Search Results (83)

Emerging digital technologies are transforming how consumers participate in financial markets, yet their benefits depend critically on the speed, reliability, and transparency of the underlying platforms. Online stock trading platforms must maintain high efficiency underload to ensure a good user experience. This paper presents performance analysis under various load conditions based on the containerized stock exchange system. A comprehensive data logging pipeline was implemented, capturing metrics such as API response times, database query times, and resource utilization. We analyze the collected data to identify performance patterns, using both statistical analysis and machine learning techniques. Preliminary analysis reveals correlations between application processing time and database load, as well as the impact of user behavior on system performance. Association rule mining is applied to uncover relationships among performance metrics, and multiple classification algorithms are evaluated for their ability to predict user activity class patterns from system metrics. The insights from this work can guide optimizations in similar distributed web applications to improve scalability and reliability under a heavy load. By framing performance not merely as a technical property but as a determinant of financial decision-making and well-being, the study contributes actionable insights for designers of consumer-facing fintech services seeking to meet sustainable development goals through trustworthy, resilient digital infrastructure. Full article

One of the main issues with paragangliomas and pheochromocytomas is that these tumors have up to a 20% rate of metastatic disease, which cannot be reliably predicted. While machine learning models hold great promise for enhancing predictive accuracy, their often opaque nature limits trust and adoption in critical fields such as healthcare. Understanding the factors driving predictions is essential not only for validating their reliability but also for enabling their integration into clinical decision-making. In this paper, we propose an architecture that combines data mining, machine learning, and explainability techniques to improve predictions of metastatic disease in these types of cancer and enhance trust in the models. A wide variety of algorithms have been applied for the development of predictive models, with a focus on interpreting their outputs to support clinical insights. Our methodology involves a comprehensive preprocessing phase to prepare the data, followed by the application of classification algorithms. Explainability techniques were integrated to provide insights into the key factors driving predictions. Additionally, a feature selection process was performed to identify the most influential variables and explore how their inclusion affects model performance. The best-performing algorithm, Random Forest, achieved an accuracy of 96.3%, precision of 96.5%, and AUC of 0.963, among other metrics, combining strong predictive capability with explainability that fosters trust in clinical applications. Full article

Artificial intelligence (AI) has found applications across diverse sectors in recent years, significantly enhancing operational efficiencies and user experiences. Educational data mining (EDM) has emerged as a pivotal AI application to transform educational environments by optimizing learning processes and identifying at-risk students. This study leverages EDM within a Moroccan university (Hassan First, University Settat, Morocco) context to augment educational quality and improve learning. We introduce a novel “Hybrid approach” that synthesizes students’ historical academic records and their in-class behavioral data, provided by instructors, to predict student performance in initial coding courses. Utilizing a range of machine learning (ML) algorithms, our research applies multi-classification, data augmentation, and binary classification techniques to evaluate student outcomes effectively. The key performance metrics, accuracy, precision, recall, and F1-score, are calculated to assess the efficacy of classification. Our results highlight the long short-term memory (LSTM) algorithm’s robustness achieving the highest accuracy of 94% and an F1-score of 0.87 along with a support vector machine (SVM), indicating high efficacy in predicting student success at the onset of learning coding. Furthermore, the study proposes a comprehensive framework that can be integrated into learning management systems (LMSs) to accommodate generational shifts in student populations, evolving university pedagogies, and varied teaching methodologies. This framework aims to support educational institutions in adapting to changing educational dynamics while ensuring high-quality, tailored learning experiences for students. Full article

Originally developed as an effective feature selection method in healthcare predictive analytics, Recursive Feature Elimination (RFE) has gained increasing popularity in Educational Data Mining (EDM) due to its ability to handle high-dimensional data and support interpretable modeling. Over time, various RFE variants have emerged, each introducing methodological enhancements. To help researchers better understand and apply RFE more effectively, this study organizes existing variants into four methodological categories: (1) integration with different machine learning models, (2) combinations of multiple feature importance metrics, (3) modifications to the original RFE process, and (4) hybridization with other feature selection or dimensionality reduction techniques. Rather than conducting a systematic review, we present a narrative synthesis supported by illustrative studies from EDM to demonstrate how different variants have been applied in practice. We also conduct an empirical evaluation of five representative RFE variants across two domains: a regression task using a large-scale educational dataset and a classification task using a clinical dataset on chronic heart failure. Our evaluation benchmarks predictive accuracy, feature selection stability, and runtime efficiency. Results show that the evaluation metrics vary significantly across RFE variants. For example, while RFE wrapped with tree-based models such as Random Forest and Extreme Gradient Boosting (XGBoost) yields strong predictive performance, these methods tend to retain large feature sets and incur high computational costs. In contrast, a variant known as Enhanced RFE achieves substantial feature reduction with only marginal accuracy loss, offering a favorable balance between efficiency and performance. These findings underscore the trade-offs among accuracy, interpretability, and computational cost across RFE variants, providing practical guidance for selecting the most appropriate algorithm based on domain-specific needs and constraints. Full article

The roughness of haul roads significantly impacts fuel consumption in open-pit coal mine trucks, yet there is currently a lack of quantitative road classification methods in this regard. This study proposes a fuel-efficient road classification methodology for open-pit coal mines. Using UAV-captured point cloud data of mine roads as the basis for roughness analysis and the International Roughness Index (IRI) as the evaluation metric, the research establishes linear relationships between IRI and fuel consumption for both loaded and unloaded trucks. The K-means clustering algorithm is employed to classify road quality into “good”, “moderate”, and “poor” categories, with the Haerwusu Open-pit Coal Mine serving as a case study. Results demonstrate that 150 m represents an appropriate IRI segmentation interval for Haerwusu, with IRI thresholds of 12 (15) and 20 (21) serving as critical segmentation points for loaded (unloaded) trucks. From analyzing two end-slope roads in the case study mine we found that upgrading “poor” roads to “moderate” quality could reduce fuel costs by 3% for loaded trucks and 2% for unloaded trucks. This study provides a quantitative road classification method for open-pit coal mines, offering a theoretical foundation for reducing transportation costs and promoting sustainable mining development. Full article

Background/Objectives: Activities of Daily Living (ADLs) are crucial for assessing an individual’s autonomy, encompassing tasks such as eating, dressing, and moving around, among others. Predicting these activities is part of health monitoring, elderly care, and intelligent systems, improving quality of life, and facilitating early dependency detection, all of which are relevant components of personalized health and social care. However, the automatic classification of ADLs from sensor data remains challenging due to high variability in human behavior, sensor noise, and discrepancies in data acquisition protocols. These challenges limit the accuracy and applicability of existing solutions. This study details the modeling and evaluation of real-time ADL classification models based on batch learning (BL) and stream learning (SL) algorithms. Methods: The methodology followed is the Cross-Industry Standard Process for Data Mining (CRISP-DM). The models were trained with a comprehensive dataset integrating 23 ADL-centric datasets using accelerometers and gyroscopes data. The data were preprocessed by applying normalization and sampling rate unification techniques, and finally, relevant sensor locations on the body were selected. Results: After cleaning and debugging, a final dataset was generated, containing 238,990 samples, 56 activities, and 52 columns. The study compared models trained with BL and SL algorithms, evaluating their performance under various classification scenarios using accuracy, area under the curve (AUC), and F1-score metrics. Finally, a mobile application was developed to classify ADLs in real time (feeding data from a dataset). Conclusions: The outcome of this study can be used in various data science projects related to ADL and Human activity recognition (HAR), and due to the integration of diverse data sources, it is potentially useful to address bias and improve generalizability in Machine Learning models. The principal advantage of online learning algorithms is dynamically adapting to data changes, representing a significant advance in personal autonomy and health care monitoring. Full article

