检索结果-内蒙古大学图书馆

Fusion of Internal Similarity to Improve the Accuracy of Recommendation Algorithm

Journal on Internet of Things 2021年第2期3卷 65-76页

作者： Zejun Yang Denghui Xia Jin Liu Chao Zheng Yanzhen Qu Yadang Chen Chengjun Zhang School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Yukun(Beijing)Network Technology Co. Ltd.Beijing102200China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China School of Computer Science and Technology Colorado Technical UniversityColorado Springs80907USA

Collaborative filtering algorithms(CF)and mass diffusion(MD)algorithms have been successfully applied to recommender systems for years and can solve the problem of information ***,both algorithms suffer from data sparsity,and both tend to recommend popular products,which have poor diversity and are not suitable for real *** this paper,we propose a user internal similarity-based recommendation algorithm(UISRC).UISRC first calculates the item-item similarity matrix and calculates the average similarity between items purchased by each user as the user’s internal *** internal similarity of users is combined to modify the recommendation score to make score predictions and *** experiments on RYM and *** datasets,the results show that UISRC can obtain better recommendation accuracy and a variety of recommendations than traditional CF and MD algorithms.

关键词： Collaborative filtering mass diffusion recommendation accuracy recommendation system user internal similarity

来源：评论

学校读者我要写书评

暂无评论

Intelligent Mobile Drone System Based on Real-Time Object Detection

引用

Journal on Artificial Intelligence 2019年第1期1卷 1-8页

作者： Chuanlong Li Xingming Sun Junhao Cai School of Computer and Software Nanjing University of Information Science and TechnologyNanjingChina Jiangsu Engineering Centre of Network Monitoring Nanjing210044China School of Politics Economics and International RelationsUniversity of ReadingBerkshireRG66BGUnited Kingdom

Drone also known as unmanned aerial vehicle(UAV)has drawn lots of attention in recent *** as one of the most popular drones has great potential in both industrial and academic *** drones are capable of taking off vertically and flying towards any *** researches of drones mainly focus on their mechanical structures and movement *** aircraft movement is usually controlled by a remote controller manually or the trajectory is pre-programmed with specific *** drones typically use mobile device together with remote controllers to realize flight control and video *** different functions on mobile devices can result in different behaviors of drones *** the development of deep learning in computer vision field,commercial drones equipped with camera can be much more intelligent and even realize autonomous *** the past,running deep learning based algorithms on mobile devices is highly computational intensive and time *** paper utilizes a novel real-time object detection method and deploys the deep learning model on the modern mobile device to realize autonomous object detection and object tracking of drones.

关键词： Drone UAV CNN object detection mobile application Ios

来源：评论

学校读者我要写书评

暂无评论

A Novel Method to against Quantum Noises in Quantum Teleportation

引用

Journal of Quantum Computing 2020年第1期2卷 33-55页

作者： Shengyao Wu Wenjie Liu Zhiguo Qu School of Computer&Software Nanjing University of Information Science and TechnologyNanjing210044China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology Nanjing University of Information Science&TechnologyNanjing210044China

In order to improve the anti-noise performance of quantum teleportation,this paper proposes a novel dynamic quantum anti-noise scheme based on the quantum teleportation which transmits single qubit state using Bell *** that quantum noise only acts on the transmitted qubit,i.e.,the entangled state that Alice and Bob share in advance is affected by the noise,thus affecting the final transmission *** this paper,a method for dynamically adjusting the shared entangled state according to the noise environment is *** calculating the maximum fidelity of the output state to determine the shared entangled state,which makes the quantum teleportation be affected by the noise as little as *** paper calculates the fidelity of teleportation under four kinds of channel noise(amplitude damping,phase damping,bit flip and depolarizing noise).The results show that the scheme has a suppression effect on phase damping,bit flip and depolarizing noise under certain *** the noise intensity is larger,the optimized efficiency is better.

关键词： Quantum noise quantum teleportation entangled channel fidelity

来源：评论

学校读者我要写书评

暂无评论

A copyright protection method for wireless sensor networks based on digital watermarking

引用

International Journal of Hybrid Information Technology 2015年第6期8卷 257-268页

作者： Wang, Baowei Su, Jianwei Zhang, Youdong Wang, Biqiang Shen, Jian Ding, Qun Sun, Xingming School of Computer and software Nanjing University of Information Science and Technology Nanjing210044 China Jiangsu Engineering Center of Network Monitoring Nanjing210044 China Department of Computer Engineering Huaiyin Institute of Technology Huaian223003 China Hubei Meteorological Service Center Wuhan430074 China

Wireless sensor networks are composed of numerous sensor nodes in the monitored area, which have been well applied in various practical areas. In these applications, data security from sensors has been threatened. Thereby in this paper, a digital watermarking based copyright protection method is proposed with regard to data security in wireless sensor networks. According to the particular characteristics of collecting data, the embedding capacity can be expanded using this method of manipulating both LSB and MSRB 4. bits of the data field. The data-related information is embedded as the digital watermarking into the data to be forwarded. When the base station receives the data, we use a lookup Table to improve the speed of data parsing. In order to achieve and verify the copyright protection on WSNs, both theoretical analysis and experimental results have demonstrated that the method can effectively detect the data reliability. In addition, we also generate two-dimensional code based on the test results, thereby facilitating the user's copyright authentication. © 2015 SERSC.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Fingerprint liveness detection using difference co-occurrence matrix based texture features

International Journal of Multimedia and Ubiquitous Engineeri...

引用

International Journal of Multimedia and Ubiquitous engineering 2016年第11期11卷 1-16页

作者： Xia, Zhihua Yuan, Chengsheng Sun, Xingming Lv, Rui Sun, Decai Gao, Guangyong Jiangsu Engineering Center of Network Monitoring Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China College of Information Science and Technology Bohai University Jinzhou121013 China School of Information Science and Technology Jiujiang University Jiujiang332005 China

Fingerprint authentication systems have been widely deployed in both civilian and government applications, however, whether fingerprint authentication systems is security or not has been an important issue under fraudulent attempts through artificial spoof fingerprints. In this paper, inspired by popular feature descriptors such as gray level cooccurrence matrix (GLCM) and Gradient (difference matrix (DM)), we propose a novel software-based fingerprint liveness detection algorithm called difference co-occurrence matrix (DCM). In doing so, quantization operation is firstly conducted on the images. DMs are constructed by calculating difference matrices of horizontal and vertical pixel values of images;difference co-occurrence arrays are constructed from the difference matrices between adjacent pixels. To reduce the influence of abnormal pixel values, truncation is used for DMs. Then, we compute four parameters (Angular Second Moment, Entropy, Inverse Differential Moment and Correlation) used as feature vectors of fingerprint images. For the first time in the fingerprint liveness detection, we construct eight difference co-occurrence matrices and extract texture features from processed DCMs. Finally, SVM classifier is used to predict classification accuracy. The experimental results reveal that our proposed method can achieve more accurate classification compared with the best algorithms of 2013 Fingerprint Liveness Detection Competition, while being able to recognize spoofed fingerprints with a better degree of accuracy. © 2016 SERSC.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

On an extension of the mean value theorems of differentiation of high dimension

引用

International Journal of Applied Mathematics and Statistics 2013年第20期50卷 132-135页

作者： Zhang, TaiZhong Cheng, YaPing Su, RunQing School of Mathematics and Statistics Nanjing University of Information Science and Technology Nanjing 210044 China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing 210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing 210044 China

In this paper, we obtain a deep differential mean value theorem of high dimension which is the exactly generalized form of the classic Role's theorem, Lagrange's theorem and Cauchy's theorem in the real st... 详细信息

关键词： Cauchy's theorem Determinant Differential mean value theorem High dimension

来源：评论

学校读者我要写书评

暂无评论

Study on Initial Alignment Under Large Misalignment Angle

引用

Journal of Information Hiding and Privacy Protection 2019年第3期1卷 95-108页

作者： Qi Wang Changsong Yang Shaoen Wu School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and TechnologyNanjing210044China Department of Computer Science Ball State UniversityMuncieUSA School of Automation Nanjing University of Information Science and TechnologyNanjing210044China

Misalignment angle error model describing the SINS mathematical platform error is presented in this paper following the idea of small misalignment angle error model and large azimuth misalignment angle error *** can be considered that the three misalignment angles are independent of the rotational sequence in the misalignment error model,but not suitable in the large misalignment error *** error angle of Euler platform is used to represent the three misalignment angles from theoretical navigation coordinate system to computational navigation coordinate *** Euler platform error angle is utilized to represent the mathematical platform error and its physical meaning is very *** SINS nonlinear error model is deduced by using the error angle of Euler platform and is simplified under the condition of large azimuth error and small *** simplified results are more comprehensive and accurate than the large azimuth misalignment error *** damping SINS algorithm and its error model are proposed to change the structure of the strapdown inertial navigation algorithm by using the external damping *** accuracy of SINS error model of large Euler platform error angle is simulated,and has strong practicability in initial alignment and is conducive to reducing the amount of calculation.

