期刊文献+
共找到116,872篇文章
< 1 2 250 >
每页显示 20 50 100
Investigation and Research on College Students' English Learning Strategies in the Network Age 预览
1
作者 Qin Ke 《计算机科学与技术汇刊:中英文版》 2019年第1期19-23,共5页
In the era of widespread use of the Internet, students are more active in English learning, and their use of learning concepts and learning strategies is an important factor in determining the success or failure of En... In the era of widespread use of the Internet, students are more active in English learning, and their use of learning concepts and learning strategies is an important factor in determining the success or failure of English learning. A university is a school that conducts higher education. It refers to a higher education institution that provides education, research conditions, and approves degree awards. The stage of studying in college is a great memory for many people in their lives. There is no pressure on college time compared to high school and high school. College students feel that English is not important, they do not want to learn. In the era when college students often go online, in order to encourage students' desire to learn, we must explore the use of the Internet, and to develop students' English learning habits, we must use the Internet. In recent years, education has gradually introduced the help of network technology, and students' learning methods are diversified and comprehensive. English is a very important skill learning focus for college students. Non-English majors can learn English through a wider range of English learning. This report is an English learning strategy for college students in the Internet age. 展开更多
关键词 Language LEARNING Concepts LEARNING Strategies DIFFERENCES NETWORK Age COLLEGE STUDENTS English LEARNING
在线阅读 下载PDF
Social Media as a Learning Management System: Is it a Tool for Achieving the Goal of “Education for All”? 预览
2
作者 Wilson O. Otchie Margus Pedaste 《美中教育评论:A》 2019年第2期79-90,共12页
Social media (SM) Apps,such as Facebook,Twitter,YouTube,Instagram,etc.are very interactive and empower people to socialize,interact,communicate,and share information from anywhere and at any time without face-to-face ... Social media (SM) Apps,such as Facebook,Twitter,YouTube,Instagram,etc.are very interactive and empower people to socialize,interact,communicate,and share information from anywhere and at any time without face-to-face (F2F) contact.However,the usability and functionality of SM make it easily accessible and affordable.Thus,it is a potential educational resource for achieving the right to education for all (EFA),as cited in Article 26 of the Charter of the United Nations (UN).Ultimately,SM empowers people to easily obtain access to information and educational resources.This paper reviews the highlights of SM appropriation in the context of learning,explores using SM as a learning management system (LMS),and provides learning scenarios for implementing SM as an LMS in the teaching and learning of science.Findings from the study suggest that using SM as an LMS could help maximize its potential and make teaching and learning more effective and interesting. 展开更多
关键词 SOCIAL media LEARNING management system FORMAL LEARNING INFORMAL LEARNING
在线阅读 下载PDF
Query by diverse committee in transfer active learning
3
作者 Hao SHAO 《中国计算机科学前沿:英文版》 SCIE EI CSCD 2019年第2期280-291,共12页
Transfer active learning, which is an emerging learning paradigm, aims to actively select informative instances with the aid of transferred knowledge from related tasks. Recently, several studies have addressed this p... Transfer active learning, which is an emerging learning paradigm, aims to actively select informative instances with the aid of transferred knowledge from related tasks. Recently, several studies have addressed this problem. However, how to handle the distributional differences betwee n the source and target domains remains an open problem. In this paper, a novel transfer active learning algorithm is proposed, inspired by the classical query by committee algorithm. Diverse committee members from both domains are maintained to improve the classification accuracy and a mechanism is included to evaluate each member during the iterations. Extensive experiments on both synthetic and real datasets show that our algorithm performs better and is also more robust than the state-of-the-art methods. 展开更多
