Browse Items (16481 total)
Sort by:
-
Deep and Hybrid Ensemble Learning Methods for Enhanced Live-Birth Prediction in Fertility Treatments
The prediction of live birth outcomes using Assisted Reproductive Technologies (ART) remains a complex task owing to the high inter-patient variability and non-linear clinical interactions. This study presents a comparative evaluation of hybrid machine-learning models to improve in vitro fertilization (IVF) success prediction using a real-world anonymized dataset of 2,000 ART cases. After pre-processing (including missing value imputation, feature selection via Recursive Feature Elimination with Cross-Validation, and class balancing using SMOTE with k=5), four hybrid models were developed: stacking with XGBoost as the meta-learner, weighted ensemble, autoencoder-based feature fusion, and cascading classifiers. Models were evaluated using accuracy, AUC, precision, recall, and F1-score metrics, and compared against a baseline Random Forest classifier. The stacking model (XGBoost with Random Forest, MLP, and SVM base learners) achieved the best performance, with an accuracy and 0.999 AUC of 0.985. The weighted hybrid ensemble followed an accuracy of 0.953 and AUC of 0.994. The statistical significance of the improvements was confirmed using Wilcoxon Signed-Rank and McNemars tests (p < 0.05). To enhance model transparency, SHapley Additive exPlanations (SHAP) was applied to interpret base model contributions in the stacking architecture. These results support the application of AI-driven hybrid modelling for personalized IVF treatment planning. Future work will focus on prospective validation and clinical decision support system (CDSS) integration to assess deployment feasibility. (2025), (Slovene Society Informatika). All rights reserved. -
Transforming network security through zero trust architecture: Principles, challenges, and future directions
Given the continued expansion of cyber threats; such perimeter-based resistance traditional security strategies have proven to be inadequate. No one is trusted by default, either inside or outside the network, in a Zero Trust architecture. Zero Trust Architecture (ZTA) is a modern security model that demands consistent authentication of users and devices and denies any presupposition of implicit trust. It should also be of strong authorization, network division, and authentication. This article covers the principles, components, pros, and cons along with zero trust implementation strategies and the impact on network security. 2026, Taru Publications. All rights reserved. -
Sustainable Financial Management (SFM) in E-Banking: Strategies and Challenges in Dubai
This paper explores the landscape of sustainable financial management (SFM) in e-banking within Dubai, focusing on the strategies banks implement to promote sustainability and the challenges they encounter. As e-banking continues to expand, sustainability has become crucial for banks aiming to minimise their environmental impact and enhance operational efficiency. The study examines various sustainable strategies, such as the adoption of energy-efficient technologies, the shift towards paperless transactions, and promoting digital customer engagement. Additionally, it considers the regulatory framework and policy support that facilitate sustainable practices in the banking sector, the challenges that banks face, including high implementation costs, technological hurdles, and issues related to customer adoption through case studies. The research illustrates the effectiveness of different approaches and solutions to these challenges. The findings underscore the significance of an integrated strategy aligning economic objectives with environmental sustainability, ultimately benefiting the banking industry and society over time. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Rebel Foods: Pioneer in Indian internet restaurant and cloud kitchen
Learning outcomes The learning outcomes are as follows: to identify the potential for disruptive innovation in the changing dynamics of the online food industry with the emergence of technology; to examine appropriate responses to emerging disruptive (environmental) threats in developing a sustainable food retail business; to evaluate the process of executing change management within the organisation, as per the dynamic external business environment; and to develop marketing and distribution strategies that can be created based on a competitive business environment by applying disruptive technological initiatives. Case overview/synopsis Rebel Foods Private Limited was one of the largest internet restaurant and cloud kitchen companies, founded by Jaydeep Barman and Kallol Banerjee in 2016. Rebel Foods had established its presence in 70 cities owing to its extensive network of 450 cloud kitchens with more than 4, 000 internet restaurants. It was involved in all three steps of the food on demand industry: ordering, distribution and order fulfillment. Faasos (earlier name of Rebel Foods) had invested around four years in the restaurant