Train Machine Learning Models Research Articles

Synthetic Meets Authentic: Leveraging LLM Generated Datasets for YOLO11 and YOLOv10-Based Apple Detection through Machine Vision Sensors

Training machine learning (ML) models for artificial intelligence (AI) and computer vision-based object detection process typically requires large, labeled datasets, a process often burdened by significant human effort and high costs associated with imaging systems and image acquisition. This research aimed to simplify image data collection for object detection in orchards by avoiding traditional fieldwork with different imaging sensors. Utilizing OpenAI's DALLE, a large language model (LLM) for realistic image generation, we generated and annotated a cost-effective dataset. This dataset, exclusively generated by LLM, was then utilized to train two state-of-the-art deep learning models: YOLOV10 and YOLO11. The YOLO11 model for apple detection was trained with its five configurations (YOLO11n, YOLO11s, YOLO11m, YOLO11l and YOLO11x), and YOLOv10 model with its six configurations (YOLOv10n, YOLOv10s, YOLOv10m, YOLOv10b, YOLOv10l and YOLOv10x), which was then tested with real-world (outdoor orchard) images captured by a digital (Nikon D5100) camera and a consumer RGB-D camera (Microsoft Azure Kinect). YOLO11 outperformed YOLOv10 as YOLO11x and YOLO11n exhibited superior precision of 0.917 and 0.916, respectively. Furthermore, YOLO11l demonstrated the highest recall among its counterparts, achieving a recall of 0.889. Likewise, the YOLO11n variant excelled in terms of mean average precision (mAP@50), achieving the highest value of 0.958. Validation tests against actual images collected through a digital camera (Nikon D5100) over Scilate apple variety in a commercial orchard environment showed a highest precision of 0.874 for YOLO11s, recall of 0.877 for YOLO11l and mAP@50 of 0.91 for YOLO11x. Additionally, validation test against actual images collected through a Microsoft Azure camera over the same orchard showed a highest precision, recall and mAP@50 respectively of 0.924, 0.781 and 0.855 with YOLO11x. All variants of YOLO11 surprisingly demonstrated a pre-processing time of just 0.2 milliseconds (ms), which was faster than any variant of YOLOv10. The fastest inference time for the YOLO11n model using the training dataset generated by the language model was 3.2 ms, while YOLOv10n, fastest among YOLOv10 variants, had a longer inference time of 5.5 ms. Likewise, the fastest inference time for the sensor-based images was 7.1 ms (for Nikon D5100 camera images) and 4.7 ms (for Azure images) with YOLO11n. This study presents a pathway for generating large image datasets using LLM in challenging agricultural fields with minimal or no labor-intensive efforts in field data-collection, which could accelerate the development and deployment of computer vision and robotic technologies in orchard environments.

Using Machine Learning and Electronic Health Records to Identify Neuropsychiatric Risk Scores for Delirium in ICU and General Hospital Settings.

Delirium is a common and acute neuropsychiatric syndrome that requires timely intervention to prevent its associated morbidity and mortality. Yet, its diagnosis and symptoms are often overlooked due to its variable clinical presentation and fluctuating nature. Thus, in this study, we address the barriers to delirium diagnosis by utilizing a machine learning-based predictive algorithm for incident delirium that relies on archived electronic health records (EHRs) data. We used the Medical Information Mart for Intensive Care (MIMIC) database to create a detailed dataset for identifying delirium in intensive care unit (ICU) patients. Our approach involved training machine learning models on this dataset to pinpoint critical clinical features for delirium detection. These features were then refined and applied to non-ICU patients using EHRs from the American University of Beirut Medical Center (AUBMC). Our study assessed machine learning models like Extreme Gradient Boosting (XGBoost), Categorical Boosting (CatBoost), Classification and Regression Trees (CART), Random Forest (RF), Neural Oblivious Decision Ensembles (NODE), and Logistic Regression (LR), highlighting superior delirium detection in diverse clinical settings. The CatBoost model excelled in ICU environments with an F1 Score of 89.2%, while XGBoost performed best in general hospital settings with a 75.4% F1 Score. Interpretations using Tabular Local Interpretable Model-agnostic Explanations (LIME) revealed critical indicators such as prothrombin time and hematocrit levels, enhancing model transparency and clinical applicability. These clinical insights help differentiate the delirium predictors between ICU patients, who are often sensitive to various factors. The proposed predictive algorithm improves delirium detection rates and streamlines efficiency in hospital electronic systems, thereby enabling prompt interventions to prevent delirium progression and associated complications. The clinical indicators for delirium that we identified in general hospital settings and ICU can greatly help healthcare professionals identify potential causes of delirium and reduce misdiagnosis.

