• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.3
• /
• pp.263-267
• /
• 2005

Building classifiers for financial real-world classification problems is often plagued by severely overlapping and highly skewed class distribution. New performance measures such as receiver operating characteristic (ROC) curve and area under ROC curve (AUC) have been recently introduced in evaluating and building classifiers for those kind of problems. They are, however, in-effective to evaluation of classifier's discrimination performance in a particular class of the classification problems that interests lie in only a local operating range of the classifier, In this paper, a new method is proposed that enables us to directly improve classifier's discrimination performance at a desired local operating range by defining and optimizing a partial area under ROC curve or domain-specific curve, which is difficult to achieve with conventional classification accuracy based learning methods. The effectiveness of the proposed approach is demonstrated in terms of fraud detection capability in a real-world fraud detection problem compared with the MSE-based approach.

• Journal of Positioning, Navigation, and Timing
• /
• v.6 no.3
• /
• pp.87-94
• /
• 2017

GNSS modernization and development is in progress throughout the globe, and it is focused on the addition of a new navigation signal. Accordingly, for the next-generation GNSS signals that have been developed or are under development, various combinations that are different from the existing GNSS signal structures can be introduced. In this regard, to design an advanced signal, it is essential to clearly understand the effects of the signal structure and design variables. In the present study, the effects of the GNSS spreading code period and GNSS data bit duration (i.e., signal design variables) on the signal processing performance were analyzed when the data bit transition was considered, based on selected GNSS signal design scenarios. In addition, a method of utilizing the obtained result for the design of a new GNSS signal was investigated.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.38 no.4
• /
• pp.255-255
• /
• 2012

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.335-337
• /
• 2024

This paper presents a new open-world object detection method emphasizing uncertainty representation in machine learning models. The focus is on adapting to real-world uncertainties, incrementally updating the model's knowledge repository for dynamic scenarios. Applications like autonomous vehicles benefit from improved multi-class classification accuracy. The paper reviews challenges in existing methodologies, stressing the need for universal detectors capable of handling unknown classes. Future directions propose collaboration, integration of language models, to improve the adaptability and applicability of open-world object detection.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.215-221
• /
• 2023

If the C++ programming class, an object-oriented language capable of modeling similar to the real world, is developed as a curriculum that introduces the flipped learning model, students' active problem-solving skills can be cultivated. In this subject development case, it is significant that the flipped learning technique was applied to the programming class and was effective in improving students' active problem-solving skills. First, the lectures in the 4th session were divided into Pre-Class, In-Class, and Post-Class, and the class was conducted in a way that suggested class goals suitable for the subject and formed a team to discuss. At the end of the lecture, a follow-up survey was conducted to check whether the learners learned effectively.

• Biomaterials Research
• /
• v.22 no.4
• /
• pp.303-310
• /
• 2018

Background: Photodynamic therapy (PDT) is photo-treatment of malignant or benign diseases using photosensitizing agents, light, and oxygen which generates cytotoxic reactive oxygens and induces tumour regressions. Several photodynamic treatments have been extensively studied and the photosensitizers (PS) are key to their biological efficacy, while laser and oxygen allow to appropriate and flexible delivery for treatment of diseases. Introduction: In presence of oxygen and the specific light triggering, PS is activated from its ground state into an excited singlet state, generates reactive oxygen species (ROS) and induces apoptosis of cancer tissues. Those PS can be divided by its specific efficiency of ROS generation, absorption wavelength and chemical structure. Main body: Up to dates, several PS were approved for clinical applications or under clinical trials. $Photofrin^{(R)}$ is the first clinically approved photosensitizer for the treatment of cancer. The second generation of PS, Porfimer sodium ($Photofrin^{(R)}$), Temoporfin ($Foscan^{(R)}$), Motexafin lutetium, Palladium bacteriopheophorbide, $Purlytin^{(R)}$, Verteporfin ($Visudyne{(R)}$), Talaporfin ($Laserphyrin^{(R)}$) are clinically approved or under-clinical trials. Now, third generation of PS, which can dramatically improve cancer-targeting efficiency by chemical modification, nano-delivery system or antibody conjugation, are extensively studied for clinical development. Conclusion: Here, we discuss up-to-date information on FDA-approved photodynamic agents, the clinical benefits of these agents. However, PDT is still dearth for the treatment of diseases in specifically deep tissue cancer. Next generation PS will be addressed in the future for PDT. We also provide clinical unmet need for the design of new photosensitizers.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.9-15
• /
• 2023

A common language for modeling software requirements and design in recent years is Unified Modeling Language (UML). Essential principles and rules are provided by UML to help visualize and comprehend complex software systems. It has therefore been incorporated into the curriculum for software engineering courses at several institutions all around the world. However, it is commonly recognized that UML is challenging for beginners to understand, mostly owing to its complexity and ill-defined nature. It is unavoidable that we need to comprehend their preferences and issues considerably better than we do presently to approach the problem of teaching UML to beginner students in an acceptable manner. This paper offers a hint-based approach that can be implemented along with an ordinary lab task. Some keywords are highlighted to indicate class diagram components and make students understand the textual descriptions. The experimental results indicate significant improvement in students' learning skills. Furthermore, the majority of students also positively responded to the survey conducted in the end experimental study.

• International Journal of Computer Science & Network Security
• /
• v.24 no.6
• /
• pp.180-186
• /
• 2024

A common language for modelling software requirements and design in recent years is Unified Modeling Language (UML). Essential principles and rules are provided by UML to help visualize and comprehend complex software systems. It has therefore been incorporated into the curriculum for software engineering courses at several institutions all around the world. However, it is commonly recognized that UML is challenging for beginners to understand, mostly owing to its complexity and ill-defined nature. It is unavoidable that we need to comprehend their preferences and issues considerably better than we do presently in order to approach the problem of teaching UML to beginner students in an acceptable manner. This paper offers a hint based approach that can be implemented along with an ordinary lab task. Some keywords are heighted to indicate class diagram component and make students to understand the textual descriptions. The experimental results indicate significant improvement in students learning skills. Furthermore, majority of students also positively responded to the survey conducted in the end experimental study.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.331-339
• /
• 2023

In programming classes, there is always a need to efficiently manage programming assignments. This is especially important as class sizes and assignment complexity grows. GitHub and GitHub Classroom makes the management of student assignments much simpler than uploading files and folders to a LMS or shared online drive. Additionally, git and GitHub are industry standard tools, so introducing students these tools in class provides them a good opportunity to start learning about how software is developed in the real-world. This study describes a workflow that uses both GitHub Pages and GitHub Classroom for more efficient classroom and assignment management. The workflow outlined in this study was used in two practical web programming classes in Spring 2023 with 46 third and fourth-year university students. GitHub Pages was used as a classroom website to distribute class announcements, assignments, lecture slides, study guides, and exams. GitHub Classroom was used as a class roster and assignment management platform. The workflow presented in this study is expected to assist other lecturers with the formidable tasks of distributing, collecting, grading, and leaving feedback on multiple students' multi-file programming assignments in practical programming classes.