http://10.9.150.37:8080/dspace//handle/atmiyauni/2056 2026-05-10T15:17:34Z 2026-05-10T15:17:34Z Dave, Nehal Kiritkumar Dr. Hiren, R. Kavathiya http://10.9.150.37:8080/dspace//handle/atmiyauni/2330 2025-09-04T07:38:25Z 2025-06-01T00:00:00Z

An Algorithmic Approach for Undergraduate Computer Science Students to Select Mentor Using Recommendation System of Machine Learning Dave, Nehal Kiritkumar; Dr. Hiren, R. Kavathiya Undergraduate students' intellectual and emotional health are significantly impacted by mentoring. Having the proper mentor can have a big impact on confidence, motivation, and long-term goal setting for computer science students, who frequently deal with high levels of academic pressure and ambiguity about their career trajectory. Nevertheless, conventional mentor selection techniques fail to consider students' psychological fit with mentors, which frequently leads to unproductive or brief mentor-mentee relationships. By using a machine learning-based recommendation system that takes psychological characteristics into account when choosing mentors, this study seeks to close that gap. Using well-known models like the Big Five Personality Traits and emotional intelligence scores, the suggested system integrates psychological profiling. In addition to academic and technical interests, mentors and students are assessed on their motivational tendencies, communication preferences, and interpersonal styles. The methodology guarantees improved emotional alignment and communicative resonance between the mentor and mentee by including psychological elements in addition to scholastic data. The model was constructed and trained using machine learning strategies, such as collaborative filtering and clustering. A psychological compatibility score was incorporated into the recommendation algorithm, and participant surveys and psychometric testing were used to create a rich dataset. According to tests, students who were paired with mentors based on psychological compatibility expressed greater levels of happiness as well as a more robust sense of belonging and support. The study also looked at the relationship between mentor-mentee psychological compatibility and stress levels, academic engagement, and self-efficacy. Pupils who had mentors who shared their psychological views demonstrated better coping strategies, more academic perseverance, and more clarity when establishing their career and personal objectives. When mentees were emotionally open and compatible with their mentoring approach, mentors found it simpler to offer advice. An innovative, human-centred method of academic support is introduced by incorporating psychological concepts into a machine learning-based mentor selection system. This method meets students' emotional and cognitive demands while also enhancing the caliber of mentoring relationships. Future studies will examine adaptive learning platforms that modify mentor recommendations in response to students' academic and psychological development.

2025-06-01T00:00:00Z Shah, Meerabahen M. Kavathiya, Hiren R. http://10.9.150.37:8080/dspace//handle/atmiyauni/2294 2025-01-28T10:24:50Z 2024-12-01T00:00:00Z

Development Of A Model To Analyze & Interpret Vernacular Voice Recognition Of Gujarati Dialects Shah, Meerabahen M.; Kavathiya, Hiren R. The development of voice recognition systems tailored to vernacular dialects holds transformative potential for enhancing accessibility and inclusivity in technology. This thesis focuses on creating a voice recognition model specifically designed for vernacular Gujarati dialects, addressing the unique linguistic and phonetic challenges inherent in regional variations of the language. The key part of this research was to gather a diverse and representative spoken Gujarati corpora sourced via varied public repositories, which includes radio broadcast, interview, folk song, community recording and public availability speech corpora. This dataset includes a variety of dialectal variation in phonology, syntax and usage to guarantee robustness and inclusivity to the development of the models. A dialect-specific recognition system using advanced techniques in voice recognition system, including deep learning architectures the proposed framework and model was developed. The model is further enriched with dialectal linguistic features integrated to its architecture, phoneme based pretraining to increase recognition accuracy, and transfer learning to adapt general speech recognition systems to dialect specific nuances. The model was evaluated and found to achieve substantial improvement in phoneme recognition accuracy over baseline systems. The results show that modeling context-aware, high quality, diverse datasets are crucial to vernacular speech recognition. The system developed is there to provide practical applications for voice enabled user interface, digital accessibility and protection of linguistic diversity more specific examples of such languages which are least represented. This work contributes to the emerging area of regional language processing with an end-to-end framework that can be used for future work on low-resource languages and dialects and to build inclusive, ubiquitous and accessible technology solutions in multilingual communities.

