Efficient Machine Learning Model Research Articles

Efficient Machine Learning Model Focusing on Active Sites for the Discovery of Bifunctional Oxygen Electrocatalysts in Binary Alloys.

The distinctive characteristics of alloy catalysts, encompassing composition, structure, and modifiable adsorption sites, present significant potential for the development of highly efficient electrocatalysts for oxygen evolution/reduction reactions [oxygen evolution reactions (OERs)/oxygen reduction reactions (ORRs)]. Machine learning (ML) methods can quickly establish the relationship between material features and catalytic activity, thus accelerating the development of alloy electrocatalysts. However, the current abundance of features presents a crucial challenge in selecting the most pertinent ones. In this study, we explored seven intrinsic features directly derived from the material's structure, with a specific focus on the chemical environment of active sites and their nearest neighbors. An accurate and efficient ML model to predict potential bifunctional oxygen electrocatalysts based on the intrinsic features of AB-type alloy active sites and intermediate free energies in the OERs/ORRs was established. These features possess clear physical and chemical meanings, closely linked to the electronic and geometric structures of active sites and neighboring atoms, thereby providing indispensable insights for the discovery of high-performance electrocatalysts. The ML model achieved R2 scores of 0.827, 0.913, and 0.711 for the predicted values of the three intermediate (OH, O, OOH) free energies, with corresponding mean absolute errors of 0.175, 0.242, and 0.200 eV, respectively. These results indicate that the ML model exhibits high accuracy in predicting the intermediate free energies. Furthermore, the ML model exhibited a prediction efficiency 150,000 times faster than traditional density functional theory calculations. This work will offer valuable insights and a framework for facilitating the rapid design of potential catalysts by ML methods.

Enhancing user experience in home networks with machine learning-based classification

With the rapid development of mobile Internet, home broadband has been integrated into people's daily lives, and the market has become increasingly saturated. User experience and broadband quality have become the key factors determining market competitiveness, and consequently, most operators currently are increasing attention to network quality issues and how to improve user experience. This paper proposes an efficient machine learning model to accurately evaluate home user network experiences. The dataset used encompasses network indicator data from 500 anonymized users, and presents a set of formidable challenges including a non-standard sampling rate and time range, an uneven distribution of observations, multiple recorded observations for identical timestamps, a constrained sample size, a subjective definition of Internet experience, and a lack of essential information regarding the data collection setup. Our novel time series characteristic-based method extracts thousands of descriptive statistics from the time series sequences which reveal that, even in the face of the dataset's inherent complexities, our proposed method excels, achieving an impressive 67% validation accuracy. This represents a substantial 3% enhancement over the performance of conventional models on this dataset. Furthermore, we explore the potential of a Recurrent Neural Network (RNN) model, which also yields promising results with a validation accuracy of 58%. It is important to underscore that the performance of the RNN model could be substantially enhanced with a larger dataset. [...]

Smart Artificial Intelligence System for Heart Disease Prediction

Heart disease playing a vital role in human life, Early detection of heart-disease we can save humans lives and it remains a leading cause of mortality worldwide, making early and accurate prediction of heart disease a critical task for improving patient outcomes. Machine learning has shown great promise in this area, with various models being developed to predict heart disease based on a range of clinical and demographic features. However, there is a growing need for more efficient machine learning models that can accurately predict heart disease while minimizing computational costs, particularly in resource-constrained settings. This research paper proposes an efficient machine learning model for heart disease prediction that combines feature selection, model optimization, and interpretability techniques to achieve accurate predictions with reduced computational complexity. The proposed model utilizes a dataset of clinical and demographic features, such as age, sex, blood pressure, cholesterol levels, and other relevant risk factors, to train a machine learning model using a large real-world dataset. The proposed efficient machine learning model is evaluated on benchmark datasets and compared with other state-of-the-art models in terms of precision, Accuracy, Recall and F1- Score. The results demonstrate the model achieved by superior prediction performance to existing models. Proposed method accuracy increased by 4.8%

Efficient data-driven machine learning models for scour depth predictions at sloping sea defences

