• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권2호
• /
• pp.600-616
• /
• 2021

SIMON and SPECK are two families of lightweight block ciphers that have excellent performance on hardware and software platforms. At CRYPTO 2019, Gohr first introduces the differential cryptanalysis based deep learning on round-reduced SPECK32/64, and finally reduces the remaining security of 11-round SPECK32/64 to roughly 38 bits. In this paper, we are committed to evaluating the safety of SIMON cipher under the neural differential cryptanalysis. We firstly prove theoretically that SIMON is a non-Markov cipher, which means that the results based on conventional differential cryptanalysis may be inaccurate. Then we train a residual neural network to get the 7-, 8-, 9-round neural distinguishers for SIMON32/64. To prove the effectiveness for our distinguishers, we perform the distinguishing attack and key-recovery attack against 15-round SIMON32/64. The results show that the real ciphertexts can be distinguished from random ciphertexts with a probability close to 1 only by 2^8.7 chosen-plaintext pairs. For the key-recovery attack, the correct key was recovered with a success rate of 23%, and the data complexity and computation complexity are as low as 2⁸ and 2^20.1 respectively. All the results are better than the existing literature. Furthermore, we briefly discussed the effect of different residual network structures on the training results of neural distinguishers. It is hoped that our findings will provide some reference for future research.

• Smart Structures and Systems
• /
• 제29권3호
• /
• pp.475-484
• /
• 2022

The loss of cable tension for civil infrastructure reduces structural bearing capacity and causes harmful deformation of structures. Currently, most of the structural health monitoring (SHM) approaches for cables rely on contact transducers. This paper proposes a cable tension identification technology using percussion sound, which provides a fast determination of steel cable tension without physical contact between cables and sensors. Notably, inspired by the concept of tensioning strings for piano tuning, this proposed technology predicts cable tension value by deep learning assisted classification of "percussion" sound from tapping a steel cable. To simulate the non-linear mapping of human ears to sound and to better quantify the minor changes in the high-frequency bands of the sound spectrum generated by percussions, Mel-frequency cepstral coefficients (MFCCs) were extracted as acoustic features to train the deep learning network. A convolutional neural network (CNN) with four convolutional layers and two global pooling layers was employed to identify the cable tension in a certain designed range. Moreover, theoretical and finite element methods (FEM) were conducted to prove the feasibility of the proposed technology. Finally, the identification performance of the proposed technology was experimentally investigated. Overall, results show that the proposed percussion-based technology has great potentials for estimating cable tension for in-situ structural safety assessment.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.233-233
• /
• 2022

As the world's population grows and food needs diversify, the demand for horticultural crops for beneficial traits is increasing. In order to meet this demand, it is necessary to develop suitable cultivars and breeding methods accordingly. Breeding methods have changed over time. With the recent development of sequencing technology, the concept of genomic selection (GS) has emerged as large-scale genome information can be used. GS shows good predictive ability even for quantitative traits by using various markers, breaking away from the limitations of Marker Assisted Selection (MAS). Moreover, GS using machine learning (ML) and deep learning (DL) has been studied recently. In this study, we aim to build a system that selects phenotype-related markers using the genomic information of the pepper population and trains a genomic selection model to select individuals from the validation population. We plan to establish an optimal genome wide association analysis model by comparing and analyzing five models. Validation of molecular markers by applying linkage markers discovered through genome wide association analysis to breeding populations. Finally, we plan to establish an optimal genome selection model by comparing and analyzing 12 genome selection models. Then We will use the genome selection model of the learning group in the breeding group to verify the prediction accuracy and discover a prediction model.

• 한국문헌정보학회지
• /
• 제48권2호
• /
• pp.65-88
• /
• 2014

본 연구는 PBL을 적용한 사서교사와 중국어 교과교사 협력으로 이루어진 수업의 사례를 분석하고 학교도서관에서 PBL에 의한 협력 수업을 운영할 때 바람직한 수업의 방향을 제시하기 위한 의도로 이루어졌다. 이러한 목적을 이루기 위하여 인문계 S고등학교 도서관에서 이루어진 PBL 문제 제시 방법, 차시별 수업 내용, 학생 결과물의 사례 등을 제시하였다. 또한 PBL 수업에 참여했던 고등학교 2학년 학생 101명을 대상으로 교과 흥미에 대한 분석을 수행한 결과, PBL에 참여한 후에 학생들의 학습관련 성취욕, 학습 실행력, 흥미가 유의미하게 향상된 것으로 나타났다.

• Imaging Science in Dentistry
• /
• 제46권3호
• /
• pp.211-216
• /
• 2016

Purpose: The use of electronic tools in teaching is growing rapidly in all fields, and there are many options to choose from. We present one such platform, Learning Catalytics$^{TM}$ (LC) (Pearson, New York, NY, USA), which we utilized in our oral and maxillofacial radiology course for second-year dental students. Materials and Methods: The aim of our study was to assess the correlation between students' performance on course exams and self-assessment LC quizzes. The performance of 354 predoctoral dental students from 2 consecutive classes on the course exams and LC quizzes was assessed to identify correlations using the Spearman rank correlation test. The first class was given in-class LC quizzes that were graded for accuracy. The second class was given out-of-class quizzes that were treated as online self-assessment exercises. The grading in the self-assessment exercises was for participation only and not accuracy. All quizzes were scheduled 1-2 weeks before the course examinations. Results: A positive but weak correlation was found between the overall quiz scores and exam scores when the two classes were combined (P<0.0001). A positive but weak correlation was likewise found between students' performance on exams and on in-class LC quizzes (class of 2016) (P<0.0001) as well as on exams and online LC quizzes (class of 2017) (P<0.0001). Conclusion: It is not just the introduction of technological tools that impacts learning, but also their use in enabling an interactive learning environment. The LC platform provides an excellent technological tool for enhancing learning by improving bidirectional communication in a learning environment.

• 성인간호학회지
• /
• 제20권5호
• /
• pp.778-790
• /
• 2008

Purpose: This study was conducted to develop Web-based multimedia contents for supporting student nurses' clinical practice on critical care, and to evaluate learners' responses. Methods: Based on the steps of Assessment, Design, Development, Implementation, & Evaluation(ADDIE) model, a total of 13 self-directed learning modules including live lectures and real video clips were developed through faculty collaboration of nine nursing colleges in Gwangju and Chonnam province. The finally developed multimedia contents were published on the Web of the learning management system at a local e-learning center. Results: The Web contents were evaluated after self-learning by 81 junior college nursing students who were encouraged to study it at their own pace during their two-week clinical practice at a medical or surgical intensive care unit of a university hospital and two hospitals. The knowledge (t = -27.66, p < .001) and self-evaluated clinical performance level(t = 7.54, p < .001) were significantly increased after learning of the Web contents and clinical practice, and satisfaction level that measured post-test only was 4.0 out of 5 point. Conclusion: The use of Web contents for critical care need to be extended as a complimentary material in a class room lecture or clinical practice of students to increase their self-learning ability and understandings of clinical knowledge and situation.

• 정보교육학회논문지
• /
• 제7권2호
• /
• pp.227-237
• /
• 2003

기존의 CAI나 ITS 연구물은 문제 해결 과정이 일반화되어 있어, 특별한 문제를 해결하기 위해서는 학습자가 수동적인 입장을 가지고 불필요한 과정을 거쳐서 시스템의 요구에 따라 해결할 수밖에 없었다. 결과적으로 본 연구와 같은 분수의 연산과 분야에서는 창의적이고 개별화된 문제 풀이 과정을 지원할 수 없었다. 본 연구는 보충학습자들을 위한 분수의 연산에 관한 ITS 시스템의 설계와 구현에 관한 연구이다. 본 연구는 학습 오류를 진단하고 학습 오류 상태를 학습자가 분명하게 인지할 수 있도록 안내한다. 또한 본 시스템은 학습자의 자기 주도적인 학습을 지원하며, 학습자 자신의 학습 결손을 보충할 수 있으며 또한 분수연산 과정을 학습자의 수준에서 창의적으로 스스로 조정이 가능하다. 우리는 이 시스템이 학교 교사 부족으로 인해 보충 학습자에 대한 배려가 소홀할 수밖에 없는 문제점이 개선됨을 보여주었고, 학습자도 이 시스템으로 인해 스스로 문제를 해결하는 능력이 신장되어 보다 높은 학습 효과를 얻는 것을 발견할 수 있었다.

• 컴퓨터교육학회논문지
• /
• 제5권2호
• /
• pp.39-48
• /
• 2002

지능형 컴퓨터 보조교육(ICAI : Intelligent Computer Assisted Instruction) 시스템은 전문가 모듈, 교사 모듈, 학습자 모듈, 정숙 모듈 등의 4가지 모듈로 구성하는 것이 일반적이다. 각 모듈 구성에 있어 교과 내용과 평가 문제, 평가 결과와 진단, 진단 결과에 따른 처방 등의 관련 전략을 효율적이고 체계적으로 제어하기 위한 규칙이 필요하다. 이를 위해 교과 과정을 일정한 단위로 구분하는 방법을 제시하였다. 또한 구분 된 단위간에 연관성을 부여하고 이를 참고로 학습 진행과 평가, 진단, 처방의 모든 과정에 적용할 수 있도록 하였다. 구분된 단위(개념)와 연관성(관계)을 그래프 형식으로 나타내는 방법을 제안하였다. 또한, 이 개념을 적용하여 인터넷 상에서 여러 전문가가 협력하여 동시에 코스웨어를 구축할 수 있는 환경을 지원하는 인터넷 기반의 코스웨어 저작 도구를 구현하였다.

• 정보과학회지
• /
• 제35권7호
• /
• pp.9-25
• /
• 2017

In this paper, we surveyed state-of-the-art health and wellness platforms. The motivation of this paper is to review the state-of-the-art health and wellness platforms and their maturity with respect to adoption of latest enabling technologies. The is review is classified into four categories: healthcare systems, AI-assisted healthcare, wellness platforms, and open source health and wellness initiatives. From this comprehensive review, it can be stated that the contemporary healthcare systems are well-adopting wellness due to the concentration shift towards prevention. Thus, the gap between health and wellness is slowly yet carefully entering gray area. Where both the domains can freely invoke each other's services, and supporting enabling technologies. Furthermore, the biomedical researchers and physicians are no longer carrying the myopic views of trusting their knowledge for diagnosis. AI-assisted technologies based on machine learning and big data are influencing today's prognosis with trust and confidence.

• 대한전자공학회논문지
• /
• 제26권7호
• /
• pp.140-145
• /
• 1989

이 논문에서는 ASIC 칩의 설계도면에서 발생하는 임의의 모양을 갖는 영역에서의 효과적인 회로배치 방법인 SOAP (self-organization assisted placement) 를 제안한다. 자율조직이란 Kohonen[1]이 제안한 신경회로망의 학습방법으로 가까이 위치하고 있는 신경소자들이 물리적으로 유사한 외부입력에 민감하도록 소자에 연결된 시냅스 (synapse)의 가중치들을 조절하는 것이다. SOAP에서는 회로 블럭을 신경소자에 회로 블럭의 위치 (x, y좌표)를 해당 신경소자에 연결된 2개의 학습입력으로부터의 시냅스의 가중치 쌍으로 대응시킴으로써 임의의 영역에서의 좋은 회로 배치 결과를 얻을 수 있었다. 이 방법은 또한 입체 표면에서의 회로 배치에도 확장될 수 있다.