Learning Model Research Articles

Design and Implementation of an AI-Based Robotic Arm for Strawberry Harvesting

This study presents the design and implementation of a wire-driven, multi-joint robotic arm equipped with a cutting and gripping mechanism for harvesting delicate strawberries, with the goal of reducing labor and costs. The arm is mounted on a lifting mechanism and linked to a laterally movable module, which is affixed to the tube cultivation shelf. The trained deep learning model can instantly detect strawberries, identify optimal picking points, and estimate the contour area of fruit while the mobile platform is in motion. A two-stage fuzzy logic control (2s-FLC) method is employed to adjust the length of the arm and bending angle, enabling the end of the arm to approach the fruit picking position. The experimental results indicate a 90% accuracy in fruit detection, an 82% success rate in harvesting, and an average picking time of 6.5 s per strawberry, reduced to 5 s without arm recovery time. The performance of the proposed system in harvesting strawberries of different sizes under varying lighting conditions is also statistically analyzed and evaluated in this paper.

Seasonal and annual trends in reference evapotranspiration and prediction using machine learning models across seven climatic zones of Bangladesh

ABSTRACT The primary aim of this investigation is to examine the historical (1989–2020) and future trends and magnitude of Reference Evapotranspiration (ET0) in terms of spatiotemporal measures, considering its significance as a hydro-meteorological parameter influenced by changing climate. The FAO-56 Penman-Monteith method is employed to analyze ET0, while the Modified Mann Kendall test is utilized to assess trends and Sen’s Slope Estimator is used for magnitude analysis. The future prediction is conducted using Support Vector Machine (SVM), Artificial Neural Network (ANN), and Random Forest (RF) models. Results show an increasing ET0 trend annually in the southeastern and northeastern zones, while decreased values are observed in other regions, particularly in the northwest (0.83 mm). Sen’s slope estimator reveals distinct fluctuations in ET0, with notable disparities in the Southeastern, Northeastern, Southwestern, and South-Central zones. Notably, Chattogram and Sitakunda experience an ET0 magnitude of 0.02 mm/Year, while other zones show a magnitude of 0.01 mm/Year. SVM outperformed other models, predicting rising ET0 in various seasons. These findings offer insights for optimizing irrigation systems and sustainable water management under changing climatic conditions.

Research on National Short-Term Precipitation Forecast Method Based on Machine Learning

Abstract. Climate change is closely related to human lives. With the development of information technology, meteorological data gradually show the characteristics of big data. The purpose of this study is to compare the application effects of different machine learning models in short-term precipitation prediction, to improve the accuracy and efficiency of prediction. Based on the annual average precipitation data of prefecture-level cities in China from 1990 to 2022, this paper uses Random Forest, eXtreme Gradient Boosting and Neural Networks to construct prediction models, and comprehensively evaluate them. In this study, the data is preprocessed to ensure the data quality of the input model. Next, the data is fed into three machine learning algorithm models, Random Forest, eXtreme Gradient Boosting and Neural Networks. Finally, the prediction performance of each model is evaluated by various indexes. In this paper, it is found that the Random Forest model has the best performance, and its prediction accuracy is higher than the other two models, which has great application potential in the field of short-term precipitation prediction. This study shows that a reasonable selection of machine learning methods and optimization of model parameters can effectively improve the accuracy of short-term precipitation prediction. This paper provides some empirical evidence for precipitation prediction, which will help to make more effective decisions in dealing with extreme weather events and climate change challenges in the future.

