architecture with 16 layers is employed in this study as it uses the small size of 3×3 convolution filters that reduces system complexity.The softmax layer in VGG assumes that the training samples belong to exactly only one class,which is not valid in a real situation,such as in medical image diagnosis.To overcome this situation,SVM is employed instead of the softmax layer in VGG.Data augmentation is also employed as DLA usually requires a large number of samples.VGG model with different SVM kernels is built to classify the mammograms.Results show that the VGG-SVM model has good potential for the classification of Mammographic Image Analysis Society(MIAS)database images with an accuracy of 98.67%,sensitivity of 99.32%,and specificity of 98.34%.

Modified Mackenzie Equation and CVOA Algorithm Reduces Delay in UASN

In Underwater Acoustic Sensor Network(UASN),routing and propagation delay is affected in each node by various water column environmental factors such as temperature,salinity,depth,gases,divergent and rotational wind.High sound velocity increases the transmission rate of the packets and the high dissolved gases in the water increases the sound velocity.High dissolved gases and sound velocity environment in the water column provides high transmission rates among UASN nodes.In this paper,the Modified Mackenzie Sound equation calculates the sound velocity in each node for energy-efficient routing.Golden Ratio Optimization Method(GROM)and Gaussian Process Regression(GPR)predicts propagation delay of each node in UASN using temperature,salinity,depth,dissolved gases dataset.Dissolved gases,rotational and divergent winds,and stress plays a major problem in UASN,which increases propagation delay and energy consumption.Predicted values from GPR and GROM leads to node selection and Corona Virus Optimization Algorithm(CVOA)routing is performed on the selected nodes.The proposed GPR-CVOA and GROM-CVOA algorithm solves the problem of propagation delay and consumes less energy in nodes,based on appropriate tolerant delays in transmitting packets among nodes during high rotational and divergent winds.From simulation results,CVOA Algorithm performs better than traditional DF and LION algorithms.

Growth of Pure and Mo Doped Potassium Titanyl Phosphate (KTP) Crystals:Influence of KTP/Flux Ratios on the Growth Morphology

Pure and Molybdenum (Mo) doped Potassium Titanyl Phosphate (KTP) inorganic crystals were grown by high temperature solution growth (HTSG) from poly phosphate (K6P4O13) flux using different KTP/Flux ratios. The pure and doped KTP crystals of size 20x13x5 mm3 and 7x5x2.5 mm3 respectively were grown successfully by spontaneous nucleation. The grown crystals were characterized by XRD, UV, FTIR and Hardness studies. Micro hardness studies show that the pure crystals are harder than the Mo doped crystals.

Chromatic Number of Graphs with Special Distance Sets-V

An integer distance graph is a graph G(Z,D) with the set of integers as vertex set and an edge joining two vertices u and?v if and only if ∣u - v∣D where D is a subset of the positive integers. It is known that x(G(Z,D) )=4 where P is a set of Prime numbers. So we can allocate the subsets D of P to four classes, accordingly as is 1 or 2 or 3 or 4. In this paper we have considered the open problem of characterizing class three and class four sets when the distance set D is not only a subset of primes P but also a special class of primes like Additive primes, Deletable primes, Wedderburn-Etherington Number primes, Euclid-Mullin sequence primes, Motzkin primes, Catalan primes, Schroder primes, Non-generous primes, Pell primes, Primeval primes, Primes of Binary Quadratic Form, Smarandache-Wellin primes, and Highly Cototient number primes. We also have indicated the membership of a number of special classes of prime numbers in class 2 category.

