Knowledge Connect @ SASTRA
Not a member yet
201 research outputs found
Sort by
Encountering and Mitigating Selfish Mining in Bitcoin Mining Pools
No full textBlockchain, an innovative decentralized distributed, disrupting programming paradigm embodies key principles such as decentralization, data provenance, immutability, and transparency. At its core blockchain begins with the genesis block and progresses with each subsequent block containing the hash of the previous block, Merkle root, timestamp, a coin base transaction address, and a nonce. Miners compete to discover a target hash value (hash value of the previous block and nonce) for the current block, that is less than or equal to the difficulty value set by the system, a process known as mining.
This work encounters selfish mining attacks in bitcoin mining pools, launches selfish mining attacks, mitigates the attack and devises the optional stopping time for a miner to quit mining. The classification of the crypto addresses belonging to a mining pool or individual miners, the miners within the pool being clustered based on their hash rate to infer their computational power is done as the preliminary analysis.
There are two primary phases one is classification of crypto addresses with notable accuracy of 99.47% accuracy with 1,53,011 observations which surpasses Kaggle’s 98.93% accuracy with 22,000 observations. Clustering of the crypto addresses to group miners with similar computational power within mining pools is the second phase.
This clustering yielded a silhouette coefficient value of 0.5 for all four clusters. The launching of the selfish mining attack, predicts relative gain, from the NIST dataset with the root mean square for the deep learning model as 0.0565. In addition, the prediction of miners\u27 block rewards, yielding a root mean square error of 1.336 and an R-squared value of 0.0059 is devised.
The upper confidence bound algorithm was tailored to mitigate the selfish mining attack with generation and plot of upper confidence bound values, regret graph, and revenue graph plotted and compared with previous results from the literature. The lemmas concerning the potential ruin of honest miners are then investigated and the concept of optional stopping time, to cease mining to prevent complete ruin, is thoroughly examined and elucidated
Hindcasting the Occurrence Time of Major Earthquakes using Machine Learning and Time Series Analysis
No full textAn earthquake is an intense shaking of the ground that typically occurs when tectonic plates move beneath the surface of the Earth. Scientists analyze historical seismic records and geophysical and atmospheric signs to build models estimating the probability of major earthquakes by detecting patterns and anomalies in data such as ground deformation and seismic waves. This study would help in predicting earthquakes to minimize risks of people and buildings.
The present study investigates the devastating earthquakes along the Chilean subduction zone in South America, linking non-seismic data to machine learning predictions of Outgoing Longwave Radiation (OLR) and Relative Humidity (RH) anomalies. Tectonic activity is highly variable in space, therefore the study region must be defined. The first stage which is getting the clusters done by the proposed method Local Maxima-based Spatio Cluster Analysis Network (LMSCAN). In this clustering method, the main quake are taken into consideration to classify the data into the seismology parameters of interest (magnitude and latitude) and the grouping of microshocks. To assess the efficacy of the clustering process, the effectiveness of their proposed technique will be measured against of conventional clustering algorithms such as K-means, Agglomerative Hierarchical Clustering, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN).
By providing detection of Outgoing Longwave Radiation (OLR) as non-seismic precursor, the Singular Spectrum Analysis - Percentile-median Absolute Deviation Method (SSA-PADM) has been proposed, proving a new technique, for predicting the anomaly activity up to 6 months prior to the occurrence of major earthquakes.
The existing techniques which include Isolation Forest, 2 Sigma, Median Absolute Deviation and Percentile algorithms are compared for performance against this technique on detecting anomalies preceding a major earthquake. Moreover, the correlation of atmospheric parameters, OLR and RH are also implicated as predictors of the estimated seismic events through the Proposed Atmospheric and Radiative Anomaly Detection (ARAD) approach. The analysis explores the relationship between the drop of RH flux index value related to the raise of the flux index of OLR near the epicenter as a possible precursor of major earthquakes, with advance times from 3 to 40 days.
Accuracy improvements are found compared to wellknown methods like One-Class SVM (Support Vector Machine), Elliptic Envelope and Isolation Forest. With OLR and RH considered reliable predictors, the atmospheric variables are being forecasted with a hybrid machine learning model called Multi-Layer Perceptron with Expanded Window Cross-Validation (MLP-EWCV). The established methods, including Extreme Gradient Boosting (XGBoost), Random Forest Regressor, and Support Vector Regression (SVR), were used for comparison in order to evaluate the improvement in hindcasting accuracy and efficiency offered by the MLP-EWCV model.
