1,721,240 research outputs found
Mal class: a deep learning approach for automatic classification of malware images
No full textThese days, malware evolves and multiplies exponentially through structural changes and camouflage using methods like encryption, obfuscation, polymorphism, and metamorphism. As deep learning has advanced, techniques like convolutional neural networks (CNN) have become powerful instruments for identifying complex patterns in this malicious software. The present study leverages CNN's capacity to detect patterns in malware datasets generated from RGB or images in greyscale and to determine the global structure of code that has been converted into an image. Convolutional Neural Networks (CNN) are a method of deep learning that has recently demonstrated better performance than conventional learning algorithms, particularly in applications like image categorization. Motivated by this result, a CNN-based malware sample categorisation architecture is proposed. After converting binaries of malware to monochrome images, we train a CNN to classify the images.</p
Brain MR images involving examining resemblances study of denoising algorithms
No full textMagnetic Resonance Imaging (MRI) denoising acting technique introduced and these are very high qualities giving the power to produce an intended effect in the direction of medical image diagnosis and cause of some phenomenon. The intentionally contemptuous behavior and its change for the better progress in development in acquiring possession speed and signal to noise ratio of magnetic resonance imaging practical application of science to medical image diagnosis, MR images are still behaving in an artificial way to make an impression by noise and artifacts. MR images are unrestrained by convention by rician noise, which occurs during the acquisition sustained phenomenon. This noise reduces the level of the caliber of post-processing diagnostics employ to MR data, for instance, segmentation, morphometry and so forth. Post-processing filtering proficiency has been over a great extent used in MRI denoising for the reason that they did not greater in an amount the acquisition time. At this time, this research often with explanation and alternatives an appraisal of different post-processing MRI brain denoising procedure such as the spatial domain, transform domain and machine learning domain. No single MRI denoising method has demonstrated to get the better of to all others regarding noise reduction, boundary preservation, robustness, user interaction, computation complexity, and cost. The objective of this look back upon paper is to get a bird’s-eye view of MRI denoising algorithms which activity of contributing to the fulfillment need of researchers to formulate a higher-ranking brain MRI denoising proficiency.</p
Enhanced deep-joint segmentation with deep learning networks of glioma tumor for multi-grade classification using MR images
No full textThe crucial imaging modality employed in medicinal diagnostic tools to detect the tumors is magnetic resonance image (MRI). Based on the glioma anatomical structures, MRI poses the capability to provide detailed information. Anyhow, in the MRI classification the foremost problem is the semantic gap between optical information at the low level, which is attained from the MRI machine, whereas information at the high level is alleged by a clinician. In this research, Tunicate-Exponential weighted moving average (TEWMA)-based deep convolutional neural Network (TEWMA-deep CNN) is devised for multi-grade classification. In this method, the preprocessing is employed to eradicate the artifacts present in the image. Moreover, deep-joint segmentation is modified with the weighted Euclidean and Levenshtein distance measures, which are effectively used for segmenting the tumor regions. Then, the classification is done from the image-segmented areas by deep CNN to determine gliomas, meningioma, pituitary, and others, which is tuned by developed TEWMA. The experimentation of the devised approach is performed by three datasets, such as BRATS 2015, figshare, and BRATS 2020 dataset. The developed TEWMA is designed by incorporating Tunicate swarm algorithm (TSA) and exponentially weighted moving average (EWMA) algorithm, with the highest specificity of 99%, highest accuracy of 98.76%, highest sensitivity of 98.88%, maximal precision of 94.76%, maximal F1-measure of 98.46%, and minimal time of 7.24 s using dataset-1 for classification. Also, the proposed method attains average specificity, accuracy, sensitivity, precision, F-measure, and time of 91.09, 93.79, 95.46, 92.33, 94.30%, and 6.23 s, respectively, using dataset-1
Medical MR image synthesis using DCGAN
No full textGenerative Adversarial Networks (GANs) have been extensively gained considerable attention since 2014. Irrefutably saying, their most remarkable success has been made in domains such as computer vision and medical image processing. Despite the noteworthy success attained to date, applying GANs to real world problems still posses significant challenges, one among which is diversity of image generation and detection of fake images from real ones. Focusing on the extend to which various GAN models have made headway against these challenges, this study provides an overview of DCGAN architecture and its application as a synthetic data generator and act an a binary classifier, which detects real or fake images using brain tumorous Magnetic Resonance Imaging (MRI) datase
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Automated models for the classification of magnetic resonance brain tumour images
No full textBrain tumours are the second largest cause of cancer death in children under 15 and young adults until age 34. Also, among people over 65, these tumours are the second-fastest-growing cause of cancer death. Computer-assisted tumour diagnosis is challenging, and efforts to increase the accuracy of tumour classification and generalisation are continually being made despite the plethora of studies conducted. This study of automated multi-class brain tumour classification utilising Magnetic Resonance Images aims to design and develop three automatic brain tumour classification approaches to categorise the brain tumours as glioma, meningioma, and pituitary tumours, which assist clinicians in making brain tumour diagnoses and developing further treatment plans to save patient's life. This research proposes a transfer learning approach using ResNet 50, hand-crafted features with machine learning classifiers, and a hybrid firefly-optimised multi-class classifier for tumour classification. The hybrid methodology yields the highest classification accuracy of 99% using the Figshare dataset. Furthermore, using the Figshare dataset, the hybrid technique yields the highest sensitivity (recall) of 99% for meningioma and pituitary tumours, the highest precision of 100% for pituitary tumours, and the highest F1-measure of 99% for pituitary tumour
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
