Search Results (35)

Forecasting outcomes in high-stakes competitive spectacles like the Olympic Games, World Cups, and professional league championships has grown increasingly vital, directly impacting strategic planning, resource allocation, and performance optimization across a multitude of fields. However, accurate forecasting remains challenging due to complex, nonlinear interactions inherent in high-dimensional time-series data, further complicated by socioeconomic indicators, historical influences, and host-country advantages. In this study, we propose a comprehensive forecasting framework integrating structured time-series modeling with ensemble learning. We extract key structural features via two novel indices: the Advantage Index (measuring a competitor’s dominance in specific areas) and the Herfindahl Index (quantifying performance outcome concentration). We also evaluate host-country advantage using a Difference-in-Differences (DiD) approach. Leveraging these insights, we develop a dual-branch predictive model combining an Attention-augmented Long Short-Term Memory (Attention-LSTM) network and a Random Forest classifier. Attention-LSTM captures long-term dependencies and dynamic patterns in structured temporal data, while Random Forest handles predictions for unrecognized contenders, addressing zero-inflation issues. Extensive stability and comparative analyses demonstrate that our model outperforms traditional and state-of-the-art methods, exhibiting strong resilience to input perturbations, consistent performance across multiple runs, and appropriate sensitivity to key features. Our key contributions include the development of a novel integrated forecasting framework, the introduction of two innovative structural indices for competitive dynamics analysis, and the demonstration of robust predictive performance that bridges technical innovation with practical strategic application. Finally, we transform our modeling insights into actionable strategic insights. This translation is powered by interpretable feature importance rankings and stability analysis that rigorously validate the robustness of key predictors. These insights apply across multiple dimensions—encompassing advantage assessment, resource distribution, strategic simulation, and breakthrough potential identification—providing comprehensive decision support for strategic planners and policymakers navigating competitive environments. Full article

Accurate prediction of river runoff is significant for flood control, water resource allocation, and basin ecological management. Despite the promise of integrating signal decomposition with deep learning, current decomposition-based hybrid models face critical forward data contamination: decomposition algorithms improperly access future test data in full-series applications, artificially inflating prediction accuracy. In contrast, the stepwise decomposition method currently proposed leads to high computational costs. To address this limitation, we introduce a novel framework integrating segmented decomposition sampling with a multi-input neural network. Specifically, a hybrid forecasting model combining Seasonal-Trend decomposition using Loess (STL) and Convolutional Long Short-Term Memory (CNN-LSTM) networks was implemented for daily runoff estimation. Method reliability was evaluated using historical runoff data from Huaxian Station in China’s Weihe River Basin, with comparative experiments conducted against established single and hybrid models. The results showed that the proposed framework can effectively avoid future information leakage and simultaneously improve prediction accuracy. For 1–3-day-ahead Nash-Sutcliffe efficiency (NSE) at Huaxian Station, the STL-CNN-LSTM model achieved values of 0.96, 0.83, and 0.80, respectively—representing improvements of 5.49%, 5.06%, and 12.68% over the VMD-CNN-LSTM model. This STL-based configuration outperformed the standalone LSTM counterpart by 23.08%, 9.21%, and 17.65% in NSE, respectively. Therefore, the proposed framework, which incorporates the segmented decomposition sampling method and a multi-input neural network, proves to be both practical and reliable. Full article

Action recognition actions in video are sophisticated processes that demand more and more explicitly captured spatial and temporal information. This paper gives a comparison of several advanced techniques for action recognition using the UCF101 dataset. We look at two-stream convolutional networks, 3D convolutional networks, long short-term memory networks, two-stream inflated 3D convolutional networks, attention mechanisms, and hybrid models. Their methods have been examined for each of the proposed options along with their architectures, as well as their pros and cons. The results of our experiments have revealed the performance of these approaches on the UCF101 dataset, including a focus on the tradeoffs between computational efficiency, data requirements, and recognition accuracy. Full article

This study introduces a novel approach for analyzing the dynamic interplay among key economic indicators by employing a Caputo Fractional Fisher Information framework combined with partial information decomposition. By integrating fractional derivatives into traditional Fisher Information metrics, our methodology captures long-range memory effects that govern the evolution of monetary policy, credit risk, market volatility, and inflation, represented by INTEREST, CDS, VIX, CPI, and PPI, respectively. We perform a comprehensive comparative analysis using rolling-window estimates to generate Caputo Fractional Fisher Information values at different fractional orders alongside the memoryless Ordinary Fisher Information. Subsequent correlation, cross-correlation, and transfer entropy analyses reveal how historical dependencies influence both unique and synergistic information flows between indices. Notably, our partial information decomposition results demonstrate that deep historical interactions significantly amplify the informational contribution of each indicator, particularly under long-memory conditions, while the Ordinary Fisher Information framework tends to underestimate these synergistic effects. The findings underscore the importance of incorporating memory effects into information-theoretic models to better understand the intricate, time-dependent relationships among financial indicators, with significant implications for forecasting and policy analysis. Full article