The study of anomalous behaviour of OLR and RH may help to detect anomalies before earthquakes, thereby possibly functioning as an early warning for disaster management systems. The current research study attempts to understand Chile (South America) possible micro shocks with respect to tectonic model as a whole because it falls in the inter plate region where usually micro shocks are observed just before the major earthquakes
Experimental Characterisation of Laser Cladding of CrNiW and CrNiFeAlZr Powders on H13 Tool Steel and Optimisation of Process Parameters
No full textIn this work, laser cladding on H13 steel substrate with two different powder compositions CrNiW and CrNiFeAlZr has been carried out. The laser power, powder feed rate, and scanning speed were varied and the clad dimensions, aspect ratio, and dilution percentage were measured. The microhardness found in the CrNiW clad is 834 ± 20 HV0.5, which is higher than that of the CrNiFeAlZr clad (780 ± 20 HV0.5) as well as the substrate (548 ± 20 HV0.5).
The X-ray Diffraction (XRD) patterns identified the common phase creation of Ni3C and Fe3C for CrNiFeAlZr and CrNiW coatings, while the oxide formation was only noticed in CrNiFeAlZr coatings and the addition of carbon content in the CrNiW clad layer forms WC, Cr23C6, Ni3C, and Fe3C. A response surface methodology with a Box–Behnken design is used in the optimisation process.
The optimal deposition conditions were acquired for corrosion, wear, and residual stress study. Compared to the H13 steel substrate, the cladded samples exhibited significantly lower coefficient of friction and superior wear resistance. Furthermore, increased corrosion resistance was achieved by both clad specimens in a 3.5% NaCl solution.
The clad specimens had a higher Ecorr value than the substrate. In contrast, the icorr value of the clad was lower than base metal. The compressive residual stress that was produced on the surface of clad specimens was caused by the difference in the substrate and surface cooling rates during the cladding process
AI Based Early Detection Of Hormonal Imbalance And Poly-Cystic Ovary Syndrome In Young Women
No full textA hormonal disorder, Poly-Cystic Ovary Syndrome (PCOS) usually affects women during the reproductive age. It is characterised by imbalances in hormones, particularly a rise in the female body\u27s androgen level (male hormone) and enlarged ovaries with small cysts. PCOS can cause ovarian cysts, weight gain, acne, excessive hair growth, insulin resistance, and irregular menstrual cycles along with other health problems. While the exact origin of PCOS is uncertain and its symptoms are unclear, diagnosing PCOS in real-world conditions is a difficult task. Therefore, prompt and precise PCOS diagnosis is essential for efficient treatment and for averting long-term issues.
Clinicians typically use clinical, hormonal and ultrasound ovary images to manually analyse PCOS, although this method is labor-intensive and unreliable. Thus, the development of effective and automated PCOS classification models becomes essential for optimizing time and medical resources. This work uses the predictive power of Machine Learning (ML) and Deep Learning (DL) approaches to address the need for enhanced PCOS categorization. The goal is to investigate, create and evaluate ML and DL models that can accurately categorize PCOS from clinical, hormonal and ultrasound ovarian images, ultimately improving diagnostic accuracy and enabling timely intervention.
In machine learning, protecting the privacy of sensitive information has always been a top concern, particularly in the healthcare domain. Data may be exposed during various stages of model implementation including data collection, training and even after the release of a trained model. Thus, it is crucial to prevent data leakage and ensure patient privacy concerning Personally Identifiable Information (PII), ML model updates and Personal Health Information (PHI). To address these issues, a Fog-based Federated Learning approach is adopted, enabling collaborative learning where only gradients or updates from locally trained models are shared with the global server.
This research initially proposes a hybrid machine learning model using clinical and hormonal datasets for PCOS classification. Ensemble Feature Selection (FS) methods are used to identify the most significant indicators by selecting relevant features from a large feature set. A common issue in real-world applications is the instability of FS algorithms when applied repeatedly on the same or slightly modified datasets. Therefore, assessing FS robustness is crucial. In this study, Jensen–Shannon Divergence (JSD), an information-theoretic measure, is used along with ensemble FS to manage diverse outputs such as complete rankings, top-k lists and partial rankings. The resulting high-stability features are then used for training, and the proposed hybrid model achieved a remarkable accuracy of 97.81% using the AdaBoost classifier.
