- Conference Article
- 10.1109/ic3it66137.2025.11341346
Hybrid CNN-LSTM Model for EEG-Based Emotion Recognition: A Comparative Analysis Using DEAP and SEED Datasets
- Oct 24, 2025
- Alekh Choudhary + 5 more +5
Publications from 2021 to 2026
Showing 10 of 30 papers
Hybrid CNN-LSTM Model for EEG-Based Emotion Recognition: A Comparative Analysis Using DEAP and SEED Datasets
Work after work-unpacking the complexity of moonlighting through a bibliometric and TCCM lens
Purpose This study aims to investigate the evolving phenomenon of employee moonlighting, particularly in the post-pandemic era, with the objective of identifying key research themes, theoretical underpinnings and future directions in the field of human resource management. Design/methodology/approach A bibliometric analysis was conducted on 68 peer-reviewed papers sourced from the Scopus database (1975–2025). Tools such as VOSviewer and Biblioshiny were used to map publication trends, co-authorship networks and keyword co-occurrence patterns. Additionally, the theory-context-characteristics-methodology (TCCM) framework was applied to categorise and critically assess the literature. Findings The analysis revealed four distinct research clusters: organisational and institutional dimensions, core conceptual themes, psychological and behavioural aspects and socioeconomic contexts. Theoretical insights were primarily grounded in social exchange theory and the attitudes and alternatives model, explaining moonlighting behaviour through lenses of reciprocity, dissatisfaction and alternative career strategies. The findings also demonstrate the fragmented nature of current research, signalling a need for more integrated and industry-specific studies. Originality/value This paper offers a comprehensive synthesis of literature on moonlighting by combining bibliometric techniques with a structured thematic framework. To the best of the authors’ knowledge, this is the first study to systematically map the intellectual and thematic structure of moonlighting literature using a combined bibliometric and TCCM framework within the HRM context. It provides a unique contribution by mapping intellectual foundations, highlighting underexplored areas and proposing a forward-looking research agenda. The study also offers actionable insights for HR managers to manage moonlighting through proactive policy and engagement strategies.
Read moreComparative and Systematic Review of Technical Analysis-Based Forecasting Techniques: Global V/S Indian Perspectives
This paper conducts a systematic review of Technical Analysis (TA) based forecasting research from 2013 to 2022, encompassing global and Indian authors. It addresses the evolving landscape of financial forecasting, including tool choices, variable selection, error measurement, and accuracy. Employing the PRISMA framework, we analyze 176 papers (88 global, 88 Indian) to examine trends in TA research. Key inquiries involve the publication trends, popular forecasting approaches, consideration of Transaction Costs and Data Snooping Bias, research time cycles, outcomes, and performance metrics. The study reveals that Indian researchers favor TA-based machine learning (ML) techniques, while global counterparts rely more on manual forecasting methods. Notably, many studies neglect to incorporate ‘transaction costs’ and ‘data snooping bias’ in their models. Most research focuses on forecasting within a 5–10-year timeframe, with TA-based techniques generally viewed as profitable. However, Indian authors tend to prioritize risk mitigation in their models, in contrast to global authors who often measure performance through return and profitability metrics. Additionally, this paper critiques the prevailing forecasting techniques, highlighting gaps in both global and Indian research. Its aim is to aid future researchers in identifying gaps, formulating research questions, and understanding methodological considerations within financial forecasting.
