Browse Items (16481 total)
Sort by:
-
Artificial intelligence and deep learning based driverless cars to reduce the road accident, death rate using python /
Patent Number: 202221047470, Applicant: Rashel Sarkar.
2% of global deaths each year are caused by automobile accidents. This corresponds to around 3,287 each day, or 1,300,000 per year. 20 million to 50 million people are seriously injured in automobile accidents annually. Why do these recurring problems persist People do make errors. One careless or foolish action is all it takes to transform a safe drive into one that could kill someone. This holds true regardless of whether the driver is preoccupied, intoxicated, or simply careless or irresponsible. In terms of technology, Artificial Intelligence (AI) has always been ahead of the curve. -
Credit card fraud detection using python and machine learning /
Patent Number: 202221047470. Applicant: Pankaj Shambunath Mishra.
Credit Card Fraud Detection Using Python and Machine Learning Abstract: As we are heading towards the digital world cyber security is becoming an essential element of our life. When we talk about security in digital life then the major challenge is to discover the anomalous activities. When we make any transaction while purchasing any product online a big proportion of consumers choose credit cards. The credit limit in credit cards often helps us to making purchases even if we don’t have the funds at that time. But, on the other hand, these features are utilised by cyber attackers. -
Stock market prediction using artificial neural networks in python /
Patent Number: 202231052415, Applicant: Dr. Rashel Sarkar.
When the issue of forecasting time series is mentioned, the reader, listener, or observer instantly considers forecasting stock prices. This should help individuals determine when to sell and when to purchase more. On occasion, we encounter resources that explain how this is possible. Throughout Deep Learning with Python, Chollet cautions against using time series prediction algorithms to estimate market values. You should not attempt to predict how the stock market will behave in the future based on past performance. Due to the design of the martingale system, the present price of a share of stock is the most accurate indicator of its future price (in terms of the error associated with estimation). -
Method of enhancing quality of services in cloud computing environment using load balancer /
Patent Number: 202211006218, Applicant: Dr. Pratibha Giri. -
A smart attendance system and method for permission inventory during the class /
Patent Number: 202111060922, Applicant: Shivani Chaudhry.
A smart attendance system (1). The system (1) comprises a smart lecture stand (2), which having an electronic unit (2A) which is connected to the other smart door, smart bench, and smart chair of the system; a smart bench (3), which having an electronic unit (3A), which is connected to the other smart door, smart stand, and smart chair of the system; a smart chair (4) comprises which having an electronic unit (4A); which is connected to the other smart door, smart bench, and smart stand of the system; a smart door (5) comprises a electronic unit (5A), which is connected to the other smart door, smart bench, and smart chair of the system. -
Enhancing Education Policy Estimation: A Novel Ridge Fuzzy Regression Approach for Handling Multicollinearity with Fuzzy Input Data
Multicollinearity often complicates regression analysis, both in classical and fuzzy input setup. This research introduces a new approach that combines ridge regression with fuzzy regression to tackle correlated covariates impact, with a specific focus on improving education policy systems. Our method utilizes the ?-level estimation algorithm and a dataset where Grade Point Average (GPA) serves as a fuzzy input, while input variables remain crisp. We assess our estimators performance using RMSE and MAPE. This applied research showcases the potential of our method in enhancing education policies through more accurate data-driven decision-making. The Author(s), under exclusive license to Springer Nature Switzerland AG 2025. -
Real-time detection and response: How AI is shaping the future of hate speech
This chapter traverse how artificial intelligence is transforming hate speech detection by facilitating real-time detection and response. It focuses on the technical aspects of using machine learning. Natural language processing and deep learning models to identify and mark spiteful content. This chapter also discusses the advantages, obstacles, and ethical considerations associated with using AI to moderate online speech. The ultimate objective is to provide insights into how AI is changing the landscape of content moderation on platforms around the world. 2025, IGI Global Scientific Publishing. All rights reserved. -
Porous Carbon Nanospheres Derived From Caesalpinia Sappan Pods as Novel Antibacterial Agents
The current work shows how catalyst-free carbon nanospheres (CNS) can be produced utilizing straightforward one-step pyrolysis methods employing biowaste Caesalpinia sappan pods as a carbon precursor. The manufactured CNS with a particle size range of 4050 nm that is obtained show a porous nature and contain more than 87% carbon. The synthesized CNS are used as potential antibacterial agents against E. coli and S. aureus by microscopic analysis. By observing the distorted cell envelopes of both E. coli and S. aureus compared with those of untreated cells, it is well understood that CNS, by binding to the outer envelope of cells, renders some changes in the peptidoglycan layer of both Gram-positive and Gram-negative microbes, which in turn restricts their further growth. This study confirms the first report of use of CNS as an effective antibacterial agent. 2025 Wiley-VCH GmbH. -
Hydro-thermo-electromechanical response in a size-dependent porous piezoelectric medium under memory-dependent MGT theory
