• Nuclear Engineering and Technology
• /
• 제53권7호
• /
• pp.2341-2347
• /
• 2021

Because single-photon emission computed tomography (SPECT) is one of the widely used nuclear medicine imaging systems, it is extremely important to acquire high-quality images for diagnosis. In this study, we designed a super-resolution (SR) technique using dense block-based deep convolutional neural network (CNN) and evaluated the algorithm on real SPECT phantom images. To acquire the phantom images, a real SPECT system using a^99mTc source and two physical phantoms was used. To confirm the image quality, the noise properties and visual quality metric evaluation parameters were calculated. The results demonstrate that our proposed method delivers a more valid SR improvement by using dense block-based deep CNNs as compared to conventional reconstruction techniques. In particular, when the proposed method was used, the quantitative performance was improved from 1.2 to 5.0 times compared to the result of using the conventional iterative reconstruction. Here, we confirmed the effects on the image quality of the resulting SR image, and our proposed technique was shown to be effective for nuclear medicine imaging.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4456-4475
• /
• 2021

The system for re-identifying persons is used to find and verify the persons crossing through different spots using various cameras. Much research has been done to re-identify the person by utilising features with deep-learned or hand-crafted information. Deep learning techniques segregate and analyse the features of their layers in various forms, and the output is complex feature vectors. This paper proposes a distinctive framework called Integrated Level Feature Pattern (ILFP) framework, which integrates local and global features. A new deep learning architecture named modified XceptionNet (m-XceptionNet) is also proposed in this work, which extracts the global features effectively with lesser complexity. The proposed framework gives better performance in Rank1 metric for Market1501 (96.15%), CUHK03 (82.29%) and the newly created NEC01 (96.66%) datasets than the existing works. The mean Average Precision (mAP) calculated using the proposed framework gives 92%, 85% and 98%, respectively, for the same datasets.

• 융합신호처리학회논문지
• /
• 제23권3호
• /
• pp.143-149
• /
• 2022

This excerpt delineates a quantitative measure of relationship between a research title and its respective abstract extracted from different journal articles documented through a Korean Citation Index (KCI) database published through various journals. In this paper, we propose a machine learning-based similarity metric that does not assume normality on dataset, realizes the imbalanced dataset problem, and zero-variance problem that affects most of the rule-based algorithms. The advantage of using this algorithm is that, it eliminates the limitations experienced by Pearson correlation coefficient (r) and additionally, it solves imbalanced dataset problem. A total of 107 journal articles collected from the database were used to develop a corpus with authors, year of publication, title, and an abstract per each. Based on the experimental results, the proposed algorithm achieved high correlation coefficient values compared to others which are cosine similarity, euclidean, and pearson correlation coefficients by scoring a maximum correlation of 1, whereas others had obtained non-a-number value to some experiments. With these results, we found that an effective title must have high correlation coefficient with the respective abstract.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2021년도 제33회 한글 및 한국어 정보처리 학술대회
• /
• pp.293-299
• /
• 2021

본 논문은 외국어 학습을 위한 딥러닝 기반 영어 교육 플랫폼인 PEEP-Talk (Personalized English Education Platform)을 제안한다. PEEP-Talk는 딥러닝 기반 페르소나 대화 시스템과 영어 문법 교정 피드백 기능이 내장된 교육용 플랫폼이다. 또한 기존 페르소나 대화시스템과 다르게 대화의 흐름이 벗어날 시 이를 자동으로 판단하여 대화 주제를 실시간으로 변경할 수 있는 CD (Context Detector) 모듈을 제안하며 이를 적용하여 실제 사람과 대화하는 듯한 느낌을 사용자에게 줄 수 있다. 본 논문은 PEEP-Talk의 각 모듈에 대한 정량적인 분석과 더불어 CD 모듈을 객관적으로 판단할 수 있는 새로운 성능 평가지표인 CDM (Context Detector Metric)을 기반으로 PEEP-Talk의 강건함을 검증하였다. 이와 더불어 PEEP-Talk를 카카오톡 채널을 이용하여 배포하였다.

• 산업경영시스템학회지
• /
• 제47권2호
• /
• pp.21-29
• /
• 2024

Fueled by international efforts towards AI standardization, including those by the European Commission, the United States, and international organizations, this study introduces a AI-driven framework for analyzing advancements in drone technology. Utilizing project data retrieved from the NTIS DB via the "drone" keyword, the framework employs a diverse toolkit of supervised learning methods (Keras MLP, XGboost, LightGBM, and CatBoost) enhanced by BERTopic (natural language analysis tool). This multifaceted approach ensures both comprehensive data quality evaluation and in-depth structural analysis of documents. Furthermore, a 6T-based classification method refines non-applicable data for year-on-year AI analysis, demonstrably improving accuracy as measured by accuracy metric. Utilizing AI's power, including GPT-4, this research unveils year-on-year trends in emerging keywords and employs them to generate detailed summaries, enabling efficient processing of large text datasets and offering an AI analysis system applicable to policy domains. Notably, this study not only advances methodologies aligned with AI Act standards but also lays the groundwork for responsible AI implementation through analysis of government research and development investments.

