ISI Digital Commons (Indian Statistical Institute )
Not a member yet
7571 research outputs found
Sort by
Deep Ensembling with Multimodal Image Fusion for Efficient Classification of Lung Cancer
No full textThis study focuses on the classification of cancerous and healthy slices from multimodal lung images. The data used in the research comprises Computed Tomography (CT) and Positron Emission Tomography (PET) images. The proposed strategy achieves the fusion of PET and CT images by utilizing Principal Component Analysis (PCA) and an Autoencoder. Subsequently, a new ensemble-based classifier developed, Deep Ensembled Multimodal Fusion (DEMF), employing majority voting to classify the sample images under examination. Gradient-weighted Class Activation Mapping (Grad-CAM) employed to visualize the classification accuracy of cancer-Affected images. Given the limited sample size, a random image augmentation strategy employed during the training phase. The DEMF network helps mitigate the challenges of scarce data in computer-Aided medical image analysis. The proposed network compared with state-of-The-Art networks across three publicly available datasets. The network outperforms others based on the metrics-Accuracy, F1Score, Precision, and Recall. The investigation results highlight the effectiveness of the proposed network
Demystifying Galaxy Classification: An Elegant and Powerful Hybrid Approach
No full textThe process of identifying a galaxy\u27s structure from telescopic images and then classifying it into its appropriate group has long been a topic of extensive research. The importance of this classification task stems from the fact that the structure as well as the physical properties such as color and texture hold important clues to the contents of the galaxy, its age, and the course of its evolution over time. In fact, the nature of its evolution process provides insights towards prediction of its future state and the time required to reach it. Consequently, such classification studies of galaxies shed light on the understanding of the large-scale structure of the universe as well as its course of evolution. This article proposes a novel, simple yet powerful approach for galaxy classification. One of the major contributions of the proposed approach includes a well-designed effective pre-processing stage to extract only the galaxy portion from the noisy telescopic images, which is itself an important but challenging task. This is especially necessary since noise and artifacts in telescopic images adversely affect the training of the classification network and interfere with the learning of the useful galaxy features. Another significant contribution is the introduction of CoAtNet0-R deep architecture, which is an augmentation of the existing CoAtNet-o network by introducing Relative Self Attention for boosting its performance. The incorporation of two additional structural features for fine-tuning the classifier performance is yet another feather in the cap. The recently annotated dataset Galaxy10 DECals is used for experimentation. The performance of the proposed algorithm for classification into 4 and 10 classes of galaxy structures establishes, in no uncertain terms, the power of the proposed strategy. Hence, this work effectively gives rise to an elegant, hybrid scheme that achieves classification of galaxies at a level hitherto unattained by state-of-the-art networks
Indifferentiability of 3-Round Confusion-Diffusion Networks
No full textSubstitution-Permutation Networks (SPNs) are a popular and powerful technique for designing block ciphers. Confusion-Diffusion Networks (CDNs), as formalised by Dodis et al. at Eurocrypt’16, treat unkeyed SPNs as a means of extending the domain of public permutations. Dodis et al. showed that 5-round CDNs are indifferentiable from an ideal permutation, and subsequent works by Da et al. at Indocrypt’21 and Nandi et al. at C2SI’23 have established that 2-round CDNs cannot achieve the weaker notion of sequential indifferentiability even with non-linear diffusion layers. In this paper we show for the first time that 3-round CDNs with linear diffusion layers can achieve indifferentiability from an ideal permutation
Quantum Quest: Resource Requirement of RC4 Cryptanalysis under Grover\u27s Lens
No full textThe RC4 cipher is a widely used software stream cipher which has long stood as a cornerstone in cryptographic applications due to its design simplicity, speed and efficiency. In this paper, we present an approach to decrypt RC4-encrypted data by leveraging Grover\u27s quantum search algorithm. To the best of our knowledge, this is the first documented attempt to employ Grover\u27s algorithm in breaking RC4 encryption. We enumerate the quantum resources required to perform exhaustive key search attack on RC4. Our approach demonstrates the potential of quantum computing to revolutionize cryptanalysis
Which Region Proposal to Choose? A Case Study for Automatic Identification of Retail Products
