Model Training Research Articles

Implementing Long Short Term Memory (LSTM) in Chatbots for Multi Usaha Raya

The furniture industry is an important sector in Indonesia that supports the economy and provides quality furniture. An in-depth understanding of the furniture business is essential for industry players to improve operational efficiency and customer satisfaction. This research aims to develop a chatbot for Multi Usaha Raya furniture company to improve customer service and operational efficiency. In its development, the Machine Learning Model Development Life Cycle (MDLC) and deep learning approach using the Flask platform are employed. LSTM, a type of recurrent neural network (RNN) architecture capable of handling long-term dependencies, is utilized in this chatbot model. The model training results show an accuracy of 99%, validation accuracy of 96%, loss of 0.1%, and validation loss of 0.2% after 200 epochs, demonstrating the effectiveness of the LSTM algorithm for developing a chatbot in this company.

A Recurrent Deep Network for Gait Phase Identification from EMG Signals During Exoskeleton-Assisted Walking

Lower limb exoskeletons represent a relevant tool for rehabilitating gait in patients with lower limb movement disorders. Partial assistance exoskeletons adaptively provide the joint torque needed, on top of that produced by the patient, for a correct and stable gait, helping the patient to recover an autonomous gait. Thus, the device needs to identify the different phases of the gait cycle to produce precisely timed commands that drive its joint motors appropriately. In this study, EMG signals have been used for gait phase detection considering that EMG activations lead limb kinematics by at least 120 ms. We propose a deep learning model based on bidirectional LSTM to identify stance and swing gait phases from EMG data. We built a dataset of EMG signals recorded at 1500 Hz from four muscles from the dominant leg in a population of 26 healthy subjects walking overground (WO) and walking on a treadmill (WT) using a lower limb exoskeleton. The data were labeled with the corresponding stance or swing gait phase based on limb kinematics provided by inertial motion sensors. The model was studied in three different scenarios, and we explored its generalization abilities and evaluated its applicability to the online processing of EMG data. The training was always conducted on 500-sample sequences from WO recordings of 23 subjects. Testing always involved WO and WT sequences from the remaining three subjects. First, the model was trained and tested on 500 Hz EMG data, obtaining an overall accuracy on the WO and WT test datasets of 92.43% and 91.16%, respectively. The simulation of online operation required 127 ms to preprocess and classify one sequence. Second, the trained model was evaluated against a test set built on 1500 Hz EMG data. The accuracies were lower, yet the processing times were 11 ms faster. Third, we partially retrained the model on a subset of the 1500 Hz training dataset, achieving 87.17% and 89.64% accuracy on the 1500 Hz WO and WT test sets, respectively. Overall, the proposed deep learning model appears to be a valuable candidate for entering the control pipeline of a lower limb rehabilitation exoskeleton in terms of both the achieved accuracy and processing times.

Plastic Constitutive Training Method for Steel Based on a Recurrent Neural Network

The deep learning steel plastic constitutive model training method was studied based on the recurrent neural network (RNN) model to improve the allocative efficiency of the deep learning steel plastic constitutive model and promote its application in practical engineering. Two linear hardening constitutive datasets of steel were constructed using the Gaussian stochastic process. The RNN, long short-term memory (LSTM), and gated recurrent unit (GRU) were used as models for training. The effects of the data pre-processing method, neural network structure, and training method on the model training were analyzed. The prediction ability of the model for different scale series and the corresponding data demand were evaluated. The results show that LSTM and the GRU are more suitable for stress–strain prediction. The marginal effect of the stacked neural network depth and number gradually decreases, and the hysteresis curve can be accurately predicted by a two-layer RNN. The optimal structure of the two models is A50-100 and B150-150. The prediction accuracy of the models increased with the decrease in batch size and the increase in training batch, and the training time also increased significantly. The decay learning rate method could balance the prediction accuracy and training time, and the optimal initial learning rate, batch size, and training batch were 0.001, 60, and 100, respectively. The deep learning plastic constitutive model based on the optimal parameters can accurately predict the hysteresis curve of steel, and the prediction abilities of the GRU are 6.13, 6.7, and 3.3 times those of LSTM in short, medium, and long sequences, respectively.