Wheat is one of the most essential food crops globally, but diseases significantly threaten its yield and quality, resulting in considerable economic losses. The identification of wheat diseases faces challenges, such as interference from complex environments in the field, the inefficiency of traditional machine learning methods, and difficulty in deploying the existing deep learning models. To address these challenges, this study proposes a multi-scale feature fusion shuffle network model (MFFSNet) for wheat disease identification from complex environments in the field. MFFSNet incorporates a multi-scale feature extraction and fusion module (MFEF), utilizing inflated convolution to efficiently capture diverse features, and its main constituent units are improved by ShuffleNetV2 units. A dual-branch shuffle attention mechanism (DSA) is also integrated to enhance the model’s focus on critical features, reducing interference from complex backgrounds. The model is characterized by its smaller size and fast operation speed. The experimental results demonstrate that the proposed DSA attention mechanism outperforms the best-performing Squeeze-and-Excitation (SE) block by approximately 1% in accuracy, with the final model achieving 97.38% accuracy and 97.96% recall on the test set, which are higher than classical models such as GoogleNet, MobileNetV3, and Swin Transformer. In addition, the number of parameters of this model is only 0.45 M, one-third that of MobileNetV3 Small, which is very suitable for deploying on devices with limited memory resources, demonstrating great potential for practical applications in agricultural production. Full article

In semiconductor manufacturing, the final testing phase is critical for ensuring chip quality and operational efficiency. Accurate yield prediction at this stage optimizes testing workflows, boosts production efficiency, and enhances quality control. However, existing research primarily focuses on wafer-level yield prediction, leaving the unique challenges of final testing—such as test condition variability and complex failure patterns—insufficiently addressed. This is especially critical for Radio Frequency Front-End (RFFE) chips, where high precision is essential, highlighting the need for a specialized prediction approach. In our study, a rigorous RF correlation parameter selection process was applied, leveraging metrics such as Spearman’s correlation coefficient and variance inflation factors to identify key RF-related features, such as multiple frequency-point PAE measurements and other critical electrical parameters, that directly influence final test yield. To overcome the limitations of traditional methods, this study proposes a multistrategy dynamic weighted fusion model for yield prediction. The proposed approach combines convolutional neural networks (CNNs) and long short-term memory (LSTM) networks with sliding window averaging to capture both local features and long-term dependencies in RFFE test data, while employing a learnable weighting mechanism to dynamically fuse outputs from multiple submodels for enhanced prediction accuracy. It further incorporates incremental training to adapt to shifting production conditions and utilizes principal component analysis (PCA) in data preprocessing to reduce dimensionality and address multicollinearity. Evaluated on a dataset of over 24 million RFFE chips, the proposed model achieved a Mean Absolute Error (MAE) below 0.84% and a Root Mean Square Error (RMSE) of 1.24%, outperforming single models by reducing MAE and RMSE by 7.69% and 13.29%, respectively. These results demonstrate the high accuracy and adaptability of the fusion model in predicting semiconductor final test yield. Full article

The accurate prediction of PM_2.5 concentration across extensive temporal and spatial scales is essential for air pollution control and safeguarding public health. To address the challenges of the uneven coverage and limited number of traditional PM_2.5 ground monitoring networks, the low inversion accuracy of PM_2.5 concentration, and the incomplete understanding of its spatiotemporal dynamics, this study proposes a refined PM_2.5 concentration estimation model, Bi-LSTM-SA, integrating multi-source remote sensing data. First, utilizing multi-source remote sensing data, such as MODIS aerosol optical depth (AOD) products, meteorological data, and PM_2.5 monitoring sites, AERONET AOD was used to validate the accuracy of the MODIS AOD data. Variables including temperature (TEMP), relative humidity (RH), surface pressure (SP), wind speed (WS), and total precipitation (PRE) were selected, followed by the application of the variance inflation factor (VIF) and Pearson’s correlation coefficient (R) for variable screening. Second, to effectively capture temporal dependencies and emphasize key features, an improved Long Short-Term Memory Network (LSTM) model, Bi-LSTM-SA, was constructed by combining a bidirectional LSTM (Bi-LSTM) model with a self-adaptive attention mechanism (SA). This model was evaluated through ablation and comparative experiments using three cross-validation methods: sample-based, temporal, and spatial. The effectiveness of this method was demonstrated on Beijing–Tianjin–Hebei urban agglomeration, achieving a coefficient of determination (R²) of 0.89, root mean squared error (RMSE) of 12.76 μg/m³, and mean absolute error (MAE) of 8.27 μg/m³. Finally, this model was applied to predict PM_2.5 concentration on Beijing–Tianjin–Hebei urban agglomeration in 2023, revealing the characteristics of its spatiotemporal evolution. Additionally, the results indicated that this model performs exceptionally well in hourly PM_2.5 concentration forecasting and can be used for PM_2.5 concentration hourly prediction tasks. This study provides technical support for the large-scale, accurate remote sensing inversion of PM_2.5 concentration and offers fundamental insights for regional atmospheric environmental protection. Full article

Human CMV, regularly reactivated by simple triggers, results in asymptomatic viral shedding, powerful cellular immune responses, and memory inflation. Immunocompetent individuals benefit from a robust immune response, which aids in viral management without causing clinically significant illness; however, immunodeficient individuals are always at a higher risk of CMV reactivation and disease. Hematopoietic stem cell transplant (HSCT) recipients are consistently at higher risk of CMV reactivation and clinically significant CMV illness due to primary disease, immunosuppression, and graft vs. host disease. Early recovery of CMV-CMI responses may mitigate effects of viral reactivation in HSCT recipients. Immune reconstitution following transplantation occurs spontaneously and is mediated initially by donor-derived T cells, followed by clonal growth of T cells produced from graft progenitors. CMV-specific immune reconstitution post-transplant is related to spontaneous clearance of CMV reactivation and may eliminate the need for prophylactic or pre-emptive medication, making it a potential predictive marker for monitoring CMV reactivation. This review highlights current thoughts and therapeutic options for CMV reactivation in HSCT, with focus on CMV immune reconstitution and post-HSCT monitoring. Immune monitoring aids in risk stratification of transplant recipients who may progress from CMV reactivation to clinically significant CMV infection. Implementing this approach in clinical practice reduces the need for periodic viral surveillance and antiviral therapy in recipients who have a high CMV-CMI and thus may experience self-limited reactivation. Therefore, in the age of precision medicine, it is critical to incorporate CMV-specific cellular immune surveillance into conventional procedures and algorithms for the management of transplant recipients. Full article

An online social media platform such as Instagram has become a popular communication channel that millions of people are using today. However, this media also becomes an avenue where fake accounts are used to inflate the number of followers on a targeted account. Fake accounts tend to alter the concepts of popularity and influence on the Instagram media platform and significantly impact the economy, politics, and society, which is considered cybercrime. This paper proposes a framework to classify fake and real accounts on Instagram based on a deep learning approach called the Long Short-Term Memory (LSTM) network. Experiments and comparisons with existing machine and deep learning frameworks demonstrate considerable improvement in the proposed framework. It achieved a detection accuracy of 97.42% and 94.21% on two publicly available Instagram datasets, with F-measure scores of 92.17% and 89.55%, respectively. Further experiments on the Twitter dataset reveal the effectiveness of the proposed framework by achieving an impressive accuracy rate of 99.42%. Full article

This study confirms gold’s role as a reliable inflation hedge while introducing new insights into lesser-explored assets like art and wheat. Using advanced methodologies such as the ARDL framework and LSTM deep learning, it conducts a detailed analysis of inflation-hedging dynamics, exploring non-linear relationships and unexpected inflation impacts across various asset classes. The findings reveal complex dynamics. Gold demonstrates strong long-term inflation hedging potential. The negative coefficient for the US dollar index suggests that gold acts as a hedge against currency depreciation. Furthermore, a positive relationship between gold returns and inflation during high inflation periods highlights its effectiveness in protecting purchasing power. Art presents a more intricate picture. Long-term analysis suggests a weak mean-reverting tendency, but a negative relationship with inflation, potentially linked to economic downturns. Interestingly, unexpected inflation positively correlates with art returns in the long run, hinting at its potential inflation-hedging abilities. No statistically significant connection between wheat prices and overall inflation was observed; the short-run analysis reveals a dynamic interplay between inflation, real GDP growth, and wheat prices at different time points. Full article

This study is aimed at assessing the feasibility of employing an innovative, smart-material-based control effector for an inflatable wing. A shape memory alloy (SMA) actuator is primarily investigated as a control effector in this work for its advantages of a simple actuation mechanism and a high force-to-weight ratio. This paper presents the design, control strategy and simulation results of the SMA actuator used as a stability augmentation system for a small-scale prototype kite. Stable flight of the kite is achieved during open wind tunnel tests using the SMA actuator. Based on experimental and simulation analyses, it is evident that the current SMA actuator is better for low-frequency actuations rather than stability augmentation purposes, as its performance is sensitive to practical conditions. The study also discusses potential improvements and applications of the SMA actuator. Full article