This study establishes a combination method-based prediction model for the CSI 300 stock index price embedded with options market information. Firstly, utilizing options and spot market information, a BP neural network is employed to predict the CSI 300 stock index price. Secondly, a logical framework based on a combination method is constructed to further optimize the CSI 300 stock index price prediction through decomposition–clustering, error adjustment, and weighted integration approaches. The results demonstrate the following: (1) Compared to price predictions based solely on spot market information, the introduction of options market information significantly enhances the forecasting performance for the CSI 300 index price. (2) From the perspective of options moneyness classification, after incorporating options information, different types of options contracts exhibit varying impacts on the CSI 300 index price prediction. Prior to optimization, predictions incorporating in-the-money call options with maximum trading volume yield the optimal performance based on the MSE metric. (3) Under the logical framework of the combination method, the prediction effect for the CSI 300 stock index price is gradually improved after introducing the decomposition–clustering method, the error adjustment method, and the price-weighted integration method, which shows that it is appropriate to use the combination method to optimize the price prediction. Overall, this study proposes a combination method for price forecasting incorporating options market information across diverse contract types. It allows for weighted integration of prediction results derived from various options information, offering a novel research angle for spot market price prediction. The study also underscores the importance of implicit information mining and multi-market information fusion for price prediction, which is expected to become a key research focus in this field. Full article

This study examines the psychological well-being (PWB) of lower secondary school students in Bangkok’s Secondary Educational Service Area Offices (SESAO) 1 and 2, using data mining techniques to analyze key influencing factors and develop a culturally adapted PWB questionnaire. The research framework is based on six components: autonomy, environmental mastery, personal growth, positive relationships, life purpose, and self-acceptance. Data were collected from 2543 students in the 2023 academic year and analyzed using the Waikato Environment for Knowledge Analysis (WEKA) program and the JRip rule-based classification model. Results indicate that personal growth is the most predictive in the classification performance of PWB, followed by positive relationships and life purpose. A newly developed PWB questionnaire was tested for reliability, with the Supplied Test Set (80:20) method yielding strong performance metrics, including accuracy (90.18%), precision (69.00%), recall (90.90%), and F-measure (78.40%). This study demonstrates data mining’s effectiveness in identifying factors influencing adolescent PWB within the Thai context. The findings provide educators and policymakers with insights for fostering student well-being and contribute to research by offering a validated, culturally relevant assessment tool. Full article

Training deep learning models for classification with limited data and computational resources remains a challenge when the number of classes is large. Metric learning offers an effective solution to this problem. However, it has its own shortcomings due to the known imperfections of widely used loss functions such as contrastive loss and triplet loss, as well as sample mining methods. This paper address these issues by proposing a novel mining method and metric loss function. Firstly, this paper presents an auto-probabilistic mining method designed to automatically select the most informative training samples for Siamese neural networks. Combined with a previously proposed auto-clustering technique, the method improves model training by optimizing the utilization of available data and reducing computational overhead. Secondly, this paper proposes the novel cluster-aware triplet-based metric loss function that addresses the limitations of contrastive and triplet loss, enhancing the overall training process. To evaluate the proposed methods, experiments were conducted with the optical character recognition task using the PHD08 and Omniglot datasets. The proposed loss function with the random-mining method achieved $82.6\%$ classification accuracy on the PHD08 dataset with full training on the Korean alphabet, surpassing the known baseline. The same experiment, using a reduced training alphabet, set a new baseline of $88.6\%$ on the PHD08 dataset. The application of the novel mining method further enhanced the accuracy to $90.6\%$ (+2.0%) and, combined with auto-clustering, achieved $92.3\%$ (+3.7%) compared with the new baseline. On the Omniglot dataset, the proposed mining method reached $92.32\%$, rising to $93.17\%$ with auto-clustering. These findings highlight the potential effectiveness of the developed loss function and mining method in addressing a wide range of pattern recognition challenges. Full article

