Browse Items (16488 total)
Sort by:
-
Interpretable Breast Cancer Risk Stratification Using Statistical Feature Engineering on Thermal Images
This research solves the black box problem of AI implementation in imaging by introducing a transparent, statistically grounded approach to breast cancer risk stratification via infrared thermography without compromising performance. Using the public DMR-IR dataset, statistical feature engineering was applied to training data by extracting first- and second-order statistical features. After ensuring non-normality with a Shapiro-Wilk test, feature significance was established with the Mann-Whitney U test. LASSO regularization selected the five most predictive features: mean, standard deviation, kurtosis, correlation, and energy. To counteract class imbalance, SMOTE was applied, and two machine learning modelslogistic regression and random forest (classifier)were trained on the balanced data and then evaluated on an unseen test dataset. Reporting an AUC of 0.98 over logistic regressions 0.96 reflects stringent statistical feature engineering and great generalization, creating a strong and interpretable model for breast cancer diagnosis in thermal images, and instills more clinical confidence in AI-based diagnostic systems. The Author(s), under exclusive license to Springer Nature Switzerland AG 2026. -
Interpretable Deep Learning for Multiclass Psychological Disorder Classification Using CNN and TCAV Using fMRI
In this paper a 3D convolutional neural network model is presented that has been improved with squeeze-and-excitation blocks and residual blocks to categorize functional MRI data across healthy controls, schizophrenia, and attention deficit hyperactivity disorder classes. A post hoc explainability framework was applied to concept activation vectors based on mean activation for each class and testing using TCAV. The merging of CAV and TCAV for fMRI data was to improve transparency by providing an interpretable model. This helps in understanding the prediction sensitivity of the models. Concept vectors are defined through the extraction and analysis of intermediate activations from the CNN-SE model. These vectors are then used to calculate the TCAV scores, which indicate the degree to which each brain region influences the model output. The precision of the deep learning model was up to 79%. Similarity matrices indicate the degree of overlap and correlate with the model's results. Visualizations such as activation heat maps and glass brain overlays based on the AAL atlas further support the interpretability of the model, making it more transparent and suitable for clinical applications. Variations in activation between classes can be observed using a visual feature plot. This framework allows mapping model predictions to interpretable neuroanatomical regions and identifies classspecific dependencies on particular brain networks. 2025 IEEE. -
Interpreting Scope of Predictive Analytics in Advanced Driving Assistant System
Distracted driving, caused by various factors such as human emotions or reading distracting messages on the roadside, has become a leading cause of traffic accidents today. Ensuring the safety of both individuals and vehicles while minimizing maintenance costs poses a significant challenge for the automotive industry. Fortunately, recent advancements in machine learning offer a potential solution. One promising method is the further development of Advanced Driver Assistance Systems (ADAS), for which machine learning serves as an ideal solution. The proposed model develops an advanced predictive learning enabled driving assistance system with prediction capabilities like traffic light behavior and parking availability detection. The model gave an optimum accuracy of 98.2% with 50 epochs count and the validation loss retains a constant value of 0.3 over epochs. 2023 IEEE. -
Interpreting the Evidence on Life Cycle to Improve Educational Outcomes of Students Based on Generalized ARC-GRU Approach
Research on the effects of teachers' fatigue on students' learning has been significantly less common than research on the effects of teachers' fatigue on teachers' own performance. Therefore, the purpose of this research is to see if teachers' emotional weariness has any bearing on their students' performance in the classroom. Consideration is given to a student's grades and their impressions of whether or not the system receive assistance from teachers, as well as to the student's general outlook on school, confidence in their own abilities, and faith in the availability of faculty support. Data preparation, feature extraction, and model training are the first steps in the proposed approach. Indicators of the quality of the education being provided are eliminated (by outlier removal and feature scaling). k-mean clustering approach is a technique of clustering which is commonly used in feature extraction. Following feature extraction, GARCH-GRU models are trained. The proposed approach is superior to two popular alternatives, ARCH and GRU. Using the provided method, the system were able to achieve a maximum accuracy of 97.07%. 2024 IEEE. -
Interrogating Populist Tendencies within the Left Rhetoric in Kerala
After the disintegration of the Soviet Union, there has been an increasing shift from class-based politics to politics based on mobilising "people" within the left-wing political praxis and rhetoric. Such tendencies are visible even within the left rhetoric in Kerala. In the particular context of Kerala, this process is enmeshed with sub-nationalist sentiments and concerns around vikasanam (development). It is possible that this tendency can metamorphose into different directions, depending on the tactical priorities of the left in Kerala. 2022 Economic and Political Weekly. All rights reserved. -
