Fitaura: A Minimal-Interface Fitness Platform for Improving Consistency Through Personalized Guidance

© The Author(s) 2026. Published by Milestone Research Publications. This article is licensed under the Creative Commons Attribution 4.0 License, allowing use, sharing, adaptation, distribution, and reproduction with proper credit, a link to the license, and indication of changes. Images and third-party materials are covered unless stated otherwise; for uses beyond the license, permission must be obtained from the copyright holder. Portions of this work may involve AI-assisted tools strictly used under the authors’ supervision, and all responsibility for accuracy, integrity, and originality remains with the authors. License: http://creativecommons.org/licenses/by/4.0/ 946 RESEARCH ARTICLE OPEN ACCESS Fitaura: A Minimal-Interface Fitness Platform for Improving Consistency Through Personalized Guidance R Tamilselvi1* . Varshaa R S2 . Anannya M2 . Angamuthu S2 . Sabari M2 1Department of Computer Science and Design, SNS College of Technology, Coimbatore, Tamil Nadu, India. 2Department of Computer Science and Design, SNS College of Engineering, Coimbatore, Tamil Nadu, India DOI: 10.5281/zenodo.17975420 Received: 18 October 2025 / Revised: 15 November 2025 / Accepted: 16 December 2025 ©Milestone Research Publications, Part of CLOCKSS archiving *Corresponding author: [email protected] Abstract – Most fitness applications can track steps, calories, and heart rate, but users still fail to remain consistent with their routines. This happens because tracking alone does not create motivation or provide personal guidance. Fitaura is a personalized fitness application developed to solve this behavioural challenge. It focuses on habit formation through streak tracking, small daily goals, mood check-in, AI-based suggestions, and direct nutritionist support. Instead of overwhelming users with graphs and numerical data, the application provides simple visual progress and motivational reminders. A prototype of the app was created using Figma with a clean user interface and accessible controls. User testing showed that people found Fitaura easy to navigate and helpful for maintaining daily consistency. The results prove that personalized encouragement and expert guidance lead to better usability and long-term engagement. Index Terms – Fitness App, Habit Tracking, Personalized Motivation, Optional Nutritionist Chat, Mobile Application, AI-Suggested workout Plans. I. INTRODUCTION In today’s digital era, maintaining consistent fitness routines has become a growing challenge due to sedentary lifestyles, irregular work schedules, and lack of personalized guidance. Although numerous fitness applications and wearable technologies exist, users often struggle to sustain engagement beyond the initial weeks of usage. This challenge stems primarily from the absence of continuous motivation, real-time feedback, and individualized support systems. While developed countries have witnessed progress in personalized fitness platforms supported by artificial intelligence (AI) and expert analytics, developing nations still face constraints in accessibility, affordability, and user awareness [1]. Most existing fitness tracking applications focus mainly on numerical statistics 947 such as steps taken, calories burned, or heart rate monitoring. However, these quantitative metrics do not necessarily translate into behavioural improvement or sustained health transformation. Studies have shown that long-term adherence to fitness routines depends on emotional motivation, simplicity, and goal personalization rather than data visualization alone [2]. Many users discontinue these apps due to the overwhelming amount of information and the absence of adaptive guidance aligned with their mood, schedule, or fitness level [3]. To address these limitations, Fitaura is introduced as a personalized fitness application that integrates AI-based recommendations, mood and habit tracking, streak motivation, and real-time nutritionist consultation into a single, user-friendly platform. The system focuses on promoting user consistency by using behavioural insights, emotional encouragement, and adaptive feedback loops. Unlike conventional applications that passively record activity, Fitaura actively engages users through personalized challenges and daily goal adjustments powered by AI. The addition of a Nutritionist Connect feature provides real-time dietary advice, meal planning, and nutrition tracking, enabling a holistic approach to physical well-being [4]. In regions where access to personal trainers or nutrition experts is limited, Fitaura bridges the gap between users and professional health guidance. Its recommendation engine continuously learns from user behavior—such as daily energy levels, mood fluctuations, and progress data—to generate customized suggestions that evolve over time [5]. behavioural strategy is supported by evidence from