본 논문에서는 인공 신경망의 일종인 Extreme Learning Machine의 학습 알고리즘을 기반으로 하여 노이즈에 강한 특성을 보이는 퍼지 집합 이론을 이용한 새로운 패턴 분류기를 제안 한다. 기존 인공 신경망에 비해 학습속도가 매우 빠르며, 모델의 일반화 성능이 우수하다고 알려진 Extreme Learning Machine의 학습 알고리즘을 퍼지 패턴 분류기에 적용하여 퍼지 패턴 분류기의 학습 속도와 패턴 분류 일반화 성능을 개선 한다. 제안된 퍼지 패턴 분류기의 학습 속도와 일반화 성능을 평가하기 위하여, 다양한 머신 러닝 데이터 집합을 사용한다.

Extreme Learning Machine 기반 퍼지 패턴 분류기 설계

The recent appearance of low cost Virtual Reality (VR) technologies – like the Oculus Rift, the HTC Vive and the Sony PlayStation VR – and Mixed Reality Interfaces (MRITF) – like the Hololens – is attracting the attention of users and researchers suggesting it may be the next largest stepping stone in technological innovation. However, the history of VR technology is longer than it may seem: the concept of VR was formulated in the 1960s and the first commercial VR tools appeared in the late 1980s. For this reason, during the last twentyyears, hundreds of researchers explored the processes, effects and applications of this technology producing thousands of scientific papers. What is the outcome of this significant research work? This paper wants to provide an answer to this question by exploring, using advanced scientometric techniques, the existing research corpus in the field. We collected all the existent articles about VR in the Web of Science Core Collection scientific database, and the resultant dataset contained 21,667 records for VR and 9,944 for AR. The bibliographic record contained various fields, such as author, title, abstract, country, and all the references (needed for the citation analysis). The network and cluster analysis of the literature showed a composite panorama characterized by evolutions over the time. Indeed, whether until five years ago, the main publication media on VR concerned both conference proceeding and journals, more recently journals constitute the main medium. Similarly, if at first computer science was the leading research field, nowadays clinical areas increased, as well as the number of countries involved in virtual reality research. The present work discusses the evolution of the use of virtual reality in the main areas of application with an emphasis on the future expected virtual reality’s capacities, increases and challenges. We conclude considering the disruptive contribution that VR/AR/MRITF will be able to get in scientific fields, as well in human communication and interaction, as already happened with the advent of mobile phones by increasing the use and the development of scientific applications (e.g. in clinical areas) and by modifying the social communication and interaction among people.

/pdf/the-past-present-and-future-of-virtual-and-augmented-reality-1qmnxew4eq.pdf

The Past, Present, and Future of Virtual and Augmented Reality Research: A Network and Cluster Analysis of the Literature

https://dr.ntu.edu.sg/bitstream/10356/104474/2/Experimental%20study%20on%20mix%20proportion%20and%20fresh%20properties%20of%20fly%20ash.pdf

Experimental study on mix proportion and fresh properties of fly ash based geopolymer for 3D concrete printing

https://onlinelibrary.wiley.com/doi/epdf/10.1002/cey2.29

Recycling of mixed cathode lithium-ion batteries for electric vehicles: Current status and future outlook

A framework to expedite joint energy-reserve payment cost minimization using a custom-designed method based on Mixed Integer Genetic Algorithm

Lithium-ion Battery pack which is comprised of assembly of battery modules is the main source of power transmission for electric vehicles. During the actual operation of electric vehicle, the battery packs and its enclosure is subjected to harsh environmental conditions such as the external vibrations and shocks due to varying road slopes. This will result in stresses and deformations of different degrees. The vehicle safety heavily depends on on the safety of battery pack which in turn is dependent on its mechanical features, such as the ability to resist deformation and vibration shocks. In addition, lighter weight vehicle is preferred because it can increase the range of vehicle and the life cycle of a battery pack. In this study, a design optimization methodology is proposed to optimize the features of mechanical design (e.g. minimization of mass, maximization of minimum natural frequency and minimization of maximum deformation) of the battery pack enclosure. The proposed methodology is comprised of four phases. In the first phase, finite element models for maximum deformation (based on static analysis), minimum natural frequency (based on modal analysis) and the mass are developed by using the combination of four methods (i.e. central composite design (CCD) and response surface methodology (RSM), CCD and artificial neural network (ANN), Latin hypercube sampling (LHS) and RSM, LHS and ANN). In the second phase, the best combination of methodology (CCD and ANN) is then selected for experimental design and the empirical models are formulated for three features of mechanical design. In the third phase, the models based on CCD and ANN for the maximum deformation, minimum natural frequency and mass are further optimized by using non-dominated sorted genetic algorithm (NSGA II). In the fourth phase, the optimum combination of inputs obtained by using NSGA II is used for the manufacturing of battery pack enclosure. Conclusions are made and research recommendations are proposed for the future work.

Design optimization of battery pack enclosure for electric vehicle

Robust model design for evaluation of power characteristics of the cleaner energy system

Summary
The improvement in the operating range of electric vehicles can be accomplished by robust modelling of the design and optimization of the energy storage capacity of the battery pack system. In this work, the authors have conducted a comprehensive survey on battery modelling methods and identified critical areas of improvement vital for estimating the battery capacity. This work proposes the artificial intelligence approach of automated neural networks search (ANS) in development of the robust battery capacity models for the lithium ion batteries based on the inputs (temperature and discharge rates). The robustness in the models is introduced by incorporating uncertainties in the inputs (the temperature and discharge rates, the architecture of algorithm and the models). The statistical analysis and validation of the models reveal that the models formulated using an ANS approach outperform the response surface regression models with correlation coefficient achieved as high as 0.97. The uncertainty analysis based on normal distribution of the inputs suggests that the models formulated from ANS are least sensitive to change in the input conditions when compared to response surface regression models. The global sensitivity analysis reveals that the temperature is a dominant factor for accurate battery capacity estimation. Copyright © 2017 John Wiley & Sons, Ltd.

Design of robust battery capacity model for electric vehicle by incorporation of uncertainties

Study of effect of nanofluid concentration on response characteristics of machining process for cleaner production

User experience has a significant impact on the effective product design and improvement, especially for a personalized product to meet user’s individual need The development of personalized produ

http://journals.sagepub.com/doi/pdf/10.1177/0954405417711736

Jian Zhang

Papers

Design optimization of battery pack enclosure for electric vehicle

Robust model design for evaluation of power characteristics of the cleaner energy system

Design of robust battery capacity model for electric vehicle by incorporation of uncertainties

Study of effect of nanofluid concentration on response characteristics of machining process for cleaner production

Improvement of user experience using virtual reality in open-architecture product design: