In the present times, artificial-intelligence based techniques are considered as one of the prominent ways to classify images which can be conveniently leveraged in the real-world scenarios. This technology can be extremely beneficial to the lepidopterists, to assist them in classification of the diverse species of Rhopalocera, commonly called as butterflies. In this article, image classification is performed on a dataset of various butterfly species, facilitated via the feature extraction process of the Convolutional Neural Network (CNN) along with leveraging the additional features calculated independently to train the model. The classification models deployed for this purpose predominantly include K-Nearest Neighbors (KNN), Random Forest and Support Vector Machine (SVM). However, each of these methods tend to focus on one specific class of features. Therefore, an ensemble of multiple classes of features used for classification of images is implemented. This research paper discusses the results achieved from the classification performed on basis of two different classes of features i.e., structure and texture. The amalgamation of the two specified classes of features forms a combined data set, which has further been used to train the Growing Convolutional Neural Network (GCNN), resulting in higher accuracy of the classification model. The experiment performed resulted in promising outcomes with TP rate, FP rate, Precision, recall and F-measure values as 0.9690, 0.0034, 0.9889, 0.9692 and 0.9686 respectively. Furthermore, an accuracy of 96.98% was observed by the proposed methodology.

: Biometric applications widely use the face as a component for recognition and automatic detection. Face rotation is a variable component and makes face detection a complex and challenging task with varied angles and rotation. This problem has been investigated, and a novice algorithm, namely RIFDS (Rotation Invariant Face Detection System), has been devised. The objective of the paper is to implement a robust method for face detection taken at various angle. Further to achieve better results than known algorithms for face detection. In RIFDS Polar Harmonic Transforms (PHT) technique is combined with Multi-Block Local Binary Pattern (MBLBP) in a hybrid manner. The MBLBP is used to extract texture patterns from the digital image, and the PHT is used to manage invariant rotation characteristics. In this manner, RIFDS can detect human faces at different rotations and with different facial expressions. The RIFDS performance is validated on different face databases like LFW, ORL, CMU, MIT-CBCL, JAFFF Face Databases, and Lena images. The results show that the RIFDS algorithm can detect faces at varying angles and at different image resolutions and with an accuracy of 99.9%. The RIFDS algorithm outperforms previous methods like Viola-Jones, Multi-block Local Binary Pattern (MBLBP), and Polar HarmonicTransforms (PHTs). The RIFDS approach has a further scope with a genetic algorithm to detect faces (approximation) even from shadows.

Image segmentation is a key step in the image analysis, pattern recognition, low-level vision, medical data analysis, objects tracking, recognition task and grasping of things from the field of robotics. Being a problematic and demanding chore in image processing, it governs the eminence of absolute outcomes of image analysis. The method aims to improve color detection using formulations in RGB arrays. First targeted color is selected and identified the desired color location by sliding window techniques. Then threshold has been calculated using the summation of within and between the class variance of the selected color. Proposed method overcomes the limitation of complex, the dearth incorrectness, and steadiness of conventional multilevel thresholding for image segmentation. This work is tested on a different kind of images such as two-dimensional images, low-quality images, complex images, blur images, and medical images. The simulated results designate the maximum accuracy and minimum computational time over other methods.

Refining visibility through haze removal from image becomes an inevitable chore and essential to recognize and track vehicles, traffic signal, and signs clearly under road safety. That can face a recurrent degradation under destitute climatic circumstances for instance fog, rain, cloud, and smog. To diminish this constraint, various methods were designed and implemented, but most were not capable of obtaining the improved quantitative outcomes. Therefore, a new algorithm Fog Elimination using Multiple Thresholds (FEMT) for single image haze eviction that meritoriously obtains the significant results on both gray and colored over real and synthetic images using multiple thresholds is proposed in this paper. The proposed method targets on the light regions by reducing the brightness and increasing the contrast of image at different levels. Finally, by grouping all the obtained resultant images leads to the generation of the resultant defogged image. The qualitative and quantitative analysis is carried out for an assessment of digitalized de-hazed images acquired from the proposed algorithm and compared to the prior techniques. Simulated fallouts entitle high resemblance to the corresponding ground truth, reduction in computation time consumption to 88% and error of 98%. The proposed approach can be applied in the field of robotics, human activity monitoring, smart systems, and digital investigation on the hazy images.

