检索结果-内蒙古大学图书馆

11th international conference on Education Technology and Computers, ICETC 2019

作者： Zhang, Jianzhen Niu, Yuyan Long, Jiehong Shanxi Institute of Mechanical and Electrical Engineering Changzhi China Agricultural Bank of China Changzhi Branch Office Changzhi China

ISBN: (纸本)9781450372541

Massive Open Online Courses (MOOCs) are one of the most important events in the history of education in the 21st century, which not only tearing down the walls of universities, but also achieving greatly the sharing of high-quality educational resources and providing opportunities for everyone who wants to improve themselves. this paper explored the feasibilities of MOOCs in China's vocational education and training from three aspects, including national economic strategy, enterprise market competition and individual career planning. After analyzing the difficulties, such as how to select the typical work tasks, how to draw private professional MOOC plan, how to develop professional ability, and how to get social recognition for MOOCs, four approaches were proposed, including that MOOC platform and enterprises build and share the professional MOOCs collectively, getting private MOOCs plan by big data analysis technology and data mining technology, learning professional MOOCs with online and offline, adding online virtual simulation to MOOCs learning. Approaches above will enhance MOOCs feasibility in China's Vocational education and training. © 2019 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Prediction of Recurrence and Non-recurrence Events of Breast Cancer using Bagging Algorithm

Prediction of Recurrence and Non-recurrence Events of Breast...

引用

international conference on Computing and Networking Technology (ICCNT)

作者： Sajib Kabiraj Laboni Akter M. Raihan Nusrat Jahan Diba Etu Podder Md. Mehedi Hassan North Western University Khulna Bangladesh Khulna University of Engineering & Technology Khulna Bangladesh Electronics and Communication Engineering Discipline Khulna University Khulna Bangladesh

ISBN: (数字)9781728168517

ISBN: (纸本)9781728168524

Breast cancer is a type of cancer which prescribed life-threading cancer of women. Cancer growth begins when cells start to out of control. Breast cancer is basically found in family sources, routinely on account of DNA changes. Normal or inside parts, for instance: age, sex, procured inherited deformations and skin type. For this study, 275 instances with 12 features and outcome of having recurrence and non-recurrence event were collected. 10-fold cross-validation had applied for training the data and the accuracy for Bagging algorithm is 73.8182 %. Naive Bayes classifier had been used as base learner of Bagging algorithm.

关键词： Breast cancer Bagging Machine learning algorithms Prediction algorithms Support vector machines Training Decision trees

来源：评论

学校读者我要写书评

暂无评论

Basic Consideration of Collaborative Filtering Based on Rough C-Means Clustering

Basic Consideration of Collaborative Filtering Based on Roug...

引用

international Symposium on Soft Computing and intelligent Systems (SCIS)

作者： Seiki Ubukata Shu Takahashi Akira Notsu Katsuhiro Honda Graduate School of Engineering Osaka Prefecture University Sakai Japan Graduate School of Humanities and Sustainable System Sciences Osaka Prefecture University Sakai Japan

ISBN: (数字)9781728197326

ISBN: (纸本)9781728197333

Collaborative filtering (CF) is a technique for realizing recommender systems found in e-commerce sites and video streaming services. Appropriate content recommendations to individual users will improve usability, purchase rates, video ratings, and corporate profits. Clustering is a technique for automatically classifying and summarizing the data by extracting clusters composed of similar objects. Clustering-based CF extracts clusters composed of users with similar interests and preferences, and recommends contents with high preference degree within the cluster. Rough C-means (RCM)-type methods can extract overlapped clusters dealing with the certainty, possibility, and uncertainty of belonging of object to clusters. In this study, we propose two-types of RCM-based CF, namely, GRCM-based CF (GRCM-CF) and π GRCM-based CF ( π GRCM-CF). Furthermore, we verified the recommendation performance of the proposed methods, GRCM-CF and π GRCM-CF, through numerical experiments using two real-world datasets, namely, NEEDS-SCAN/PANEL dataset and MovieLens dataset.