Multi-Dimension Support Vector Machine Based Crowd Detection and Localisation Framework for Varying Video Sequences

In this paper, we propose a novel method for anomalous crowd behaviour detection and localization with divergent centers in intelligent video sequence through multiple SVM (support vector machines) based appearance model. In multi-dimension SVM crowd detection, many features are available to track the object robustly with three main features which include 1) identification of an object by gray scale value, 2) histogram of oriented gradients (HOG) and 3) local binary pattern (LBP). We propose two more powerful features namely gray level co-occurrence matrix (GLCM) and Gaber feature for more accurate and authenticate tracking result. To combine and process the corresponding SVMs obtained from each features, a new collaborative strategy is developed on the basis of the confidence distribution of the video samples which are weighted by entropy method. We have adopted subspace evolution strategy for reconstructing the image of the object by constructing an update model. Also, we determine reconstruction error from the samples and again automatically build an update model for the target which is tracked in the video sequences. Considering the movement of the targeted object, occlusion problem is considered and overcome by constructing a collaborative model from that of appearance model and update model. Also if update model is of discriminative model type, binary classification problem is taken into account and overcome by collaborative model. We run the multi-view SVM tracking method in real time with subspace evolution strategy to track and detect the moving objects in the crowded scene accurately. As shown in the result part, our method also overcomes the occlusion problem that occurs frequently while objects under rotation and illumination change due to different environmental conditions.

Implementation of FPGA Based Hybrid Power Generator for PV and Wind Grid Applications

This paper deals with implementation of Sinusoidal Pulse-Width-Modulation (SPWM) for a single-phase hybrid power filter generator for Photovoltaic (PV) and wind grid applications. Using policy iteration algorithm, an improved variable step-size perturbation and observation algorithm is contrived and it is implemented proficiently using a hard-ware description language (VHDL) (Very High Speed Integrated Circuit Hardware Description Language). Subsequently, the new generated grid source supplements the existing grid power in rural houses during its cut off or restricted supply period. The software is used for generating SPWM modulation integrated with a solar-power & wind power grid system which is implemented on the Spartan 3 FPGA. The proposed algorithm performs as a conventional controller in terms of tracking speed and mitigating fluctuation output power in steady state operation which is shown in the experimental results with a commercial PV array and HPW (Height Weight Proportional) show. Simulation results demonstrate the validity with load of the proposed algorithm.

Developing Dijik-Primbert Algorithm for Finding Unpredictable Paths over Time-Varying Networks

Cooperation among multiple unmanned vehicles is an intensely challenging topic from a theoretical and practical standpoint, with far reaching indications in scientific and commercial mission scenarios. The difficulty of time coordination for a rapid of multirotor UAVs includes predefined spatial paths according to mission necessities. With the solution proposed, cooperative control is accomplished in the presence of time-varying communication networks, as well as stringent temporal constraints, such as concurrent arrival at the desired final locations. The proposed explanation solves the time-coordination problem under the acceptance that the trajectory-genera- tion and the path-following algorithms meeting convinced cohesion conditions are given. Communication is processed in unpredictable paths by the use of path following and directed communication graph. Dijik-Primbert algorithm for finding the shortest collision free paths is used to avoid and detect collision/congestion in unpredictable paths. Without collision detection, it doesn’t seem agreeable to have collision avoidance because there wouldn’t be everything to avoid. Dijikloyd algorithm is used for finding shortest paths in a weighted directed graph with positive and negative edges. Primloyd algorithm is used for finding shortest paths in a weighted undirected graph for conquering the complexity in matrix coding. In case of conges- tion or collision then the whole network is learned about it to all the communica- tors. Hence, communication is taken place in an unpredictable path in a secured manner.

Inverter Power Stage Connected with PV-Grid

This paper focuses on the design of the inverter power stage connected with PV-grid which supports the contrived PV system. The increased number of grid connected photovoltaic (PV) inverters gave rise to problems concerning the stability and safety of the utility grid, as well as power quality issues. The proposed systems can overcome these issues and improve standard regulation methods for gird connected PV inverter. The maximum available voltage in the PV string is tracked by the power stage which has been planned and designed in such a way. The tracked voltage is boosted then. The important components to voltage source inverter (VSI) are boost inductor and input capacitor which are calculated. To get a clear sinusoidal output phase voltage of 230 V from a DC capacitance bus projected to deal with 400 V, the important inverter stage parameters have been planned and modeled in Mat lab. Each block stage of the converter is easily understandable by the Simlink of the dual stage DC-AC converter explanation. The control schemes which have been proposed would compromise with the inverter power stage which forms the neat grid system. The existing renewable energy sources in the laboratory are integrated by the proposed control.