Identification of Exploited Unreliable Account Passwords in the Information Infrastructure Using Machine Learning Methods

Accounts are an integral part of most modern information systems and provide their owners with the ability to authenticate within the system. This paper presents an analysis of existing methods for detecting simple account passwords in automated systems. Their advantages and disadvantages are listed. A method was developed to detect simple exploitable passwords that administrators can use to supplement other existing methods to increase the overall security of automated systems against threats from accounts potentially compromised by attackers. The method was based on the analysis of commands executed in automated or manual modes with the indication of credentials in plain text. Minimum password strength requirements are provided based on the security level. A special case was considered in which all passwords analyzed in this way were found explicitly in the system logs. We developed a unified definition of the classification of passwords into simple and strong, and also developed machine learning technology for their classification. The method offers a flexible adaptation to a specific system, taking into account the level of significance of the information being processed and the password policy adopted, expressed in the possibility of retraining the machine learning model. The experimental method using machine learning algorithms, namely the ensemble of decision trees, for classifying passwords into strong and potentially compromised by attackers based on flexible password strength criteria, showed high results. The performance of the method is also compared against other machine learning algorithms, specifically XGBoost, Random Forest, and Naive Bayes. The presented approach also solves the problem of detecting events related to the use and storage of credentials in plain text. We used the dataset of approximately 770,000 passwords, allowing the machine learning model to accurately classify 98% of the passwords by their significance levels.

Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic, genomic, and radiographic latent features.

Artificial intelligence models have been increasingly used in the analysis of tumor histology to perform tasks ranging from routine classification to identification of molecular features. These approaches distill cancer histologic images into high-level features, which are used in predictions, but understanding the biologic meaning of such features remains challenging. We present and validate a custom generative adversarial network-HistoXGAN-capable of reconstructing representative histology using feature vectors produced by common feature extractors. We evaluate HistoXGAN across 29 cancer subtypes and demonstrate that reconstructed images retain information regarding tumor grade, histologic subtype, and gene expression patterns. We leverage HistoXGAN to illustrate the underlying histologic features for deep learning models for actionable mutations, identify model reliance on histologic batch effect in predictions, and demonstrate accurate reconstruction of tumor histology from radiographic imaging for a "virtual biopsy."

Exploring the role of machine learning models in risk assessment models for developed organizations’ management decision policies

The goal of this work was to create and assess machine-learning models for estimating the risk of budget overruns in developed projects. Finding the best model for risk forecasting required evaluating the performance of several models. Using a dataset of 177 projects took into account variables like environmental risks employee skill level safety incidents and project complexity. In our experiments, we analyzed the application of different machine learning models to analyze the risk for the management decision policies of developed organizations. The performance of the chosen model Neural Network (MLP) was improved after applying the tuning process which increased the Test R2 from −0.37686 before tuning to 0.195637 after tuning. The Support Vector Machine (SVM), Ridge Regression, Lasso Regression, and Random Forest (Tuned) models did not improve, as seen when Test R2 is compared to the experiments. No changes in Test R2’s were observed on GBM and XGBoost, which retained same Test R2 across different tuning attempts. Stacking Regressor was used only during the hyperparameter tuning phase and brought a Test R2 of 0. 022219.Decision Tree was again the worst model among all throughout the experiments, with no signs of improvement in its Test R2; it was −1.4669 for Decision Tree in all experiments arranged on the basis of Gender. These results indicate that although, models such as the Neural Network (MLP) sees improvements due to hyperparameter tuning, there are minimal improvements for most models. This works does highlight some of the weaknesses in specific types of models, as well as identifies areas where additional work can be expected to deliver incremental benefits to the structured applied process of risk assessment in organizational policies.

Evaluate Multi-Objective Optimization Model for Product Supply Chain Inventory Control Based on Grey Wolf Algorithm

Enterprise supply chain inventory control plays a critical role in modern enterprise management. Yet achieving multi-objective optimization remains challenging. This paper proposes a deep learning integrated model based on grey wolf optimization (GWO-DLIM) aimed at optimizing inventory holding costs, stockout costs, and order costs. The model integrates multi-layer perceptron (MLP), DeBERTa, and GWO, leveraging the powerful predictive and feature extraction capabilities of deep learning models, combined with the global optimization ability of the grey wolf algorithm, to achieve multi-objective optimization. These results demonstrate that the GWO-DLIM model significantly outperforms other comparative models across all metrics, exhibiting lower prediction errors and root mean square errors, as well as higher service levels. This study provides an effective multi-objective optimization solution for supply chain inventory management, holding significant theoretical and practical implications.

