141 Hits in 2.2 sec

European Car Safety

Shin-Jye Lee, Ching-Hsun Tseng, Ying-Yi Chou, Hsueh-Cheng Liu
2021 International Journal of Social Relevance & Concern  
Due to the speedy progression of vehicles technology, the assessment of car safety has become an increasing issue in the latest decade. To reflect the technology of car safety, a great diversity of new car assessment programme has been developed for the purpose of more ensuring the occupant safety as well as pedestrian safety. The Euro New Car Assessment Program (NCAP) aims to encourage the significant safety improvement to new car design, and a strict and complete NCAP can either enhance
more » ... nt safety or ensure adequate pedestrian safety. Thus, either the occupant safety or the pedestrian safety has to be seriously considered for the further assessment of NCAP in the future.
doi:10.26821/ijsrc.9.2.2021.9211 fatcat:wjhfmywwqfcfzmvipdoeh2qlwq

Regional Population Forecast and Analysis Based on Machine Learning Strategy

Chian-Yue Wang, Shin-Jye Lee
2021 Entropy  
Regional population forecast and analysis is of essence to urban and regional planning, and a well-designed plan can effectively construct a sound national infrastructure and stabilize positive population growth. Traditionally, either urban or regional planning relies on the opinions of demographers in terms of how the population of a city or a region will grow. Multi-regional population forecast is currently possible, carried out mainly on the basis of the Interregional Cohort-Component model.
more » ... While this model has its unique advantages, several demographic rates are determined based on the decisions made by primary planners. Hence, the only drawback for cohort-component type population forecasting is allowing the analyst to specify the demographic rates of the future, and it goes without saying that this tends to introduce a biased result in forecasting accuracy. To effectively avoid this problem, this work proposes a machine learning-based method to forecast multi-regional population growth objectively. Thus, this work, drawing upon the newly developed machine learning technology, attempts to analyze and forecast the population growth of major cities in Taiwan. By effectively using the advantage of the XGBoost algorithm, the evaluation of feature importance and the forecast of multi-regional population growth between the present and the near future can be observed objectively, and it can further provide an objective reference to the urban planning of regional population.
doi:10.3390/e23060656 pmid:34073825 fatcat:hfg5nv4bhrbajmlpbo2j34cegm

Perturbated Gradients Updating within Unit Space for Deep Learning [article]

Ching-Hsun. Tseng, Liu-Hsueh. Cheng, Shin-Jye. Lee, Xiaojun Zeng
2022 arXiv   pre-print
In deep learning, optimization plays a vital role. By focusing on image classification, this work investigates the pros and cons of the widely used optimizers, and proposes a new optimizer: Perturbated Unit Gradient Descent (PUGD) algorithm with extending normalized gradient operation in tensor within perturbation to update in unit space. Via a set of experiments and analyses, we show that PUGD is locally bounded updating, which means the updating from time to time is controlled. On the other
more » ... nd, PUGD can push models to a flat minimum, where the error remains approximately constant, not only because of the nature of avoiding stationary points in gradient normalization but also by scanning sharpness in the unit ball. From a series of rigorous experiments, PUGD helps models to gain a state-of-the-art Top-1 accuracy in Tiny ImageNet and competitive performances in CIFAR- 10, 100. We open-source our code at link:
arXiv:2110.00199v2 fatcat:alae662dz5bt5dqnb4dw54a5hm

Industrial Nickel Wastewater Rejection by Polyimide Membrane

Jing Ying Chuah, Kok Chung Chong, Soon Onn Lai, Woei Jye Lau, Sze Shin Lee, Hang Meng Ong
2018 Chemical Engineering Transactions  
Membrane distillation (MD) is one of the emerging thermal driven membrane separation processes in wastewater treatment attributed to its lower energy requirement and able to couple with waste heat relative to pressure driven process. In this study, polyimide was used as the polymeric materials in hollow fiber membrane fabrication whereas 1-methyl-2-pyrrolidone (NMP) was use as solvent for synthesize industrial wastewater in nickel removal. The properties of the fabricated membrane were found to
more » ... possesses the optimum characteristic in terms of LEP, porosity, inner diameter and morphology as reported in literature forthe application of DCMD. The permeate flux performance in the range of 67 to 79 kg/m2h with the rejectionrate of more than 98.80 % suggested that the PI membrane possesses the potential to be applied in the industrial wastewater treatment in nickel removal.
doi:10.3303/cet1863117 doaj:834120f027a44bfcac213e3e934ce31c fatcat:f54vz7kmovf6df4i5ddmo2u5u4

Negotiation of US Beef Imports in Taiwan

Shin-Jye Lee, Hsueh-Cheng Liu, Ching-Hsun Tseng, Ying-Yi Chou
2021 International Journal of Social Relevance & Concern  
US beef imports in Taiwan is always a popular issue of how to make an optimal negotiation under a complete trade-off. A potential 'non-obvious' solution or creative compromise based on the integrative bargaining is that Taiwan government may imports conditional U.S. beef (boneless beef and cow internal organs, except beef mince), and the U.S. government may offer the visa free of the U.S. entering (after one year) and provide the advanced military procurement (more advanced military equipment) in the next military procurement.
doi:10.26821/ijsrc.9.4.2021.9417 fatcat:4thb4uaehvah3mq3ibmcroukne