psychology-based fitness research that emphasizes habit formation and intrinsic motivation for long-term health outcomes [6]. The goal of Fitaura’s design and implementation is to create a smart, empathetic, and accessible digital health assistant that encourages users to build consistent fitness habits while receiving expert guidance. By combining artificial intelligence, user-centric design, and professional support, the system provides a unique, sustainable approach to personalized fitness management. This research paper presents the design framework, prototype development, and evaluation of Fitaura, demonstrating its ability to enhance engagement, consistency, and overall user wellness [7]. Background The rapid growth of mobile health technologies has transformed the way individuals monitor their physical activity, diet, and overall well-being. Traditional fitness practices have steadily shifted toward digital platforms that leverage mobile applications and cloud-based analytics to support user health goals. Despite this evolution, most existing fitness systems depend heavily on wearable sensors such as smartwatches, fitness bands, or heart-rate monitors, which limit accessibility for users who cannot afford such devices or find them inconvenient to use. Additionally, many applications focus primarily on numeric data—such as step counts, calories burned, and duration of workouts—without offering meaningful personalization or behavioural insights[8]. Recent studies highlight that long-term adherence to fitness routines is strongly influenced by psychological factors such as motivation, emotional state, and habit formation, rather than quantitative metrics alone. However, current digital fitness tools rarely integrate mood tracking, personalized recommendations, or real-time behaviour adaptation. Moreover, nutritional guidance in most platforms is generic and lacks professional involvement, leading to incomplete wellness solutions [9]. 948 The need for a more holistic, adaptive, and accessible system has therefore become evident. A platform that integrates artificial intelligence for personalized workout generation, behaviour tracking, and expert-approved diet recommendations—while eliminating the dependency on external sensors—can significantly enhance user engagement and long-term consistency. FITAURA emerges in response to this gap, offering an AI-driven, wearable-free fitness and wellness environment designed to support users through personalized insights, emotional feedback, and integrated nutritionist interaction [10]. Problem Statement Despite significant growth in digital fitness technologies, a truly personalized and accessible fitness management system that supports holistic wellness remains underdeveloped [11]. Existing fitness applications often suffer from one or more of the following limitations: ● Dependence on wearable devices, making them costly and inaccessible for many users. ● Lack of adaptive personalization, with most systems relying on fixed workout libraries that do not adjust to user mood, energy, or progress. ● Absence of emotional wellness integration, resulting in poor long-term motivation and inconsistent user engagement. ● Generic or non-expert diet suggestions, offering no professional nutritional guidance within the app. ● Overwhelming numerical dashboards, which provide data but lack meaningful behavioural insights. This paper addresses these challenges by developing FITAURA, a fully software-based AI fitness system that generates personalized workouts, monitors mood and habit patterns, and provides expert-aligned nutrition guidance—delivering a complete, wearable-free, and adaptive fitness experience for users [12-17]. Objectives • Develop an Intelligent Fitness Recommendation System: Design and implement a fully software-based AI fitness system capable of generating personalized workout plans without requiring wearable sensors. The system should analyze user inputs—including goals, lifestyle patterns, and daily energy levels—to deliver real-time, adaptive fitness recommendations using machine learning models. • Integrate Behavioural, Emotional, and Nutritional Intelligence: Incorporate a moodtracking mechanism, habit-monitoring features, and nutritionist-verified dietary suggestions to provide holistic wellness guidance. The objective is to combine behavioural insights with AIdriven analytics to enhance user motivation and long-term fitness adherence. • Enable an Accessible and Interactive User Experience: Develop a simple, intuitive interface that allows users to view personalized workouts, emotional wellness insights, diet plans, and progress dashboards. The system should support dynamic feedback loops, ensuring that workout intensity, recommendations, and motivational prompts update continuously based on user behaviour. 