Biography

is a senior academician in Mathematics with over 15 years of experience. She holds a Ph.D. in Applied Mathematics. She has published several research papers. She has guided student projects. Her research interests include numerical methods and optimization techniques. She actively participates in academic activities. She contributes to curriculum development. She is a member of professional bodies. She has received awards for teaching excellence. She mentors students in research and problem-solving. She is committed to academic and research excellence.The subsequent structure of the paper is outlined as follows. Section 2 addressed pertinent research within our field of interest and included a summary of the higher education system. Section 3 presented the CNN-LSTM framework, which will execute the proposed technique. Section 4 presents the experimental data and a comparison of the approaches. Our conclusions and recommendations for future research are presented in section 5, the final section of this report. II. LITERATURE SURVEY The phenomenon of student-teacher relationships in university environments has often been analyzed through the concept of teacher immediacy defined as the extent to which the teacher signals of warmth friendliness and affection. In order to maximize the model's congruence with the input data DL approaches use multi-neuron architectures to carry out learning tasks with neurons connected to the data via a loss function that allows for weight updates [6]. In RL agents interact with their environment in a trial-and-error fashion to maximize cumulative rewards all without the need for labeled data. This framework allows for experience-based autonomous learning. Methods like policy search and approximating value functions are the backbone of RL. In order to better manage and develop data two tools that analyze and interpret data were created: AI and ML. Many industries including education have recognized the trend of integrating these processes into company as having the potential to revolutionize their operations [7]. Higher education institutions and online education can thus greatly benefit from the application of AI and ML. Explore the role DL as a mediator between student-centered teaching methods and the enhancement of students' theoretical and practical skills. It developed a competency-based assessment instrument for classrooms by DL combining exploratory confirmatory and reliability analyses [8]. Students' use of DL techniques and self-reported ability improvement were both positively predicted by student-centered teaching in large classes and DL mediated the relationship. With the development of ML methods some studies have evaluated learning system usage prediction models using a hybrid strategy that combines ML with more conventional SEM. Based on students' real-world tasks in information management one study by used their self reported data to predict their behavior in regard to educational mobile cloud computing [9]. Through the integration of ML methods with a conventional SEM. Innovations in data science as a discipline, big data for large-scale analysis, and state-of-the-art methods and technologies such as AI, NN, DL and ML have paved the way for new approaches to quantitative knowledge production and decision-making complementing traditional statistical methods [10]. The goal of this study is to take a look at how different assessment and evaluation methods that leverage AI can improve educational outcomes. A major goal of this research was to compile a list of the most widely utilized AI and ML algorithms for enhancing students' academic performance. It compared FCN to its rivals using ANN, XG Boost, SVM, RF and DT as performance indicators. The FCN consistently produced better performance [11]. The results of the comparative analysis study can help school administrator’s principals and teachers better understand how to incorporate data into their practice develop less DL assessments that are still valid reliable and constructive and discover new ways to use assessment and feedback to Adaboost students' learning [12]. This research introduces an innovative DL architecture that integrates LSTM networks with CNNs to address the issues associated with Teachers and Students Activities. This approach applies a CNN preprocessing step to convert raw data into multidimensional inputs in an effort to improve LSTM's prediction performance. Datasets pertaining to students' academic performance proved that this hybrid model was effective, showing that it outperformed conventional prediction approaches and independent CNN and LSTM models. PROPOSED SYSTEM III. According to studies in education, creating a positive classroom climate for learning depends on students and teachers developing a strong relationship. Educators and politicians must scrutinise college classroom methods and rules regarding teaching and learning in university environments, considering the disparities in student outcomes. Colleges draw a varied student population and yield varying outcomes, underscoring the necessity for more dynamic pedagogical approaches in higher education.