Intersecting Barriers: Gender, Religion and the Political Under-representation of Muslim Women in Local Governance in Bihar
Womens reservation policies have substantially expanded female political participation in India, yet the representation of Muslim women continues to remain disproportionately low across levels of governance. Drawing on detailed administrative data from the 2016 and 2021 Panchayat elections in Bihar, this study examines the institutional, structural and behavioural mechanisms that shape Muslim womens political inclusion. Using a supply-side framework, the analysis formalizes two key determinants of contest entry, past co-ethnic competitiveness and demographic potential, and shows how these factors jointly influence womens decisions to contest elections. The results highlight the central role of institutional design and strategic expectations in shaping minority womens political agency, even in communities where demographic conditions appear favourable for political representation. 2026 Lokniti, Centre For The Study Of Developing Societies -
Intersecting Ecocriticism and Gender in Selected Writings of Easterine Kire
The research study, Intersecting Ecocriticism and Gender in Selected newlineWritings of Easterine Kire, analyses the intersection of histories, identities, gender, and ecology to understand the larger context of marginalisation and newlinerepresentation. Indigenous literature often subverts Western worldviews and mainstream discourses with counter-discourse narratives by placing their stories at the centre. In recent times, literature from Indigenous societies has established a position in which Indigenous people represent, resist, newlinedecolonise, and construct their identity. The Indigenous Naga community has experienced marginalisation for decades, having suffered multiple oppressions of their history, stories, knowledge, and lack of rights; however, contemporary literary writings challenged the silencing system through writing back and representation. In her fictional works, Naga author Easterine Kire explores the possibilities of reviving and restoring the Angami Naga community and their newlinelost cultures and identities. Focusing on analysing three important themes: Peoplestories, Ecopolitics, and Gender politics, the study represents Naga histories, emerging identities, gender, and ecological concerns as interpreted in the fiction of Easterine Kire. The objective is to represent Indigenous Naga voices using fictional narratives of Easterine Kire to reclaim, revive, and redefine Indigenous culture and history from an insider s perspective. It also examines how intersecting narratives contribute to the larger context of Naga identity construction. newlineEasterine Kire s writing is a culturally conscious and decolonial strategy in newlinewhich she incorporates her community s oral tradition and storytelling in her fictional narratives. Easterine Kire s narrative engages in a deep conscious cultural revival and reinvention of her community s cultural heritage. -
Intersecting queer rights and legislative theatre in India: advocacy narrative of power, justice and expression
Queer activism and Legislative Theatre (LT) converge in myriad ways at their intersection, influencing and shaping each other. The present work investigates how LT can help to identify queer marginalisation in the fissured legal paradigm of India. It explores how LT can address the hegemonic silencing of the queer from an advocacy perspective. Our conviction is that the LT challenges the entrenched power structures against a queer-inclusive democratic space, offers a blueprint to advance queer dialogue, and coalition-building for legislation and policy discussions. It is the time when such a potent artistic activism must shape the public discourse. 2025 Informa UK Limited, trading as Taylor & Francis Group. -
Intersection of AI and business intelligence in data-driven decision-making
In today's rapidly evolving business landscape, organizations are inundated with vast amounts of data, making it increasingly challenging to extract meaningful insights and make informed decisions. The traditional business intelligence (BI) approach must often address the complexity and speed required for effective decision-making in this data-rich environment. As a result, many businesses need help to leverage their data to drive sustainable growth and remain competitive. Intersection of AI and Business Intelligence in Data-Driven Decision-Making presents a transformative solution to this pressing challenge. By exploring the convergence of artificial intelligence (AI) and BI, our book provides a comprehensive framework for leveraging AI-powered BI to revolutionize data analysis, predictive modeling, and decision-making processes. Readers will gain valuable insights into practical applications, emerging trends, and ethical considerations, inspiring and exciting them about the potential of AI in driving business success. Through in-depth discussions, case studies, and best practices, this book equips professionals, researchers, and students with the knowledge and tools needed to navigate the complexities of AI-powered business intelligence. Whether you're looking to predict trends, analyze consumer behavior, or optimize supply chains, this book offers actionable strategies and techniques for implementing AI-powered BI solutions in your organization. 2024 by IGI Global. All rights reserved. -
Interval-Valued Fuzzy Trees and Cycles
Interval-valued fuzzy tree (IVFT) and interval-valued fuzzy cycle (IVFC) are defined in this chapter. We characterize interval-valued fuzzy trees. We also prove that if G is an IVFG whose underlying crisp graph is not a tree then G is an IVFT if and only if G contains only ? strong arcs and weak arcs. It is shown that an IVFG G whose underlying crisp graph is a cycle is an IVFC if and only if G has at least two ? strong arcs. 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. -
Interventions for the improvement of social skills in autism spectrum disorder in India: A systematic review
Background: The increasing prevalence of Autism Spectrum Disorders (ASD) in India is in a gaping contrast with the existing interventions in India. Though several interventions have proved their efficiency in foreign countries, such studies within India are scarce. Aims: This review attempts to systematically examine the different intervention practices that include improvement of social skills in ASD that is practiced in India as revealed through published literature on the same. Methods: Studies published from 2000 to 2020 were selected for the study. Evidence is presented for nine treatment categories: Behavior-based interventions, Developmental Interventions, TEACHH approach, Parent-mediated Interventions, speech-based Interventions, electronics-based interventions, augmentative and alternative communication, play-based interventions and Yoga-based interventions. These studies were drawn from databases Ebsco, Proquest, PubMed, MEDLINE, science direct and Google Scholar. Though a definitive conclusion cannot be drawn without a meta-analysis, the available evidence is gathered and evaluated in the present review. Results: The review has proved to be a reliable summary of the interventions that include improvement of social skills in ASD that is practiced in India. Conclusions: Parent-mediated interventions may be more appropriate for the resource-poor settings of India, when developmental interventions may be more appropriate for the resourcerich settings of India. The scarcity of published literature on the topic in India is also a significant factor that highlighted itself through the research. 2021, Indian Association for Child and Adolescent Mental Health. All rights reserved. -
Interventions to help students find a deeper purpose during their academic journey
This comprehensive exploration delves deeply into academic interventions aimed at guiding students toward a more profound sense of purpose throughout their educational journeys. It emphasizes that education offers a unique opportunity for students to discover their passions, interests, and aspirations beyond textbooks and exams. The interventions discussed, including mentorship, career counseling, experiential learning, and self-discovery exercises, are meticulously designed to empower students to recognize their distinct strengths and interests. These interventions not only aim to facilitate academic excellence but also enable students to pursue careers aligned with their core values and aspirations. The exploration scrutinizes effective strategies, programs, and support mechanisms, addressing challenges students face when making career choices, and culminates in recommendations for educators, career counselors, and policymakers interested in enriching students' educational experiences and fostering purpose-driven learners. 2024, IGI Global. -
Into the Dark World of User Experience: A Cognitive Walkthrough Study
In this age of AI, the unison of man and machine is going to be more prominent than ever, thus creating a need to understand the underlying framework that is adopted by app designers and developers from a psychological point of view. Research on the various benefits and harmful effects of user experience design and furthermore developing interventions and regulations to moderate the use of dark strategies in digital tools is the need of the hour. This paper calls for an ethical consideration of designing the experience of users by looking at the unethical practices that exist currently. The purpose of the study was to understand the cognitive, behavioural and affective experience of dark patterns in end users. There is a scarcity in the scientific literature with regard to dark patterns. This paper adopts the methodology of user cognitive walkthrough with 6 participants whose transcripts were analysed using thematic network analyses. The results are presented in the form of a thematic network. A few examples of the themes found are the experience of manipulation in users, rebellious attitudes, and automatic or habitual responses. These findings provide a basis for an in-depth understanding of dark patterns in user experience and provide themes that will help future researchers and designers develop ethical and more enriching user experiences for users. 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG. -
Intricate Plane of Adversarial Attacks in Sustainable Territory and the Perils faced Machine Intelligent Models
