• Title/Summary/Keyword: IoU

Search Result 192, Processing Time 0.029 seconds

Design of Mutual Authentication and Grouping Protocol Based On Network Control Server Applicable to General Purpose (범용적으로 적용 가능한 네트워크제어서버 기반의 상호인증 및 그룹핑 프로토콜 설계)

  • Park, Jungoh
    • Journal of Korea Society of Digital Industry and Information Management
    • /
    • v.13 no.4
    • /
    • pp.13-23
    • /
    • 2017
  • In order to protect personal information and important information (confidential information, sales information, user information, etc.) in the internal network, companies and organizations apply encryption to the Server-To-Server or Server-To-Client communication section, And are experiencing difficulties due to the increasing number of known attacks and intelligent security attacks. In order to apply the existing S / W encryption technology, it is necessary to modify the application. In the financial sector, "Comprehensive Measures to Prevent the Recurrence of Personal Information Leakage in the Domestic Financial Sector" has been issued, and standard guidelines for financial computing security have been laid out, and it is required to expand the whole area of encryption to the internal network. In addition, even in environments such as U-Health and Smart Grid, which are based on the Internet of Things (IoT) environment, which is increasingly used, security requirements for each collection gateway and secure transmission of the transmitted and received data The requirements of the secure channel for the use of the standard are specified in the standard. Therefore, in this paper, we propose a secure encryption algorithm through mutual authentication and grouping for each node through H / W based Network Control Server (NCS) applicable to internal system and IoT environment provided by enterprises and organizations. We propose a protocol design that can set the channel.

Effects of the PNF Stabilization Technique for the Hip Joint and the Bridging Exercise on the Trunk Stabilizer Muscles in Healthy Adults (고관절에 적용한 PNF 안정화 기법과 교각운동이 요부안정화 근육에 미치는 영향)

  • Kim, Yong-Hun;Jung, Ju-Hyeon
    • PNF and Movement
    • /
    • v.15 no.1
    • /
    • pp.51-56
    • /
    • 2017
  • Purpose: The purpose of this study was to examine the effects of the PNF stabilization technique for the hip joint and the bridging exercise on the trunk stabilizer muscles in healthy adults. Methods: Twenty-eight healthy adults were randomly allocated to either a PNF stabilization exercise group (n = 12) or a bridging exercise group (n = 16). The outcome measures included the contraction thickness ratio in the transversus abdominis (TrA), internal oblique (IO), and external oblique (EO), and the TrA lateral slide was assessed during the abdominal drawing-in maneuver using b-mode ultrasound. The researcher measured the abdominal muscle thickness of each participant before the therapist began the intervention and at the moment that the intervention was applied. Between-group comparisons were performed using the Mann-Whitney U test. The level of statistical significance was set at 0.05. Results: The PNF intervention program showed a significant increase in the trunk stabilizer muscle. The percentage of change in the TrA thickness showed a significant interaction between intervention. However, there were no significant differences in the IO and EO between the two groups. Conclusion: The PNF stabilization technique for the hip joint can be used effectively to improve the IO and TrA muscles in healthy adults.

Design Concept Value Competitive Research Between Service Provider and Service Receiver (수면무호흡 환자의 양압기 제품서비스디자인 개발에 대한 서비스 제공자와 수혜자가 느끼는 디자인 컨셉 가치 비교연구)

  • Lee, Sung Pil;Jung, Ju Young;Lee, Sang Ki;Hong, Jung Pyo
    • Journal of Service Research and Studies
    • /
    • v.7 no.4
    • /
    • pp.39-50
    • /
    • 2017
  • As a comparative study on the value of design concept between service provider (Developer) and service receiver (Customer) group, the aims of this study was to present a service model focused on Continuous positive airway pressure (CPAP) based on U-health care and user environment. Double Diamond-based methods led to a case study that conducted jointly by the department of otolaryngology in U hospital, Ulsan. By targeted on Sleep Apnea patients from the stage of diagnosis to CPAP treatment, variety of meaningful experiences have been extracted and classified into several types of customers. In the final analysis of the 13 service scenario models, Kano Satisfaction and Potential Customer Satisfaction Improvement Index (PCSI) were conducted with the customers, yet Score Model and Concept Position were evaluated by the service provider groups who engaged in development services. The results of this study showed that 7 items in the total of 12 items reached a consensus of viewpoint on value between service receiver and service provider, which the attributes of the service model are based on user environment. Whereas the other 5 items showed the divergent viewpoint on value which included the attributes of U-healthcare service model.

