Search Results (4,928)

Financial time series prediction is a fundamental problem in investment and risk management. Deep learning models, such as multilayer perceptrons, Convolutional Neural Networks (CNNs), and Long Short-Term Memory (LSTM), have been widely used in modeling time series data by incorporating historical information. Among them, LSTM has shown excellent performance in capturing long-term temporal dependencies in time-series data, owing to its enhanced internal memory mechanism. In spite of the success of these models, it is observed that in the presence of sharp changing points, these models fail to perform. To address this problem, we propose, in this article, an innovative financial time series prediction method inspired by the Deep Operator Network (DeepONet) architecture, which uses a combination of transformer architecture and a one-dimensional CNN network for processing feature-based information, followed by an LSTM based network for processing temporal information. It is therefore named the CNN–LSTM–Transformer (CLT) model. It not only incorporates external information to identify latent patterns within the financial data but also excels in capturing their temporal dynamics. The CLT model adapts to evolving market conditions by leveraging diverse deep-learning techniques. This dynamic adaptation of the CLT model plays a pivotal role in navigating abrupt changes in the financial markets. Furthermore, the CLT model improves the long-term prediction accuracy and stability compared with state-of-the-art existing deep learning models and also mitigates adverse effects of market volatility. The experimental results show the feasibility and superiority of the proposed CLT model in terms of prediction accuracy and robustness as compared to existing prediction models. Moreover, we posit that the innovation encapsulated in the proposed DeepONet-inspired CLT model also holds promise for applications beyond the confines of finance, such as remote sensing, data mining, natural language processing, and so on. Full article

Background/Objectives: Inflammation serves as a vital response to diverse harmful stimuli like infections, toxins, or tissue injuries, aiding in the elimination of pathogens and tissue repair. However, persistent inflammation can lead to chronic diseases. Peptide therapeutics have gained attention for their specificity in targeting cells, yet their development remains costly and time-consuming. Therefore, small molecules, with their stability, low immunogenicity, and oral bioavailability, have become a focal point for predicting anti-inflammatory small molecules (AISMs). Methods: In this study, we introduce a computational method called AISMPred, designed to classify AISMs and non-AISMs. To develop this approach, we constructed a dataset comprising 1750 AISMs and non-AISMs, each annotated with ${\mathrm{I}\mathrm{C}}_{50}$ values sourced from the PubChem BioAssay database. We computed two distinct types of molecular descriptors using PaDEL and Mordred tools. Subsequently, these descriptors were concatenated to form a hybrid feature set. The SVC-L1 regularization method was implemented for the optimum feature selection to develop robust Machine learning (ML) models. Five different conventional ML classifiers were employed, such as RF, ET, KNN, LR, and Ensemble methods. Results: A total of 15 ML models were developed using 2D, FP, and Hybrid feature sets, with the ET model with hybrid features achieving the highest accuracy of 92% and an AUC of 0.97 on the independent test dataset. Conclusions: This study provides an effective method for screening AISMs, potentially impacting drug discovery and design. Full article

Recently, AI systems such as autonomous driving and smart homes have become integral to daily life. Intelligent multi-sensors, once limited to single data types, now process complex text and image data, demanding faster and more accurate processing. While integrating NPUs and sensors has improved processing speed and accuracy, challenges like low resource utilization and long memory latency remain. This study proposes a method to reduce processing time and improve resource utilization by virtualizing NPUs to simultaneously handle multiple deep-learning models, leveraging a hardware scheduler and data prefetching techniques. Experiments with 30,000 SA resources showed that the hardware scheduler reduced memory cycles by over 10% across all models, with reductions of 30% for NCF and 70% for DLRM. The hardware scheduler effectively minimized memory latency and idle NPU resources in resource-constrained environments with frequent context switching. This approach is particularly valuable for real-time applications like autonomous driving, enabling smooth transitions between tasks such as object detection and route planning. It also enhances multitasking in smart homes by reducing latency when managing diverse data streams. The proposed system is well suited for resource-constrained environments that demand efficient multitasking and low-latency processing. Full article

Accurate protein secondary structure prediction (PSSP) plays a crucial role in biopharmaceutics and disease diagnosis. Current prediction methods are mainly based on multiple sequence alignment (MSA) encoding and collaborative operations of diverse networks. However, existing encoding approaches lead to poor feature space utilization, and encoding quality decreases with fewer homologous proteins. Moreover, the performance of simple stacked networks is greatly limited by feature extraction capabilities and learning strategies. To this end, we propose MHTAPred-SS, a novel PSSP framework based on the fusion of six features, including the embedding feature derived from a pre-trained protein language model. First, we propose a highly targeted autoencoder (HTA) as the driver to encode sequences in a homologous protein-independent manner. Second, under the guidance of biological knowledge, we design a protein secondary structure prediction model based on the multi-task learning strategy (PSSP-MTL). Experimental results on six independent test sets show that MHTAPred-SS achieves state-of-the-art performance, with values of 88.14%, 84.89%, 78.74% and 77.15% for Q3, SOV3, Q8 and SOV8 metrics on the TEST2016 dataset, respectively. Additionally, we demonstrate that MHTAPred-SS has significant advantages in single-category and boundary secondary structure prediction, and can finely capture the distribution of secondary structure segments, thereby contributing to subsequent tasks. Full article

In high-dimensional machine learning tasks, supervised feature extraction is essential for improving model performance, with Linear Discriminant Analysis (LDA) being a common approach. However, LDA tends to deliver suboptimal performance when dealing with class imbalance. To address this issue, we propose a novel feature extraction model, Weighted Linear Discriminant Analysis (WLDA), which integrates cost-sensitive techniques into the traditional LDA framework. By assigning weights inversely proportional to class sample sizes, WLDA achieves effective feature extraction under imbalanced sample conditions. We introduce an efficient solution algorithm for the proposed model and provide a thorough complexity analysis. Experimental results demonstrate the superior performance of WLDA in handling imbalanced datasets, confirming its potential as a robust tool for high-dimensional data scenarios. Overall, WLDA not only improves feature extraction for imbalanced datasets but also enhances classification accuracy across diverse applications. Full article

A multi-strategy improved honey badger algorithm (MIHBA) is proposed to address the problem that the honey badger algorithm may fall into local optimum and premature convergence when dealing with complex optimization problems. By introducing Halton sequences to initialize the population, the diversity of the population is enhanced, and premature convergence is effectively avoided. The dynamic density factor of water waves is added to improve the search efficiency of the algorithm in the solution space. Lens opposition learning based on the principle of lens imaging is also introduced to enhance the ability of the algorithm to get rid of local optimums. MIHBA achieves the best ranking in 23 test functions and 4 engineering design problems. The improvement of this paper improves the convergence speed and accuracy of the algorithm, enhances the adaptability and solving ability of the algorithm to complex functions, and provides new ideas for solving complex engineering design problems. Full article

In our interconnected society, prioritizing the resilience and sustainability of road infrastructure has never been more critical, especially in light of growing environmental and climatic challenges. By harnessing data from various sources, we can proactively enhance our ability to detect road damage. This approach will enable us to make well-informed decisions for timely maintenance and implement effective mitigation strategies, ultimately leading to safer and more durable road systems. This paper presents a new method for detecting road potholes during low-light conditions, particularly at night when influenced by street and traffic lighting. We examined and assessed various advanced machine learning and computer vision models, placing a strong emphasis on deep learning algorithms such as YOLO, as well as the combination of Grad-CAM++ with feature pyramid networks for feature extraction. Our approach utilized innovative data augmentation techniques, which enhanced the diversity and robustness of the training dataset, ultimately leading to significant improvements in model performance. The study results reveal that the proposed YOLOv11+FPN+Grad-CAM model achieved a mean average precision (mAP) score of 0.72 for the 50–95 IoU thresholds, outperforming other tested models, including YOLOv8 Medium with a score of 0.611. The proposed model also demonstrated notable improvements in key metrics, with mAP50 and mAP75 values of 0.88 and 0.791, reflecting enhancements of 1.5% and 5.7%, respectively, compared to YOLOv11. These results highlight the model’s superior performance in detecting potholes under low-light conditions. By leveraging a specialized dataset for nighttime scenarios, the approach offers significant advancements in hazard detection, paving the way for more effective and timely driver alerts and ultimately contributing to improved road safety. This paper makes several key contributions, including implementing advanced data augmentation methods and a thorough comparative analysis of various YOLO-based models. Future plans involve developing a real-time driver warning application, introducing enhanced evaluation metrics, and demonstrating the model’s adaptability in diverse environmental conditions, such as snow and rain. The contributions significantly advance the field of road maintenance and safety by offering a robust and scalable solution for pothole detection, particularly in developing countries. Full article

Student admission prediction is a crucial aspect of academic planning, offering insights into enrollment trends, resource allocation, and institutional growth. However, traditional methods often lack the ability to address fairness and transparency, leading to potential biases and inequities in the decision-making process. This paper explores the development and evaluation of machine learning models designed to predict student admissions while prioritizing fairness and interpretability. We employ a diverse set of algorithms, including Logistic Regression, Decision Trees, and ensemble methods, to forecast admission outcomes based on academic, demographic, and extracurricular features. Experimental results on real-world datasets highlight the effectiveness of the proposed models in achieving competitive predictive performance while adhering to fairness metrics such as demographic parity and equalized odds. Our findings demonstrate that machine learning can not only enhance the accuracy of admission predictions but also support equitable access to education by promoting transparency and accountability in automated systems. Full article

Microfluidic devices have revolutionized biosensing by enabling precise manipulation of minute fluid volumes across diverse applications. This review investigates the incorporation of machine learning (ML) into the design, fabrication, and application of microfluidic biosensors, emphasizing how ML algorithms enhance performance by improving design accuracy, operational efficiency, and the management of complex diagnostic datasets. Integrating microfluidics with ML has fostered intelligent systems capable of automating experimental workflows, enabling real-time data analysis, and supporting informed decision-making. Recent advances in health diagnostics, environmental monitoring, and synthetic biology driven by ML are critically examined. This review highlights the transformative potential of ML-enhanced microfluidic systems, offering insights into the future trajectory of this rapidly evolving field. Full article

To address the issues of slow convergence and large errors in existing metaheuristic algorithms when optimizing neural network-based subway passenger flow prediction, we propose the following improvements. First, we replace the random initialization method of the population in the SSA with Circle mapping to enhance its diversity and quality. Second, we introduce a hybrid mechanism combining dimensional small-hole imaging backward learning and Cauchy mutation, which improves the diversity of the individual sparrow selection of optimal positions and helps overcome the algorithm’s tendency to become trapped in local optima and premature convergence. Finally, we enhance the individual sparrow position update process by integrating a cosine strategy with an inertia weight adjustment, which improves the algorithm’s global search ability, effectively balancing global search and local exploitation, and reducing the risk of local optima and insufficient convergence precision. Based on the analysis of the correlation between different types of subway station passenger flows and weather factors, the ISSA is used to optimize the hyperparameters of the CNN-LSTM model to construct a subway passenger flow prediction model based on ISSA-CNN-LSTM. Simulation experiments were conducted using card swipe data from Harbin Metro Line 1. The results show that the ISSA provides a more accurate optimization with the average values and standard deviations of the 12 benchmark test function simulations being closer to the optimal values. The ISSA-CNN-LSTM model outperforms the SSA-CNN-LSTM, PSO-ELMAN, GA-BP, CNN-LSTM, and LSTM models in terms of error evaluation metrics such as MAE, RMSE, and MAPE, with improvements ranging from 189.8% to 374.6%, 190.9% to 389.5%, and 3.3% to 6.7%, respectively. Moreover, the ISSA-CNN-LSTM model exhibits the smallest variation in prediction errors across different types of subway stations. The ISSA demonstrates superior parameter optimization accuracy and convergence speed compared to the SSA. The ISSA-CNN-LSTM model is suitable for the precise prediction of passenger flow at different types of subway stations, providing theoretical and data support for subway station passenger density and trend forecasting, passenger organization and management, risk emergency response, and the improvement of service quality and operational safety. Full article

The emergence of Generative Artificial Intelligence (GenAI) raises critical questions about learner autonomy and agency. This exploratory case study examines how four university-level German language learners with diverse backgrounds developed autonomy in their learning process through engagement with AI tools. The study was conducted in early 2023 when most learners were first discovering ChatGPT’s potential for language learning. Data were collected through reflective journals, digital portfolios, and interviews during a semester-long course that scaffolded self-directed learning with AI integration. The findings reveal emerging patterns of shared agency between learners and AI tools. Learners developed distinct strategies for AI integration based on their language learning backgrounds, with heritage speakers focusing on accuracy improvement while classroom learners emphasized communication practice. Cross-case analyses identified key dimensions of autonomy development: a critical evaluation of AI output, evolving learner–AI relationships, maintaining and developing a second language (L2) voice, and the strategic integration of AI tools while preserving learner agency. These patterns suggest that autonomy in AI-mediated environments manifests through learners’ capacity to engage productively with AI while maintaining critical awareness and personal agency in their learning process. Full article

Background: Accurate and rapid detection of COVID-19 remains critical for clinical management, especially in resource-limited settings. Current diagnostic methods face challenges in terms of speed and reliability, creating a need for complementary AI-based models that integrate diverse data sources. Objectives: This study aimed to develop and evaluate a multi-modal machine learning model that combines clinical biomarkers and chest X-ray images to enhance diagnostic accuracy and provide interpretable insights. Methods: We used a dataset of 250 patients (180 COVID-19 positive and 70 negative cases) collected from clinical settings. Biomarkers such as CRP, ferritin, NLR, and albumin were included alongside chest X-ray images. Random Forest and Gradient Boosting models were used for biomarkers, and ResNet and VGG CNN architectures were applied to imaging data. A late-fusion strategy integrated predictions from these modalities. Stratified k-fold cross-validation ensured robust evaluation while preventing data leakage. Model performance was assessed using AUC-ROC, F1-score, Specificity, Negative Predictive Value (NPV), and Matthews Correlation Coefficient (MCC), with confidence intervals calculated via bootstrap resampling. Results: The Gradient Boosting + VGG fusion model achieved the highest performance, with an AUC-ROC of 0.94, F1-score of 0.93, Specificity of 93%, NPV of 96%, and MCC of 0.91. SHAP and LIME interpretability analyses identified CRP, ferritin, and specific lung regions as key contributors to predictions. Discussion: The proposed multi-modal approach significantly enhances diagnostic accuracy compared to single-modality models. Its interpretability aligns with clinical understanding, supporting its potential for real-world application. Full article

Combined Cycle Power Plants (CCPPs) generate electrical power through gas turbines and use the exhaust heat from those turbines to power steam turbines, resulting in 50% more power output compared to traditional simple cycle power plants. Predicting the full-load electrical power output ($P_E$) of a CCPP is crucial for efficient operation and sustainable development. Previous studies have used machine learning models, such as the Bagging and Boosting models to predict $P_E$. In this study, we propose employing Super Learner (SL), an ensemble machine learning algorithm, to enhance the accuracy and robustness of predictions. SL utilizes cross-validation to estimate the performance of diverse machine learning models and generates an optimal weighted average based on their respective predictions. It may provide information on the relative contributions of each base learner to the overall prediction skill. For constructing the SL, we consider six individual and ensemble machine learning models as base learners and assess their performances compared to the SL. The dataset used in this study was collected over six years from an operational CCPP. It contains one output variable and four input variables: ambient temperature, atmospheric pressure, relative humidity, and vacuum. The results show that the Boosting algorithms significantly influence the performance of the SL in comparison to the other base learners. The SL outperforms the six individual and ensemble machine learning models used as base learners. It indicates that the SL improves the generalization performance of predictions by combining the predictions of various machine learning models. Full article

The rapid growth of Internet of Things (IoT) devices has significantly increased reliance on sensor-generated data, which are essential to a wide range of systems and services. Wireless sensor networks (WSNs), crucial to this ecosystem, are often deployed in diverse and challenging environments, making them susceptible to faults such as software bugs, communication breakdowns, and hardware malfunctions. These issues can compromise data accuracy, stability, and reliability, ultimately jeopardizing system security. While advanced sensor fault detection methods in WSNs leverage a machine learning approach to achieve high accuracy, they typically rely on centralized learning, and face scalability and privacy challenges, especially when transferring large volumes of data. In our experimental setup, we employ a decentralized approach using federated learning with long short-term memory (FedLSTM) for sensor fault detection in WSNs, thereby preserving client privacy. This study utilizes temperature data enhanced with synthetic sensor data to simulate various common sensor faults: bias, drift, spike, erratic, stuck, and data-loss. We evaluate the performance of FedLSTM against the centralized approach based on accuracy, precision, sensitivity, and F1-score. Additionally, we analyze the impacts of varying the client participation rates and the number of local training epochs. In federated learning environments, comparative analysis with established models like the one-dimensional convolutional neural network and multilayer perceptron demonstrate the promising results of FedLSTM in maintaining client privacy while reducing communication overheads and the server load. Full article

Student gender differences in technology acceptance and use have persisted for years, giving rise to equity concerns in higher education (HE). To explore if such differences extend to generative artificial intelligence (genAI) chatbot use, we surveyed a large Norwegian HE student sample (n = 2692) using a fully mixed concurrent equal status design. Our findings show that men exhibit more frequent engagement with genAI chatbots across a broader spectrum of applications. Further, men demonstrate a heightened interest in genAI chatbots as tools and in their relevance to future career prospects. Women primarily utilize genAI chatbots in text-related tasks and express greater concerns regarding critical and independent thinking. Women also exhibit a stronger need to learn how to determine when it is wise to use and how to trust genAI chatbots. Consequences are discussed for the individual, society, and HE institutions in terms of social reproduction, diversity competence, and equitable teaching practices. Full article