• 한국식품영양학회지
• /
• 제37권4호
• /
• pp.197-210
• /
• 2024

This study aims to develop a deep learning model to monitor rice serving amounts in institutional foodservice, enhancing personalized nutrition management. The goal is to identify the best convolutional neural network (CNN) for detecting rice quantities on serving trays, addressing balanced dietary intake challenges. Both a vanilla CNN and 12 pre-trained CNNs were tested, using features extracted from images of varying rice quantities on white trays. Configurations included optimizers, image generation, dropout, feature extraction, and fine-tuning, with top-1 validation accuracy as the evaluation metric. The vanilla CNN achieved 60% top-1 validation accuracy, while pre-trained CNNs significantly improved performance, reaching up to 90% accuracy. MobileNetV2, suitable for mobile devices, achieved a minimum 76% accuracy. These results suggest the model can effectively monitor rice servings, with potential for improvement through ongoing data collection and training. This development represents a significant advancement in personalized nutrition management, with high validation accuracy indicating its potential utility in dietary management. Continuous improvement based on expanding datasets promises enhanced precision and reliability, contributing to better health outcomes.

• Advances in nano research
• /
• 제17권2호
• /
• pp.149-155
• /
• 2024

It is argued that advanced nanostructures must be integrated into ideological teaching to provide avenues for enhanced student engagement in active learning, with the ultimate goal of creating critical thinking across disciplines. In this regard, educational strategies that correspondingly address the unique structures and applications of the concept could be considered for further study, which would avail students the opportunity for interactive involvement in the educational process. This paper reflects on the potential of nano-enhanced education tools, such as nanosensors and nano-based interactive displays, in providing dynamic and responsive educational environments. It then proceeds to examine exactly how present students-using these technologies, also in the near future-can be equipped to engage with multiple ideas and perspectives to use in application. According to the findings presented, the use of advanced nanostructures in education will enhance effectiveness in methodologies of teaching and learning while preparing students for their future challenges by providing them with skills to navigate and analyze complex ideological landscapes. It is succeeded by the knowledge integration metric, which moved from an initial 61% to 87%, thereby growing by 42.62%.

• 한국멀티미디어학회논문지
• /
• 제21권5호
• /
• pp.617-625
• /
• 2018

Phishing website has become a crucial concern in cyber security applications. It is performed by fraudulently deceiving users with the aim of obtaining their sensitive information such as bank account information, credit card, username, and password. The threat has led to huge losses to online retailers, e-business platform, financial institutions, and to name but a few. One way to build anti-phishing detection mechanism is to construct classification algorithm based on machine learning techniques. The objective of this paper is to compare different classifier ensemble approaches, i.e. random forest, rotation forest, gradient boosted machine, and extreme gradient boosting against single classifiers, i.e. decision tree, classification and regression tree, and credal decision tree in the case of website phishing. Area under ROC curve (AUC) is employed as a performance metric, whilst statistical tests are used as baseline indicator of significance evaluation among classifiers. The paper contributes the existing literature on making a benchmark of classifier ensembles for web phishing detection.

• 한국멀티미디어학회논문지
• /
• 제23권8호
• /
• pp.927-939
• /
• 2020

Gait recognition can identify people's identity from a long distance, which is very important for improving the intelligence of the monitoring system. Among many human features, gait features have the advantages of being remotely available, robust, and secure. Traditional gait feature extraction, affected by the development of behavior recognition, can only rely on manual feature extraction, which cannot meet the needs of fine gait recognition. The emergence of deep convolutional neural networks has made researchers get rid of complex feature design engineering, and can automatically learn available features through data, which has been widely used. In this paper,conduct feature metric learning in the three-dimensional space by combining the three-dimensional convolution features of the gait sequence and the Siamese structure. This method can capture the information of spatial dimension and time dimension from the continuous periodic gait sequence, and further improve the accuracy and practicability of gait recognition.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 추계 학술대회 학술발표 논문집
• /
• pp.53-56
• /
• 2003

유사도 혹은 자료간의 거리 개념은 많은 기계학습 알고리즘에서 사용되고 있는 중요한 측정개념이다 하지만 입력되는 자료의 속성들중 순서가 정의되지 않은 범주형 속성이 포함되어 있는 경우, 자료간의 유사도나 거리 측정에 어려움이 따른다. 비거리 기반의 알고리즘들의 경우-C4.5, CART-거리의 측정없이 작동할 수 있지만, 거리기반의 알고리즘들의 경우 범주형 속성의 거리 정보 결여로 효과적으로 적용될 수 없는 문제점을 갖고 있다. 본 논문에서는 이러한 범주형 자료들간 거리 측정을 자료 집합의 특성을 충분히 고려한 방법을 제안한다. 이를 위해 자료 집합의 선험적인 정보를 필요로 한다. 이런 선험적 정보인 조건부 확률을 기반으로한 거리 측정방법을 제시하고 오류 피드백을 통해서 속성 간 거리 측정을 최적화 하려고 노력한다. 주어진 자료 집합에 대해 서로 다른 두 범주형 값이 목적 속성에 대해서 유사한 분포를 보인다면 이들 값들은 비교적 가까운 거리로 결정한다 이렇게 결정된 거리를 기반으로 학습 단계를 진행하며 이때 발생한 오류들에 대해 피드백 작업을 진행한다. UCI Machine Learning Repository의 자료들을 이용한 실험 결과를 통해 제안한 거리 측정 방법의 우수한 성능을 확인하였다.