• Title/Summary/Keyword: 머신 기술 언어

Search Result 45, Processing Time 0.022 seconds

Development of a Machine Learning-based Language Corrector for AI Speakers of Patients with Articulation Disorders (조음장애인용 AI스피커를 위한 머신러닝 기반 언어교정기 개발)

  • Lee, DongHeon;Moon, Mikyeong
    • Proceedings of the Korean Society of Computer Information Conference
    • /
    • 2020.07a
    • /
    • pp.371-372
    • /
    • 2020
  • 최근 인공지능의 발달로 인해 AI스피커에 대한 연구가 활발히 이루어지고 있다. 조음장애는 구강 안에서 말소리를 제대로 만들지 못해서 제대로 된 언어를 구사하지 못하는 장애를 말한다. 조음장애인들이 AI스피커를 사용하면 발음을 제대로 인식하지 못하기 때문에 사용의 어려움이 있다. 본 논문에서는 경증 조음장애인들이 AI스피커를 이용할 수 있도록 머신러닝 기반 언어교정기의 개발내용에 관하여 기술한다. 이는 언어로 명령 줄 수 있는 여러 시스템에 활용될 수 있을 것으로 기대한다.

  • PDF

Machine Learning Language Model Implementation Using Literary Texts (문학 텍스트를 활용한 머신러닝 언어모델 구현)

  • Jeon, Hyeongu;Jung, Kichul;Kwon, Kyoungah;Lee, Insung
    • The Journal of the Convergence on Culture Technology
    • /
    • v.7 no.2
    • /
    • pp.427-436
    • /
    • 2021
  • The purpose of this study is to implement a machine learning language model that learns literary texts. Literary texts have an important characteristic that pairs of question-and-answer are not frequently clearly distinguished. Also, literary texts consist of pronouns, figurative expressions, soliloquies, etc. They hinder the necessity of machine learning using literary texts by making it difficult to learn algorithms. Algorithms that learn literary texts can show more human-friendly interactions than algorithms that learn general sentences. For this goal, this paper proposes three text correction tasks that must be preceded in researches using literary texts for machine learning language model: pronoun processing, dialogue pair expansion, and data amplification. Learning data for artificial intelligence should have clear meanings to facilitate machine learning and to ensure high effectiveness. The introduction of special genres of texts such as literature into natural language processing research is expected not only to expand the learning area of machine learning, but to show a new language learning method.

Design of an Automatic Generation System for Embedded Processor Cores with Minimal Power Consumption (저전력 소모 임베디드 프로세서 코어 자동생성 시스템의 설계)

  • Kim, Dong-Won;Hwang, Sun-Young
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.32 no.10C
    • /
    • pp.1042-1050
    • /
    • 2007
  • This paper describes the system which automatically generates power-minimized embedded cores from MDL descriptions. An automatic generation system is constructed which generated embedded cores which consumes less power for application programs. From the usage information on pipeline stages for each instruction, the proposed system generates embedded cores with the capability of detecting/resolving pipeline hazards. The generated cores are configured such that the power consumption is minimized. The proposed system has been tested by generating HDL codes for ARM9, MIPS R3000 architectures. Experimental results show functional accuracy of the generated cores, and show that power reduction of $20%{\sim}40%$ has been observed for benchmark programs.

Generating Korean Sentences Using Word2Vec (Word2Vec 모델을 활용한 한국어 문장 생성)

  • Nam, Hyun-Gyu;Lee, Young-Seok
    • Annual Conference on Human and Language Technology
    • /
    • 2017.10a
    • /
    • pp.209-212
    • /
    • 2017
  • 고도화된 머신러닝과 딥러닝 기술은 영상처리, 자연어처리 등의 분야에서 많은 문제를 해결하고 있다. 특히 사용자가 입력한 문장을 분석하고 그에 따른 문장을 생성하는 자연어처리 기술은 기계 번역, 자동 요약, 자동 오류 수정 등에 널리 이용되고 있다. 딥러닝 기반의 자연어처리 기술은 학습을 위해 여러 계층의 신경망을 구성하여 단어 간 의존 관계와 문장 구조를 학습한다. 그러나 학습 과정에서의 계산양이 방대하여 모델을 구성하는데 시간과 비용이 많이 필요하다. 그러나 Word2Vec 모델은 신경망과 유사하게 학습하면서도 선형 구조를 가지고 있어 딥러닝 기반 자연어처리 기술에 비해 적은 시간 복잡도로 고차원의 단어 벡터를 계산할 수 있다. 따라서 본 논문에서는 Word2Vec 모델을 활용하여 한국어 문장을 생성하는 방법을 제시하였다. 본 논문에서는 지정된 문장 템플릿에 유사도가 높은 각 단어들을 적용하여 문장을 구성하는 Word2Vec 모델을 설계하였고, 서로 다른 학습 데이터로부터 생성된 문장을 평가하고 제안한 모델의 활용 방안을 제시하였다.

