Browse Items (16481 total)
Sort by:
-
Data-Driven Drug Discovery Optimization for Breast Cancer Using Interpretable Machine Learning Models
Breast cancer remains one of the most prevalent malignancies worldwide, posing significant therapeutic challenges due to tumor heterogeneity and drug resistance. This study presents a reproducible, data-driven machine learning protocol for predicting drug sensitivity in breast cancer cell lines, with the dual objective of identifying potent single agents and synergistic drug combinations. Using curated datasets from the Genomics of Drug Sensitivity in Cancer (GDSC), two predictive approaches were implemented: a standalone XGBoost regressor and a hybrid Autoencoder-XGBoost pipeline. Preprocessing included label encoding, one-hot encoding, Z-score standardization, missing value imputation, and dimensionality reduction via PCA. Model evaluation demonstrated that XGBoost achieved superior performance (MSE = 1.3789, R2 = 0.8145) compared to the hybrid model (MSE = 4.0322, R2 = 0.4577). Interpretability was addressed using SHapley Additive exPlanations (SHAP), which identified TARGET_PATHWAY, DRUG_ID, TARGET, and CELL_LINE_NAME as key predictive features, aligning with established pharmacological mechanisms. Predicted synergy scores, derived from combining model outputs with DrugComb and SynergyDB data, highlighted promising drug pairs such as Bortezomib + Romidepsin and Paclitaxel + Bortezomib. These findings were further supported by PCA-based pharmacological clustering, revealing biologically relevant groupings of drugs with similar mechanisms of action. The proposed protocol provides a transparent and adaptable framework for precision oncology research, enabling both predictive accuracy and biological interpretability. By integrating rigorous preprocessing, model validation, explainability, and drug synergy analysis, this workflow offers a scalable foundation for translational drug discovery and repurposing in breast cancer treatment. 2025 JoVE Journal of Visualized Experiments. -
Optical Spectroscopy of Classical Be Stars in The Galaxy
A classical Be (Be hereafter) star is a special type of massive B-type main newlinesequence star surrounded by a geometrically thin, equatorial, gaseous, decretion disc orbiting the central star. Spectra of Be stars show emission lines of different elements. Studying these lines provide an excellent opportunity to understand the geometry and kinematics of the circumstellar newlinedisc and properties of the central star itself. Be stars, thus provide excellent opportunities to study circumstellar discs. However, the disc formation mechanism in Be stars the Be phenomenon is still poorly understood. The present study focuses on studying a large sample of Be stars through newlineoptical spectroscopy and using two national optical telescope facilities. We performed the spectroscopic study of all major emission lines for a sample of 115 feld Be stars in the wavelength range of 3800 - 9000 using the 2.1-m HCT facility at Ladakh. To our knowledge, this is the frst study where near simultaneous spectra covering the whole spectral range of 3800 - 9000 has been studied for over 100 feld Be stars. We, therefore, produce an atlas of emission lines for Be stars which will be a valuable resource for researchers involved in Be star research. We made use of the unprecedented capability of the Gaia mission to re-estimate the extinction parameter (AV ) for these stars. The estimated AV values are used for extinction correction in the analysis of Balmer decrement (D34 and D54) for our program stars. D34 in our sample ranges between 0.1 and 9.0, whereas the corresponding D54 value mostly (and#8776; 70%) ranges between 0.2 and 1.5, clustering somewhere near 0.8 and#8722; 1.0. Our study indicates that Be star discs are generally optically thick in nature in majority of the cases. Through comparative study with the literature, we also noticed that the Hand#945; EW values in Be stars are usually lower than -40 Further from our analysis, it appears that the emission strength of Hand#945;, P14, FeII 5169 and OI 8446 is more in early B-type stars. -
Privacy over instant messaging platforms: are users making the right decisions?