Read moreDeep Learning Approaches to Predict Student Success in English Language Learning
Predicting student achievement in English language learning has traditionally relied on standardized tests and trainer opinions. While these methods provide precious insights, they often fail to capture nuanced components of language talent and character gaining knowledge of desires. Existing techniques commonly contain static checks that don't adapt to the evolving nature of scholar overall performance or provide personalized feedback. This study proposes a singular approach utilizing GPT-3 (Generative Pre-skilled Transformer) models to enhance the prediction of scholar fulfillment in English language learning. GPT-3 models, regarded for their superior natural language processing skills, provide a dynamic and personalized evaluation of scholar texts. Unlike traditional methods, GPT-three can compare complex language capabilities, including grammar, vocabulary utilization, and coherence, and generate tailored remarks that addresses precise areas of development. The methodology entails amassing a various dataset of scholar-written texts and engagement metrics. These data are preprocessed and used to high-quality-song a GPT-three version, allowing it to assess language talent and predict destiny performance. The satisfactory-tuned version analyzes student submissions, generates personalized feedback, and predicts fulfillment primarily based on found styles and contextual know-how. Results exhibit that the GPT-3 based approach substantially improves the accuracy of fulfillment predictions and offers greater actionable feedback as compared to conventional methods. The version’s potential to generate real-time, contextually relevant remarks complements the gaining knowledge of revel in by using addressing man or woman wishes and adapting to student progress.
Read moreThe Impact of AI on Healthcare Jobs: Will Automation Replace Doctors
The integration of artificial intelligence (AI) into healthcare has sparked considerable debate regarding its impact on the workforce, particularly concerning the roles of healthcare professionals such as doctors. This article explores the potential for AI-driven automation to replace certain medical tasks traditionally performed by physicians, as well as the broader implications for employment in the healthcare sector. While AI has demonstrated significant capabilities in areas like diagnostics, data analysis, and even surgical assistance, its role is largely seen as complementary rather than substitutive. Many experts argue that AI will enhance the efficiency and accuracy of medical practices rather than eliminate the need for human doctors. Moreover, the implementation of AI in healthcare is expected to create new roles focused on managing, interpreting, and improving AI systems, thereby shifting the nature of healthcare jobs rather than reducing their number. However, concerns about the potential for job displacement and the need for reskilling within the medical profession remain. This article concludes that while AI will inevitably alter the landscape of healthcare employment, it is unlikely to replace doctors entirely. Instead, it will transform the profession, requiring a new set of skills and a reimagining of the doctor-patient relationship.
Read moreExplainable AI in NLP: Interpretable Models for Transparent Decision Making
In the realm of Natural Language Processing NLP, the (XAI) initiative aims to build interpretable models that provide light on decision-making procedures. A challenge in this field is the development of models that not only perform admirably but also explain their reasoning behind certain forecasts or assessments. The problem arises from the fact that top-notch models are required. s for this kind of study often include topics like feature visualisation, attention processes, and model-agnostic techniques like LIME. Many believe that these approaches will make NLP models easier to understand and work with. Users may have trust in and understanding of the outcomes thanks to XAI in natural language processing, which explains how these models function. This facilitates the incorporation of these models into real-world applications that prioritise openness and interpretability, while also promoting accountability. The study compares the accuracy and error rates of traditional and proposed treatments. The proposed model reduces processing time and time taken for training, while the previous approach was prolonged by unfiltered data. The study also compares the time taken for the proposed approach and the time taken for the conventional approach. The results show that the proposed approach is more efficient and time-efficient than traditional treatments, resulting in better results.
Read moreLaw and Emerging Issues
The scientific publication analyses the interdisciplinary concept of corporate governance, thereby illuminating different aspects of this phenomenon.Three interconnected aspects are observed: corporate governance as a management category, its social context and its legal implications.Examining each component in isolation from the others serves to limit the corporation's functionality to its applied value in the social arena.An assessment of corporate governance as behavioural models, considering representation, efficiency, growth, financial structure and attitude toward stakeholders, enables the depersonalisation of organisational unity, a defining characteristic of any legal entity.Through an interdisciplinary approach, we demonstrate how corporate management functions to organise a corporation's activities by influencing the subjects of management in microeconomic processes and their interaction with one another, ultimately ensuring optimal socioeconomic viability of the corporation within the macroeconomic environment.