industry using the brick-and-mortar format, slowly shifting to the online business model. Due to the spread of the COVID-19 virus in March 2020, Rebel Foods closed 70% of its kitchens and began selling do-it-yourself meal kits. After the pandemic, the kitchens at Rebel Foods used cutting-edge technology such as robotics, drum machines, automatic Tawas (pans) and auto fryers. The chefs at Rebel Foods had automated the cooking process using modern technology like computer vision and artificial intelligence. Despite all efforts, the companys operating revenue had dropped by 27.5% during FY21 to reach 405.1 crore INR, down from 558.7 crore INR in FY20. Sales have also been declining in the past few years. Complexity academic level The learners can be early-career entrepreneurs operating in the food industry and/or enrolled in postgraduate or short-term management programs. The case can also be used in Executive MBA courses in Strategic Management, Marketing Management and Entrepreneurship Management. Supplementary material Teaching notes are available for educators only. Subject code CSS 8: Marketing. 2025 Emerald Publishing Limited -
A Study on the impact of e-service quality perceived customer value and customer satisfaction on customer loyalty in online travel agencies
As the markets have become more competitive in every business sector especially in online, many companies have recognized the importance of developing a strong loyal customer base. The benefits associated with newlinecustomer loyalty include lower costs of retaining existing customers as compare to acquiring new customers, repeat business, word of mouth marketing, cross selling opportunities and so on. However, in case of newlineonline business, customers could effortlessly cover the globe at the click of a mouse in search of the lowest price and that results in break in customer loyalty. Hence, it is necessary to conduct research on newlineidentifying the drivers of customer loyalty and their influence on customer loyalty. newlineThis research explored the impact of e-service quality, perceived customer value, customer satisfaction on customer loyalty in online travel agencies. A conceptual model is proposed based on previous studies and newlinetested using structural equation modeling technique, bootstrapping estimates and multi group SEM (MSEM) analysis. The study employed newlinepurposeful sampling technique and was conducted on a sample size of 405 respondents working in information and communication technology organizations set up in Bengaluru. The study also tested the mediating effect of perceived customer value and customer satisfaction on the relationship between e-service quality and customer loyalty. The study also made an attempt to test the moderating effect of switching cost on newlinerelationship between e-service quality and customer loyalty, perceived customer value and customer loyalty as well as customer satisfaction and customer loyalty. Results indicated that e-service quality, perceived newlinecustomer value and customer satisfaction has a significant and positive impact on customer loyalty.Results of the study also indicated that perceived customer value and customer satisfaction partially mediate the newlinerelationship between the antecedent and outcome variables. -
Predicting Football Players Market Value via Machine Learning
Football, arguably the most popular sport in the world, has become much more than just a sport, it is a multibillion-dollar industry with its center in Europe. Every year millions of euros are spent in transfer window to buy and sell players and a common theme that has been seen is players not living up to the price the clubs paid for them. This research aims to predict football players market values using machine learning techniques. Departing from traditional methods that broadly categorize players into positions like Goalkeeper, Defender, Midfielder, and Forward, this study provides a more nuanced approach by classifying players into specific roles such as Center-back, Full-back, Defensive Midfielder, Attacking Midfielder, and Winger. By incorporating performance metrics tailored to each position and weighing the performance indicators based on the relevance to that specific position, the research aims to provide a robust method to predict players market value within a negotiation tolerance range. Using data from the past three seasons, including detailed player performance statistics and contractual details, models were developed to assist clubs in making data-driven transfer decisions. Machine learning algorithms, including Random Forest Regressor and Light GBM, were utilized, with RMSE and R2 Score as evaluation metrics. Both algorithms demonstrated robust performance, with some positional models predicting market values within an acceptable error range of 312million, enabling clubs to negotiate transfer fees with greater precision based on empirical evidence of player performance. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Reflexive Praxis in University Classrooms in India: A Case Study