关键词 TRANSFER LEARNING ACTIVE LEARNING MACHINE LEARNING
M-Learning大学英语学习方式的挑战及应对策略 预览
4
作者 佟秋华 《齐齐哈尔大学学报:哲学社会科学版》 2019年第4期186-188,共3页
M-Learning的学习方式存在缺乏系统性、有时会分散一些注意力、会带来一定的经济耗损及一定程度上会影响身心健康等问题,但也具有方便快捷、信息量大、形式多样、实时更新及沟通及时等优点。针对以上问题,可以采取规范资源建设、改善移... M-Learning的学习方式存在缺乏系统性、有时会分散一些注意力、会带来一定的经济耗损及一定程度上会影响身心健康等问题,但也具有方便快捷、信息量大、形式多样、实时更新及沟通及时等优点。针对以上问题,可以采取规范资源建设、改善移动设备功能及加强网络监管和审查力度等措施,以促进移动学习的积极发展。 展开更多
关键词 M-LEARNING 英语学习 移动多媒体
在线阅读 下载PDF
Underwater Object Recognition Based on Deep Encoding-Decoding Network 预览
5
作者 WANG Xinhua OUYANG Jihong +1 位作者 LI Dayu ZHANG Guang 《中国海洋大学学报:英文版》 SCIE CAS CSCD 2019年第2期376-382,共7页
Ocean underwater exploration is a part of oceanography that investigates the physical and biological conditions for scientific and commercial purposes.And video technology plays an important role and is extensively ap... Ocean underwater exploration is a part of oceanography that investigates the physical and biological conditions for scientific and commercial purposes.And video technology plays an important role and is extensively applied for underwater environment observation.Different from the conventional methods,video technology explores the underwater ecosystem continuously and non-invasively.However,due to the scattering and attenuation of light transport in the water,complex noise distribution and lowlight condition cause challenges for underwater video applications including object detection and recognition.In this paper,we propose a new deep encoding-decoding convolutional architecture for underwater object recognition.It uses the deep encoding-decoding network for extracting the discriminative features from the noisy low-light underwater images.To create the deconvolutional layers for classification,we apply the deconvolution kernel with a matched feature map,instead of full connection,to solve the problem of dimension disaster and low accuracy.Moreover,we introduce data augmentation and transfer learning technologies to solve the problem of data starvation.For experiments,we investigated the public datasets with our proposed method and the state-of-the-art methods.The results show that our work achieves significant accuracy.This work provides new underwater technologies applied for ocean exploration. 展开更多
关键词 DEEP LEARNING transfer LEARNING encoding-decoding UNDERWATER OBJECT OBJECT recognition
在线阅读 下载PDF
Artificial intelligence-Developments in medicine in the last two years
6
作者 Rezida Maratovna Galimova Igor Vyacheslavovich Buzaev +2 位作者 Kireev Ayvar Ramilevich Lev Khadyevich Yuldybaev Aigul Fazirovna Shaykhulova 《慢性疾病与转化医学:英文版》 CSCD 2019年第1期64-68,共5页
Dear Editor , Artificial intelligence (AI) is the theory and development of computer systems that are able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, deci... Dear Editor , Artificial intelligence (AI) is the theory and development of computer systems that are able to perform tasks that normally require human intelligence, such as visual perception, speech recognition, decision-making, and translation between languages. There are some knowledge and thinking tasks that humans cannot perform as perfectly as they wish to or should be able to. These tasks are closely related to security and responsibility. A multitude of cognitive distortions have been well explored1 and present opportunities to use AI for powerful assistance in thinking tasks. The core of the Industrial Revolution 4.0 is the adoption of AI methods. This revolution has affected all aspects of human activities and medicine is one example. AI systems can usually include formal algorithms for subtasks that can be solved using logic, for example, a decision tree. The task solution process moves from logic point to logic point similar to a train on a railway. These algorithms are fast and have the ability to explain. 展开更多
关键词 Artificial INTELLIGENCE Clinical DECISION Machine LEARNING SCIENTIFIC tools Healthcare Deep LEARNING
《国标》视域下英美文学的“教学做合一” 预览
7
作者 王秀杰 《杭州电子科技大学学报:社会科学版》 2019年第3期63-67,共5页