EEG-based responses of patients with disorders of consciousness and healthy controls to familiar and non-familiar emotional videos

ObjectiveTo investigate the differences in the brain responses of healthy controls (HC) and patients with disorders of consciousness (DOC) to familiar and non-familiar audiovisual stimuli and their consistency with the clinical progress. MethodsEEG responses of 19 HC and 19 patients with DOC were recorded while watching emotionally-valenced familiar and non-familiar videos. Differential entropy of the EEG recordings was used to train machine learning models aimed to distinguish brain responses to stimuli type. The consistency of brain responses with the clinical progress of the patients was also evaluated. ResultsModels trained using data from HC outperformed those for patients. However, the performance of the models for patients was not influenced by their clinical condition. The models were successfully trained for over 75% of participants, regardless of their clinical condition. More than 75% of patients whose CRS-R scores increased post-study displayed distinguishable brain responses to both stimuli. ConclusionsResponses to emotionally-valenced stimuli enabled modelling classifiers that were sensitive to the familiarity of the stimuli, regardless of the clinical condition of the participants and were consistent with their clinical progress in most cases. SignificanceEEG responses are sensitive to familiarity of emotionally-valenced stimuli in HC and patients with DOC.

S841 Training Machine Learning Models for the Assessment of the Endoscopic Mayo Score in Ulcerative Colitis: A Systematic Review

S841 Training Machine Learning Models for the Assessment of the Endoscopic Mayo Score in Ulcerative Colitis: A Systematic Review

A critical reflection on attempts to machine-learn materials synthesis insights from text-mined literature recipes.

Synthesis of predicted materials is the key and final step needed to realize a vision of computationally accelerated materials discovery. Because so many materials have been previously synthesized, one would anticipate that text-mining synthesis recipes from the literature would yield a valuable dataset to train machine-learning models that can predict synthesis recipes for new materials. Between 2016 and 2019, the corresponding author (Wenhao Sun) participated in efforts to text-mine 31 782 solid-state synthesis recipes and 35 675 solution-based synthesis recipes from the literature. Here, we characterize these datasets and show that they do not satisfy the "4 Vs" of data-science-that is: volume, variety, veracity and velocity. For this reason, we believe that machine-learned regression or classification models built from these datasets will have limited utility in guiding the predictive synthesis of novel materials. On the other hand, these large datasets provided an opportunity to identify anomalous synthesis recipes-which in fact did inspire new hypotheses on how materials form, which we later validated by experiment. Our case study here urges a re-evaluation on how to extract the most value from large historical materials-science datasets.

Federated learning: A cutting-edge survey of the latest advancements and applications

Robust machine learning (ML) models can be developed by leveraging large volumes of data and distributing the computational tasks across numerous devices or servers. Federated learning (FL) is a technique in the realm of ML that facilitates this goal by utilizing cloud infrastructure to enable collaborative model training among a network of decentralized devices. Beyond distributing the computational load, FL targets the resolution of privacy issues and the reduction of communication costs simultaneously. To protect user privacy, FL requires users to send model updates rather than transmitting large quantities of raw and potentially confidential data. Specifically, individuals train ML models locally using their own data and then upload the results in the form of weights and gradients to the cloud for aggregation into the global model. This strategy is also advantageous in environments with limited bandwidth or high communication costs, as it prevents the transmission of large data volumes. With the increasing volume of data and rising privacy concerns, alongside the emergence of large-scale ML models like Large Language Models (LLMs), FL presents itself as a timely and relevant solution. It is therefore essential to review current FL algorithms to guide future research that meets the rapidly evolving ML demands. This survey provides a comprehensive analysis and comparison of the most recent FL algorithms, evaluating them on various fronts including mathematical frameworks, privacy protection, resource allocation, and applications. Beyond summarizing existing FL methods, this survey identifies potential gaps, open areas, and future challenges based on the performance reports and algorithms used in recent studies. This survey enables researchers to readily identify existing limitations in the FL field for further exploration.