  • PDF

A Dynamic Approach to Extract the Original Semantics and Structure of VM-based Obfuscated Binary Executables (가상 머신 기반으로 난독화된 실행파일의 구조 및 원본의미 추출 동적 방법)

  • Lee, Sungho;Han, Taisook
    • Journal of KIISE
    • /
    • v.41 no.10
    • /
    • pp.859-869
    • /
    • 2014
  • In recent years, the obfuscation techniques are commonly exploited to protect malwares, so obfuscated malwares have become a big threat. Especially, it is extremely hard to analyze virtualization-obfuscated malwares based on unusual virtual machines, because the original program is hidden by the virtual machine as well as its semantics is mixed with the semantics of the virtual machine. To confront this threat, we suggest a framework to analyze virtualization-obfuscated programs based on the dynamic analysis. First, we extract the dynamic execution trace of the virtualization-obfuscated executables. Second, we analyze the traces by translating machine instruction sequences into the intermediate representation and extract the virtual machine architecture by constructing dynamic context flow graphs. Finally, we extract abstract semantics of the original program using the extracted virtual machine architecture. In this paper, we propose a method to extract the information of the original program from a virtualization-obfuscated program by some commercial obfuscation tools. We expect that our tool can be used to understand virtualization-obfuscated programs and integrate other program analysis techniques so that it can be applied to analysis of the semantics of original programs using the abstract semantics.

인공지능 워크스테이션의 개발동향 분석

  • Lee, Jin-Hyeong;Park, Seng-Kyu
    • Electronics and Telecommunications Trends
    • /
    • v.3 no.1
    • /
    • pp.77-85
    • /
    • 1988
  • 인공지능 프로그램을 효과적으로 수행시키기 위해서는 특별한 하드웨어 또는 진보된 소프트웨어 기술이 구현된 시스팀이 필요하게 된다. 1980년대 초에 Symbolics의 lisp machine이 처음 출현한 이래 dedicated architecture를 갖는 lisp machine이 지배하던 인공지능 머신은 최근 general purpose workstation에 인공지능 언어 및 환경을 갖춘 인공지능 워크스테이션이 대두됨에 따라 그 개발 경향이 옮겨가고 있다. 본고에서는 이와 같은 최근의 인공지능 워크스테이션의 개발동향 분석 및 그에 따른 인공지능 워크스테이션의 정의를 하였으며, 마지막으로 우리나라에서 이러한 인공지능 워크스테이션을 개발하기 위한 연구뱡향에 대해 기술하였다.

Implementation of R-language-based REST API and Solution for Security Issues (R 언어 기반의 REST API 구현 및 보안문제의 해결 방안)

  • Kang, DongHoon;Oh, Sejong
    • Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
    • /
    • v.9 no.1
    • /
    • pp.387-394
    • /
    • 2019
  • Recently, the importance of big data has been increased, and demand for data analysis for the big data is also increased. R language is developed for data analysis, and users are analyzing data by using algorithms of various statistics, machine learning and data mining packages in R language. However, it is difficult to develop an application using R. Early study proposed a method to call R script through another language such as PHP, Java, and so on. However, it is troublesome to write such a development method in addition to R in combination with other languages. In this study, we introduce how to write API using only R language without using another language by using Plumber package. We also propose a solution for security issues related with R API. If we use propose technology for developing web application, we can expect high productivity, easy of use, and easy of maintenance.

A Study on Finger Language Translation System using Machine Learning and Leap Motion (머신러닝과 립 모션을 활용한 지화 번역 시스템 구현에 관한 연구)

  • Son, Da Eun;Go, Hyeong Min;Shin, Haeng yong
    • Annual Conference of KIPS
    • /
    • 2019.10a
    • /
    • pp.552-554
    • /
    • 2019
  • Deaf mutism (a hearing-impaired person and speech disorders) communicates using sign language. There are difficulties in communicating by voice. However, sign language can only be limited in communicating with people who know sign language because everyone doesn't use sign language when they communicate. In this paper, a finger language translation system is proposed and implemented as a means for the disabled and the non-disabled to communicate without difficulty. The proposed algorithm recognizes the finger language data by leap motion and self-learns the data using machine learning technology to increase recognition rate. We show performance improvement from the simulation results.

Constructing Java Vulnerable API List based on Java Access Permission Checking Tree (자바 접근 권한 검사 트리 기반의 자바 취약 API 리스트 생성)

  • Park, Hyo-Seong;Park, Chul-Woo;Lim, Young-Chan;Kim, Ki-Chang
    • Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
    • /
    • v.5 no.2
    • /
    • pp.289-296
    • /
    • 2015
  • Java is an interpreted language that can run on a variety of platforms, also Java has a number of useful features for network. Due to theses features of Java language, Java is used in various fields. In this paper, we will talk about how the malware that threaten the Java Security Manager of the Java Virtual Machine is using the vulnerability of the Java Virtual Machine. And for corresponding measures, this paper suggest vulnerability analysis method of Java system class by using Java Call Graph and Java Access Permission Checking Tree. By suggesting that, we want to lay groundwork for preventing Java security threats in advance.

Real-Time Stock Price Prediction using Apache Spark (Apache Spark를 활용한 실시간 주가 예측)

  • Dong-Jin Shin;Seung-Yeon Hwang;Jeong-Joon Kim
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.23 no.4
    • /
    • pp.79-84
    • /
    • 2023
  • Apache Spark, which provides the fastest processing speed among recent distributed and parallel processing technologies, provides real-time functions and machine learning functions. Although official documentation guides for these functions are provided, a method for fusion of functions to predict a specific value in real time is not provided. Therefore, in this paper, we conducted a study to predict the value of data in real time by fusion of these functions. The overall configuration is collected by downloading stock price data provided by the Python programming language. And it creates a model of regression analysis through the machine learning function, and predicts the adjusted closing price among the stock price data in real time by fusing the real-time streaming function with the machine learning function.