• Title/Summary/Keyword: training database

Search Result 470, Processing Time 0.027 seconds

Advanced Neighbor Embedding based on Support Vector Regression (SVR에 기반한 개선된 네이버 임베딩)

  • Eum, Kyoung-Bae;Jeon, Chang-Woo;Choi, Young-Hee;Nam, Seung-Tae;Lee, Jong-Chan
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2014.10a
    • /
    • pp.733-735
    • /
    • 2014
  • Example based Super Resolution(SR) is using the correspondence between the low and high resolution image from a database. This method uses only one image to estimate a high resolution image and can get the larger image than 2 times. Example based SR is proposed to solve the problem of classical SR. Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the advanced NE baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we estimate a pixel in its high resolution version by using SVR based NE. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.

  • PDF

Improving Human Activity Recognition Model with Limited Labeled Data using Multitask Semi-Supervised Learning (제한된 라벨 데이터 상에서 다중-태스크 반 지도학습을 사용한 동작 인지 모델의 성능 향상)

  • Prabono, Aria Ghora;Yahya, Bernardo Nugroho;Lee, Seok-Lyong
    • Database Research
    • /
    • v.34 no.3
    • /
    • pp.137-147
    • /
    • 2018
  • A key to a well-performing human activity recognition (HAR) system through machine learning technique is the availability of a substantial amount of labeled data. Collecting sufficient labeled data is an expensive and time-consuming task. To build a HAR system in a new environment (i.e., the target domain) with very limited labeled data, it is unfavorable to naively exploit the data or trained classifier model from the existing environment (i.e., the source domain) as it is due to the domain difference. While traditional machine learning approaches are unable to address such distribution mismatch, transfer learning approach leverages the utilization of knowledge from existing well-established source domains that help to build an accurate classifier in the target domain. In this work, we propose a transfer learning approach to create an accurate HAR classifier with very limited data through the multitask neural network. The classifier loss function minimization for source and target domain are treated as two different tasks. The knowledge transfer is performed by simultaneously minimizing the loss function of both tasks using a single neural network model. Furthermore, we utilize the unlabeled data in an unsupervised manner to help the model training. The experiment result shows that the proposed work consistently outperforms existing approaches.

A Study on the Classification of Unstructured Data through Morpheme Analysis

  • Kim, SungJin;Choi, NakJin;Lee, JunDong
    • Journal of the Korea Society of Computer and Information
    • /
    • v.26 no.4
    • /
    • pp.105-112
    • /
    • 2021
  • In the era of big data, interest in data is exploding. In particular, the development of the Internet and social media has led to the creation of new data, enabling the realization of the era of big data and artificial intelligence and opening a new chapter in convergence technology. Also, in the past, there are many demands for analysis of data that could not be handled by programs. In this paper, an analysis model was designed and verified for classification of unstructured data, which is often required in the era of big data. Data crawled DBPia's thesis summary, main words, and sub-keyword, and created a database using KoNLP's data dictionary, and tokenized words through morpheme analysis. In addition, nouns were extracted using KAIST's 9 part-of-speech classification system, TF-IDF values were generated, and an analysis dataset was created by combining training data and Y values. Finally, The adequacy of classification was measured by applying three analysis algorithms(random forest, SVM, decision tree) to the generated analysis dataset. The classification model technique proposed in this paper can be usefully used in various fields such as civil complaint classification analysis and text-related analysis in addition to thesis classification.

An Empirical Study on the Alternative Work Organization and Workers' Outcome - Focus on Lean Production - (대안적 작업조직 유형과 노동자 성과에 관한 실증적 고찰 - 제조업의 린 방식을 중심으로 -)

  • Son, Dong-Hui
    • Korean Journal of Labor Studies
    • /
    • v.17 no.1
    • /
    • pp.1-36
    • /
    • 2011
  • The purpose of this study is to analyze the effect to financial outcome and workers' outcome, using the manufacturing industry database of Human Capital corporate Panel from Korea Research Institute for Vocational Education & Training. Especially, this study used the typology of Lean production and Autonomous team production, that are the typical form of alternative work organization, to analyze. In the case of domestic manufacturing industry, individual participation practices, that have the main characteristics such as QC or suggestion system, is expanded. Therefore, with the reference of Lean production, Autonomous Team Production and the Taylor system are compared and analyzed, considering the characteristics of Socio-technical System. As a result, it is showed that the Lean production and Autonomous Team Production as a alternative work organization are more positive about the organizational performance and workers' outcome than the taylor system. However, when Lean production and Autonomous Team Production are compared, it is showed unsignificant distinction to the effect of organizational performance. Meanwhile, Lean production showed more negative effect on the every dependent variables such as working hours, income, job satisfaction, and organizational commitment as workers' performance than the Autonomous Team Production. Although the common ideas and belief is that the Lean Production is superior for the quality and organizational performance improvement, it is implied the possibility that there is some damaged workers' performance on the hidden side of that mechanism.