关键词： Uncertainty Streaming media Recommender systems Indexes data mining Collaboration Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Ad hoc multi-input functional encryption 11

Ad hoc multi-input functional encryption

引用

11th Innovations in theoretical Computer Science conference, ITCS 2020

作者： Agrawal, Shweta Clear, Michael Frieder, Ophir Garg, Sanjam O’Neill, Adam thaler, Justin Dept. of Computer Science and Engineering IIT Madras Chennai India Dept. of Computer Science Georgetown University WashingtonDC United States Dept. of EECS University of California BerkeleyCA United States Dept. of Computer Science University of Massachusetts AmherstMA United States

ISBN: (纸本)9783959771344

Consider sources that supply sensitive data to an aggregator. Standard encryption only hides the data from eavesdroppers, but using specialized encryption one can hope to hide the data (to the extent possible) from the aggregator itself. For flexibility and security, we envision schemes that allow sources to supply encrypted data, such that at any point a dynamically-chosen subset of sources can allow an agreed-upon joint function of their data to be computed by the aggregator. A primitive called multi-input functional encryption (MIFE), due to Goldwasser et al. (EUROCRYPT 2014), comes close, but has two main limitations: it requires trust in a third party, who is able to decrypt all the data, and it requires function arity to be fixed at setup time and to be equal to the number of parties. To drop these limitations, we introduce a new notion of ad hoc MIFE. In our setting, each source generates its own public key and issues individual, function-specific secret keys to an aggregator. For successful decryption, an aggregator must obtain a separate key from each source whose ciphertext is being computed upon. the aggregator could obtain multiple such secret-keys from a user corresponding to functions of varying arity. For this primitive, we obtain the following results: We show that standard MIFE for general functions can be bootstrapped to ad hoc MIFE for free, i.e. without making any additional assumption. We provide a direct construction of ad hoc MIFE for the inner product functionality based on the learning with Errors (LWE) assumption. this yields the first construction of this natural primitive based on a standard assumption. At a technical level, our results are obtained by combining standard MIFE schemes and two-round secure multiparty computation (MPC) protocols in novel ways highlighting an interesting interplay between MIFE and two-round MPC. © Shweta Agrawal, Michael Clear, Ophir Frieder, Sanjam Garg, Adam O’Neill, and Justin thaler.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Predicting fishing activities based on DeepFM 3

Predicting fishing activities based on DeepFM

引用

3rd international conference on Computer Science and Artificial Intelligence, CSAI 2019 and its Workshop - the 11th international conference on Information and Multimedia Technology, ICIMT 2019

作者： Yu, Yongzhao Liu, Li Su, Wei Zhang, Jiuwen Wu, Jinzhao School of Information Science and Engineering Lanzhou University Lanzhou China Guangxi University and Guangxi University for Nationalities Nanning China

ISBN: (纸本)9781450376273

With the advent of the era of big data, it is necessary to obtain volume, veracity information on fishing activities. In this paper, we present a new approach to predict fishing activities using DeepFM with historical fishing data of Chinese vessels. this work is an innovative attempt to use deep learning model to find worthy feature interactions in historical fishing data automatically. First, we pre-processed the historical fishing data. then we used DeepFM to learned low-order and high order feature interactions from pre-processed historical fishing data automatically, and the output of DeepFM was taken as the probability of fishing. Finally, we assessed experimental results by calculating the Area Under Curve (AUC). By comparing with the FM and DNN, DeepFM had achieved the best results, and we founded that high-order feature interactions are more worthy than low-order feature interactions in predicting fishing activities. © 2019 Association for Computing Machinery.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Sensors-based Human Activity Recognition with Convolutional Neural Network and Attention Mechanism

Sensors-based Human Activity Recognition with Convolutional ...