Although hormonal data contributes to PCOS diagnosis, it alone is insufficient. Ultrasound ovary images provide crucial visual information such as follicle size, count, shape and texture, essential for accurate diagnosis. A CNN-based Automated High-Precision PCOS Detection model is developed using ESRGAN for image resolution enhancement and SAM for cyst segmentation. Using VGG-19 with enhanced and segmented images, the model achieved an impressive 99.31% accuracy. Furthermore, a Differential Privacy (DP)-enabled Federated Learning framework is implemented for decentralized model training to ensure privacy and prevent data leakage. To balance the trade-off between privacy budget and utility, DP is applied only to the top-k participants, enabling the global model to achieve 87.29% accuracy with 0.3 top participants. The proposed model is also validated against two major attacks: gradient-based data reconstruction and model inversion
Design and Realization of Concurrent Cryptosystem for Medical Image Privacy on Reconfigurable Hardware
No full textThe protection of medical image privacy plays a crucial role in maintaining confidentiality for the secure storage and transmission of patient’s sensitive healthcare data. Medical images are the widely used data type in the e-healthcare sector. Traditional cryptographic algorithms have limitations when applied to large-scale medical image datasets due to their high computational requirements. The primary goal of this research work is to design and implement indigenous algorithms to provide confidentiality for grayscale and color DICOM (Digital Imaging and Communications in Medicine) images through an encryption process. The research leverages the benefits of reconfigurable hardware, namely the Field-Programmable Gate Arrays (FPGAs), to accelerate cryptographic operations through concurrent processing to maximize the hardware throughput.
Confusion and diffusion are the major operations for any cryptographic algorithm. This work proposes an edge detection process using the Sobel mask algorithm as a novel attack mechanism to cryptanalyse the encrypted images from confusionless cryptography schemes. A grayscale lightweight image encryption scheme was designed and implemented on FPGA using a robust diffusion unit utilising the random keys generated by the Lorentz attractor. This work aimed to arrive at an optimal number to achieve block-level concurrency on FPGA by dividing the 256×256 DICOM input image into distinct blocks.
This technique achieved a throughput of 200 Mbps per concurrent block, consuming only 3% of Logic Elements (LEs) with a minimal power dissipation of 138.85 mW under the optimal block count of 4. Another scheme for the encryption of color DICOM images with concurrency among the encryption of Red (R), Green (G), and Blue (B) planes was achieved with substitution boxes constructed using the Zhongtong chaotic system. The RGB cryptosystem offered a significantly expanded keyspace of 2912, a reduced resource utilization of 2212 LEs, and a minimal power consumption of 131.40 mW.
An additional layer of security for exchanging encrypted medical images between Xilinx PYNQ-Z1 SoC boards with incorporated integrity checks through encrypted hash values obtained through a whirlpool hashing scheme has been proposed. To ease the hash generation, hash encryption/decryption, and transmission/reception processes on the sending/receiving device, a user-friendly graphical user interface (GUI) was designed under the jupyterlab platform.
The proposed grayscale and color encryption schemes were developed using Verilog HDL code and implemented on the Intel Cyclone IV FPGA, utilizing less than 3% of available resources, making it a lightweight solution with significantly lower resource utilization compared to similar hardware-based encryption schemes reported in the literature.
The FPGA operated at a frequency of 50 MHz in the Quartus-II Integrated Development Environment (IDE). The developed concurrent cryptosystems were evaluated with a comprehensive set of performance metrics, including throughput, resource utilization, and power dissipation on FPGA. The security strength of the proposed medical image security schemes was analysed through various statistical metrics, including the NIST test suite.
Further, attack mechanisms such as Chosen Plain Text (CPT) and the proposed edge detection attacks assured the quality of encrypted images. This research has significant implications for protecting medical image privacy and the secure exchange of medical images with integrity verification, contributing to the advancement of a secure healthcare system
Bioprospecting of Wheat Straw Pyrolysis Aqueous Phase to Combat Multi-Drug Resistant Pathogens
No full textHospital-acquired infections (HAIs) significantly contribute to the emergence and spread of antimicrobial resistance (AMR), primarily through the contamination of high-touch surfaces. Current disinfectants have drawbacks like high environmental persistence, ecotoxicity, and resistance development, prompting the need for environmentally friendly alternatives.
One potential approach is pyrolysis, during which the biomass components are broken down into solid, liquid, and pyro-gas. The aqueous phase of the liquid fraction is usually discarded as waste, but it contains a variety of organic compounds that have the potential for antibacterial and antifungal activity. The present study assessed the anti-infective and anti-biofilm properties of wheat straw pyrolysis aqueous phase (WS AQ) under nine conditions.
