Learning Modeling Research Articles

The Personalized System of E-Modul Instructions in Physical Education Online Learning

The Covid-19 pandemic has disrupted the world of education which has made schools implement online learning. This situation is very challenging for Physical Education (PE) course. The study purpose was to examine the condition of physical education online learning and the needs of teachers for electronic modules based on personalized system of learning instruction models in PE online learning. Materials and methods This study used Research and Development (R&D) method with qualitative and quantitative setting using questionnaire as an instrument. 61 of 86 respondents responded and filled out the questionnaire completely between 7-14 October 2021. Results Three main findings were highlighted in this study. Firstly, the condition of PE online learning has not been effective during the Covid-19 pandemic. Teachers experienced several obstacles in implementing PE online learning. Secondly, teachers need e-modules as material for student learning independently at home. Lastly, it is necessary to apply a personalized system of instruction learning model in PE online learning. This model is believed to be appropriate and effective as an independent learning model. Conclusions PE online learning has not been effective so far. An electronic module based on a personalized system of instruction is needed to support the implementation of PE online learning. Keywords: physical education, online learning, e-module, personalized system, instruction.

Optimization of Early Detection of Tuberculosis Through Machine Learning Using Clinical Data: Development and Evaluation of Multilayer Perceptron and Extreme Learning Machine for Tuberculosis Classification

This research takes an innovative step in the fight against Tuberculosis (TB), one of Indonesia's prominent public health challenges, by developing and evaluating Multilayer Perceptron (MLP) and Extreme Learning Machine (ELM) models in machine learning for early detection of TB using clinical data. The main result of this study was the discovery that the MLP model, when applied without the Synthetic Minority Over-sampling Technique (SMOTE), achieved an impressive accuracy of 95.00%, signaling significant progress in TB early detection efforts. This discovery not only highlights the great potential of applying machine learning technology in improving the accuracy of TB diagnosis but also paves the way for the possible application of advanced technology in the health sector to deal with infectious diseases. This research illustrates how machine learning technology can be integrated into clinical practice to effectively detect TB cases at an early stage, thus enabling faster and more precise treatment, which can ultimately reduce the spread of the disease. This is particularly important given TB's significant impact on public health, especially in developing countries. The results also open up opportunities for further research into the application of machine learning techniques to other infectious diseases, promising a paradigm shift in the way we detect and manage various health conditions.

Identifying player skill of dota 2 using machine learning pipeline

The esports industry is one of the prominent business sectors in the digital era, particularly, Multiplayer Online Battle Arena (MOBA) games which gain much attention from gamers and streaming audiences. Among such games, Defense of the Ancient 2 or Dota 2 is the record holder for the highest prize esports tournament. Therefore, various companies and investors start their esports teams to compete in the Dota 2 tournaments, the Internationals. To success in the competition, player recruitment is a crucial process as it usually takes considerable effort to find a skillful player. Watching the game replay to evaluate the player’s skill is one of the approaches. However, it can be too exhaustive, also some player’s ranking, which represent the player’s skill, are often not available. In this paper, we propose an effective machine learning pipeline to evaluate the player’s skill. Our designed pipeline includes data collection, feature engineering, and machine learning modeling. We show the data collection process using open-source API. An effective method for feature engineering is proposed. Features, e.g., end-game, or tactical decision related statistics, are incorporated along with the resource in the game distribution, harassment tactic, or spatiotemporal features, in order to provide effective models. Subsequently, we apply major machine learning models based on a single game data, i.e., logistic regression and random forest, to the processed data. The most effective model can achieve up to 0.7091 precision, 0.5850 recall, 0.6411 F1-score, and 0.8123 ROC AUC score.

Loss-optimal classification trees: a generalized framework and the logistic case

Classification trees are one of the most common models in interpretable machine learning. Although such models are usually built with greedy strategies, in recent years, thanks to remarkable advances in mixed-integer programming (MIP) solvers, several exact formulations of the learning problem have been developed. In this paper, we argue that some of the most relevant ones among these training models can be encapsulated within a general framework, whose instances are shaped by the specification of loss functions and regularizers. Next, we introduce a novel realization of this framework: specifically, we consider the logistic loss, handled in the MIP setting by a piece-wise linear approximation, and couple it with ℓ1\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\ell _1$$\\end{document}-regularization terms. The resulting optimal logistic classification tree model numerically proves to be able to induce trees with enhanced interpretability properties and competitive generalization capabilities, compared to the state-of-the-art MIP-based approaches.

