4,425 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
Divya Iratchakar’s Pillai Thamizh
No full textJust as the Pallavar period is said to be the period of devotional literature and the medieval Chola period is said to be the period of preservation, so the period of Nayak who ruled Tamil Nadu from 1350 AD can be said to be the period of minor literature. Pallu, Ula, Thootu, Kalambagam, Pillaitamil etc. are minor literary works that are written to entertain the rich people and kings. There are 96 types of minor literary work called Prabandhams. In the book Sathuragarathi written by Veeramamunivar, mentions 96 types of Prabandhams. Pillai Thamizh ia also known as Pilliakavi, Pillaipaatu, and Seithamil. Some of these Pillai Thamizh books have been composed with changes in the structural and cultural elements. Thus, the article examines the overall changes that took place in Divya Iratchakar’s Pillai Thamizh
The review of studies of Divya cave: the longest cave in Perm region (Russia)
No full textAbstract The work presented is a review of modern research conducted in Divya Cave—the longest cave in Perm Region, the first mention of which dates back to the 70’s of the eighteenth century. The cave provides the richest material for geologists, karstologists and speleologists, since it is a relic of an ancient aquifer, in which almost all types of secondary calcite formations found in caves are collected. The remote location of the cave from roads and settlements has never been an obstacle for explorers. The first plan of Divya cave was drawn up in 1949. Subsequently, a lot of speleologists kept exploring the cave, but not all passages were marked on the latest maps. Hydrogeological and hydrochemical research was done for the first time in 1948, 1956, 1962 and 1967. Numerous springs between the village of Divya and Divya cave were surveyed, water temperature and flow rates were measured and the hydrochemical indicators of water in the cave lakes were studied. Findings of cryogenic calcite in 1968 prompted further research related to the study of cave deposits, using isotopic analysis methods, taking into account their dating, to determine the migration of permafrost boundaries. From 2016 to 2020 the authors of this article conducted a number of studies in Divya cave itself and in the surrounding area, namely, they carried out instrumental and semi-instrumental topographic surveys of the cave and the surface, followed by the creation of a combined plan, and also determined the absolute marks of the earth’s surface, the entrance, the roof and the base of the cave and the new data on the length of the cave were obtained. For the first time, isotopic studies of atmospheric precipitation, surface channel runoff (the Kolva river) and groundwater emerging to the surface near Divya cave were carried out, and their relationship was determined. Data on the chemical composition of waters were supplemented. Samples of speleothems, including cryogenic calcite, were selected, their isotopic composition was studied and dating was carried out, which made it possible to obtain completely new information about interglacial periods. The modern data obtained allowed us to supplement previously known information about Divya cave
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
Brachinus (Brachynolomus) devagiriensis Akhil & Divya & Sabu 2020, sp. nov.
No full textBrachinus (Brachynolomus) devagiriensis sp. nov. Fig. 4 Type material. Holotype (male) labelled: “ Male; India: Kerala: Pattambi (KAU Campus, 10°48’42.9”N 76°11’25.7”E), ‘Light’, 14.XI.2016, coll. and det. S. V. Akhil ”, deposited in ZSIC; Paratypes labelled “ Female, India: Kerala: Pattambi (KAU Campus, 10°48’42.9”N 76°11’25.7”E), ‘ Light’, 14.XI.2016, coll. and det. S. V. Akhil ”, deposited in ZSIC; labelled: “ Male; India: Kerala: Peruvannamoozhi (IISR station, 11°36’26.0”N 75°49’24.9”E), 02.ii.2017, coll. V. A. Jithmon, det. S. V. Akhil ” deposited in ZSIC. Description: Length (TLA) 5.8–6.1 mm. Head, pronotum, scutellum and region around scutellum dark reddish brown; first two segments of antennae, palpi and legs pale reddish yellow (apical segments of palpi darker); femur, apex of tibiae and tarsi dark brown; antennal segments 3–4 dark reddish yellow, rest of the antennal segments reddish brown; lateral margin of pronotum and elytra black; eyes pitch black; genae, gula and prosternum dark reddish yellow; mesosternum, metasternum and abdominal ventrites brownish yellow. Head broad, wider than