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 58

Web Mining Customer Perceptions to Define Product Positions and Design Preferences
(2020-04-01)
Chang, Ai-Che
;
Trappey, Charles, V
;
Trappey, Amy J. C.
;
Chen, Luna W. L.
;
交大名義發表
E-commerce provides a global platform supporting product transactions through the consumer purchase lifecycle including communications of perceived satisfaction and dissatisfaction. The customer feedback functions and social networks of many e-commerce websites allow for the creation of extremely large databases that can be mined to model the customers' perceptions toward online purchases. This research uses online customer reviews as the business intelligence corpus to help companies redesign products that better satisfy consumer preferences and differentiate their product offerings. After identifying the specific webpages of customer reviews, a web crawler collects review text. Computer-supported text mining, cluster analysis, and perceptual mapping are combined as a systematic analytic approach to compare products in a given domain. The study assists phone manufacturers to understand the positive and negative perceptions of customers related to their post-purchase experiences. The customer-preferred product functions, features, and price positions provide valuable strategic intelligence for new product designs and market differentiation.
Intelligent trademark similarity analysis of image, spelling, and phonetic features using machine learning methodologies
(2020-08-01)
Trappey, Charles, V
;
Trappey, Amy J. C.
;
Lin, Sam C-C
;
管理科學系
;
Department of Management Science
The rapid development of consumer products with short life spans, along with fast, global e-commerce and e-marketing distribution of products and services requires greater due diligence to protect intangible assets such as brands and corporate logos which can easily be copied or distributed through grey channels and internet sales sites. Trademarks (TMs) are government registered intellectual property rights (IPRs) used to legally protect a companies' identities and brand equity. The rapid growth of global trademark (TM) registrations and the number of TM infringement cases pose a great challenge for TM owners to detect infringement and take action to protect TMs, consumer trust, and market share. This research develops advanced TM similarity assessment models using machine learning (ML) approaches. Litigation principles over similarity follow US TM laws which are consistent with global TM protection convention under the World Intellectual Property Organization (WIPO). This research covers the similarity analysis of TM spelling, pronunciation, and images, which are most likely to cause TM confusion among customers. The research focuses on deploying machine learning for natural language (spelling and phonetic features) and image similarity analyses. The vector space modeling algorithms are trained and verified for the similarity analysis of TM wordings in both spelling and pronunciation. The convolutional neural network and Siamese neural network models are trained and verified for TM image similarity comparison. The training and testing sets consist of 250,000 and 20,000 different image pairs respectively. This research provides a significant contribution toward implementing intelligent and automated IPR protection. The system solution supports users (companies, TM attorneys, or IP officers) to identify similar registered TMs before registering new TMs ensuring uniqueness to avoid infringement disputes. The solution also supports automatic screening of online content to detect potential infringement of TM images and wording for effective global IPR protection.
Detecting Trademark Image Infringement Using Convolutional Neural Networks
(2019-01-01)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Lin, Sam C-C.
;
管理科學系
;
Department of Management Science
The rapid development of consumer products with short life spans, along with fast, global e-commerce and e-marketing distribution of products and services requires greater corporate diligence to protect intangible assets such as brands which can easily be coped or placed in grey markets. Trademarks are the government registered legal intellectual property rights (IPRs) used to protect companies' brands and build brand equity. Given the rapid growth in the number of global trademark registrations, the number of trademark infringement cases is also increasing, a great challenge for the original trademark owner to detect the infringement and takes action to protect the brand image and related commercial interests. This research develops a trademark similarity assessment methodology based on the US trademark law related to the high likelihood of confusion and associated regulations. The research focuses on identifying trade mark image similarity using a deep learning approach. The convolutional neural network (CNN) and Siamese neural network (SNN) algorithms are modeled and trained using Cifar-10 and TopLogo-10 corpuses. These corpuses consist of more than 100,000 positive image pairs and more than 150,000 negative image pairs as training data. After training the model, an image input to the model extracts and recommends similar trade mark images found in the corpus. The solution assists users registering new trademarks to identifying similar marks that may lead to disputes. The solution also automatically screens images to identify marks that potentially infringe upon registered trademarks.
