學術出版;;Publications

Permanent URI for this communityhdl:11536/1

收集所有交通大學研究人員與學生個人或團體所發表之各項學術著作，涵蓋期刊論文、教師專書、學位論文等項。;;Collections of Publications of NCTU Researchers and Students Like Journal Papers and Thesis.

Browse

🏛️國立陽明交通大學機構典藏

Search Results

Now showing 1 - 10 of 20

RiceTalk: Rice Blast Detection Using Internet of Things and Artificial Intelligence Technologies
(2020-02-01)
Chen, Wen-Liang
;
Lin, Yi-Bing
;
Ng, Fung-Ling
;
Liu, Chun-You
;
Lin, Yun-Wei
Rice blast is one of the most serious plant diseases. Many rice blast management approaches require know-how of experienced farmers or agronomists. Monitoring the farm for disease detection is labor intensive and time consuming. By using the Internet of Things (IoT) and artificial intelligence (AI), we are able to detect plant diseases more efficiently. Existing AI and IoT studies detect plant diseases by images or nonimage hyperspectral data, which require manual operations to obtain the photographs or data for analysis. Also, image detection typically is too late as rice blast may already spread to other plants. Based on an IoT platform for soil cultivation, we develop the RiceTalk project that utilizes nonimage IoT devices to detect rice blast. Unlike the image-based plant disease detection approaches, our agriculture sensors generate nonimage data that can be automatically trained and analyzed by the AI mechanism in real time. The beauty of RiceTalk is that the AI model is treated as an IoT device and is managed like other IoT devices. In this way, our approach significantly reduces the platform management cost to provide real-time training and predictions. We also propose an innovative spore germination mechanism as a new feature extraction model for agriculture. In the current implementation, the accuracy of the RiceTalk prediction on rice blast is 89.4%.
Intelligent compilation of patent summaries using machine learning and natural language processing techniques
(2020-01-01)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Wu, Jheng-Long
;
Wang, Jack W. C.
;
管理科學系
Patents are a type of intellectual property with ownership and monopolistic rights that are publicly accessible published documents, often with illustrations, registered by governments and international organizations. The registration allows people familiar with the domain to understand how to re-create the new and useful invention but restricts the manufacturing unless the owner licenses or enters into a legal agreement to sell ownership of the patent. Patents reward the costly research and development efforts of inventors while spreading new knowledge and accelerating innovation. This research uses artificial intelligence natural language processing, deep learning techniques and machine learning algorithms to extract the essential knowledge of patent documents within a given domain as a means to evaluate their worth and technical advantage. Manual patent abstraction is a time consuming, labor intensive, and subjective process which becomes cost and outcome ineffective as the size of the patent knowledge domain increases. This research develops an intelligent patent summarization methodology using artificial intelligence machine learning approaches to allow patent domains of extremely large sizes to be effectively and objectively summarized, especially for cases where the cost and time requirements of manual summarization is infeasible. The system learns to automatically summarize patent documents with natural language texts for any given technical domain. The machine learning solution identifies technical key terminologies (words, phrases, and sentences) in the context of the semantic relationships among training patents and corresponding summaries as the core of the summarization system. To ensure the high performance of the proposed methodology, ROUGE metrics are used to evaluate precision, recall, accuracy, and consistency of knowledge generated by the summarization system. The Smart machinery technologies domain, under the sub-domains of control intelligence, sensor intelligence and intelligent decision-making provide the case studies for the patent summarization system training. The cases use 1708 training pairs of patents and summaries while testing uses 30 randomly selected patents. The case implementation and verification have shown the summary reports achieve 90% and 84% average precision and recall ratios respectively.
Development and Validation of an EEG-Based Real-Time Emotion Recognition System Using Edge AI Computing Platform With Convolutional Neural Network System-on-Chip Design
(2019-12-01)
Fang, Wai-Chi
;
Wang, Kai-Yen
;
Fahier, Nicolas
;
Ho, Yun-Lung
;
Huang, Yu-De