This study explores the intricate coupled hydro-thermo-electromechanical behavior of a size-dependent porous piezoelectric medium. We uniquely employ the memory-dependent MooreGibsonThompson (MGT) framework for heat conduction in conjunction with Eringens nonlocal elasticity theory to analyze the effects of time-delay and nonlocality on various physical fields. Novel constitutive relations are developed to capture these combined influences. Analytical solutions for displacements, temperatures (solid and fluid phases), stresses (normal and shear), and electric displacements and potentials are obtained using normal mode technique. A detailed graphical analysis illustrates the impact of time, nonlocality, and porosity under both open and short circuit electrical boundary conditions. Three-dimensional plots confirm the dispersive, diffusive, and memory-dependent behavior. The main findings reveal that nonlocality significantly smooths field gradients and broadens spatial profiles, while memory-dependent thermal conduction results in wave-like and delayed temperature responses, with the solid phase reacting faster than the fluid. Furthermore, electric potentials and displacements are considerably enhanced under open-circuit conditions, highlighting boundary effect sensitivity. It is also observed that increasing porosity consistently decreases the magnitudes of all fields and restricts their penetration depths, indicating a structural softening effect. This work presents a unique analytical model that integrates memory-dependent MGT theory with nonlocal elasticity to analyze the hydro-thermo-electromechanical behavior of a fluid-saturated porous piezoelectric medium. The theoretical framework provides a robust foundation for advancing the design and development of piezoelectric sensors and actuators operating in coupled hydro-thermo-electromechanical environments, particularly those with porous structures. Potential applications span geophysical monitoring, biomedical implants under complex loadings, and MEMS where size-dependent and relaxation effects are significant. 2025 Taylor & Francis Group, LLC. -
KleinGordon nonlocal dynamics of porous piezo-thermoelastic medium with surface irregularity under fractional-order modified LS model
The miniaturization of devices alongside advances in thermal management technologies necessitates the generalization of heat conduction and thermal elastic coupling to faithfully represent material responses at ultrashort temporal scales. Motivated by viscoelastic mechanical analogies, this work develops an analytical framework for investigating vibrational behavior in an orthotropic, size-dependent piezo-thermoelastic substrate featuring voids, modeled within the Modified LordShulman (MLS) thermoelasticity theory augmented by fractional derivatives. Employing the KleinGordon nonlocal elasticity formulation, the governing equations of motion are rigorously derived. The normal mode method facilitates the examination of coupled thermoelectro-mechanical excitation phenomena. Emphasis is placed on a corrugated interface contiguous to a vacuum, where comprehensive boundary conditions encompassing thermal, electrical, mechanical, and stress equilibria are imposed to determine fundamental field variables. The study systematically evaluates the influence of pivotal parameters, including temporal evolution, nonlocality characteristics, and spatial coordinates, on the thermomechanical and electrical responses, with outcomes substantiated through detailed graphical representations. Although previous investigations have addressed vibrations in porous piezo-thermoelastic media under varying theoretical constructs, the current research uniquely elucidates the dynamic response of a size-dependent porous piezo-thermoelastic medium with a corrugated surface within the fractional-order modified LordShulman framework, marking a significant advancement in the modeling of smart microstructured materials. The Author(s), under exclusive licence to Springer Nature B.V. 2026. -
Fractional and memory effects on wave reflection in pre-stressed microstructured solids with dual porosity
The present work investigates the influence of fractional-order derivative and memory-dependent derivative on the behavior of various waves reflected at the free surface of a size-dependent, pre-stressed, microstructured thermoelastic solid with a dual porosity framework. A generalized MooreGibsonThomson (MGT) model, incorporating higher-order terms and memory effects, is adopted to describe the complex heat transfer behavior within the material. A nonlocal framework based on Eringen's theory is utilized to derive the basic relations of the considered medium. An examination of the non-dimensionalized governing equations is conducted employing the normal mode technique to provide accurate solutions. The research demonstrates the presence of six separate wave modes that travel at varying speeds within the medium. The energy and amplitude ratios of reflected waves are determined by applying suitable boundary conditions. The influence of varying incidence angles on the reflected wave energy distribution is investigated numerically and visualized using MATLAB software. The study reveals that the energy ratios of the reflected waves are sensitive to the fractional-order parameter, kernel functions, initial stress, and nonlocality parameter. The analysis suggests a conservative reflection process, indicating minimal energy loss during reflection. Key findings and their implications for relevant scenarios are presented in the conclusion. Comparisons with existing models for certain cases demonstrate good agreement, supporting the validity of the present model. 2025 Elsevier Masson SAS -
Credit card fraud detection using python and machine learning /
Patent Number: 202221047470. Applicant: Pankaj Shambunath Mishra.