This article explores the impact of perceived vulnerability, self-efficacy, resistance to change, and habit on users perception of privacy over users intention to use messaging platforms. The conceptual model includes perceived vulnerability, self-efficacy, resistance to change, habit, and its impact on users perception of privacy over users intention to use messaging platforms. A structural equation and hierarchical regression model were used for data analysis. The results show that age and profession affect peoples decision of shifting to a different platform significantly. The study is based on a few specific instant messaging platforms at one particular point in time and is undertaken in India; hence, the findings cannot be extended/applicable to other countries. The paper discusses the factors impacting the users sensitivity to data privacy while using a communication application through an electronic device, especially a mobile phone. Copyright 2025 Inderscience Enterprises Ltd. -
Nudging children towards a sustainable toy story
In a world which is under a huge environmental strain, choosing sustainable products can be a significant way to correct the delicate balance. Population explosion and rapid industrialization with low concern about sustainability are affecting our environment faster than anticipated. The present study explores if children can be nudged to choose a sustainable product. A pre-test, post-test experiment design was used to observe the preference of children towards wooden toys and their packaging materials eco-friendliness. An experimental research approach is chosen in the present study, as the main motive for this study is to examine the cause-effect relationships between communications nudge and an increased preference towards wooden toys. The experiment reveals that after gaining knowledge about the benefits of sustainable toys, children preferred wooden toys over the plastic ones. The experiment was conducted on 36 children after taking their parents consent. It was concluded that persuasive communication used as nudge can help children make better choice. 2026 selection and editorial matter, Dipak Saha, Mrinal Kanti Das, Sunil Sahadev, Rabin Mazumder and Soumya Mukherjee; individual chapters, the contributors. -
Novel system for mental health state analysis using machine learning and methods thereof /
Patent Number: 202041044754, Applicant: Prof.Santosh Kumar J.
Systems and methods are provided to understand mental health state of an individual by audio sensors, video sensors and log data of mobile devices. To get more accurate and reliable data machine learning module is also integrated with three input forms of data provided to the system. Once any abnormality is observed, it is reported to the caretakers with a coping strategy to solve the illness at initial stages. -
DNA Data Storage: A Novel Approach to High Density, Long Term Digital Storage
With global data volume expected to reach 175 zettabytes by 2025, existing data storage systems face growing issues due to limited durability, high costs, and susceptibility to data loss. DNA, a naturally occurring biomolecule with extremely high storage density and extraordinary stability, has emerged as a promising alternative for long-term digital data preservation. Major challenges remain, including the high cost of DNA synthesis and the slow rates of encoding and data retrieval. Recent advances in DNA nanotechnology, molecular computation, nanopore sequencing, and hybrid silicon-DNA systems are helping to overcome these difficulties. Sequence-based techniques provide exceptional density, while structural DNA approaches allow for dynamic rewriting and reusability. Ongoing research and innovation indicate that DNA-based storage is becoming more feasible in terms of efficiency, scalability, and cost-effectiveness, making it a plausible contender for meeting future data preservation demands. 2026, TUBITAK. All rights reserved. -
Sentiment analysis in customer relationship management
Modern networking conversations generate annotated metadata, necessitating a method for synthesizing insights from statistics. Emotion detection is crucial for practical conversations, distinguishing joy, grief, and wrath. Corpora are becoming the standard for human-machine interaction, aiming to make interactions feel natural and real. A paradigm that identifies debates and customer views can provide a human touch to these interactions. Researchers developed a machine learning framework for assessing emotions in English phrases, utilizing LSTM (Long Short Term Memory) perspective and real-time emotion recognition in idiomatic speech. Emotion recognition rule (ERR) is created using ontologies like Word Net and Concept Net, Naive Bayes, and Random Forest. Real-time analysis of written words and facial expressions significantly outperforms current algorithms and commandment classifiers in identifying emotional states. 2025, IGI Global Scientific Publishing. All rights reserved. -
The paradox of sex: A thematic analysis of identity among indian cis-gendered female asexuals
