• Smart Media Journal
• /
• v.11 no.7
• /
• pp.94-103
• /
• 2022

Weeds bring disadvantages to crops since they can damage them, and a clean treatment with less pollution and contamination should be developed. Artificial intelligence gives new hope to agriculture to achieve smart farming. This study delivers an automated weeds growth point detection using deep learning. This study proposes a combination of semantic graphics for generating data annotation and U-Net with pre-trained deep learning as a backbone for locating the growth point of the weeds on the given field scene. The dataset was collected from an actual field. We measured the intersection over union, f1-score, precision, and recall to evaluate our method. Moreover, Mobilenet V2 was chosen as the backbone and compared with Resnet 34. The results showed that the proposed method was accurate enough to detect the growth point and handle the brightness variation. The best performance was achieved by Mobilenet V2 as a backbone with IoU 96.81%, precision 97.77%, recall 98.97%, and f1-score 97.30%.

• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.354-361
• /
• 2023

Most of spinal diseases are diagnosed based on the subjective judgment of a specialist, so numerous studies have been conducted to find objectivity by automating the diagnosis process using deep learning. In this paper, we propose a method that combines segmentation and feature extraction, which are frequently used techniques for diagnosing spinal diseases. Four models, U-Net, U-Net++, DeepLabv3+, and M-Net were trained and compared using 1000 X-ray images, and key-points were derived using Douglas-Peucker algorithms. For evaluation, Dice Similarity Coefficient(DSC), Intersection over Union(IoU), precision, recall, and area under precision-recall curve evaluation metrics were used and U-Net++ showed the best performance in all metrics with an average DSC of 0.9724. For the average Euclidean distance between estimated key-points and ground truth, U-Net was the best, followed by U-Net++. However the difference in average distance was about 0.1 pixels, which is not significant. The results suggest that it is possible to extract key-points based on segmentation and that it can be used to accurately diagnose various spinal diseases, including spondylolisthesis, with consistent criteria.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.611-614
• /
• 2023

갈비뼈 병변 진단 과정은 방사선 전문의가 CT 스캐너를 통해 생성된 2 차원 CT 이미지들을 해석하며 진행된다. 병변의 위치를 파악하고 정확한 진단을 내리기 위해 수백장의 2차원 CT 이미지들이 세밀하게 검토되며 갈비뼈를 분류한다. 본 연구는 이런 노동 집약적 작업의 문제점을 개선시키기 위해 Biaxial Rib Segmentation(BARS)을 제안한다. BARS 는 흉부 CT 볼륨의 관상면과 수평면으로 구성된 2 차원 이미지들을 U-Net 모델에 학습한다. 모델이 산출한 세그멘테이션 마스크들의 조합은 서로 다른 평면의 공간 정보를 보완하며 3 차원 갈비뼈 볼륨을 재건한다. BARS 의 성능은 DSC, Recall, Precision 지표를 사용해 평가하며, DSC 90.29%, Recall 89.74%, Precision 90.72%를 보인다. 향후에는 이를 기반으로 순차적 갈비뼈 레이블링 연구를 진행할 계획이다.

• Journal of Korean Dental Science
• /
• v.16 no.2
• /
• pp.156-163
• /
• 2023

Purpose: The aim of this study was to evaluate the feasibility of deep learning techniques to classify the morphology and severity of peri-implantitis bone defects based on periapical radiographs. Materials and Methods: Based on a pre-trained and fine-tuned ResNet-50 deep learning algorithm, the morphology and severity of peri-implantitis bone defects on periapical radiographs were classified into six groups (class I/II and slight/moderate/severe). Accuracy, precision, recall, and F1 scores were calculated to measure accuracy. Result: A total of 971 dental images were included in this study. Deep-learning-based classification achieved an accuracy of 86.0% with precision, recall, and F1 score values of 84.45%, 81.22%, and 82.80%, respectively. Class II and moderate groups had the highest F1 scores (92.23%), whereas class I and severe groups had the lowest F1 scores (69.33%). Conclusion: The artificial intelligence-based deep learning technique is promising for classifying the morphology and severity of peri-implantitis. However, further studies are required to validate their feasibility in clinical practice.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.494-510
• /
• 2024

Internet users are exposed to sophisticated cyberattacks that intrusion detection systems have difficulty detecting. Therefore, research is increasing on intrusion detection methods that use artificial intelligence technology for detecting novel cyberattacks. Unsupervised learning-based methods are being researched that learn only from normal data and detect abnormal behaviors by finding patterns. This study developed an anomaly-detection method based on unsupervised machines and deep learning for a network intrusion detection system (NIDS). We present a hybrid anomaly detection approach based on unsupervised learning techniques using the autoencoder (AE), Isolation Forest (IF), and Local Outlier Factor (LOF) algorithms. An oversampling approach that increased the detection rate was also examined. A hybrid approach that combined deep learning algorithms and traditional machine learning algorithms was highly effective in setting the thresholds for anomalies without subjective human judgment. It achieved precision and recall rates respectively of 88.2% and 92.8% when combining two AEs, IF, and LOF while using an oversampling approach to learn more unknown normal data improved the detection accuracy. This approach achieved precision and recall rates respectively of 88.2% and 94.6%, further improving the detection accuracy compared with the hybrid method. Therefore, in NIDS the proposed approach provides high reliability for detecting cyberattacks.

