• 전자통신동향분석
• /
• 제33권5호
• /
• pp.103-110
• /
• 2018

Studies on artificial intelligence have been developed for the past couple of decades. After a few periods of prosperity and recession, a new machine learning method, so-called Deep Learning, has been introduced. This is the result of high-quality big- data, an increase in computing power, and the development of new algorithms. The main targets for deep learning are 1D audio and 2D images. The application domain is being extended from a discriminative model, such as classification/segmentation, to a generative model. Currently, deep learning is used for processing 3D data. However, unlike 2D, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become more popular owing to advances in 3D vision technology, the generation/acquisition of 3D data remains a very difficult problem. Moreover, it is not easy to directly apply an existing network model, such as a convolution network, owing to the variety of 3D data representations. In this paper, we summarize the 3D deep learning technology that have started to be developed within the last 2 years.

• 전자통신동향분석
• /
• 제33권5호
• /
• pp.121-134
• /
• 2018

The Von Neumann based architecture of the modern computer has dominated the computing industry for the past 50 years, sparking the digital revolution and propelling us into today's information age. Recent research focus and market trends have shown significant effort toward the advancement and application of artificial intelligence technologies. Although artificial intelligence has been studied for decades since the Turing machine was first introduced, the field has recently emerged into the spotlight thanks to remarkable milestones such as AlexNet-CNN and Alpha-Go, whose neural-network based deep learning methods have achieved a ground-breaking performance superior to existing recognition, classification, and decision algorithms. Unprecedented results in a wide variety of applications (drones, autonomous driving, robots, stock markets, computer vision, voice, and so on) have signaled the beginning of a golden age for artificial intelligence after 40 years of relative dormancy. Algorithmic research continues to progress at a breath-taking pace as evidenced by the rate of new neural networks being announced. However, traditional Von Neumann based architectures have proven to be inadequate in terms of computation power, and inherently inefficient in their processing of vastly parallel computations, which is a characteristic of deep neural networks. Consequently, global conglomerates such as Intel, Huawei, and Google, as well as large domestic corporations and fabless companies are developing dedicated semiconductor chips customized for artificial intelligence computations. The AI Processor Research Laboratory at ETRI is focusing on the research and development of super low-power AI processor chips. In this article, we present the current trends in computation platform, parallel processing, AI processor, and super-threaded AI processor research being conducted at ETRI.

• Journal of Computational Design and Engineering
• /
• 제3권2호
• /
• pp.91-101
• /
• 2016

The automated part quality inspection poses many challenges to the engineers, especially when the part features to be inspected become complicated. A large quantity of part inspection at a faster rate should be relied upon computerized, automated inspection methods, which requires advanced quality control approaches. In this context, this work uses innovative methods in remote part tracking and quality control with the aid of the modern equipment and application of support vector machine (SVM) learning approach to predict the outcome of the quality control process. The classifier equations are built on the data obtained from the experiments and analyzed with different kernel functions. From the analysis, detailed outcome is presented for six different cases. The results indicate the robustness of support vector classification for the experimental data with two output classes.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2009년도 세계 도시지반공학 심포지엄
• /
• pp.1522-1529
• /
• 2009

When a shaft is excavated in Korea, the mechanized method such as RBM(Raise Boring Machine) or RC(Raise Climber) is used independently of depth. But usually, the mechanized method is useful for the deep depth. On the contrary, when the depth of shaft is short, the cost of excavation increase. So in the case of shaft constructon less than 100m, we need to consider more suitable method of shaft construction such as Stage-cut which is one of blasting methods. Stage-Cut is widely used in the field of shaft construction in Japan as a tool of rock excavation. The main purpose of this study is to provide technical guidance for design and construction of shafts in rock, using Stage-cut method which is suitable for 20m~80m depth shaft. In this study, Blasting tests was performed in field, according to rock classification. Finally, the stage-cut method which is suitable for the geology of Korea was developed.

• 제어로봇시스템학회논문지
• /
• 제12권12호
• /
• pp.1178-1183
• /
• 2006

This paper is concerned with the modeling and identification of pH neutralization process as nonlinear chemical system. The pH control has been applied to various chemical processes such as wastewater treatment, chemical, and biochemical industries. But the control of the pH is very difficult due to its highly nonlinear nature which is the titration curve with the steepest slope at the neutralization point. We apply SVM which have become an increasingly popular tool for machine teaming tasks such as classification, regression or detection to model pH process which has strong nonlinearities. Linear and radial basis function kernels are employed and each result has been compared. So SVH based on kernel method have been found to work well. Simulations have shown that the SVM based on the kernel substitution including linear and radial basis function kernel provides a promising alternative to model strong nonlinearities of the pH neutralization but also to control the system.