Infection with cytomegalovirus (CMV) is highly prevalent in the general population and largely controlled by CD8^pos T cells. Intriguingly, anti-CMV T cells accumulate over time to extraordinarily high numbers, are frequently present as tumor-resident ‘bystander’ T cells, and remain functional in cancer patients. Consequently, various strategies for redirecting anti-CMV CD8^pos T cells to eliminate cancer cells are currently being developed. Here, we provide an overview of these strategies including immunogenic CMV peptide-loading onto endogenous HLA complexes on cancer cells and the use of tumor-directed fusion proteins containing a preassembled CMV peptide/HLA-I complex. Additionally, we discuss conveying the advantageous characteristics of anti-CMV T cells in adoptive cell therapy. Utilization of anti-CMV CD8^pos T cells to generate CAR T cells promotes their in vivo persistence and expansion due to appropriate co-stimulation through the endogenous (CMV-)TCR signaling complex. Designing TCR-engineered T cells is more challenging, as the artificial and endogenous TCR compete for expression. Moreover, the use of expanded/reactivated anti-CMV T cells to target CMV peptide-expressing glioblastomas is discussed. This review highlights the most important findings and compares the benefits, disadvantages, and challenges of each strategy. Finally, we discuss how anti-CMV T cell therapies can be further improved to enhance treatment efficacy. Full article

This paper deals with the analysis of the persistence in the Harmonized Indices of Consumer Prices in France, Germany, Italy, and Spain. The degree of persistence is measured through fractional integration or I (d) techniques, using monthly data from January 2010 to February 2023. We first conducted the analysis with data ending in December 2019, that is, with data prior to the COVID-19 pandemic. Then, we extended the sample, first up to December 2021 and finally to February 2023. Our results show that the findings of our series are highly persistent, with values of the differencing parameter about one or higher than one in the majority of cases. In fact, mean reversion is only observed in the case of Germany with pre-pandemic data. Generally, we observed an increase in the degree of persistence of the series as a consequence of both the COVID-19 pandemic and the Russia–Ukraine war, with the only exception being Spain, where we observe a reduction in the order of integration when including 2022–2023 data. Full article

Groundwater is the most abundant freshwater resource. Agriculture, industrialization, and domestic water supplies rely on it. The depletion of groundwater leads to drought. Topographic elevation, aquifer properties, and geomorphology influence groundwater quality. As the groundwater level data (GWL) are time series in nature, it is challenging to determine appropriate metrics and to evaluate groundwater levels accurately with less information loss. An effort has been made to forecast groundwater levels in India by developing a deep ensemble learning approach using a double-edge bi-directed long-short-term-memory (DEBi-LSTM) model approximated with a randomized low-ranked approximation algorithm (RLRA) and the variance inflation factor (VIF) to reduce information loss and to preserve data consistency. With minimal computation time, the model outperformed existing state-of-the-art models with $96.1\%$ accuracy. To ensure sustainable groundwater development, the proposed work is discussed in terms of its managerial implications. By applying the model, we can identify safe, critical, and semi-critical groundwater levels in Indian states so that strategic plans can be developed. Full article

The 1988 Yellowstone fire altered the structure of the local forest ecosystem and left large non-recovery areas. This study assessed the pre-fire drivers and post-fire characteristics of the recovery and non-recovery areas and examined possible reasons driving non-recovery of the areas post-fire disturbance. Non-recovery and recovery areas were sampled with 44,629 points and 77,501 points, from which attribute values related to topography, climate, and subsequent soil conditions were extracted. We calculated the 1988 Yellowstone fire burn thresholds using the differenced Normalized Burn Ratio (dNBR) and official fire maps. We used a burn severity map from the US Forest Service to calculate the burn severity values. Spatial regressions and Chi-Square tests were applied to determine the statistically significant characteristics of a lack of recovery. The non-recovery areas were found to cover 1005.25 km². Among 11 variables considered as potential factors driving recovery areas and 13 variables driving non-recovery areas, elevation and maximum temperature were found to have high Variance Inflation Factors (4.73 and 4.72). The results showed that non-recovery areas all experienced severe burns and were located at areas with steeper slopes (13.99°), more precipitation (871.73 mm), higher pre-fire vegetation density (NDVI = 0.38), higher bulk density (750.03 kg/m³), lower soil organic matter (165.61 g/kg), and lower total nitrogen (60.97 mg/L). Chi-square analyses revealed statistically different pre-fire forest species (p < 0.01) and soil order (p < 0.01) in the recovery and non-recovery areas. Although Inceptisols dominated in both recovery and non-recovery areas, however, the composition of Mollisols was higher in the non-recovery areas (14%) compared to the recovery areas (11%). This indicated the ecological memory of the non-recovery site reverting to grassland post-disturbance. Unlike conventional studies only focusing on recovery areas, this study analyzed the non-recovery areas and found the key characteristics that make a landscape not resilient to the 1988 Yellowstone fire. The significant effects of elevation, precipitation, and soil pH on recovery may be significant to the forest management and forest resilience in the post-fire period. Full article