• Journal of the Korean Society for Library and Information Science
• /
• v.19
• /
• pp.189-241
• /
• 1990

This study identified cognitive styles of online searchers in terms of Field Dependence (FD) and Field Independence (FI) dimension and determined whether searching performance was affected by FD / FI cognitive differences between online searchers and the extent to which searching performance was affected by the FD / FI dimension of cognitive style. This study used a quasi experimental design with 41 student subjects using the Lockheed DIALOG system and ERIC ONT AP database. Cognitive styles of student subjects were measured by using GEFT (Group Embedded Figure Test) and the subjects were divided into two cognitive groups- FD and FI based on the GEFT scores. Each subject was assigned two predetermined searches which had different search goals-a 'high precision search' and a 'high recall search.' Search performance of the two cognitive groups on the two problems was compared in order to see how these two groups responded to achieving different search goals in terms of search strategy, search inputs, and resulting search outputs. The major findings of this study were: 1. The pattern of approaching a search problem regardless of whether it was a high precision search or a high recall search was not significantly different between the two cognitive groups. 2. The FI group tended to use significantly more terms for the high recall search than the FD group but slightly less time than the FD group. However, significant differences in connect time between the two groups were not revealed. 3. For both search problems the FI group achieved a significantly higher success rate than the FD group. The FI group were significantly more successful searchers than the FD group. As for unit / cost, although the FI group were more cost effective than those of the FD group for both searches, these differences were too small to be statistically significant. 4. Mean differences of the search performance variables between the FD / FI groups were consistent across the two types of search questions. The FI group seemed to be equally effective for both types of search questions. In conclusion, the differences found in number of terms used and success rate between the two cognitive groups apparently resulted from different cognitive styles.

• The KIPS Transactions:PartB
• /
• v.19B no.1
• /
• pp.19-26
• /
• 2012

The rapid increase of information imposes new demands of content management. The purpose of automatic audio segmentation and classification is to meet the rising need for efficient content management. With this reason, this paper proposes a high-accuracy algorithm that segments audio signals and classifies them into different classes such as speech, music, silence, and environment sounds. The proposed algorithm utilizes support vector machine (SVM) to detect audio-cuts, which are boundaries between different kinds of sounds using the parameter sequence. We then extract feature vectors that are composed of statistical data and they are used as an input of fuzzy c-means (FCM) classifier to partition audio-segments into different classes. To evaluate segmentation and classification performance of the proposed SVM-FCM based algorithm, we consider precision and recall rates for segmentation and classification accuracy for classification. Furthermore, we compare the proposed algorithm with other methods including binary and FCM classifiers in terms of segmentation performance. Experimental results show that the proposed algorithm outperforms other methods in both precision and recall rates.

• Journal of Internet Computing and Services
• /
• v.7 no.2
• /
• pp.71-80
• /
• 2006

In web search engines, there are two main methods: directory searching and keyword searching. Keyword searching shows high recall rate but tends to come up with too many search results to find which users want to see the pages. Directory searching has also a difficulty to find the pages that users want in case of selecting improper category without knowing the exact category, that is, it shows high precision rates but low recall rates. We designed and implemented a new web search engine to resolve the problems of directory search method. It regards a category as a fuzzy set which contains keywords and calculate the degree of inclusion between categories. The merit of this method is to enhance the recall rate of directory searching by expanding subcategories on the basis of similarity.

• Journal of Biomedical Engineering Research
• /
• v.36 no.4
• /
• pp.128-134
• /
• 2015

Recently, the structured data format in RDF/OWL has played an increasingly vital role in the semantic web. We converted pediatric and oncologic nuclear medicine imaging reports in free text into RDF/OWL format and evaluated the usefulness of nuclear medicine imaging reports in RDF/OWL by comparing SPARQL query results with the manually retrieved results by physicians from the reports in free text. SPARQL query showed 95% recall for simple queries and 91% recall for dedicated queries. In total, SPARQL query retrieved 93% (51 lesions of 55) recall and 100% precision for 20 clinical query items. All query results missed by SPARQL query were of some inference. Nuclear medicine imaging reports in the format of RDF/OWL were very useful for retrieving simple and dedicated query results using SPARQL query. Further study using more number of cases and knowledge for inference is warranted.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.7B
• /
• pp.968-974
• /
• 2001

최근 정보통신기술의 발전과 함께 영상매체의 급속한 증가로 영상의 효율적인 관리와 검색의 필요성이 요구되면서 내용기반 영상검색이 핵심기술로 대두되고 있다. 내용기반 영상검색에서 영상의 특징을 표현하기 위해 색상 히스토그램을 많이 사용하고 있으나, 색상만을 고려하는 것은 많은 단점을 지니고 있으므로 본 논문에서는 먼저 순차영역분할(sequential clustering)기법을 도입하여 영역을 분할하며, 분할된 영역의 색상평균값과 영역의 중심점으로부터의 거리 히스토그램을 영상의 특징으로 구하여 이를 비교함으로써 색상과 공간정보를 함께 고려하는 방법을 제안한다. 제안된 방법의 특성의 수가 18개로 타 방법보다 매우 작은 저장공간을 가지면서도 동시에 검색효율이 8.5% 이상 개선되었다. Precision 대 Recall에서도 각 질의영상에서 대부분의 Recall 값에서 제안한 방법의 우수함이 확인되었으며, 시각적으로도 양호한 검색결과를 얻을 수 있었다.