社会经济大潮的影响使各高校的英美文学因所谓的"无用"而被置边缘。笔者秉承《高等学校英语专业本科教学质量国家标准》"全人教育"之旨,以陶行知"教学做合一"的教学思想为依据进行英美文学教学。文章就... 社会经济大潮的影响使各高校的英美文学因所谓的"无用"而被置边缘。笔者秉承《高等学校英语专业本科教学质量国家标准》"全人教育"之旨,以陶行知"教学做合一"的教学思想为依据进行英美文学教学。文章就英美文学教学内容、课堂操作及课程评价等进行详细阐述,认为实施英美文学的"教学做合一"式教学,构建以"做"为中心、师生共同参与的学习共同体,不仅打破了传统的教师中心论和现代的学生中心论之师/生、教/学等二元分界,还强调教、学、做为学习共同体异质化交互行动的合一过程,实现了《国标》对学生综合能力与人文素质的"全人培养"目标,彰显英美文学对人才培养的"致用性"。 展开更多
关键词 国标 英美文学课程 教学做合一 学习共同体
在线阅读 下载PDF
Safe semi-supervised learning: a brief introduction
8
作者 Yu-Feng LI De-Ming LIANG 《中国计算机科学前沿:英文版》 SCIE EI CSCD 2019年第4期669-676,共8页
Semi-supervised learning constructs the predictive model by learning from a few labeled training examples and a large pool of unlabeled ones. It has a wide range of application scenarios and has attracted much attenti... Semi-supervised learning constructs the predictive model by learning from a few labeled training examples and a large pool of unlabeled ones. It has a wide range of application scenarios and has attracted much attention in the past decades. However, it is noteworthy that although the learning performance is expected to be improved by exploiting unlabeled data, some empirical studies show that there are situations where the use of unlabeled data may degenerate the performance. Thus, it is advisable to be able to exploit unlabeled data safely. This article reviews some research progress of safe semi-supervised learning, focusing on three types of safeness issue: data quality, where the training data is risky or of low?quality;model uncertainty, where the learning algorithm fails to handle the uncertainty during training;measure diversity, where the safe performance could be adapted to diverse measures. 展开更多
关键词 MACHINE LEARNING SEMI-SUPERVISED LEARNING SAFE
The State of the Art of Data Science and Engineering in Structural Health Monitoring 预览
9
作者 Yuequan Bao Zhicheng Chen +3 位作者 Shiyin Wei Yang Xu Zhiyi Tang Hui Li 《工程(英文)》 2019年第2期234-242,共9页
Structural health monitoring (SHM) is a multi-discipline field that involves the automatic sensing of structural loads and response by means of a large number of sensors and instruments, followed by a diagnosis of the... Structural health monitoring (SHM) is a multi-discipline field that involves the automatic sensing of structural loads and response by means of a large number of sensors and instruments, followed by a diagnosis of the structural health based on the collected data. Because an SHM system implemented into a structure automatically senses, evaluates, and warns about structural conditions in real time, massive data are a significant feature of SHM. The techniques related to massive data are referred to as data science and engineering, and include acquisition techniques, transition techniques, management techniques, and processing and mining algorithms for massive data. This paper provides a brief review of the state of the art of data science and engineering in SHM as investigated by these authors, and covers the compressive sampling-based data-acquisition algorithm, the anomaly data diagnosis approach using a deep learning algorithm, crack identification approaches using computer vision techniques, and condition assessment approaches for bridges using machine learning algorithms. Future trends are discussed in the conclusion. 展开更多
关键词 Structural HEALTH MONITORING MONITORING DATA COMPRESSIVE sampling Machine LEARNING DEEP LEARNING
在线阅读 免费下载
Unsupervised learning on scientific ocean drilling datasets from the South China Sea
10
作者 Kevin C.TSE Hon-Chim CHIU +2 位作者 Man-Yin TSANG Yiliang LI Edmund Y.LAM 《地球科学前沿:英文版》 SCIE CAS CSCD 2019年第1期180-190,共11页
Unsupervised learning methods were applied to explore data patterns in multivariate geophysical datasets collected from ocean floor sediment core samples coming from scientific ocean drilling in the South China Sea.Co... Unsupervised learning methods were applied to explore data patterns in multivariate geophysical datasets collected from ocean floor sediment core samples coming from scientific ocean drilling in the South China Sea.Compared to studies on similar datasets,but using supervised learning methods which are designed to make predictions based on sample training data,unsupervised learning methods require no a priori information and focus only on the input data.In this study,popular unsupervised learning methods including K-means,self-organizing maps,hierarchical clustering and random forest were coupled with different distance metrics to form exploratory data clusters.The resulting data clusters were externally validated with lithologic units and geologic time scales assigned to the datasets by conventional methods. Compact and connected data clusters displayed varying degrees of correspondence with existing classification by lithologic units and geologic time scales.K-means and self-organizing maps were observed to perform better with lithologic units while random forest corresponded best with geologic time scales.This study sets a pioneering example of how unsupervised machine learning methods can be used as an automatic processing tool for the increasingly high volume of scientific ocean drilling data. 展开更多
关键词 machine LEARNING UNSUPERVISED LEARNING ODP IODP clustering
Anchor-based manifold binary pattern for finger vein recognition
11
作者 Haiying LIU Gongping YANG +2 位作者 Lu YANG Kun SU Yilong YIN 《中国科学:信息科学(英文版)》 SCIE EI CSCD 2019年第5期129-144,共16页
This paper proposes a novel learning method of binary local features for recognition of the finger vein. The learning methods existing in local features for image recognition intend to maximize the data variance, redu... This paper proposes a novel learning method of binary local features for recognition of the finger vein. The learning methods existing in local features for image recognition intend to maximize the data variance, reduce quantitative errors, exploit the contextual information within each binary code, or utilize the label information, which all ignore the local manifold structure of the original data. The manifold structure actually plays a very important role in binary code learning, but constructing a similarity matrix for large-scale datasets involves a lot of computational and storage cost. The study attempts to learn a map, which can preserve the manifold structure between the original data and the learned binary codes for large-scale situations. To achieve this goal, we present a learning method using an anchor-based manifold binary pattern(AMBP) for finger vein recognition. Specifically, we first extract the pixel difference vectors(PDVs) in the local patches by calculating the differences between each pixel and its neighbors. Second,we construct an asymmetric graph, on which each data point can be a linear combination of its K-nearest neighbor anchors, and the anchors are randomly selected from the training samples. Third, a feature map is learned to project these PDVs into low-dimensional binary codes in an unsupervised manner, where(i) the quantization loss between the original real-valued vectors and learned binary codes is minimized and(ii) the manifold structure of the training data is maintained in the binary space. Additionally, the study fuses the discriminative binary descriptor and AMBP methods at the image representation level to further boost the performance of the recognition system. Finally, experiments using the MLA and PolyU databases show the effectiveness of our proposed methods. 展开更多
关键词 FINGER VEIN recognition feature LEARNING local linear EMBEDDING fusion MANIFOLD LEARNING ANCHOR
Universally composable oblivious transfer from ideal lattice
12
作者 Momeng LIU Yupu HU 《中国计算机科学前沿:英文版》 SCIE EI CSCD 2019年第4期879-906,共28页
As a fundamental cryptographic primitive, oblivious transfer (OT) is developed for the sake of efficient usability and combinational feasibility. However, most OT protocols are built upon some quantum non-immune cryp?... As a fundamental cryptographic primitive, oblivious transfer (OT) is developed for the sake of efficient usability and combinational feasibility. However, most OT protocols are built upon some quantum non-immune cryp? tosystems by assuming the hardness of discrete logarithm or factoring problem, whose security will break down directly in the quantum setting. Therefore, as a subarea of postquantum cryptography, lattice-based cryptography is viewed as a promising alternative and cornerstone to support for building post-quantum protocols since it enjoys some attractive properties, such as provable security against quantum adversaries and lower asymptotic complexity. In this paper, we first build an efficient l-out-of-2 OT protocol upon the hardness of ring learning with errors (RLWE) problem, which is at least as hard as some worst-case ideal lattice problems. We show that this l-out-of-2 OT protocol can be universally composable and secure against static corruptions in the random oracle model. Then we extend it to a general case, i.e., l-out-of-N OT with achieving the same level of security. Furthermore, on the basis of the above OT structure, we obtain two improved OT protocols using two improved lattice-based key exchange protocols (respectively relying on the RLWE problem and learning with errors (LWE) problem, and both achieving better efficiency by removing the Gaussian sampling for saving cost) as building blocks. To show that our proposed OT protocol indeed achieves comparable security and efficiency, we make a comparison with another two lattice-based OT protocols in the end of the paper. With concerning on the potential threat from quantum computing and expecting on the practical use of OT with high efficiency, an efficient post-quantum OT protocol is pressing needed. As shown in this paper, our proposed OT protocols may be considered as post-quantum OT candidates since they can both preserve provable security relying on lattice problems and enjoy practical efficiency. 展开更多
关键词 oblivious transfer universally COMPOSABILITY lattice-based CRYPTOGRAPHY LEARNING with ERRORS ring LEARNING with ERRORS RANDOM oracle model
Impact of self-directed learning readiness and learning attitude on problem-solving ability among Chinese undergraduate nursing students 预览
13
作者 Ru-Zhen Luo Xiao-Hong Zhang +1 位作者 Chun-Mei Zhang Yan-Hui Liu 《护理前沿(英文)》 CAS 2019年第2期143-150,共8页
Objective: To explore the effects of self-directed learning readiness and learning attitude on problem-solving ability among Chinese undergraduate nursing students. Methods: A convenience sampling of 460 undergraduate... Objective: To explore the effects of self-directed learning readiness and learning attitude on problem-solving ability among Chinese undergraduate nursing students. Methods: A convenience sampling of 460 undergraduate nursing students was surveyed in Tianjin, China. Students who participated in the study completed a questionnaire that included social demographic questionnaire, Self-directed Learning Readiness Scale, Attitude to Learning Scale, and Social Problem-Solving Inventory. Pearson’s correlation analysis was performed to test the correlations among problem-solving ability, self-directed learning readiness, and learning attitude. Hierarchical linear regression analyses were performed to explore the mediating role of learning attitude. Results: The results showed that learning attitude (r=0.338, P<0.01) and self-directed learning readiness (r=0.493, P<0.01) were positively correlated with problem-solving ability. Learning attitude played a partial intermediary role between self-directed learning readiness and problem-solving ability (F=74.227, P<0.01). Conclusions: It is concluded that nursing educators should pay attention on students’ individual differences and take proper actions to inspire students’ self-directed learning readiness and learning attitude. 展开更多
关键词 UNDERGRADUATE NURSING students self-directed LEARNING READINESS LEARNING ATTITUDE problem-solving ABILITY China
在线阅读 免费下载
影响医学生移动学习有效开展的因素 预览
14
作者 张良 岳建平 胡大鹏 《科教导刊》 2019年第4期37-38,共2页
这是一个知识快速膨胀的时代,医学生需要学习、掌握的知识、技能也越来越多,如何在有限的时间内,利用信息技术手段,来快速提高医学生学习、掌握更多实用的医学知识和技能,成为了研究的热点,通过对影响医学生移动学习应用效果的,医学生... 这是一个知识快速膨胀的时代,医学生需要学习、掌握的知识、技能也越来越多,如何在有限的时间内,利用信息技术手段,来快速提高医学生学习、掌握更多实用的医学知识和技能,成为了研究的热点,通过对影响医学生移动学习应用效果的,医学生素质、教师、移动课程资源和基本硬件环境进行分析,得出了影响医学生移动学习效果和效能的关键因素,为有效开展医学生移动学习提供了借鉴和指导。 展开更多
关键词 移动学习 自我效能感 学习专注度 有意识教师
在线阅读 下载PDF
基于强化学习的自主式水下潜器障碍规避技术 预览
15
作者 Prashant Bhopale Faruk Kazi Navdeep Singh 《船舶与海洋工程学报:英文版》 CSCD 2019年第2期228-238,共11页
Obstacle avoidance becomes a very challenging task for an autonomous underwater vehicle(AUV)in an unknown underwater environment during exploration process.Successful control in such case may be achieved using the mod... Obstacle avoidance becomes a very challenging task for an autonomous underwater vehicle(AUV)in an unknown underwater environment during exploration process.Successful control in such case may be achieved using the model-based classical control techniques like PID and MPC but it required an accurate mathematical model of AUV and may fail due to parametric uncertainties,disturbance,or plant model mismatch.On the other hand,model-free reinforcement learning(RL)algorithm can be designed using actual behavior of AUV plant in an unknown environment and the learned control may not get affected by model uncertainties like a classical control approach.Unlike model-based control model-free RL based controller does not require to manually tune controller with the changing environment.A standard RL based one-step Q-learning based control can be utilized for obstacle avoidance but it has tendency to explore all possible actions at given state which may increase number of collision.Hence a modified Q-learning based control approach is proposed to deal with these problems in unknown environment.Furthermore,function approximation is utilized using neural network(NN)to overcome the continuous states and large statespace problems which arise in RL-based controller design.The proposed modified Q-learning algorithm is validated using MATLAB simulations by comparing it with standard Q-learning algorithm for single obstacle avoidance.Also,the same algorithm is utilized to deal with multiple obstacle avoidance problems. 展开更多
关键词 OBSTACLE AVOIDANCE AUTONOMOUS UNDERWATER vehicle REINFORCEMENT learning Q-LEARNING Function approximation
在线阅读 下载PDF
Closed-Loop Iterative Learning Control for Discrete Singular Systems with Fixed Initial Shift
16
作者 GU Panpan TIAN Senping LIU Qian 《系统科学与复杂性学报:英文版》 SCIE EI CSCD 2019年第2期577-587,共11页
This paper deals with the problem of iterative learning control for a class of discrete singular systems with fixed initial shift. According to the characteristics of the discrete singular systems, a closed-loop learn... This paper deals with the problem of iterative learning control for a class of discrete singular systems with fixed initial shift. According to the characteristics of the discrete singular systems, a closed-loop learning algorithm is proposed and the corresponding state limiting trajectory is presented.It is shown that the algorithm can guarantee that the system state converges uniformly to the state limiting trajectory on the whole time interval. Then the initial rectifying strategy is introduced to the discrete singular systems for eliminating the effect of the fixed initial shift. Under the action of the initial rectifying strategy, the system state can converge to the desired state trajectory within the pre-specified finite time interval no matter what value the fixed initial shift takes. Finally, a numerical example is given to illustrate the effectiveness of the proposed approach. 展开更多
关键词 CLOSED-LOOP LEARNING algorithm discrete singular systems fixed INITIAL SHIFT ITERATIVE LEARNING control
Implementing Augmented Reality in Learning 预览
17
作者 Ajit Singh 《心理学研究:英文版》 2019年第4期172-177,共6页
Technologies are changing and ever growing.One of the newest developing technologies is augmented reality(AR),which can be applied to many different existing technologies,such as computers,tablets,and smartphones.AR t... Technologies are changing and ever growing.One of the newest developing technologies is augmented reality(AR),which can be applied to many different existing technologies,such as computers,tablets,and smartphones.AR technology can also be utilized through wearable components,for example,glasses.Throughout this paper review on AR,the following aspects are discussed at length:research explored,theoretical foundations,applications in education,challenges,reactions,and implications.Several different types of AR devices and applications are discussed at length,and an in-depth analysis is done on several studies that have implemented AR technology in an educational setting. 展开更多
关键词 AUGMENTED REALITY LEARNING and development EDUCATOR flow theory JUST-IN-TIME LEARNING
在线阅读 下载PDF
M-learning在大学英语教学应用中的可行性调查研究 预览
18
作者 明净 《教育教学论坛》 2019年第3期96-97,共2页