Hiding data in electrocardiogram signals are a big challenge due to the embedded information that can hamper the accuracy of disease detection. On the other hand, hiding data into ECG signals provides more security for, and authenticity of, the patient's data. Some recent studies used non-blind watermarking techniques to embed patient information and data of a patient into ECG signals. However, these techniques are not robust against attacks with noise and show a low performance in terms of parameters such as peak signal to noise ratio (PSNR), normalized correlation (NC), mean square error (MSE), percentage residual difference (PRD), bit error rate (BER), structure similarity index measure (SSIM). In this study, an improved blind ECG-watermarking technique is proposed to embed the information of the patient's data into the ECG signals using curvelet transform. The Euclidean distance between every two curvelet coefficients was computed to cluster the curvelet coefficients and after this, data were embedded into the selected clusters. This was an improvement not only in terms of extracting a hidden message from the watermarked ECG signals, but also robust against image-processing attacks. Performance metrics of SSIM, NC, PSNR and BER were used to measure the superiority of presented work. KL divergence and PRD were also used to reveal data hiding in curvelet coefficients of ECG without disturbing the original signal. The simulation results also demonstrated that the clustering method in the curvelet domain provided the best performance-even when the hidden messages were large size.

Digital image watermarking aims to protect the information in an image without significantly affecting visual quality. In this paper, a new image watermarking technique has been proposed that uses Gaussian filters and first-order partial differential matrix to extort the edge surface of a host image. This paper influence on the edge surface curvelet coefficients as human eyes are not equally sensitive to a smooth and an edged surface. To preserve the quality of the artwork and to increase the resistance against attacks, the author utilizes the edge surface area of an image, coarse levels of curvelet transform, and strength parameters. The selection of host coefficients are conforming to the human visual system (HVS) is the uniqueness of the research. The exploitation of the Gaussian filters and first-order partial differential coarse curvelet coefficients and the watermark strength parameter offers robustness against image processing attacks. The standard visual quality perception of HVS evaluation metrics are used to measure the superiority of the presented work.

Modern component retrieval approaches are based on the context and domain of the software component in addition to using various classification and retrieval techniques like keyword search, attribute-based search and semantic search. This work proposes ontological retrieval framework for software components that makes the use of ontology for effective retrieval of components. Ontological component retrieval framework has been created to facilitate the users and developers to retrieve software components matching precisely to their needs. A well-framed set of queries ranging from little to specific knowledge about the component requirement has been used to validate the results.

The presence of mixed pixels in remote sensing images is the major issue for accurate classification. In this paper, we have focused on two aspects of mixed pixel problem: firstly, to identify mixed pixels from an image and secondly to label them to their appropriate class. In phase I, extraction of mixed pixels has been performed from the RSI images-based super-pixel algorithm and RGB model by using fuzzy C-means (FCM). In phase II, the extracted mixed pixel from phase I has been decomposed to the appropriate class. This new proposed technique is the amalgamation of PSO-FCM (particle swarm optimization-fuzzy C-means) for clustering of mixed pixels and ANN-BPO (artificial neural network-biogeography-based particle swarm optimization) for the classification purpose. Experimental results reveal that the proposed method has improved the accuracy as compared to the existing techniques and succeeds in better classification of the remote sensing images.

