Search

Hypoglycemic effects and the use of kelp in diabetes mellitus (DM) model rats induced by alloxan were investigated. Sixty healthy male rats were used to establish DM models by injecting alloxan intraperitoneally. Kelp powder was added to the general forage for the rats. The levels of fasting blood glucose (FBG) were determined by an automatic blood glucose device. Electrochemiluminescence immunoassay was applied to determine the serum levels of insulin. The serum levels of malondialdehyde (MDA) were measured by thiobarbituric acid assay and nitric oxide (NO) by nitrate reductase assay. The activities of superoxide dismutase (SOD) were determined by xanthinoxidase assay and glutathione peroxidase (GSH-Px) by chemical colorimetry. The shape and structure of islet cells were observed with Hematine-Eosin staining, and the expression of superoxide dismutase (SOD) and inducible nitric oxide synthase (iNOS) in islet cells were detected by immunohistochemical assay. The results showed that the serum levels of insulin after treatment with kelp powder increased significantly compared to those in the DM-model group, while the FBG in the medium-high dose treated groups decreased significantly compared to those in the DM-model group (P < 0.05). The levels of MDA and NO in the kelp powder groups were lower than those in the DM-model group, while the activities of SOD and GSH-Px were higher than those in the DM-model group, of which a significant difference existed between the medium-high dose treated groups and the DM-model group (P < 0.05). The shape and structure of islet cells improved with the up-expressing SOD and down-expressing iNOS in the medium-high dose treated groups compared to those in the DM-model group (P < 0.05). There were no significant differences between the medium and high dose treated groups, all above indexes (P > 0.05). It is suggested that kelp might aid recovery of the the islet cell secreting function and reduce the level of FBG by an antioxidant effect.

In some practical applications of neural networks, fast response to external events within an extremely short time is highly demanded and expected. However, the extensively used gradient-descent-based learning algorithms obviously cannot satisfy the real-time learning needs in many applications, especially for large-scale applications and/or when higher generalization performance is required. Based on Huang's constructive network model, this paper proposes a simple learning algorithm capable of real-time learning which can automatically select appropriate values of neural quantizers and analytically determine the parameters (weights and bias) of the network at one time only. The performance of the proposed algorithm has been systematically investigated on a large batch of benchmark real-world regression and classification problems. The experimental results demonstrate that our algorithm can not only produce good generalization performance but also have real-time learning and prediction capability. Thus, it may provide an alternative approach for the practical applications of neural networks where real-time learning and prediction implementation is required. Index Terms--Backpropagation (BP), extreme learning machine, Feed-forward networks, generalization performance, k-NN, real-time learning, real-time prediction.

Neural networks with threshold activation functions are highly desirable because of the ease of hardware implementation. However, the popular gradient-based learning algorithms cannot be directly used to train these networks as the threshold functions are nondifferentiable. Methods available in the literature mainly focus on approximating the threshold activation functions by using sigmoid functions. In this paper, we show theoretically that the recently developed extreme learning machine (ELM) algorithm can be used to train the neural networks with threshold functions directly instead of approximating them with sigmoid functions. Experimental results based on real-world benchmark regression problems demonstrate that the generalization performance obtained by ELM is better than other algorithms used in threshold networks. Also, the ELM method does not need control variables (manually tuned parameters) and is much faster. Index Terms--Extreme learning machine (ELM), gradient descent method, threshold neural networks.