Seawalls are critical defence infrastructures in coastal zones that protect hinterland areas from storm surges, wave overtopping and soil erosion hazards. Scouring at the toe of sea defences, caused by wave-induced accretion and erosion of bed material imposes a significant threat to the structural integrity of coastal infrastructures. Accurate prediction of scour depths is essential for appropriate and efficient design and maintenance of coastal structures, which serve to mitigate risks of structural failure through toe scouring. However, limited guidance and predictive tools are available for estimating toe scouring at sloping structures. In recent years, Artificial Intelligence and Machine Learning (ML) algorithms have gained interest, and although they underpin robust predictive models for many coastal engineering applications, such models have yet to be applied to scour prediction. Here we develop and present ML-based models for predicting toe scour depths at sloping seawall. Four ML algorithms, namely, Random Forest (RF), Gradient Boosted Decision Trees (GBDT), Artificial Neural Networks (ANNs), and Support Vector Machine Regression (SVMR) are utilised. Comprehensive physical modelling measurement data is utilised to develop and validate the predictive models. A Novel framework for feature selection, feature importance, and hyperparameter tuning algorithms are adopted for pre- and post-processing steps of ML-based models. In-depth statistical analyses are proposed to evaluate the predictive performance of the proposed models. The results indicate a minimum of 80% prediction accuracy across all the algorithms tested in this study and overall, the SVMR produced the most accurate predictions with a Coefficient of Determination (r2) of 0.74 and a Mean Absolute Error (MAE) value of 0.17. The SVMR algorithm also offered most computationally efficient performance among the algorithms tested. The methodological framework proposed in this study can be applied to scouring datasets for rapid assessment of scour at coastal defence structures, facilitating model-informed decision-making.

PCOS stratification for precision diagnostics and treatment.

Globally, polycystic ovarian syndrome (PCOS) affects approximately 10% of fertile women, leading to great health and economic burden. PCOS is a heterogenous illness that can cause infertility, irregular menstrual cycles, acne, and hirsutism, among other symptoms. The clinical diagnosis is primarily a diagnosis of exclusion if one or more of the three primary symptoms, namely, oligo- or anovulation, hyperandrogenism, and polycystic ovarian morphology, are present. Obesity and PCOS are often coexisting disorders that may be bidirectionally causally related. Phenotypic heterogeneity throughout the reproductive lifespan, such as the overlap of PCOS symptoms with regular fluctuations in a woman's menstrual cycle and metabolism during the menarche and menopausal transition, further complicates diagnosis. PCOS etiology is mostly unknown and complex, likely due to the fact that it is a group of disorders with overlapping metabolic and reproductive problems. Evidence-based, common, standardized guidelines for PCOS diagnosis and treatment are urgently needed. Genomics and clinical data from populations across diverse ages and ethnicities are urgently needed to build efficient machine learning models for the stratification of PCOS. PCOS subtype-specific strategies for early screening, an accurate diagnosis, and management throughout life will optimize healthcare resources and reduce unnecessary testing. This will pave the way for women to be able to take the best possible care of their own health using the latest clinical expertise combined with their unique needs and preferences.

Feature importance feedback with Deep Q process in ensemble-based metaheuristic feature selection algorithms

Feature selection is an indispensable aspect of modern machine learning, especially for high-dimensional datasets where overfitting and computational inefficiencies are common concerns. Traditional methods often employ either filter, wrapper, or embedded approaches, which have limitations in terms of robustness, computational load, or capability to capture complex interactions among features. Despite the utility of metaheuristic algorithms like Particle Swarm Optimization (PSO), Firefly Algorithm (FA), and Whale Optimization (WOA) in feature selection, there still exists a gap in efficiently incorporating feature importance feedback into these processes. This paper presents a novel approach that integrates the strengths of PSO, FA, and WOA algorithms into an ensemble model and further enhances its performance by incorporating a Deep Q-Learning framework for relevance feedbacks. The Deep Q-Learning module intelligently updates feature importance based on model performance, thereby fine-tuning the selection process iteratively. Our ensemble model demonstrates substantial gains in effectiveness over traditional and individual metaheuristic approaches. Specifically, the proposed model achieved a 9.5% higher precision, an 8.5% higher accuracy, an 8.3% higher recall, a 4.9% higher AUC, and a 5.9% higher specificity across multiple software bug prediction datasets and samples. By resolving some of the key issues in existing feature selection methods and achieving superior performance metrics, this work paves the way for more robust and efficient machine learning models in various applications, from healthcare to natural language processing scenarios. This research provides an innovative framework for feature selection that promises not only superior performance but also offers a flexible architecture that can be adapted for a variety of machine learning challenges.

Toward reliable diabetes prediction: Innovations in data engineering and machine learning applications.