Background: With an exponential increase in software online as well as offline, through each passing day, the task of digging out precise and relevant software components has become the need of the hour. There is no dearth of techniques used for the retrieval of software component from the available online and offline repositories in the conceptual as well as the empirical literature. However each of these techniques has its own set of limitations and suitability. Objective: The proposed technique gives concrete decision using schematic based search that gives better result and higher precision and recall values. Methods: In this paper, a component decision and retrieval engine called SR-SCRS (Schematic and Refinement based Software Component Retrieval System) has been presented using OPAM. OPAM is a github repository containing software components (packages), designed by OcamlPro. This search engine employs two retrieval techniques for a robust decision vis-o-vis Schematic-based search with fuzzy logic and Refinement-based search. The Schematic based search is based on matching the attribute values and the threshold of those values as given by the user. Thereafter the results are optimized to achieve the level of relevance using fuzzy logic. Refinement based search works on one particular attribute value. The experiments have been conducted and validated on OPAM dataset. Results: Precisely, the average precision of Schematic based search and Refinement based search is 60% and 27.86% which shows robust results. Conclusion: Hence, the performance and efficiency of the proposed work has been evaluated and compared with the other retrieval technique.

Automation in medical industry has become one of the necessities in today’s medical scenario. Radiologists/physicians need such automation techniques for accurate diagnosis and treatment planning. Automatic segmentation of tumor portion from Magnetic Resonance (MR) brain images is a challenging task. Several methodologies have been developed with an objective to enhance the segmentation efficiency of the automated system. However, there is always scope for improvement in the segmentation process of medical image analysis. In this work, deep learning-based approach is proposed for brain tumor image segmentation. The proposed method includes the concept of Stationary Wavelet Transform (SWT) and new Growing Convolution Neural Network (GCNN). The significant objective of this work is to enhance the accuracy of the conventional system. A comparative analysis with Support Vector Machine (SVM) and Convolution Neural Network (CNN) is carried out in this work. The experimental results prove that the proposed technique has outperformed SVM and CNN in terms of accuracy, PSNR, MSE and other performance parameters.

An edge detection is important for its reliability and security which delivers a better understanding of object recognition in the applications of computer vision, such as pedestrian detection, face detection, and video surveillance. This paper introduced two fundamental limitations encountered in edge detection: edge connectivity and edge thickness, those have been used by various developments in the state-of-the-art. An optimal selection of the threshold for effectual edge detection has constantly been a key challenge in computer vision. Therefore, a robust edge detection algorithm using multiple threshold approaches (B-Edge) is proposed to cover both the limitations. The majorly used canny edge operator focuses on two thresholds selections and still witnesses a few gaps for optimal results. To handle the loopholes of the canny edge operator, our method selects the simulated triple thresholds that target to the prime issues of the edge detection: image contrast, effective edge pixels selection, errors handling, and similarity to the ground truth. The qualitative and quantitative experimental evaluations demonstrate that our edge detection method outperforms competing algorithms for mentioned issues. The proposed approach endeavors an improvement for both grayscale and colored images.

This chapter reviews some ontologies, tools, and editors used in building and maintaining the ontology from those reported in the literature, and the main focus is on the interoperability between them. The essential thing while developing an ontology or using an ontology from world web are tools. Through tools, ontology can either be developed or aligned in a manner that the researcher wants and given direction in term of opinion from the source files as meta data. This chapter presents various editors for building the ontology and various tools for matching between the two ontologies and conclusion based on the repository extracted as from the data in term of mining results. Comparison of various ontologies, tools, and editors are also there in order for the ease of user to access a particular ontology tool for selection of data in term of repository or components from the enormous data.

This paper describes the prerequisites of software component retrieval which further explore the information about the algorithms and tools of software component retrieval. These techniques and procedures are mainly used for analyzing the enormous software components and their parameters. There is a need to find enhanced and optimized result using advance technologies of software component analysis. The objectives of the paper are to understand the component retrieval concepts, to get acquainted with software component extraction, to analyze the enormous amount of component and its parameter and to understand the need of software component analysis.

There is a tremendous growth of component retrieval in the field of component-based software engineering, but the lack of interrelations between concepts and interfaces is still an issue. The gap is fulfilled by the ontology so that the best component can be retrieved by providing interrelationships between components. The objectives of this paper are to study various ontologies that are built by human and to find out the process of ontology retrieval. This paper reviews the current tools and techniques for retrieving the component from repository. To attain good results for retrieving the component from repository, the components in the repository should not only be interlinked but also provide interrelationships of the component that can only be done by using ontology.

Automatic speech recognition is a field related to the interaction between user and machine using effective techniques. ASR is one of the very hot concepts in these days. A lot of researchers worked on different techniques to achieve the best accuracy for speech recognition. In previous research techniques used provides accuracy for a single utterance. Due to which for continuous utterance combination of the technique used in this research work which provides best accurate performance with less noisy interaction. For this research work, Mel Frequency Cepstrum Coefficient (MFCC) and Vector Quantization (VQ) techniques are used. These techniques provide easy speech processing with Mel-frequency scale which includes spacing of linear frequency less than 1000 Hz. Due to which MFCC provides high accuracy, less complexity and high performance with capturing main characteristics of speech. This approach provides efficient and more accurate results than other techniques for a continuous speech by minimizing the distortion created by noise. In this research work algorithms for each technique are represented. This research work presents best possible accuracy for continuous speech signal as compared to other feature extraction techniques. (C) 2018 The Authors. Published by IASE.

Communication among several internet users has become more convenient through social networking sites to where each user sharing his own opinions on different matters, such as Healthcare, Education, marketing etc. The Objective of this paper is to present a method to make it easier for even a layman to predict and analyze one’s health issues on his own bymaking use of tweets on the social website twitter.com. As far as methodology or techniques is concerned, an algorithm has been framed for the same to perform the analysis on health care tweets with association rules to classify the ailments and their symptoms using a corpus through fuzzy set and two step approach for Document Term Matrix & Term Document Matrix. The results demonstrate the comparison of different terms over the WordCloud which concludes that inthis novel approach of two step authentication the average accuracy of association between the hiv ailments is 98% through correlation table and association between the HIV ailments with 98% correlation.

A code smell detection and refactor is one of the very hot concepts in these days. A Lot of researcher worked on it to create an automatic bad smell detection and refactoring system. Main purpose behind the development of these type of systems is to create automatic for enhance the development quality of software systems. In the previous research the smell detection system perform detection on specific areas or specific language. Due to this companies needs to use more than one detector for software testing for large projects. The system is combination of various modules which can be developed in various languages. Our proposed method which is helpful their users to test their code and detect bad smell on more than one language. It acts as a bridge with some optimization techniques which provide highly accurate working for smell detection along with refactoring. Proposed approach uses optimization along with fact and rule programming to detect and refactor the bad smell from input programs. Various bad smells like long methods, dead code, lazy class, long class, etc. are used to check the quality of the code. The proposed approach is also working for Java, c++ and c#. net codes for the test all these bad smell and refactor c++ and Java code. The performance of the proposed approach is also better than other existing algorithms in terms of accuracy for detection and refactoring of bad smells. Some other challenges that the proposed approach faced to find the smells in the code also affect the performance. One of the main challenges is the way of writing code is different for everyone. So it's difficult to detect and refactor the thing on smell detection tool. Proposed approach used fact and rule processing for detection and eliminates unwanted entries with the help of the optimization process. The performance in terms of accuracy and FAR, FRR are stable and better for all the test cases in the comparison of existing methods and proposed approach. (C) 2017 The Authors. Published by IASE. This is an open access article under the CC BY-NC-ND license.

The software engineering based on components is an evolving branch of software engineering. The evolution in data mining and information retrieval techniques forms the basis of the approaches to component retrieval. This has paved way to new techniques to be used for efficient storage, retrieval and management of component repository and storage systems. Such information retrieval caters to the needs of rapid delivery and intelligent computations on Big Data can be used as well for recommender systems for the areas like component based development.

Cloud computing is basically excogitated from the word internet, which is an advance technology. Cloud computing enables us to access services and infrastructure over the cloud through internet and also permits secure sharing of resources. The use of computing resources as a service with the help of internet is called Cloud Computing. It has started to gain vision in corporate data centers. In recent years, cloud computing is including grid computing because utilization of virtualization at data center could increase. With increase in the number of user and data, there is a need of data confidentiality as well as authenticity of users connected to the cloud so as to protect them from each other as well as from the hackers too.