A Deep Learning Based Strategy to the Energy Prediction

Cian-Hua Chen, Shin-Jye Lee, Ching-Hsun Tseng
2021 International Journal of Software & Hardware Research in Engineering  
With the high industrialization in a rapid pace, optimizing the production and distribution of energy has become a popular issue in this century. As for the energy planning, the analysis of supply usually starts from the perspective of the supplier that takes into account production at the minimum cost while meeting demand. On the other hand, the analysis of demand gradually draws much more attention in recent years, as it mainly focuses on finding out the demand pattern. Inasmuch as the rapid
more » ... rogression of AI technology in the industrial field, the application of AI technology in the technology management has become an increasing issue as an interdisciplinary study. To fulfill this advanced analysis in an intelligent way, this work focuses on the analysis of demand starting from predicting the demand for energy by deep learning. This work predicts the future energy demand by giving historical production data to the neural network and estimates the energy demand. Once the energy demand is predicted through the proposed method, the enterprise can use it as a basis for the decision making of production policy or investing policy.
doi:10.26821/ijshre.9.3.2021.9305 fatcat:ur4yr72i4zbpblnqdkzu3yutmu

A Machine Learning Based Strategy to theOptimized Investment Portfolio

Wei-Ju Chiu, Shin-Jye Lee, Ching-Hsun Tseng
2021 International Journal of Software & Hardware Research in Engineering  
Cash flow is the key leading companies to go further, like blood flowing in us. We need to face for those fixed cost and variable costs. But the source of the funds are always happened to be ignored by the founders in practical experience. They consider technique and creativity to be more essential. According to CB Insights's analysis on those failed startup companies, lacking of funds is the second reason that caused their companies to shut down. For startup companies, the way to increase
more » ... tment funds is a significance issue. The way to use limited flow on investment will play an important role in how long they can keep a startup company alive. We would like to find the most optimized portfolio of affordable risk with comparatively high return to others. Using quantitative research and algorithms for machine learning to analyze which portfolio will be the best choice for those startup companies. Furthermore, we would dynamic adjust the factors in the algorithms for each period. Startups need to figure out how much they can earn in their business model. Processes on financing are always consuming more time than we assumed. Founders are always reserving enough time for turnover, and getting more source of funds to survive from the markets.
doi:10.26821/ijshre.9.3.2021.9307 fatcat:mfahm4hr2jcztbo47o7qf3wabe

Editorial: Recent advances in artificial neural networks and embedded systems for multi-source image fusion

Xin Jin, Jingyu Hou, Shin-Jye Lee, Dongming Zhou
2022 Frontiers in Neurorobotics  
Editorial on the Research Topic Recent advances in artificial neural networks and embedded systems for multi-source image fusion In the first work entitled "Multi-Focus Color Image Fusion Based on Quaternion Multi-Scale Singular Value Decomposition (QMSVD)", Wan et al. employed multichannel quaternion multi-scale singular value to decompose the multi-focus color images, and a set of low-frequency and high-frequency sub-images was obtained. The
doi:10.3389/fnbot.2022.962170 fatcat:gjrefhvxqzayrpalphnxrw7z2y

The Solution to the Problem of Count-toInfinity in Network Routing

Shin-Jye Lee, Ching-Hsun Tseng, Hsueh-Cheng Liu
2021 International Journal of Software & Hardware Research in Engineering  
Routing algorithms are worked between routers to determine paths and maintain routing tables. Once the path is determined, routers can route routing protocols with other routers in the whole topology. As a whole, a proper routing protocol cannot only reduce the loading of the traffic in the Network Layer, but also can improve the performance of the entire network. In this work, to fulfil the aforementioned goal, we propose a topology which combines algorithms and protocols into a one integrated
more » ... solution to fix count-to-infinity problem in network routing.
doi:10.26821/ijshre.9.3.2021.9318 fatcat:zlieaix5vjbqjbokhv5jcf442u

A Boosting Regression Based Method to Evaluate the Vital Essence in Semiconductor Industry Performance

Ping-Yu Hsu, I-Wen Yeh, Ching-Hsun Tseng, Shin-Jye Lee
2020 IEEE Access  
In accordance with the statistical analysis, the industrial performance is usually related to research and development (R&D) intensity, and this factor indeed plausibly brings the biggest profit with patents and supporting products to the development of semiconductor industry. How to evaluate the completive performance of modern industries is an increasing issue, especially for the semiconductor industries in these decades. However, almost every traditional statistical model is deterred by the
more » ... ypothesis of population and independent correlation among each feature, and this makes the result of typical regression model potentially lose reliability. To avoid this weakness, this paper therefore applies a gradient boosting based method -XGBoost to evaluate the feature importance of semiconductor industries. In the simulation experiments, different findings revel certain information, apart from R&D intensity, actually sway the gross net value in the annual financial announcement of semiconductor industries. Moreover, this paper proposes another concept to evaluate the essential factor contributing the development of semiconductor industries. Instead of only focusing on the effect of R&D intensity, this paper also predicts the future growth rate (GR) of net value by applying the greedy search of XGBoost Regression.
doi:10.1109/access.2020.3019332 fatcat:ya5qq664x5fthpslhkhwqf3kre

