Performance comparison between the training method and the numerical method of the orthogonal neural network in function approximation

The orthogonal neural network is a recently developed neural network based on the properties of orthogonal functions. It can avoid the drawbacks of traditional feedforward neural networks such as initial values of weights, number of processing elements, and slow convergence speed. Nevertheless, it needs many processing elements if a small training error is desired. Therefore, numerous data sets are required to train the orthogonal neural network. In the article, a least‐squares method is proposed to determine the exact weights by applying limited data sets. By using the Lagrange interpolation method, the desired data sets required to solve for the exact weights can be calculated. An experiment in approximating typical continuous and discrete functions is given. The Chebyshev polynomial is chosen to generate the processing elements of the orthogonal neural network. The experimental results show that the numerical method in determining the weights gives as good performance in approximation error as the known training method and the former has less convergence time. © 2004 Wiley Periodicals, Inc. Int J Int Syst 19: 1257–1275, 2004.     

Applying case-based reasoning for product configuration in mass customization environments

Product variation and customization is a trend in current market-oriented manufacturing environment. Companies produce products in order to satisfy customer's needs. In the customization environment, the R&D sector in an enterprise should be able to offer differentiation in product selection after they take the order. Such product differentiation should meet the requirement of cost and manufacturing procedure. In the light of this, how to generate an accurate bill of material (BOM) that meets the customer's needs and gets ready for the production is an important issue in the intensely competitive market.

The purpose of this study is to reduce effectively the time and cost of design under the premise to manufacture an accurate new product. In this study, the Case-Based Reasoning (CBR) algorithm was used to construct the new BOM. Retrieving previous cases that resemble the current problem can save a lot of time in figuring out the problem and offer a correct direction for designers. When solving a new problem, CBR technique can quickly help generate a right BOM that fits the present situation.     

Engineered Immature Testicular Tissue by Electrospun Mats for Prepubertal Fertility Preservation in a Bioluminescence Imaging Transgenic Mouse Model

Prepubertal boys with cancer may suffer from reduced fertility and maturity following gonadotoxic chemoradiotherapy. Thus, a viable method of immature testicular tissue (ITT) preservation is required in this cohort. In this study, we used poly-L-lactic acid electrospun scaffolds with two levels of fineness to support the development of ITT transplanted from transgenic donors to wild-type recipient mice. The purpose of this study was to evaluate the potential of ITT transplantation and spermatogenesis after using the two scaffolds, employing bioluminescence imaging for evaluation. The results suggest that ITT from 4-week-old mice possessed the most potential in spermatogenesis on the 70th day, together with the fine electrospun scaffolds. Moreover, bioluminescent imaging intensity was observed in recipient mice for up to 107 days, approximately six times more than the coarse electrospun scaffold and the control group. This occurs since the fine scaffold is more akin to the microenvironment of native testicular tissue as it reduces stiffness resulting from micronization and body fluid infiltration. The thermal analysis also exhibited recrystallization during the biodegradation process, which can lead to a more stable microenvironment. Overall, these findings present the prospect of fertility preservation in prepubertal males and could serve as a framework for future applications.     

Physical,Chemical, and Biological Properties of Chitosan-Coated Alginate Microparticles Loaded with Porcine Interleukin-1β: A Potential Protein Adjuvant Delivery System

We previously developed chicken interleukin-1β (IL-1β) mutants as single-dose adjuvants that induce protective immunity when co-administered with an avian vaccine. However, livestock such as pigs may require a vaccine adjuvant delivery system that provides long-lasting protection to reduce the need for successive booster doses. Therefore, we developed chitosan-coated alginate microparticles as a carrier for bovine serum albumin (BSA) or porcine IL-1β (pIL-1β) and assessed their physical, chemical, and biological properties. Electrospraying of the BSA-loaded alginate microparticles (BSA/ALG MPs) resulted in an encapsulation efficiency of 50%, and those MPs were then coated with chitosan (BSA/ALG/CHI MPs). Optical and scanning electron microscopy, zeta potential analysis, and Fourier transform infrared spectroscopy were used to characterize these MPs. The BSA encapsulation parameters were applied to ALG/CHI MPs loaded with pIL-1β, which were not cytotoxic to porcine fibroblasts but had enhanced bio-activity over unencapsulated pIL-1β. The chitosan layer of the BSA/ALG/CHI MPs prevented burst release and facilitated sustained release of pIL-1β for at least 28 days. In conclusion, BSA/ALG/CHI MPs prepared as a carrier for pIL-1β may be used as an adjuvant for the formulation of pig vaccines.     