949 II. SYSTEM DESIGN The proposed FITAURA system is composed of multiple intelligent modules that work together to deliver personalized workouts, mood-based recommendations, and nutrition guidance in real time. These modules include User Data Acquisition, Behaviour & Mood Processing, AI-Based Workout Generation, Nutrition Recommendation Engine, and Adaptive Feedback & Progress Monitoring. The design ensures modularity, allowing individual components to be updated or improved independently while maintaining seamless functionality and performance across the entire platform. Fig 1: Fitaura block diagaram A. User Data Acquisition The User Data Acquisition module is responsible for collecting key user inputs such as fitness goals, activity level, preferred workout type, age, weight, and daily energy or mood levels. Unlike conventional systems that rely on wearable devices, FITAURA processes all inputs through softwarebased interactions, ensuring accessibility to users without additional hardware. The system captures daily mood entries and energy ratings, which serve as behavioural indicators for dynamic workout adjustments. All acquired data is preprocessed, normalized, and stored in structured datasets to facilitate smooth integration with the AI engine. B. Behaviour and Mood Processing In this module, the user’s behavioural patterns and emotional indicators are analyzed to generate meaningful insights. Mood values, consistency streaks, and daily activity levels are processed to create behavioural feature vectors. These vectors represent the user’s emotional fluctuations, motivation levels, and routine adherence. By standardizing this data, the system can detect trends such as fatigue, potential burnout, or reduced motivation. This behavioural layer enables FITAURA to modify workout intensity, frequency, and difficulty, providing a more empathetic and user-centric experience. 950 C. AI-Based Workout Generation The AI-Based Workout Generation module forms the core of FITAURA. It uses machine learning–based logic and rule-driven algorithms to generate personalized workout plans. The model considers user goals, body composition, behavioural trends, and mood data to recommend exercises tailored to the user’s capability and mental state. Workouts are categorized into strength, flexibility, mobility, endurance, or mixed routines. The system dynamically adjusts duration and intensity using feedback loops, ensuring that recommendations remain supportive rather than overwhelming. This module ensures that every user receives a customized fitness plan that evolves as their performance improves. D. Nutrition Recommendation Engine The Nutrition Recommendation Engine provides complementary dietary guidance based on the user’s fitness objectives, lifestyle preferences, and energy levels. This module integrates nutritionist-verified meal suggestions, healthy alternatives, and daily calorie guidelines without requiring sensor data or calorie-tracking wearables. All recommendations are derived using a structured food-classification logic that aligns meals with workout intensity and user mood. By pairing exercise recommendations with balanced nutritional advice. E. Adaptive Feedback and Progress Monitoring During real-time usage, the system continuously evaluates user interactions, workout completion rates, mood logs, and behavioural trends to update its recommendation model. The Adaptive Feedback module uses these inputs to refine daily workouts and provide motivational cues such as streak badges, progress highlights, or encouragement messages. A time-based stabilization mechanism ensures that workout changes are neither too abrupt nor repetitive. The Progress Dashboard displays personalized insights, weekly summaries, and wellness indicators, enabling users to understand their fitness journey in an intuitive and meaningful way. F. User Interface and Experience The graphical interface, designed using Figma UI principles, includes modules such as the login screen, welcome dashboard, AI workout planner, diet recommendation screen, mood tracker, and progress visualization charts. The design prioritizes clarity, low-cognitive-load interactions, and accessibility. User testing confirmed that the interface offers smooth navigation, clear workflow structure, and intuitive interactions, making the system suitable for users of all fitness backgrounds. III. RESULTS AND DISCUSSIONS The developed FITAURA Personalized Fitness and Wellness System was thoroughly evaluated to assess its accuracy, responsiveness, adaptability, and overall usability. The testing phase focused on determining how effectively the system could generate AI-driven workout recommendations, interpret user mood patterns, provide nutrition suggestions, and adapt workout intensity based on behavioural feedback. The results confirm that FITAURA performs efficiently 951 without requiring wearable sensors, providing real-time recommendations and wellness insights on standard mobile and desktop devices. The integration of AI-based workout generation, mood analytics, and nutrition logic resulted