Diabetes is a metabolic disorder that causes the risk of stroke, heart disease, kidney failure, and other long-term complications because diabetes generates excess sugar in the blood. Machine learning (ML) models can aid in diagnosing diabetes at the primary stage. So, we need an efficient ML model to diagnose diabetes accurately. In this paper, an effective data preprocessing pipeline has been implemented to process the data and random oversampling to balance the data, handling the imbalance distributions of the observational data more sophisticatedly. We used four different diabetes datasets to conduct our experiments. Several ML algorithms were used to determine the best models to predict diabetes faultlessly. The performance analysis demonstrates that among all ML algorithms, random forest surpasses the current works with an accuracy rate of 86% and 98.48% for Dataset 1 and Dataset 2; extreme gradient boosting and decision tree surpass with an accuracy rate of 99.27% and 100% for Dataset 3 and Dataset 4, respectively. Our proposal can increase accuracy by 12.15% compared to the model without preprocessing. This excellent research finding indicates that the proposed models might be employed to produce more accurate diabetes predictions to supplement current preventative interventions to reduce the incidence of diabetes and its associated costs.

Study and Analysis of Deep Learning Techniques for Solving Financial Problems

Financial markets are competitive environments influenced by several variables and sectors. Wrong decisions can compromise several areas and cause chain reactions that could disrupt various sectors of the economy. In recent years, intelligent models have been used as tools to aid decision-making in financial markets. Deep learning models stand out among them, as they can achieve good generalization with large datasets. The main goal of this paper is to introduce and evaluate deep learning for solving financial problems. We document the process and present the techniques employed to develop models using a dataset containing over 2 million financial data observations. We believe this paper could guide researchers working on similar problems by suggesting resources that can be used and steps that can be followed in similar scenarios, narrowing down the search for efficient financial machine learning models.

Pneumonia Detection Using Machine Learning

An enormous amount of morbidity and mortality cases are caused by pneumonia, which is still a major global health concern. Pneumonia must be accurately and quickly detected in order to manage patients effectively and achieve better results. Machine learning (ML) algorithms have become effective instruments in recent years for automating the detection and diagnosis of pneumonia from medical imaging data. The goal of this review paper is to give a thorough overview of recent developments in ML-based pneumonia detection. It includes the various ML algorithms used, the training and testing datasets, and the evaluation metrics used to rate the effectiveness of these models. Additionally, this review highlights the difficulties encountered in the field and suggests possible directions for improvement in order to create a more reliable and robust pneumonia detection system. Healthcare professionals place a high value on pneumonia detection, and machine learning (ML)-based automation of There's been a lot of attention paid to this process. The importance of pneumonia detection and the part that ML techniques play in automating this process are highlighted in the introduction to this review paper. In the following section, it examines different machine learning (ML) The various system used for the discernment of pneumonia. Such include supervised understanding algorithms like logistic statistics, vector machine and randomization. forests, and convolutional neural networks. The review also discusses pneumonia detection using unsupervised learning techniques like clustering, dimensionality reduction, and autoencoders. In order to develop them, an assessment of pneumonia detection models is essential. The study has examined several appraisal metrics which are commonly used for that purpose, such as sensitivity, specificity, precision and the operational status of receivers. characteristic (ROC) curve, recall, precision, and F1-score. The selection of suitable metrics, which considers specific requirements for pneumonia detection, is main factor to be taken into consideration. The main obstacles is that there are no annotation data. to creating reliable pneumonia detection models. Accurate ML algorithms must be trained on high-quality labelled datasets. However, since chest X-ray images must be annotated by qualified radiologists, obtaining a sizable annotated dataset for pneumonia is frequently challenging. The creation of efficient ML models for pneumonia detection is hampered by the limited availability of annotated data.

Evaluating the effectiveness of machine learning models for detecting AI-generated art

Breakthroughs in technology mean the creation of new programs that can produce results startlingly close to human creations. AI-generated art, for example, has garnered attention and debate by redefining artistic creations, originality, and the ethics of artificial intelligence. By training on existing artwork, these programs can generate images startlingly close to the intended art style and topic and can fool the ordinary person. In this paper, we examine whether the type and style of the input image will impact the accuracy of existing AI-detection machine learning models. The first part of the hypothesis is that the existing models are more accurate in classifying whether an image is AI or human-created if the image is centered around human subjects rather than the environment. The second part of the hypothesis is that the models are more accurate in classifying realistic images compared to images in animation style and traditional mediums. The data show that current models are slightly better at classifying images of the environment, with 84.7% accuracy, compared to images of human characters, with 81.9% accuracy, which doesn’t support the first part of our hypothesis. However, most models have greater success with realism style than with traditional and animation styles, which supports the second part of our hypothesis. These results may serve as suggestions for further improvements in current models. With efficient machine learning models, artists and the general public can discern between AI and human-created art, which may help improve the regulation and usage of AI-generated art.

