检索结果-内蒙古大学图书馆

arXiv 2018年

作者： Bayley, Sean Falessi, Davide Dept. of Computer Science and Engineering Notre Dame United States Dept. of Computer Science and Software Engineering California Polytechnic State University

Recent studies have shown that tuning prediction models increases prediction accuracy and that Random Forest can be used to construct prediction intervals. However, to our best knowledge, no study has investigated the need to, and the manner in which one can, tune Random Forest for optimizing prediction intervals - this paper aims to fill this gap. We explore a tuning approach that combines an effectively exhaustive search with a validation technique on a single Random Forest parameter. This paper investigates which, out of eight validation techniques, are beneficial for tuning, i.e., which automatically choose a Random Forest configuration constructing prediction intervals that are reliable and with a smaller width than the default configuration. Additionally, we present and validate three meta-validation techniques to determine which are beneficial, i.e., those which automatically chose a beneficial validation technique. This study uses data from our industrial partner (Keymind Inc.) and the Tukutuku Research Project, related to post-release defect prediction and Web application effort estimation, respectively. Results from our study indicate that: i) the default configuration is frequently unreliable, ii) most of the validation techniques, including previously successfully adopted ones such as 50/50 holdout and bootstrap, are counterproductive in most of the cases, and iii) the 75/25 holdout meta-validation technique is always beneficial;i.e., it avoids the likely counterproductive effects of validation techniques. Copyright © 2018, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Underrepresented Groups Threats to Belonging in Computing

Underrepresented Groups Threats to Belonging in Computing

引用

Research in Equity and Sustained Participation in engineering, Computing, and Technology (RESPECT)

作者： Marlon Mejias Ketly Jean-Pierre Gloria Washington Legand Burge Dept. of Software & Information Systems University. of North Carolina at Charlotte Charlotte NC USA Post-Doctoral Fellow - Process Data Educcational Testing Services Princeton NJ USA Dept. of Electrical Engineering & Computer Science Howard Unversity Washingington D.C. USA

Increasing the number of students exposed to computer science (CS) may not increase throughput in the pipeline if barriers to retention are not addressed. One major barrier is student's perception of belonging. To begin creating theoretical grounds for a common discourse to successfully matriculating underrepresented students, and retaining them in the field, threats to their belonging (barriers to retention) and how a survey of literature suggest they impact CS are presented.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Android Malware Detection Using Feature Selections and Random Forest

Android Malware Detection Using Feature Selections and Rando...

引用

International Conference on software Security and Assurance (ICSSA)

作者： Taehoon Eom Heesu Kim SeongMo An Jong Sou Park Dong Seong Kim Dept. of Computer Engineering Korea Aerospace University Seoul South Korea Dept. of Computer Science and Software Engineering The University of Queensland Australia

ISBN: (数字)9781538692103

ISBN: (纸本)9781538692110

Malicious software (Malware) applications in Android ecosystem is one of the critical issues. Manual detection of malware is not cost-effective and cannot keep up with the fast evolution of malware development in Android. A machine learning based malware detection has attempted to automate the detection of malware in Android. In this paper, we present new Android malware detection methods. The main idea of our proposed approach is to use three different feature selection methods before malware detection model using a machine learning algorithm is constructed. We used both Malware Genome Project dataset and our own crawled dataset to show the effectiveness of the proposed methods.

关键词： Malware Feature extraction Forestry Androids Humanoid robots Machine learning algorithms Smart phones

来源：评论

学校读者我要写书评

暂无评论

LARNN: Linear Attention Recurrent Neural Network

arXiv

引用

arXiv 2018年

作者： Chevalier, Guillaume Dept. of Computer Science and Software Engineering Laval University Quebec Canada

The Linear Attention Recurrent Neural Network (LARNN) is a recurrent attention module derived from the LSTM cell and ideas from the consciousness Recurrent Neural Network (RNN). Yes, it LARNNs. The LARNN uses attention on its past cell state values for a limited window size k. The formulas are also derived from the Batch Normalized Long Short-Term Memory (BN-LSTM) cell and the Transformer Network for its Multi-Head Attention Mechanism. The Multi-Head Attention Mechanism is used inside the cell such that it can query its own k past values with attention with restricted windowing on the k most recent previous cell state. This has the effect of augmenting the rank of the tensor with the attention mechanism, such that the cell can perform complex queries to question its previous inner memories, which should augment the long short-term effect of the memory. With a clever trick, the LARNN cell with attention can be easily used inside a loop on the cell state, just like how any other Recurrent Neural Network (RNN) cell can be looped linearly through time series. This is due to the fact that its state, which is looped upon throughout time steps within time series, stores the inner states in a "first in, first out" queue which contains the k most recent states and on which it is easily possible to add static positional encoding when the queue is represented as a tensor. This neural architecture yields better results than the plain, vanilla LSTM cells. It can obtain results of 91.924% for the test accuracy, compared to the previously attained 91.653% using vanilla LSTM cells. Note that this is not to compare to other research, where up to 93.349% is obtained, but by costly using 18 LSTM cells rather than with 2 to 3 cells as analyzed here and in comparison. Finally, an interesting discovery is made, such that adding activation within the multi-head attention mechanism’s linear layers can yield better results in the context researched hereto. Copyright © 2018, The Authors. All

关键词： Cells

来源：评论

学校读者我要写书评

暂无评论

Deep learning for automated image classification of seismic damage to built infrastructure 11

Deep learning for automated image classification of seismic ...