No full textIdentifying products visible in an image of a rack of a supermarket is a challenging and commercially relevant machine vision problem. For identification, the region proposal algorithm generates a number of (mostly overlapped) region proposals around each product on the rack. Each region proposal is then assigned a product class with a certain classification score. Finally, the products are detected using non-maximal suppression (NMS) discovering winners among the region proposals. Greedy-NMS takes classification scores of the proposals as a key factor and thereby often eliminates (geometrically) better-fitted proposals. Graph-based NMS (G-NMS) provides a better alternative performance-wise but an inferior solution timecomplexity-wise (O(N3)) compared to O(N2) time-complexity of greedy-NMS. This paper introduces a adjusted classification score for use in the novel rectified non-maximal suppression (RNMS) setup that runs in O(N2). The efficacy of the proposed adjusted classification score is theoretically characterized in better discriminating overlapped region proposals. Our experiments establish that the performance of the proposed R-NMS is never inferior to G-NMS, and outperforms greedy-NMS while testing on several datasets
Chi-square Method
No full textDifferent tools from probability and statistics are now heavily used in cryptography. Among them, the χ2-method is a recent addition in cryptographic literature. The idea was introduced to cryptography in Dai et al., who showed pseudorandom function security (PRF-security) of two constructions, namely the sum of random permutations and encrypted Davies-Meyer. This chapter discusses the χ2-method and applies this technique to the PRF-security of the truncated random permutation construction. It sketches the proof of PRF-security of the sum of two random permutations and discusses some other applications. A PRF is a very popular security notion in cryptography. The chapter discusses hypergeometric distribution. It briefly outlines other results obtained using the χ2-method. One of the important applications of the χ2-method is in the analysis of PRF-security of the eXclusive OR construction or its variants
How the health-benefit components of tea vary depending on the cultivar and season: The example of Darjeeling tea
No full textTea, in brief, infused leaves of Camellia sinensis can be ascribed as the most popular, cheapest, and utility drink after water. Tea leaves contain a plethora of naturally occurring phytochemicals, including polyphenols, catechins, and their derivatives, demonstrated to have commendable antioxidant properties. Antioxidants are proving to be essential as they neutralize free radicals (voluntarily evolved during different metabolic functions). Considering this, demand for quality tea production is a frontline issue for health-conscious people. Presently, available Darjeeling tea cultivars are mostly developed through the selection of elite genotypes from wild or controlled cross-pollinated cultivars. Tasks for exploring distinguished cultivars with favorable agronomic traits are still viable and a priority in tea research. Owing to the same, 22 tea cultivars were studied during three different plucking seasons to determine how much compositional variation exists in cultivars in terms of “tea health benefits” as well as the variations across plucking seasons
Intrinsic Dynamics of State, Market, and Social Movements
No full textAfter reading this chapter, you will be able to: Know about the inclusive nature of social movements; Understand that a social movement is a flow and not just a reactive force against the state oppression and hegemonic power of the market; Explore the intrinsic and complex patterns of dynamics among state, market, and social movements from a critical sociological perspective; and Reflect on the way the triad has degenerated over space and time
Replacement models with fixed and random replacement times
No full textIn this chapter, replacement models under which replacements take place at fixed time t or random time T or upon failure have been discussed. A review of results by Kattumannil and Anisha (2019) for replacements occurring at fixed time, has been included. For random replacement time, the properties of mean time to failure (MTTF) of the proposed model have been included. Lifetimes of two replacement models with different random replacement times have been compared using few stochastic orderings. A nonparametric test based on U-statistics has been proposed for testing constancy of MTTF against new better than used in expectation alternative. The finite sample performance of the proposed test is evaluated through Monte Carlo simulation study. Finally, proposed test procedure is illustrated using lifetime data of air-conditioning equipment
Wasting Among Under-Five Children from 1990 to 2020: A Systematic Review and Meta-Analysis
No full textWasting is crucial for decision-makers to have current and comprehensive data on malnutrition levels to prioritize interventions effectively. It is a widespread global health issue, particularly severe in developing countries like Bangladesh. The prevalence of wasting varies worldwide due to factors such as climate, ethnicity, and time trends. This study aimed to assess the prevalence and risk factors of wasting among young children through a systematic review and meta-analysis. In total, 12 non-repetitive articles were identified for the study from databases like PubMed, Endnote, and others. Q, I2, and Forest plots were employed to analyze data collected from selected published papers between 1990 and 2020, focusing on wasting of under-five children. In published articles, the prevalence of wasting among under-five children has been reported between 5.3% and 30%. Pooled hazard ratios for wasted children ranged from 6.97 to 14.37, it was indicating a significant risk. The research highlighted fetal growth restriction as a major risk factor of wasting among under-five children