A5064384493- Neural Networks and Reservoir Computing
- Advanced Memory and Neural Computing
- Neural Networks and Applications
- Optical Network Technologies
- Nanopore and Nanochannel Transport Studies
- Industrial Technology and Control Systems
- Machine Learning and ELM
- Microfluidic and Capillary Electrophoresis Applications
- Advanced biosensing and bioanalysis techniques
- Ion-surface interactions and analysis
- Microfluidic and Bio-sensing Technologies
- Water Quality Monitoring and Analysis
- Advanced Sensor and Control Systems
- Electrostatics and Colloid Interactions
- Advanced Algorithms and Applications
- Industrial Gas Emission Control
- Mineral Processing and Grinding
- Fuel Cells and Related Materials
- Medical Research and Treatments
- Monoclonal and Polyclonal Antibodies Research
- Advanced Computing and Algorithms
- Membrane-based Ion Separation Techniques
- Brain Tumor Detection and Classification
- Slime Mold and Myxomycetes Research
- Face and Expression Recognition
University of Jinan
2015-2025
University of Massachusetts Amherst
2020-2023
Beijing Academy of Artificial Intelligence
2015-2016
Beijing University of Technology
2015-2016
Peking University
2010
An echo-state network (ESN) is an effective alternative to gradient methods for training recurrent neural network. However, it difficult determine the structure (mainly reservoir) of ESN match with given application. In this paper, a growing (GESN) proposed design size and topology reservoir automatically. First, GESN makes use block matrix theory add hidden units existing group by group, which leads multiple subreservoirs. Second, every subreservoir weight in created predefined singular...
Abstract Protein kinases play central roles in cellular regulation by catalyzing the phosphorylation of target proteins. Kinases have inherent structural flexibility allowing them to switch between active and inactive states. Quantitative characterization kinase conformational dynamics is challenging. Here, we use nanopore tweezers assess Abl domain, which shown interconvert two major states where one conformation comprises three sub-states. Analysis kinase-substrate kinase-inhibitor...
Construction of a self-regenerating biochemical system is critical for building synthetic cell. An essential step in self-regenerative producing complete set tRNAs translation, which remains significant challenge. We reconstituted 21 vitro transcribed (IVT) by improving the transcription yield four and optimized their abundance to improve protein yield. Next, we showed that expression PURE transcription-translation can be achieved situ transcribing from linear tRNA templates or single...
The current research investigated whether employees' self-construals moderated the effects of supplementary fit and complementary on their work-related outcomes (i.e. affective commitment citizenship behavior). An organisational sample 317 Chinese employees provided evidence that relations between these two were stronger among with a higher interdependent self-construal. Conversely, independent Theoretical practical implications findings are discussed.
The basic concept of teacher education professional certification is "students-centered, export-oriented, and continuous improvement". evaluation graduation requirements strictly controls the "export" higher education, which a key link in certification. It an important guarantee for deepening reform system improving training quality normal students. Comprehensive objective results provide basis improvement system. majors involves various aspects student, closed-loop system, including...
Measuring nitrogen oxide (NOx) concentration accurately and timely is critical for pollution control during cement clinker calcination. However, due to the harsh environment complex reactions, NOx in calcination systems cannot be directly measured. In this article, a flexible cascaded echo-state network (FCESN) developed online measurement of First, structure proposed, where some networks (ESNs) as basic modules are added form cascade one by until learning error satisfied. Then, based on...
The clustering of raw meal composition is great significance for accurately dividing the production conditions and improving quality clinker calcination. method based on principal component analysis Kmeans was studied in this paper. According to cement process, variables were determined. Then, used obtain components cluster variables, dimension reduced according cumulative contribution rate components. On basis, feature after reduction. Finally, data a plant. results showed that feasible....
Abstract Nanopore sequencing is one of only a few methods that can potentially determine the amino acid sequence individual protein molecules as these are passed through pore sensor. However, mechanisms for unfolding and translocation proteins still unavailable to date. Here we describe general approach realizing unidirectional transport full-length nanopores. We combine chemically resistant biological nanopore platform with high concentration guanidinium chloride buffer achieve...
In this paper, a fast growing cascade neural network (FGCNN) is proposed, as software sensor, to rapidly estimate the biochemical oxygen demand (BOD) in wastewater treatment plants (WWTPs). Firstly, novel method, based on orthogonal least squares (OLS), put forward add input and hidden units existing one by one. Every unit added affords maximal reduction of sum squared errors (SSE). Then, FGCNN incrementally updates its output weights iterations without gradients generalized inverses, while...
Abstract Nanopore sensors could revolutionize single-molecule proteomics by providing a means for identification of known proteins through fingerprinting or de novo sequencing. However, the complex chemical and physical properties present multiple challenges to conventional nanopore sensing method, predominantly, single-file threading protein chain into its transport it. Herein we describe general approach realizing unidirectional full-length nanopores. We show that combination chemically...