Search

Medical image reporting is an important information carrier for medical staff to record medical activities for patients. It contains a large number of technical terms and medical knowledge. Extracting effective information from medical imaging reports can better serve clinical decision making and promote the development of the medical field. This paper focuses on the breast medical imaging report, analyzes the structural characteristics of the report, designs the medical record structured template, extracts the text features from the image report, and forms the structured data in the canonical form. In this paper, the machine learning model bidirectional CNNs-LSTM-CRF is used to extract the characteristic information of related lesions in the image report. The experimental data comes from an imaging inspection report provided by a medical institution to evaluate the effect of the structure by predicting the BI-RADS classification information. The data was provided by a medical institution, and the extracting result of the feature tagging is that the average accuracy is 95.71%, the average recall is 98.10%, and the average F1 values 97.29%.

A multimedia teaching platform based on network technology with the function of multimedia animation and sound effects was designed and built. For the need of modern teaching work under the condition of information, it was meaningful to construct a multimedia teaching platform with the network on line and multimedia, and the remote control for the remote teaching platform needed to be realized. Then the expense and resources of the education and teaching were saved with the network teaching platform, and also the quality of teaching was improved by the multimedia network teaching platform. The network transmission system was established based on the TCP/IP Protocol and C/S. the remote control and data transmission was realized successfully, and it also can save the training and experiments expenses with this platform. The design and test result shows that the multimedia performance if the platform is very nice. The network test effect shows the performance of remote control and data transmission is stable, the prospect of the platform application is showcased.

A niche ant colony algorithm (NACA) for multi-modal function optimization, which bases on principle of ant colony algorithm, is devised. It adopts real code. By simulation research of the NACA, and comparing with correlative algorithms, the results show that the NACA has advantages, such as easy to select parameters, strong adaptability, and good convergence, and is very suitable for multi-modal functions optimization with searching for multiple optimal solutions or global optimal solutions.

The control to the speed of coaler actually is the control to diesel engine's speed, in this paper we tune the parameters of fractional order controller by using immune clone selection algorithm and simulate the result by using mat lab. The result demonstrate that fractional order controller has very good dynamic performance and strong robust than general integrate PID controller. It largely improved the defect of speed control system of diesel engine and has broader prospect.

An approximation method of false alarm probability and detection probability is presented using cepstrum moments. A new CFAR processor, OSEXCA-CFAR (order statistics excision cell averaged-constant false alarm rate), is proposed and its performance is discussed by computer simulation and cepstrum moments.