Control strategy of primary clarifier operation in wastewater treatment plant during rainfall inflow (초기강우 유입 시 하수처리시설 일차 침전지 운전제어 전략)

  • You, Kwang Tae;Kwon, Hyuk Jae
    • Journal of Korea Water Resources Association
    • /
    • v.52 no.11
    • /
    • pp.947-950
    • /
    • 2019
  • The main feature of this paper is to provide a driving control strategy to improve the primary clarifier treatment efficiency in the initial rainfall inflow. With the recent development of IoT technology and sensing technology, the basis for operation control of wastewater treatment facilities has been improved. As a result of improving the efficiency of treatment of primary clarifier using on-line measurement results, it is possible to minimize the outflow of untreated sewage and contribute to the improvement of operation efficiency of wastewater treatment plants.

Security Architecture for U-Healthcare Application in Wireless Sensor Network (무선 센서 네트워크에서의 유비쿼터스 헬스케어 시스템을 위한 보안 구조)

  • Shin, Yoon-gu;Kim, Hankyu;Kim, Sujin;Kim, Jung Tae
    • Proceedings of the Korean Institute of Information and Commucation Sciences Conference
    • /
    • 2014.05a
    • /
    • pp.884-885
    • /
    • 2014
  • The use of Radio Frequency Identification technology (RFID) in medical context enables not only drug identification, but also a rapid and precise identification of patients, physicians, nurses or any other health care related staffs. The combination of RFID tag identification with structured and secured Internet of Things (IoT) solutions enables ubiquitous and easy access to medical related records, while providing control and security to all interactions. This paper surveyed a basic security architecture, easily deployable on mobile platforms, which would allow to establish and manage a medication prescription service in mobility context making use of electronic personal health records.

  • PDF

Attention Aware Residual U-Net for Biometrics Segmentation (생체 인식 인식 시스템을 위한 주의 인식 잔차 분할)

  • Htet, Aung Si Min;Lee, Hyo Jong
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • 2022.11a
    • /
    • pp.300-302
    • /
    • 2022
  • Palm vein identification has attracted attention due to its distinct characteristics and excellent recognition accuracy. However, many contactless palm vein identification systems suffer from the issue of having low-quality palm images, resulting in degradation of recognition accuracy. This paper proposes the use of U-Net architecture to correctly segment the vascular blood vessel from palm images. Attention gate mechanism and residual block are also utilized to effectively learn the crucial features of a specific segmentation task. The experiments were conducted on CASIA dataset. Hessian-based Jerman filtering method is applied to label the palm vein patterns from the original images, then the network is trained to segment the palm vein features from the background noise. The proposed method has obtained 96.24 IoU coefficient and 98.09 dice coefficient.

U-Healthcare Patch Type Wireless Body Temperature Monitoring System (유헬스케어 패치형 무선 체온 모니터링 시스템 구현)

  • Park, Young-Sang;Kwon, Oeon;Cho, Hyun-Sung;Son, Jaebum
    • Journal of Biomedical Engineering Research
    • /
    • v.41 no.1
    • /
    • pp.55-61
    • /
    • 2020
  • Recently, there have been many research on fever management using u-healthcare technology. Especially, fever of infants requires continuous monitoring of body temperature by parents. For infants between 4 weeks and under 5 years old, it is recommended to use an electronic thermometer or chemical thermometer in the axilla, or to use an infrared thermometer. However, in order to overcome the reality of not being able to waste significant time on continuous monitoring, there have been demands of patch type thermometers with the internet of things (IoT) and wireless communication technologies. Existing IoT thermometers are difficult to attach to infants' body because they do not take into account its size, and their interoperability is not guaranteed because they do not comply with standards in communication. Therefore, in this study, a patch-type thermometer with a diameter of 20 mm and a weight of 2.9 g was developed to manage the fever of infants, while it communicates wirelessly with Bluetooth Low Energy (BLE) communication protocol and complies with IEEE 11073 PHD(Personal Health Device) at the same time. We verified its performance under the requirements of thermometers regulated by the Korean Ministry of Food and Drug Safety.