Scanning the aged to minimize missed injury: An EAST multicenter study.

Despite the high incidence of blunt trauma in older adults, there is a lack of evidence-based guidance for computed tomography (CT) imaging in this population. We aimed to identify an algorithm to guide use of a Pan-Scan (Head/C-spine/Torso) or a Selective Scan (Head/C-spine ± Torso). We hypothesized that a patient's initial history and exam could be used to guide imaging. We prospectively studied blunt trauma patients aged 65+ at 18 Level I/II trauma centers. Patients presenting >24 h after injury or who died upon arrival were excluded. We collected history and physical elements and final injury diagnoses. Injury diagnoses were categorized into CT body regions of Head/C-spine or Torso (chest, abdomen/pelvis, and T/L spine). Using machine learning and regression modeling as well as a priori clinical algorithms based, we tested various decision rules against our dataset. Our priority was to identify a simple rule which could be applied at the bedside, maximizing sensitivity (Sens) and negative predictive value (NPV) to minimize missed injuries. We enrolled 5,498 patients with 3,082 injuries. Nearly half (47.1%, n = 2,587) had an injury within the defined CT body regions. No rule to guide a Pan-Scan could be identified with suitable Sens/NPV for clinical use. A clinical algorithm to identify patients for Pan-Scan, using a combination of physical exam findings and specific high-risk criteria, was identified and had a Sens of 0.94 and NPV of 0.86 This rule would have identified injuries in all but 90 patients (1.6%) and would theoretically spare 11.9% (655) of blunt trauma patients a torso CT. Our findings advocate for Head/Cspine CT in all geriatric patients with the addition of torso CT in the setting of positive clinical findings and high-risk criteria. Prospective validation of this rule could lead to streamlined diagnostic care of this growing trauma population. Level 2, Diagnostic Tests or Criteria.

Multi-Endpoint Acute Toxicity Assessment of Organic Compounds Using Large-Scale Machine Learning Modeling.

In recent years, alternative animal testing methods such as computational and machine learning approaches have become increasingly crucial for toxicity testing. However, the complexity and scarcity of available biomedical data challenge the development of predictive models. Combining nonlinear machine learning together with multicondition descriptors offers a solution for using data from various assays to create a robust model. This work applies multicondition descriptors (MCDs) to develop a QSTR (Quantitative Structure-Toxicity Relationship) model based on a large toxicity data set comprising more than 80,000 compounds and 59 different end points (122,572 data points). The prediction capabilities of developed single-task multi-end point machine learning models as well as a novel data analysis approach with the use of Convolutional Neural Networks (CNN) are discussed. The results show that using MCDs significantly improves the model and using them with CNN-1D yields the best result (R2train = 0.93, R2ext = 0.70). Several structural features showed a high level of contribution to the toxicity, including van der Waals surface area (VSA), number of nitrogen-containing fragments (nN+), presence of S-P fragments, ionization potential, and presence of C-N fragments. The developed models can be very useful tools to predict the toxicity of various compounds under different conditions, enabling quick toxicity assessment of new compounds.

A novel dynamic ensemble of numerical weather prediction for multi-step wind speed forecasting with deep reinforcement learning and error sequence modeling

Accurate wind forecasts for one day ahead or longer periods have significant impacts on the safe and efficient dispatch of power grids, where Numerical Weather Prediction (NWP) serves as the essential tool, such as ensemble NWP integrating multiple single simulations. Typically, ensembles include all single members with fixed weights; however, the relative accuracy of each member may change over time. This study introduces an attractive idea: improving ensemble performance by dynamically recognizing and avoiding low-performing members. It proposes a dynamic ensemble strategy based on NWP, reinforcement learning and error sequence correction. The process begins with Weather Research and Forecasting ensemble simulations. A dynamic framework is then constructed by mapping the multi-step ensemble problem into a Markov decision process, which is further solved using deep deterministic policy gradient. Subsequently, a hybrid deep learning model, comprising temporal convolutional network and bidirectional long short-term memory, is constructed for error sequence estimation of dynamic ensemble, using the high-frequency information of NWP as input. Conducting experiments at two wind farms, and focusing on the 24-h wind speed forecast with a 15-min time resolution, the proposed system demonstrates a reliable and stable ensemble throughout the entire forecasting horizon, significantly reducing the probability of large forecasting errors.