Using Machine Learning Approach to Identify Synonyms for Document Mining
(2019-01-01)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Wu, Jheng-Long
;
Tsai, Kevin T. -C
;
管理科學系
Technical or knowledge documents, such as research papers, patents, and technical documents, e.g., request for quotations (RFQ), are important knowledge references for multiple purposes. For example, enterprises and R&D institutions often need to conduct literature and patent searches and analyses before, during, and after R&D and commercialization. These knowledge discovery processes help them identify prior arts related to the current R&D efforts to avoid duplicating research efforts or infringing upon existing intellectual property rights (IPRs). It is common to have many synonyms (i.e., words and phrases with near-identical meanings) appeared in documents, which may hinder search results, if queries do not consider these synonyms. For instance, conducting "freedom-to-operate" (FTO) patent search may not find all related patents if synonyms were not taking into consideration. This research develops methodologies of generating domain specific "word" and "phrase" synonym dictionaries using machine learning. The generation and validation of both domain-specific "word" and "phrase" synonym dictionaries are conducted using more than 2000 solar power related patents as testing document set. The testing result shows that, in the solar power domain, both word level and phrase level dictionaries identify synonyms effectively and, thus, significantly improve the patent search results.
Behavioral Therapy for Phobias Using Immersive Virtual Reality Technology
(2020-04-01)
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Chang, Chia-Ming
;
Govindarajan, Usharani Hareesh
;
Shih, Xyuan-Yu
Mental disorders are difficult to diagnose and treat. Global economic growth, changing social organizations, and urban conditions affect mental health resulting in increased costs, limited benefits, and fewer facilities for behavioral treatment. Virtual reality-based behavioral treatments for mental illness offer benefits to supplement conventional therapies. Virtual Reality Treatment (VRT) let patients confront phobias using a virtual environment with a therapist. A therapist observes and coaches the patient through increasingly difficult levels of confrontation to desensitize patient phobias. This research presents a generic framework and discusses the related behavioral therapy. A VRT for confronting fear of spiders is the case used for the technology development and data collection processes which establish the basis for future clinical trials and analysis. The preliminary trial of the arachnophobia VRT platform with eight scenario levels has produced accurate bio-feedback results. The system demonstrates promise for rapid VRT application development for clinical behavioral psychotherapy.
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.
E-discover State-of-the-art Research Trends of Deep Learning for Computer Vision
(2019-01-01)
Li, Annie A. S.
;
Trappey, Amy J. C.
;
Trappey, Charles V.
;
Fan, C. Y.
;
交大名義發表
Computer vision (CV) attempts to mimic human eyes for image processing and identifications of detailed visual information, such as object positions, features of appearances, and even human emotions and behaviors. In this research, more than one hundred literatures, relating to applying deep learning (DL) methodologies in advanced computer visions (2010 similar to 2018), are reviewed and analyzed. The objective is to discover the state-of-the-art DL methods, topics, and trends for CV and their practical applications. DL algorithms aim at representing multilevels of distributed neural networks. Because of the enhancement of high speed computational power, DL modeling, based on accumulated big data analytics, has found practical applications for non-supervised intelligent decision supports, such as detection of product defects and prognosis of machine malfunctions based on real-time signal or feature data analyses. There are a vast number of literature, describing DL related researches, developments, and implementations for problem solving. For the comprehensive mining of the related literature, we integrate Latent Dirichlet Allocation (LDA), K-means (Clustering), and normalized term frequency-inverse document frequency (NTF-IDF) approaches to discover, or called technology mining, of the major trends in DL for computer visions, specifically for key applications in object detection, semantic segmentation, image retrieval, and human pose estimation.