Deep learning-based apical lesion segmentation from panoramic radiographs

  • Il-Seok, Song;Hak-Kyun, Shin;Ju-Hee, Kang;Jo-Eun, Kim;Kyung-Hoe, Huh;Won-Jin, Yi;Sam-Sun, Lee;Min-Suk, Heo
    • Imaging Science in Dentistry
    • /
    • v.52 no.4
    • /
    • pp.351-357
    • /
    • 2022
  • Purpose: Convolutional neural networks (CNNs) have rapidly emerged as one of the most promising artificial intelligence methods in the field of medical and dental research. CNNs can provide an effective diagnostic methodology allowing for the detection of early-staged diseases. Therefore, this study aimed to evaluate the performance of a deep CNN algorithm for apical lesion segmentation from panoramic radiographs. Materials and Methods: A total of 1000 panoramic images showing apical lesions were separated into training (n=800, 80%), validation (n=100, 10%), and test (n=100, 10%) datasets. The performance of identifying apical lesions was evaluated by calculating the precision, recall, and F1-score. Results: In the test group of 180 apical lesions, 147 lesions were segmented from panoramic radiographs with an intersection over union (IoU) threshold of 0.3. The F1-score values, as a measure of performance, were 0.828, 0.815, and 0.742, respectively, with IoU thresholds of 0.3, 0.4, and 0.5. Conclusion: This study showed the potential utility of a deep learning-guided approach for the segmentation of apical lesions. The deep CNN algorithm using U-Net demonstrated considerably high performance in detecting apical lesions.

U-Net Cloud Detection for the SPARCS Cloud Dataset from Landsat 8 Images (Landsat 8 기반 SPARCS 데이터셋을 이용한 U-Net 구름탐지)

  • Kang, Jonggu;Kim, Geunah;Jeong, Yemin;Kim, Seoyeon;Youn, Youjeong;Cho, Soobin;Lee, Yangwon
    • Korean Journal of Remote Sensing
    • /
    • v.37 no.5_1
    • /
    • pp.1149-1161
    • /
    • 2021
  • With a trend of the utilization of computer vision for satellite images, cloud detection using deep learning also attracts attention recently. In this study, we conducted a U-Net cloud detection modeling using SPARCS (Spatial Procedures for Automated Removal of Cloud and Shadow) Cloud Dataset with the image data augmentation and carried out 10-fold cross-validation for an objective assessment of the model. Asthe result of the blind test for 1800 datasets with 512 by 512 pixels, relatively high performance with the accuracy of 0.821, the precision of 0.847, the recall of 0.821, the F1-score of 0.831, and the IoU (Intersection over Union) of 0.723. Although 14.5% of actual cloud shadows were misclassified as land, and 19.7% of actual clouds were misidentified as land, this can be overcome by increasing the quality and quantity of label datasets. Moreover, a state-of-the-art DeepLab V3+ model and the NAS (Neural Architecture Search) optimization technique can help the cloud detection for CAS500 (Compact Advanced Satellite 500) in South Korea.

A Study on Countermeasures of Convergence for Big Data and Security Threats to Attack DRDoS in U-Healthcare Device (U-Healthcare 기기에서 DRDoS공격 보안위협과 Big Data를 융합한 대응방안 연구)

  • Hur, Yun-A;Lee, Keun-Ho
    • Journal of the Korea Convergence Society
    • /
    • v.6 no.4
    • /
    • pp.243-248
    • /
    • 2015
  • U-Healthcare is a convergence service with medical care and IT which enables to examine, manage and maintain the patient's health any time and any place. For communication conducted in U-Healthcare service, the transmission methods are used that patient's medical checkup analysis results or emergency data are transmitted to hospital server using wireless communication method. At this moment when the attacker who executes the malicious access makes DRDoS(Distributed Reflection DoS) attack to U-Healthcare devices or BS(Base Station), various damages occur that contextual information of urgent patients are not transmitted to hospital server. In order to deal with this problem, this study suggests DRDoS attack scenario and countermeasures against DRDoS and converges with Big Data which could process large amount of packets. When the attacker attacks U-Healthcare devices or BS(Base Station), DB is interconnected and the attack is prevented if it is coincident. This study analyzes the attack method that could occur in U-Healthcare devices or BS which are remote medical service and suggests countermeasures against the security threat using Big Data.