Pi Class – A Revolutionary Step Forward in Hybrid Class Management System

The COVID-19 pandemic has caused widespread disruptions globally, resulting in a state of health emergency with numerous deaths reported and an overall implementation of quarantine and isolation. Strict lockdowns have been implemented to curb the spread of the virus, requiring social distancing and limiting physical interactions. These measures had far-reaching impacts on all aspects of life, including education. Education was one of the most affected sectors, with difficulty delivering quality education in schools, colleges, and universities. It was hard to provide quality education, a basic need of humanity. In this research paper, we propose an adequate solution to overcome the difficulties of maintaining educational quality during and after the COVID-19 pandemic and its multiple variants. The proposed solution is a hybrid model for an autonomous lecture recording system that facilitates students to attend physical classes and attend lectures virtually. The solution proposed is a cost-effective and convenient way for students to access lectures. The application involves hardware and software components that record and preserve lectures' audio and visual aspects. The system will allow lectures to be delivered directly to the students' devices. The major modules of the project include Python scripting, model training, UI/UX design, and app development.

Deployment of mobile application using a novel CNN model for the detection of COVID-19 thoracic disease

In January 2021 and January 2022, COVID-19 caused roughly 13,000 and 6,000 deaths respectively per day. In August 2022, 26,000 deaths per day were estimated to be caused by COVID-19, followed by 13,000 deaths per day in February 2024. The timely identification and treatment of malignant diseases can potentially lower the mortality rate. Nonetheless, the use of manual methods for diagnosing these conditions requires a meticulous and comprehensive examination, making it susceptible to errors, burdensome for healthcare professionals, and time-intensive. Hence, the objective of this study is to design and deploy a novel deep-learning model for the detection of COVID-19 thoracic diseases. A Convolutional Neural Network (CNN) with less trainable parameters was implemented. This proposed model was deployed on a mobile device using Android Studio and Flutter for the detection of COVID-19 thoracic diseases. Specificity, accuracy, precision, sensitivity, f1-score, ROC, and PR curves were used to evaluate the model's performance. Moreover, the carbon footprint as well as how responsible the proposed model is according to Responsible AI rules was also assessed. The model's evaluation results show an overall accuracy of 93.27 %, specificity of 97.33 %, precision of 93.75 %, sensitivity of 94.42 %, F1-Score of 94.06 %, ROC rate of 98.0 %, PR rate of 96.8 %. The evaluation of the mobile application shows higher generalizability on the COVID-19 dataset. Also, the overall FACETS Score representing responsible AI is 83 % and the carbon footprint (representing the amount of carbon emission emitted into the environment during model training and testing) of 416.73 g with equivalent tree months of 0.45 was obtained. This application with better performance and a low carbon footprint was deployed using Android Studio and Flutter and can assist physicians in the diagnosis of COVID-19 and related diseases.

Exploring neural markers of dereification in meditation based on EEG and personalized models of electrophysiological brain states

With mounting evidence for the benefits of meditation, there has been a growing interest in measuring and quantifying meditative states. This study introduces the Inner Dereification Index (IDI), a class of personalized models designed to quantify the distance from non-meditative states such as mind wandering based on a single individual’s neural activity. In addition to demonstrating high classification accuracy (median AUC: 0.996) at distinguishing meditation from thinking states moment by moment, IDI can accurately stratify meditator cohorts by experience, and correctly identify the practices most effective at training the dereification aspect of meditation (decentering from immersion with thoughts and perceptions and recognizing them as mental constructs). These results suggest that IDI models may be a useful real-time proxy for dereification and meditation progress, requiring only 1 min of mind wandering data (and no meditation data) during model training. Thus, they show promise for applications such as real-time meditation feedback, progress tracking, personalization of practices, and potential therapeutic applications of neurofeedback-assisted generation of positive states of consciousness.

Addressing the Generalizability of AI in Radiology Using a Novel Data Augmentation Framework with Synthetic Patient Image Data: Proof-of-Concept and External Validation Classification Tasks in Multiple Sclerosis.