Read moreRole of Artificial Intelligence and Robotics in Shaping the Students: A Higher Educational Perspective
An unprecedented shift in technology has begun in the modern era. Robotics and artificial intelligence (AI) advancements have created fresh positions while de-skilling or retraining many existing ones. Technical developments at higher education institutions (HEIs) protect students against potential changes in their field of study brought on by A) and prepare them for success in the workplace. This research aims to investigate how, over the past 150 years; globalization has fundamentally changed human civilization. Conventional education confronts enormous challenges as energy, the internet of things, and the cyber-physical systems they oversee diminish. One may argue that energy, the internet of things, and the cyber-physical systems that are under its jurisdiction are the foundations of all future education. The demise of these systems presents a significant threat to traditional schooling. Students' screen time is increased by this action, which has an impact on their mental health. Five-fold cross-validation with 210 students from Delhi NCR and abroad is beneficial for the classification techniques SVM, Naive Bayes, and Random Forest. The study examined the factors that contributed to an increased rate of mental health issues among undergraduate students in Delhi, India, following the introduction of the COVID-19 virus. The results have demonstrated that while technology’s practical applications will likely have a positive influence on education in the future, there may be negative effects as well. This is an opportunity for educators and learners to support excellence and remove obstacles that prevent many kids and schools from achieving it. Therefore, in the future, every nation will need to create an education system that is more technologically sophisticated.
Read moreA Systematic Review of Technical Analysis-Based Forecasting Techniques: Global v/s Indian Perspectives
This paper conducts a systematic review of Technical Analysis (TA) based forecasting research from 2013 to 2022, encompassing global and Indian authors. It addresses the evolving landscape of financial forecasting, including tool choices, variable selection, error measurement, and accuracy. Employing the PRISMA framework, we analyze 176 papers (88 global, 88 Indian) to examine trends in TA research. Key inquiries involve the publication trends, popular forecasting approaches, consideration of Transaction Costs and Data Snooping Bias, research time cycles, outcomes, and performance metrics. The study reveals that Indian researchers favor TAbased machine learning (ML) techniques, while global counterparts rely more on manual forecasting methods. Notably, many studies neglect to incorporate 'transaction costs' and 'data snooping bias' in their models. Most research focuses on forecasting within a 5-10-year timeframe, with TA-based techniques generally viewed as profitable. However, Indian authors tend to prioritize risk mitigation in their models, in contrast to global authors who often measure performance through return and profitability metrics. Additionally, this paper critiques the prevailing forecasting techniques, highlighting gaps in both global and Indian research. Its aim is to aid future researchers in identifying gaps, formulating research questions, and understanding methodological considerations within financial forecasting.
Read moreEducational Aspirations as The Predictors of Teacher Engagement in Classroom in Context of Emotional Intelligence of Teachers
In the intricate network of factors that influence teacher engagement within the classroom, educational aspirations stand as potential critical predictors. These aspirations, which could be defined as the goals and objectives set by educational institutions or by the teachers themselves, could serve as a guiding force, steering the level and quality of engagement teachers display in the class. This essay explores the hypothesis that educational aspirations could indeed be potent predictors of teacher engagement, delineating the pathways through which aspirations mold teachers' dedication, enthusiasm, and proactive involvement in the educational process. Initially, it is fundamental to understand that educational aspirations are a two-pronged entity - encompassing the macro-level aspirations set forth by educational boards and policies, and the micro-level aspirations nurtured by individual teachers for their personal growth and the academic progression of their students. These aspirations, when clearly articulated and aligned, can act as a catalyst, propelling teachers towards higher levels of engagement in class. From one perspective, aspirations can foster engagement by instilling a sense of purpose and direction. When teachers are driven by well-defined goals - be it enhancing student literacy levels, fostering critical thinking skills, or nurturing holistic development - their engagement in class is naturally heightened. They are more likely to invest time and effort in devising innovative teaching strategies, engaging in continuous learning, and fostering an environment that is conducive to achieving these aspirations. Furthermore, educational aspirations often encapsulate the ideals of inclusive and equitable education. Teachers working towards these aspirations are likely to be more engaged, as they strive to create classrooms where every student is given an opportunity to thrive. This inclusive approach not only fosters positive student outcomes but also enriches the teacher's experience, as they find fulfillment and satisfaction in witnessing the growth and development of their students. Moreover, educational aspirations can foster a collaborative spirit among teachers. As they work towards common goals, there is an enhanced sense of community and collaboration.
Read more