Biomedical subjects

Jing-Qi Yuan

Publications and source records attributed to Jing-Qi Yuan.

3 recordsLinked to original sources

PubMed2006

[Fermentation process monitoring and fault detection based on dynamic MPCA].

A dynamic multiway principle component analysis for on-line batch process monitoring and fault detection was proposed. It integrates the time-lagged windows of process dynamic behavior with the multiway principle component analysis (MPCA). Using multi-model instead of single model, the dynamic MPCA approach emphasizes particularly on-line process performance monitoring and fault defecting. On-line process monitoring of cephalosporin C fermentation was studied, the results demonstrate that the dynamic MPCA method is able to efficiently monitor performance of the fermentation process and exactly detect faults which results in extraordinary behavior of processes.

Cephalosporins↗

PubMed2005

[Neural network detection of abnormalities in fed-batch fermentation].

During fermentation, it is often difficult to detect the abnormalities, for example, caused by contamination on-line. Instead, the faults were detected usually by off-line laboratory analysis or other ways, which in most cases, is too late to remedy the situation. In this paper, a simple three-layers BP network was used for the early prediction of the amount of product, based on the difference in prediction errors between normal and abnormal charges and other accessorial information, such as profit function and pH value. In addition, three indications characteristic to abnormal charge are incorporated in practical operation. The prediction for Cephalosporin C Fed-batch Fermentation in a Chinese pharmaceutical factory was studied in details as an example and the result shows the abnormal charge can be discovered early successfully using the method.

Bioreactors↗

PubMed2004

Spike sorting based on automatic template reconstruction with a partial solution to the overlapping problem.

A new method for spike sorting is proposed which partly solves the overlapping problem. Principal component analysis and subtractive clustering techniques are used to estimate the number of neurons contributing to multi-unit recording. Spike templates (i.e. waveforms) are reconstructed according to the clustering results. A template-matching procedure is then performed. Firstly all temporally displaced templates are compared with the spike event to find the best-fitting template that yields the minimum residue variance. If the residue passes the chi(2)-test, the matching procedure stops and the spike event is classified as the best-fitting template. Otherwise the spike event may be an overlapping waveform. The procedure is then repeated with all possible combinations of two templates, three templates, etc. Once one combination is found, which yields the minimum residue variance among the combinations of the same number of component templates and makes the residue pass the chi(2)-test, the matching procedure stops. It is unnecessary to check the remaining combinations of more templates. Consequently, the computational effort is reduced and the over-fitting problem can be partly avoided. A simulated spike train was used to assess the performance of the proposed method, which was also applied to a real recording of chicken retina ganglion cells.

Action Potentials↗