Sri Shakthi SIET Journals
Not a member yet
211 research outputs found
Sort by
Credit Card Fraud Detection Using State-of-the-Art Machine Learning and Deep Learning Algorithms
Get PDFCredit card fraud is a major concern for both financial institutions and consumers, leading to significant financial losses and a decline in trust. With the rise in online transactions and increasingly sophisticated fraudulent schemes, there is a pressing need for strong and effective fraud detection systems. This research explores how machine learning and deep learning algorithms, particularly Random Forest (RF) and K-Nearest Neighbors (KNN), can be applied to detect credit card fraud. The main goal is to assess and compare how well these algorithms perform in accurately spotting fraudulent transactions while keeping false positives to a minimum. To carry out this research, we use a publicly available dataset of credit card transactions, which is marked by an imbalanced class distribution, where fraudulent transactions are far fewer than legitimate ones. We apply various preprocessing techniques, such as data cleaning, feature scaling, and addressing class imbalance through resampling methods like SMOTE (Synthetic Minority Over-sampling Technique), to improve data quality and model performance. Random Forest is a powerful ensemble learning method that uses a collection of decision trees to boost prediction accuracy and cut down on overfitting. K-Nearest Neighbors (KNN) is a straightforward, instance-based learning algorithm that classifies transactions by looking at the majority class of their k-nearest neighbours in the feature space. To evaluate how well both algorithms perform, we look at various metrics like precision, recall, F1-score, and the Area Under the Receiver Operating Characteristic Curve (AUC-ROC). The findings show that Random Forest typically outshines K-Nearest Neighbors in overall accuracy and F1-score, especially when dealing with imbalanced datasets. This research emphasizes the need to tackle class imbalance and choose the right evaluation metrics for effective fraud detection
Smart Drainage System for Urban Flood Prevention
Get PDFUrban flooding has become a significant issue in contemporary cities, exacerbated by climate change, increased urbanization, and outdated drainage infrastructure. This study introduces a Smart Drainage System that uses cutting-edge technology like IoT, AI, and real-time monitoring to stop urban floods. An interactive municipal dashboard, automated flow control valves, AI-driven predictive analytics, and smart drain covers with integrated sensors are all features of the system. The system dynamically controls water flow, identifies obstructions, and sends out early flood warnings by integrating information from environmental sensors, weather forecasts, and historical trends. With features for offline operation and both manual and autonomous modes of operation, the system guarantees uninterrupted functioning even in emergency situations. According to the research, this kind of intelligent technology provides an adaptable, scalable, and economical way to reduce urban flooding
Comparative Analysis on Different Deepfake Detection Techniques
Get PDFAdvancements in deep learning have led to the emergence of highly realistic AI-generated videos known as deepfakes. These videos utilize generative models to expertly modify facial features, creating convincingly altered identities or expressions. Despite their complexity, deepfakes pose significant threats by potentially misleading or manipulating individuals, which can undermine trust and have repercussions on legal, political, and social frameworks. To address these challenges, researchers are actively developing strategies to detect deepfake content, essential for safeguarding privacy and combating the spread of manipulated media. This article explores current methods for generating deepfake images and videos, with a focus on facial features and expression alterations. It also provides an overview of publicly available deepfake datasets, crucial for developing and evaluating detection systems. Additionally, the research examines the challenges associated with identifying deepfake face swaps and expression changes, while proposing future research directions to overcome these hurdles. By offering guidance to researchers, the document aims to foster the development of robust solutions for deepfake detection, contributing to the preservation of the integrity and reliability of visual media
Harnessing Artificial Intelligence for Disease Detection and Rapid Drug Discovery: A Path to Accelerated Medical Responses