Enhancing water security through advanced modeling: integrating deep learning and a novel metaheuristic optimization algorithm for accurate pan evaporation prediction

ABSTRACT This study evaluates and enhances machine learning models for predicting pan evaporation under diverse climatic conditions. Five fundamental machine learning models were employed and tested across four different stations. Subsequent comparisons were made with advanced techniques, including long short-term memory (LSTM) networks. An innovative approach was introduced, combining LSTM with Binary Al-Biruni Earth Radius (BER–LSTM). This hybrid method was benchmarked against other optimization techniques. The BER–LSTM model consistently outperformed other models across all stations and time scales, achieving up to a 97.54% improvement in root mean square error (RMSE) compared to standard LSTM on daily time scales. Compared to simpler models like Multilayer Perceptron and Support Vector Regressor, BER–LSTM showed even more substantial improvements, with up to a 99.03% reduction in RMSE. The BER–LSTM model demonstrates superior predictive capabilities for pan evaporation across varied climatic conditions, offering significant improvements over both traditional and advanced machine learning techniques. This approach shows promise for enhancing evaporation forecasting in diverse environmental contexts.

Causality-Driven Feature Selection for Calibrating Low-Cost Airborne Particulate Sensors Using Machine Learning

With escalating global environmental challenges and worsening air quality, there is an urgent need for enhanced environmental monitoring capabilities. Low-cost sensor networks are emerging as a vital solution, enabling widespread and affordable deployment at fine spatial resolutions. In this context, machine learning for the calibration of low-cost sensors is particularly valuable. However, traditional machine learning models often lack interpretability and generalizability when applied to complex, dynamic environmental data. To address this, we propose a causal feature selection approach based on convergent cross mapping within the machine learning pipeline to build more robustly calibrated sensor networks. This approach is applied in the calibration of a low-cost optical particle counter OPC-N3, effectively reproducing the measurements of PM1 and PM2.5 as recorded by research-grade spectrometers. We evaluated the predictive performance and generalizability of these causally optimized models, observing improvements in both while reducing the number of input features, thus adhering to the Occam’s razor principle. For the PM1 calibration model, the proposed feature selection reduced the mean squared error on the test set by 43.2% compared to the model with all input features, while the SHAP value-based selection only achieved a reduction of 29.6%. Similarly, for the PM2.5 model, the proposed feature selection led to a 33.2% reduction in the mean squared error, outperforming the 30.2% reduction achieved by the SHAP value-based selection. By integrating sensors with advanced machine learning techniques, this approach advances urban air quality monitoring, fostering a deeper scientific understanding of microenvironments. Beyond the current test cases, this feature selection method holds potential for broader applications in other environmental monitoring applications, contributing to the development of interpretable and robust environmental models.

Are AI tools better than traditional tools in literature searching? Evidence from E-commerce research

This article examines the potential implications of Artificial Intelligence (AI) for literature search, comparing AI-based tools to conventional research methods. It also addresses the scarcity of academic literature on specific AI tools for research writing, posing four critical questions regarding accuracy, quality, uniqueness, and qualified uniqueness. Employing Algorithmic Theory and Data Dependency Theory, this project scrutinizes AI performance in algorithms, machine learning models, and data quality. Testing nine e-commerce topics using Scopus, Web of Science, Elicit, and SciSpace, the authors conclude that while conventional methods excel in accuracy and quality, AI tools show promise in uniqueness, complementing literature reviews. The findings also emphasize the judicious integration of AI tools and advocate for further research into new applications and diverse fields. Ultimately, this research offers highly relevant insights into leveraging AI tools to enhance conventional literature search practices in research and professional domains.

