• Journal of Broadcast Engineering
• /
• v.24 no.4
• /
• pp.564-572
• /
• 2019

With the development of deep learning, the performance of facial landmark detection methods has been greatly improved. The heat map regression method, which is a representative facial landmark detection method, is widely used as an efficient and robust method. However, the landmark coordinates cannot be directly obtained through a single network, and the accuracy is reduced in determining the landmark coordinates from the heat map. To solve these problems, we propose to combine integral regression with the existing heat map regression method. Through experiments using various datasets, we show that the proposed integral regression network significantly improves the performance of facial landmark detection.

• Journal of Information Technology Applications and Management
• /
• v.31 no.3
• /
• pp.149-163
• /
• 2024

As conversational AI systems such as ChatGPT have become more advanced, researchers are exploring ways to use them in education. However, we need effective ways to evaluate these systems before allowing them to help teach students. This study proposes a detailed framework for testing conversational AI across three important criteria as follow. First, specialized benchmarks that measure skills include giving clear explanations, adapting to context during long dialogues, and maintaining a consistent teaching personality. Second, adaptive standards check whether the systems meet the ethical requirements of privacy, fairness, and transparency. These standards are regularly updated to match societal expectations. Lastly, evaluations were conducted from three perspectives: technical accuracy on test datasets, performance during simulations with groups of virtual students, and feedback from real students and teachers using the system. This framework provides a robust methodology for identifying strengths and weaknesses of conversational AI before its deployment in schools. It emphasizes assessments tailored to the critical qualities of dialogic intelligence, user-centric metrics capturing real-world impact, and ethical alignment through participatory design. Responsible innovation by AI assistants requires evidence that they can enhance accessible, engaging, and personalized education without disrupting teaching effectiveness or student agency.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.1
• /
• pp.105-125
• /
• 2024

Gliomas are the most common malignant brain tumor and cause the most deaths. Manual brain tumor segmentation is expensive, time-consuming, error-prone, and dependent on the radiologist's expertise and experience. Manual brain tumor segmentation outcomes by different radiologists for the same patient may differ. Thus, more robust, and dependable methods are needed. Medical imaging researchers produced numerous semi-automatic and fully automatic brain tumor segmentation algorithms using ML pipelines and accurate (handcrafted feature-based, etc.) or data-driven strategies. Current methods use CNN or handmade features such symmetry analysis, alignment-based features analysis, or textural qualities. CNN approaches provide unsupervised features, while manual features model domain knowledge. Cascaded algorithms may outperform feature-based or data-driven like CNN methods. A revolutionary cascaded strategy is presented that intelligently supplies CNN with past information from handmade feature-based ML algorithms. Each patient receives manual ground truth and four MRI modalities (T1, T1c, T2, and FLAIR). Handcrafted characteristics and deep learning are used to segment brain tumors in a Global Convolutional Neural Network (GCNN). The proposed GCNN architecture with two parallel CNNs, CSPathways CNN (CSPCNN) and MRI Pathways CNN (MRIPCNN), segmented BraTS brain tumors with high accuracy. The proposed model achieved a Dice score of 87% higher than the state of the art. This research could improve brain tumor segmentation, helping clinicians diagnose and treat patients.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.145-154
• /
• 2022