本文基于以武汉设计工程学院的大一学生为对象实施的问卷调查,分析了手机在大学英语学习中的使用情况,并结合Gardner的学习动机理论,调查学生利用智能手机学习的动机以及兴趣点,考察了手机在大学英语教学应用中的可行性。研究表明,将手... 本文基于以武汉设计工程学院的大一学生为对象实施的问卷调查,分析了手机在大学英语学习中的使用情况,并结合Gardner的学习动机理论,调查学生利用智能手机学习的动机以及兴趣点,考察了手机在大学英语教学应用中的可行性。研究表明,将手机导入课堂的可行性很高,学生对于利用手机学习英语感兴趣并较为期待。从动机来看,手机辅助教学可以满足学生提高英语水平的愿望。 展开更多
关键词 移动学习 手机 学习动机
在线阅读 下载PDF
Deep-learning classifier with ultrawide-field fundus ophthalmoscopy for detecting branch retinal vein occlusion
19
作者 Daisuke Nagasato Hitoshi Tabuchi +7 位作者 Hideharu Ohsugi Hiroki Masumoto Hiroki Enno Naofumi Ishitobi Tomoaki Sonobe Masahiro Kameoka Masanori Niki Yoshinori Mitamura 《国际眼科杂志:英文版》 SCIE CAS 2019年第1期94-99,共6页
AIM: To investigate and compare the efficacy of two machine-learning technologies with deep-learning(DL) and support vector machine(SVM) for the detection of branch retinal vein occlusion(BRVO) using ultrawide-field f... AIM: To investigate and compare the efficacy of two machine-learning technologies with deep-learning(DL) and support vector machine(SVM) for the detection of branch retinal vein occlusion(BRVO) using ultrawide-field fundus images. METHODS: This study included 237 images from 236 patients with BRVO with a mean±standard deviation of age 66.3±10.6 y and 229 images from 176 non-BRVO healthy subjects with a mean age of 64.9±9.4 y. Training was conducted using a deep convolutional neural network using ultrawide-field fundus images to construct the DL model. The sensitivity, specificity, positive predictive value(PPV), negative predictive value(NPV) and area under the curve(AUC) were calculated to compare the diagnostic abilities of the DL and SVM models. RESULTS: For the DL model, the sensitivity, specificity, PPV, NPV and AUC for diagnosing BRVO was 94.0%(95%CI: 93.8%-98.8%), 97.0%(95%CI: 89.7%-96.4%), 96.5%(95%CI: 94.3%-98.7%), 93.2%(95%CI: 90.5%-96.0%) and 0.976(95%CI: 0.960-0.993), respectively. In contrast, for the SVM model, these values were 80.5%(95%CI: 77.8%-87.9%), 84.3%(95%CI: 75.8%-86.1%), 83.5%(95%CI: 78.4%-88.6%), 75.2%(95%CI: 72.1%-78.3%) and 0.857(95%CI: 0.811-0.903), respectively. The DL model outperformed the SVM model in all the aforementioned parameters(P<0.001). CONCLUSION: These results indicate that the combination of the DL model and ultrawide-field fundus ophthalmoscopy may distinguish between healthy and BRVO eyes with a high level of accuracy. The proposed combination may be used for automatically diagnosing BRVO in patients residing in remote areas lacking access to an ophthalmic medical center. 展开更多
关键词 automatic diagnosis branch RETINAL vein OCCLUSION deep learning MACHINE-LEARNING technology ultrawide-field FUNDUS ophthalmoscopy
A Novel RRAM Based PUF for Anti-Machine Learning Attack and High Reliability
20
作者 戴澜 闫强强 +2 位作者 易盛禹 刘文楷 钱鹤 《上海交通大学学报:英文版》 EI 2019年第1期101-106,共6页
Due to the unique response mechanism, physical unclonable function(PUF) has been extensively studied as a hardware security primitive. And compared to other PUFs, the resistive random access memory(RRAM)based PUF has ... Due to the unique response mechanism, physical unclonable function(PUF) has been extensively studied as a hardware security primitive. And compared to other PUFs, the resistive random access memory(RRAM)based PUF has more flexibility with the change of conductive filaments. In this work, we propose an exclusive or(XOR) strong PUF based on the 1 Kbit 1-transistor-1-resistor(1 T1 R) arrays, and unlike the traditional RRAM based strong PUF, the XOR PUF has a stronger anti-machine learning attack ability in our experiments. The reliability of XOR RRAM PUF is determined by the read instability, thermal dependence of RRAM resistance,and aging. We used a split current distribution scheme to make the reliability of XOR PUF significantly improved.After baking for 50 h at a high temperature of 150?C, the intra-chip Hamming distance(Intra-HD) only increased from 0 to 4.5%. The inter-chip Hamming distance(Inter-HD) and uniformity are close to 50%(ideally). And it is proven through the NIST test that XOR PUF has a high uniqueness. 展开更多
关键词 physical unclonable functions resistive random access memory MACHINE LEARNING ATTACK anti-machine LEARNING ATTACK XOR RRAM PUF
上一页 1 2 250 下一页 到第
使用帮助 返回顶部 意见反馈