"Just Accepted" papers have undergone full peer review and have been accepted for publication in Radiology: Artificial Intelligence. This article will undergo copyediting, layout, and proof review before it is published in its final version. Please note that during production of the final copyedited article, errors may be discovered which could affect the content. Artificial intelligence (AI) models often face performance drops after deployment to external datasets. This study evaluated the potential of a novel data augmentation framework based on generative adversarial networks (GAN) that creates synthetic patient image data during model training to improve model generalizability. Model development and external testing were performed for a given classification task, namely the detection of new fluid-attenuated inversion recovery (FLAIR) lesions on MRI during longitudinal follow-up of patients with multiple sclerosis (MS). An internal dataset of 669 patients with MS (n = 3083 examinations) was used to develop an attention-based network, trained both with and without the inclusion of the GAN-based synthetic data augmentation framework. External testing was performed on 134 patients with MS from a different institution, with MR images acquired using different scanners and protocols than images used during training. Models trained using synthetic data augmentation showed a significant performance improvement when applied on external data (AUC 83.6% without synthetic data versus AUC 93.3% with synthetic data augmentation, P = .03), achieving comparable results to the internal test set (AUC 95.5%, P = .53), whereas models without synthetic data augmentation demonstrated a performance drop upon external testing (AUC 93.8% on internal dataset versus AUC 83.6% on external data, P = .03). Data augmentation with synthetic patient data substantially improved performance of AI models on unseen MRI data and may be extended to other clinical conditions or tasks to mitigate domain shift, limit class imbalance, and enhance the robustness of AI applications in medical imaging. ©RSNA, 2024.

Blockchain-Based Federated Learning: A Survey and New Perspectives

Federated learning, as a novel distributed machine learning mode, enables the training of machine learning models on multiple devices while ensuring data privacy. However, the existence of single-point-of-failure bottlenecks, malicious threats, scalability of federated learning implementation, and lack of incentive mechanisms have seriously hindered the development of federated learning technology. In recent years, as a distributed ledger, blockchain has the characteristics of decentralization, tamper-proof, transparency, security, etc., which can solve the issues encountered in the above-mentioned federated learning. Particularly, the integration of federated learning and blockchain leads to a new paradigm, called blockchain-based federated learning (BFL), which has been successfully applied in many application scenarios. This paper aims to provide a comprehensive review of recent efforts on blockchain-based federated learning. More concretely, we propose and design a taxonomy of blockchain-based federated learning models, along with providing a comprehensive summary of the state of the art. Various applications of federated learning based on blockchain are introduced. Finally, we expand on current trends and provide new perspectives pertaining to this new and exciting development in the field.

Diffusion probabilistic priors for zero-shot low-dose CT image denoising.

Denoising low-dose computed tomography (CT) images is a critical task in medical image computing. Supervised deep learning-based approaches have made significant advancements in this area in recent years. However, these methods typically require pairs of low-dose and normal-dose CT images for training, which are challenging to obtain in clinical settings. Existing unsupervised deep learning-based methods often require training with a large number of low-dose CT images or rely on specially designed data acquisition processes to obtain training data. To address these limitations, we propose a novel unsupervised method that only utilizes normal-dose CT images during training, enabling zero-shot denoising of low-dose CT images. Our method leverages the diffusion model, a powerful generative model. We begin by training a cascaded unconditional diffusion model capable of generating high-quality normal-dose CT images from low-resolution to high-resolution. The cascaded architecture makes the training of high-resolution diffusion models more feasible. Subsequently, we introduce low-dose CT images into the reverse process of the diffusion model as likelihood, combined with the priors provided by the diffusion model and iteratively solve multiple maximum a posteriori (MAP) problems to achieve denoising. Additionally, we propose methods to adaptively adjust the coefficients that balance the likelihood and prior in MAP estimations, allowing for adaptation to different noise levels in low-dose CT images. We test our method on low-dose CT datasets of different regions with varying dose levels. The results demonstrate that our method outperforms the state-of-the-art unsupervised method and surpasses several supervised deep learning-based methods. Our method achieves PSNR of 45.02 and 35.35dB on the abdomen CT dataset and the chest CT dataset, respectively, surpassing the best unsupervised algorithm Noise2Sim in the comparative methods by 0.39 and 0.85dB, respectively. We propose a novel low-dose CT image denoising method based on diffusion model. Our proposed method only requires normal-dose CT images as training data, greatly alleviating the data scarcity issue faced by most deep learning-based methods. At the same time, as an unsupervised algorithm, our method achieves very good qualitative and quantitative results. The Codes are available in https://github.com/DeepXuan/Dn-Dp.