Comparative evaluation of machine learning models for assessment of seabed liquefaction using finite element data

Predicting wave-induced liquefaction around submarine pipelines is crucial for marine engineering safety. However, the complex of interactions between ocean dynamics and seabed sediments makes rapid and accurate assessments challenging with traditional numerical methods. Although machine learning approaches are increasingly applied to wave-induced liquefaction problems, the comparative accuracy of different models remains under-explored. We evaluate the predictive accuracy of four classical machine learning models: Gradient Boosting (GB), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), and Random Forest (RF). The results indicate that the GB model exhibits high stability and accuracy in predicting wave-induced liquefaction, due to its strong ability to handle complex nonlinear geological data. Prediction accuracy varies across output parameters, with higher accuracy for seabed predictions than for pipeline surroundings. The combination of different input parameters significantly influences model predictive accuracy. Compared to traditional finite element numerical methods, employing machine learning models significantly reduces computation time, offering an effective tool for rapid disaster assessment and early warning in marine engineering. This research contributes to the safety of marine pipeline protections and provides new insights into the intersection of marine geological engineering and artificial intelligence.

Implementation of the 2013 Curriculum in Integrated Thematic Learning in Elementary Schools: Strategies, Challenges, and its Impact on Learning

Education is the process of imparting knowledge, character development, and producing a more harmonious social order and way of life, including through the development of students' intellectual capital, skills, and intellectual development. One of the innovations brought by the introduction of the 2013 curriculum is the integrative theme learning model. To provide meaningful educational experiences to students, integrative thematic learning connects various disciplines and materials through themes. The 2013 curriculum states that in order to place students as the center of the learning process, teachers must play an active role as facilitators and motivators of learning. This article aims to explain how the 2013 curriculum is applied to integrative thematic learning, and its impact on the teaching and learning process in elementary schools. The implementation of the curriculum in integrative thematic learning shows several challenges, such as difficulties in determining assessment or evaluation criteria for students, teachers' lack of understanding in compiling thematic integrative lesson plans, limited teaching aids, and the use of traditional learning methods that are less varied. The proposed solution is training and education for teachers, principals, and supervisors to acquire skills and knowledge in implementing the curriculum according to students' needs. By implementing a variety of learning methods, it is hoped that it can increase student motivation and independence in the learning process.

Stress Detection System using Machine Learning and Sensors

This project presents a novel stress detection system that leverages machine learning and sensor technology to monitor and assess stress levels in real-time. As stress has become a widespread concern affecting mental health, our system integrates wearable sensors—such as heart rate monitors, galvanic skin response sensors, and accelerometers—to capture physiological data indicative of stress. The project involves several key components: data collection and preprocessing, feature extraction, and the development of machine learning models capable of accurately classifying stress levels based on the sensor data. Various algorithms, including Support Vector Machines and Neural Networks, will be employed and optimized for performance. The system is designed to provide real-time feedback to users, offering insights and personalized recommendations for stress management based on detected levels. A user-friendly interface will enable individuals to track their stress over time, fostering greater awareness and encouraging proactive coping strategies

Segmentation of glioblastomas via 3D FusionNet

IntroductionThis study presented an end-to-end 3D deep learning model for the automatic segmentation of brain tumors.MethodsThe MRI data used in this study were obtained from a cohort of 630 GBM patients from the University of Pennsylvania Health System (UPENN-GBM). Data augmentation techniques such as flip and rotations were employed to further increase the sample size of the training set. The segmentation performance of models was evaluated by recall, precision, dice score, Lesion False Positive Rate (LFPR), Average Volume Difference (AVD) and Average Symmetric Surface Distance (ASSD).ResultsWhen applying FLAIR, T1, ceT1, and T2 MRI modalities, FusionNet-A and FusionNet-C the best-performing model overall, with FusionNet-A particularly excelling in the enhancing tumor areas, while FusionNet-C demonstrates strong performance in the necrotic core and peritumoral edema regions. FusionNet-A excels in the enhancing tumor areas across all metrics (0.75 for recall, 0.83 for precision and 0.74 for dice scores) and also performs well in the peritumoral edema regions (0.77 for recall, 0.77 for precision and 0.75 for dice scores). Combinations including FLAIR and ceT1 tend to have better segmentation performance, especially for necrotic core regions. Using only FLAIR achieves a recall of 0.73 for peritumoral edema regions. Visualization results also indicate that our model generally achieves segmentation results similar to the ground truth.DiscussionFusionNet combines the benefits of U-Net and SegNet, outperforming the tumor segmentation performance of both. Although our model effectively segments brain tumors with competitive accuracy, we plan to extend the framework to achieve even better segmentation performance.