Machine Learning Modeling for Forecasting Repeat Purchases in Online Shopping

Online shopping merchants will conduct a series of marketing activities to increase customers, but in many cases, most of the new customers will not make repeat purchases, which is not conducive to the long-term interests of the merchants. Therefore, it is important for merchants to target users who are more likely to repurchase, as this can reduce marketing costs and increase ROI. Based on the dataset provided by the online shopping website, this paper conducts mining and exploratory analysis of the data, utilizes feature engineering methodology, and modeling analysis using LightGBM, Logistic, Xgboost for machine learning modeling. Meanwhile, parameter optimization and model evaluation verification are performed, Finally, the comparative analysis resulted in LightGBM as the best prediction model, will provide efficient marketing decisions for the operation of online shopping stores.

Can machine learning assist in systemic sclerosis diagnosis and management? A scoping review

This scoping review aims to summarize the existing literature on how machine learning can be used to impact systemic sclerosis diagnosis, management, and treatment. Following Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews (PRISMA-ScR) reporting guidelines, Embase, Web of Science, Medline (PubMed), IEEE Xplore, and ACM Digital Library were searched from inception to 3 March 2024, for primary literature reporting on machine learning models in any capacity regarding scleroderma. Following robust triaging, 11 retrospective studies were included in this scoping review. Three studies focused on the diagnosis of scleroderma to influence preferred management and nine studies on treatment and predicting treatment response to scleroderma. Nine studies used supervision in their machine learning model training; two used supervised and unsupervised training and one used solely unsupervised training. A total of 817 patients were included in the data sets. Seven of the included articles used patients from the United States, one from Belgium, two from Japan, and two from China. Although currently limited to retrospective studies, the results indicate that machine learning modeling may have a role in early diagnosis, management, therapeutic decision-making, and in the development of future therapies for systemic sclerosis. Prospective studies examining the use of machine learning in clinical practice are recommended to confirm the utility of machine learning in patients with systemic sclerosis.

#2067 Prediction of gastrointestinal bleeding hospitalization risk in hemodialysis using machine learning techniques

Abstract Background and Aims INitiativeS on advancing Patients’ outcomes In REnal disease (INSPIRE) is an academia and industry collaboration set forth to identify critical investigations needed to advance the practice of medicine in nephrology. Gastrointestinal bleeding (GIB) is one of the most common types of bleeding events in the kidney dialysis population [1]. We aimed to develop a model to predict GIB hospitalization risk in a hemodialysis (HD) patient within 180 days. We evaluated advanced machine learning algorithm (XGBoost) and compared it to traditional machine learning algorithm (logistic regression) modeling techniques. Method We used data from a kidney care network from 2017 through 2020. We included data from adult dialysis patients (age ≥18 years). GIB related hospitalization was defined based on international classification of diseases (ICD) diagnosis codes recorded as the primary, secondary, or tertiary discharge reason for hospitalization. Two distinct models were created using XGBoost and logistic regression algorithms and using the same dataset. Both models were evaluated using metrics such as area under the receiver operating curve (AUROC), accuracy, sensitivity, and specificity. Missing data was imputed using mean for quantitative data and mode for qualitative data. The dataset then was randomly divided into 60% training, 20% validation and 20% test dataset. The test data, comprising unseen patients and data was used to evaluate the performance of the model. This means that the model had never encountered the test data during its learning phase, which included training the model and then validating the model. Results The incidence of 180-day GIB hospitalization was 1.12% in the HD population (n = 5 116 with GIB hospitalization/ n = 451 653 without GIB hospitalization), and consistent in the unseen test dataset (n = 465 with GIB hospitalization/ n = 38586 without GIB hospitalization). The XGBoost model showed higher predictive performance compared to logistic regression (Table). The AUROC was 0.72 (95% confidence interval (CI) 0.69, 0.74) for the XGBoost model. In comparison, the AUROC was 0.615 (95% CI 0.60, 0.64) for the logistic regression model. Specificity was 67% versus 58% for the XGBoost model versus logistic regression model respectively. However, sensitivity for both the models was 65%. The top predictors for major GIB were consistent in both models for many factors, yet some factors showed different importance on outcome prediction (Fig. 1). Higher risk of GIB hospitalization was associated with older age, lower ferritin levels, and recent all-cause hospitalizations in both models. The XGBoost showed high importance on outcome prediction for lower hemoglobin and higher serum 25 hydroxy (25OH) vitamin D values, and the logistic regression model showed high importance for higher amounts of saline delivered during an HD treatment and lower intact parathyroid hormone (iPTH) levels. Conclusion We found advanced machine learning prediction modeling (XGBoost) appears suitable for identifying a HD patient at risk for a GIB hospitalization in the next 180 days, and outperforms traditional machine learning (logistic regression) modeling techniques. Although both models showed identical sensitivity, the XGBoost model had higher specificity. Prospective testing is needed to confirm the model's performance. The association between bone mineral metabolism markers and GIB hospitalization risk is unexpected and warrants further investigation.

