Search Results (194)

Learner engagement is a pivotal factor affecting the effectiveness of Massive Open Online Courses (MOOCs), as it promotes collaborative learning environments. However, measuring the extent of learners’ contributions in MOOC learning forums presents challenges due to the complex nature of engagement and its variability. Given the limited research in this domain, further investigation is necessary. This study aims to address this gap by utilizing the Hidden Markov Model (HMM) to identify latent states of MOOC learners and improve their participation in learning forums. The study constructs a multidimensional observable signal sequence based on learner-generated post data from MOOC forums, with a particular focus on the widely attended course on a MOOC platform. To evaluate the predictive accuracy of HMM in forecasting learner contributions, the study employs several prominent prediction models for comparative analysis, including k-nearest neighbor, logistic regression, random forest, extreme gradient boosting tree, and the long short-term memory network. The results demonstrate that HMM provides superior accuracy in predicting learner contributions compared to other models. These findings not only validate the effectiveness of HMM but also offer significant insights and recommendations for enhancing forum management practices. This research represents a substantial advancement in addressing the challenges related to learner engagement in MOOC learning forums and underscores the potential benefits of employing the HMM approach in this context. Full article

Accurate parameter identification in nonlinear and chaotic dynamic systems requires optimization algorithms that can reliably balance global exploration and local refinement in complex, multimodal search landscapes. To address this challenge, a modified artificial protozoa optimizer (mAPO) is developed in this study by embedding two complementary mechanisms into the original artificial protozoa optimizer: a probabilistic random learning strategy to enhance population diversity and global search capability, and a Nelder–Mead simplex-based local refinement stage to improve exploitation and fine-scale solution adjustment. The general optimization performance and scalability of the proposed framework are first evaluated using the CEC2017 benchmark suite. Statistical analyses conducted over shifted and rotated, hybrid, and composition functions demonstrate that mAPO achieves improved mean performance and reduced variability compared with the original APO, indicating enhanced robustness in high-dimensional and complex optimization problems. The effectiveness of mAPO is then examined in nonlinear system identification applications involving chaotic dynamics. Offline and online parameter identification experiments are performed on the Rössler chaotic system and a permanent magnet synchronous motor, including scenarios with abrupt parameter variations. Comparative simulations against APO and several state-of-the-art optimizers show that mAPO consistently yields smaller objective function values, more accurate parameter estimates, and superior statistical stability. In the PMSM case, exact parameter reconstruction with zero error is achieved across all independent runs, while rapid and smooth convergence is observed under both static and time-varying conditions. Full article

Electric vehicles (EVs) rely on a battery pack as their primary energy source, making it a critical component for their operation. To guarantee safe and correct functioning, a Battery Management System (BMS) is employed, which uses variables such as State of Charge (SOC) to set charge/discharge limits and to monitor pack health. In this article, we propose a Multilayer Perceptron (MLP) network to estimate the SOC of a 14.8 V battery pack installed in a robotic vacuum cleaner. Both offline and online (real-time) tests were conducted under continuous load and with rest intervals. The MLP’s output is compared against two commonly used approaches: NARX (Nonlinear Autoregressive Exogenous) and CNN (Convolutional Neural Network). Performance is evaluated via statistical metrics, Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), and we also assess computational cost using Operational Intensity. Finally, we map these results onto a Roofline Model to predict how the MLP would perform on an automotive-grade microcontroller unit (MCU). A generalization analysis is performed using Transfer Learning and optimization using MLP–Kalman. The best performers are the MLP–Kalman network, which achieved an RMSE of approximately 13% relative to the true SOC, and NARX, which achieved approximately 12%. The computational cost of both is very close, making it particularly suitable for use in BMS. Full article

With Transformers achieving outstanding performance on individual remote sensing (RS) tasks, we are now approaching the realization of a unified model that excels across multiple tasks through multi-task learning (MTL). Compared to single-task approaches, MTL methods offer improved generalization, enhanced scalability, and greater practical applicability. Recently, vision-language models (VLMs) have achieved promising results in RS image understanding, grounding, and ultra-high-resolution (UHR) image reasoning, respectively. Moreover, the unified text-based interface demonstrates significant potential for MTL. Hence, in this work, we present RSCoVLM, a simple yet flexible VLM baseline for RS MTL. Firstly, we create the data curation procedure, including data acquisition, offline processing and integrating, as well as online loading and weighting. This data procedure effectively addresses complex RS data enviroments and generates flexible vision-language conversations. Furthermore, we propose a unified dynamic-resolution strategy to address the diverse image scales inherent in RS imagery. For UHR images, we introduce the Zoom-in Chain mechanism together with its corresponding dataset, LRS-VQA-Zoom. The strategies are flexible and effectively mitigate the computational burdens. Additionally, we significantly enhance the model’s object detection capability and propose a novel evaluation protocol that ensures fair comparison between VLMs and conventional detection models. Extensive experiments demonstrate that RSCoVLM achieves state-of-the-art performance across diverse tasks, outperforming existing RS VLMs and even rivaling specialized expert models. All the training and evaluating tools, model weights, and datasets have been fully open-sourced to support reproducibility. We expect that this baseline will promote further progress toward general-purpose RS models. Full article