Optimized virtual reality design through user immersion level detection with novel feature fusion and explainable artificial intelligence.

Virtual reality (VR) and immersive technology have emerged as powerful tools with numerous applications. VR technology creates a computer-generated simulation that immerses users in a virtual environment, providing a highly realistic and interactive experience. This technology finds applications in various fields, including gaming, healthcare, education, architecture, and training simulations. Understanding user immersion levels in VR is crucial and challenging for optimizing the design of VR applications. Immersion refers to the extent to which users feel absorbed and engrossed in the virtual environment. This research primarily aims to detect user immersion levels in VR using an efficient machine-learning model. We utilized a benchmark dataset based on user experiences in VR environments to conduct our experiments. Advanced deep and machine learning approaches are applied in comparison. We proposed a novel technique called Polynomial Random Forest (PRF) for feature generation mechanisms. The proposed PRF approach extracts polynomial and class prediction probability features to generate a new feature set. Extensive research experiments show that random forest outperformed state-of-the-art approaches, achieving a high immersion level detection rate of 98%, using the proposed PRF technique. We applied hyperparameter optimization and cross-validation approaches to validate the performance scores. Additionally, we utilized explainable artificial intelligence (XAI) to interpret the reasoning behind the decisions made by the proposed model for user immersion level detection in VR. Our research has the potential to revolutionize user immersion level detection in VR, enhancing the design process.

Developing an Efficient Support Vector Machine Learning Model for Mobile Charging Stations.

In the context of increasing global energy scarcity, optimizing electric vehicle (EV) mobile charging stations is critical for promoting sustainable transportation. This study introduces the use Artificial Neural Network (ANN) models, and Support Vector Machine (SVM) enhanced with the Adams optimizer, to address the challenge of efficient EV charging in energy-constrained environments. The models are designed to predict optimal charging station locations and schedules, with the ANN-Adams optimization fine-tuning the model parameters to improve accuracy and performance, while ensuring dynamic adaptation to fluctuating energy availability and demand patterns. This research contributes to the development of intelligent, adaptive systems for EV infrastructure, paving the way for more resilient and energy-efficient urban mobility solutions. The system employs supervised learning, where models were trained and tested on labeled datasets. The performance of the SVM models was compared to that of a Multilayer Perceptron Network (MLPN) with Adams optimization. The results showed that the MLPN with Adams optimization achieved an accuracy of 97.85%, while the SVM model had a prediction accuracy of 81%. The ANN recorded 91.29% accuracy. Both approaches significantly improved classification accuracy, model generalization on testing datasets, and reduced misclassification errors.

Predicting Loop Vectorization through Machine Learning Algorithms

Automatic vectorization is often utilized to improve the speed of compute-intensive programs on current CPUs. However, there is enormous space for improvement in present compiler auto-vectorization capabilities. Execution with optimizing code on these resource-controlled strategies is essential for both energy and performance efficiency. While vectorization suggests major performance developments, conventional compiler auto-vectorization techniques often fail. This study investigated the prospective of machine learning algorithms to enhance vectorization. The study proposes an ensemble learning method by employing Random Forest (RF), Feedforward Neural Network (FNN), and Support Vector Machine (SVM) algorithms to estimate the effectiveness of vectorization over Trimaran Single-Value Code (TSVC) loops. Unlike existing methods that depend on static program features, we leverage dynamic features removed from hardware counter-events to build efficient and robust machine learning models. Our approach aims to improve the performance of e-business microcontroller platforms while identifying profitable vectorization opportunities. We assess our method using a benchmark group of 155 loops with two commonly used compilers (GCC and Clang). The results demonstrated high accuracy in predicting vectorization benefits in e-business applications.