Intelligent collaborative patent mining using excessive topic generation
(2019-10-01)
Govindarajan, Usharani Hareesh
;
Trappey, Amy J. C.
;
Trappey, Charles, V
;
管理科學系
;
Department of Management Science
An inevitable consequence of the technology-driven economy has led to the increased importance of intellectual property protection through patents. Recent global pro-patenting shifts have further resulted in high technology overlaps. Technology components are now spread across a huge corpus of patent documents making its interpretation a knowledge-intensive engineering activity. Intelligent collaborative patent mining facilitates the integration of inputs from patented technology components held by diverse stakeholders. Topic generative models are powerful natural language tools used to decompose data corpus topics and associated word bag distributions. This research develops and validates a superior text mining methodology, called Excessive Topic Generation (ETG), as a preprocessing framework for topic analysis and visualization. The presented ETG methodology adapts the topic generation characteristics from Latent Dirichlet Allocation (LDA) with added capability to generate word distance relationships among key terms. The novel ETG approach is used as the core process for intelligent collaborative patent mining. A case study of 741 global Industrial Immersive Technology (ITT) patents covering inventive and novel concepts of Virtual Reality (VR), Augmented Reality (AR), and Brain Machine Interface (BMI) are systematically processed and analyzed using the proposed methodology. Based on the discovered topics of the IIT patents, patent classification (IPC/CPC) predictions are analyzed to validate the superior ETG results.
Patent Analysis of Key Technologies for Smart Retailing and their Projected Economic Impact
(2018-01-01)
Trappey, Amy J. C.
;
Wang, W. C.
;
Trappey, Charles
;
Hsieh, H. I.
;
管理科學系
With the growing population of digital users gaining online consumption power, retail industries are facing evolutionary changes in attracting and maintaining online and offline customers. The concepts and implementation of smart malls and retail shops are proposed by retailers or solution providers to satisfy new customer demands. The foundation of smart retailing includes information integration, customer experience, and e-transactions. This research investigates the economic impact of smart retailing and the growth of related intellectual properties (IPs), specifically, the retail domain online related patents. The technological aspect of smart retailing is organized by constructing a patent ontology map to define the domain boundary. The economic impact of technological transformations is studied by measuring the economic growth of the leading regions and countries and the representative patent assignees. Consumption preferences and labor structure changes in relation to the retail industry are analyzed to verify the economic impact of corresponding intellectual properties. The goal of the research is to develop regional development strategies for smart retailing using global patent and economic impact analyses.
Patent Analytics of Robotics Technology for Intelligent Manufacturing in the Semiconductor Industry
(2018-01-01)
Chen, Paul P. J.
;
Trappey, Amy J. C.
;
Lin, Betty H. L.
;
Trappey, Charles V.
;
管理科學系
Manufacturers are making a transition to intelligent production, particularly in high-tech industries. Robotic arms play a crucial role in the effectiveness of transforming processes. This research searches and analyzes patents related to robotic arms utilized by intelligent manufacturing systems. For this preliminary study, global patent trends are discussed which help evaluate the technology domain to be developed. Key words from a literature review are used to search for relevant patents, and then the patent text is analyzed using text mining software and program. The core technique applied to the patent document analysis is "Term Frequency-Inverse Document Frequency" (TF-IDF). Using TF-IDF, the patent documents are grouped into meaningful sub-technology cluster. Thus, the economic data related to the semiconductor industry is analyzed to correlate the economic impact which may be related to the transitions in technology. The data of Taiwan firms were targeted for anticipating research directions and expand intellectual property domains to invest in and pursue. For the advanced analysis, the international patent codes for global and local companies are compared. The final results help define the strength and weakness of Taiwanese robotic technology development for the semiconductor industry. Patent cluster and patent distribution analysis via a technology function matrix are the primary research approaches used for the case study. The research prepares for the development of a theoretical foundation to predict intelligent manufacturing trends.

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