Drilling and completion condition identification is of great significance in improving operational efficiency, reducing safety risks and optimizing resource utilization. However, traditional methods rely on experts’ experience and rules and have low recognition accuracy and poor robustness when facing dynamic working condition changes. In recent years, deep learning technology has shown great potential in the field of time series data analysis and multimodal data fusion. In this paper, we propose a hybrid deep learning model (CNN-GNN-LSTM) based on a convolutional neural network (CNN), graph neural network (GNN) and long short-term memory network (LSTM). The model extracts the local spatial features of multi-sensors via a CNN module to reduce the noise interference; models the nonlinear dependency between sensors via a GNN module to capture the complex interaction relationship; and mines the long- and short-term time dependencies via an LSTM module to accurately identify the dynamic change and transition process of the working conditions. This significantly improves the classification accuracy under dynamic changes in multi-conditions. This study compares the performance of four models: a CNN, LSTM, CNN-LSTM, and CNN-GNN-LSTM. The results show that the CNN-GNN-LSTM outperforms the other models in key metrics such as the classification accuracy, recall, F1 score, etc., and is more robust to noise interference and changes in complex working conditions. This study verifies the advantages of the hybrid model in multi-sensor complex scenarios and provides technical support for the intelligent development of drilling and completion condition recognition. Full article

The Patient Rule Induction Method is a data mining technique used for identifying patterns in datasets, particularly focusing on discovering regions of the chosen input space where the response variable is unusually high or low. It falls in the subgroup discovery field, where finding small groups is more relevant for the explainability of the results, although it is not a classification technique, per se. In this paper, we introduce a new framework for breast cancer classification based on the PRIM. This new method involves, first, the random choice of different input spaces for each class label; second, the organization and pruning of the rules using metarules; and finally, it also includes the proposition of a way to handle the class overlapping and, hence, define the final classifier. The framework is tested on five real-life breast cancer datasets compared to three often-used algorithms for breast cancer classification: XG Boost, Logistic Regression, and Random Forest. Across the four metrics and datasets, both our PRIM-based framework and Random Forest demonstrate robust performance, with our framework showing notable accuracy and recall. XGBoost maintains strong F1-scores across the board, indicating balanced precision and recall. On the other hand, Logistic Regression, while competent, generally underperforms compared to the other algorithms, especially in terms of accuracy and recall, achieving 94.1% accuracy against 96.8% and 85.4% recall against 94.2% for the PRIM-based framework on the Wisconsin dataset. Full article

Historically known for its tin mining industry, Phuket Island has undergone significant transformation into a global tourism hub. This study aims at analyzing the evolutionary dynamics of Phuket Island from the years 1987 to 2024. We integrate Landsat satellite images and sophisticated analytical methods to assess the effects of tourism and economic policies on changes in land use and land cover using Google Earth Engine (GEE) for cloud-based data processing and Random Forest (RF) models for classification, and the Urban Expansion Intensity Index (UEII) and Shannon Entropy metrics for measuring the intensity of urban expansion and diversity, respectively. The results show that there has been a dynamic change in the patterns of land use which was brought about by the economic and environmental forces. Some of the major events that have had a great effect on Phuket’s landscape include the 1997 Asian Financial Crisis, the 2004 Indian Ocean Tsunami, and the COVID-19 pandemic; this highlights how the island is fragile and can be affected easily by events happening around the world. This work reveals a dramatic reduction in forest and mangrove cover, which calls for increased conservation measures to prevent the loss of biodiversity and to preserve the natural balance. Full article

