Enterprise AI Analysis
Estimation of daily energy requirements using a hybrid artificial intelligence model
This study explores the applicability of hybrid artificial intelligence models for calculating daily energy requirements based on individuals' anthropometric measurements and demographic data. The primary goal is to develop a model that offers a reliable and practical solution with higher accuracy than existing methods while ensuring ease of use in field settings. The study collected data from volunteer individuals at Sakarya University between September 2023 and February 2024. Anthropometric measurements were performed by a bioelectrical impedance analysis (BIA) device, and demographic data were obtained through face-to-face surveys. Eighty-seven features were analyzed using the Spearman feature selection algorithm, and these were utilized to estimate energy requirements. Based on collaborative hybridization, the hybrid artificial intelligence model integrates three distinct Gaussian Process Regression (GPR) models using squared exponential, rational quadratic, and Matern52 kernels. These models were structured based on gender, and performance evaluation was carried out using criteria such as MAPE, MAD, MSE, R, and R². The best model performance in males was achieved at level 10 with 100% R², while the highest accuracy in females was observed at level 15. To increase model simplicity, the PCA method was applied; however, a decrease in performance was detected (R = 0.48, R² = 0.23). The accuracy of the artificial intelligence models proposed in this study was significantly higher than that of traditional formulas commonly preferred in the current literature. Hybrid artificial intelligence models offer practicality, accuracy, and flexibility in estimating energy requirements. Gender-based modeling has enhanced prediction performance while providing more reliable results by accounting for individual differences. This approach holds significant potential for advancing health and nutritional sciences.
Executive Impact
Our AI solution significantly enhances the accuracy and efficiency of energy requirement estimation, delivering measurable benefits for health and nutritional applications.
0
Peak Accuracy Achieved
0
Prediction Speed (Obs/Sec)
0
Optimized Feature Set Reduction
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
The core of our solution is a hybrid artificial intelligence model integrating three distinct Gaussian Process Regression (GPR) models: GPR-S (Squared Exponential kernel), GPR-R (Rational Quadratic kernel), and GPR-M (Matern52 kernel). GPR models are non-parametric, flexible, and robust, excelling in high-dimensional, small-sample, or non-linear datasets by learning complex mappings through kernel functions. This hybrid approach combines the strengths of these diverse kernels to reduce variance and improve overall prediction robustness, particularly with gender-specific modeling to account for physiological variations.
Model performance was rigorously evaluated using standard metrics: Mean Absolute Percentage Error (MAPE), Mean Absolute Deviation (MAD), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), R, and R². The hybrid AI models consistently achieved R values close to 1 and R² values up to 100% for optimal feature sets (e.g., Level 10 for males, Level 15 for females, Level 11 for combined dataset). This significantly outperforms traditional formulas. Computational efficiency was also assessed, with prediction speeds reaching hundreds of thousands of observations per second and training times remaining in seconds to minutes, demonstrating practical feasibility.
Data was collected from 485 volunteers (196 males, 289 females) at Sakarya University, including anthropometric measurements via bioelectrical impedance analysis (BIA) and demographic data from surveys. Eighty-seven features were initially identified. The Spearman feature selection algorithm was applied to optimize feature subsets, leading to gender-specific optimal levels for prediction. While Principal Component Analysis (PCA) was explored for dimensionality reduction, it resulted in a performance decrease (R=0.48, R²=0.23), indicating that crucial non-linear interactions were lost, thus confirming the superiority of the Spearman selection approach for this problem.
0
R² Accuracy on Optimal Feature Set
Enterprise Process Flow
Data Acquisition
→
Data Preprocessing
→
Feature Selection
→
GPR Models (S, R, M)
→
Hybrid ML Algorithm
| Model | R Value | R² Value |
|---|---|---|
| Hybrid AI Model (This Study) | 1.00 | 1.00 |
| Harris-Benedict | 0.91 | 0.83 |
| Scholfield | 0.92 | 0.84 |
| Mifflin | 0.89 | 0.80 |
| Owen | 0.88 | 0.77 |
| Notes: Higher R and R² values indicate superior model accuracy. | ||
Transforming Energy Requirement Estimation
Our hybrid AI model represents a significant leap forward from traditional methods and wearable devices. Unlike time-consuming and expensive indirect calorimetry or less reliable self-reported dietary records, our model offers a practical, cost-effective, and highly accurate solution. It leverages readily available anthropometric and demographic data, eliminating the need for specialized equipment or restrictive protocols. Furthermore, its ability to capture complex non-linear relationships and adapt to gender-specific differences ensures a comprehensive and reliable estimation, making it ideal for integration into clinical decision support systems and mobile health applications for broader population health management.
Calculate Your Enterprise AI ROI
Estimate the potential savings and reclaimed productivity hours by integrating our advanced AI solutions into your operations.
Estimated Annual Savings
$0
Reclaimed Productivity Hours
0
Implementation Roadmap for Enterprise AI Integration
A structured approach to integrate AI seamlessly into your organization, from data validation to continuous optimization.
Phase 1: Data Integration & Validation
Establish secure pipelines for integrating existing anthropometric and demographic data from various sources. Conduct thorough validation of integrated data against established clinical standards to ensure data quality and consistency for AI model training and deployment.
Phase 2: Custom Model Adaptation & Training
Adapt the hybrid GPR model to specific enterprise datasets, including fine-tuning kernel hyperparameters and feature selection strategies. Retrain the model using updated data to maximize predictive accuracy and generalizability across diverse user populations within the enterprise.
Phase 3: Pilot Deployment & User Feedback
Deploy the AI model in a pilot program with a select user group, integrating it into existing health monitoring or nutritional planning tools. Collect and analyze user feedback to identify areas for improvement in usability, performance, and feature set.
Phase 4: Scalable Rollout & Continuous Optimization
Based on pilot success, scale the AI solution across the entire enterprise. Implement continuous learning mechanisms to retrain and optimize the model with new data, ensuring sustained high performance and adaptability to evolving user needs and health trends.
Ready to Transform Your Health & Nutritional Strategy?
Book a personalized session with our AI specialists to discuss how these insights can be applied to your enterprise.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat