보편적인 스마트폰의 사용이 ICT의 발달을 견인하고 있다. 스마트폰의 스펙이 높아지면서 PC를 대체해 가고 있고 특히, 스마트폰에 카메라, GPS를 비롯한 다양한 센서가 탑재되면서 PC가 할 수 없는 영역까지 확정 되어 실생활에서 반드시 필요한 기기가 되고 있다. 빅데이터 기술의 발달과 ICT의 발달로 인해 이미지 검색이 가능한 시대가 되면서 개인 식별정보가 다양해지고 있다. 개인을 식별할 수 있는 정보 및 파일이 스마트폰을 통 해 쉽게 생성되고, 저장되고 있다. 개인의 사생활에 관련된 사진이나 동영상의 경우 유출 시 그 피해가 개인에 크게 다가온다. 고정적이고 쉽게 변하지 않는 정보인 정적인 정보와 다르게 동적인 정보의 유출이 개인에게는 더 큰 피해를 준다. 개인의 사생활에 해당되는 동적인 정보를 보호하고, 유출을 막을 수 있는 기법이 필요하다. 본 논문에서는 동적인 정보 중에서 스마트폰으로 찍은 동영상의 유출을 막을 수 있는 기법을 제안하고자 한다. 스마트폰에서 다른 단말기로 이동된 동영상은 인증 없이는 재생되지 않도록 기법을 제안한다. 이를 위해 동영상 에 DRM 기술을 접목하여 보호하고자 한다. 스마트폰 분실로 인한 동영상 유출의 경우 인증서를 이용하여 분실 여부를 확인하고, 동영상을 재생하는 기법이 필요하다.

핀테크 환경에서 다양한 서비스를 제공하기 위해 스마트 폰을 대표적으로 사용하고 있다. 또한, 스마트 폰에서의 안 전한 서비스를 이용하기 위해 사용자 인증기술이 요구되고 있다. 인증하기 위해 PIN이나 패스워드를 입력하고 완료 버튼을 터치한 순간 서버에 인증정보를 전달하여 인증을 수행한다. 하지만 카메라 등을 이용한 레코딩 공격, 엿보기 공격이 아니더라 도 터치스크린 사용 흔적인 스머지가 남게 되어 사후 공격이 가능하다. 스머지 공격을 차단하기 위해 사용자는 인증 후 사용 자는 지문을 지워야 한다. 본 연구에서 지문 지우기 여부를 판단할 수 있는 기법을 제안하였다. 제안기법은 PIN를 입력한 다 음에 터치한 흔적인 지문 지우기를 수행하고, 지우기 여부를 판단되면 자동으로 입력 완료 버튼 대신에 처리하는 보안 키패드 를 설계하였다. 패스워드 입력시 반드시 지문을 지우는 동작을 요구하는 방식이다. 이 기법을 통해 사용자는 반드시 지문 지 우기를 해야만 서비스 요청이 완료되어 스머지 공격을 차단할 수 있다.

개인별 서비스를 위한 ID 기반 인증으로 ID가 식별정보로 활용되고, 패스워드가 사용자 인증에 사용된다. 안전한 사 용자 인증을 위해 패스워드는 클라이언트에서 해시값으로 생성하여 서버에 전달되고 서버에 저장된 정보와 해시값을 비교하 며 인증을 수행한다. 하지만 패스워드의 해시값은 패스워드에서 한 개라도 틀리면 전혀 다른 해시값이 생성되어 사용자 인증 에 실패하여 패스워드에 의한 다양한 기능을 적용할 수 없다. 본 연구에서는 입력된 패스워드의 해시값을 허수를 포함하여 여 러 개 생성하고 서버에 전송해서 인증을 수행한다. 또한 제안 기법에서는 여러 권한을 가진 사용자가 하나의 계정으로 다양한 권한을 부여받을 수 있도록 패스워드에 따라 권한을 차등적으로 부여할 수 있다. 제안 기법을 통해 허수 패스워드를 생성함으 로써 엿보기 공격을 차단하고, 패스워드 기반으로 권한을 부여하므로 다양한 권한을 가진 사용자에게 편리성을 제공할 수 있다.

Recently, image recognition technology using deep learning has improved significantly, and security systems and home services that use biometric information such as fingerprints, iris scans, and face recognition are attracting attention. In particular, user authentication methods that utilize face recognition have been studied at length. This study presents a visitor authentication technology that uses CCTV with a Jetson Nano and webcam. In the preprocessing phase for face recognition, face data with 7 features that can be identified as a person are collected using CCTV. The collected dataset goes through the annotation process to classify the data, and facial features are detected using deep learning. If there are four or more detected features, the image data is determined to be a person, and the visitor’s face is matched with stored user data in detail using 81 feature vectors. Additionally, the security of the access control system was enhanced by implementing logging functions such as recording the face of the visitor, the number of visitors, and the time of the visit. This paper implements a visitor authentication system using a Jetson Nano and evaluates performance by analyzing the accuracy and detection speed of the system. The tiny-YOLOv3 in the Jetson Nano was effective in real-time verification for the real-time face authentication system with an average detection speed of 6.5 FPS and 86.3% accuracy. Through this study, we designed a system based on deep learning technology that recognizes and authenticates the face of a user during the visitor access process and controls user access.

Background: Information and communication technology development provides services to various fields. In particular, the development of mobile technology has made ubiquitous services possible. However, as technology advances, security is being emphasized more and more. The existing method of user authentication by entering an ID and password is likely to leak sensitive information if the server is attacked or keylogged. Therefore, multi-level authentication is needed to prevent server attacks or keylogging. Methods: Biometric authentication technology has been utilized by smartphones, but it is challenging to apply in the case of a lost device because the central server does not manage biometric data. Encrypting transactions through blockchain technology makes data management more secure because blockchain technology is distributed, and there is no primary target for hackers. Results: The method proposed in this study can become a basis for an authentication method that guarantees both security and integrity due to the synergetic use of biometric and blockchain technologies. Conclusions: The information stored in the service provider does not include sensitive information such as the user’s biometric data but is only a means of verifying the user’s information in the blockchain transaction with guaranteed anonymity. Therefore, users can receive services with confidence and safety.

핀테크 환경에서 스마트 폰을 이용한 금융거래가 활발하게 이루어지고 있다. 안전한 금융거래를 위해 사용자 인증 기술이 필수적이다. 기존 보안 키패드를 통한 PIN 인증은 입력 편리성이 좋지만, 보안성이 떨어지고 취약점이 존재한다. 생 체인증 기법은 보안성이 안전하지만 오탐 및 미탐 인증 가능성이 있다. 이를 보완하기 위해 2-factor 인증을 사용한다. 본 논 문에서는 생체인증 기법을 적용한 PIN 입력을 통해 편리성과 보안성을 높일 수 있는 1.5-factor 인증을 제안하고자 한다. 지 문인증의 안정성과 2~4번의 PIN 입력을 통해 편리성을 제공하여 안전한 금융거래가 가능하다. 제안기법은 PIN 입력 시 생 체인증을 동시에 수행하므로 PIN 입력할 때 터치하는 영역에 지문인식을 적용하는 방식이다. 보안이 요구되는 경우 높은 안 전성이 요구되는 상황에서는 추가적인 PIN 입력을 통해 입력 편리성을 보장하면서 사용자 인증을 수행하여 안전한 금융거래 가 가능하다.

We propose a study to predict health abnormalities by analyzing body temperature and the heart rate variability parameters of pulse waves. The research method firstly selects fever by applying a deep learning model to thermal images, and secondly, extracts heart rate variability from pulse waves through a photo-plethysmograph sensor. It analyzes the relevance of body temperature and health status by dividing the presence or absence of fever cases and comparing parameters related to autonomic nerves and stress cases. As a result of the experiment, the control group with normal body temperature had a mean pulse variability of 37.65, SDNN of 64.83, and RMSSD of 42.24. In contrast, in the experimental group, which consisted of individuals with fever, the average pulse variability was 31.91, the SDNN was 42.34, and the RMSSD was 26.80. Our research expects to be applicable to a thermal imaging system that can measure body temperature and bio-signals together and show the predicted results of health status for fever cases.

최근, 코로나 19로 인해 전염병에 대응하기 위해 전 국민의 백신 접종을 독려하고, 이로 인해 집단 면역 을 구축하고자 노력하고 있다. 개인이 어려서부터 다양한 전염병에 대한 백신 예방 접종을 하고 있지만 백신 접 종내역 및 접종일자를 기억하기 쉽지 않다. 특히, 여러 차례 접종하거나 주기적으로 접종해야 하는 경우, 효과적 인 방역을 위한 경우 백신 접종 사실을 확인할 필요가 있다. 국내에서는 코로나 19의 백신접종 사실을 확인한 후 에 출입을 허용하는 방역에서는 특히, 더 필요하다. 해외 여행시 백신접종 사실이 더욱 필요한 상태이지만 증명 서의 위변조 가능성이 있어 이를 대응할 수 있는 연구가 필요하다. 블록체인 기술은 생성된 정보를 체인으로 연 결되어 정보의 무결성을 보장하고, 신뢰기관에서 접종사실을 등록함으로써 정보의 신뢰성을 보장한다. 최근 DID 기술을 활용하여 개인의 신원을 블록체인에 분산 저장하고 검증한다. 백신접종 내역 정보를 저장하고, 정보의 제 어권을 개인에게 부여할 수 있는 DID 기반 위에서 신뢰성있게 검증할 수 있는 기법을 설계하였다.