Credit Card Fraud Detection Using Python and Machine Learning Abstract: As we are heading towards the digital world cyber security is becoming an essential element of our life. When we talk about security in digital life then the major challenge is to discover the anomalous activities. When we make any transaction while purchasing any product online a big proportion of consumers choose credit cards. The credit limit in credit cards often helps us to making purchases even if we don’t have the funds at that time. But, on the other hand, these features are utilised by cyber attackers. -
Stock market prediction using artificial neural networks in python /
Patent Number: 202231052415, Applicant: Dr. Rashel Sarkar.
When the issue of forecasting time series is mentioned, the reader, listener, or observer instantly considers forecasting stock prices. This should help individuals determine when to sell and when to purchase more. On occasion, we encounter resources that explain how this is possible. Throughout Deep Learning with Python, Chollet cautions against using time series prediction algorithms to estimate market values. You should not attempt to predict how the stock market will behave in the future based on past performance. Due to the design of the martingale system, the present price of a share of stock is the most accurate indicator of its future price (in terms of the error associated with estimation). -
Method of enhancing quality of services in cloud computing environment using load balancer /
Patent Number: 202211006218, Applicant: Dr. Pratibha Giri. -
A smart attendance system and method for permission inventory during the class /
Patent Number: 202111060922, Applicant: Shivani Chaudhry.
A smart attendance system (1). The system (1) comprises a smart lecture stand (2), which having an electronic unit (2A) which is connected to the other smart door, smart bench, and smart chair of the system; a smart bench (3), which having an electronic unit (3A), which is connected to the other smart door, smart stand, and smart chair of the system; a smart chair (4) comprises which having an electronic unit (4A); which is connected to the other smart door, smart bench, and smart stand of the system; a smart door (5) comprises a electronic unit (5A), which is connected to the other smart door, smart bench, and smart chair of the system. -
The impact of AI and agile HR on talent acquisition and onboarding in the service industry
The high speed and competition levels in the service sector make it imperative to have a workforce that is capable of responding to rapid change. This research studies the synergistic impact of the utilization of Artificial Intelligence and Agile Human Resources in the service sector in enhancing the talent acquisition and onboarding process. Transforming the present study into a quest to see how these two transformative forces interact in the quest for identifying their potential for increasing efficiency and effectiveness, along with the employee experience. It investigates how AI can contribute to Agile HR in order to make talent acquisition easier. This involves using AI-based tools in talent sourcing, candidate screening, and assessment, and automating other routine tasks in order to set HR free for more strategic activities. The study also investigates the application of AI in personalizing onboarding, improving employee engagement, and accelerating time-to-productivity. Best practices and challenges are identified by analyzing case studies of service organizations that successfully put both AI and Agile HR into practice. This paper covers the ethical issues associated with AI and the requirement for human judgment in the process of talent acquisition and onboarding. Ultimately, the chapter will contribute to an understanding of how AI and Agile HR can combine in order to build a competitive advantage for service organizations. This will involve the optimization of talent acquisition and onboarding in a manner that enables the building of high-performing teams in order to deliver better customer satisfaction and drive business growth. 2026 Pushan Kumar Dutta, Amarnath Padhi, Sulagna Das, Vinod Kr Sharma and Poshan Yu. All rights reserved. -
Label Informativeness-Based Minority Oversampling in Graphs (LIMO)
Class imbalance is a pervasive issue in many realworld datasets, particularly in graph-structured data, where certain classes are significantly underrepresented. This imbalance can severely impact the performance of Graph Neural Networks (GNNs), leading to biased learning or over-fitting. The existing oversampling techniques often overlook the intrinsic properties of graphs, such as Label Informativeness (LI), which measures the amount of information a neighbor's label provides about a node's label. To address this, we propose Label Informativenessbased Minority Oversampling (LIMO), a novel algorithm that strategically oversamples minority class nodes by augmenting edges to maximize LI. This technique generates a balanced, synthetic graph that enhances GNN performance without significantly increasing data volume. Our theoretical analysis shows that the effectiveness of GNNs is directly proportional to label informativeness, with mutual information as a mediator. Additionally, we provide insights into how variations in the number of inter-class edges influence the LI by analyzing its derivative. Experimental results on various homophilous and heterophilous benchmark datasets demonstrate the effectiveness of LIMO in improving the performance of node classification for different imbalance ratios, with particularly significant improvements observed in heterophilous graph datasets. Our code is available at https://github.com/smlab-niser/limo. 2025 IEEE. -