Efficient machine learning models for the detection of coconut milk adulteration

Coconut milk adulteration detection involves the use of analytical methods, including machine learning, to detect the presence of impurities or additives in coconut milk. Adulteration can occur when substances such as water or other cheaper ingredients are added to coconut milk, compromising its quality, nutritional value, and authenticity. Identifying adulteration is crucial for ensuring consumer safety, maintaining product quality, and upholding industry standards. The aim of this study was to propose a machine learning model to detect adulteration in coconut milk. To implement the proposed work, a coconut milk adulteration dataset is collected from a standard source. The amount of available data is limited; hence, synthetic data is generated by applying the CTGAN algorithm. The proposed framework employs three different Feature Extraction (FE) strategies, i.e., Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Autoencoder (AE). Then, the feature-extracted dataset is classified through four effective machine learning algorithms, such as Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). The machine learning algorithms outcomes are evaluated using four performance metrics, i.e., Accuracy, Precision, Recall, and F1-score. RF provides the highest accuracy of 99.17%, precision value of 97.29%, recall value of 96.71%, and F1 Score of 97% for the LDA techniques.

Element-configuration dependent first-principles machine learning studies of multiple alloying effects on the structure stability of Co3(Al, W)

Multiple alloying is desired to improve the stability of metastable Co3(Al, W) of Co-based superalloys. However, computational studies of alloying effects are costly due to the enormous combinations of compositions and configurations. Most current element-based machine learning methods that rely solely on composition lack the ability to distinguish between polymorph materials and various local alloying configurations. In this work, we developed efficient machine learning (ML) models using element-configuration dependent Center-Environment (CE) and element-based Chemical Composition (CC) features to describe alloying element type and substitution configuration, crucial for data-driven study of correlated alloying effects and local short-range chemical ordering. We employed first-principles computation and ML methods to investigate the structure stabilities of the Al-W substitution site models with 3d and 4d transition metal (TM) elements, then the optimized ML models were validated using the untrained dual-Al or dual-W site configurations with 3d, 4d, and 5d TM elements. The ML-CE models were generally more accurate than the ML-CC models. The most stable substitution pairs are Sc-Fe 3d TM elements at the Al-W and dual-W sites with lattice constant ∼4 Å. Therefore, we propose a “Co-left” design rule to stabilize Co3(Al, W) by multiple alloying with early 3d TM elements (IIIB-VIII group). The stabilizing 3d “Co-left” elements also can improve the mechanical properties. The ML-CE approach can be generally applied to study local correlated alloying effects and chemical ordering in medium/high-entropy or amorphous alloys.

A powerful Peripheral Arterial Disease detection using machine learning-based severity level classification model and hyper parameter optimization methods

This study addresses the critical need for improved detection and assessment of Peripheral Arterial Disease (PAD) using Artificial Intelligence (AI) algorithms, aiming to reduce global mortality rates associated with this condition. The research focuses on enhancing the efficiency of machine learning (ML) models for PAD detection and severity categorization by employing optimization techniques. Notably, this study introduces the application of Synthetic Minority Oversampling Technique (SMOTE) to mitigate imbalanced data challenges in PAD detection. The primary objective of this research is to develop highly efficient ML models utilizing six distinct AI classifiers and Hyper Parameter Optimization (HPO), specifically targeting PAD identification and severity level categorization. Leveraging the Cleveland and Statlog datasets, the study constructs and evaluates these models using all relevant features. The principal findings indicate remarkable advancements in PAD detection accuracy. The proposed models, optimized using SMOTE and Enhanced Decision Tree (EDT) through HPO, surpass state-of-the-art methodologies, achieving exceptional accuracies of 99.20% and 98.52% on the Cleveland and Statlog datasets, respectively. These models outperform existing approaches, assessed using comprehensive metrics such as F1 score, Accuracy, Precision, Recall, Specificity, and MCC. In conclusion, this study's innovative approach significantly improves the capability to assess PAD and categorize its severity levels accurately. The proposed models hold promise in aiding physicians to evaluate patients' cardiac conditions effectively, enabling early interventions that have the potential to mitigate mortality rates associated with cardiovascular diseases.

Efficient machine learning model to detect early stage Parkinson’s disease

<p class="root-block-node">Parkinson’s disease (PD) often manifests itself in memory loss and cognitive decline. The decline is inexorable, and damage to the brain’s cortex has already occurred. Numerous studies have shown that by detecting dementia early and beginning treatment, the disease’s course can be slowed, and any further atrophy can be prevented. Brain imaging data, such as from an MRI, is frequently used in the diagnosis of Parkinson’s disease (PD). In recent years, utilizing deep convolutional neural networks has greatly improved Parkinson’s disease diagnosis. However, getting to the level of quality needed for clinical use is still challenging. In this study, we introduce a machine learning-based approach for more accurately diagnosing Parkinson’s disease. This research makes use of information gleaned from single-photon emission computerized tomography (SPECT) scan and positron emission tomography (PET) scans performed on patients with Parkinson’s disease (PD) and healthy controls. The most crucial characteristics of these datasets are isolated with the aid of the Fisher discriminate ratio (FDR) and non-negative matrix factorization (NMF). The K-nearest neighbor, Decision Tree, Support vector machine (SVM), and Deep Convolution neural network (DCCN) classifiers with confidence bounds classify the NMF-transformed data sets with a decreased number of features. The proposed DCCN technique has a classification accuracy of up to 93.7 percent when compared to decision trees, K-Nearest Neighbor (KNN)s, and SVMs. The DCCN is now a reliable approach for classifying SPECT and PET, PD images.</p>

