• Title/Summary/Keyword: Training Datasets

Search Result 340, Processing Time 0.022 seconds

Generative optical flow based abnormal object detection method using a spatio-temporal translation network

  • Lim, Hyunseok;Gwak, Jeonghwan
    • Journal of the Korea Society of Computer and Information
    • /
    • v.26 no.4
    • /
    • pp.11-19
    • /
    • 2021
  • An abnormal object refers to a person, an object, or a mechanical device that performs abnormal and unusual behavior and needs observation or supervision. In order to detect this through artificial intelligence algorithm without continuous human intervention, a method of observing the specificity of temporal features using optical flow technique is widely used. In this study, an abnormal situation is identified by learning an algorithm that translates an input image frame to an optical flow image using a Generative Adversarial Network (GAN). In particular, we propose a technique that improves the pre-processing process to exclude unnecessary outliers and the post-processing process to increase the accuracy of identification in the test dataset after learning to improve the performance of the model's abnormal behavior identification. UCSD Pedestrian and UMN Unusual Crowd Activity were used as training datasets to detect abnormal behavior. For the proposed method, the frame-level AUC 0.9450 and EER 0.1317 were shown in the UCSD Ped2 dataset, which shows performance improvement compared to the models in the previous studies.

Corneal Ulcer Region Detection With Semantic Segmentation Using Deep Learning

  • Im, Jinhyuk;Kim, Daewon
    • Journal of the Korea Society of Computer and Information
    • /
    • v.27 no.9
    • /
    • pp.1-12
    • /
    • 2022
  • Traditional methods of measuring corneal ulcers were difficult to present objective basis for diagnosis because of the subjective judgment of the medical staff through photographs taken with special equipment. In this paper, we propose a method to detect the ulcer area on a pixel basis in corneal ulcer images using a semantic segmentation model. In order to solve this problem, we performed the experiment to detect the ulcer area based on the DeepLab model which has the highest performance in semantic segmentation model. For the experiment, the training and test data were selected and the backbone network of DeepLab model which set as Xception and ResNet, respectively were evaluated and compared the performances. We used Dice similarity coefficient and IoU value as an indicator to evaluate the performances. Experimental results show that when 'crop & resized' images are added to the dataset, it segment the ulcer area with an average accuracy about 93% of Dice similarity coefficient on the DeepLab model with ResNet101 as the backbone network. This study shows that the semantic segmentation model used for object detection also has an ability to make significant results when classifying objects with irregular shapes such as corneal ulcers. Ultimately, we will perform the extension of datasets and experiment with adaptive learning methods through future studies so that they can be implemented in real medical diagnosis environment.

Effectiveness of the Detection of Pulmonary Emphysema using VGGNet with Low-dose Chest Computed Tomography Images (저선량 흉부 CT를 이용한 VGGNet 폐기종 검출 유용성 평가)

  • Kim, Doo-Bin;Park, Young-Joon;Hong, Joo-Wan
    • Journal of the Korean Society of Radiology
    • /
    • v.16 no.4
    • /
    • pp.411-417
    • /
    • 2022
  • This study aimed to learn and evaluate the effectiveness of VGGNet in the detection of pulmonary emphysema using low-dose chest computed tomography images. In total, 8000 images with normal findings and 3189 images showing pulmonary emphysema were used. Furthermore, 60%, 24%, and 16% of the normal and emphysema data were randomly assigned to training, validation, and test datasets, respectively, in model learning. VGG16 and VGG19 were used for learning, and the accuracy, loss, confusion matrix, precision, recall, specificity, and F1-score were evaluated. The accuracy and loss for pulmonary emphysema detection of the low-dose chest CT test dataset were 92.35% and 0.21% for VGG16 and 95.88% and 0.09% for VGG19, respectively. The precision, recall, and specificity were 91.60%, 98.36%, and 77.08% for VGG16 and 96.55%, 97.39%, and 92.72% for VGG19, respectively. The F1-scores were 94.86% and 96.97% for VGG16 and VGG19, respectively. Through the above evaluation index, VGG19 is judged to be more useful in detecting pulmonary emphysema. The findings of this study would be useful as basic data for the research on pulmonary emphysema detection models using VGGNet and artificial neural networks.