The issue of model security and reliability in Artificial Intelligence (AI) is a concern due to adversarial attacks. In order to tackle this issue, researchers have developed sustainable defense strategies, but certain challenges remain. These challenges involve transferability, higher computing costs, and adaptability. Striking a balance between accuracy and robustness is difficult, as defense mechanisms often come with trade-offs between the two. Real-world situations demonstrate the practical implications of sustainable adversarial AI. For example, it improves the security of self-driving vehicles, enhances the accuracy of medical imaging diagnoses, and incorporates AI-driven defenses into network intrusion detection and phishing detection systems. It is crucial to consider ethical aspects throughout this process. Future trends in adversarial AI research for cybersecurity will involve ensemble defense mechanisms, adversarial learning from limited data, and hybrid attacks. By embracing the evolving landscape, researchers and practitioners can develop sustainable AI systems that are more secure and resilient, effectively countering adversarial threats. 2023 IEEE. -
Intrinsic betterness and reason based extrinsic preference towards social shopping: A study among college students in Bangalore
The main purpose of this study is to analyze the Intrinsic and Extrinsic factors and its impact on the social shopping of student community in the city of Bangalore. Bangalore is one of the most popular cities in the down south. This city attracts a mix of various cultures from various countries of the world. Thus, this city and population would be apt to study the social shopping pattern considering the Intrinsic and Extrinsic factors. The data was collected from the student community, perusing their college education in the city of Bangalore. Using convenient sampling method, a sample size of 225 was drawn from educational institutions in the city of Bangalore. The research work makes use of both first hand and second-hand data. The reliability of the data is acceptable as the Cronbach's alphas value is more than. 6. The drafted questionnaire was subjected to expert opinion before the data collection process. The study results make it clear that both intrinsic and extrinsic values motivate the consumers to get involved in the social shopping. But comparatively consumers are more influenced by those factors present in the external environment. It can be concluded by saying that, youngsters are quite smart before putting themselves into the purchase behavior, as they are in a group of friends, they get influenced by various experiences and comments shared by many. In a way social shopping is better, as too many minds generate ideas for a single purchase. 2018 Transilvanian Association for the Literarure and Culture of Romanian People (ASTRA). All rights reserved. -
Introduction
[No abstract available] -
Introduction
[No abstract available] -
Introduction
In the digital era, signal processing has found application in daily life from medical diagnosis to social networking. The digital domain has evolved as the preferred choice in communication system design due to its advantages over analog systems, such as high-speed transmission, improved quality, and effortless copying with high precision. The advancement of digital media brings new opportunities. The internet boom of this millennium has allowed digital data to move around the world in real time. Efficient segmentation, recognition, and analysis of multidimensional data such as hyperspectral images, medical imaging, data analysis in social media, and audio signals are still challenging issues. Digital data produced through data-processing algorithms has the fundamental advantages of transportability, proficiency, and accuracy of information content; but such data is also at significant risk because perfect illegal replicas can be made in unlimited numbers. 2021 John Wiley & Sons Ltd. -
INTRODUCTION
World politics in the twenty-first century represents a complex arena characterised by a diversity of paradigms. These paradigms entail a dynamic interplay of conventional and newer ways of engagement. Today, the globalising world witnesses newer imaginations of space and interactions where state actors continue to enjoy a preeminent status, adopting policies based on imaginations of space in terms of connectivity and gateways while maintaining their territorial integrity. They devise a whole array of mechanisms to define, redefine and secure their interests as well as elevate their aspirations of assuming newer responsibilities and bigger roles. What we witness today is dynamic endeavours by the states to hold on to and amplify their traditional roles and carving out newer contours of forging and consolidating relationships in the global framework of international relations. This also leads to the construction of new geo-strategic and economic hotspots. This complex interplay of the traditional and the newer interactions creates both synergies and discord. The Indo-Pacific represents such a hotspot in contemporary world politics, and Indias engagement with Southeast Asia is a significant area of interest therein. 2024 Taylor & Francis. -
INTRODUCTION
The twenty-first century has been witnessing a global federal resurgence, distinguished by conversations focusing on interdependencies, multiculturalism, overlapping jurisdictions, multilateralism, multiple centres of policy-making and multiple notions of citizenship. Any assessment of cooperative federalism needs to go beyond institutional structures by incorporating images of diversity, pluralism, identity, issues of empowerment and democratization. Cooperative federalism facilitates cooperation among the national, state and local governments. It perceives the federation and the states as complementary parts of an arrangement where sovereignty is shared. 2024 selection and editorial matter, M.J. Vinod, Stefy V Joseph, Joseph Chacko Chennatuserry and Dimitris N. Chryssochoou; individual chapters, the contributors.