Automatic Target Recognition (ATR) technology is emerging as a core technology of Future Combat Systems (FCS). Conventional ATR is performed based on IMINT (image information) collected from the SAR sensor, and various image-based deep learning models are used. However, with the development of IT and sensing technology, even though data/information related to ATR is expanding to HUMINT (human information) and SIGINT (signal information), ATR still contains image oriented IMINT data only is being used. In complex and diversified battlefield situations, it is difficult to guarantee high-level ATR accuracy and generalization performance with image data alone. Therefore, we propose a knowledge graph-based ATR method that can utilize image and text data simultaneously in this paper. The main idea of the knowledge graph and deep model-based ATR method is to convert the ATR image and text into graphs according to the characteristics of each data, align it to the knowledge graph, and connect the heterogeneous ATR data through the knowledge graph. In order to convert the ATR image into a graph, an object-tag graph consisting of object tags as nodes is generated from the image by using the pre-trained image object recognition model and the vocabulary of the knowledge graph. On the other hand, the ATR text uses the pre-trained language model, TF-IDF, co-occurrence word graph, and the vocabulary of knowledge graph to generate a word graph composed of nodes with key vocabulary for the ATR. The generated two types of graphs are connected to the knowledge graph using the entity alignment model for improvement of the ATR performance from images and texts. To prove the superiority of the proposed method, 227 documents from web documents and 61,714 RDF triples from dbpedia were collected, and comparison experiments were performed on precision, recall, and f1-score in a perspective of the entity alignment..

• The Journal of Korean Society for Radiation Therapy
• /
• v.21 no.2
• /
• pp.89-95
• /
• 2009

Purpose: The purpose is to evaluate efficiency of the CT simulator QA phantom manufactured for daily QA. Materials and Methods: We made holes ($1{\times}100{\times}1\;mm$) to verify accuracy between image and real measurement in polystyrene phantom and made 1 mm holes to verify table movement accuracy at superior and inferior 100 mm to the center of the phantom and inserted radiopacity material. To evaluate laser alignment, we made cross mark on the right and left side at phantom and to evaluate CT number accuracy we made 3 cylindrical holes and inserted equivalence material of bone, water, air in them. After CT scanning the phantom, We evaluated accuracy between image and real measurement, accuracy of table movement, laser, and CT number using exposed image. Results: It was measured that the accuracy between image and real measurement was ${\pm}0.3\;mm$, table movement accuracy was ${\pm}0.3\;mm$, laser accuracy was ${\pm}0.5\;mm$ from 7th January to 7th March in 2008 as within the reference point ${\pm}1\;mm$. In the CT number accuracy of bone was ${\pm}10\;HU$, air was ${\pm}5\;HU$, water was ${\pm}5\;HU$ as within the reference point is ${\pm}10\;HU$. Conclusion: We was able to perform CT simulator QA and laser equipment QA more conveniently and fast using manufactured phantom at the same time. We will be able to make more accurate treatment plan that added to QA procedures using images at previous daily QA.

• Progress in Medical Physics
• /
• v.17 no.4
• /
• pp.192-200
• /
• 2006

We evaluated the positional accuracy of the delivered beams to the target in a phantom by simulating the whole process of the radiation treatments Including CT scanning, planning and beam exposures with MLCs. For this purpose, a phantom was made to calibrate the alignment between the CT and the attached laser system. A new, convenient method was also devised to align the setup lasers in the treatment room. Film was used for the Identification of the delivered beam and analyzed with a homemade computer program. The positional differences between the target and the beam centers varied with the couch rotations. The accelerator we used showed a maximum discrepancy of 2.0 mm at the table angle of $295^{\circ}$. The same measurements based on the new isocenter from the Winston-Lutz test resulted in the maximum of 1.35 mm for all rotation angles. The evaluation of the differences between the target and the beam centers is useful for the treatment planning.

• International Journal of Highway Engineering
• /
• v.9 no.2 s.32
• /
• pp.101-114
• /
• 2007