Signal-aware deep learningbased respiratory motion prediction for lung tumor management
Introduction: Respiratory motion management in radiotherapy for lung cancer patients remains a significant challenge, as it directly affects accurate tumor targeting. Furthermore, unaccounted tumor motion during treatment planning and delivery can lead to imaging artifacts and biased dose distributions, which compromises the accuracy of image-guided radiotherapy. This issue places clinicians in a dilemma between expanding treatment margins, which increases radiation exposure to healthy tissue or risking reduced targeting precision. Methods: In this work, a hybrid deep learning model composed of dilated convolutional layers, bidirectional long-short term memory layers, and a generative autoencoder module is proposed to jointly model the spatial and temporal characteristics of respiratory motion, while enabling reconstruction of the physiologically coherent respiratory signals. Each architectural component learns complementary motion-related patterns from respiratory signals to support tumor motion prediction. The model performs motion-range classification, captures abnormal breathing patterns across spatial and temporal domains, reconstructs physiologically coherent respiratory cycles, and predicts tumor motion within an algorithmic validation framework. Results: Experimental evaluation demonstrates high motion-range classification performance of 98.37%, including low root-mean square error in motion prediction, while maintaining stable performance across long and complex respiratory signals over multiple breathing cycles. Discussion: This study focuses on algorithmic feasibility and establishes a computational foundation for future clinically calibrated and dosimetrically validated models. The findings indicate that the proposed approach can support future motion-aware radiotherapy planning strategies by improving motion characterization at the algorithmic level. Copyright 2026 Das, J. and Medhi. -
The Legal and Ethical Guiding Principle of Artificial Intelligence in Smart Healthcare Systems
The relationship between life and technology has been a constant theme throughout history, with healthcare being a significant industry that has seen considerable advancements. The Digital Revolution in the health sector is increasing reliance on emerging technology, including Artificial Intelligence (AI). This chapter explores the advancement of technology in healthcare and its link with Intellectual Property Management. It traces the evolution of AI in healthcare and explores the legal and ethical issues surrounding its implementation in smart healthcare systems. The authors assess existing regulatory frameworks and suggest recommendations for integrating AI into healthcare while adhering to ethical standards and legal limitations. They also discuss the process of creative destruction leading to accelerated innovation, particularly in the rapid ramping up of digital health capabilities. The chapter also addresses significant legal and ethical problems in AI-powered healthcare, such as patient privacy, data security, liability, and algorithmic prejudice. The authors propose guidelines for policymakers, healthcare providers, and AI developers to create AI applications that comply with legal standards and uphold ethical principles, promoting trust and safety in smart healthcare systems. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Brand protection in Indias digital economy: trademarks vs. competition regulation
The digital economy in India has significantly impacted brand protection, with the need for robust trademark protection intensifying to combat issues like counterfeiting, cybersquatting, and unauthorised use. Competition regulation aims to ensure fair market practices, prevent monopolistic behaviour, and foster innovation. This study examines the legislative and judicial framework governing trademarks in India, highlighting key provisions under the Trade Marks Act, of 1999, and their application in the digital context. It also assesses the role of the Competition Commission of India (CCI) in addressing anti-competitive practices. The study identifies tensions and synergies between trademark protection and competition regulation, examining how digital platforms, e-commerce, and social media influence these legal domains. Comparing the study with jurisdictions like the EU and the USA, the paper proposes a balanced approach that harmonises trademark enforcement with competition law principles to ensure brand protection efforts do not stifle competition and innovation in Indias burgeoning digital economy. Recommendations include policy reforms, enhanced cooperation between regulatory bodies, and the adoption of technology-driven solutions to safeguard brands while promoting a competitive and fair digital marketplace. Copyright 2025 Inderscience Enterprises Ltd.