Building a Korean conversational speech database in the emergency medical domain (응급의료 영역 한국어 음성대화 데이터베이스 구축)

  • Kim, Sunhee;Lee, Jooyoung;Choi, Seo Gyeong;Ji, Seunghun;Kang, Jeemin;Kim, Jongin;Kim, Dohee;Kim, Boryong;Cho, Eungi;Kim, Hojeong;Jang, Jeongmin;Kim, Jun Hyung;Ku, Bon Hyeok;Park, Hyung-Min;Chung, Minhwa
    • Phonetics and Speech Sciences
    • /
    • v.12 no.4
    • /
    • pp.81-90
    • /
    • 2020
  • This paper describes a method of building Korean conversational speech data in the emergency medical domain and proposes an annotation method for the collected data in order to improve speech recognition performance. To suggest future research directions, baseline speech recognition experiments were conducted by using partial data that were collected and annotated. All voices were recorded at 16-bit resolution at 16 kHz sampling rate. A total of 166 conversations were collected, amounting to 8 hours and 35 minutes. Various information was manually transcribed such as orthography, pronunciation, dialect, noise, and medical information using Praat. Baseline speech recognition experiments were used to depict problems related to speech recognition in the emergency medical domain. The Korean conversational speech data presented in this paper are first-stage data in the emergency medical domain and are expected to be used as training data for developing conversational systems for emergency medical applications.

Expanded Workflow Development for OSINT(Open Source Intelligence)-based Profiling with Timeline (공개정보 기반 타임라인 프로파일링을 위한 확장된 워크플로우 개발)

  • Kwon, Heewon;Jin, Seoyoung;Sim, Minsun;Kwon, Hyemin;Lee, Insoo;Lee, Seunghoon;Kim, Myuhngjoo
    • Journal of Digital Convergence
    • /
    • v.19 no.3
    • /
    • pp.187-194
    • /
    • 2021
  • OSINT(Open Source Intelligence), rapidly increasing on the surface web in various forms, can also be used for criminal investigations by using profiling. This technique has become quite common in foreign investigative agencies such as the United States. On the other hand, in Korea, it is not used a lot, and there is a large deviation in the quantity and quality of information acquired according to the experience and knowledge level of investigator. Unlike Bazzell's most well-known model, we designed a Korean-style OSINT-based profiling technique that considers the Korean web environment and provides timeline information, focusing on the improved workflow. The database schema to improve the efficiency of profiling is also presented. Using this, we can obtain search results that guarantee a certain level of quantity and quality. And it can also be used as a standard training course. To increase the effectiveness and efficiency of criminal investigations using this technique, it is necessary to strengthen the legal basis and to introduce automation technologies.

Status and Quality Analysis on the Biodiversity Data of East Asian Vascular Plants Mobilized through the Global Biodiversity Information Facility (GBIF) (세계생물다양성정보기구(GBIF)에 출판된 동아시아 관속식물 생물다양성 정보 현황과 자료품질 분석)

  • Chang, Chin-Sung;Kwon, Shin-Young;Kim, Hui
    • Journal of Korean Society of Forest Science
    • /
    • v.110 no.2
    • /
    • pp.179-188
    • /
    • 2021
  • Biodiversity informatics applies information technology methods in organizing, accessing, visualizing, and analyzing primary biodiversity data and quantitative data management through the scientific names of accepted names and synonyms. We reviewed the GBIF data published by China, Japan, Taiwan, and internal institutes, such as NIBR, NIE, and KNA of the Republic of Korea, and assessed data in diverse aspects of data quality using BRAHMS software. Most data from four Asian countries have quality problems with the lack of data consistency and missing information on georeferenced data, collectors, collection date, and place names (gazetteers) or other invalid data forms. The major problem is that biodiversity management institutions in East Asia are using unstructured databases and simple spreadsheet-type data. Owing to the nature of the biodiversity information, if data relationships are not structured, it would be impossible to secure the data integrity of scientific names, human names, geographical names, literature, and ecological information. For data quality, it is essential to build data integrity for database management and training systems for taxonomists who are continuous data managers to correct errors. Thus, publishers in East Asia play an essential role not only in using specialized software to manage biodiversity data but also in developing structured databases and ensuring their integration and value within biodiversity publishing platforms.