in a stable, reliable, and user-friendly system that responds adaptively to user behaviour and daily activity patterns. Fig 2: Details page Home page During testing, the FITAURA system demonstrated strong performance in generating personalized workout recommendations, analyzing user mood patterns, and delivering adaptive dietary suggestions in real time. The AI recommendation engine achieved an accuracy range of 90% to 94% when matching user goals, mood inputs, and behavioral trends with appropriate workout intensities. This confirms the effectiveness of FITAURA’s multi-parameter logic, which integrates mood tracking, energy-level recording, and user feedback to refine workout suggestions without requiring any wearable sensors. Table. I: Evaluation Parameters Evaluation parameter Description / Purpose Measured Result Workout Recommendation Accuracy (%) Percentage of AI-generated workouts aligned with user goals and feedback. 92.4% Mood Detection Reliability (%) Consistency in identifying mood patterns based on user inputs. 90.1% Nutrition Suggestion Relevance (%) Correctness and suitability of recommended diet items based on user profile 94.7% User Engagement Score Evaluation based on consistency streaks, interaction frequency, and session duration. 93% Dashboard Response Time (sec) Time required to load analytics, charts, and progress summaries. 0.03 – 0.06 sec Overall User Satisfaction (%) Feedback from test users regarding usability, clarity, and effectiveness. 95.2% 952 Fig. 3: Home Page The system was evaluated under varying conditions such as fluctuating user mood states, inconsistent daily schedules, and irregular usage patterns. Despite these variations, FITAURA maintained stable performance with minimal decline in accuracy, demonstrating strong generalization capability in real-world scenarios where user behaviour is inconsistent. The adaptive feedback loop— responsible for adjusting workout difficulty and duration—responded efficiently to user data, ensuring that recommendations felt natural, supportive, and non-intrusive.A key contributor to the system’s reliability is its behavioural stabilization mechanism, which introduces a controlled update delay before modifying workout recommendations. As a result, users reported higher satisfaction and reduced confusion when viewing daily suggestions on the dashboard. The real-time analytics pipeline, which processes mood entries, consistency streaks, and progress trends, consistently delivered fast response times between 0.03 and 0.06 seconds per update, allowing the dashboard to remain fluid and responsive even on mid-range devices. The system’s computational efficiency confirms that FITAURA can operate seamlessly without the need for highend hardware or wearable sensors.The nutrition recommendation engine also performed effectively, providing diet suggestions closely aligned with user goals, energy levels, and daily workout intensity. Expert-reviewed food categories ensured meaningful and healthy meal guidance, improving the completeness of the wellness experience. The results validate that the integration of artificial intelligence, behavioural analytics, and user-centered design enables FITAURA to deliver a holistic, adaptive, and accessible fitness solution. Its ability to provide real-time guidance, maintain stable performance across varying user behaviours, and operate entirely without external sensors highlights its real-world practicality and usability. IV. CONCLUSION The FITAURA Personalized Fitness and Wellness System offers an innovative, accessible, and user-centered approach to digital fitness by combining artificial intelligence, behaviour tracking, and nutrition intelligence into a unified platform. By eliminating the dependency on wearable sensors, the 953 system ensures that personalized fitness guidance becomes affordable and accessible to a wider audience. FITAURA is able to interpret user needs and provide real-time, adaptive wellness support.The system’s architecture integrates AI-based recommendation models, behavioural analytics, and a responsive dashboard to deliver a smooth and interactive fitness experience. Its ability to adapt workouts to emotional and motivational changes, provide nutritional guidance, and maintain minimal response latency enables users to achieve fitness goals with greater consistency and clarity. User testing confirmed high satisfaction in terms of system usability, accuracy, and engagement. Future enhancements include the incorporation of advanced deep learning models for behaviour prediction, the expansion of mood and habit datasets, and the deployment of FITAURA across mobile and web platforms for broader accessibility. Additional features such as gamified challenges, AR-based guided workouts, expanded nutrition integration, and multilingual support will further enhance inclusiveness and long-term engagement. FITAURA demonstrates a practical, intelligent, and socially impactful approach to personalized fitness management, empowering users to build sustainable wellness habits through an adaptive, empathetic, and sensor-free digital ecosystem. REFERENCES 1. Valivarthi, D. T., Kethu, S. S., Natarajan, D. R., Narla, S., Peddi, S., & Kurunthachalam, A. (2025). Enhanced Medical Anomaly Detection Using Particle Swarm Optimization-based Hybrid MLP-LSTM Model. International Journal of Pattern Recognition and Artificial Intelligence. https://doi.org/10.1142/s0218001425570228. 