Interpretable Machine Learning: A Case Study on Predicting Fuel Consumption in VLGC Ship Propulsion

The integration of machine learning (ML) in marine engineering has been increasingly subjected to stringent regulatory scrutiny. While environmental regulations aim to reduce harmful emissions and energy consumption, there is also a growing demand for the interpretability of ML models to ensure their reliability and adherence to safety standards. This research highlights the need to develop models that are both transparent and comprehensible to domain experts and regulatory bodies. This paper underscores the importance of transparency in machine learning through a use case involving a VLGC ship two-stroke propulsion engine. By adhering to the CRISP-DM standard, we fostered close collaboration between marine engineers and machine learning experts to circumvent the common pitfalls of automated ML. The methodology included comprehensive data exploration, cleaning, and verification, followed by feature selection and training of linear regression and decision tree models that are not only transparent but also highly interpretable. The linear model achieved an RMSE of 23.16 and an MRAE of 14.7%, while the accuracy of decision trees ranged between 96.4% and 97.69%. This study demonstrates that machine learning models for predicting propulsion engine fuel consumption can be interpretable, adhering to regulatory requirements, while still achieving adequate predictive performance.

Generalizable and automated classification of TNM stage from pathology reports with external validation

Cancer staging is an essential clinical attribute informing patient prognosis and clinical trial eligibility. However, it is not routinely recorded in structured electronic health records. Here, we present BB-TEN: Big Bird – TNM staging Extracted from Notes, a generalizable method for the automated classification of TNM stage directly from pathology report text. We train a BERT-based model using publicly available pathology reports across approximately 7000 patients and 23 cancer types. We explore the use of different model types, with differing input sizes, parameters, and model architectures. Our final model goes beyond term-extraction, inferring TNM stage from context when it is not included in the report text explicitly. As external validation, we test our model on almost 8000 pathology reports from Columbia University Medical Center, finding that our trained model achieved an AU-ROC of 0.815–0.942. This suggests that our model can be applied broadly to other institutions without additional institution-specific fine-tuning.

SAR-driven flood inventory and multi-factor ensemble susceptibility modelling using machine learning frameworks

Climate change has substantially increased both the occurrence and intensity of flood events, particularly in the Indian subcontinent, exacerbating threats to human populations and economic infrastructure. The present research employed novel ML models—LR, SVM, RF, XGBoost, DNN, and Stacking Ensemble—developed in the Python environment and leveraged 18 flood-influencing factors to delineate flood-prone areas with precision. A comprehensive flood inventory, obtained from Sentinel-1 Synthetic Aperture Radar (SAR) data using the Google Earth Engine (GEE) platform, provided empirical data for entire model training and validation. Model performance was assessed using precision, recall, F1-score, accuracy, and ROC-AUC metrics. The results highlighted Stacking Ensemble’s superior predictive ability (0.965), followed closely by, XGBoost (0.934), DNN (0.929), RF (0.925), LR (0.921), and SVM (0.920) respectively, establishing the feasibility of ML applications in disaster management. The maps depicting susceptibility to flooding generated by the current research provide actionable insights for decision-makers, city planners, and authorities responsible for disaster management, guiding infrastructural and community resilience enhancements against flood risks.

Interpretable machine‐learning models for predicting creep recovery of concrete

AbstractCreep recovery of concrete is essential for accurately assessing the performance of concrete structures over service time. Existing creep recovery models exhibit low accuracy, and the influencing factors of creep recovery remain inadequately elucidated. In this paper, interpretable machine learning (ML) techniques were employed to develop a prediction model for concrete creep recovery. Several ML techniques were selected including random forest (RF), support vector regression (SVR), extreme gradient boosting (XGBoost) and light gradient boosting machine (LGBM). In order to maximize the sample size of the dataset, 109 sets of creep recovery data were collected from existing literatures for model training. Feature selection is utilized to determine the input parameters for ML models, and 12 input variables were selected. The model is fine‐tuned using Bayesian optimization techniques. To ensure the reliability of ML models, 10‐fold cross‐validation and random data splitting were implemented. The results indicate that the ML models exhibited higher accuracy compared to the existing creep recovery model. Among these ML models, LGBM demonstrated superior accuracy, efficiency and stability (with R2 = 0.993, 0.978, and 0.973 for the training, testing, and validation sets, respectively). Shapley additive explanations (SHAP) were employed to interpret the significance of each input parameter on ML model prediction. Duration after unloading, stress magnitude, and ambient relative humidity were the main feature variables influencing concrete creep recovery. Upon comparing the influencing factors, it was discerned that there exists a distinct difference between creep and creep recovery of concrete.

Knowledge abstraction and filtering based federated learning over heterogeneous data views in healthcare

Robust data privacy regulations hinder the exchange of healthcare data among institutions, crucial for global insights and developing generalised clinical models. Federated learning (FL) is ideal for training global models using datasets from different institutions without compromising privacy. However, disparities in electronic healthcare records (EHRs) lead to inconsistencies in ML-ready data views, making FL challenging without extensive preprocessing and information loss. These differences arise from variations in services, care standards, and record-keeping practices. This paper addresses data view heterogeneity by introducing a knowledge abstraction and filtering-based FL framework that allows FL over heterogeneous data views without manual alignment or information loss. The knowledge abstraction and filtering mechanism maps raw input representations to a unified, semantically rich shared space for effective global model training. Experiments on three healthcare datasets demonstrate the framework’s effectiveness in overcoming data view heterogeneity and facilitating information sharing in a federated setup.

Fault Diagnosis Method for Hydropower Units Based on Dynamic Mode Decomposition and the Hiking Optimization Algorithm–Extreme Learning Machine

The diagnosis of vibration faults in hydropower units is essential for ensuring the safe and stable operation of these systems. This paper proposes a fault diagnosis method for hydropower units that combines Dynamic Mode Decomposition (DMD) with an optimized Extreme Learning Machine (ELM) utilizing the Hiking Optimization Algorithm (HOA). To address the issue of noise interference in the vibration signals of hydropower units, this study employs DMD technology alongside a thresholding technique for noise reduction, demonstrating its effectiveness through comparative trials. Furthermore, to facilitate a thorough analysis of the operational status of hydropower units, this paper extracts multidimensional features from denoised signals. To improve the efficiency of model training, Principal Component Analysis (PCA) is applied to streamline the data. Given that the weights and biases of the ELM are generated randomly, which may impact the model’s stability and generalization capabilities, the HOA is introduced for optimization. The HOA-ELM model achieved a classification accuracy of 95.83%. A comparative analysis with alternative models substantiates the superior performance of the HOA-ELM model in the fault diagnosis of hydropower units.

Zone-based many-objective building decarbonization considering outdoor temperature and occupation uncertainty

Operational building decarbonization is challenging due to complex weather conditions and occupation uncertainty. This paper introduces a precise optimization framework integrating the building information modelling technique and intelligent algorithms to dynamically predict multi-scenario building carbon emissions and optimize the building emissions performance considering building zones and weather conditions. Firstly, the on-site data and building information modeling-supported building emissions simulation data are collected for model training. Secondly, using intelligent algorithms, zone-based hourly carbon emissions and multi-scenario carbon emissions prediction are conducted simultaneously. Thirdly, the optimal decarbonization strategies are conducted using intelligent algorithms under various weather conditions. This framework has been verified for decarbonization in a high-rise operational building. The results reveal that: (1) The carbon emissions prediction is highly consistent with the ground truth after considering the sub-zone correlations; the R2 for the west, south, and east zones are 0.900, 0.900, and 0.942, respectively; (2) The surrogate models can accurately predict carbon emissions and thermal comforts with all R2 are higher than 0.912. The optimization rate of the building reaches 59.2 % while the outdoor temperature is above 35 °C. (3) In the many-objective optimization model, considering occupation uncertainty makes the strategy close to the actual situation, reaching the decarbonization by 6815.23 kg compared to the empirical operation for the cooling period. This work provides a new path for operational building precise management and control-oriented optimization decarbonization.

Resource-optimized cnns for real-time rice disease detection with ARM cortex-M microprocessors

This study explores the application of Artificial Intelligence (AI), specifically Convolutional Neural Networks (CNNs), for detecting rice plant diseases using ARM Cortex-M microprocessors. Given the significant role of rice as a staple food, particularly in Malaysia where the rice self-sufficiency ratio dropped from 65.2% in 2021 to 62.6% in 2022, there is a pressing need for advanced disease detection methods to enhance agricultural productivity and sustainability. The research utilizes two extensive datasets for model training and validation: the first dataset includes 5932 images across four rice disease classes, and the second comprises 10,407 images across ten classes. These datasets facilitate comprehensive disease detection analysis, leveraging MobileNetV2 and FD-MobileNet models optimized for the ARM Cortex-M4 microprocessor. The performance of these models is rigorously evaluated in terms of accuracy and computational efficiency. MobileNetV2, for instance, demonstrates a high accuracy rate of 97.5%, significantly outperforming FD-MobileNet, especially in detecting complex disease patterns such as tungro with a 93% accuracy rate. Despite FD-MobileNet’s lower resource consumption, its accuracy is limited to 90% across varied testing conditions. Resource optimization strategies highlight that even slight adjustments, such as a 0.5% reduction in RAM usage and a 1.14% decrease in flash memory, can result in a notable 9% increase in validation accuracy. This underscores the critical balance between computational resource management and model performance, particularly in resource-constrained settings like those provided by microcontrollers. In summary, the deployment of CNNs on microcontrollers presents a viable solution for real-time, on-site plant disease detection, demonstrating potential improvements in detection accuracy and operational efficiency. This study advances the field of smart agriculture by integrating cutting-edge AI with practical agricultural needs, aiming to address the challenges of food security in vulnerable regions.