Classification of Alzheimer’s Disease and Frontotemporal Dementia Using Electroencephalography to Quantify Communication between Electrode Pairs

Accurate diagnosis of dementia subtypes is crucial for optimizing treatment planning and enhancing caregiving strategies. To date, the accuracy of classifying Alzheimer’s disease (AD) and frontotemporal dementia (FTD) using electroencephalogram (EEG) data has been lower than that of distinguishing individuals with these diseases from healthy elderly controls (HCs). This limitation has impeded the feasibility of a cost-effective differential diagnosis for the two subtypes in clinical settings. This study addressed this issue by quantifying communication between electrode pairs in EEG data, along with demographic information, as features to train machine learning (support vector machine) models. Our focus was on refining the feature set specifically for AD-FTD classification. Using our initial feature set, we achieved classification accuracies of 76.9% for AD-HC, 90.4% for FTD-HC, and 91.5% for AD-FTD. Notably, feature importance analyses revealed that the features influencing AD-HC classification are unnecessary for distinguishing between AD and FTD. Eliminating these unnecessary features improved the classification accuracy of AD-FTD to 96.6%. We concluded that communication between electrode pairs specifically involved in the neurological pathology of FTD, but not AD, enables highly accurate EEG-based AD-FTD classification.

Improved Data Privacy with Differential Privacy in Federated Learning

Multiple users may train machine learning models cooperatively using Federated Learning (FL). There is a risk of malicious acquisition of participants' personal data due to the fact that traditional machine learning needs users to provide data for training. Through the use of federated learning, which involves moving the training process from a central server to terminal devices, users' data may be protected. Each participant keeps their dataset local and only exchanges model updates. This research proposed an innovative proposal for the medical industry's differentiated privacy approach for overcoming these problems. When several healthcare organizations work together to develop models that use different and extensive information, clinical applications may be greatly enhanced. Thus, the Local and Centre Differential Privacy (LCDP) on clinical datasets is a feature of our proposed approach. Reason being that the training data is the primary emphasis of the local model, while the machine learning model is the primary focus of the central model. We discover that the local model and the central model are linked in a unique way, changes in the original data lead to changes in the gradient, which in turn lead to changes in the model parameters. Based on this finding, our technique is better than prior central methods since it protects the data, gradient, and model all at once by bridging the gap between the two. Our system provides better privacy protections and even higher performance than some of the best previous central methods, which is an excellent outcome of rigorous evaluation.

Assessment of Machine Learning Techniques for Simulating Reacting Flow: From Plasma-Assisted Ignition to Turbulent Flame Propagation

Combustion involves the study of multiphysics phenomena that includes fluid and chemical kinetics, chemical reactions and complex nonlinear processes across various time and space scales. Accurate simulation of combustion is essential for designing energy conversion systems. Nonetheless, due to its multiscale, multiphysics nature, simulating these systems at full resolution is typically difficult. The massive and complex data generated from experiments and simulations, particularly in turbulent combustion, presents both a challenge and a research opportunity for advancing combustion studies. Machine learning facilitates data-driven techniques to manage the substantial amount of combustion data that is either obtained through experiments or simulations, and thereby can find the hidden patterns underlying these data. Alternatively, machine learning models can be useful to make predictions with comparable accuracy to existing models, while reducing computational costs significantly. In this era of big data, machine learning is rapidly evolving, offering promising opportunities to explore its integration with combustion research. This work provides an in-depth overview of machine learning applications in turbulent combustion modeling and presents the application of machine learning models: Decision Trees (DT) and Random Forests (RF), for the spatio-temporal prediction of plasma-assisted ignition kernels, based on the initial degree of ionization, with model validations against DNS data. The results demonstrate that properly trained machine learning models can accurately predict the spatio-temporal ignition kernel profile based on the initial energy deposition and distribution.

Cross-device Portability of Machine Learning Models in Electromagnetic Side-Channel Analysis for Forensics

The possession of smart devices has ingrained itself into daily life. Therefore, smart devices, such as IoT and smartphones, are crucial sources of evidence in instances where criminal activity occurs. Due to the challenges in traditional digital forensic techniques involving smart devices, it has been recently proposed in the literature to leverage electromagnetic side-channel analysis (EM-SCA) for the purpose. This paper identifies and discusses an important barrier that exists in the application of EM-SCA for digital forensics that hinders its successful use, namely, the issue of cross-device portability of machine learning (ML) models that are used for EM-SCA. Firstly, the paper empirically evaluates the possibility of using trained ML models to extract forensic insights from EM radiation data of IoT devices. During this empirical study, the inability to reuse a trained ML model across different devices is identified. Secondly, the paper surveys the literature in search of related work that has studied the use of EM-SCA to gather information from smart devices. The purpose of the survey is to identify whether any existing work has been able to introduce potential approaches to enable cross-device portability of ML models in EM-SCA. The findings of this survey point to the fact that the identified problem still exists and requires further studies opening the door to future research.