With the increasing integration of distributed energy resources and the growing variability of multiple loads, distribution networks face significant uncertainties in measurement data, line parameters, and topology. Traditional state estimation methods, such as weighted least squares, rely on accurate network parameters and are therefore highly sensitive to measurement noise and topology variations. To address these challenges, this work proposes a comprehensive data-driven framework for ADN state estimation that features a novel integration of an improved deep residual network (i-ResNet) and transfer learning. An improved deep residual network (i-ResNet) is developed to enable fast and robust state estimation without dependence on online parameters, even under uncertain data conditions. Furthermore, a transfer learning–based model is introduced to accommodate topology changes by leveraging historical data from multiple network configurations. Experimental studies on the IEEE 33-bus and 118-bus test systems are conducted to evaluate the performance of the proposed approach. The results demonstrate that the proposed method achieves higher accuracy and faster convergence than conventional techniques, with voltage magnitude errors consistently maintained below 1%. Full article

This paper presents HV-LIOM (Adaptive Hash-Voxel LiDAR–Inertial Odometry and Mapping), a unified LiDAR–inertial SLAM and autonomous exploration framework for real-time 3D mapping in dynamic, GNSS-denied environments. We propose an adaptive hash-voxel mapping scheme that improves memory efficiency and real-time state estimation by subdividing voxels according to local geometric complexity and point density. To enhance robustness to poor initialization, we introduce a multi-resolution relocalization strategy that enables reliable localization against a prior map under large initial pose errors. A learning-based loop-closure module further detects revisited places and injects global constraints, while global pose-graph optimization maintains long-term map consistency. For autonomous exploration, we integrate a Soft Actor–Critic (SAC) policy that selects informative navigation targets online, improving exploration efficiency in unknown scenes. We evaluate HV-LIOM on public datasets (Hilti and NCLT) and a custom mobile robot platform. Results show that HV-LIOM improves absolute pose accuracy by up to 15.2% over FAST-LIO2 in indoor settings and by 7.6% in large-scale outdoor scenarios. The learned exploration policy achieves comparable or superior area coverage with reduced travel distance and exploration time relative to sampling-based and learning-based baselines. Full article

Network covert channels embed secret data into legitimate traffic, but existing methods struggle to balance undetectability, robustness, and throughput. Application-independent channels at lower protocol layers are easily normalized or disrupted by network noise, while application-dependent streaming schemes rely on handcrafted traffic manipulations that fail to preserve the spatio-temporal dynamics of real encrypted flows and thus remain detectable by modern machine learning (ML)-based classifiers. Meanwhile, with the rapid adoption of HTTP/3, Quick UDP Internet Connections (QUIC) has become the dominant transport for streaming services, offering stable long-lived flows with rich spatio-temporal structure that create new opportunities for constructing resilient covert channels. In this paper, a QUIC streaming-based Covert Channel framework, QuicCC-SMD, is proposed that dynamically Shapes Multi-Dimensional traffic features to identify and exploit redundancy spaces for secret data embedding. QuicCC-SMD models the statistical and temporal dependencies of QUIC flows via Markov chain-based state representations and employs convex optimization to derive an optimal deformation matrix that maps source traffic to legitimate target distributions. Guided by this matrix, a packet-level modulation performs through packet padding, insertion, and delay operations under a periodic online optimization strategy. Evaluations on a real-world HTTP/3 over QUIC (HTTP/3-QUIC) dataset containing 18,000 samples across four video resolutions demonstrate that QuicCC-SMD achieves an average F1 score of 56% at a 1.5% embedding rate, improving detection resistance by at least 7% compared with three representative baselines. Full article

Despite the success of reinforcement learning (RL), the common assumption of online interaction prevents its widespread adoption. Offline RL has emerged as an alternative that learns a policy from precollected data. However, this learning paradigm introduces a new challenge called “distributional shift”, degrading the performance of the policy when evaluated on out-of-distribution (OOD) scenarios (i.e., outside of the training data). Most existing works resolve this by policy regularization to optimize a policy within the support of the data. However, this overlooks the potential for high-reward regions outside of the data. This motivates offline policy optimization that is capable of finding high-reward regions outside of the data. In this paper, we devise a causality-based model architecture to accurately capture the OOD scenarios wherein the policy can be optimized without performance degradation. Specifically, we adapt causal normalizing flows (CNFs) to learn the transition dynamics and reward function for data generation and augmentation in offline policy learning. Based on the physics-based qualitative causal graph and precollected data, we develop a model-based offline OOD-adapting causal RL (MOOD-CRL) algorithm to learn the quantitative structural causal model. Consequently, MOOD-CRL can exercise counterfactual reasoning for sequential decision-making, revealing a high potential for OOD adaptation. The effectiveness is validated through extensive empirical evaluations with ablations including data quality and algorithmic sensitivity. Our results show that MOOD-CRL achieves comparable results with its online counterparts and consistently outperforms state-of-the-art model-free and model-based baselines by a significant margin. Full article

Massive open online courses (MOOCs) represent an innovative online learning paradigm that has garnered considerable popularity in recent years, attracting a multitude of learners to MOOC platforms due to their accessible and adaptable instructional structure. However, the elevated dropout rate in current MOOCs limits their advancement. Current dropout prediction models predominantly employ fixed-size convolutional kernels for feature extraction, which insufficiently address temporal dependencies and consequently demonstrate specific limitations. We propose a Lie Group-based feature context-local fusion attention model for predicting dropout in MOOCs. This model initially extracts shallow features using Lie Group machine learning techniques and subsequently integrates multiple parallel dilated convolutional modules to acquire high-level semantic representations. We design an attention mechanism that integrates contextual and local features, effectively capturing the temporal dependencies in the study behaviors of learners. We performed multiple experiments on the XuetangX dataset to evaluate the model’s efficacy. The results show that our method attains a precision score of 0.910, exceeding the previous state-of-the-art approach by 3.3%. Full article

The accurate identification of crop pests and diseases is critical for global food security, yet the development of robust deep learning models is hindered by the limitations of existing datasets. To address this gap, we introduce DLCPD-25, a new large-scale, diverse, and publicly available benchmark dataset. We constructed DLCPD-25 by integrating 221,943 images from both online sources and extensive field collections, covering 23 crop types and 203 distinct classes of pests, diseases, and healthy states. A key feature of this dataset is its realistic complexity, including images from uncontrolled field environments and a natural long-tail class distribution, which contrasts with many existing datasets collected under controlled conditions. To validate its utility, we pre-trained several state-of-the-art self-supervised learning models (MAE, SimCLR v2, MoCo v3) on DLCPD-25. The learned representations, evaluated via linear probing, demonstrated strong performance, with the SimCLR v2 framework achieving a top accuracy of 72.1% and an F1 score (Macro F1) of 71.3% on a downstream classification task. Our results confirm that DLCPD-25 provides a valuable and challenging resource that can effectively support the training of generalizable models, paving the way for the development of comprehensive, real-world agricultural diagnostic systems. Full article

Over the last fifteen years, the Google Earth Engine (GEE) has become a pivotal tool for large-scale geospatial analysis, with growing applications in urban environmental monitoring. This review examines the peer-reviewed literature, published between 2015 and 2024, that utilizes GEE to evaluate urban environments through remote sensing-derived indices. The literature search strategy was guided by predefined search terms, which were applied to online databases including Scopus and Google Scholar. The inclusion criteria for this review comprised English-language publications, limited to articles only from journals, while book series, books, and conference articles were excluded. The eligibility criteria applied aimed to identify peer-reviewed studies that applied GEE to urban contexts using vegetation, thermal, greenness, or density indices. Studies without a clear urban focus or not employing GEE as a primary tool were excluded. The selection process followed a structured methodological flow, where a total of 291 studies were identified that fulfilled the applied criteria. This review indicates that key methodological trends encompass both conventional techniques, such as Random Forests (RFs), Support Vector Machines (SVMs), and classification/regression trees, as well as emerging machine learning algorithms, with Landsat, Sentinel, and MODIS as the most commonly used satellite datasets. The articles included in this review show a geographic focus, with over 44% of publications from China, 11% from the United States, and 9% from India, while the rest of the countries identified in this review contribute fewer than 5% each, suggesting that there is a significant opportunity for research in underrepresented regions. The main result of this review is that GEE proves to be an effective, scalable, and reproducible platform for urban environmental analysis, with most studies focusing on vegetation and thermal indices using Landsat, Sentinel, and MODIS data. As GEE has become one of the most widely used platforms for urban environmental monitoring, future research should focus on addressing challenges such as the standardization of indices, the consistency of methodological approaches, and the expansion of global coverage through advanced cloud-based geospatial frameworks. Full article

The present study focuses on wind power forecasting (WPF) models based on deep neural networks (DNNs), aiming to evaluate current approaches, identify gaps, and provide insights into their importance for the integration of Renewable Energy Sources (RESs). The systematic review was conducted following the methodology of Kitchenham and Charters, including peer-reviewed articles from 2020 to 2024 that focused on WPF using deep learning (DL) techniques. Searches were conducted in the ACM Digital Library, IEEE Xplore, ScienceDirect, Springer Link, and Wiley Online Library, with the last search updated in April 2024. After the first phase of screening and then filtering using inclusion and exclusion criteria, risk of bias was assessed using a Likert-scale evaluation of methodological quality, validity, and reporting. Data extraction was performed for 120 studies. The synthesis established that the state of the art is dominated by hybrid architectures (e.g., CNN-LSTM) integrated with signal decomposition techniques like VMD and optimization algorithms such as GWO and PSO, demonstrating high predictive accuracy for short-term horizons. Despite these advancements, limitations include the variability in datasets, the heterogeneity of model architectures, and a lack of standardization in performance metrics, which complicate direct comparisons across studies. Overall, WPF models based on DNNs demonstrate substantial promise for renewable energy integration, though future work should prioritize standardization and reproducibility. This review received no external funding and was not prospectively registered. Full article

This literature review addresses a major research gap in electromobility by providing a comprehensive synthesis of machine learning (ML) and deep learning (DL) applications for forecasting energy consumption, managing battery state of charge (SoC), and integrating electric vehicles (EVs) with charging infrastructure and smart grids, including vehicle-to-grid (V2G) systems. Despite the rapid increase in publications between 2016 and 2025, few comparative studies systematically evaluate ML/DL approaches, their effectiveness in specific applications, and their limitations under real-world conditions. To bridge this gap, this review analyzes 95 publications, covering methods from ensemble learners (e.g., Random Forest, XGBoost) to advanced hybrids (e.g., LSTM + MPC). Key influencing factors such as driving style, topography, and weather are considered. This review identifies persistent challenges, including the lack of standardized datasets, limited model generalization, and high computational demands. It also outlines research directions, such as adaptive online learning and integration with V2X technologies. By consolidating current knowledge, this review supports engineers, EV system designers, and policymakers in planning effective energy management and charging strategies, thereby contributing to the sustainable development of electromobility. Full article

Cardiovascular diseases claim millions of lives each year, yet timely diagnosis remains a significant challenge due to the high number of patients and associated costs. Although various machine learning solutions have been proposed for this problem, most approaches rely on careful data preprocessing and feature engineering workflows that could benefit from more comprehensive documentation in research publications. To address this issue, this paper presents a machine learning framework for predicting heart attack risk online. Our systematic methodology integrates a unified pipeline featuring advanced data preprocessing, optimized feature selection, and an exhaustive hyperparameter search using cross-validated grid evaluation. We employ a metamodel ensemble strategy, testing and combining six traditional supervised models along with six stacking and voting ensemble models. The proposed system achieves accuracies ranging from 90.2% to 98.9% on three independent clinical datasets, outperforming current state-of-the-art methods. Additionally, it powers a deployable, lightweight web application for real-time decision support. By merging cutting-edge AI with clinical usability, this work offers a scalable solution for early intervention in cardiovascular care. Full article

Despite the remarkable progress of deep learning in image segmentation, models often struggle with generalization across diverse datasets. This study explores novel input augmentation techniques and ensemble strategies to improve image segmentation performance. We investigate how the Segment Anything Model (SAM) can produce relevant information for model training. We believe that SAM offers a promising source of prior information that can be exploited to improve robustness and accuracy. Building on this, we propose input augmentation techniques that integrate SAM information directly into the images, enhancing the learning process of segmentation models. Each proposed augmentation method comes with its unique advantages; therefore, to leverage the strengths of each approach, we introduce AuxMix, a model trained with a combination of SAM-based augmentation methods. We conduct experiments on different state-of-the-art segmentation models, evaluating the effects of each method independently and within an ensemble framework. The results show that our ensemble strategy, combining complementary information from each augmentation, leads to robust and improved segmentation performance in a large set of datasets. We use only publicly available datasets in our experiments, and all the code developed to reproduce our results is available online on GitHub. Full article