Border Gateway Protocol Route Leak Detection Technique Based on Graph Features and Machine Learning

In the Internet, ASs are interconnected using BGP. However, due to a lack of security considerations in the design of BGP, a series of security issues arise during the propagation of routing information, such as prefix hijacking, route leakage, and AS path tampering. Therefore, this paper conducts research on the detection of route leakage. By analyzing BGP routing information, we abstract the routing propagation relationship between ASs into a network topology graph, and extract graph features from the graph abstracted from routing data at certain time intervals. Based on the structural robustness features and centrality measurement features of the graph, we determine whether a route leakage has occurred during the current time period. To this end, we use machine learning methods and propose a weighted voting model. This model trains multiple single models and assigns weights to them, and through the weighted analysis of the results of multiple models, it can determine whether a route leakage has occurred. In addition, to determine the corresponding weights, we use genetic algorithms for identifying route leaks. The experimental results show that the method used in this paper has a high accuracy rate, and compared with a single model, it performs better on multiple datasets.

Depression Detection on Mandarin Text through Bert Model

Depression is currently one of the most prevalent mental disorders and its incidence has been rising significantly in Malaysia amid the Covid-19 pandemic. While previous studies have demonstrated the potential of artificial intelligence technology in analysing social media texts to detect signs of depression, most of these studies have focused on English textual content. Considering that Mandarin is the second most widely spoken language worldwide, it is worthwhile to explore depression detection techniques specifically tailored for Mandarin textual content. This research aims to examine the effectiveness of the BERT model in text classification, particularly for detecting depression in Mandarin. The study proposes the utilization of the BERT model to analyse social media posts related to depression. The model is trained using the WU3D dataset, which comprises a collection of over 2 million text data sourced from Sina Weibo, a prominent Chinese social media platform. Given the dataset's inherent imbalance, text augmentation techniques were employed to assess whether they contribute to improved model performance. The findings suggest that the BERT model trained on the original dataset outperformed the model trained on the augmented dataset. This implies that the BERT model is well-equipped to handle imbalanced datasets effectively. Furthermore, it is speculated that the augmented dataset did not introduce novel information or knowledge during the model training process. Notably, the highest-performing model achieved an impressive accuracy rate of 88% on the testing dataset.

Leveraging Deep Learning and Generative AI for Predicting Rheological Properties and Material Compositions of 3D Printed Polyacrylamide Hydrogels.

Artificial intelligence (AI) has the ability to predict rheological properties and constituent composition of 3D-printed materials with appropriately trained models. However, these models are not currently available for use. In this work, we trained deep learning (DL) models to (1) predict the rheological properties, such as the storage (G') and loss (G") moduli, of 3D-printed polyacrylamide (PAA) substrates, and (2) predict the composition of materials and associated 3D printing parameters for a desired pair of G' and G". We employed a multilayer perceptron (MLP) and successfully predicted G' and G" from seven gel constituent parameters in a multivariate regression process. We used a grid-search algorithm along with 10-fold cross validation to tune the hyperparameters of the MLP, and found the R2 value to be 0.89. Next, we adopted two generative DL models named variational autoencoder (VAE) and conditional variational autoencoder (CVAE) to learn data patterns and generate constituent compositions. With these generative models, we produced synthetic data with the same statistical distribution as the real data of actual hydrogel fabrication, which was then validated using Student's t-test and an autoencoder (AE) anomaly detector. We found that none of the seven generated gel constituents were significantly different from the real data. Our trained DL models were successful in mapping the input-output relationship for the 3D-printed hydrogel substrates, which can predict multiple variables from a handful of input variables and vice versa.