引用

IEEE international conference on Software engineering and Service Sciences (ICSESS)

作者： Wenbo Zhang Tao Zhu Congmin Yang Jiyi Xiao Huansheng Ning School of Computer University of South China Hengyang Hunan China School of Computer and Communication Engineering University of Science & Technology Beijing Beijing China

ISBN: (数字)9781728165790

ISBN: (纸本)9781728165806

Recently, Human Recognition Activity (HAR) has received more and more attention. At present, Recurrent neural networks (RNN), long short-term memory in particular, are main approaches in HAR. However, RNN suffers from the fact that it cannot process sequences in parallel and longer sequences cannot be remembered well. therefore, this paper applies the attention mechanism to explore the relevant time context, and proposes a new model, named DeepConvAttn. DeepConvAttn is based on a well-known deep learning model, DeepConvLSTM. these two models are compared in experiments, and the results show DeepConvAttn is better than DeepConvLSTM on two popular HAR benchmark datasets.

关键词： Wireless communication Wireless sensor networks Recurrent neural networks Sensor fusion data processing Feature extraction Software engineering

来源：评论

学校读者我要写书评

暂无评论

Prediction and Rule Generation for Leukemia using Decision Tree and Association Rule Mining

Prediction and Rule Generation for Leukemia using Decision T...

引用

international conference on Electrical and Computer engineering (ICECE)

作者： Anamika Das Mou Md. Wahid Hasan Protap Kumar Saha Nabil Al Raian Priom Anirban Saha East West University Dhaka Bangladesh Florida International University Florida USA

ISBN: (数字)9781665422543

ISBN: (纸本)9781665446617

Leukemia is familiar as the cancer of the bone marrow. Bone marrow is known as the spongy tissue which creates blood cells. that's why for blood cell productivity problems, Leukemia can boost heavily. It generally impacts the leukocytes or white blood cells. And also it grows gradually in human bodies. Both children and adults can be affected by leukemia. In this research, our objective is to detect leukemia applying Machine learning algorithms, which can help medical science to detect leukemia. therefore, we need a system to decide to detect Leukemia. that's why we propose some well-known algorithms to compare accuracy to detect Leukemia in our study. We have used some different types of machine learning algorithms like Decision Tree, Logistic Regression and Random Forest algorithm to get the result that a patient is a cancer patient or not. We collected our data from Z H Shikder Medical College and Hospital, which includes 401 data in our dataset. Among the algorithms, the Decision tree algorithm gives the best result with 84.15% accuracy of prediction. In this paper, we show the comparative results analyzing different algorithms precision, recall and F1 score for our all data samples. We also try to extract rules from features with the help of Apriori algorithm and association rule.

关键词： White blood cells Machine learning algorithms Cells (biology) Prediction algorithms Feature extraction Bones Cancer

来源：评论

学校读者我要写书评

暂无评论

S2-GI: intelligent Selection of Guard Interval in High throughput WLANs

S2-GI: Intelligent Selection of Guard Interval in High Throu...

引用

international conference on Computing and Networking Technology (ICCNT)

作者： Raja Karmakar Soumalya De Arindam Ghosh Tinku Adhikari Punit Jain Techno International New Town Kolkata INDIA

ISBN: (数字)9781728168517

ISBN: (纸本)9781728168524

Short guard interval (SGI) is a new feature of the physical (PHY) layer in High throughput Wireless Local Area Networks (HT-WLANs), like IEEE 802.11n/ac, where the value of the guard interval is set to 400ns instead of general 800ns. By reducing the overhead of extra idle time between transmissions of two successive symbols, SGI helps to enhance the average system throughput, compared to the guard interval of 800ns. However, the signal quality of the channel and high data traffic can affect the performance of SGI in a network. In a congested network scenario, channel interference and load of data transmission are increased; and consequently, inter-symbol interference becomes higher, which increases the rate of packet losses and thus, reduces average throughput in the case of SGI. In this paper, we design thompson sampling based online learning mechanism, Smart Selector of Guard Interval (S2-GI), to select guard interval dynamically by considering the present channel condition. We analyze the performance of S2-GI through a thorough simulation in IEEE 802.11ac WLAN and we observe that S2-GI can enhance the network performance.