Machine learning modeling of lake chlorophyll content in a data scarce region (Northern Patagonia, Chile): insights for environmental monitoring

Among South America, Chile is highly susceptible to climate change impacts on water resources and ecosystems. Chilean lakes and rivers have been impacted by anthropogenic activities leading to chemical pollution and eutrophication. Concerns for conservation and management of water resources has led to the current development of secondary norms for environmental quality of Northern Patagonian lakes. In this context, we analyze historical limnological databases (1979-2022) for these lakes utilizing Random Forest (RF) models. After filtering, we retained data for 11 lakes including key variables of: dissolved oxygen, electric conductivity, transparency, temperature, pH, total nitrogen, total phosphorus and chlorophyll-a. This dataset yielded robust results, accurately predicting chlorophyll-a content. Furthermore, we added lake geomorphological parameters, enhancing the performance of the model. Our study demonstrates the need to improve long-term monitoring programs, optimizing environmental data recording and decreasing costs. We conclude that the studied lakes generally maintain their oligotrophic characteristics, however further analysis suggests that these lakes are more sensitive to nitrogen loading than phosphorus. Our results highlight the need to implement adaptative management plans at the watershed level to regulate anthropogenic nitrogen contamination (from agriculture, pisciculture and urbanization). The features selected by RF, coupled with the assessment of historical trophic state variation, allow the establishment of permissible concentration thresholds for major nutrients and other sentinel parameters, informing the development of regulations such as the secondary norms for environmental quality. Lastly, the enhanced performance of RF modeling when including geographical parameters unveils the need to standardize and integrate geographical data in monitoring practices.

Efficient and easily recyclable photocatalytic reduction of Se(IV) from wastewater using stable TiO2/BiOBr/cloth: Mechanism insight and machine learning modeling

Photocatalytic technology is extensively employed for the reductive removal of water contaminants; however, it contends with low catalytic efficiency and challenges in catalyst recovery. In this study, we propose integrating experimental procedures with artificial intelligence modeling to enhance the purification of Se(IV)-contaminated wastewater. We present an efficient, easily recyclable, and cost-effective strategy for photocatalyst fabrication. Specifically, we develop a novel method for Se(IV) removal by immobilizing TiO2/BiOBr onto glass fiber cloth surfaces using chitosan for Se(IV) reduction in aqueous solutions. The TiO2/BiOBr/cloth (TB-4/cloth) catalyst achieves a remarkable 99.2 % Se(IV) removal within 2 h under visible light and maintains excellent Se(IV) reduction photocatalytic activity (86.4 %) even after eight cycles, remaining easily reusable. Additionally, we develop two machine learning models, namely artificial neural network (ANN) and long short-term memory (LSTM), to validate the anticipated experimental outcomes. Both models exhibit high accuracy and predictive capability (R2 > 0.99, RMSE < 0.03). This study introduces a novel approach that combines experimentation with artificial intelligence modeling, paving the way for future advancements in Se(IV)-contaminated wastewater purification methods.

How much can ChatGPT really help computational biologists in programming?