Get PDFThe history of Artificial Intelligence (AI) in drug discovery spans decades, from rule-based systems to sophisticated machine learning and deep learning algorithms. Early applications included virtual screening and QSAR modeling, which paved the way for data-driven drug development. Today, systems like IBM Watson Health and DeepMind's AlphaFold are good at analyzing medical data, predicting molecular interactions, and accelerating the design of novel drugs. Yet in most AI solutions that already exist, they usually only solve the specific tasks rather than formulating a comprehensive framework in emerging disease management. This paper proposes the integration of disease symptom data, pathogen-level analysis, and treatment prediction via an AI-driven model about diseases with symptoms such as cold, cough, or fever. The system correlates new pathogens with stored datasets and identifies potential medicine combinations for rapid testing and refinement, thereby significantly reducing the timelines for drug development. Hence, this approach addresses the severe need for scalable, fast-response solutions in managing infectious diseases and future pandemics
Energy-Saving Triggering Series Low-Power, High-Performance Locking Systems for Element Design: Pseudo NMOS
Get PDFFlip-flops represent a significant source of power dissipation within a system. The clocking system itself comprises sequential components, such as latches and flip-flops, alongside the network that delivers clock signals. The pseudo-NMOS technology, split path, and clock tree sharing schemes are employed to propose a positive edge triggering flip-flop that is designed for both speed and power efficiency. The flip-flop's latching section's floating node instability and inadequate circuit energy loss are solved via pseudo NMOS and split path approaches, respectively. By enabling the latching part of the flip-flop to share the clock provision network for gathering the data D, the clock tree sharing technique reduces the D-Q delay and the overall number of transistors required to construct the clock provision network. Cutting back on the number of clocked loads is one method that reduces dynamic power dissipation and switching activity. The flip-flop’s latching part is made using this process in the suggested design. This study evaluates the performance of a flip-flop circuit modeled using 0.12 nm CMOS process technology. According to the simulation comparison, the suggested register element design improves The power delay product increased from 56.86th% to 71.26th%, the energy delay product rose from 77.86th% to 82.4th%, and the power energy product (PEP) escalated from 56.22th% to 81.22th%. It conserves between 7.06th% and 32.83rd% of energy
Automated System to Preventing Social Security Fund Misuse by Identifying Deceased Beneficiaries
Get PDFEnsuring safe and convenient access to essential services, including pension retrieval, is crucial in the current digital era. Passwords and PINs are examples of traditional authentication systems that frequently expose people to fraud and identity theft. In order to replace these traditional methods with biometric verification (such as fingerprint and facial recognition), this project suggests a Web Biometric Credentialing System for pension retrieval. The system incorporates Auth0 for secure identity and management of sessions and WebAuthn API for biometric authentication. This method greatly enhances security and user experience by enabling pensioners to verify their identity using biometric information. The technology makes sure that only authorized people can access sensitive financial data and, after successful verification, enables pensioners to safely retrieve their pension amounts. By lowering fraud, eliminating unwanted access, and streamlining the authentication procedure, the suggested solution improves security
Comparative Study on Normal Reinforced Concrete with Bamboo Reinforced Concrete
Get PDFConcrete is a commonly utilized building material due to its durability and affordability. It has properties that allow it to resist fire and provide earthquake protection. However, a major drawback of concrete is its limited tensile strength. Steel is one of the most effective materials for compensating for concrete's low tensile strength, it has high tensile properties. Therefore, steel bars are incorporated for reinforcement. Unfortunately, the natural resources required for steel are dwindling, necessitating alternative materials. Some structures worldwide have been constructed using only plain concrete or bricks without steel reinforcement. These structures are vulnerable to the impacts of natural disasters like earthquakes, hurricanes, and storms. Bamboo emerges as an excellent material to replace reinforcing bars in concrete. As a composite material, bamboo consists of long, parallel cellulose fibers, granting it notable flexibility and toughness. It fully matures in just a few months, achieving its peak mechanical strength within a few years. While the strength of bamboo can increase with age, its maximum strength is usually reached at 3 to 4 years, after which it may begin to decline. Bamboo features nodes throughout its length, which help prevent buckling. Remarkably, bamboo can bend significantly, even touching the ground, without fracturing. This characteristic sets bamboo apart from other wooden materials. Additionally, bamboo is widely available, found in nearly all tropical and subtropical regions. This availability reduces construction costs while enhancing the structural integrity of buildings that otherwise lack reinforcement. Its lightweight design and impressive strength render bamboo a favorable building material. Bamboo possesses high tensile strength. This project focuses on evaluating the effectiveness of bamboo as a reinforcement material in concrete beams, specifically analyzing the flexural strength and comparing the results to those of steel-reinforced concrete beams