Assessment of the Object Detection Ability of Interproximal Caries on Primary Teeth in Periapical Radiographs Using Deep Learning Algorithms (유치의 치근단 방사선 사진에서 딥 러닝 알고리즘을 이용한 모델의 인접면 우식증 객체 탐지 능력의 평가)

  • Hongju Jeon;Seonmi Kim;Namki Choi
    • Journal of the korean academy of Pediatric Dentistry
    • /
    • v.50 no.3
    • /
    • pp.263-276
    • /
    • 2023
  • The purpose of this study was to evaluate the performance of a model using You Only Look Once (YOLO) for object detection of proximal caries in periapical radiographs of children. A total of 2016 periapical radiographs in primary dentition were selected from the M6 database as a learning material group, of which 1143 were labeled as proximal caries by an experienced dentist using an annotation tool. After converting the annotations into a training dataset, YOLO was trained on the dataset using a single convolutional neural network (CNN) model. Accuracy, recall, specificity, precision, negative predictive value (NPV), F1-score, Precision-Recall curve, and AP (area under curve) were calculated for evaluation of the object detection model's performance in the 187 test datasets. The results showed that the CNN-based object detection model performed well in detecting proximal caries, with a diagnostic accuracy of 0.95, a recall of 0.94, a specificity of 0.97, a precision of 0.82, a NPV of 0.96, and an F1-score of 0.81. The AP was 0.83. This model could be a valuable tool for dentists in detecting carious lesions in periapical radiographs.

A Study on the Use of Contrast Agent and the Improvement of Body Part Classification Performance through Deep Learning-Based CT Scan Reconstruction (딥러닝 기반 CT 스캔 재구성을 통한 조영제 사용 및 신체 부위 분류 성능 향상 연구)

  • Seongwon Na;Yousun Ko;Kyung Won Kim
    • Journal of Broadcast Engineering
    • /
    • v.28 no.3
    • /
    • pp.293-301
    • /
    • 2023
  • Unstandardized medical data collection and management are still being conducted manually, and studies are being conducted to classify CT data using deep learning to solve this problem. However, most studies are developing models based only on the axial plane, which is a basic CT slice. Because CT images depict only human structures unlike general images, reconstructing CT scans alone can provide richer physical features. This study seeks to find ways to achieve higher performance through various methods of converting CT scan to 2D as well as axial planes. The training used 1042 CT scans from five body parts and collected 179 test sets and 448 with external datasets for model evaluation. To develop a deep learning model, we used InceptionResNetV2 pre-trained with ImageNet as a backbone and re-trained the entire layer of the model. As a result of the experiment, the reconstruction data model achieved 99.33% in body part classification, 1.12% higher than the axial model, and the axial model was higher only in brain and neck in contrast classification. In conclusion, it was possible to achieve more accurate performance when learning with data that shows better anatomical features than when trained with axial slice alone.

Prediction of the remaining time and time interval of pebbles in pebble bed HTGRs aided by CNN via DEM datasets

  • Mengqi Wu;Xu Liu;Nan Gui;Xingtuan Yang;Jiyuan Tu;Shengyao Jiang;Qian Zhao
    • Nuclear Engineering and Technology
    • /
    • v.55 no.1
    • /
    • pp.339-352
    • /
    • 2023
  • Prediction of the time-related traits of pebble flow inside pebble-bed HTGRs is of great significance for reactor operation and design. In this work, an image-driven approach with the aid of a convolutional neural network (CNN) is proposed to predict the remaining time of initially loaded pebbles and the time interval of paired flow images of the pebble bed. Two types of strategies are put forward: one is adding FC layers to the classic classification CNN models and using regression training, and the other is CNN-based deep expectation (DEX) by regarding the time prediction as a deep classification task followed by softmax expected value refinements. The current dataset is obtained from the discrete element method (DEM) simulations. Results show that the CNN-aided models generally make satisfactory predictions on the remaining time with the determination coefficient larger than 0.99. Among these models, the VGG19+DEX performs the best and its CumScore (proportion of test set with prediction error within 0.5s) can reach 0.939. Besides, the remaining time of additional test sets and new cases can also be well predicted, indicating good generalization ability of the model. In the task of predicting the time interval of image pairs, the VGG19+DEX model has also generated satisfactory results. Particularly, the trained model, with promising generalization ability, has demonstrated great potential in accurately and instantaneously predicting the traits of interest, without the need for additional computational intensive DEM simulations. Nevertheless, the issues of data diversity and model optimization need to be improved to achieve the full potential of the CNN-aided prediction tool.

KOMUChat: Korean Online Community Dialogue Dataset for AI Learning (KOMUChat : 인공지능 학습을 위한 온라인 커뮤니티 대화 데이터셋 연구)

  • YongSang Yoo;MinHwa Jung;SeungMin Lee;Min Song
    • Journal of Intelligence and Information Systems
    • /
    • v.29 no.2
    • /
    • pp.219-240
    • /
    • 2023
  • Conversational AI which allows users to interact with satisfaction is a long-standing research topic. To develop conversational AI, it is necessary to build training data that reflects real conversations between people, but current Korean datasets are not in question-answer format or use honorifics, making it difficult for users to feel closeness. In this paper, we propose a conversation dataset (KOMUChat) consisting of 30,767 question-answer sentence pairs collected from online communities. The question-answer pairs were collected from post titles and first comments of love and relationship counsel boards used by men and women. In addition, we removed abuse records through automatic and manual cleansing to build high quality dataset. To verify the validity of KOMUChat, we compared and analyzed the result of generative language model learning KOMUChat and benchmark dataset. The results showed that our dataset outperformed the benchmark dataset in terms of answer appropriateness, user satisfaction, and fulfillment of conversational AI goals. The dataset is the largest open-source single turn text data presented so far and it has the significance of building a more friendly Korean dataset by reflecting the text styles of the online community.