Smartphone tests quantify lower extremities dysfunction in multiple sclerosis

IntroductionIncreasing shortage of neurologists compounded by the global aging of the population have translated into suboptimal care of patients with chronic neurological diseases. While some patients might benefit from expanding telemedicine, monitoring neurological disability via telemedicine is challenging. Smartphone technologies represent an attractive tool for remote, self-administered neurological assessment. To address this need, we have developed a suite of smartphone tests, called neurological functional test suite (NeuFun-TS), designed to replicate traditional neurological examination. The aim of this study was to assess the ability of two NeuFun-TS tests—short walk and foot tapping—to quantify motor functions of lower extremities as assessed by a neurologist.MethodsA cohort of 108 multiple sclerosis (MS) patients received a full neurological examination, imaging of the brain, and completed the NeuFun-TS smartphone tests. The neurological exam was digitalized using the NeurEx™ platform, providing calculation of traditional disability scales, as well as quantification of lower extremities-specific disability. We assessed unilateral correlations of 28 digital biomarkers generated from the NeuFun-TS tests with disability and MRI outcomes and developed machine learning models that predict physical disability. Model performance was tested in an independent validation cohort.ResultsNeuFun-TS-derived digital biomarkers correlated strongly with traditional outcomes related to gait and lower extremities functions (e.g., Spearman ρ > 0.8). As expected, the correlation with global disability outcomes was weaker, but still highly significant (e.g., ρ 0.46–0.65; p < 0.001 for EDSS). Digital biomarkers also correlated with semi-quantitative imaging outcomes capturing locations that can affect lower extremity functions (e.g., ρ ~ 0.4 for atrophy of medulla). Reliable digital outcomes with high test-retest values showed stronger correlation with disability outcomes. Combining strong, reliable digital features using machine learning resulted in models that outperformed predictive power of best individual digital biomarkers in an independent validation cohort.DiscussionNeuFun-TS tests provide reliable digital biomarkers of lower extremity motor functions.

Machine learning for predicting in-hospital mortality in elderly patients with heart failure combined with hypertension: a multicenter retrospective study.

Heart failure combined with hypertension is a major contributor for elderly patients (≥ 65 years) to in-hospital mortality. However, there are very few models to predict in-hospital mortality in such elderly patients. We aimed to develop and test an individualized machine learning model to assess risk factors and predict in-hospital mortality in in these patients. From January 2012 to December 2021, this study collected data on elderly patients with heart failure and hypertension from the Chongqing Medical University Medical Data Platform. Least absolute shrinkage and the selection operator was used for recognizing key clinical variables. The optimal predictive model was chosen among eight machine learning algorithms on the basis of area under curve. SHapley Additive exPlanations and Local Interpretable Model-agnostic Explanations was employed to interpret the outcome of the predictive model. This study ultimately comprised 4647 elderly individuals with hypertension and heart failure. The Random Forest model was chosen with the highest area under curve for 0.850 (95% CI 0.789-0.897), high accuracy for 0.738, recall 0.837, specificity 0.734 and brier score 0.178. According to SHapley Additive exPlanations results, the most related factors for in-hospital mortality in elderly patients with heart failure and hypertension were urea, length of stay, neutrophils, albumin and high-density lipoprotein cholesterol. This study developed eight machine learning models to predict in-hospital mortality in elderly patients with hypertension as well as heart failure. Compared to other algorithms, the Random Forest model performed significantly better. Our study successfully predicted in-hospital mortality and identified the factors most associated with in-hospital mortality.

