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.

This study conducts a comparative analysis of various machine learning and deep learning models for predicting order quantities in supply chain tiers. The models employed include XGBoost, Random Forest, CNN-BiLSTM, Linear Regression, Support Vector Regression (SVR), K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), Bidirectional LSTM (BiLSTM), Bidirectional GRU (BiGRU), Conv1D-BiLSTM, Attention-LSTM, Transformer, and LSTM-CNN hybrid models. Experimental results show that the XGBoost, Random Forest, CNN-BiLSTM, and MLP models exhibit superior predictive performance. In particular, the XGBoost model demonstrates the best results across all performance metrics, attributed to its effective learning of complex data patterns and variable interactions. Although the KNN model also shows perfect predictions with zero error values, this indicates a need for further review of data processing procedures or model validation methods. Conversely, the BiLSTM, BiGRU, and Transformer models exhibit relatively lower performance. Models with moderate performance include Linear Regression, RNN, Conv1D-BiLSTM, Attention-LSTM, and the LSTM-CNN hybrid model, all displaying relatively higher errors and lower coefficients of determination (R²). As a result, tree-based models (XGBoost, Random Forest) and certain deep learning models like CNN-BiLSTM are found to be effective for predicting order quantities in supply chain tiers. In contrast, RNN-based models (BiLSTM, BiGRU) and the Transformer show relatively lower predictive power. Based on these results, we suggest that tree-based models and CNN-based deep learning models should be prioritized when selecting predictive models in practical applications.

This research aims to develop a Synergy Learning Model in the context of science learning.  This research was conducted at Islamic Junior High School, Madrasah Tsanawiyah Negeri 2 Medan, involving 64 students of Grade 7 as the research subject. The method used in this research refers to the development research approach (R&D). In collecting the data, the research employed test and non-test techniques. The results prove that the Synergy learning model developed is effective in improving student learning outcomes. This is evident through the t-test statistical test where the t-count of 4.26 is higher than the t-table of 1.99. In addition, the level of practicality with a score of 3.39 is categorized as practical. This learning model emphasizes the learning process that supports the development of science skills and develops students' competencies in planning, collaborating, and critically reflecting. The findings of this study contribute to pedagogical practices and literature in the field of science learning.

Recognizing the importance of competition analysis in telecommunications markets is essential to improve conditions for users and companies. Several indices in the literature assess competition in these markets, mainly through company concentration. Artificial Intelligence (AI) emerges as an effective solution to process large volumes of data and manually detect patterns that are difficult to identify. This article presents an AI model based on the LINDA indicator to predict whether oligopolies exist. The objective is to offer a valuable tool for analysts and professionals in the sector. The model uses the traffic produced, the reported revenues, and the number of users as input variables. As output parameters of the model, the LINDA index is obtained according to the information reported by the operators, the prediction using Long-Short Term Memory (LSTM) for the input variables, and finally, the prediction of the LINDA index according to the prediction obtained by the LSTM model. The obtained Mean Absolute Percentage Error (MAPE) levels indicate that the proposed strategy can be an effective tool for forecasting the dynamic fluctuations of the communications market.

Brain tumors are a primary factor causing cancer-related deaths globally, and their classification remains a significant research challenge due to the variability in tumor intensity, size, and shape, as well as the similar appearances of different tumor types. Accurate differentiation is further complicated by these factors, making diagnosis difficult even with advanced imaging techniques such as magnetic resonance imaging (MRI). Recent techniques in artificial intelligence (AI), in particular deep learning (DL), have improved the speed and accuracy of medical image analysis, but they still face challenges like overfitting and the need for large annotated datasets. This study addresses these challenges by presenting two approaches for brain tumor classification using MRI images. The first approach involves fine-tuning transfer learning cutting-edge models, including SEResNet, ConvNeXtBase, and ResNet101V2, with global average pooling 2D and dropout layers to minimize overfitting and reduce the need for extensive preprocessing. The second approach leverages the Vision Transformer (ViT), optimized with the AdamW optimizer and extensive data augmentation. Experiments on the BT-Large-4C dataset demonstrate that SEResNet achieves the highest accuracy of 97.96%, surpassing ViT’s 95.4%. These results suggest that fine-tuning and transfer learning models are more effective at addressing the challenges of overfitting and dataset limitations, ultimately outperforming the Vision Transformer and existing state-of-the-art techniques in brain tumor classification.

This study employs a transfer matrix, dynamic degree, stability index, and the PLUS model to analyze the spatiotemporal changes in forest land and their driving factors in Yibin City from 2000 to 2022. The results reveal the following: (1) The land use in Yibin City is predominantly characterized by cultivated land and forest land (accounting for over 95% of the total area). The area of cultivated land initially increased and then decreased, while forest land continued to decline and construction land expanded significantly. The rate of forest land loss has slowed (with the dynamic degree decreasing from −0.62% to −0.04%), and ecosystem stability has improved (the F-value increased from 2.27 to 2.9). The conversion of cultivated land to forest land is the primary driver of forest recovery, whereas the conversion of forest land to cultivated land is the main cause of reduction; (2) cultivated land is concentrated in the central and northeastern regions, while forest land is distributed in the western and southern mountainous areas. Construction land is predominantly located in urban areas and along transportation routes. Areas of forest land reduction are mainly found in the central and southern regions with rapid economic development, while areas of forest land increase are concentrated in high-altitude zones or key ecological protection areas. Stable forest land is distributed in the western and southern ecological conservation zones; (3) changes in forest land are primarily influenced by annual precipitation, elevation, and distance to rivers. Road accessibility and GDP have significant impacts, while slope, annual average temperature, and population density exert moderate influences. Distance to railways, aspect, and soil type have relatively minor effects. The findings of this study provide a scientific basis for the sustainable management of forest resources and ecological conservation in Yibin City.