Dowel bars in the jointed concrete pavement are used to both provide load transfer across pavements joints and prevent the joint faulting leading to longer service life. On the contrary, the misplacement of dowel bar can provide negative results including the joint freezing(locking) that may cause the joint spatting and unexpected mid-slab cracking. The dowel bar can be placed using the assembly or dowel bar inserter (DBI) during the concrete pavement construction. In the domestic practice of the concrete pavement construction, the dowel bar is placed using the assembly method. This study primarily focuses on the comparison of these two dowel placement methods using the field data from the KHC test road in which both dowel placement methods have been applied to a certain length of the concrete pavement. The field data regarding the alignment of the dowel bars placed by both methods was collected using MIT-SCAN2, a nondestructive measuring equipment, and processed to compute Joint Score and Running Ave. Joint Score which are used as indicators of the dowel bar performance. The comparison of the methods for the dowel bar placement using these indicators shows that the DBI method provided much better alignment of the dowel bars reducing the risk of joint freezing than the assembly method. In order to improve the quality of the dowel bar placement using the assembly method, the current weak points of the assembly method including the fabrication, storage, and installation of dowel bar assembly were investigated and the solution was suggested. The improved dowel bar sets based on the suggested solution have been applied to an actual practice of the concrete pavement construction. The field data shows that the improved assembly method suggested in this study can highly reduce the risk of joint freezing.

• Korean Journal of Optics and Photonics
• /
• v.8 no.6
• /
• pp.510-515
• /
• 1997

Packaging takes an extremely important element of optical module cost due primarily to the added complication of alignment between semiconductor devices and optical fiber, and many efforts have been devoted on reducing the cost by eliminating the complicated optical alignment procedures in passive manner. In this study, we fabricated silicon optical benches on which the optical alignments are accomplished passively. To improve the positioning accuracy of a flip-chip bonded LD, we adopted fiducial marks and solder dams which are self-aligned with V-groove etch patterns, and a stand-off to control the height and to improve the heat dissipation of LD. Optical sub-assemblies exhibited an average efficiency of -11.75$\pm$1.75 dB(1$\sigma$) from the LD-to-single mode fiber coupling and an average sensitivity of -35.0$\pm$1.5 dBm from the fiber and photodetector coupling.

• Journal of the Korean Orthopaedic Association
• /
• v.53 no.6
• /
• pp.478-489
• /
• 2018

Total knee arthroplasty has become a standard procedure for advanced knee arthritis to relieve pain and improve function. Computer-assisted navigation systems have been used in total knee arthroplasty to improve the mechanical axis of the limb as well as the alignment and position of the components. A computer-assisted navigation system has the advantage of real-time feedback during surgery, such as mediolateral balance in extension and flexion gap, alignment of the lower limb, and components. On the other hand, the computer-assisted navigation system requires an additional stab wound for tracker fixation, which can increase the likelihood of superficial wound infection and stress fractures and increase the operation time and cost of surgery. The clinical efficacy of computer-assisted navigation in total knee arthroplasty is also controversial. Compared to the conventional technique, computer navigation improves the accuracy of the postoperative mechanical axis within outliers of $3^{\circ}$ varus or $3^{\circ}$ valgus. This paper reviews the surgical technique, pitfalls, clinical and radiological outcomes, useful clinical cases, and future perspectives in computer-assisted navigation total knee arthroplasty.

• KIPS Transactions on Computer and Communication Systems
• /
• v.13 no.1
• /
• pp.21-30
• /
• 2024

As the self-driving car market continues to grow, the need for charging infrastructure is growing. However, in the case of a wireless charging system, stability issues are being raised because it requires a large amount of power compared with conventional wired charging. SAE J2954 is a standard for building autonomous vehicle wireless charging infrastructure, and the standard defines a communication method between a vehicle and a power transmission system. SAE J2954 recommends using physical media such as Wi-Fi, Bluetooth, and UWB as a wireless charging communication method for autonomous vehicles to enable communication between the vehicle and the charging pad. In particular, UWB is a suitable solution for indoor and outdoor charging environments because it exhibits robust communication capabilities in indoor environments and is not sensitive to interference. In this standard, the process for building a wireless power transmission system is divided into several stages from the start to the completion of charging. In this study, UWB technology is used as a means of fine alignment, a process in the wireless power transmission system. To determine the applicability to an actual autonomous vehicle wireless power transmission system, experiments were conducted based on distance, and the distance information was collected from UWB. To improve the accuracy of the distance data obtained from UWB, we propose a Single Model and Multi Model that apply machine learning and deep learning techniques to the collected data through a three-step preprocessing process.