引用

11th National Conference on Earthquake engineering 2018: Integrating Science, engineering, and Policy, NCEE 2018

作者： Patterson, B. Leone, G. Pantoja, M. Behrouzi, A. Dept. of Computer Science & Software Engineering California Polytechnic State University - San Luis Obispo San Luis ObispoCA93407 United States Dept. of Architectural Engineering California Polytechnic State University - San Luis Obispo San Luis ObispoCA93407 United States

ISBN: (纸本)9781510873254

The amount of structural damage image data produced in the aftermath of an earthquake can be staggering. It is challenging for a few human volunteers to efficiently filter and tag these images with meaningful damage information. The proposed solution is to automate post-earthquake reconnaissance image tagging activities by training a computer algorithm to classify each occurrence of damage per building material and structural member type. The approach is based on deep learning (DL), a subset of machine learning loosely based on the operation of a biologic neural system, which aims to learn and extract accurate representations from large data sets. DL algorithms are data driven;improving with increased training data. Thanks to the vast amount of data available and advances in computer architectures, DL has become one of the most popular image classification algorithms producing results comparable to and in some cases superior to human experts. The authors implemented a DL algorithm to automatically identify multiple damage types and associated structural members in a single image by adapting a pre-trained deep residual network. The algorithm was tested as follows: (i) binning building images as damage-no damage (88% accuracy), (ii) drawing a bounding box around damage in buildings (85% accuracy) and short/captive reinforced concrete columns with shear damage (77% accuracy). The lower accuracy of correctly identifying a target region in an image (test ii) compared to simple binning (test i) is anticipated since it is a more complex problem and there is a more limited number of expertly tagged training images (200 count) for shear damage-short column condition being studied. The research team expects algorithm accuracy will improve as with training on additional images tagged for certain damage-structure pairs by a diverse set of experts. Copyright © 2018 Earthquake engineering Research Institute. All rights reserved.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Context Based Classification of Twitter 4

Comparative Analysis of Context Based Classification of Twit...

引用

4th International Conference on Advances in Computing, Communication and Automation, ICACCA 2018

作者： Tiwana, Muhammad Salman Javeed, Farooq Lali, Muhammad Ikramullah Dar, Hafsa Bilal, Muhammad Dept. of CS and IT University of Sargodha Sargodha Pakistan Dept. of Computer Science University of Gujrat Gujrat Pakistan Dept. of Software Engineering University of Gujrat Gujrat Pakistan School of Computing and IT Taylor's University Subang Jaya Malaysia Centre for Data Science and Analytics Taylor's University Subang Jaya Malaysia

ISBN: (纸本)9781538671672

Social media offers online data source where internet users' share their opinions, views and discuss any news or events that happen around the world. Twitter is a popular social media which effectively takes part in any mega event and is used before, during and after live events. Some tweets become trend based on their popularity. The trending tweets are classified by twitter into categories like: Sports (S), Entertainment (E), Politics (P), and Technology (T) which are used in our work. We have used context based meanings to further improve the trending tweet classification results. In this article, we have verified the twitter's automated classification results with manual classification by experts. Furthermore, we compared the classification results with SVM, Linear Regression, Logistic Regression and Naive Bayes implemented in Weka tool. We found that twitter's classifier works with almost 89% accuracy in our dataset. This work would contribute in improving misclassification of data of different categories on social media. © 2018 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

ICN-Based Light-Weighted Mobility Support in IoT

ICN-Based Light-Weighted Mobility Support in IoT

引用

International Conference on computer Communications and Networks (ICCCN)

作者： Donghyeok An Dohyung Kim Dept. of Computer Engineering Changwon National University Changwon South Korea Dept. of Software and Computer Engineering Ajou University Suwon south Korea

In Information-Centric Networking (ICN), name-based addressing and in-network caching allow content to be efficiently distributed/accessed. These properties of ICN have been researched in the arena of wireless domain to implement light-weighted communication protocols. In this paper, specifically, we present an ICN-based content delivery scheme for Internet-of-Things (IoT), and show how the proposed scheme support seamless hand-off.