ChatGPT, a recently developed product by openAI, is successfully leaving its mark as a multi-purpose natural language based chatbot. In this paper, we are more interested in analyzing its potential in the field of computational biology. A major share of work done by computational biologists these days involve coding up bioinformatics algorithms, analyzing data, creating pipelining scripts and even machine learning modeling and feature extraction. This paper focuses on the potential influence (both positive and negative) of ChatGPT in the mentioned aspects with illustrative examples from different perspectives. Compared to other fields of computer science, computational biology has (1) less coding resources, (2) more sensitivity and bias issues (deals with medical data), and (3) more necessity of coding assistance (people from diverse background come to this field). Keeping such issues in mind, we cover use cases such as code writing, reviewing, debugging, converting, refactoring, and pipelining using ChatGPT from the perspective of computational biologists in this paper.

Financing and Management Strategies for Expanding Green Development Projects: A Case Study of Energy Corporation in China’s Renewable Energy Sector Using Machine Learning (ML) Modeling

Financing and Management Strategies for Expanding Green Development Projects: A Case Study of Energy Corporation in China’s Renewable Energy Sector Using Machine Learning (ML) Modeling

Insights from modelling sixteen years of climatic and fumonisin patterns in maize in South Africa

Mycotoxin contamination of agricultural commodities is a global public health problem that has remained elusive to various mitigation approaches, particularly in developing countries. Climate change and its impact exacerbates South Africa’s vulnerability to mycotoxin contamination, and significantly threatens its’s food systems, public health, and agro-economic development. Herein we analyse sixteen years (2005/2006–2020/2021) of annual national meteorological data on South Africa which reveals both systematic and erratic variability in critical climatic factors known to influence mycotoxin contamination in crops. Within the same study period, data on fumonisin (FB) monitoring show clear climate-dependent trends. The strongest positive warming trend is observed between 2018/2019 and 2019/2020 (0.51 °C/year), and a strong positive correlation is likewise established between FB contamination and temperature (r ranging from 0.6 to 0.9). Four machine learning models, viz support vector machines, eXtreme gradient boosting, random forest, and orthogonal partial least squares, are generalized on the historical data with suitable performance (RMSE as low as 0.00). All the adopted models are able to predict future FB contamination patterns with reasonable precision (R2 ranging from 0.34 to 1.00). The most important model feature for predicting average FB contamination (YA) is the historical pattern of average FB contamination in maize within the region (ΣFBs_avg). The two most significant features in modelling maximum FB contamination (YM) are minimum temperature from the CMIP6 data (Pro_tempMIN) and observed precipitation from the CRU data (O_prep). Our study provides strong evidence of the impact of climate change on FB in South Africa and reiterates the significance of machine learning modelling in predicting mycotoxin contamination in light of changing climatic conditions, which could facilitate early warnings and the adoption of relevant mitigation measures that could help in mycotoxin risk management and control.

Towards Fault-Tolerant Federated and Distributed Machine Learning

Machine learning (ML) models are routinely trained and deployed among distributed devices, e.g., learning with geo-distributed data centers and federated learning with mobile devices. Such shared computing platforms are susceptible to hardware, software, communication errors, and security concerns. This talk will outline some of the threat models in distributed learning, along with robust learning methods proposed to augment the fault tolerance of distributed machine learning, showing both theoretical and empirical evidence of robustness to benign and adversarial attacks.

Exploring Alternative Approaches to Language Modeling for Learning from Data and Knowledge

Despite their extensive application in language understanding tasks, large language models (LLMs) still encounter challenges including hallucinations - occasional fabrication of information - and alignment issues - lack of associations with human-curated world models (e.g., intuitive physics or common-sense knowledge). Moreover, the black-box nature of LLMs presents significant obstacles in training them effectively to achieve desired behaviors. In particular, modifying the concept embedding spaces of LLMs can be highly intractable. This process involves analyzing the implicit impact of such adjustments on the myriad parameters within LLMs and the resulting inductive biases. We propose a novel architecture that wraps powerful function approximation architectures within an outer, interpretable read-out layer. This read-out layer can be scrutinized to explicitly observe the effects of concept modeling during the training of the LLM. Our method stands in contrast with gradient-based implicit mechanisms, which depend solely on adjustments to the LLM parameters and thus evade scrutiny. By conducting extensive experiments across both generative and discriminative language modeling tasks, we evaluate the capabilities of our proposed architecture relative to state-of-the-art LLMs of similar sizes. Additionally, we offer a qualitative examination of the interpretable read-out layer and visualize the concepts it captures. The results demonstrate the potential of our approach for effectively controlling LLM hallucinations and enhancing the alignment with human expectations.

