A5103079699- Colorectal Cancer Screening and Detection
- Fault Detection and Control Systems
- Mineral Processing and Grinding
- Drilling and Well Engineering
- Hydraulic Fracturing and Reservoir Analysis
- Corporate Finance and Governance
- Geology and Paleoclimatology Research
- Iron and Steelmaking Processes
- Auditing, Earnings Management, Governance
- Infrared Target Detection Methodologies
- Advanced Neural Network Applications
- Hydrocarbon exploration and reservoir analysis
- Fluid Dynamics and Mixing
- Gastric Cancer Management and Outcomes
- Paleontology and Stratigraphy of Fossils
- Gastrointestinal Bleeding Diagnosis and Treatment
- Geological and Geochemical Analysis
- Radiomics and Machine Learning in Medical Imaging
- Advanced Image and Video Retrieval Techniques
- COVID-19 diagnosis using AI
- Metaheuristic Optimization Algorithms Research
- E-commerce and Technology Innovations
- Anomaly Detection Techniques and Applications
- Domain Adaptation and Few-Shot Learning
- Financial Reporting and Valuation Research
University of Aizu
2020-2025
Northeastern University
2020-2025
University of Science and Technology Beijing
2023-2025
China University of Geosciences
2023-2024
State Key Laboratory of Synthetical Automation for Process Industries
2024
Sun Yat-sen University
2023
China University of Petroleum, Beijing
2019-2022
Northwest University
2019
State Key Laboratory of Continental Dynamics
2019
Macau University of Science and Technology
2017
Principal component analysis (PCA) and independent (ICA) have been widely used for process monitoring in industry. Since the operation data of blast furnace (BF) ironmaking contain both non-Gaussian distribution Gaussian data, above single PCA or ICA method hardly describes information BF completely, which makes diagnosis abnormal working-conditions only with a prone to false positives negatives. In this article, novel integrated PCA-ICA is proposed diagnosing conditions by comprehensively...
Capsule endoscopy is a common method for detecting digestive diseases. The location of capsule endoscope should be constantly monitored through visual inspection the endoscopic images by medical staff to confirm examination’s progress. In this study, we proposed computer-aided analysis (CADx) localization endoscope. At first, classifier based on Swin Transformer was classify each frame videos into stomach, small intestine, and large respectively. Then, K-means algorithm used correct outliers...
As one of the pivotal Gondwana–derived blocks, kinematic history northern Qiangtang Block (in Tibetan Plateau) remains unclear, mainly because quantitative paleomagnetic data to determine paleoposition are sparse. Thus, for this study, we collected 226 samples (17 sites) from Triassic sedimentary rocks in Raggyorcaka and Tuotuohe areas (NQB). Stepwise demagnetization isolated high temperature/field components samples. Both Early Late datasets passed field tests at a 99% confidence level were...
Automatic polyp detection is reported to have a high false-positive rate (FPR) because of various polyp-like structures and artifacts in complex colon environment. An efficient polyp's computer-aided (CADe) system should sensitivity low FPR (high specificity). Convolutional neural networks been implemented colonoscopy-based automatic achieved performance improving rate. However, environments caused excessive false positives are going prevent the clinical implementation CADe systems. To...
Abstract The Early Eocene Climatic Optimum (EECO) may be a potentially useful analog for future global warming under high CO 2 concentrations. However, paucity of orbital‐scale terrestrial records limits our understanding how the hydrological cycle responded during this protracted (∼4 Myr) interval warmth. In study, we combine zircon U‐Pb dating and cyclostratigraphy to establish high‐resolution astronomical timescale spanning EECO (∼52.9 Ma ∼49.9 Ma) through >1 km fluviolacustrine...
Artificial intelligence (AI) with white light imaging (WLI) is not enough for detecting non-polypoid colorectal polyps and it still has high false positive rate (FPR). We developed AIs using blue laser (BLI) linked color (LCI) to detect them specific learning sets (LS).
The purpose of this paper is to discuss the variation wellbore temperature and bottom-hole pressure with key factors in case coupled under multi-pressure system during deep-water drilling circulation. According law energy conservation momentum equation, calculation model developed by using comprehensive convective heat transfer coefficient. discretized solved finite difference method Gauss Seidel iteration respectively. Then results are compared verified previous research models field...
Aiming at the nonstationary characteristics of many practical industrial systems as well long memory and seasonality some process data, this article proposes a novel anomaly detection method based on fractional cointegration vector autoregression (FCVAR). First, augmented Dickey–Fuller (ADF) test is used to divide variables into stationary categories. For variables, trend extraction algorithm extract avoid information from being overwhelmed due strong data. Meanwhile, considering that...
Blast furnace (BF) ironmaking is a key process in iron and steel production. Because BF dynamic time series process, it more appropriate to use recurrent neural network for modeling. The long short-term memory (LSTM) commonly used model data. However, its performance generalization ability heavily depend on the parameter configuration. Therefore, necessary study optimization LSTM model. sparrow search algorithm (SSA) holds advantages over traditional algorithms several aspects, such as no...
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Diagnostic performance of a computer-aided diagnosis (CAD) system for deep submucosally invasive (T1b) colorectal cancer was excellent, but the "regions interest" (ROI) within images are not obvious. Class activation mapping (CAM) enables identification ROI that CAD utilizes diagnosis. The purpose this study quantitative investigation difference between and endoscopists.
Task inharmony problem commonly occurs in modern object detectors, leading to inconsistent qualities between classification and regression tasks. The predicted boxes with high scores but poor localization positions or low accurate will worsen the performance of detectors after Non-Maximum Suppression. Furthermore, when collaborate Quantization-Aware Training (QAT), we observe that task be further exacerbated, which is considered one main causes degradation quantized detectors. To tackle this...