Asexuality is the absence of sexual attraction to others or a low desire for sexual activity. In the collectivistic culture of India, the lack of sexual relations after marriage is judged from a lens of "normalcy." Asexuality is often an invisible spectrum among the queer population and usually does not get the desired attention. Individuals who identify as asexuals may not always be opposed to romantic relationships. However, the heteronomative pressures of adhering to approved social roles for romantic partners may affect them. The study aims to understand the different sources of coercion and constraints in romantic relationships experienced by individuals who identify as asexuals through in-depth interviews. The interviews tap into the mental health of asexual women in a heteronormative society. The variables in focus are coping styles, beliefs, self-image, social attitude, and relationship dynamics. The study follows a thematic approach where the emerging themes from the in-depth interviews will be analyzed in detail to form a theoretical framework to explain the heteronormative pressures on asexual women. The findings will be examined from a feminist perspective, considering the equality of all genders and sexual expressions. The findings are also analyzed using Kristeva's concept of abjection, to explore asexuality as an "abject" in a collectivistic society. Asexuality is thus seen as deviant and worthy of separation from "normal sexual expression" in a society that has conflicting opinions about sex and sexuality. Springer Nature Singapore Pte Ltd. 2025. All rights reserved. -
Promoting Emotional Well-being and Mental Health through Student Mentorship During Human Emergencies
The aim of this chapter is to elucidate the factors that are important in maintaining emotional well-being and promoting mental health through student mentorship in higher education in times of a pandemic. The COVID-19 pandemic has prompted academic institutions to go online prompting a profound change in the pedagogical experience of students and their mentors. It has been a challenge to adapt to this new normal for many, and the socially distant lifestyle has procured novel shortcomings. The lack of focus on awareness of mental health and well-being among academic mentors has been proven to be detrimental to the students. The mental health and well-being of mentors are also a matter of concern in the present situation. Spreading awareness about emotional well-being, imparting the knowledge of positive psychology, and psychoeducation of mental health issues among students will facilitate better coping. Motivating mentors to enhance communication and arrange for outreach programmes can be beneficial to their students. The chapter focuses on these pressing needs in the path of pedagogical experience and aims to help mentors, in turn, help themselves and their students by promoting better mental health. 2025 selection and editorial matter, Kennedy Andrew Thomas and Joseph Varghese Kureethara; individuals, the contributors. -
ENHANCING EXECUTIVE FUNCTIONS THROUGH COGNITIVE-BASED INTERVENTION IN INDIVIDUALS WITH SUICIDAL IDEATION AND ATTEMPTS: A Mixed-Method Pilot Study
One of the primary causes of death around the world can be attributed to suicidality. Almost 1 million people across the globe commit suicide annually. Neurocognition has an impact on suicidal ideation, and deficits in cognitive markers influence the progression of suicide-related thoughts to behaviours. The present study aims to determine the efficacy of cognitive-based intervention on executive functions implicated in suicidal ideation and suicide attempters. A mixed-method approach was followed, which involved intervention and a quantitative and qualitative analysis. A group of 22 participants aged between 18 and 25 years with suicidal ideation and behaviour was chosen. Ten participants reported having suicidal ideation and no history of suicide attempt or self-harm, whereas 12 participants reported having suicidal ideation and at least one attempt at self-harm or suicidal behaviour. All the participants were assessed on planning, verbal fluency, and response inhibition tests. The participants then receive eight sessions of cognitive-behavioural intervention focusing on suicidal behaviour and thoughts. Post-therapy, the participants underwent a reassessment of their executive functions. The results suggested that cognitive behaviour-based therapy significantly improved planning, verbal fluency, and response inhibition. The feeling of entrapment and the level of depression were qualitatively found to be influencing suicidal ideation and suicide attempts. The study paves the way for further exploration of factors that predict suicide and determines the cause-and-effect relationship between the factors. 2026 selection and editorial matter, K. Jayasankara Reddy; individual chapters, the contributors. All rights reserved. -
Framework for Sustainable Energy Management using Smart Grid Panels Integrated with Machine Learning and IOT based Approach.