Prediction of Postoperative Lung Function in Lung Cancer Patients Using Machine Learning Models

  • Oh Beom Kwon;Solji Han;Hwa Young Lee;Hye Seon Kang;Sung Kyoung Kim;Ju Sang Kim;Chan Kwon Park;Sang Haak Lee;Seung Joon Kim;Jin Woo Kim;Chang Dong Yeo
    • Tuberculosis and Respiratory Diseases
    • /
    • v.86 no.3
    • /
    • pp.203-215
    • /
    • 2023
  • Background: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. Methods: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R2 and mean squared error (MSE) in the three sets. Results: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R2 value was 0.27 and in set II, LightGBM was the best model with the highest R2 value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R2 value of 0.56 and the lowest MSE of 174.07. Conclusion: The LightGBM model showed the best performance in predicting postoperative lung function.

Analysis of the Abstract Structure in Scientific Papers by Gifted Students and Exploring the Possibilities of Artificial Intelligence Applied to the Educational Setting (과학 영재의 논문 초록 구조 분석 및 이에 대한 인공지능의 활용 가능성 탐색)

  • Bongwoo Lee;Hunkoog Jho
    • Journal of The Korean Association For Science Education
    • /
    • v.43 no.6
    • /
    • pp.573-582
    • /
    • 2023
  • This study aimed to explore the potential use of artificial intelligence in science education for gifted students by analyzing the structure of abstracts written by students at a gifted science academy and comparing the performance of various elements extracted using AI. The study involved an analysis of 263 graduation theses from S Science High School over five years (2017-2021), focusing on the frequency and types of background, objectives, methods, results, and discussions included in their abstracts. This was followed by an evaluation of their accuracy using AI classification methods with fine-tuning and prompts. The results revealed that the frequency of elements in the abstracts written by gifted students followed the order of objectives, methods, results, background, and discussions. However, only 57.4% of the abstracts contained all the essential elements, such as objectives, methods, and results. Among these elements, fine-tuned AI classification showed the highest accuracy, with background, objectives, and results demonstrating relatively high performance, while methods and discussions were often inaccurately classified. These findings suggest the need for a more effective use of AI, through providing a better distribution of elements or appropriate datasets for training. Educational implications of these findings were also discussed.

A Gap Analysis Using Spatial Data and Social Media Big Data Analysis Results of Island Tourism Resources for Sustainable Resource Management (지속가능한 자원관리를 위한 섬 지역 관광자원의 공간정보와 소셜미디어 빅데이터 분석 결과를 활용한 격차분석)

  • Lee, Sung-Hee;Lee, Ju-Kyung;Son, Yong-Hoon;Kim, Young-Jin
    • Journal of Korean Society of Rural Planning
    • /
    • v.30 no.2
    • /
    • pp.13-24
    • /
    • 2024
  • This study conducts an analysis of social media big data pertaining to island tourism resources, aiming to discern the diverse forms and categories of island tourism favored by consumers, ascertain predominant resources, and facilitate objective decision-making grounded in scientific methodologies. To achieve this objective, an examination of blog posts published on Naver from 2022 to 2023 was undertaken, utilizing keywords such as 'Island tourism', 'Island travel', and 'Island backpacking' as focal points for analysis. Text mining techniques were applied to sift through the data. Among the resources identified, the port emerged as a significant asset, serving as a pivotal conduit linking the island and mainland and holding substantial importance as a focal point and resource for tourist access to the island. Furthermore, an analysis of the disparity between existing island tourism resources and those acknowledged by tourists who actively engage with and appreciate island destinations led to the identification of 186 newly emerging resources. These nascent resources predominantly clustered within five regions: Incheon Metropolitan City, Tongyeong/Geoje City, Jeju Island, Ulleung-gun, and Shinan-gun. A scrutiny of these resources, categorized according to the tourism resource classification system, revealed a notable presence of new resources, chiefly in the domains of 'rural landscape', 'tourist resort/training facility', 'transportation facility', and 'natural resource'. Notably, many of these emerging resources were previously overlooked in official management targets or resource inventories pertaining to existing island tourism resources. Noteworthy examples include ports, beaches, and mountains, which, despite constituting a substantial proportion of the newly identified tourist resources, were not accorded prominence in spatial information datasets. This study holds significance in its ability to unearth novel tourism resources recognized by island tourism consumers through a gap analysis approach that juxtaposes the existing status of island tourism resource data with techniques utilizing social media big data. Furthermore, the methodology delineated in this research offers a valuable framework for domestic local governments to gauge local tourism demand and embark on initiatives for tourism development or regional revitalization.