关键词： throughput Signal to noise ratio Interference Probability distribution Wireless LAN data communication Standards

来源：评论

学校读者我要写书评

暂无评论

A big data framework for network security of small and medium enterprises for future computing

引用

JOURNAL OF SUPERCOMPUTING 2019年第6期75卷 3334-3367页

作者： Kim, Ha-Kyun So, Won-Hyun Je, Seung-Mo Pukyong Natl Univ Daeyeon Dept MIS Div Business Busan South Korea Acad Korean Studies Grad Sch Korean Studies Seongnam South Korea Korea Univ Dept Comp Sci Educ Seoul South Korea

Recently, there have been some concerns for the network control systems which have been built for the major closed national communication infrastructures in the Republic of Korea. In particular, the control systems used by the small- and medium-sized enterprises (SMEs) often did not consider much on the sophisticated internal or external threats such as hacking or identity theft when they were first developed. For this reason, SMEs have been constantly exposed to internal/external security threats posed by both internal and external attackers, while they are using their own internal business networks constantly stay linked to the external networks operated by their cooperating companies or institutions for the convenience of conducting business. Hence, the security of SMEs' business networks is still vulnerable, but it is not easy to obtain the information from security officials about what are the actual problems they are facing. In this study, a method of strengthening the SMEs' security capability is proposed, especially focusing on a framework to be used when applying big data. For the simulations, necessary data was provided by the SMEs who have experienced security threats in the past. An empirical analysis was conducted with such data, and a framework was designed accordingly. the framework was simulated in a test bed for adjustment. the demographic characteristics of the data providers were studied to ensure a more accurate analysis of the data. the frequency and reliability analysis methods were used together with the machine learning technique to measure the reliability of the data, whereas a factor analysis was applied the validity. Partial least squares (PLS) was used for the empirical analysis as well. An application to which these methodologies were applied was implemented with Java Android and will be provided to the security managers of SMEs upon completion. It is expected that the framework proposed in this study will be a useful solution for SMEs f

关键词： Big data Framework Big data framework SMEs PLS Python Java Android UML User interface Android application

来源：评论

学校读者我要写书评

暂无评论

Deep learning Techniques for Early Detection of Diabetic Retinopathy: Recent Developments and Techniques

Deep Learning Techniques for Early Detection of Diabetic Ret...

引用

IEEE international conference on Computing, Communication and Security (ICCCS)

作者： Dolly Das Saroj Kumar Biswas Sivaji Bandyopadhyay Rabul Hussain Laskar Computer Science and Engineering National Institute of Technology Silchar Silchar India Electronics and Communication Engineering National Institute of Technology Silchar Silchar India

ISBN: (数字)9781728191805

ISBN: (纸本)9781728191812

Diabetic Retinopathy (DR) is a health disorder in human retina, caused as a result of Diabetes Mellitus (DM). It leads to loss of vision and in severe cases it results in blindness, as a result of mutilation of the retina. Statistical data estimates that 80% of diabetic patients, suffering from prolonged diabetes, also suffer from DR. Hence, in the present time DR has become an imperative matter and requires primary stage evaluation and assessment such that loss of vision and blindness can be averted. However, the physical diagnosis of the disease is laborious and susceptible to error. Besides, the convenience of availing Ophthalmologist irrespective of place and time, is not possible. thus, the necessity of an exceedingly enhanced and computerized intelligent system arises, that can be engaged for the initial stage detection of DR. A number of Machine learning models are proposed by researchers since decades, for the diagnosis of DR. Various feature extraction techniques are also proposed for deriving prominent retinal lesions, for initial stage diagnosis of DR. However, traditional Machine learning models showcase poor generalization during feature extraction because of smaller datasets. this can be overcome through use of Deep learning models, larger dataset and high computing processing units for generalization. this paper aims to give an overview about DR, a brief description of the earlier works, and the current automated systems and advancements, for the purpose of early detection of DR. this paper also focuses on the state-of-the-art DR lesions, origin and signs of DR, categories of DR and state-of-the-art Deep learning models, that are proposed and applied for DR detection, at the preliminary stage.

关键词： Retina Diabetes Biomedical imaging Feature extraction Retinopathy Lesions Deep learning

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：