A5102769483- Stock Market Forecasting Methods
- Fault Detection and Control Systems
- Statistical Methods and Inference
- Market Dynamics and Volatility
- Financial Markets and Investment Strategies
- Reliability and Maintenance Optimization
- Machine Fault Diagnosis Techniques
- Economic and Environmental Valuation
- Emotion and Mood Recognition
- Advanced Measurement and Metrology Techniques
- Building Energy and Comfort Optimization
- Financial Risk and Volatility Modeling
- Anomaly Detection Techniques and Applications
- Probabilistic and Robust Engineering Design
- Advanced Statistical Methods and Models
- EEG and Brain-Computer Interfaces
- Gaze Tracking and Assistive Technology
- Oxidative Organic Chemistry Reactions
- Income, Poverty, and Inequality
- Statistical Methods and Bayesian Inference
- Technology Assessment and Management
- Musculoskeletal pain and rehabilitation
- Pain Mechanisms and Treatments
- Fiscal Policy and Economic Growth
- Urban Transport and Accessibility
Wuchang University of Technology
2025
Wuhan No.1 Hospital
2025
University of Chinese Academy of Sciences
2023-2024
Technology and Engineering Center for Space Utilization
2018-2024
Chinese Academy of Sciences
2018-2024
Weifang Medical University
2024
Xinjiang University
2024
The University of Texas at San Antonio
2018-2023
UNSW Sydney
2023
Xidian University
2023
We apply four machine learning methods to cross-sectional return prediction for hedge fund selection. equip the forecast model with a set of idiosyncratic features, which are derived from historical returns and capture variety fund-specific information. Evaluating out-of-sample performance, we find that our method significantly outperforms styled Hedge Fund Research indices in almost all situations. Among methods, deep neural network appears be overall most effective. Investigating source...
Covalent organic frameworks (COFs) have been widely used in photocatalytic hydrogen peroxide (H2O2) production due to their favorable band structure and excellent light absorption. Due the rapid recombination rate of charge carriers, however, applications are mainly restricted. This study presents design development two highly conjugated triazine-based COFs (TBP-COF TTP-COF) evaluates H2O2 performance. The nitrogen-rich structures high degrees conjugation TBP-COF TTP-COF facilitate improved...
Image recognition has long been one of the research hotspots in computer vision tasks. The development deep learning is rapid recent years, and convolutional neural networks usually need to be designed with fixed resources. If sufficient resources are available, model can scaled up achieve higher accuracy, for example, VggNet, ResNet, GoogLeNet, etc. Although accuracy large-scale models improved, following problems will occur expansion scale: (1) There may over-fitting; (2) increasing...
Abstract Background and Objectives: Neurologic deterioration frequently occurs during the acute phase of isolated pontine infarction (IPI). However, factors that predict early neurologic (END) are not well understood. The purpose this study is to identify analyze predictors END in individuals with IPI. Methods: One hundred fifty-three patients diagnosed IPI were included retrospective study, including 41 group 112 non-END group. Demographic characteristics, clinical data, imaging features...
Forecasting stock returns is extremely challenging in general, and this task becomes even more difficult given the turbulent nature of Chinese market. We address selection process as a statistical learning problem build cross-sectional forecast models to select individual stocks Shanghai Composite Index. Decile portfolios are formed according rankings forecasted future cumulative returns. The equity market's neutral portfolio—formed by buying top decile portfolio selling short bottom...
Catalytic construction of oxindoles bearing all-carbon-quaternary centers attracts wide attention from the synthetic chemistry community.
Abstract Often the research interest in causal inference is on regression effect, which mean difference potential outcomes conditional covariates. In this paper, we use sufficient dimension reduction to estimate a lower dimensional linear combination of covariates that model effect. Compared with existing applications inference, our approaches are more efficient reducing dimensionality covariates, and avoid estimating individual outcome regressions. The proposed can be used three ways assist...
We introduce stable estimation procedures for several aspects of a sufficient dimension-reduction matrix. first propose method estimating structural dimension, which only selects the correct directions in central subspace with no false positive selection. then provide Grassmann manifold sparse estimate subspace. By using subsampling, we develop an ensemble to obtain nonsparse This idea is also used stabilize choice number slices sliced inverse methods. Theoretical results are established,...
The systematic evaluation of Ir catalysts generates the highest reported TONs and a safe protocol for air oxidation.
Condition monitoring or safety monitor is a cost-effective protection technique which widely used in safety-critical industries, such as nuclear plants and aerospace operation. The adoption of offers continuous real-time at high level diversity its implementation relatively simple thus for verification validation. In practice, the monitors are practical to improve overall system because: 1) Safety generally small do not normally have complex algorithms; 2) involve checking essential...
With the rapid development of deep learning and artificial intelligence, affective computing, as a branch field, has attracted increasing research attention. Human emotions are diverse directly expressed via non-physiological indicators, such electroencephalogram (EEG) signals. However, whether emotion-based or EEG-based, these remain single-modes emotion recognition. Multi-mode fusion recognition can improve accuracy by utilizing feature diversity correlation. Therefore, three different...
Emotions serve various functions. The traditional emotion recognition methods are based primarily on readily accessible facial expressions, gestures, and voice signals. However, it is often challenging to ensure that these non-physical signals valid reliable in practical applications. Electroencephalogram (EEG) more successful than other signal recognizing characteristics real-time since they difficult camouflage. Although EEG commonly used current emotional research, the accuracy low when...
Methods for fault diagnosis based on metric learning, in which a query sample is classified by picking the closest prototype from support set their feature similarities, have been subject of many studies. In real-world applications in-orbit products, such as circulating pumps, computation similarity between different pairs prone to degrees inaccuracy, especially epistemic uncertainty. Knowing and considering uncertainty may improve detection accuracy. This article provides unique approach...