On account of prevalence of mobile devices, a variety of mobile-based services have been conducted recently. In this situation, it is possible to serve the information that fits to users’ requests according to the users’ context using mobile devices. Therefore, it is necessary to research data mining techniques with mobile devices. Therefore, we researched information retrieval system in mobile environment. We applied semantic data mining method with context information ontology. These techniques of semantic information retrieval can provide the information according to users’ context information such as location, weather, user preference etc. exactly and rapidly anytime and anyplace. In modern society, it is essential to develop mobile information retrieval system which is efficient to users. Also, the system can provide users’ current location and the location information with Google map APIs in mobile devices. Therefore, in this paper, we researched semantic data mining technique with context information ontology using mobile techniques. And we compared and evaluated our proposed model and the existing model in three areas and showed our proposed model has higher performance.

Although the internet has gained many conveniences and benefits, it is causing economic and social damage to users due to intelligent malware. Most of the signature-based anti-virus programs are used to detect and defend this, but it is insufficient to prevent malware variants becoming more intelligent. Therefore, we proposes a model that detects and defends the intelligent malware that is pouring out in the paper. The proposed model learns by imaging the characteristics of malware based on deeplearning, and detects newly detected malware variants using the learned model. It was shown that the proposed model detects not only the existing malware but also most of the variants that transform the existing malware.

Due to COVID-19, non-F2F (non-face-to-face) learning is being conducted in educational sites around the world. Unlike theoretical subjects, which have a variety of applicable non-F2F learning content, in practical subjects, learners may undergo many difficulties due to many learning activities. Therefore, this research tries to design and develop a mobile application that allows learners to perform a self-diagnostic on their learning progress. In this research, we conducted a mobile application usability evaluation for 36 students who participated in non-F2F Arduino practice learning. To this end, we applied the ADDIE (Analysis, Design, Development, Implement, and Evaluation) model to develop a self-diagnostic mobile application for students’ learning progress according to the learning content. The research tool modified and distributed the question item appropriate for this subject’s study for the mobile usability evaluation that was used in the previous study. This research applied the ADDIE model to analyze the characteristics of students and learning contents, including designed learning contents, database, menu structure, developed learning contents, and mobile application. After using this in non-F2F practice learning for 15 weeks, a mobile application usability evaluation was conducted. As a result of the study, due to receiving usability scores between 3.53 and 4.42, it was found that the learning progress self-diagnostic in non-F2F practice learning was essential and that mobile applications were useful in non-F2F practice learning. Additionally, 33 out of 36 students responded that it would be useful for their learning if they actively used it in other subjects as well. We have found that leveraging self-diagnostic mobile applications through the mobile application usability evaluation tool can be useful for non-F2F practice learning. Additionally, it is expected to be useful for non-F2F practice learning if additional research is conducted on other factors as well such as teaching presence, online learning engagement, and learning flow in the future.

As a way to solve the side effects of urban development, a smart city with information and communication technology converges in the city is being built. For this, a smart city platform should support the development and integration of smart city services. Therefore, the underlying technology and the functional and non-functional requirements that the smart platform must support were analyzed. As a result of this, we classified the Internet of Things, cloud computing, big data and cyber-physical systems into four categories as the underlying technologies supported by the smart city platform, and derived the functional and non-functional requirements that can be implemented and the reference model of the smart city platform. The reference model of the smart city platform is used for decision-making on investment in infrastructure technology and the development scope of services according to functional or non-functional requirements to solve specific city problems for city managers. It provides platform developers with guidelines to identify and determine the functional and non-functional requirements and implementation technologies of software platforms for building smart cities.

Due to the development of the recent ICT (Information and Communication Technology), ICT has been applied to the agriculture and it is improving the productivity and quality of the crop through its utilization. In addition, with the realization of fast networks like 5G, IoT (Internet of Things) technology which can link various things around us has been applied in various aspects of life. Consequently, the services and related markets applying it are expected to grow greatly in the future. On the other hand, in the field of crop cultivation, it was possible to improve productivity by spraying fertilizer or pesticide on crops in the past, but for consumers who seek healthy food, they want to be eco-friendly, and cause no harm to the health of crops. In this paper, we develop an ultrasonic wave emission system based on multimedia database in a smart farm using ICT. Through this, environmental information of crops growing in smart farm is collected by using IoT device and is managed by multimedia database. In addition, by providing an optimal environment through ultrasonic wave emission, we can promote crop growth and suppress diseases and pests. Also, this system stores and manages multimedia data such as temperature, humidity, and ultrasonic waves, and suggests a method of extracting knowledge information for ultrasonic emission based on this. In order to prevent transmission delay time between each component, we also propose optimization methods for database processing. Using the system developed in this paper, it will be possible to make consumers interested in finding healthy food by cultivating more eco-friendly crops.