关键词： Logic gates Relays Wireless communication Ad hoc networks Internet of Things Unicast Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Towards Optimal Search: An Efficient Search Algorithm for Arabic Text using Secant Method 2

Towards Optimal Search: An Efficient Search Algorithm for Ar...

引用

2nd Borneo International Conference on Applied Mathematics and engineering, BICAME 2018

作者： Kabir, Muhammad Nomani Alginahi, Yasser Ali, Jahan Benseghir, Hocine University Malaysia Pahang Faculty of Computer Systems Software Engineering Gambang Kuantan26300 Malaysia University of Windsor Dept. of Electrical and Computer Engineering WindsorONN9B 3P4 Canada University Malaysia Faculty of Engineering Technology Pahang Kuantan26300 Malaysia

ISBN: (纸本)9781538677254

Search techniques are an integral part for text authentication and plagiarism checks. In this work, our aim is to develop an efficient search algorithm for Arabic text (words and sentences) in a large database. The database contains the authentic source of information where information is ordered;thus the efficient algorithm can be used for searching the text in the database. The proposed search algorithm uses a quasi-Newton method - Secant method instead of the traditional binary search. The results show that the secant method has much faster convergence property than the binary search and hence the algorithm can find the search text in a shorter time period. © 2018 IEEE.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Fair and autonomous sharing of federate learning models in mobile Internet of Things

arXiv

引用

arXiv 2020年

作者： Hao, Xiaohan Ren, Wei Xiong, Ruoting Zheng, Xianghan Zhu, Tianqing Xiong, Neal N. School of Computer Science China University of Geoscience Wuhan China Guangxi Key Laboratory of Cryptography and Information Security Guilin541004 China Key Laboratory of Network Assessment Technology CAS Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Mingbyte Technology QingDao China School of Software University of Technology Sydney UltimoNSW2007 Australia Dept. of Mathematics and Computer Science Northeastern State University United States

Federate learning can conduct machine learning as well as protect the privacy of self-owned training data on corresponding ends, instead of having to upload to a central trusted data aggregation server. In mobile scenarios, a centralized trusted server may not be existing, and even though it exists, the delay will not be manageable, e.g., smart driving cars. Thus, mobile federate learning at the edge with privacy-awareness is attracted more and more attentions. It then imposes a problem - after data are trained on a mobile terminal to obtain a learned model, how to share the model parameters among others to create more accurate and robust accumulative final model. This kind of model sharing confronts several challenges, e.g., the sharing must be conducted without a third trusted party (autonomously), and the sharing must be fair as model training (by training data)is valuable. To tackle the above challenges, we propose a smart contract and IPFS (Inter-Planetary File System) based model sharing protocol and algorithms to address the challenges. The proposed protocol does not rely on a trusted third party, where individual-learned models are shared/stored in corresponding ends. Conducted through extensive experiments, three main steps of the proposed protocol are evaluated. The average executive time of the three steps are 0.059s, 0.060s and 0.032s, demonstrating its efficiency. Copyright © 2020, The Authors. All rights reserved.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

CFEA: Collaborative feature ensembling adaptation for domain adaptation in unsupervised optic disc and cup segmentation

arXiv

引用

arXiv 2019年

作者： Liu, Peng Kong, Bin Li, Zhongyu Zhang, Shaoting Fang, Ruogu J. Crayton Pruitt Family Dept. of Biomedical Engineering University of Florida GainesvilleFL United States Department of Computer Science UNC Charlotte CharlotteNC United States School of Software Engineering Xi'an Jiaotong University Xi'an China Sensetime Research

Recently, deep neural networks have demonstrated comparable and even better performance with board-certified ophthalmologists in well-annotated datasets. However, the diversity of retinal imaging devices poses a significant challenge: domain shift, which leads to performance degradation when applying the deep learning models to new testing domains. In this paper, we propose a novel unsupervised domain adaptation framework, called Collaborative Feature Ensembling Adaptation (CFEA), to effectively overcome this challenge. Our proposed CFEA is an interactive paradigm which presents an exquisite of collaborative adaptation through both adversarial learning and ensembling weights. In particular, we simultaneously achieve domain-invariance and maintain an exponential moving average of the historical predictions, which achieves a better prediction for the unlabeled data, via ensembling weights during training. Without annotating any sample from the target domain, multiple adversarial losses in encoder and decoder layers guide the extraction of domain-invariant features to confuse the domain classifier and meanwhile benefit the ensembling of smoothing weights. Comprehensive experimental results demonstrate that our CFEA model can overcome performance degradation and outperform the state-of-the-art methods in segmenting retinal optic disc and cup from fundus images. Code is available at https://***/cswin/AWC. Copyright © 2019, The Authors. All rights reserved.

关键词： Ophthalmology

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：