A Modular Method for Estimating Null Values in Relational Database Systems

Shin-Jye Lee, Xiaojun Zeng
2008 2008 Eighth International Conference on Intelligent Systems Design and Applications  
Furthermore, the Shin-Jye Lee is with the School of Computer Science, University of Manchester, Kilburn Building, Oxford Road, Manchester M13 9PL, UK (email:  ...  Hui-Shin Wang.  ...  Author Biographies Shin-Jye Lee  ... 
doi:10.1109/isda.2008.194 dblp:conf/isda/LeeZ08 fatcat:54ljbrgitjbeno4nz3xtyv3qty

UPANets: Learning from the Universal Pixel Attention Networks [article]

Ching-Hsun Tseng, Shin-Jye Lee, Jia-Nan Feng, Shengzhong Mao, Yu-Ping Wu, Jia-Yu Shang, Mou-Chung Tseng, Xiao-Jun Zeng
2021 arXiv   pre-print
Among image classification, skip and densely-connection-based networks have dominated most leaderboards. Recently, from the successful development of multi-head attention in natural language processing, it is sure that now is a time of either using a Transformer-like model or hybrid CNNs with attention. However, the former need a tremendous resource to train, and the latter is in the perfect balance in this direction. In this work, to make CNNs handle global and local information, we proposed
more » ... ANets, which equips channel-wise attention with a hybrid skip-densely-connection structure. Also, the extreme-connection structure makes UPANets robust with a smoother loss landscape. In experiments, UPANets surpassed most well-known and widely-used SOTAs with an accuracy of 96.47% in Cifar-10, 80.29% in Cifar-100, and 67.67% in Tiny Imagenet. Most importantly, these performances have high parameters efficiency and only trained in one customer-based GPU. We share implementing code of UPANets in
arXiv:2103.08640v2 fatcat:jlh6oumobzfbfgjzbsgx6gjdte

A Deep Learning Based Strategy to Promote the Performance of Project Management

Yo-Hsien Chen, Shin-Jye Lee, Ching-Hsun Tseng
2021 International Journal of Software & Hardware Research in Engineering  
REFERENCE [ 1 ] 1 Lee, S. -J. #, Lin, G. T. -R. and Hsi, P. -H. (2017). Industrial Cluster Development and Its Contribution to Economic Growth in Taiwan -Hsinchu Science and Industrial Park.  ... 
doi:10.26821/ijshre.9.3.2021.9306 fatcat:g6qva3j2ffcvffj7hoekjku4ey

Traffic Sign Recognition by Combining Global and Local Features Based on Semi-supervised Classification

Zhenli He, Fengtao Nan, Xinfa Li, Shin-Jye Lee, Yun Yang
2019 IET Intelligent Transport Systems  
The legibility of traffic signs has been considered from the beginning of design, and traffic signs are easy to identify for humans. For computer systems, however, identifying traffic signs still poses a challenging problem. Both image-processing and machine-learning algorithms are constantly improving, aimed at better solving this problem. However, with a dramatic increase in the number of traffic signs, labelling a large amount of training data means high cost. Therefore, how to use a small
more » ... mber of labelled traffic sign data reasonably to build an efficient and high-quality traffic sign recognition (TSR) model in the Internet-of-things-based (IOT-based) transport system has been an urgent research goal. Here, the authors propose a novel semi-supervised learning approach combining global and local features for TSR in an IOT-based transport system. In their approach, histograms of oriented gradient, colour histograms (CH), and edge features (EF) are used to build different feature spaces. Meanwhile, on the unlabelled samples, a fusion feature space is found to alleviate the differences between different feature spaces. Extensive evaluations on a collection of signs from the German Traffic Sign Recognition Benchmark (GTSRB) dataset shows that the proposed approach outperforms the others and provides a potential solution for practical applications.
doi:10.1049/iet-its.2019.0409 fatcat:kotnw6zmxrhtbfgetgzhazqhmy

A Machine Learning Based Strategy to Support Decision Making of Open Innovation

Yang Huang, Shin-Jye Lee, Ching-Hsun Tseng
2021 International Journal of Software & Hardware Research in Engineering  
Lee, etc. constructed a causal model of the interaction model between direct and autonomous learning, and developed a mathematical model for it, and applied it to the target.  ... 
doi:10.26821/ijshre.9.3.2021.9304 fatcat:rve3y4m3t5hi7a6w7vfaopugre
« Previous Showing results 1 — 15 out of 141 results