Data-Driven Insights Into Post-Earthquake Reconnaissance Findings: 2023 Türkiye Earthquake Sequence

Post-earthquake reconnaissance stands as a vital endeavor, encompassing a systematic survey and data collection to gain insights into the aftermath of seismic events. Grappling with a multitude of multidimensional data poses inherent challenges in the proper interpretation and extraction of hidden information. This paper unfolds in two parts. Initially, we delineate the reconnaissance mission following the February 06 Türkiye earthquake sequence, elucidating the challenges, complexities, and nature of the amassed data. Subsequently, a paradigm shift toward automated machine learning (AutoML) is embraced to ascertain the optimal model, categorize observed damages, and unveil underlying patterns within the collected data. The most accurate machine learning model is then coupled with Shapley Additive Explanations (SHAP) to explicate observations, steering away from a black-box model. SHAP values discern and prioritize factors significantly contributing to various damage levels. The results reveal a test set accuracy of 0.75 and 0.95 for multi- and binary-class problems, respectively, employing both raw and composite features. Building-related features exert more control over light damage, while earthquake-related factors dominate severe damage. In critical damage scenarios, duration- and velocity-dependent intensity measures assume significance. Furthermore, findings indicate that if column and wall indices are below 0.07 and 0.08, respectively, they positively contribute to the likelihood of critical structural damage.

Penerapan Model Station Rotation untuk Meningkatkan Penguasaan Konsep dan Keterampilan pada Mata Pelajaran Bahasa Inggris

This study aims to evaluate the effectiveness of the Station Rotation learning model in improving students' mastery of concepts and skills in United Kingdom subjects in grade III. The research was conducted in three cycles, each with an approach that involved the use of different stations for learning, exercise, and evaluation. The results show that the application of this model significantly improves students' ability to understand the material and communication skills. The increase in the average competency score of students in designing learning, communicating, and using the United Kingdom was recorded from cycle one to cycle three. However, challenges still exist in terms of material understanding and use of technology, which indicates the need for further adjustments in learning methods and the provision of adequate facilities. Overall, the Station Rotation model has proven to be effective in improving students' collaboration skills and understanding of United Kingdom concepts.

Machine Learning-Based Software for Predicting Pseudomonas spp. Growth Dynamics in Culture Media

In predictive microbiology, both primary and secondary models are widely used to estimate microbial growth, often applied through two-step or one-step modelling approaches. This study focused on developing a tool to predict the growth of Pseudomonas spp., a prominent bacterial genus in food spoilage, by applying machine learning regression models, including Support Vector Regression (SVR), Random Forest Regression (RFR) and Gaussian Process Regression (GPR). The key environmental factors—temperature, water activity, and pH—served as predictor variables to model the growth of Pseudomonas spp. in culture media. To assess model performance, these machine learning approaches were compared with traditional models, namely the Gompertz, Logistic, Baranyi, and Huang models, using statistical indicators such as the adjusted coefficient of determination (R2adj) and root mean square error (RMSE). Machine learning models provided superior accuracy over traditional approaches, with R2adj values from 0.834 to 0.959 and RMSE values between 0.005 and 0.010, showcasing their ability to handle complex growth patterns more effectively. GPR emerged as the most accurate model for both training and testing datasets. In external validation, additional statistical indices (bias factor, Bf: 0.998 to 1.047; accuracy factor, Af: 1.100 to 1.167) further supported GPR as a reliable alternative for microbial growth prediction. This machine learning-driven approach bypasses the need for the secondary modelling step required in traditional methods, highlighting its potential as a robust tool in predictive microbiology.

Multimodal Data Fusion for Precise Lettuce Phenotype Estimation Using Deep Learning Algorithms

Effective lettuce cultivation requires precise monitoring of growth characteristics, quality assessment, and optimal harvest timing. In a recent study, a deep learning model based on multimodal data fusion was developed to estimate lettuce phenotypic traits accurately. A dual-modal network combining RGB and depth images was designed using an open lettuce dataset. The network incorporated both a feature correction module and a feature fusion module, significantly enhancing the performance in object detection, segmentation, and trait estimation. The model demonstrated high accuracy in estimating key traits, including fresh weight (fw), dry weight (dw), plant height (h), canopy diameter (d), and leaf area (la), achieving an R2 of 0.9732 for fresh weight. Robustness and accuracy were further validated through 5-fold cross-validation, offering a promising approach for future crop phenotyping.