Credit Default Analysis and Prediction Based on Machine Learning

The Credit Default Prediction project aims to develop an efficient machine learning model to accurately predict loan default risk on the Lending Club platform. The project is based on historical loan data, including borrower personal information, financial metrics, and credit history records, with the goal of building a robust predictive model. The project's workflow encompasses several critical steps, including data preprocessing, exploratory data analysis, feature engineering, model selection, and performance evaluation. In terms of model selection, the project employs two primary machine learning algorithms, namely Artificial Neural Networks (ANN) and Random Forest. These algorithms are renowned for their outstanding performance in handling extensive borrower data and providing reliable risk predictions. Model training and evaluation are conducted using a substantial amount of historical data to ensure accurate predictions across various scenarios. Furthermore, the project conducts feature importance analysis to identify factors that significantly influence loan default risk. These insights contribute to enhancing Lending Club's risk assessment process and supporting more informed decisions regarding loan approval and pricing strategies. By combining data-driven predictive modeling with in-depth data analysis, this project aims to enhance the efficiency of Lending Club's loan operations and elevate its risk management capabilities, ultimately providing more dependable financial services to investors and borrowers.

Predicting the Risk of Verticillium Wilt in Olive Orchards Using Fuzzy Logic

Developing models to understand disease dynamics and predict the risk of disease outbreaks to facilitate decision making is an integral component of plant disease management. However, these models have not yet been developed for one of the most damaging diseases in Mediterranean olive-growing areas (verticillium wilt (VW), caused by the fungus Verticillium dahliae Kleb.), although there are parameters (e.g., level of V. dahliae inoculum in the soil, level of susceptibility of the olive cultivar, isothermality, coefficient of variation of seasonal precipitation, etc.) that have previously been correlated with the severity of the disease. Using the data from previous VW studies conducted in the Guadalquivir Valley of Andalusia (one of the most damaged areas worldwide), in this work, a set of fuzzy logic (FL) models is developed with the aforementioned disease and climatic parameters, and the results are compared with machine learning (ML) models, of known effectiveness, to predict the risk levels of VW appearance in an olive orchard. Under these conditions, both groups of models were less effective than those previously studied with simpler models or models used under controlled conditions. However, the accuracy achieved with the most efficient FL model (60%; classification system based on fuzzy rules using the Ishibuchi method with a weighting factor) was somewhat greater than the efficiency achieved with the most efficient ML model (59.0%; decision tree classifier), in addition to being more appropriate (from a practical point of view) for the incorporation into a decision support system by allowing the risk of appearance of each observation to be known by providing rules for each of the combinations of the different parameters with similar precision. Therefore, in this study, we propose the FL methodology as suitable to act as an expert system for the future creation of a decision support system for VW in olives.

AI-Assisted Cotton Grading: Active and Semi-Supervised Learning to Reduce the Image-Labelling Burden

The assessment of food and industrial crops during harvesting is important to determine the quality and downstream processing requirements, which in turn affect their market value. While machine learning models have been developed for this purpose, their deployment is hindered by the high cost of labelling the crop images to provide data for model training. This study examines the capabilities of semi-supervised and active learning to minimise effort when labelling cotton lint samples while maintaining high classification accuracy. Random forest classification models were developed using supervised learning, semi-supervised learning, and active learning to determine Egyptian cotton grade. Compared to supervised learning (80.20–82.66%) and semi-supervised learning (81.39–85.26%), active learning models were able to achieve higher accuracy (82.85–85.33%) with up to 46.4% reduction in the volume of labelled data required. The primary obstacle when using machine learning for Egyptian cotton grading is the time required for labelling cotton lint samples. However, by applying active learning, this study successfully decreased the time needed from 422.5 to 177.5 min. The findings of this study demonstrate that active learning is a promising approach for developing accurate and efficient machine learning models for grading food and industrial crops.