Transfer learning-enabled outcome prediction for guiding CRRT treatment of the pediatric patients with sepsis

Continuous renal replacement therapy (CRRT) is a life-saving procedure for sepsis but the benefit of CRRT varies and prediction of clinical outcomes is valuable in efficient treatment planning. This study aimed to use machine learning (ML) models trained using MIMIC III data for identifying sepsis patients who would benefit from CRRT. We first selected patients with sepsis and CRRT in the ICU setting and their gender, and an array of routine lab results were included as features to train machine learning models using 30-day mortality as the primary outcome. A total of 4161 patients were included for analysis, among whom there were 1342 deaths within 30 days. Without data augmentation, extreme gradient boosting (XGBoost) showed an accuracy of 64.2% with AUC-ROC of 0.61. Data augmentation using a conditional generative adversarial neural network (c-GAN) resulted in a significantly improved accuracy (82%) and ROC-AUC (0.78%). To enable prediction on pediatric patients, we adopted transfer learning approaches, where the weights of all but the last hidden layer were fixed, followed by fine-tuning of the weights of the last hidden layer using pediatric data of 200 patients as the inputs. A significant improvement was observed using the transfer learning approach (AUCROC = 0.76) compared to direct training on the pediatric cohort (AUCROC = 0.62). Through this transfer-learning-facilitated patient outcome prediction, our study showed that ML can aid in clinical decision-making by predicting patient responses to CRRT for managing pediatric sepsis.

Hospital Re-Admission Prediction Using Named Entity Recognition and Explainable Machine Learning.

Early hospital readmission refers to unplanned emergency admission of patients within 30 days of discharge. Predicting early readmission risk before discharge can help to reduce the cost of readmissions for hospitals and decrease the death rate for Intensive Care Unit patients. In this paper, we propose a novel approach for prediction of unplanned hospital readmissions using discharge notes from the MIMIC-III database. This approach is based on first extracting relevant information from clinical reports using a pretrained Named Entity Recognition model called BioMedical-NER, which is built on Bidirectional Encoder Representations from Transformers architecture, with the extracted features then used to train machine learning models to predict unplanned readmissions. Our proposed approach achieves better results on clinical reports compared to the state-of-the-art methods, with an average precision of 88.4% achieved by the Gradient Boosting algorithm. In addition, explainable Artificial Intelligence techniques are applied to provide deeper comprehension of the predictive results.

Critical insights into data curation and label noise for accurate prediction of aerobic biodegradability of organic chemicals.

The focus of this work is to enhance state-of-the-art Machine Learning (ML) models that can predict the aerobic biodegradability of organic chemicals through a data-centric approach. To do that, an already existing dataset that was previously used to train ML models was analyzed for mismatching chemical identifiers and data leakage between test and training set and the detected errors were corrected. Chemicals with high variance between study results were removed and an XGBoost was trained on the dataset. Despite extensive data curation, only marginal improvement was achieved in the classification model's performance. This was attributed to three potential reasons: (1) a significant number of data labels were noisy, (2) the features could not sufficiently represent the chemicals, and/or (3) the model struggled to learn and generalize effectively. All three potential reasons were examined and point (1) seemed to be the most decisive one that prevented the model from generating more accurate results. Removing data points with possibly noisy labels by performing label noise filtering using two other predictive models increased the classification model's balanced accuracy from 80.9% to 94.2%. The new classifier is therefore better than any previously developed classification model for ready biodegradation. The examination of the key characteristics (molecular weight of the substances, proportion of halogens present and distribution of degradation labels) and the applicability domain indicate that no/not a large share of difficult-to-learn substances has been removed in the label noise filtering, meaning that the final model is still very robust.

