A fuzzy neural network is an approach to mimic the structure and function of our brain. This method is widely applied in character recognition, but not in medical image recognition. The area of medical image recognition is challenging to our interest and can be maximally utilized the advantage of fuzzy neural networks in practice. In this paper we propose and new neural algorithm which is integrated both fuzzy self-organized and supervised learning methods. The proposed algorithm is applied for bronchogenic cancer diagnosis. The experimental results show that the correct recognition rate of our algorithm is superior to that of other neural networks.
Brain ; Diagnosis ; Fuzzy Logic ; Learning

OBJECTIVE: This study aimed to develop expert fuzzy logic model to assist physicians in the prediction of postoperative complications of prostatic hyperplasia before surgery. METHODS: A method for classification of surgical risks was developed. The effect of rotation of the current-voltage characteristics at biologically active points (acupuncture points) was used for the formation of classifier descriptors. The effect determined reversible and non-reversible changes in electrical resistance at acupuncture points with periodic exposure to a sawtooth probe current. Then, the developed method was tested on the prediction of the success of surgical treatment of benign prostatic hyperplasia. RESULTS: Input descriptors were obtained from collected data including current-voltage characteristics of 5 acupuncture points and composed of 27 arrays feeding in the model. The maximum diagnostic sensitivity of the classifier for the success of a surgical operation in the control sample was 88% and for testing data set prediction accuracy was 97%. CONCLUSION The use of tuples of current-voltage characteristic descriptors of acupuncture points in the classifiers could be used to predict the success of surgical treatment with satisfactory accuracy. The model can be a valuable tool to support physicians' diagnosis.
Acupuncture Points ; Acupuncture Therapy ; Fuzzy Logic

This article provides demonstrations and calculations, using rough-set theory and method, of the math-morphological features (MMFs), such as form parameter, lobation and sphericity, etc. drawn from 28 species of insects of the Hemiptera, Lepidoptera and Coleoptera based on their images. The results are compared with statistical analysis made by Zhao Hanqing, and also with the traditional classifications through the pattern recognition of neural network on the basis of the rough-set disposal. The result of the experiments showed that when used in categorical taxonomy, the importance of MMF was ranked from high to low: (roundness-likelihood. eccentricity) > (hot-hole number, sphericity, circularity) > (lobation, form parameter). The results of pattern recognition by neural network were completely identical with those of traditional classifications. Accordingly, the conclusion was that this theory applied in insect taxonomy was more idealistic compared with statistical analysis method, and it had great significance when used with rough-set neural network.
Algorithms ; Animals ; Fuzzy Logic ; Insecta ; classification ; Neural Networks (Computer)

For optimal adaptive cultivation region selection, we used ecology factors characterized Duolun region as model area to carry out the adaptive habitat division of Paeonia lactiflora. Similar priority comparison of ecology factors.in 91 cities were calculated by Fuzzy methods, then, distance of the ecology factors were transferred to spacial model by geography information system (,GIS) and modified by soil utilization map of China. The results showed that P. lactiflora were mainly distributed in the Daxing'an Mountain, Changbaishan and qinling range which were divided into six grades of suitable regions belonging to three geographical distributed units. The most similar areas to Duolun were Huade, Xilinhaote, Suolun and Zhangbei. P. lactiflora's distribution and quality are relevant with longitude and latitude, and temperature and rainfall.
China ; Environment ; Fuzzy Logic ; Paeonia ; classification ; growth & development ; Temperature

Cluster Analysis ; Fuzzy Logic ; Humans ; Mathematics ; Medicine, Chinese Traditional

In order to develop safe training intensity and training methods for the passive balance rehabilitation train- ing system, we propose in this paper a mathematical model for human standing balance adjustment based on T-S fuzzy identification method. This model takes the acceleration of a multidimensional motion platform as its inputs, and human joint angles as its outputs. We used the artificial bee colony optimization algorithm to improve fuzzy C--means clustering algorithm, which enhanced the efficiency of the identification for antecedent parameters. Through some experiments, the data of 9 testees were collected, which were used for model training and model results validation. With the mean square error and cross-correlation between the simulation data and measured data, we concluded that the model was accurate and reasonable.
Algorithms ; Cluster Analysis ; Fuzzy Logic ; Humans ; Models, Theoretical ; Postural Balance

Fuzzy Logic ; Humans ; Occupational Diseases ; etiology ; Risk Assessment

Risks exist in medicine related fields, which cannot be defined and quantified precisely. It is necessary to adopt a method for the risk assessment of uncertain and fuzzy phenomenon. This paper summarizes the thinking, procedure, advantage and application of fuzzy analytic hierarchy process in the risk assessment in medicine related fields for the purpose of providing reference for its further application.
Analytic Hierarchy Process ; Fuzzy Logic ; Humans ; Risk Assessment/methods*

This paper descries a new non-invasive method for diagnosis of breathing disorders based on adaptive-network-based fuzzy inference system (ANFIS). In this method, PetCO2, SpO2 and HR are chosen as inputs, and the breathing condition is selected as output ofANFIS. The inputs and output are then classified into fuzzy subsets by experts' knowledge. After, the fuzzy IF-THEN rules are built up according to the corresponding membership functions by set up of fuzzy subsets. The neural network was finally established and the membership functions and fuzzy rules were optimized by training. The results of experiment shows that ANFIS is more effective than BP Network regarding the diagnosis of breathing disorders.
Artificial Intelligence ; Fuzzy Logic ; Humans ; Neural Networks (Computer) ; Respiration Disorders ; diagnosis

The paper presents a novel fetal heart rate (FHR) detecting system which is a fuzzy counter using the auto-correlation and fuzzy mathematic algorithm. This system is able to deal with the increase and decrease phenomena of FHR, caused by the various interference and noises. It has a higher detection level than ever and a better robust system based on the DSP.
Algorithms ; Echocardiography, Doppler ; instrumentation ; Equipment Design ; Fetal Monitoring ; instrumentation ; Fuzzy Logic ; Heart Rate, Fetal