Maintaining a consistent supply of power is essential for the well-being of the economy, the public, and one's own health. The generation of energy, as well as its distribution, monitoring, and management, are all undergoing fundamental changes as a result of the implementation of a smart grid (SG), which is authorised to include communication technology and sensors into power systems. There are a lot of problems that need to be fixed before the interoperability of the smart grid can be determined. The integration of renewable energy sources and smart grid technology market size and energy management is a sustainable solution to the problem of energy demand management. The importance work quickly toward the development of an efficient Energy Management Model (EMM) that integrates smart grids and renewable energy sources. When it comes to the modelling of complex and non-linear data, machine learning (ML), Internet of Things (IoT) approaches often perform better than statistical models. So, utilizing a machine learning approach for the EMM is a good option since it simplifies the EMM by generating a single trained model to anticipate its performance characteristics across all conditions. This may be accomplished via the use of an EMM created using an ML method. It was recommended that a certain flexibility sample be used as a control mechanism for incursion into the smart grid. The outcomes of the experiment indicate that the demand-side management (DSM) device is more resistant to infiltration and is enough to lower the energy usage of the smart grid. 2024, Ismail Saritas. All rights reserved. -
Rice Yield Forecasting in West Bengal Using Hybrid Model
Agriculture in India is the primary source of revenue, yet farmers still face challenges. The primary goal of agricultural development is to produce a high crop yield. The Datasets collected for the study of real-world time series include a blend of linear and nonlinear patterns. A mixture of linear and non - linear models, rather than a single linear or non - linear model, gives a more precise forecasting models for time series data. The ARIMA and ANN prediction models are combined in this paper to create a Hybrid model. This model is used to predict rice yield for all 18 West Bengal districts during the Kharif season, based on 20years of information(20002019) collected from various sources such as India Meteorological Department, Area, and production Statistics, DAV from NASA, etc. The hybrid model aims to enhance efficiency indicators such as MSE, MAE, and MAPE, demonstrating excellent performance for rice yield prediction in all the districts of West Bengal. In the future, it can be applied to other crops that can support farmers in their farming. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Multiple Approaches in Retail Analytics to Augment Revenues
Knowledge is power. The retail sector has been revolutionized around the clock by the plentiful product knowledge available to customers. Today, customers can use the knowledge available online at any time to study, compare and purchase products from anywhere. Retail companies can stay ahead of shopper trends by using retail information analytics to discover and analyze online and in-store shopper patterns. A product recommender will suggest products from a wide selection that would otherwise be very difficult to locate for the customer. The algorithm would recommend various products, increase the sales of items that would otherwise be difficult to sell. Market basket analysis is a common use scenario for the search for frequent patterns, which involves analyzing the transactional data of a retail store to decide which items are bought together. To do so data from online resource has been taken, which is analyzed and several conclusions were made. 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Capturing customers spirit in the digital era
The chapter discusses the concepts of customer engagement in the digital era, more specifically focusing on emotional branding, convergence of physical and digital touchpoints for marketing, and the elements of technology. It explains in detail the processes of how brands are able to emotionally connect with their target audience, how they are able to use the data collected in a legal manner, and how they can provide a more engaging and personalized experience. By assessing consumer behavior patterns and trends in technology, the chapter provides useful insights on how brands can go after the soul of their consumers in a more and more online world. 2025, IGI Global Scientific Publishing. -
A STUDY ON CONJUGACY GRAPHS
In this paper, we introduce the notion of an equivalence graph based on equivalence relation defined on a group. Furthermore, restricting ourselves to conjugacy relation, a special type of equivalence graph called a conjugacy graph is also defined. In addition, a graph theoretical expression for the class equation is established followed by related results. 2025, RAMANUJAN SOCIETY OF MATHEMATICS AND MATHEMATICAL SCIENCES. All rights reserved. -
ON L(2, 1)-ORDER SUM SIGNED GRAPH OF A FINITE GROUP