People tend to share their opinions on social media daily. This text needs to be accurately mined for different purposes like enhancements in services and/or products. Mining and analyzing Arabic text have been a big challenge due to many complications inherited in Arabic language. Although, many research studies have already investigated the Arabic text sentiment analysis problem, this paper investigates the specific research topic that addresses Arabic comparative opinion mining. This research topic is not widely investigated in many research studies. This paper proposes a lexicon-based framework which includes a set of proposed algorithms for the mining and analysis of Arabic comparative sentences. The proposed framework comprises a set of contributions including an Arabic comparative sentence keywords lexicon and a proposed algorithm for the identification of Arabic comparative sentences, followed by a second proposed algorithm for the classification of identified comparative sentences into different types. The framework also comprises a third proposed algorithm that was developed to extract relations between entities in each of the identified comparative sentence types. Finally, two proposed algorithms were developed for the extraction of the preferred entity in each sentence type. The framework was evaluated using three different Arabic language datasets. The evaluation metrics used to obtain the evaluation results include precision, recall, F-score, and accuracy. The average values of the evaluation metrics for the proposed sentences identification algorithm reached 97%. The average evaluation values of the evaluation metrics for the proposed sentence type identification algorithm reached 96%. Finally, the average results showed 97% relation word extraction precision for the proposed relation extraction algorithm. Full article

The effectiveness of grouting management is closely linked to the safety of mining operations, making the scientific and accurate evaluation of mine water hazard grouting management a critical issue that demands immediate attention. Current evaluation technologies for grouting effectiveness are limited by singularity in indicator assignment, reliance on isolated indicators, and the generalization of weak metrics. Using the top and bottom grouting project of the 110504 working face at the Banji coal mine in Anhui Province as a case study, both theoretical and practical insights were integrated. Drilling fluid consumption, final grouting pressure, water permeability, and dry material per unit length were selected as key indicators to establish a comprehensive grouting effect evaluation index system. To address the limitations of previous assignment methods, this study proposes a novel approach that combines the Precedence Chart (PC) with the Criteria Importance Through Intercriteria Correlation (CRITIC) method. This integrated approach resolves the issues of singularity and subjectivity in prior assignment techniques. The evaluation system was constructed based on a single indicator framework, incorporating a comprehensive evaluation model that uses the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) for ranking and the Rank Sum Ratio (RSR) for classification support. The model demonstrates a high goodness-of-fit, with a value of 0.938, indicating strong performance. The model’s results were visualized in the form of a grouting effect zoning map, further validated through comparisons with actual on-site water discharge data and exploration borehole water inflow measurements. A maximum recorded influx of 70 m³/h, aligning with the relatively weak grouting zones identified in the evaluation. The findings demonstrate that the proposed model exhibits a high degree of reliability and scientific rigor, providing valuable theoretical guidance for enhancing coal body stability and minimizing coal loss. Full article

Presidential elections are an important political event that often trigger intense debate. With more than 139 million users, YouTube serves as a significant platform for understanding public opinion through sentiment analysis. This study aimed to implement deep learning techniques for a multi-label sentiment analysis of comments on YouTube videos related to the 2024 Indonesian presidential election. Offering a fresh perspective compared to previous research that primarily employed traditional classification methods, this study classifies comments into eight emotional labels: anger, anticipation, disgust, joy, fear, sadness, surprise, and trust. By focusing on the emotional spectrum, this study provides a more nuanced understanding of public sentiment towards presidential candidates. The CRISP-DM method is applied, encompassing stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment, ensuring a systematic and comprehensive approach. This study employs a dataset comprising 32,000 comments, obtained via YouTube Data API, from the KPU and Najwa Shihab channels. The analysis is specifically centered on comments related to presidential candidate debates. Three deep learning models—Convolutional Neural Network (CNN), Bidirectional Long Short-Term Memory (Bi-LSTM), and a hybrid model combining CNN and Bi-LSTM—are assessed using confusion matrix, Area Under the Curve (AUC), and Hamming loss metrics. The evaluation results demonstrate that the Bi-LSTM model achieved the highest accuracy with an AUC value of 0.91 and a Hamming loss of 0.08, indicating an excellent ability to classify sentiment with high precision and a low error rate. This innovative approach to multi-label sentiment analysis in the context of the 2024 Indonesian presidential election expands the insights into public sentiment towards candidates, offering valuable implications for political campaign strategies. Additionally, this research contributes to the fields of natural language processing and data mining by addressing the challenges associated with multi-label sentiment analysis. Full article