The WS AQ showed antimicrobial activity against drug-resistant nosocomial pathogens like Acinetobacter baumannii, Methicillin-resistant Staphylococcus aureus (MRSA), and Candida auris, and showed 62%-74% matured biofilm disruption ability under mono and polymicrobial conditions. It also downregulated virulence genes involved in quorum sensing and biofilm formation. The study evaluated the storage stability of WS AQ over 60 days at different storage conditions (25 °C, 4°C, and -20°C), revealing no significant changes in functional groups or antimicrobial activity, indicating its long-term stability.
Further, we xxiii evaluated three major compounds, furfuryl alcohol, 2-methyl-2-cyclopentenone, and guaiacol, as inhibitors from the aqueous phase. The compounds showed an additive effect and biofilm eradication of 52% on preformed biofilms. They also showed a reduction in quorum sensing and biofilm adhesion gene expressions. A disinfectant formulation containing EDTA, ethanol, SLS, and AQ was developed and tested for efficacy.
The phenol coefficient of two (for mixed species) was observed, implying that the disinfectant formulation is more potent and efficient. A custom-made Centre for Disease Control and Prevention (CDC) biofilm reactor was fabricated to mimic clinical biofilms. The biofilms were allowed to form on stainless steel 316 coupons, and the formulated disinfectant efficacy was evaluated. The toxicity of the formulation was further assessed using the filter paper contact test using earthworms as a biological model.
Based on our study findings, WS AQ showed antimicrobial and antibiofilm properties, highlighting its stability and efficacy against drug-resistant nosocomial pathogens, suggesting a promising, environmentally sustainable alternative for infection control and biofilm management in healthcare settings
ITIHAS Vol. 25 Issue No. 1
No full textNEWSLETTER FROM SASTRA DEEMED UNIVERSITYhttps://knowledgeconnect.sastra.edu/itihas/1000/thumbnail.jp
Structural Response of RC Columns Strengthened using BFRP based BFEGC system – Under Fire and Cooling Regime
Get PDFRetrofitting fire-damaged columns is essential for restoring structural integrity. This study evaluates the effectiveness of BFRP based Basalt fiber Engineered Geopolymer Composites (BFEGC). The performance of basalt fiber wrapping and BFEGC was tested for fire protection system and retrofitted system. An optimal BFEGC mix achieved a compressive strength of 55.34 MPa, with split tensile strength, flexural strength, and strain hardening behaviour of 15.5 MPa, 5.13 MPa, and 6% respectively.
Microstructural analysis was accessed for the optimum mix. Durability tests include water absorption, sorptivity, and RCPT which confirmed compliance with standards. Thermo gravimetry analysis (TGA) shows the minimal weight loss of 2-5%. BFEGC also demonstrated significant environmental benefits, reducing carbon emissions and embodied energy compared to conventional cement binders. Machine Learning (ML) models were utilized to estimate the compressive strength of concrete, proving more reliable than conventional methods.
Cylindrical and column specimens of normal and high-grade concrete were tested under axial loading after exposure to 300°C (30 minutes), 600°C (20 minutes), and 900°C (15 minutes), followed by gradual (GC) or rapid cooling (RC). Specimens were left unwrapped (GC-NW, RC-NW), wrapped as a fire protection system (GC-WBF, RC-WBF), and wrapped as a retrofitted system (GC-WAF, RC-WAF) before axial loading. BFEGC wrapping significantly improved the mechanical performance of fire-damaged columns, particularly in NS_600RC and HS_300GC specimens.
Enhancements were observed in ultimate load, confinement coefficient, energy absorption, and ductility index. Microstructural analysis confirmed key hydration products\u27 formation at elevated temperatures. A thermo-structural analysis using ANSYS Workbench 2023 showed that BFEGC effectively functioned as an insulator, regardless of the cooling pattern. Implementing a repair technique before wrapping would further improve column performance under high intensity of temperature. BFEGC shows significant reduction in carbon emissions and embodied energy, compared to conventional cement-based binders for fiber-reinforced polymer systems. These findings underscore the importance of a sustainable BFRP-BFEGC (fire protection, retrofitted system) for RC columns under elevated temperature
Artificial Intelligence-Based Adaptive Data-Driven Techniques for Disruption Prediction in Tokamak
No full textTokamaks are nuclear fusion reactors designed to generate sustainable energy by confining plasma, yet plasma disruptions remain a major obstacle as they can damage reactor components and interrupt fusion reactions. Addressing this challenge requires reliable models that can classify plasma discharges and predict disruptions in advance. This thesis develops machine learning and deep learning approaches to improve both classification and forecasting.The first contribution is a semi-supervised active learning framework, Nearest Margin-Ranked Batch Mode Active Learning (NM-RBMAL), integrated with an ensemble model.
