• Title/Summary/Keyword: Fine annotation

Search Result 6, Processing Time 0.021 seconds

A Study of Establishment and application Algorithm of Artificial Intelligence Training Data on Land use/cover Using Aerial Photograph and Satellite Images (항공 및 위성영상을 활용한 토지피복 관련 인공지능 학습 데이터 구축 및 알고리즘 적용 연구)

  • Lee, Seong-hyeok;Lee, Moung-jin
    • Korean Journal of Remote Sensing
    • /
    • v.37 no.5_1
    • /
    • pp.871-884
    • /
    • 2021
  • The purpose of this study was to determine ways to increase efficiency in constructing and verifying artificial intelligence learning data on land cover using aerial and satellite images, and in applying the data to AI learning algorithms. To this end, multi-resolution datasets of 0.51 m and 10 m each for 8 categories of land cover were constructed using high-resolution aerial images and satellite images obtained from Sentinel-2 satellites. Furthermore, fine data (a total of 17,000 pieces) and coarse data (a total of 33,000 pieces) were simultaneously constructed to achieve the following two goals: precise detection of land cover changes and the establishment of large-scale learning datasets. To secure the accuracy of the learning data, the verification was performed in three steps, which included data refining, annotation, and sampling. The learning data that wasfinally verified was applied to the semantic segmentation algorithms U-Net and DeeplabV3+, and the results were analyzed. Based on the analysis, the average accuracy for land cover based on aerial imagery was 77.8% for U-Net and 76.3% for Deeplab V3+, while for land cover based on satellite imagery it was 91.4% for U-Net and 85.8% for Deeplab V3+. The artificial intelligence learning datasets on land cover constructed using high-resolution aerial and satellite images in this study can be used as reference data to help classify land cover and identify relevant changes. Therefore, it is expected that this study's findings can be used in the future in various fields of artificial intelligence studying land cover in constructing an artificial intelligence learning dataset on land cover of the whole of Korea.

Molecular Identification and Fine Mapping of a Major Quantitative Trait Locus, OsGPq3 for Seed Low-Temperature Germinability in Rice

  • Nari Kim;Rahmatullah Jan;Jae-Ryoung Park;Saleem Asif;Kyung-Min Kim
    • Proceedings of the Korean Society of Crop Science Conference
    • /
    • 2022.10a
    • /
    • pp.283-283
    • /
    • 2022
  • Abiotic stresses such as high/low temperature, drought, salinity, and submergence directly or indirectly influence the physiological status and molecular mechanisms of rice which badly affect yield. Especially, the low temperature causes harmful influences in the overall process of rice growth such as uneven germination and the establishment of seedlings, which has become one of the main limiting factors affecting rice production in the world. It is of great significance to find the candidate genes controlling low-temperature tolerance during seed germination and study their functions for breeding new rice cultivars with immense low-temperature tolerance during seed germination. In this study, 120 lines of Cheongcheong/Nagdong double haploid population were used for quantitative trait locus analysis of low-temperature germinability. The results showed significant difference in germination under low different temperature conditions. In total, 4 QTLs were detected on chromosome 3, 6, and 8. A total of 41 genes were identified from all the 4 QTLs, among them, 25 genes were selected by gene function annotation and further screened through quantitative real time polymerase chain reaction. Based on gene function annotation and level of expression under low-temperature, our study suggested OsGPq3 gene as a candidate gene controlling viviparous germination, ABA and GA signaling under low-temperature. This study will provide a theoretical basis for marker-assisted breeding.

  • PDF

A study of Corpus Annotation for Aspect Based Sentiment Analysis of Korean financial texts (한국어 경제 도메인 텍스트 속성 기반 감성 분석을 위한 말뭉치 주석 요소 연구)

  • Seoyoon Park;Yeonji Jang;Yejee Kang;Hyerin Kang;Hansaem Kim
    • Annual Conference on Human and Language Technology
    • /
    • 2022.10a
    • /
    • pp.232-237
    • /
    • 2022
  • 본 논문에서는 미세 조정(fine-tuning) 및 비지도 학습 기법을 사용하여 경제 분야 텍스트인 금융 리포트에 대해 속성 기반 감성 분석(aspect-based sentiment analysis) 데이터셋을 반자동적으로 구축할 수 있는 방법론에 대한 연구를 수행하였다. 구축 시에는 속성기반 감성분석 주석 요소 중 극성, 속성 카테고리 정보를 부착하였으며, 미세조정과 비지도 학습 기법인 BERTopic을 통해 주석 요소를 자동적으로 부착하는 한편 이를 수동으로 검수하여 데이터셋의 완성도를 높이고자 하였다. 데이터셋에 대한 실험 결과, 극성 반자동 주석의 경우 기존에 구축된 데이터셋과 비슷한 수준의 성능을 보였다. 한편 정성적 분석을 통해 자동 구축을 동일하게 수행하였더라도 기술의 원리와 발달 정도에 따라 결과가 상이하게 달라짐을 관찰함으로써 경제 도메인의 ABSA 데이터셋 구축에 여전히 발전 여지가 있음을 확인할 수 있었다.