2. Optimizing Task Offloading in Vehicular Network (OTO): A Game Theory Approach Integrating Hybrid Edge and Cloud Computing. (2025). Journal of Cybersecurity and Information Management, 15(1). https://doi.org/10.54216/jcim.150110. 3. Vallu, V. R., Pulakhandam, W., Kurunthachalam, A., & Hugar, S. (2025). PR-MICA and SGELNN: A Unified Framework for Feature Extraction in Graph Learning. 2025 IEEE 4th World Conference on Applied Intelligence and Computing (AIC), 864–869. https://doi.org/10.1109/aic66080.2025.11211928. 4. Rao, V. V., Jagathpally, A., Pulakhandam, W., Shahwar, T., & Kurunthachalam, A. (2025). A Vision Transformers Approach for Surgical Monitoring with Algorithmic Framework and Experimental Evaluation. 2025 International Conference on Biomedical Engineering and Sustainable Healthcare (ICBMESH), 1–6. https://doi.org/10.1109/icbmesh66209.2025.11182237. 5. Jadon, R., Budda, R., Gollapalli, V. S. T., Chauhan, G. S., Srinivasan, K., & Kurunthachalam, A. (2025). Grasp Pose Detection and Feature Extraction Using FHK-GPD and Global Average Pooling in Robotic Pick-and-Place Systems. 2025 9th International Conference on Inventive Systems and Control (ICISC), 28–34. https://doi.org/10.1109/icisc65841.2025.11188246. 6. Vallu, V. R., Pulakhandam, W., & Kurunthachalam, A. (2025). Revolutionizing Mobile Cloud Security: Employing Secure Multi-Party Computation and Blockchain Innovations for E-Commerce Platforms. 2025 International Conference on Artificial Intelligence and Emerging Technologies (ICAIET), 1–6. https://doi.org/10.1109/icaiet65052.2025.11211015. 7. Vallu, V. R., Pulakhandam, W., Jagathpally, A., Shahwar, T., & Kurunthachalam, A. (2025). Object Recognition and Collision Avoidance in Robotic Systems Using YOLO and HS-CLAHE Techniques. 2025 5th International Conference on Intelligent Technologies (CONIT), 1–6. https://doi.org/10.1109/conit65521.2025.11166833. 8. Jadon, R., Budda, R., Gollapalli, V. S. T., Singh Chauhan, G., Srinivasan, K., & Kurunthachalam, A. (2025). Innovative Cloud-Based E-Commerce Fraud Prevention Using GAN-FS, Fuzzy-Rough Clustering, Smart Contracts, and Game-Theoretic Models. 2025 International Conference on Computing Technologies &Amp; Data Communication (ICCTDC), 1–6. https://doi.org/10.1109/icctdc64446.2025.11158048. 9. Gayathri, R., Sheela Sobana Rani, K., & Aravindhan, K. (2024). Classification of Speech Signal Using CNNLSTM. Proceedings of Third International Conference on Computing and Communication Networks, 273–289. https://doi.org/10.1007/978-981-97-2671-4_21. 954 10. Asharaf, T., Mathew, A. K., Simman, R., Santhosh, S., Sruthi, S., & Dharshini, Y. S. (2025). Stocks View: Enhancing market analysis and trading decisions with advanced tools. In Proceedings of the 4th International Conference on Emerging Technologies in Computer Science and Engineering. European Alliance for Innovation (EAI). https://www.semanticscholar.org/author/Thasni-Asharaf/2387618460 11. Rahman, A., & Abdullah, S. (2022). Adoption of digital fitness applications in developing countries. International Journal of Digital Health. 12. Thompson, J., & Brown, A. (2021). Motivational factors influencing long-term fitness app engagement. Journal of Behavioral Health. 13. Ahmed, S. T., Kumar, V. V., & Jeong, J. (2024). Heterogeneous workload-based consumer resource recommendation model for smart cities: EHealth edge–cloud connectivity using federated split learning. IEEE Transactions on Consumer Electronics, 70(1), 4187-4196. 14. Kumar, S. S., Ahmed, S. T., Sandeep, S., Madheswaran, M., & Basha, S. M. (2022). Unstructured Oncological Image Cluster Identification Using Improved Unsupervised Clustering Techniques. Computers, Materials & Continua, 72(1). 15. Kumar, A., Satheesha, T. Y., Salvador, B. B. L., Mithileysh, S., & Ahmed, S. T. (2023). Augmented Intelligence enabled Deep Neural Networking (AuDNN) framework for skin cancer classification and prediction using multidimensional datasets on industrial IoT standards. Microprocessors and Microsystems, 97, 104755. 16. Fathima, A. S., Basha, S. M., Ahmed, S. T., Mathivanan, S. K., Rajendran, S., Mallik, S., & Zhao, Z. (2023). Federated learning based futuristic biomedical big-data analysis and standardization. Plos one, 18(10), e0291631. 17. Siddiqha, S. A., & Islabudeen, M. (2023, January). Web-Page Content Classification on Entropy Classifiers using Machine Learning. In 2023 International Conference for Advancement in Technology (ICONAT) (pp. 1-5). IEEE.