Implement of Web-based Remote Monitoring System of Smart Greenhouse (스마트 온실 통합 모니터링 시스템 구축)

  • Dong Eok, Kim;Nou Bog, Park;Sun Jung, Hong;Dong Hyeon, Kang;Young Hoe, Woo;Jong Won, Lee;Yul Kyun, Ahn;Shin Hee, Han
    • Journal of Practical Agriculture & Fisheries Research
    • /
    • v.24 no.4
    • /
    • pp.53-61
    • /
    • 2022
  • Growing agricultural products in greenhouses controlled by creating suitable climatic conditions and root zone of crop has been an important research and application subject. Appropriate environmental conditions in greenhouse are necessary for optimum plant growth improved crop yields. This study aimed to establish web-based remote monitoring system which monitors crops growth environment and status of crop on a real-time basis by applying to greenhouses IT technology connecting greenhouse equipment such as temperature sensors, soil sensors, crop sensors and camera. The measuring items were air temperature, relative humidity, solar radiation, CO2 concentration, EC and pH of nutrient solution, medium temperature, EC of medium, water content of medium, leaf temperature, sap flow, stem diameter, fruit diameter, etc. The developed greenhouse monitoring system was composed of the network system, the data collecting device with sensors, and cameras. Remote monitoring system was implemented in a server/client environment. Information on greenhouse environment and crops is stored in a database. Items on growth and environment is extracted from stored information, could be compared and analyzed. So, A integrated monitoring system for smart greenhouse would be use in application practice and understanding the environment and crop growth for smart greenhouse management. sap flow, stem diameter and pant-water relations

Effect of Tongue Exercise on Stroke Patients With Dysphagia : A Systematic Review (혀 운동(tongue exercise)이 연하장애를 가진 뇌졸중 환자에게 미치는 효과 : 체계적 고찰)

  • Son, Yeong Soo;Choi, Yoo Im
    • Therapeutic Science for Rehabilitation
    • /
    • v.11 no.3
    • /
    • pp.7-22
    • /
    • 2022
  • Objectives : This study was a systematic review of tongue movements in stroke patients with dysphagia. This study aimed to provide a basis for verifying the effects of tongue movement and identifying the tendency of tongue movement. Methods : A systematic review was conducted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist and flow chart. PubMed, MEDLINE, CINAHL, RISS, and e-articles databases were searched. A total of six documents were investigated, and the PEDro scale was used to evaluate the quality of the papers. Results : Three intervention methods were included in the six papers analyzed. Regarding the type of tongue exercise, three TPRT (Tongue to Palate Resistance Trainings) and two TSAT (Tongue Strength and Accuracy Training) were mediated through the IOPI (Iowa Oral Performance Instrument), and only one study applied TSE (Tongue Stretching Exercise). The treatment effects for each intervention implemented in the literature were confirmed to be effective. However, generalizability of findings is difficult because of the small sample size. Further, no significant difference was found between the experimental and control groups. Conclusions : This study can help occupational therapists provide efficient swallowing rehabilitation treatment by applying tongue exercises to stroke patients with dysphagia. More research should be conducted to determine the effects of tongue exercise.

A Multi-speaker Speech Synthesis System Using X-vector (x-vector를 이용한 다화자 음성합성 시스템)

  • Jo, Min Su;Kwon, Chul Hong
    • The Journal of the Convergence on Culture Technology
    • /
    • v.7 no.4
    • /
    • pp.675-681
    • /
    • 2021
  • With the recent growth of the AI speaker market, the demand for speech synthesis technology that enables natural conversation with users is increasing. Therefore, there is a need for a multi-speaker speech synthesis system that can generate voices of various tones. In order to synthesize natural speech, it is required to train with a large-capacity. high-quality speech DB. However, it is very difficult in terms of recording time and cost to collect a high-quality, large-capacity speech database uttered by many speakers. Therefore, it is necessary to train the speech synthesis system using the speech DB of a very large number of speakers with a small amount of training data for each speaker, and a technique for naturally expressing the tone and rhyme of multiple speakers is required. In this paper, we propose a technology for constructing a speaker encoder by applying the deep learning-based x-vector technique used in speaker recognition technology, and synthesizing a new speaker's tone with a small amount of data through the speaker encoder. In the multi-speaker speech synthesis system, the module for synthesizing mel-spectrogram from input text is composed of Tacotron2, and the vocoder generating synthesized speech consists of WaveNet with mixture of logistic distributions applied. The x-vector extracted from the trained speaker embedding neural networks is added to Tacotron2 as an input to express the desired speaker's tone.