Unlike traditional classifiers that operate on static training data, this approach continuously adapts to new plasma conditions, reducing model ageing. Tested on the Aditya dataset of 162 shots, it achieves 94% accuracy with a 93% ROC score. Building on this, a Double-Phase Stacking with Active Learning (DPST-PAL) model combines outputs from multiple classifiers in two phases to enhance robustness and adaptability. This method improves classification performance, achieving 98% accuracy and a 99% F1-score.
For disruption prediction, a Bi-LSTM with Dynamic Time Window Aggregation (Bi-LSTM-DTWA) is proposed to overcome the problem of premature alarms. By dynamically adjusting the time window based on evolving plasma signals, the model provides early and reliable forecasts, predicting disruptions 10–23 ms in advance with low computational cost on 220 Aditya shots. In addition, an unsupervised approach, the Gated Recurrent Neural Network with Dynamic Threshold-based Temporal Differentiation (GRNN-DTTD), is developed to eliminate reliance on fixed thresholds and labeled data. By analyzing temporal fluctuations in plasma current, it achieves 98.9% prediction accuracy with lead times of 12–30 ms.
Together, these models form a comprehensive framework for plasma discharge classification and disruption prediction. They not only enhance accuracy but also adapt to evolving plasma behavior, offering timely warnings with reduced false alarms. The findings contribute toward building reliable predictive systems for tokamak reactors, which is essential for achieving stable and sustainable fusion energy
Cyclone Intensity Prediction in the Bay of Bengal Using Deep Learning Methods
No full textThe Bay of Bengal region\u27s coastlines have been badly devastated by tropical cyclones, as the region experiences an average of five to six cyclones per year, with about two to three of these intensifying into tropical storms or severe cyclones. Thus it necessitates to study the accurate and efficient forecasting of their intensity to improve preparedness and response to natural disasters. The present study compares and examines three distinct approaches to cyclone intensity prediction using historical datasets from 1998 to 2020: hybrid optimisation, deep learning-based, and empirical approaches.The predicted accuracy, computational effectiveness, and feasibility for real-time scenarios of each model are assessed.
The first study has proposed an enhanced empirical model that used 12-hour wind speed variations and a correction procedure to improve forecast accuracy across 72-hour periods. The model has significantly reduced both the absolute error (from 21.53 to 12.04 knots) and RMSE (from 25.29 to 21.62 knots), improving previous empirical methods. Its affordability and simplicity of usage make it perfect for easy forecasting. It relies on a limited set of criteria, however, limits its ability to predict long-duration and high-intensity cyclone activities.
To address these limitations, the second study introduced LEGEMP, a deep multilayer perceptive classification model that combines feature selection using Herfindahl correlation with classification using Jaccardized similarity-based learning. The LEGEMP framework has an average prediction accuracy of 85.97%, which is significantly better than existing models. The soft-step activation function and Nesterov gradient descent for training has significantly improved the efficiency of the model by reducing the average error rate to 14.15%. Limited observational data and dynamic unpredictability in cyclone activity have been better managed by this approach.
In order to enhance cyclone prediction, the third study used a hybrid deep learning model developed with Long Short-Term Memory (LSTM) networks tuned by Cat Swarm Optimization (CSO). The model successfully demonstrated long-term temporal dependencies without gradient loss, with a high accuracy of 91.38%. It has the lowest MAE (11.32 knots) and RMSE (13.76 knots), as well as the highest Pierce Skill Score (0.79) and Hit Rate (0.97). Furthermore, the LSTM-CSO model has a low false alarm rate (0.20), indicating its robustness and usefulness in real-world cyclone forecasting scenarios.
These models have collectively demonstrated the progress of cyclone intensity forecasting methods. Even if the empirical method yields a fast and intelligible response, the deep learning and hybrid optimization frameworks have significantly increased accuracy and scalability. This thesis emphasizes the necessity of integrating data-driven intelligence with accurate modelling techniques to improve early warning systems and strengthen coastal resilience against tropical cyclone dangers