In this paper, we have constructed a color-induced signed graph of an algebraic graph, called the L(2, 1)-order sum signed graph of a group. Based on the nature of the group, the L(2, 1)-span of the order sum graph is obtained and the structural aspects of thus obtained L(2, 1)-order sum signed graph such as planarity, chordality, etc. have been investigated. We have also defined an automorphism which turns out to be the only possible automorphism on the graph and have investigated the structural aspects of the graph such as edge transitivity and vertex transitivity. Further, a line-signed graph of L(2, 1)-order sum signed graph, which is a line graph with a signing protocol defined for the edges, has also been introduced. We have also explored the regularity of the line-signed graph. 2025 Sciendo. All rights reserved. -
Fraud detection in the era of AI: Harnessing technology for a safer digital economy
Fraudulent activities have increased along with the new prospects of the digital economy's quick growth for both consumers and enterprises. Conventional techniques of fraud detection are insufficient to keep up with these ever-evolving fraudulent strategies. In this sense, machine learning (ML) and artificial intelligence (AI) have become potent instruments to prevent and detect fraud and guarantee the safety of online transactions. This study examines the function of AI and ML and shows how these technologies can spot irregularities and intricate patterns that would be challenging to find with conventional methods. The study includes various methods of AI-based fraud detection and analyses important ethical issues related to these practices. Furthermore, the study looks at developing technology and trends that will probably influence fraud detection in the future. In conclusion, the revolutionary potential of AI and ML in building a safer digital economy is analysed. 2024, IGI Global. All rights reserved. -
From bean to brain: Coffee, gray matter, and neuroprotection in neurological disorders spectrum
Coffee is a popular drink enjoyed around the world, and scientists are very interested in studying how it affects the human brain. This chapter looks at lots of different studies to understand how drinking coffee might change the brain and help protect it from neurodegenerative disorders especially like schizophrenia. With the help of available literature a link between the coffee mechanism and neurodegenerative disorders is established in this chapter. Researchers have found that drinking coffee can change the size of certain parts of the brain that control things like thinking and mood. Scientists also study how coffee's ingredients, especially caffeine, can change how the brain works. They think these changes could help protect the brain from diseases. This chapter focuses on how coffee might affect people with schizophrenia as hallucination is caused during and after excess consumption of caffeine. There's still a lot we don't know, but researchers are learning more by studying how different people's brains respond to coffee over time. Overall, this chapter shows that studying coffee and the brain could lead to new ways to help people with brain disorders. This study also draws ideas for future research and ways to help people stay healthy. 2024 Elsevier B.V. -
The Transparency Paradox: Rebuilding Trust in AI Shopping Agents Through Explainability
AI shopping agent systems that search, compare, negotiate, and purchase on a consumers behalf promise to reduce friction in digital commerce, but they also intensify long-standing concerns about price discrimination, manipulative choice architecture, and opaque data use. This chapter argues that the resulting transparency paradox is not merely a communication problem: the same AI capabilities that enable personalization can also conceal and optimize exploitation. Building on research in trust, explainable artificial intelligence, humanAI interaction, and consumer protection, the chapter develops a socio-technical approach to rebuilding trust in agentic commerce. It synthesizes regulatory and standards developments and proposes design and governance mechanisms layered explanations, contestable outcomes, auditability, and choice-integrity controls intended to make AI shopping agents intelligible and accountable across jurisdictions and market contexts. Copyright 2026, IGI Global Scientific Publishing. -
Nature-inspired Metaheuristic Algorithms: Solving Real World Engineering Problems
This comprehensive text provides practical guidance for implementing nature-inspired algorithms and metaheuristics in real-life scenarios to solve complex optimization problems. It further demonstrates how nature inspired metaheuristic algorithms have the potential to contribute to multiple United Nations sustainable development goals such as climate action, clean energy, and sustainable cities. This book: Discusses load balancing and demand response using nature-inspired optimization techniques Presents energy-efficient routing and scheduling, energy management, and optimization using metaheuristic algorithms Covers disease diagnosis, and prognosis using metaheuristic algorithms, drug discovery, and development using nature-inspired optimization techniques Explains waste reduction and recycling, image processing, and computer vision using nature-inspired optimization techniques Illustrates medical image analysis and segmentation using Ant Colony optimization, and Particle Swarm optimization techniques Nature-inspired Metaheuristic Algorithms is primarily written for senior undergraduates, graduate students, and academic researchers in the fields of electrical engineering, electronics and communication engineering, computer engineering, and information technology. 2025 selection and editorial matter, Sulabh Bansal, Aprna Tripathi, Shilpa Srivastava and Prem Prakash Vuppuluri; individual chapters, the contributors.