A5011724758- Fault Detection and Control Systems
- Water Quality Monitoring and Analysis
- Mineral Processing and Grinding
- Advanced Image and Video Retrieval Techniques
- Air Quality Monitoring and Forecasting
- Iron and Steelmaking Processes
- Advanced Chemical Sensor Technologies
- Wastewater Treatment and Nitrogen Removal
- Spectroscopy and Chemometric Analyses
- Advanced Welding Techniques Analysis
- Water Quality Monitoring Technologies
- Pharmaceutical and Antibiotic Environmental Impacts
- Data Management and Algorithms
- 3D Surveying and Cultural Heritage
- Robotics and Sensor-Based Localization
- Semiconductor materials and devices
- Remote Sensing and LiDAR Applications
- Anomaly Detection Techniques and Applications
- Bipolar Disorder and Treatment
- Industrial Vision Systems and Defect Detection
- Advancements in Semiconductor Devices and Circuit Design
- Ammonia Synthesis and Nitrogen Reduction
- Color Science and Applications
- Advanced Algorithms and Applications
- Recommender Systems and Techniques
Zhejiang University
2021-2024
Guangzhou Vocational College of Science and Technology
2024
State Key Laboratory of Industrial Control Technology
2020-2024
Hainan University
2024
Guizhou University
2024
Chengdu Institute of Biology
2021-2023
Chinese Academy of Sciences
2019-2023
Qinghai Normal University
2023
Park University
2022
Nanjing Forestry University
2018-2021
A dynamic Gaussian process regression based partial least-squares (D-GPR-PLS) model is proposed to improve estimation ability and compared the conventional nonlinear PLS. Considering strong of GPR in modeling, this method used build a between each pair latent variables least-squares. In addition, augmented matrices are embedded into D-GPR-PLS obtain better prediction accuracy processes. To evaluate modeling performance method, two simulated cases real industrial on wastewater treatment...
As a key thermal-state indicator of the iron ore sintering process, content ferrous oxide (FeO) in finished sinter is directly related to product quality. Based on massive data data-driven soft sensor model provides good choice for real-time FeO detection. However, complex characteristics data, including dynamics, nonlinearity, and multisource heterogeneity, are still main obstacles improving modeling accuracy. To solve this problem, article, information fusion autoformer (MIF-Autoformer)...
The ability of penetration the blood–brain barrier is one significant properties a drug or drug-like compound for central nervous system (CNS), which commonly expressed by log BB (log = (C brain/C blood)). In this work, dataset 320 compounds with values was split into training set including 198 and test 122 according to their structure Kohonen's self-organizing map (SOM). Each molecule represented global shape descriptors, 2D autocorrelation descriptors RDF calculated ADRIANA.Code. Several...
The Three-River Source Nature Reserve is located in the core area of Qinghai-Tibetan Plateau, with alpine swamp, meadow and steppe as main ecosystem types. However, microbial communities these ecosystems, their carbon nitrogen degrading metabolic networks limiting factors remain unclear.We sequenced diversity bacteria fungi swamps, meadows, steppes, degraded artificially restored ecosystems analyzed soil environmental conditions.The results indicated that moisture content had a greater...
Burn-through point (BTP) is a very key factor in maintaining the normal operation of sintering process, which guarantees yield and quality sinter ore. Due to characteristics time-varying multivariable coupling actual it difficult for traditional soft-sensor models extract spatial-temporal features reduce multistep prediction error accumulation. To address these issues, this study, we propose probabilistic aware network, called BTPNet, used feature accurate BTP prediction. The BTPNet model...
Abstract The sweetness of a compound is large interest for the food additive industry. In this work, 2 quantitative models were built to predict logSw (the logarithm sweetness) 320 unique compounds with molecular weight from 132 1287 and 22 22500000. whole dataset was randomly split into training set including 214 test 106 compounds, represented by 12 selected descriptors. Then, predicted using multilinear regression (MLR) analysis support vector machine (SVM). For set, correlation...
The explosive growth of user-generated contents in social networking websites necessitates the recommendation functionality that can push to user content he/she is most likely be interested in. Such should happen real-time as new become available, because "freshness" an important consideration people's content-consumption behavior. Representing users and feature vectors a high-dimensional space, we essentially cast problem recommendations computing list k nearest neighbors each user, which...
In the color difference inspection system based on machine vision, two types of dyeing effects need to be evaluated quantitatively according measurement results: consistency – matching degree between product and target; levelness uniformity in different regions same product. The purpose this paper is develop evaluation algorithms a new model dyed fabrics Support Vector Machine (SVM). Firstly, goals were classified into five levels ISO 105-A02:1993; secondly, six difference-related features...