A novel adjusted real-time decision-making for dynamic distribution in the grocery supply chain

PurposeThe current research has developed a novel method to update the decisions regarding real-time data, named the dynamic adjusted real-time decision-making (DARDEM), for updating the decisions of a grocery supply chain that avoids both frequent modifications of decisions and apathy. The DARDEM method is an integration of unsupervised machine learning and mathematical modeling. This study aims to propose a dynamic proposed a dynamic distribution structure and developed a bi-objective mixed-integer linear program to make distribution decisions along with supplier selection in the supply chain.Design/methodology/approachThe constantly changing environment of the grocery supply chains shows the necessity for dynamic distribution systems. In addition, new disruptive technologies of Industry 4.0, such as the Internet of Things, provide real-time data availability. Under such conditions, updating decisions has a crucial impact on the continued success of the supply chains. Optimization models have traditionally relied on estimated average input parameters, making it challenging to incorporate real-time data into their framework.FindingsThe proposed dynamic distribution and DARDEM method are studied in an e-grocery supply chain to minimize the total cost and complexity of the supply chain simultaneously. The proposed dynamic structure outperforms traditional distribution structures in a grocery supply chain, particularly when there is higher demand dispersion. The study showed that the DARDEM solution, the online solution, achieved an average difference of 1.54% compared to the offline solution, the optimal solution obtained in the presence of complete information. Moreover, the proposed method reduced the number of changes in downstream and upstream decisions by 30.32% and 40%, respectively, compared to the shortsighted approach.Originality/valueIntroducing a dynamic distribution structure in the supply chain that can effectively manage the challenges posed by real-time demand data, providing a balance between distribution stability and flexibility. The research develops a bi-objective mixed-integer linear program to make distribution decisions and supplier selections in the supply chain simultaneously. This model helps minimize the total cost and complexity of the e-grocery supply chain, providing valuable insights into decision-making processes. Developing a novel method to determine the status of the supply chain and online decision-making in the supply chain based on real-time data, enhancing the adaptability of the system to changing conditions. Implementing and analyzing the proposed MILP model and the developed real-time decision-making method in a case study in a grocery supply chain.

Machine Learning Modeling to Predict Atrial Fibrillation Detection in Embolic Stroke of Undetermined Source Patients.

In patients with embolic stroke of undetermined source (ESUS), occult atrial fibrillation (AF) has been implicated as a key source of cardioembolism. However, only a minority acquire implantable cardiac loop recorders (ILRs) to detect occult paroxysmal AF, partly due to financial cost and procedural inconvenience. Without the initiation of appropriate anticoagulation, these patients are at risk of increased ischemic stroke recurrence. Hence, cost-effective and accurate methods of predicting AF in ESUS patients are highly sought after. We aimed to incorporate clinical and echocardiography data into machine learning (ML) algorithms for AF prediction on ILRs in ESUS. This was a single-center cohort study that included 157 consecutive patients diagnosed with ESUS from October 2014 to October 2017 who had ILR evaluation. We developed four ML models, with hyperparameters tuned, to predict AF detection on an ILR. The median age of the cohort was 67 (IQR 59-74) years old and the median monitoring duration was 1051 (IQR 478-1287) days. Of the 157 patients, 32 (20.4%) had occult AF detected on the ILR. Support vector machine predicted for AF with a 95% confidence interval area under the receiver operating characteristic curve (AUC) of 0.736-0.737, multilayer perceptron with an AUC of 0.697-0.708, XGBoost with an AUC of 0.697-0.697, and random forest with an AUC of 0.663-0.674. ML feature importance found that age, HDL-C, and admitting heart rate were important non-echocardiography variables, while peak mitral A-wave velocity and left atrial volume were important echocardiography parameters aiding this prediction. Machine learning modeling incorporating clinical and echocardiographic variables predicted AF in ESUS patients with moderate accuracy.

Studies on thermal degradation kinetics and machine learning modeling of hydrochar produced from hydrothermal carbonization of municipal sewage sludge and key lime peel

Studies on thermal degradation kinetics and machine learning modeling of hydrochar produced from hydrothermal carbonization of municipal sewage sludge and key lime peel