long, sparsely pubescent, smooth, with very faint wrinkles; frons with frontal foveae setose, shallow, densely punctated (mid region finely punctated, with short setae), smooth; vertex very faintly wrinkled, glabrous; neck rough, densely punctated, pubescent; labrum rectangular, transverse, anterior margin straight, apical angles almost at right angle, having six setae at anterior margin with two long setae at the corners, four (2 long, 2 intermediate) setae in the middle, rest glabrous. Clypeus sub-rectangular, anterior angles obtuse, with one long setae on each lateral edge, minute setae in the anterior margin; fronto-clypeal suture well impressed, deep, intended. Mentum transverse with two triangular, large lateral lobes which are toothed laterally, a single long seta present at the apex of lateral tooth, rest of the mentum glabrous; lateral lobes pointed apically; mentum without median tooth. Submentum very narrow, glabrous. Antennae long, slender, reaching beyond the middle of elytra; segment 1 longest, segment 2 elongate oval, all the segments densely pubescent with a ring of long setae in the apex of the segments. Palpi with segment 2 longest, wide, rectangular; the entire segment pubescent, penultimate segment long, slender, in the shape of an inverted cone, apical segment conical, tapering towards apex. Mandibles stout, scrobe plurisetose, tip pointed, arcuate, not crossing. Eyes highly protruding, prominent. Genae evidently wrinkled except at the base, a few setae present below eyes, rest of the genae glabrous. Gula large, widening towards pronotum, gular suture divergent, well impressed. Pronotum shiny, as long as wide, disc punctated, sparsely pubescent, smooth without wrinkles; disc apically sinuate without forward projection on lateral region of apical margin, disc straight at base, hind angles rounded, blunt, right angled; disc broad, laterally with anterior two-thirds convex and posterior third narrowed, with parallel sides; surface of disc convex; median groove deep, reaching both apical and basal margin; lateral bead narrow, widest near apical region. Elytra subparallel, slightly narrowed towards base, shiny, densely punctated and densely pubescent with short yellow setae; humerus prominent, corners rounded; apex obliquely truncate without any re-entrant angle; scutellum long, narrow, pointed, glabrous; striations well marked, deep, carinate; intervals broad, convex/ carinate; suture not completely closed apically; setae present on striations as well as on intervals. Hind wings well developed. Legs strong, densely pubescent; protibial comb rounded with spur at the basal end of the comb. Two tibial spurs pointing inwards. Tarsi with article 1 longest, article 4 shortest. Ventrally, pronotum smooth, pubescent, punctate. Prosternal process prominent, pubescent, extending beyond procoxae, apex pointing downwards. Ventral region densely punctate, pubescent with golden brown setae; hind coxae contiguous; abdomen rounded till apex, apex pointed; mesepisternum prominent, long and broad. Sexual dimorphism. Symmetrically and diagonally arranged adhesive pads on male pro-tarsomeres 1, 2 and 3. Male genitalia. Median lobe (in lateral view) straight in the basal half, sharply curving downwards towards the apex, with apex blunt, pointing straight rather than downwards. Measurements. Holotype (male), TLA = 6.08 mm, TLB = 5.74 mm, PL = 1.10 mm, PW = 1.16 mm, EL = 3.60 mm, EW = 2.39 mm; Paratype (female), TLA = 5.81 mm, TLB = 5.74 mm, PL = 1.10 mm, PW = 1.18 mm, EL = 3.52 mm, EW = 2.48 mm. Distribution. INDIA: Kerala: Pattambi, Peruvannamoozhi. Collecting circumstances. Light-attracted, collected using low-intensity UV light trap. Etymology. Named after the host institution of the authors. Remarks. This new species is similar to B. dryas but differs in having rounded, obliquely truncate elytral apex without re-entrant angle, deeply impressed elytral striations, hind angle of pronotum right angled, blunt, not projecting laterally and strongly protruding eyes.Published as part of Akhil, S. V., Divya, M. & Sabu, K. Thomas, 2020, Bombardier beetles of genus Brachinus Weber, 1801 (Carabidae: Brachininae Brachinini) from India, pp. 576-600 in Zootaxa 4816 (4) on pages 595-598, DOI: 10.11646/zootaxa.4816.4.7, http://zenodo.org/record/395468
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
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
Personal, professional and interprofessional ethics in policing in a child protection context
No full text- …