Improving machine-learning models in materials science through large datasets

The accuracy of a machine learning model is limited by the quality and quantity of the data available for its training and validation. This problem is particularly challenging in materials science, where large, high-quality, and consistent datasets are scarce. Here we present alexandria, an open database of more than 5 million density-functional theory calculations for periodic three-, two-, and one-dimensional compounds. We use this data to train machine learning models to reproduce seven different properties using both composition-based models and crystal-graph neural networks. In the majority of cases, the error of the models decreases monotonically with the training data, although some graph networks seem to saturate for large training set sizes. Differences in the training can be correlated with the statistical distribution of the different properties. We also observe that graph-networks, that have access to detailed geometrical information, yield in general more accurate models than simple composition-based methods. Finally, we assess several universal machine learning interatomic potentials. Crystal geometries optimised with these force fields are very high quality, but unfortunately the accuracy of the energies is still lacking. Furthermore, we observe some instabilities for regions of chemical space that are undersampled in the training sets used for these models. This study highlights the potential of large-scale, high-quality datasets to improve machine learning models in materials science.

Evaluating the Reliability of Machine Learning Predictors in m6A-SNP Association Analysis: A Comparative Study Using m6A-QTL Data

Introduction: N6-Methyladenosine (m6A) plays a crucial role in determining the fate of RNA after transcription. Understanding the downstream functions of individual m6A sites is of critical interest in epitranscriptomics. In published studies, two main approaches have been used to decipher the specific impact of m6A sites on gene expression and disease/traits: the m6A quantitative trait loci (m6A-QTL) and in-silico mutation prediction by Machine Learning (ML) models. However, earlier works still lack independent validation for the performance of ML-based methods. Methods: In this study, we use m6A-QTL as ground truth to evaluate the outcomes of in-silico mutation models. We benchmark both the newly trained machine learning models using genomic or sequence features and the existing model inference results published in in-silico mutationdependent databases against m6A-QTL. Results: We found that the consistency between in-silico mutation and m6A-QTL is weak, regardless of the ML algorithms and predictive features used. This trend was also consistent across multiple published databases based on in-silico mutation, including RMDisease2, m6AVar, and RMVar. Conclusion: These results highlight the importance of critical empirical evaluations for ML models in future SNP-m6A association studies and suggest the need for more high-quality m6A-QTL experiments to guide model development.

Mosna reveals different types of cellular interactions predictive of response to immunotherapies and survival in cancer.

Spatially resolved omics enable the discovery of tissue organization of biological or clinical importance. Despite the existence of several methods, performing a rational analysis including multiple algorithms while integrating different conditions such as clinical data is still not trivial. To make such investigations more accessible, we developed mosna, a Python package to analyze spatial omics data with respect to clinical or biological data and to gain insight on cell interaction patterns or tissue architecture of biological relevance. mosna is compatible with all spatial omics methods, it leverages tysserand to build accurate spatial networks, and is compatible with Squidpy. It proposes an analysis pipeline, in which increasingly complex features computed at each step can be explored in integration with clinical data, either with easy-to-use descriptive statistics and data visualization, or by seamlessly training machine learning models and identifying variables with the most predictive power. mosna can take as input any dataset produced by spatial omics methods, including sub-cellular resolved transcriptomics (MERFISH, seqFISH) and proteomics (CODEX, MIBI-TOF, low-plex immuno-fluorescence), as well as spot-based spatial transcriptomics (10x Visium). Integration with experimental metadata or clinical data is adapted to binary conditions, such as biological treatments or response status of patients, and to survival data. We demonstrate the proposed analysis pipeline on two spatially resolved proteomic datasets containing either binary response to immunotherapy or survival data. mosna identifies features describing cellular composition and spatial distribution that can provide biological insight regarding factors that affect response to immunotherapies or survival.

On the Inference of Original Graph Information from Graph Embeddings

Graph embedding converts a graph data into a low dimensional space to preserve the original graph information. However, graph data can be reconstructed by malicious adversaries to train machine learning models from graph embeddings. This paper studies to what extent an adversary (without the original graph data) can recover the original graph data from graph embeddings. To quantify the original graph information leakage from graph embeddings, we develop a deep neural network model InferNet that can be used by adversaries to infer the original graph information from an adversary-accessible graph embedding database. More specifically, we propose the data-free reversed knowledge distillation technique to support the InferNet training even if the original graph dataset is absent. To ensure the performance of InferNet, we design two cycle-consistency loss functions to have an interactive training of InferNet over three series of datasets. To further enhance the performance of InferNet, we provide a joint training algorithm that simultaneously trains the pseudo-sample generator and InferNet, which significantly reduces the storage space. We evaluate the performance of InferNet on three datasets, and the intensive experiments demonstrate that InferNet can infer the original graph information from the graph embedding dataset with high accuracy.

Supervised Machine Learning Techniques for Breeding Value Prediction in Horses: An Example Using Gait Visual Scores.

Gait scores are widely used in the genetic evaluation of horses. However, the nature of such measurement may limit genetic progress since there is subjectivity in phenotypic information. This study aimed to assess the application of machine learning techniques in the prediction of breeding values for five visual gait scores in Campolina horses: dissociation, comfort, style, regularity, and development. The dataset contained over 5000 phenotypic records with 107,951 horses (14 generations) in the pedigree. A fixed model was used to estimate least-square solutions for fixed effects and adjusted phenotypes. Variance components and breeding values (EBV) were obtained via a multiple-trait model (MTM). Adjusted phenotypes and fixed effects solutions were used to train machine learning models (using the EBV from MTM as target variable): artificial neural network (ANN), random forest regression (RFR) and support vector regression (SVR). To validate the models, the linear regression method was used. Accuracy was comparable across all models (but it was slightly higher for ANN). The highest bias was observed for ANN, followed by MTM. Dispersion varied according to the trait; it was higher for ANN and the lowest for MTM. Machine learning is a feasible alternative to EBV prediction; however, this method will be slightly biased and over-dispersed for young animals.

Hepatic Transcriptome Reveals Potential Key Genes Contributing to Differential Milk Production.

Despite the widespread adoption of TMR or PMR and the formulas designed to sufficiently cover the cows' requirements, individual dairy cows' milk production varies significantly. The liver is one of the most important organs in cow lactation metabolism and plays an essential role in the initiation of lactation. This study aimed to investigate the potential key genes in the liver contributing to the different milk production. We enrolled 64 cows and assigned them to high or low milk yield (MY) groups according to their first 3 weeks of milk production. We performed RNAseq for 35 liver samples with 18 from prepartum and 17 from postpartum cows. The continuous milk yield observation showed a persistently higher milk yield in high MY cows than low MY cows in the first 3 weeks. High MY cows showed better feed conversion efficiency. We identified 795 differentially expressed genes (DGEs) in the liver of high MY cows compared with low MY cows, with up-regulated genes linked to morphogenesis and development pathways. Weighted gene co-expression network analysis (WGCNA) revealed four gene modules positively correlating with milk yield, and protein and lactose yield (p < 0.05). Using the intersected genes between the four gene modules and DEGs, we constructed the linear mixed-effects models and identified six hub genes positively associated and two hub genes negatively associated with milk yield (Coefficients > 0.25, p < 0.05). Random forest machine learning model training based on these eight hub genes could efficiently predict the milk yield (p < 0.001, R2 = 0.946). Interestingly, the expression patterns of these eight hub genes remained remarkably similar before and after parturition. The present study indicated the critical role of liver in milk production. Activated processes involved in morphogenesis and development in liver may contribute to the higher milk production. Eight hub genes identified in this study may provide genetic research materials for dairy cow breeding.

A multi-stage lithium-ion battery aging dataset using various experimental design methodologies

This dataset encompasses a comprehensive investigation of combined calendar and cycle aging in commercially available lithium-ion battery cells (Samsung INR21700-50E). A total of 279 cells were subjected to 71 distinct aging conditions across two stages. Stage 1 is based on a non-model-based design of experiments (DoE), including full-factorial and Latin hypercube experimental designs, to determine the degradation behavior. Stage 2 employed model-based parameter individual optimal experimental design (pi-OED) to refine specific dependencies, along with a second non-model-based approach for fair comparison of DoE methodologies. While the primary aim was to validate the benefits of optimal experimental design in lithium-ion battery aging studies, this dataset offers extensive utility for various applications. They include training of machine learning models for battery life prediction, calibrating of physics-based or (semi-)empirical models for battery performance and degradation, and numerous other investigations in battery research. Additionally, the dataset has the potential to uncover hidden dependencies and correlations in battery aging mechanisms that were not evident in previous studies, which often relied on pre-existing assumptions and limited experimental designs.