This study proposed an electroencephalogram (EEG)-based real-time emotion recognition hardware system architecture based on multiphase convolutional neural network (CNN) algorithm implemented on a 28-nm technology chip and on field programmable gate array (FPGA) for binary and quaternary classification. Sample entropy, differential asymmetry, short-time Fourier transform, and a channel reconstruction method were used for emotion feature extraction. In this work, six EEG channels were selected (FP1, FP2, F3, F4, F7, and F8), and EEG images were generated from spectrogram fusions. The complete CNN architecture included training and acceleration for efficient artificial intelligence (AI) edge application, and we proposed a multiphase CNN execution method to accommodate hardware resource constraints. Datasets of 32 subjects from the DEAP database were used to validate the proposed design, exhibiting mean accuracies for valance binary classification and valance-arousal quaternary classification of 83.36% and 76.67%, respectively. The core area and total power consumption of the CNN chip were 1.83 x 1.83 mm(2), respectively, and 76.61 mW. The chip operation was validated using ADVANTEST V93000 PS1600, and the training process and real-time classification processing time took 0.12495 ms and 0.02634 ms for each EEG image, respectively. The proposed EEG-based realtime emotion recognition system included a dry electrode EEG headset, feature extraction processor, CNN chip platform, and graphical user interface, and the execution time costed 450 ms for each emotional state recognition.
Merging anomalous data usage in wireless mobile telecommunications: Business analytics with a strategy-focused data-driven approach for sustainability
(2020-03-16)
Chen, Yi-Ting
;
Sun, Edward W.
;
Lin, Yi-Bing
;
資訊工程學系
;
Department of Computer Science
Mobile internet usage has exploded with the mass popularity of smartphones that offer more convenient and efficient ways of doing anything from watching movies, playing games, and streaming music. Understanding the patterns of data usage is thus essential for strategy-focused data-driven business analytics. However, data usage has several unique stylized facts (such as high dimensionality, heteroscedasticity, and sparsity) due to a great variety of user behaviour. To manage these facts, we propose a novel density-based subspace clustering approach (i.e., a three-stage iterative optimization procedure) for intelligent segmentation of consumer data usage/demand. We discuss the characteristics of the proposed method and illustrate its performance in both simulation with synthetic data and business analytics with real data. In a field experiment of wireless mobile telecommunications for data-driven strategic design and managerial implementation, we show that our method is adequate for business analytics and plausible for sustainability in search of business value. (C) 2019 Published by Elsevier B.V.
Physics-Prior Bayesian Neural Networks in Semiconductor Processing
(2019-01-01)
Chen, Chun Han
;
Parashar, Parag
;
Akbar, Chandni
;
Fu, Sze Ming
;
Syu, Ming-Ying
With the fast scaling-down and evolution of integrated circuit (IC) manufacturing technology, the fabrication process becomes highly complex, and the experimental cost of the processes is significantly elevated. Therefore, in many cases, it is very costly to obtain a sufficient amount of experimental data. To develop an efficient method to predict the results of semiconductor experiments with a small amount of known data, we use a novel method based on Bayesian framework with the prior distribution constructed by technology computer-aided-design (TCAD) physical models. This method combines the advantages of statistical models and physical models in the aspect that TCAD can provide visionary guidance on an experiment when a limited amount of experimental data is available, and a machine learning model can account for subtle anomalous effects. Specifically, we use aspect ratio dependent etching (ARDE) phenomenon as an example and use variational inference with Kullback-Leibler divergence minimization to achieve the approximation to the posterior distribution. The relation between etching process input parameters and etching depth is learned using the Bayesian neural network with TCAD priors. Using this method with 35 neurons per hidden layer, mean square error (MSE) in the test set is reduced from 0.2896 to 0.0175, 0.058 to 0.0183, 0.0563 to 0.0188, 0.058 to 0.019 for partition =10, 20, 30, 40, respectively, reference to the baseline BNN where a regular normal distribution prior with zero mean and unity standard deviation N(0,1) is used.
Stylized algorithmic trading: satisfying the predictive near-term demand of liquidity
(2019-10-01)
Sun, Edward W.
;
Kruse, Timm
;
Chen, Yi-Ting
;
資訊工程學系
;
Department of Computer Science
Regulatory reform enacted (e.g., the Dodd-Frank Act enforced in the U.S.) requires the financial service industry to consider the "reasonably expected near term demand" (i.e., RENTD) in trading. To manage the price impact and transaction cost associated with orders submitted to an order driven market, market makers or specialists must determine their trading styles (aggressive, neutral, or passive) based on the market liquidity in response to RENTD, particularly for trading a large quantity of some financial instrument. In this article we introduce a model considering different trading styles to satisfy the predictive near-term customer demand of market liquidity in order to find an optimal order submission strategy based on different market situations. We show some analytical properties and numerical performances of our model in search of optimal solutions. We evaluate the performances of our model with simulations run over a set of experiments in comparison with two alternative strategies. Our results suggest that the proposed model illustrates superiority in performance.