This article presents the case study of a university teacher's journey focusing on struggles he faced in the personal and professional space during his teaching career that shaped his pedagogic practices. Bourdieu's structural parameters and Engstr's (1987) theory of expansive learning provided analytical concepts, including reflexivity, to study the pedagogical praxis of this teacher. The analysis of data collected using the biographical narrative interviewing method, classroom observation, and autobiographical writings of the teacher reveals that as he questions his social positioning, academic "field," and intellectual bias, he experiences conflicts and tensions that arise from several disruptions resulting in pain and frustrations at one level and at another level shaping his desire and the ability to engage critically and historically with the processes and outcomes of personal and pedagogic interrogations. He realizes that there is no "A" algorithm for developing reflexivity. It takes a lifetime for a teacher to build a reflexive praxis. 2025 Common Ground Research Networks. All rights reserved. -
Hybrid EconometricMachine Learning Models for High- Dimensional Data: Robust Approaches to Anomaly Detection and Inference
This chapter, according to the authors, looks at making modeling robust and interpretable when faced with complex, irregular, and contaminated data environments. As empirical research continues to move towards larger datasets having numerous variables and high dependency among variables, along with instances of irregular data, traditional models of analysis can no longer be very effective. The chapter looks at the possibility of having a comprehensive modeling approach by integrating concepts of robustness like bounded sensitivity and stability analysis, along with flexible modeling at the analytical and computational levels. A major focus is on finding influential data points, rare observations, and structural breaks during the modeling process and not after the process is complete. 2026 by IGI Global Scientific Publishing. All rights reserved. -
Toward Smart 5G and 6G: Standardization of AI-Native Network Architectures and Semantic Communication Protocols
Semantic communication and AI-native design are widely recognized as defining features of 6G, yet existing surveys often treat them conceptually or in isolation. This article provides a standards-oriented perspective that integrates these paradigms and evaluates their implications for architectural design and standardization. We make three concrete contributions: 1) we propose enriched KPI frameworks, security and privacy taxonomies, and interoperability prescriptions that extend beyond current 3GPP, ITU-T, and O-RAN activities; 2) we analyze implementation trade-offs such as computational overhead of semantic encoding and the scalability of federated learning in ultra-dense deployments; and 3) we demonstrate the potential of semantic communication through a UAV case study, highlighting measurable improvements in bandwidth, latency, and coordination efficiency. These contributions distinguish our work from prior surveys by moving beyond high-level vision toward feasibility analysis and concrete standardization pathways, thereby offering actionable insights for the evolution of semantic-aware 6G systems. 2017 IEEE. -
Analysis using a modified Johnsoncook model for AISI 304 stainless steel and ofprior dynamic tensile behavior deformed AISI type 304 stainless steel
304 stainless austenitic steel (AISI 304) is renowned for its high temperature resistance and has been the subject of considerable research. To explore its rheological behavior at high temperature, isothermal hot compression experiments were conducted on the Gleeble-3800 thermal simulator at temperatures of 8001200 C, strain rates of 0.01111 s-1, and a total strain of 60%. From the experimental data, a JohnsonCook (JC) constitutive model was formulated and further optimized. The optimized model considers the combined effect of strain, strain rate, and temperature, resulting in a more precise constitutive equation. The enhanced JC model had excellent predictive power, with a correlation coefficient (Rco) of 0.9884 and an average absolute relative error (AARE) of 8.42%. ABAQUS simulations for verification confirmed the model to be valid. This study offers valuable theoretical information for the hot working of SS 304, enabling more precise predictions of stress behavior at high temperature and easier optimization of processing parameters and overall material behavior. Also, deformation of metastable austenitic stainless steel at temperatures below the Md point leads to the transformation of austenite into martensite. This study investigates how prior deformation, conducted at temperatures both below and above Md, affects the dynamic tensile behavior of AISI 304 stainless steel. Pre-deformation at 25C (below Md), as well as at elevated temperatures of 200C and 300C (above Md), enhances both the yield strength and ultimate tensile strength of the material. Notably, prior deformation at 25C to a small equivalent strain (< 0.03) results in significant improvements in strength (22%) and ductility (2137%) during subsequent high strain-rate tensile loading at 200 and 300s?1. The evolution of local strain fields and strain rates is analyzed using digital image correlation. Additionally, the development of localized necking is investigated through in-situ high-speed camera imaging. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025. -