  • PDF

Comparison of transcriptome between high- and low-marbling fineness in longissimus thoracis muscle of Korean cattle

  • Beak, Seok-Hyeon;Baik, Myunggi
    • Animal Bioscience
    • /
    • v.35 no.2
    • /
    • pp.196-203
    • /
    • 2022
  • Objective: This study compared differentially expressed genes (DEGs) between groups with high and low numbers of fine marbling particles (NFMP) in the longissimus thoracis muscle (LT) of Korean cattle to understand the molecular events associated with fine marbling particle formation. Methods: The size and distribution of marbling particles in the LT were assessed with a computer image analysis method. Based on the NFMP, 10 LT samples were selected and assigned to either high- (n = 5) or low- (n = 5) NFMP groups. Using RNA sequencing, LT transcriptomic profiles were compared between the high- and low-NFMP groups. DEGs were selected at p<0.05 and |fold change| >2 and subjected to functional annotation. Results: In total, 328 DEGs were identified, with 207 up-regulated and 121 down-regulated genes in the high-NFMP group. Pathway analysis of these DEGs revealed five significant (p<0.05) Kyoto encyclopedia of genes and genomes pathways; the significant terms included endocytosis (p = 0.023), protein processing in endoplasmic reticulum (p = 0.019), and adipocytokine signaling pathway (p = 0.024), which are thought to regulate adipocyte hypertrophy and hyperplasia. The expression of sirtuin4 (p<0.001) and insulin receptor substrate 2 (p = 0.043), which are associated with glucose uptake and adipocyte differentiation, was higher in the high-NFMP group than in the low-NFMP group. Conclusion: Transcriptome differences between the high- and low-NFMP groups suggest that pathways regulating adipocyte hyperplasia and hypertrophy are involved in the marbling fineness of the LT.

Dual-stream Co-enhanced Network for Unsupervised Video Object Segmentation

  • Hongliang Zhu;Hui Yin;Yanting Liu;Ning Chen
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • v.18 no.4
    • /
    • pp.938-958
    • /
    • 2024
  • Unsupervised Video Object Segmentation (UVOS) is a highly challenging problem in computer vision as the annotation of the target object in the testing video is unknown at all. The main difficulty is to effectively handle the complicated and changeable motion state of the target object and the confusion of similar background objects in video sequence. In this paper, we propose a novel deep Dual-stream Co-enhanced Network (DC-Net) for UVOS via bidirectional motion cues refinement and multi-level feature aggregation, which can fully take advantage of motion cues and effectively integrate different level features to produce high-quality segmentation mask. DC-Net is a dual-stream architecture where the two streams are co-enhanced by each other. One is a motion stream with a Motion-cues Refine Module (MRM), which learns from bidirectional optical flow images and produces fine-grained and complete distinctive motion saliency map, and the other is an appearance stream with a Multi-level Feature Aggregation Module (MFAM) and a Context Attention Module (CAM) which are designed to integrate the different level features effectively. Specifically, the motion saliency map obtained by the motion stream is fused with each stage of the decoder in the appearance stream to improve the segmentation, and in turn the segmentation loss in the appearance stream feeds back into the motion stream to enhance the motion refinement. Experimental results on three datasets (Davis2016, VideoSD, SegTrack-v2) demonstrate that DC-Net has achieved comparable results with some state-of-the-art methods.

Building Sentence Meaning Identification Dataset Based on Social Problem-Solving R&D Reports (사회문제 해결 연구보고서 기반 문장 의미 식별 데이터셋 구축)

  • Hyeonho Shin;Seonki Jeong;Hong-Woo Chun;Lee-Nam Kwon;Jae-Min Lee;Kanghee Park;Sung-Pil Choi
    • KIPS Transactions on Software and Data Engineering
    • /
    • v.12 no.4
    • /
    • pp.159-172
    • /
    • 2023
  • In general, social problem-solving research aims to create important social value by offering meaningful answers to various social pending issues using scientific technologies. Not surprisingly, however, although numerous and extensive research attempts have been made to alleviate the social problems and issues in nation-wide, we still have many important social challenges and works to be done. In order to facilitate the entire process of the social problem-solving research and maximize its efficacy, it is vital to clearly identify and grasp the important and pressing problems to be focused upon. It is understandable for the problem discovery step to be drastically improved if current social issues can be automatically identified from existing R&D resources such as technical reports and articles. This paper introduces a comprehensive dataset which is essential to build a machine learning model for automatically detecting the social problems and solutions in various national research reports. Initially, we collected a total of 700 research reports regarding social problems and issues. Through intensive annotation process, we built totally 24,022 sentences each of which possesses its own category or label closely related to social problem-solving such as problems, purposes, solutions, effects and so on. Furthermore, we implemented four sentence classification models based on various neural language models and conducted a series of performance experiments using our dataset. As a result of the experiment, the model fine-tuned to the KLUE-BERT pre-trained language model showed the best performance with an accuracy of 75.853% and an F1 score of 63.503%.