2024-12-01T00:00:00Z Shukla, Kapil Kaushikkumar Shukla, Parag C. http://10.9.150.37:8080/dspace//handle/atmiyauni/2284 2025-01-10T07:14:23Z 2024-01-01T00:00:00Z

To Identify Learning Path for Novice Programmer Based on Semi-supervised Dataset Using Proposed Machine Learning Algorithm Shukla, Kapil Kaushikkumar; Shukla, Parag C. In many instances, programming education is non-personalized and has left so many learners without much interest or not being proficient enough to reach the programming level of proficiency. Most of these traditional approaches give way more attention to correction mistakes instead of personalized assignments for every learning difference. In contrast, most online modern coding websites always use one work for all regardless of differing levels of proficiency by just ignoring the need to give different works for the slow, medium, and fast learners. This research work suggests a new hybrid learning methodology using machine learning to classify types of learners based on their contribution to code and performance in tasks. The system will automatically recommend individualized coding projects based on the examination of the criteria such as accuracy, error patterns, and performance, matched to the ability of each learner. It applies advanced techniques in machine learning such as Random Forest, XGBoost, and Adaptive Ensemble Classification Weighting (AECW) algorithm to make performance prediction, manage the difficulty of jobs, and effectively balance classes. These models are also appraised using other metrics, such as accuracy, precision, recall, and F1-score. The research clearly demonstrates that ensemble methods improve both the predictive accuracy and task adaptability without causing overfitting. It not only enhances the outcome of learning but also helps instructors practically understand students' performance. This is a step to transform the process of programming education using scalable, data-driven techniques with predictive analytics integrated with adaptive task sequencing.

2024-01-01T00:00:00Z Mehta, Nirav Pareshkumar Thaker, Hetal http://10.9.150.37:8080/dspace//handle/atmiyauni/2057 2024-11-26T07:49:48Z 2024-11-01T00:00:00Z

Design And Development Of Decision Support System To Recommend Nutritious Food For Cardiovascular Patients Mehta, Nirav Pareshkumar; Thaker, Hetal Cardiovascular diseases (CVDs) are among the leading causes of mortality worldwide, and their prevalence is rapidly increasing in the Gujarat region of India. A major factor in managing cardiovascular health is adhering to a heart-healthy diet, which often presents challenges for patients in balancing nutritional needs with personal food preferences. To address this issue, this research introduces a *Nutrition-Based Recommendation System (NBRS)* aimed at providing personalized dietary guidance for individuals with heart-related problems. The NBRS leverages machine learning techniques to generate food recommendations that are not only nutritious but also aligned with individual tastes, daily calorie requirements, and cultural contexts, specifically focusing on the dietary habits of Gujarat. The foundation of this research lies in a thorough analysis of both primary and secondary data sources. Primary data was collected using a detailed questionnaire distributed to individuals with cardiovascular conditions. This questionnaire sought to capture their dietary habits, preferences, and ratings for various food items on a scale from 1 to 10. A dataset of over 90 distinct foods was compiled, each categorized into 15 groups such as fruits, vegetables, staple meals, and specific regional dishes like roti, bhakhri, thepla, dal, and rice. For each food item, nutritional parameters including fat, fiber, protein, carbohydrates, serving size, and calorie content were meticulously recorded. The secondary data included established nutritional guidelines for cardiac patients, emphasizing foods with high fiber and low fat. By integrating these insights, the dataset was structured to facilitate effective analysis and recommendation generation. A significant aspect of this model is its focus on *seasonal availability* of foods, ensuring that recommendations are practical and accessible. For instance, fruits like mangoes and apples were included, but their suggestions were aligned with their seasonal production to enhance freshness and nutritional value. This seasonal consideration allows the NBRS to remain relevant and adaptive throughout the year, providing users with timely options that are both heart-healthy and regionally appropriate.

2024-11-01T00:00:00Z