Thermal deformation error is one of the most important factors affecting the CNCs’ accuracy, so research is conducted on the temperature errors affecting CNCs’ machining accuracy;on the basis of analyzing the unpred...Thermal deformation error is one of the most important factors affecting the CNCs’ accuracy, so research is conducted on the temperature errors affecting CNCs’ machining accuracy;on the basis of analyzing the unpredictability and pre-maturing of the results of the genetic algorithm, as well as the slow speed of the training speed of the particle algorithm, a kind of Mind Evolutionary Algorithm optimized BP neural network featuring extremely strong global search capacity was proposed;type KVC850MA/2 five-axis CNC of Changzheng Lathe Factory was used as the research subject, and the Mind Evolutionary Algorithm optimized BP neural network algorithm was used for the establishment of the compensation model between temperature changes and the CNCs’ thermal deformation errors, as well as the realization method on hardware. The simulation results indicated that this method featured extremely high practical value.展开更多
Based on detailed study on several kinds of fuzzy neural networks, we propose a novel compensationbased recurrent fuzzy neural network （CRFNN） by adding recurrent element and compensatory element to the conventional...Based on detailed study on several kinds of fuzzy neural networks, we propose a novel compensationbased recurrent fuzzy neural network （CRFNN） by adding recurrent element and compensatory element to the conventional fuzzy neural network. Then, we propose a sequential learning method for the structure identification of the CRFNN in order to confirm the fuzzy rules and their correlative parameters effectively. Furthermore, we improve the BP algorithm based on the characteristics of the proposed CRFNN to train the network. By modeling the typical nonlinear systems, we draw the conclusion that the proposed CRFNN has excellent dynamic response and strong learning ability.展开更多
A method is established for measuring low energy γ-rays dose by using CMOS sensors without any X-/γ-ray converters. Gamma-ray source of241 Am and152Eu are used to test the system. Based on gray value, an analysis me...A method is established for measuring low energy γ-rays dose by using CMOS sensors without any X-/γ-ray converters. Gamma-ray source of241 Am and152Eu are used to test the system. Based on gray value, an analysis method is proposed to obtain the γ-ray dose. Cumulative dose is determined by correlating the gray value to the dose readings of standard dosimeters. The relationship between gray value and the cumulative dose of γ-rays are trained by using back propagation neural network with BFGS algorithm. After comparison, it shows that BFGS algorithm trainings are suitable for different γ-ray sources under higher error condition. These indicate the feasibility of measuring low energy γ-ray dose by using common CMOS image sensors.展开更多
Dynamic monitoring of blood pressure (BP) is beneficial to obtain comprehensive cardiovascular information of patients throughout the day. However, the clinical BP measurement method relies on wearing a bulky cuff, wh...Dynamic monitoring of blood pressure (BP) is beneficial to obtain comprehensive cardiovascular information of patients throughout the day. However, the clinical BP measurement method relies on wearing a bulky cuff, which limits the long-term monitoring and control of BP. In this work, a microcavity assisted graphene pressure sensor (MAGPS) for single-vessel local BP monitoring is designed to replace the cuff. The microcavity structure increases the working range of the sensor by gas pressure buffering. Therefore, the MAGPS achieves a wide linear response of 0–1050 kPa and sensitivity of 15.4 kPa^(−1). The large working range and the microcavity structure enable the sensor to fully meet the requirements of BP detection at the radial artery. A database of 228 BP data (60-s data fragment detected by MAGPS) and 11,804 pulse waves from 9 healthy subjects and 5 hypertensive subjects is built. Finally, the BP was detected and analyzed automatically by combining MAGPS and a two-stage convolutional neural network algorithm. For the BP detection method at local radial artery, the first stage algorithm first determines whether the subject has hypertension by the pulse wave. Then, the second stage algorithm can diagnose systolic and diastolic BP with the accuracy of 93.5% and 97.8% within a 10 mmHg error, respectively. This work demonstrates a new BP detection method based on single vessel, which greatly promotes the efficiency of BP detection.展开更多
Recently many researches suggest that CEO compensation is not only related to performance. And this relation is non-linear. This paper analyzes CEO compensation, salary and stockholding value with BP neutral network w...Recently many researches suggest that CEO compensation is not only related to performance. And this relation is non-linear. This paper analyzes CEO compensation, salary and stockholding value with BP neutral network with the data from listed companies during 2003--2005 in China. The results are： 1） The fitness of network outputs are 91.09%, 97：23% and 78.44% respectively; 2） The accurate of forecast improves 92.72%, 92.08% and 53.89% respectively comparing with the results of multi-regression model.展开更多
文摘Thermal deformation error is one of the most important factors affecting the CNCs’ accuracy, so research is conducted on the temperature errors affecting CNCs’ machining accuracy;on the basis of analyzing the unpredictability and pre-maturing of the results of the genetic algorithm, as well as the slow speed of the training speed of the particle algorithm, a kind of Mind Evolutionary Algorithm optimized BP neural network featuring extremely strong global search capacity was proposed;type KVC850MA/2 five-axis CNC of Changzheng Lathe Factory was used as the research subject, and the Mind Evolutionary Algorithm optimized BP neural network algorithm was used for the establishment of the compensation model between temperature changes and the CNCs’ thermal deformation errors, as well as the realization method on hardware. The simulation results indicated that this method featured extremely high practical value.
基金Supported by the National High-Tech Research and Development Program of China (Grant No. 2006AA05A107)Special Fund of JiangsuProvince for Technology Transfer (Grant No. BA2007008)
文摘Based on detailed study on several kinds of fuzzy neural networks, we propose a novel compensationbased recurrent fuzzy neural network （CRFNN） by adding recurrent element and compensatory element to the conventional fuzzy neural network. Then, we propose a sequential learning method for the structure identification of the CRFNN in order to confirm the fuzzy rules and their correlative parameters effectively. Furthermore, we improve the BP algorithm based on the characteristics of the proposed CRFNN to train the network. By modeling the typical nonlinear systems, we draw the conclusion that the proposed CRFNN has excellent dynamic response and strong learning ability.
基金Supported by National Natural Science Foundation of China(No.10905017)the Science and Technology Innovation Team Support Plan in Henan Province(No.13IRTSTHN016)
文摘A method is established for measuring low energy γ-rays dose by using CMOS sensors without any X-/γ-ray converters. Gamma-ray source of241 Am and152Eu are used to test the system. Based on gray value, an analysis method is proposed to obtain the γ-ray dose. Cumulative dose is determined by correlating the gray value to the dose readings of standard dosimeters. The relationship between gray value and the cumulative dose of γ-rays are trained by using back propagation neural network with BFGS algorithm. After comparison, it shows that BFGS algorithm trainings are suitable for different γ-ray sources under higher error condition. These indicate the feasibility of measuring low energy γ-ray dose by using common CMOS image sensors.
基金supported by the National Natural Science Foundation of China(Nos.62201624,32000939,21775168,22174167,51861145202 and U20A20168)the Guangdong Basic and Applied Basic Research Foundation(Nos.2024A1515012056 and 2019A1515111183)+4 种基金Shenzhen Science and Technology Program(No.RCBS20221008093310024)Shenzhen Research Funding Program(Nos.JCYJ20190807160401657 and JCYJ201908073000608)Open Research Fund Program of Beijing National Research Center for Information Science and Technology(No.BR2023KF02010)The authors are also thankful for the support from Key Laboratory of Sensing Technology and Biomedical Instruments of Guangdong Province(No.2020B1212060077)the Fundamental Research Funds for the Central Universities,Sun Yat-sen University(No.24xkjc034).
文摘Dynamic monitoring of blood pressure (BP) is beneficial to obtain comprehensive cardiovascular information of patients throughout the day. However, the clinical BP measurement method relies on wearing a bulky cuff, which limits the long-term monitoring and control of BP. In this work, a microcavity assisted graphene pressure sensor (MAGPS) for single-vessel local BP monitoring is designed to replace the cuff. The microcavity structure increases the working range of the sensor by gas pressure buffering. Therefore, the MAGPS achieves a wide linear response of 0–1050 kPa and sensitivity of 15.4 kPa^(−1). The large working range and the microcavity structure enable the sensor to fully meet the requirements of BP detection at the radial artery. A database of 228 BP data (60-s data fragment detected by MAGPS) and 11,804 pulse waves from 9 healthy subjects and 5 hypertensive subjects is built. Finally, the BP was detected and analyzed automatically by combining MAGPS and a two-stage convolutional neural network algorithm. For the BP detection method at local radial artery, the first stage algorithm first determines whether the subject has hypertension by the pulse wave. Then, the second stage algorithm can diagnose systolic and diastolic BP with the accuracy of 93.5% and 97.8% within a 10 mmHg error, respectively. This work demonstrates a new BP detection method based on single vessel, which greatly promotes the efficiency of BP detection.
基金This project is supported by National Natural Science Foundation of China （70671058）
文摘Recently many researches suggest that CEO compensation is not only related to performance. And this relation is non-linear. This paper analyzes CEO compensation, salary and stockholding value with BP neutral network with the data from listed companies during 2003--2005 in China. The results are： 1） The fitness of network outputs are 91.09%, 97：23% and 78.44% respectively; 2） The accurate of forecast improves 92.72%, 92.08% and 53.89% respectively comparing with the results of multi-regression model.
