This repository contains MATLAB scripts for modeling, predicting, and analyzing microbial growth and polymer production. In the dynamic modeling step (Folder: Dynamic_modelling), experimental datasets are loaded, optimized kinetic parameters are estimated, and predictions are generated, with model performance evaluated via cross-validation, bootstrap, and error metrics. The hybrid modeling step (Folder: Hybrid_modelling) integrates neural networks with optimized parameters to simulate system behavior, assess parameter sensitivity, and generate feature explanations using LIME, Shapley, and partial dependence plots. The cross-validation of hybrid models (Subfolder: Cross_validation_hybrid_modelling) involves encoding and decoding network parameters, simulating biomass and polymer growth, calculating prediction errors, and evaluating model performance. Finally, the statistics calculation (Folder: Statistics_calculation) step consolidates results from both dynamic and hybrid models, computing MAE, RMSE, MAPE, and R² to quantify model accuracy and reliability for validation datasets.

This repository contains MATLAB scripts for modeling, predicting, and analyzing microbial growth and polymer production. In the dynamic modeling step (Folder: Dynamic_modelling), experimental datasets are loaded, optimized kinetic parameters are estimated, and predictions are generated, with model performance evaluated via cross-validation, bootstrap, and error metrics. The hybrid modeling step (Folder: Hybrid_modelling) integrates neural networks with optimized parameters to simulate system behavior, assess parameter sensitivity, and generate feature explanations using LIME, Shapley, and partial dependence plots. The cross-validation of hybrid models (Subfolder: Cross_validation_hybrid_modelling) involves encoding and decoding network parameters, simulating biomass and polymer growth, calculating prediction errors, and evaluating model performance. Finally, the statistics calculation (Folder: Statistics_calculation) step consolidates results from both dynamic and hybrid models, computing MAE, RMSE, MAPE, and R² to quantify model accuracy and reliability for validation datasets.

No description available

No description available

The increasing demand for portable and reliable medical oxygen delivery systems has highlighted the need for continuous monitoring of key performance parameters, particularly output pressure, to ensure patient safety and device efficiency. Traditional oxygen concentrators often lack real-time monitoring capabilities, making it difficult to detect pressure anomalies that may compromise therapeutic effectiveness. To address this limitation, a cost-effective, IoT-enabled monitoring system has been developed. The proposed system integrates a 1.2 MPa atmospheric pressure sensor with an HX710B analog-to-digital converter to accurately measure output pressure levels. An ATmega328 microcontroller processes the data and displays real-time readings on an LCD screen, while an ESP8266 module transmits the information to the Blynk cloud platform for remote access and data logging. This architecture allows healthcare providers and users to receive immediate alerts when pressure deviates from safe thresholds, enabling timely maintenance and minimizing risks. The system demonstrates stable performance, reliable wireless communication, and effective pressure monitoring. Its low cost, ease of integration, and remote accessibility make it well-suited for home healthcare, telemedicine applications, and smart medical device development.

The increasing demand for portable and reliable medical oxygen delivery systems has highlighted the need for continuous monitoring of key performance parameters, particularly output pressure, to ensure patient safety and device efficiency. Traditional oxygen concentrators often lack real-time monitoring capabilities, making it difficult to detect pressure anomalies that may compromise therapeutic effectiveness. To address this limitation, a cost-effective, IoT-enabled monitoring system has been developed. The proposed system integrates a 1.2 MPa atmospheric pressure sensor with an HX710B analog-to-digital converter to accurately measure output pressure levels. An ATmega328 microcontroller processes the data and displays real-time readings on an LCD screen, while an ESP8266 module transmits the information to the Blynk cloud platform for remote access and data logging. This architecture allows healthcare providers and users to receive immediate alerts when pressure deviates from safe thresholds, enabling timely maintenance and minimizing risks. The system demonstrates stable performance, reliable wireless communication, and effective pressure monitoring. Its low cost, ease of integration, and remote accessibility make it well-suited for home healthcare, telemedicine applications, and smart medical device development.

This dataset includes CCD result data for Echinocandin B, along with codes for developing multiple linear regression and artificial neural network (ANN) models to optimize the production process based on parameters such as pH, dextrose, molasses, and casein. It contains scripts for hyperparameter optimization, genetic algorithm-based ANN model optimization, explainable AI (XAI) for model interpretation, and statistical model comparison. Additionally, the package provides code for generating response surface methodology (RSM) plots, residual plots for model accuracy assessment, and LIME-SHAP plots for model explanation.

This dataset includes CCD result data for Echinocandin B, along with codes for developing multiple linear regression and artificial neural network (ANN) models to optimize the production process based on parameters such as pH, dextrose, molasses, and casein. It contains scripts for hyperparameter optimization, genetic algorithm-based ANN model optimization, explainable AI (XAI) for model interpretation, and statistical model comparison. Additionally, the package provides code for generating response surface methodology (RSM) plots, residual plots for model accuracy assessment, and LIME-SHAP plots for model explanation.

This dataset contains CCD result data for pullulan extraction using the solvent method and codes for developing linear regression and artificial neural network (ANN) models to optimize the extraction process (i.e., solvent-to-broth ratio, pH, and incubation time). It includes scripts for performing sensitivity analysis, desirability testing, and multi-objective optimization for three responses (i.e. pullulan recovery, sucrose equivalent, and protein impurities). The package also provides code to generate response surface methodology (RSM), an ANN residual plot to evaluate model accuracy, and Pareto front analysis to identify optimal trade-offs between competing objectives.

This dataset contains CCD result data for pullulan extraction using the solvent method and codes for developing linear regression and artificial neural network (ANN) models to optimize the extraction process (i.e., solvent-to-broth ratio, pH, and incubation time). It includes scripts for performing sensitivity analysis, desirability testing, and multi-objective optimization for three responses (i.e. pullulan recovery, sucrose equivalent, and protein impurities). The package also provides code to generate response surface methodology (RSM), an ANN residual plot to evaluate model accuracy, and Pareto front analysis to identify optimal trade-offs between competing objectives.