Integrating sustainability principles into human resource management: An emerging trend
This chapter "Integrating Sustainability into Human resource management" talks about the fact that Sustainability has emerged as a critical concern for organizations worldwide, demanding a holistic approach that integrates environmental, social, and economic considerations. This abstract discusses the essential role that Human Resource Management plays in achieving sustainable business practices, especially in a competitive environment, such as that of tourism. Human capital, comprising knowledge, skills, abilities, and experience, is the core of an organization's success. Tourism being a people-intensive business, the quality and dedication of the workforce will determine the degree of customer satisfaction, reputation of the brand, and competitiveness. It is not just a normative issue but also a strategic issue where sustainability integration into HRM is essential for the long-term survival of the organizations. 2025, IGI Global Scientific Publishing. All rights reserved. -
Time-Frequency Analysis of ECG Signal
Time-frequency analysis (TFA), especially well suited for biomedical applications, is a potent method for deciphering non-stationary signals, where frequency characteristics vary with time. These dynamic signals are too complex for conventional frequency analysis approaches, which calls for sophisticated techniques like the discrete wavelet transform, continuous wavelet transform, and short-time Fourier transform. This research focuses on the uses of TFA techniques in biomedical signal processing and how well they expose transitory phenomena and temporal patterns that are missed by conventional methods. In particular, we look at how TFA is applied to the analysis of electrocardiogram (ECG) signals. The chapter discusses baseline wander, notch filtering, and low-pass filtering as crucial pre-processing techniques for clean ECG readings. Furthermore, we present the symbolic aggregate approximation paradigm for effective data retrieval and storage. 2026 selection and editorial matter, Ganesh R. Naik. -
Predicting and Optimizing Synergistic Drug Combinations for Breast Cancer Treatment Using Machine Learning
Objectives: The study aims to identify highly synergistic drug combinations for breast cancer treatment using machine learning models. The primary objective is to predict drug synergy scores accurately and rank combinations with the highest potential for therapeutic efficacy. Methods: Machine learning models, including XGBoost, Random Forest (RF), and CatBoost (CB), were employed to analyze breast cancer drug combination data. Four synergy metricsZIP, Bliss, Loewe, and HSAwere used to quantify drug interaction effects. The models were trained to predict these synergy scores, and their performance was evaluated using normalized root mean squared error (NRMSE) and Pearson correlation coefficient. Predicted top-ranking drug combinations were further validated by comparing observed versus expected dose-response curves and calculating the area under the curve (AUC) for synergy assessment. Results: XGBoost (XGB_5235) outperformed other models, achieving an NRMSE of 0.074 and a Pearson correlation of 0.90 for the Bliss synergy model. Based on average synergy scores, the top 20 drug combinations were identified, with Ixabepilone+Cladribine, SN 38 Lactone+Pazopanib, and Decitabine+Tretinoin emerging as the most promising. These combinations showed high synergy and were supported by biological insights into their mechanisms of action. Conclusions: The study demonstrates the effectiveness of machine learning in predicting synergistic drug combinations for breast cancer. By accelerating the screening process and reducing experimental burden, the approach offers a promising tool for guiding future in vitro and in vivo validation of combination therapies. Copyright 2025 Wolters Kluwer Health, Inc. All rights reserved. -
Some new results on anti-adjacency spectra of regular graphs
The anti-adjacency matrix A*(G) of a simple graph G with V (G) = {v1,v2,v3,vn}, is a square matrix of order n with rows and columns indexed by V (G), where the (i,j)-entry (i?j) is 1, if the vertices vi and vj are not adjacent to each other and 0, otherwise. The (i,i)- entry of A*(G) is 1. The anti-adjacency eigenvalues of G are the eigenvalues obtained from the matrix A*(G) and the corresponding spectra is called the anti-adjacency spectra of G, denoted by a-spec(G). In this paper, we discuss the anti-adjacency spectra of join and disjoint union of regular graphs. The anti-adjacency spectra of bipartite regular graphs, line graphs of regular graphs and strongly regular graphs are also discussed. 2026 World Scientific Publishing Company. -
Neonatal Hypoglycemia in the Newborn of a Diabetic Mother: Risk Factors in Prediction and Management
Among the metabolic complications, neonatal hypoglycemia remains the most common complication, especially among infants of diabetic mothers. This paper is to briefly review landmark research studies aimed at assessing the prediction of neonatal hypoglycemia with consideration of maternal glucose monitoring, cord blood C-peptide, and HbA1c biomarkers together with advanced AI-based models. This becomes significant in reviewing the pathophysiology of neonatal hypoglycemia, clinical risk factors, and treatment strategies in view of the predictive value of both the mother and the newborn. Maternal diabetes type, gestational age, and neonatal BMI are some of the risk factors to be evaluated. The rapidly growing role of AI in clinical practice would also be discussed. In addition, an individualized management approach might be advocated to improve the outcome of the newborn by employing appropriate clinical tools coupled with AI-based predictive models. 2026 American Institute of Physics Inc.. All rights reserved. -
Challenges and innovations in applying SDG and ESG frameworks
Entrepreneurial skills have evolved significantly since initiatives like the "Green Paper on Entrepreneurship" (EU Commission, 2003) and the "Small Business Act" (European Commission, 2008), which emphasized knowledge, competencies, and sustainability. Entrepreneurs today prioritize long-term sustainability over short-term profits (Elkington, 2018), leveraging frameworks like the Sustainable Development Goals (SDGs) and Environmental, Social, and Governance (ESG) standards to integrate ethical practices with financial performance.Despite these obstacles, ESG and SDG frameworks present opportunities for innovation through systems thinking, foresight, and interdisciplinary collaboration (Senge, 1990). By adopting "green thinking," entrepreneurs mitigate external threats, foster innovation, and drive sustainability. This chapter explores the role of networking, strategic thinking, and ethics in sustainable practices, offering insights into aligning business strategies with global sustainability goals for long-term success. 2025, IGI Global Scientific Publishing. All rights reserved. -
Lights and Shadows in Autodesk 3ds Max: Methods and Features
Using the 3ds Max software, this paper describes the intricate modelling process of implying shadows onto various objects to make it look more realistic. In this article, Various Shadow types and controls are used in order to demonstrate the functions of shadows in Autodesk 3ds Max. The paper helps the reader understand the nature of the lights and shadows in a computer-generated environment and its implementation in the real-world situations. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025. -
Assessing the risk reducing strategies in international investment
International investment presents huge potential gains in economic development, technological lead and exchange of culture. But it also poses major risks to the number of successful ventures that we conduct. This chapter starts with a general discussion of how the above- mentioned factors could significantly affect risk exposure related to international investment, followed by an appraisal section on different approaches focus on some popular methodologies employed in analyzing all kind of risks and mitigation factotums for effectively reducing those assessed risks. This will provide them with the necessary foundation, a good business perspective to take calculated decisions and in turn improve the robustness and profitability of their international investments. It starts by providing definitions of terms like foreign direct investment (FDI), portfolio investment, and international trade, as well as discussing the particular forms of risks that happen in each kind of investment. 2025, IGI Global. All rights reserved. -
Cultural Blind Spots in Marketing AI: Case Studies of Failure
Artificial intelligence has been quickly shifting into the pioneer of contemporary marketing. AI powered systems influence how brands communicate with culturally diverse audiences through automated content creation and hyper personalized targeting. These systems, while highly efficient, are proving to have major cultural blind points in which algorithmic decision making fails to detect or interpret cultural, social, and representational subtleties. Such lapses appear as biased outputs, homogenization of identity, and reinforcement of stereotypes, growing into public controversies and reputational crises. This chapter explores cultural blindness in marketing- focused AI systems through four case studies: Amazons recruitment tool, H&Ms culturally insensitive campaign, Doves beauty representation controversy, and Levis AI generated diversity models. 2026 by IGI Global Scientific Publishing. All rights reserved.