Recently, many safety accidents involving children shuttle buses take place. Without a teacher for help, a safety accident occurs when the driver can’t see a child who is getting off in the blind spot of both frontside and backside. A deep learning-based smart mirror allows user authentication and provides various services. Especially, It can be a role of helper for children, and prevent accidents that can occur when drivers or assistant teachers do not see them. User authentication is carried out with children’s face registered in advance. Safety accidents can be prevented by an approximate sensor and a camera in frontside and backside of the bus. This study suggests a way of checking out whether children are missed in the process of getting in and out of the bus, designs a system that reduce blind spots in the front and back of the vehicle, and builds a safety system that provide various services using GPS

User authentication has become an essential security element that enables a wide range of applications in P2P systems for higher security and safety requirements. In previous, many researchers worked on user authentication based on certificates, passwords, and feature-based authentication (e.g. face recognition, fingerprint detection, iris recognition, voice recognition). However, authentication using those technologies may fail because this information can be easily shared among users or synthesized. Also, there are several cyber and cryptography attacks. With the progress of the latest sensor technology, wearable as Microsoft Bands, Fitbit, and Garmin has provided for more information collecting opportunities. From those above point of views, this paper presents a novel user identification system based on the bio signal analysis of arm movement (3-axis accelerometer & 3-axis gyroscope) and electromyography (EMG) signal using Myo armband as a wearable user authentication system in P2P system that identifies users based on the bio-signal of movement of a person's arm. In this study, the gesture and EMG signals are obtained from the sensor and denoised using wavelet denoising algorithm. The denoised signals are analyzed using the envelope and cepstrum analysis for extracting the potential feature vector. Finally, the feature vector is used to train and identify a user using multi-class support vector machine (MC-SVM) with different kernel function for user authentication. For validating the proposed authentication model, signals are obtained from the arm movements, i.e., directions and hand gesture data using acceleration, gyroscope and EMG sensors of several subjects. According to the experimental results, the proposed model shows satisfactory performance. To evaluate the efficiency of the proposed systems, we measure and compare its classification accuracy with state-of-the-art algorithms. And the proposed algorithm outperforms with others.

최근 원격조종과 자율조종이 가능한 무인항공기(RPAS:Remotely Piloted Aircraft System)가 택배 드론, 소방드론, 구급 드론, 농업용 드론, 예술 드론, 드론 택시 등 각 산업 분야와 공공기관에서의 관심과 활용 이 높아지고 있다. 자율조종이 가능한 무인드론의 안정성 문제는 앞으로 드론 산업의 발달과 함께 진화하면서 해결해야 할 가장 큰 과제이기도 하다. 드론은 자율비행제어 시스템이 지정한 경로로 비행하고 목적지에 정확하 게 자동 착륙을 수행할 수 있어야 한다. 본 연구는 드론의 센서와 GPS의 위치 정보의 오류를 보완하는 방법으 로서 착륙지점 영상을 통해 드론의 도착 여부를 확인하고 정확한 위치에서의 착륙을 제어하는 기법을 제안한다. 서버에서 도착지 영상을 구글맵 API로부터 수신받아 딥러닝으로 학습하고, 드론에 NAVIO2와 라즈베리파이, 카메라를 장착하여 착륙지점의 이미지를 촬영한 다음 이미지를 서버에 전송한다. Deep Learning으로 학습된 결과와 비교하여 임계치에 맞게 드론의 위치를 조정한 후 착륙지점에 자동으로 착륙할 수 있다.

Background/Objectives Deep learning which main technology in AI has high growth with being applied to field of speech recognition and Image classification.Especially, Deep learning technology in the field of Image classification is being applied as a core technology to Self-driving and crime prevention monitoring system that is recently emerging as the future industry.Methods/Statistical analysis: Various algorithm which is improved and developed CNN being able to do image process is suggested as Deep learning model in image recognition field.In this paper, we introduce various object detection algorithm including CNN.And explore most representative algorithms just R-CNN, Fast R-CNN, Faster R-CNN and difference between versions of YOLO devised to detect and track in real time.Findings: This paper evaluates deep learning algorithm's performance by comparative analysis about mAP (mean average precision) and FPS (frames per second).In result of performance evaluation, YOLO algorithm is confirmed as that It shows excellent result in speed that detects and recognizes object and accuracy in real time system environment.Finally, we search cases in field of autonomous driving and access control system and home anti-crime system.Improvements/Applications: In this research, we can understand object detection algorithm among speech recognition technologies and proper field in each algorithm, apply security service based on image, recommend proper algorithm in various environment just like autonomous driving and security work, etc.