关键词： Misalignment error model large misalignment angle Euler platform error angle SINS.

来源：评论

学校读者我要写书评

暂无评论

A Robust Document Image Watermarking Scheme using Deep Neural network

arXiv

引用

arXiv 2022年

作者： Ge, Sulong Xia, Zhihua Fei, Jianwei Sun, Xingming Weng, Jian Engineering Research Center of Digital Forensics Ministry of Education School of Computer and Software Jiangsu Engineering Center of Network Monitoring Jiangsu Collaborative Innovation Center on Atmospheric Environment and Equipment Technology Nanjing University of Information Science & Technology Nanjing210044 China College of Cyber Security Jinan University Guangzhou510632 China

Watermarking is an important copyright protection technology which generally embeds the identity information into the carrier imperceptibly. Then the identity can be extracted to prove the copyright from the watermarked carrier even after suffering various attacks. Most of the existing watermarking technologies take the nature images as carriers. Different from the natural images, document images are not so rich in color and texture, and thus have less redundant information to carry watermarks. This paper proposes an end-to-end document image watermarking scheme using the deep neural network. Specifically, an encoder and a decoder are designed to embed and extract the watermark. A noise layer is added to simulate the various attacks that could be encountered in reality, such as the Cropout, Dropout, Gaussian blur, Gaussian noise, Resize, and JPEG Compression. A text-sensitive loss function is designed to limit the embedding modification on characters. An embedding strength adjustment strategy is proposed to improve the quality of watermarked image with little loss of extraction accuracy. Experimental results show that the proposed document image watermarking technology outperforms three state-of-the-arts in terms of the robustness and image quality. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Optimized Strategy for Speculative Execution in a Heterogeneous Environment

An Optimized Strategy for Speculative Execution in a Heterog...

引用

International Conference on Future Generation Communication and networking (FGCN)

作者： Qi Liu Weidong Cai Zhangjie Fu Jian Shen Nigel Linge School of Computer and Software Nanjing University of Information Science and Technology Nanjing Jiangsu China Jiangsu Engineering Centre of Network Monitoring Nanjing University of Information Science and Technology Nanjing Jiangsu China The University of Salford Salford Greater Manchester UK

MapReduce is a popular programming model for the purposes of processing large data sets. Speculative execution known as an approach for dealing with the above problems works by backing up those tasks running on a low performance machine to a higher one. In this paper, we have modified some pitfalls and taken computer hardware into consideration (HWC-Speculation). We also have implemented it in Hadoop-2.6 and experiment results show that our method can assign tasks evenly, improve the performance of MRV2 and decrease the execution time.

关键词： Cloud computing Benchmark testing Servers Program processors Virtual machining Information science Programming

来源：评论

学校读者我要写书评

暂无评论

Quantum-based Feature Selection for Multi-Classification Problem in Complex Systems with Edge Computing

arXiv

引用

arXiv 2023年

作者： Liu, Wenjie Chen, Junxiu Wang, Yuxiang Gao, Peipei Lei, Zhibin Ma, Xu Jiangsu Engineering Center of Network Monitoring Nanjing University of Information Science and Technology Nanjing210044 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China 999077 Hong Kong School of Software Qufu Normal University Shandong273165 China

The complex systems with edge computing require a huge amount of multi-feature data to extract appropriate insights for their decision-making, so it is important to find a feasible feature selection method to improve the computational efficiency and save the resource consumption. In this paper, a quantum-based feature selection algorithm for the multi-classification problem, namely QReliefF, is proposed, which can effectively reduce the complexity of algorithm and improve its computational efficiency. First, all features of each sample are encoded into a quantum state by performing operations CMP and Ry, then the amplitude estimation is applied to calculate the similarity between any two quantum states (i.e., two samples). According to the similarities, the Grover-Long method is utilized to find the nearest k neighbor samples, and then the weight vector is updated. After a certain number of iterations through the above process, the desired features can be selected with regards to the final weight vector and the threshold τ. Compared with the classical ReliefF algorithm, our algorithm reduces the complexity of similarity calculation from O(MN) to O(M), the complexity of finding the nearest neighbor from O(M) to O(√M), and resource consumption from O(MN) to O(MlogN). Meanwhile, compared with the quantum Relief algorithm, our algorithm is superior in finding the nearest neighbor, reducing the complexity from O(M) to O(√M). Finally, in order to verify the feasibility of our algorithm, a simulation experiment based on Rigetti with a simple example is performed. © 2023, CC BY.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：