A Low Power Hybrid DCO Using Three Transistor (3-T) XNOR Gate, CMOS and Pseudo-NMOS Inverter
Get PDFThis research article presents a comprehensive investigation of three-bit hybrid-digitally controlled ring oscillator (HDCRO) implemented with TMSC 90nm CMOS technology. The hybrid circuit HDCRO comprises of three distinct delay stages, namely XNOR-based inverter, a CMOS inverter, and a Pseudo-NMOS inverter, all of which have been designed utilizing an inversion MOS varactor (IMOS). Furthermore, the investigation explores the output frequency variation in the load element of the HDCRO by adjusting the capacitance of the digitally controlled MOS varactors. This frequency variation occurs as a result of changing the digital control bits of the MOS varactors at a supply voltage of 0.7 V. The proposed HDCRO demonstrates an oscillation frequency range of 2.558 GHz to 2.649 GHz, with power consumption varying from 3.638 mW to 1.046 mW, and phase noise from -68.070 dB@1 MHz to -67.654 dB@1 MHz relative to the central oscillation frequency. Moreover, by applying a supply voltage variation between 0.5 V and 1 V, a wider frequency tuning range of 1.238 GHz to 4.438 GHz is achieved. This extended tuning range exhibits power consumption variation from 2.785 µW to 54.66 mW, and phase noise from -68.812 dB@1 MHz to -65.445 dB@1 MHz relative to the central oscillation frequency. In summary, this study presents a novel HDCRO architecture that demonstrates excellent performance in terms of frequency range, power consumption and phase noise. The proposed design offers advantages of high speed, low-power and good frequency range; thus has a promising prospect of application in high-performance integrated circuits
Study of the Behaviour of Concrete Filled Steel Tube Column and Fully Encased Composite Column on A G+10 Storey Special Moment Frame
Get PDFOne of the main problems with a G+10 Storey Special Moment Frame is its vulnerability to progressive collapse. In India fortified solid structures are generally utilized since this is the most advantageous and monetary framework for low-ascent structures. The RCC Structure is not, at this point reasonable due to the expanded dead burden, range dismissal and less solidness. There is extraordinary potential for expanding volume of steel in development. The level of steel can be expanded with the utilization of steel-solid composite segments. The undertaking presents the impact of Conventional RCC, CFST (Concrete filled Steel Tube) and Fully Encased Composite segment on a G+ 10 story extraordinary second casing. In this task three distinct structures are considered for the correlation under seismic examination. The direct static examination, for example "Identical seismic coefficient investigation" are accomplished for G+10 story structure. To correlate the behaviour of structure for seismic load, a simulation model is developed using ETAB software. Results are generated for the Self weight, Story Drift, Story Shear, Lateral burden appropriation, Base shear, Story dislodging and story float for all the three structures. As the composite is having more horizontal firmness, lesser decrease in self- weight, the base shear, and the sidelong burden appropriation along the story shows the huge variation such that Concrete-Filled Steel Tubular (CFST) and Encased Column models demonstrate a notable reduction in self-weight by 11.2% and 4.45%, respectively, compared to RCC columns
Exploratory advancement in the optimal utilization of bio-wastes for ZnO nanoparticle synthesis in antimicrobial applications
Get PDFThe wealth out of Waste (WoW) concept progressively developed for the industrial revolution in recent years. So, bio-waste mediated synthesis of nanoparticles has emerged as a promising approach, leveraging the unique properties of bio-wastes and agricultural wastes. In this study, extracts from Eggshell, Peanut husk, and Orange peels were used to synthesize zinc oxide nanoparticles. The structural, vibration, and morphological properties of the synthesized ZnO nanoparticles were investigated and reported. It reveals that the distinct vibration peaks with strong existence of Zn-O bands from FT-IR spectra. Overall, this study highlights the incomparable structural and morphological properties of bio-waste extracts and their impact on the synthesis and functionality of zinc oxide nanoparticles, paving the way for future research in antimicrobial and targeted drug delivery applications