Scene-Change Aware Dynamic Bandwidth Allocation for Real-Time VBR Video Transmission Over IEEE 802.15.3 Wireless Home Networks

IEEE 802.15.3, an emerging wireless technology, was designed to provide high-quality multimedia services at home. Dynamic bandwidth allocation for a multimedia connection should be considered in order to achieve higher channel utilization, less buffer and less delay, especially for variable bit rate (VBR) multimedia connections. For real-time VBR videos, the bandwidth requirement should be predicted adaptively for effective channel-time requests. Previously, the adaptive least-mean square (LMS) algorithm with fixed step size was applied to predict channel time requirements due to its simplicity and relatively good performance. However, the performance might degrade when scene changes occurred. In this paper, we modify the variable step-size LMS algorithm and apply it as our predictor (VSSNLMS) so that the prediction errors on scene changes can be effectively reduced. Using the prediction results of VSSNLMS, we propose a dynamic bandwidth-allocation scheme that is scene-change aware and can guarantee the delay bound of real-time VBR videos. Simulation results show that the VSSNLMS predictor is superior to previous LMS-type predictors in performance, and the proposed scheme has better performance in channel utilization, buffer usage, and packet loss     

Effects of three‐dimensional virtual reality and traditional training methods on mental workload and training performance

Industries will implement effective training programs to improve training performance, and an ideal training performance occurs under proper mental workload (MWL). Virtual reality (VR) has recently been widely utilized in training; however, only a few studies have investigated its effects on MWL and training performance simultaneously. The purpose of this study is to investigate the effects of VR training and traditional training methods, such as technical manuals (TM) and multimedia films (MF), on training performance and MWL. The results of the performance measurement show that VR training is considered the best training method compared to TM and MF, particularly in the case of complex tasks. The results of physiological measurements (GSR [galvanic skin response], LF% [low frequency], and LF/HF [high frequency] ratio) show a significant difference between reading TM and using computer (MF and VR), wherein the latter has a lower MWL. However, no significant difference in subjective MWL assessment (NASA‐TLX [task load index]) and HF% measurement is found.     

An improved approach to find membership functions and multiple minimum supports in fuzzy data mining

Fuzzy mining approaches have recently been discussed for deriving fuzzy knowledge. Since items may have their own characteristics, different minimum supports and membership functions may be specified for different items. In the past, we proposed a genetic-fuzzy data-mining algorithm for extracting minimum supports and membership functions for items from quantitative transactions. In that paper, minimum supports and membership functions of all items are encoded in a chromosome such that it may be not easy to converge. In this paper, an enhanced approach is proposed, which processes the items in a divide-and-conquer strategy. The approach is called divide-and-conquer genetic-fuzzy mining algorithm for items with Multiple Minimum Supports (DGFMMS), and is designed for finding minimum supports, membership functions, and fuzzy association rules. Possible solutions are evaluated by their requirement satisfaction divided by their suitability of derived membership functions. The proposed GA framework maintains multiple populations, each for one item’s minimum support and membership functions. The final best minimum supports and membership functions in all the populations are then gathered together to be used for mining fuzzy association rules. Experimental results also show the effectiveness of the proposed approach.     

Design and implementation of a high‐efficiency LiFePO4 battery charger for electric vehicle applications

This letter studies and implements a high‐efficiency LiFePO₄ battery charger. The modular design can satisfy the requirements of series/parallel charging for electric vehicle applications. A CC‐CC‐CV charging scheme is also realized to meet the characteristics of LiFePO₄ battery stacks. A 2 kW laboratory prototype is built and tested. The experimental results are shown to verify the feasibility of the proposed scheme. Copyright © 2012 John Wiley & Sons, Ltd.