Search Results (3,714)

Monitoring lake area changes with a higher spatial and temporal resolution can facilitate a more detailed analysis of climate-related changes in the Tibetan Plateau. In the Landsat era, optical remote sensing observation with water body index-based methods mainly contributed to alpine lake investigation. However, monitoring the seasonal or monthly change of a lake area is challenging since optical data are easily contaminated by the high cloud cover in the Tibetan Plateau. To cope with this, we generated new time series datasets including Sentinel-1 Synthetic Aperture Radar (SAR) and the Landsat-8 Operational Land Imager (OLI) observations. Meanwhile, we presented an improved deep learning model with spatial and channel attention mechanisms. Based on these datasets, we compared several deep learning models and found that the CloudNet+ had better performance. Taking this architecture as a baseline, we added spatial and channel attention mechanisms to generate our AttCloudNet+ for extracting the lake area. The results revealed that AttCloudNet+ had a better performance compared with the CloudNet+ and other CNNs (e.g., DeepLabv3+, UNet). For the accuracy of the lakeshore prediction, results from AttCloudNet+ demonstrated closer distance to the truth-value than other models. The obtained mean RMSE and MAE were 21.6 and 16.6 m, respectively. In contrast, the mean RMSE and MAE of the DeepLabv3+ were 99.5 and 76.0 m, while the corresponding RMSE and MAE for UNet were 91.1 and 64.9 m. In addition, we found our AttCloudNet+ was more robust than UNet and DeepLabv3+ because AttCloudNet+ is less influenced by the input optical images compared with DeepLabv3+ and UNet. By combining the results from different seasons and satellite sensors, we are capable of generating the complete lake area seasonal dynamics of the 15 largest lakes. The mean correlation coefficient (R²) between our seasonal lake area time series and the water level of LEGOS is 0.81, which is much better than the previous study (0.25). This indicates that our method can be used to monitor lake area seasonal variation, which is important for understanding regional climate change in the Tibetan Plateau and other similar areas. Full article

Time series forecasting, particularly within the Internet of Things (IoT) and hydrological domains, plays a critical role in predicting future events based on historical data, which is essential for strategic decision making. Effective flood forecasting is pivotal for optimal water resource management and for mitigating the adverse impacts of flood events. While deep learning methods have demonstrated exceptional performance in time series prediction through advanced feature extraction and pattern recognition, they encounter significant limitations when applied to scenarios with sparse data, especially in flood forecasting. The scarcity of historical data can severely hinder the generalization capabilities of traditional deep learning models, presenting a notable challenge in practical flood prediction applications. To address this issue, we introduce MetaTrans-FSTSF, a pioneering meta-learning framework that redefines few-shot time series forecasting. By innovatively integrating MAML and Transformer architectures, our framework provides a specialized solution tailored for the unique challenges of flood prediction, including data scarcity and complex temporal patterns. This framework goes beyond standard implementations, delivering significant improvements in predictive accuracy and adaptability. Our approach leverages Model-Agnostic Meta-Learning (MAML) to enable rapid adaptation to new forecasting tasks with minimal historical data. Our inner architecture is a Transformer-based meta-predictor capable of capturing intricate temporal dependencies inherent in flood time series data. Our framework was evaluated using diverse datasets, including a real-world hydrological dataset from a small catchment area in Wuyuan, China, and other benchmark time series datasets. These datasets were preprocessed to align with the meta-learning approach, ensuring their suitability for tasks with limited data availability. Through extensive evaluation, we demonstrate that MetaTrans-FSTSF substantially improves predictive accuracy, achieving a reduction of up to 16%, 19%, and 8% in MAE compared to state-of-the-art methods. This study highlights the efficacy of meta-learning techniques in overcoming the limitations posed by data scarcity and enhancing flood forecasting accuracy where historical data are limited. Full article

Air pollution in Jakarta, one of the most polluted cities globally, has reached critical levels, with PM_2.5 concentrations exceeding the WHO guidelines and posing significant health risks. Accurate forecasting of PM_2.5 is crucial for effective air quality management and public health interventions. PM_2.5 exhibits significant nonlinear fluctuations; thus, this study employed two machine learning approaches: self-exciting threshold autoregressive tree (SETAR-Tree) and long short-term memory (LSTM). The SETAR-Tree model integrates regime-switching capabilities with decision tree principles to capture nonlinear patterns, while LSTM models long-term dependencies in time-series data. The results showed that: (1) SETAR-Tree outperformed LSTM, achieving lower RMSE (0.1691 in-sample, 0.2159 out-sample) and MAPE (2.83% in-sample, 2.98% out-sample) compared to LSTM’s RMSE (0.2038 in-sample, 0.2399 out-sample) and MAPE (3.48% in-sample, 4.05% out-sample); (2) SETAR-Tree demonstrated better responsiveness to sudden regime changes, capturing complex pollution patterns influenced by meteorological and anthropogenic factors; (3) PM_2.5 in Jakarta often exceeds the WHO limits, highlighting this study’s importance in supporting strategic planning and providing an early warning system to reduce outdoor activity during extreme pollution. Full article