• 제어로봇시스템학회논문지
• /
• 제21권11호
• /
• pp.1008-1016
• /
• 2015

This paper proposes a method for detecting the front side of vehicles. The method can find the car side with a license plate even with complicated and cluttered backgrounds. A convolutional neural network (CNN) is used to solve the detection problem as a unified framework combining feature detection, classification, searching, and localization estimation and improve the reliability of the system with simplicity of usage. The proposed CNN structure avoids sliding window search to find the locations of vehicles and reduces the computing time to achieve real-time processing. Multiple responses of the network for vehicle position are further processed by a weighted clustering and probabilistic threshold decision method. Experiments using real images in parking lots show the reliability of the method.

• 반도체디스플레이기술학회지
• /
• 제10권2호
• /
• pp.31-38
• /
• 2011

This paper introduces a video based traffic monitoring system for detecting vehicles and obstacles on the road. To segment moving objects from image sequence, we adopt the background subtraction algorithm based on the local binary patterns (LBP). Recently, LBP based texture analysis techniques are becoming popular tools for various machine vision applications such as face recognition, object classification and so on. In this paper, we adopt an extension of LBP, called the Diagonal LBP (DLBP), to handle the background subtraction problem arise in vision-based autonomous parking systems. It reduces the code length of LBP by half and improves the computation complexity drastically. An edge based shadow removal and blob merging procedure are also applied to the foreground blobs, and a pose estimation technique is utilized for calculating the position and heading angle of the moving object precisely. Experimental results revealed that our system works well for real-time vehicle localization and tracking applications.

• Journal of Information Science Theory and Practice
• /
• 제3권1호
• /
• pp.6-23
• /
• 2015

This study develops an effective method for sentiment analysis of user-generated content on drug review websites, which has not been investigated extensively compared to other general domains, such as product reviews. A clause-level sentiment analysis algorithm is developed since each sentence can contain multiple clauses discussing multiple aspects of a drug. The method adopts a pure linguistic approach of computing the sentiment orientation (positive, negative, or neutral) of a clause from the prior sentiment scores assigned to words, taking into consideration the grammatical relations and semantic annotation (such as disorder terms) of words in the clause. Experiment results with 2,700 clauses show the effectiveness of the proposed approach, and it performed significantly better than the baseline approaches using a machine learning approach. Various challenging issues were identified and discussed through error analysis. The application of the proposed sentiment analysis approach will be useful not only for patients, but also for drug makers and clinicians to obtain valuable summaries of public opinion. Since sentiment analysis is domain specific, domain knowledge in drug reviews is incorporated into the sentiment analysis algorithm to provide more accurate analysis. In particular, MetaMap is used to map various health and medical terms (such as disease and drug names) to semantic types in the Unified Medical Language System (UMLS) Semantic Network.

• Journal of Information Processing Systems
• /
• 제16권3호
• /
• pp.718-732
• /
• 2020

Conducting sentiment analysis and opinion mining are challenging tasks in natural language processing. Many of the sentiment analysis and opinion mining applications focus on product reviews, social media reviews, forums and microblogs whose reviews are topic-similar and opinion-rich. In this paper, we try to analyze the sentiments of sentences from online webcast reviews that scroll across the screen, which we call live barrages. Contrary to social media comments or product reviews, the topics in live barrages are more fragmented, and there are plenty of invalid comments that we must remove in the preprocessing phase. To extract evaluative sentiment sentences, we proposed a novel approach that clusters the barrages from the same commenter to solve the problem of scattering the information for each barrage. The method developed in this paper contains two subtasks: in the data preprocessing phase, we cluster the sentences from the same commenter and remove unavailable sentences; and we use a semi-supervised machine learning approach, the naïve Bayes algorithm, to analyze the sentiment of the barrage. According to our experimental results, this method shows that it performs well in analyzing the sentiment of online webcast barrages.

• 정보처리학회지
• /
• 제11권6호
• /
• pp.56-75
• /
• 2004

In this article we address some system characteristics and challenging issues in developing Context-aware Middleware for Ubiquitous Computing. The functionalities of a Context-aware Middleware includes gathering context data from hardware/software sensors, reasoning and inferring high-level context data, and disseminating/delivering appropriate context data to interested applications/services. The Middleware should facilitate the query, aggregation, and discovery for the contexts, as well as facilities to specify their privacy policy. Following a formal context model using ontology would enable syntactic and semantic interoperability, and knowledge sharing between different domains. Moddleware should also provide different kinds of context classification mechanical as pluggable modules, including rules written in different types of logic (first order logic, description logic, temporal/spatial logic, fuzzy logic, etc.) as well as machine-learning mechanical (supervised and unsupervised classifiers). Different mechanisms have different power, expressiveness and decidability properties, and system developers can choose the appropriate mechanism that best meets the reasoning requirements of each context. And finally, to promote the context-trigger actions in application level, it is important to provide a uniform and platform-independent interface for applications to express their need for different context data without knowing how that data is acquired. The action could involve adapting to the new environment, notifying the user, communicating with another device to exchange information, or performing any other task.