An Intelligent Patent Summary System Deploying Natural Language Processing and Machining Learning
(2018-01-01)
Trappey, A. J. C.
;
Trappey, C. V.
;
Wang, J. W. -C.
;
Wu, J. -L.
;
管理科學系
With the growing awareness of the fourth industrial revolution and its implication, there are increasing applications of artificial intelligence to secure the value of intellectual property (IP), to develop competitive products, and to license IP. Natural language processing based on artificial intelligence methods have not been sufficiently developed and there remain many obstacles for current researchers to interpret the meaning of large numbers of intellectual property documents. The means to explain the related intellectual property documents (e.g. products in a given domain) and summarize sets of remain a significant challenge. In this research, we develop an intelligent patent summarization system based on artificial intelligence approaches that include Recurrent Neural Network (RNN), Word Embedding, and Attention Mechanisms. The aim of this system is to automatically summarize technical documents in a specific patent domain and identify potential opportunities or liabilities for R & D engineers, lawyers, and managers. The AI-based experiment-based solution for summarization is used to capture the key technique keywords, popular technical terms, and new technical terms. The compression ratios and the retention ratios are used to evaluate the density and consistency of critical information for the proposed summarization system and to measure the quality of the summary system output.
AgriTalk: IoT for Precision Soil Farming of Turmeric Cultivation
(2019-06-01)
Chen, Wen-Liang
;
Lin, Yi-Bing
;
Lin, Yun-Wei
;
Chen, Robert
;
Liao, Jyun-Kai
This paper proposes AgriTalk, an inexpensive Internet of Things (IoT) platform for precision farming of soil cultivation. We conduct experiments on turmeric cultivation, which indicates that the turmeric quality is significantly enhanced through AgriTalk. Specifically, the curcumin concentration is up to 4500-5500 mg/100 g, which is five times more than existing products. We demonstrate how to intuitively configure the connections between the sensors and the actuators with the desired farming intelligence, and to effectively maintain AgriTalk for precision farming. We conduct measurement, analytic analysis, and simulation experiments to investigate the IoT message delays of AgriTalk. This paper indicates that the delays for automatic control and automatic-manual control switching with long distances (more than 30 km) are very short (less than 0.2 s) and AgriTalk can easily respond to quick and dynamic change of the field environment conditions in soil cultivation.
A fall detection system using k-nearest neighbor classifier
(2010-10-01)
Liu, Chien-Liang
;
Lee, Chia-Hoang
;
Lin, Ping-Min
;
資訊工程學系
;
Department of Computer Science
The main purpose of this paper is to use off-the-shelf devices to develop a fall detection system. In human body identification, human body silhouette is adopted to improve privacy protection, and vertical projection histograms of the silhouette image and statistical scheme are used to reduce the effect of human body upper limb activities. The kNN classification algorithm is used to classify the postures using the ratio and difference of human body silhouette bounding box height and width. Meanwhile, since time difference is a vital factor to differentiate fall incident event and lying down event, the critical time difference is obtained from the experiment and verified by statistical hypothesis testing. With the help of the kNN classifier and the critical time difference, a fall incident detection system is developed to detect fall incident events. The experiment shows that it could reduce the effect of upper limb activities and the system has a correct rate of 84.44% on fall detection and lying down event detection. (C) 2010 Elsevier Ltd. All rights reserved.
A Dual-Mode Learning Mechanism Combining Knowledge-Education and Machine-Learning
(2008)
Chen, Yichang
;
Chen, Anpin
;
資訊管理與財務金融系註：原資管所+財金所
;
Department of Information Management and Finance
From 1956, the definitions of learning according to Artificial Intelligence and Psychology to human mind/behavior are obviously different. Owing to the rapid development of the computing power, we have potential to enhance the learning mechanism of AI. This work tries to discuss the learning process from the traditional AI learning models which are almost based on trial and error style. Furthermore, some relative literatures have pointed out that teaching-base education would increase the learning efficiency better than trial and error style. That is the reason we enhance the learning process to propose a dual-perspective learning mechanism, E&R-R XCS. As for XCS is a better accuracy model of AI, we have applied it as a basement and proposed to develop an intelligence-learning model. Finally, this work will give the inference discussion about the accuracy and accumulative performance of XCS, R-R XCS, and E&R-R XCS respectively, and the obvious summary would be concluded. That is, the proposed dual-learning mechanism has enhanced successfully.

學術出版;;Publications

Browse

Filters

Settings

Sort By

Results per page

🏛️國立陽明交通大學機構典藏

Search Results