Electroretinograms (ERGs) show differences between typically developing populations and those with a diagnosis of autism spectrum disorder (ASD) or attention deficit/hyperactivity disorder (ADHD). In a series of ERGs collected in ASD (n = 77), ADHD (n = 43), ASD + ADHD (n = 21), and control (n = 137) groups, this analysis explores the use of machine learning and feature selection techniques to improve the classification between these clinically defined groups. Standard time domain and signal analysis features were evaluated in different machine learning models. For ASD classification, a balanced accuracy (BA) of 0.87 was achieved for male participants. For ADHD, a BA of 0.84 was achieved for female participants. When a three-group model (ASD, ADHD, and control) the BA was lower, at 0.70, and fell further to 0.53 when all groups were included (ASD, ADHD, ASD + ADHD, and control). The findings support a role for the ERG in establishing a broad two-group classification of ASD or ADHD, but the model’s performance depends upon sex and is limited when multiple classes are included in machine learning modeling. Full article

The time series of agricultural prices exhibit brevity and considerable volatility. Considering that traditional time series models and machine learning models are facing challenges in making predictions with high accuracy and robustness, this paper proposes a Light gradient boosting machine model based on the boosting ensemble learning algorithm to predict prices for three representative types of fresh agricultural products (bananas, beef, crucian carp). The prediction performance of the Light gradient boosting machine model is evaluated by comparing it against multiple benchmark models (ARIMA, decision tree, random forest, support vector machine, XGBoost, and artificial neural network) in terms of accuracy, generalizability, and robustness on different datasets and under different time windows. Among these models, the Light gradient boosting machine model is shown to have the highest prediction accuracy and the most stable performance across three different datasets under both long-term and short-term time windows. As the time window length increases, the Light gradient boosting machine model becomes more advantageous for effectively reducing error fluctuation, demonstrating better robustness. Consequently, the model proposed in this paper holds significant potential for forecasting fresh agricultural product prices, thereby facilitating the advancement of precision and sustainable farming practices. Full article

Frequent algal blooms in lakes pose a serious threat to aquatic ecosystems. It is of great significance to quickly and accurately monitor the distribution of algae in lakes for the regulation of algal blooms. While remote sensing techniques and machine learning methods can be used in combination to identify algae and analyze their spatial and temporal distribution, these methods still face challenges in practical applications due to uncertainties in lake boundaries and imbalances between algae and non-algae. In order to overcome these difficulties, we studied the dynamic open water range of Ulansuhai Lake and used a non-equilibrium data processing method to identify its algae. We also performed a spatiotemporal analysis of the algal range over a long time series. The results show that (1) the spectral characteristics of Landsat 8 images are very suitable for algal identification based on remote sensing, especially in the random forest method, where the fourth band plays an important role. (2) Among various machine learning methods, the accuracy of the random forest method on the training set and validation set is more than 90%. This indicates that the random forest method is suitable for the long-term monitoring of algal blooms. This study provides scientific and technical support for the management of Ulansuhai Lake, which will be helpful in guiding future management and control work. Full article

We investigate the application of deep learning in comparing gait cycle time series from two groups of healthy children, each assessed in different gait laboratories. Both laboratories used similar gait analysis protocols with minimal differences in data collection. Utilizing a ResNet-based deep learning model, we successfully identified the source laboratory of each dataset, achieving a high classification accuracy across multiple gait parameters. To address the inter-laboratory differences, we explored various pre-processing methods and time series properties that may have been detected by the algorithm. We found that the standardization of the time series values was a successful approach to decrease the ability of the model to distinguish between the two centers. Our findings also reveal that differences in the power spectra and autocorrelation structures of the datasets play a significant role in the model performance. Our study emphasizes the importance of standardized protocols and robust data pre-processing to enhance the transferability of machine learning models across clinical settings, particularly for deep learning approaches. Full article

With the expansion of microservice-based applications over time, the number of microservices rises, resulting in an augmentation of the volume of performance metrics. Consequently, selecting the appropriate performance metrics for anomaly detection becomes a critical challenge. Since these performance metrics are typically strongly correlated with timestamps, they form time series data comprising timestamp–value pairs. To address this, we propose SRdetector, a feature-enhanced Transformer-based model that adopts a time series forecasting approach to detect anomalies in microservices. Furthermore, we integrate a dynamic weight adjustment mechanism into the original Transformer attention mechanism to assign weights to different performance and temporal features. This enables the model to dynamically learn the significance of various features at different time intervals, effectively serving as a feature selection method for microservice performance metrics. Finally, anomaly detection in microservices is conducted by evaluating the predicted performance metric data based on confidence intervals. Full article

Water quality plays a pivotal role in human health and environmental sustainability. However, traditional water quality prediction models are limited by high model complexity and long computation time, whereas AI models often struggle with high-dimensional time series and lack physical interpretability. This paper proposes a two-dimensional water quality surrogate model that couples physical numerical models and AI. The model employs physical simulation results as input, applies spectral proper orthogonal decomposition to reduce the dimensionality of the simulation results, utilizes a long short-term memory neural network for matrix forecasting, and reconstructs the two-dimensional concentration field. The simulation and predictive performance of the surrogate model were systematically evaluated through four design scenarios and three sampling dataset lengths, with a particular focus on the convection–diffusion zone and high-concentration zone. The results indicated that the model achieves high prediction accuracy for up to 7 h into the future, with sampling dataset lengths ranging from 20 to 80 h. Specifically, the model achieved an average R² of 0.92, a MAE of 0.38, and a MAPE of 1.77%, demonstrating its suitability for short-term water quality predictions. The methodology and findings of this study demonstrate the significant potential of integrating spectral proper orthogonal decomposition and deep learning for water quality prediction. By overcoming the limitations of traditional models, the proposed surrogate model provides high-accuracy predictions with enhanced physical interpretability, even in complex, dynamic environments. This work offers a practical tool for rapid responses to water pollution incidents and supports improved watershed water quality management by effectively capturing pollutant diffusion dynamics. Furthermore, the model’s scalability and adaptability make it a valuable resource for addressing intelligent management in environmental science. Full article

Accurate and timely air quality forecasting is crucial for mitigating pollution-related hazards and protecting public health. Recently, there has been a growing interest in integrating visual data for air quality prediction. However, some limitations remain in existing literature, such as their focus on coarse-grained classification, single-moment estimation, or reliance on indirect and unintuitive information from visual images. Here we present a dual-channel deep learning model, integrating surveillance images and multi-source numerical data for air quality forecasting. Our model, which combines a single-channel hybrid network consisting of VGG16 and LSTM (named VGG16-LSTM) with a single-channel Long Short-Term Memory (LSTM) network, efficiently captures detailed spatiotemporal features from surveillance image sequences and temporal features from atmospheric, meteorological, and temporal data, enabling accurate time-series forecasting of PM_2.5 and PM₁₀ concentrations. Experiments conducted on the 2021 Shanghai dataset demonstrate that the proposed model significantly outperforms traditional machine learning methods in terms of accuracy and robustness for time-series forecasting, achieving R² values of 0.9459 and 0.9045 and RMSE values of 4.79 μg/m³ and 11.51 μg/m³ for PM_2.5 and PM₁₀, respectively. Furthermore, validation results on the datasets from two stations in Kaohsiung, Taiwan, with average R² values of 0.9728 and 0.9365 and average RMSE values of 1.89 μg/m³ and 5.69 μg/m³ for PM_2.5 and PM₁₀ using a pretrain–finetune training strategy, confirm the model’s adaptability across diverse geographical contexts. These findings highlight the potential of integrating surveillance images to enhance air quality prediction, offering an effective supplement to ground-level environmental monitoring. Future work will focus on expanding datasets and optimizing network architectures to further improve forecasting accuracy and computational efficiency, enhancing the model’s scalability for broader regional air quality management. Full article

Neuroblastoma is a common malignant tumor in childhood that seriously endangers the health and lives of children, making it essential to find effective prognostic markers to accurately predict their clinical outcomes. The development of high-throughput technology in the biomedical field has made it possible to obtain multi-omics data, whose integration can compensate for missing or unreliable information in a single data source. In this study, we integrated clinical data and two omics data, i.e., gene expression and DNA methylation data, to study the prognosis of neuroblastoma. Since the features in omics data are redundant, it is crucial to conduct feature selection on them. We proposed a two-step feature selection (TSFS) method to quickly and accurately select the optimal features, where the first step aims at selecting candidate features and the second step is to remove redundant features among them using our proposed maximal association coefficient (MAC). Our goal is to predict composite clinical outcomes for neuroblastoma patients, i.e., their survival time and vital status at the last follow-up, which was validated to be two inter-correlated tasks. We conducted a series of experiments and evaluated the experimental results using accuracy and AUC (area under the ROC curve) evaluation metrics, which indicated that by the combination of the integration of the three types of data, our proposed TSFS method and a multi-task learning method can synergistically improve the reliability and accuracy of the prediction models. Full article

Due to the limited availability of high-quality optical images during the rice growth period in the Lingnan region of China, effectively monitoring the rice planting situation has been a challenge. In this study, we utilized multi-temporal Sentinel-1 data to develop a method for rapidly extracting the range of rice fields using a threshold segmentation approach and employed a U-Net deep learning model to delineate the distribution of rice fields. Spatio-temporal changes in rice distribution in Leizhou City, Guangdong Province, China, from 2017 to 2021 were analyzed. The results revealed that by analyzing SAR-intensive time series data, we were able to determine the backscattering coefficient of typical crops in Leizhou and use the threshold segmentation method to identify rice labels in SAR-intensive time series images. Furthermore, we extracted the distribution range of early and late rice in Leizhou City from 2017 to 2021 using a U-Net model with a minimum relative error accuracy of 3.56%. Our analysis indicated an increasing trend in both overall rice planting area and early rice planting area, accounting for 44.74% of early rice and over 50% of late rice planting area in 2021. Double-cropping rice cultivation was predominantly concentrated in the Nandu River basin, while single-cropping areas were primarily distributed along rivers and irrigation facilities. Examination of the traditional double-cropping areas in Fucheng Town from 2017 to 2021 demonstrated that over 86.94% had at least one instance of double cropping while more than 74% had at least four instances, which suggested that there is high continuity and stability within the pattern of rice cultivation practices observed throughout Leizhou City. Full article

This paper presents an integrated robotic trading strategy developed for the day-ahead energy market that includes different methods for time series analysis and forecasting, such as Detrended Fluctuation Analysis (DFA), Rescaled Range Analysis (R/S analysis), fractional derivatives, Long Short-Term Memory (LSTM) Networks, and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. DFA and R/S analysis may capture the long-range dependencies and fractal features inherited by the nature of the electricity price time series and give information about persistence and variability in their behavior. Given this, fractional derivatives can be used to analyze price movements concerning the minor changes in price and time acceleration for that change, which makes the proposed framework more flexible for quickly changing market conditions. LSTM, from their perspective, may capture complex and non-linear dependencies, while SARIMA models may help handle seasonal trends. This integrated approach improves market signal interpretation and optimizes the market risk through adjustable stop-loss and take-profit levels which could lead to better portfolio performance. The proposed integrated strategy is based on actual data from the Bulgarian electricity market for the years 2017–2024. Findings from this research show how the combination of fractals with statistical and machine learning models can improve complex trading strategies implementation for the energy markets. Full article

This paper presents an analysis of stock price forecasting in the financial market, with an emphasis on approaches based on time series models and deep learning techniques. Fundamental concepts of technical analysis are explored, such as exponential and simple averages, and various global indices are analyzed to be used as inputs for machine learning models, including Recurrent Neural Network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), and XGBoost. The results show that while each model possesses distinct characteristics, selecting the most efficient approach heavily depends on the specific data and forecasting objectives. The complexity of advanced models such as XGBoost and GRU is reflected in their overall performance, suggesting that they can be particularly effective at capturing patterns and making accurate predictions in more complex time series, such as stock prices. Full article

Integrating Machine Learning (ML) in industrial settings has become a cornerstone of Industry 4.0, aiming to enhance production system reliability and efficiency through Real-Time Fault Detection and Diagnosis (RT-FDD). This paper conducts a comprehensive literature review of ML-based RT-FDD. Out of 805 documents, 29 studies were identified as noteworthy for presenting innovative methods that address the complexities and challenges associated with fault detection. While ML-based RT-FDD offers different benefits, including fault prediction accuracy, it faces challenges in data quality, model interpretability, and integration complexities. This review identifies a gap in industrial implementation outcomes that opens new research opportunities. Future Fault Detection and Diagnosis (FDD) research may prioritize standardized datasets to ensure reproducibility and facilitate comparative evaluations. Furthermore, there is a pressing need to refine techniques for handling unbalanced datasets and improving feature extraction for temporal series data. Implementing Explainable Artificial Intelligence (AI) (XAI) tailored to industrial fault detection is imperative for enhancing interpretability and trustworthiness. Subsequent studies must emphasize comprehensive comparative evaluations, reducing reliance on specialized expertise, documenting real-world outcomes, addressing data challenges, and bolstering real-time capabilities and integration. By addressing these avenues, the field can propel the advancement of ML-based RT-FDD methodologies, ensuring their effectiveness and relevance in industrial contexts. Full article