检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data

作者： Michael O. Chen Julian Hodge Peter L. Jin Ella Protz Elizabeth Wong Ruth Obe Ehsan Shakeri Mostafa Cham Matthias K. Gobbert Carlos A. Barajas Vijay R. Sharma Sina Mossahebi Lei Ren Stephen W. Peterson Jerimy C. Polf Departments of Mathematics Dartmouth College USA Dept. of Mathematics and Statistics U. of Maryland USA James M. Bennett High School Salisbury MD USA Department of Mathematics and Sciences Florida Atlantic University USA Department of Mathematics Brookdale Community College USA Dept. of Computer Science and of Software Engineering U. of Houston Clear Lake USA Dept. of Information Systems U. of Maryland USA Dept. of Radiation Oncology U. of Maryland School of Medicine USA Dept. of Physics U. of Cape Town South Africa M3D Inc. USA

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Precision medicine in cancer treatment increasingly relies on advanced radiotherapies, such as proton beam radiotherapy, to enhance efficacy of the treatment. When the proton beam in this treatment interacts with patient matter, the excited nuclei may emit prompt gamma ray interactions that can be captured by a Compton camera. The image reconstruction from this captured data faces the issue of mischaracterizing the sequences of incoming scattering events, leading to excessive background noise. To address this problem, several machine learning models such as Feedfoward Neural Networks (FNN) and Recurrent Neural Networks (RNN) were developed in PyTorch to properly characterize the scattering sequences on simulated datasets, including newly-created patient medium data, which were generated by using a pipeline comprised of the GEANT4 and Monte-Carlo Detector Effects (MCDE) softwares. These models were implemented using the novel ‘Big-data REU Integrated Development and Experimentation’ (BRIDE) platform, a modular pipeline that streamlines preprocessing, feature engineering, and model development and evaluation on parallelized GPU processors. Hyperparameter studies were done on the novel patient data as well as on water phantom datasets used during previous research. Patient data was more difficult than water phantom data to classify for both FNN and RNN models. FNN models had higher accuracy on patient medium data but lower accuracy on water phantom data when compared to RNN models. Previous results on several different datasets were reproduced on BRIDE and multiple new models achieved greater performance than in previous research.

关键词： Particle beams Recurrent neural networks Accuracy Pipelines Phantoms Scattering Cameras Data models software Radiation therapy

来源：评论

学校读者我要写书评

暂无评论

software Techniques for Making Cloud Data Centers Energy-efficient: A Systematic Mapping Study

Software Techniques for Making Cloud Data Centers Energy-eff...

引用

Euromicro Conference on software engineering and Advanced Applications (SEAA)

作者： Fauzia Khan Hina Anwar Dietmar Pfahl Satish Srirama Dept of Software Engineering Foundation University Islamabad Pakistan Institute of Computer Science University of Tartu Tartu Estonia

ISBN: (数字)9781728195322

ISBN: (纸本)9781728195339

Due to high demand, many cloud data centers have been developed across the world, consuming a large amount of energy. Making cloud datacenters energy efficient has become essential. Energy consumption of data centers can be minimized by designing energy-efficient hardware, software, and infrastructure. In this paper, we aim at giving an overview of software techniques, affected stakeholders, performance features, datasets, and tools used to make cloud data centers energy-efficient. To achieve this goal, we conducted a systematic mapping study using five online databases. After applying inclusion/exclusion and quality criteria, we selected 58 publications for further analysis. Our results indicate that all publications are solution and validation type of publications. We did not find publications containing evaluations in industry. We found that workload scheduling is the most frequently proposed technique used to improve cloud datacenters' energy efficiency. We found that not considering violations of service level agreements mostly affects end-users of cloud data centers. When analyzing how suggested solutions are validated, we identified the need to develop a standardized set of performance measures to benchmark software techniques proposed to make cloud data centers greener.

关键词： Cloud computing software Data centers Energy efficiency Green products Hardware Quality of service

来源：评论

学校读者我要写书评

暂无评论

A Post-Mortem Forensic Approach for the Kik Messenger on Android

A Post-Mortem Forensic Approach for the Kik Messenger on And...

引用

International Conference on Information and Communication Systems (ICICS)

作者： Ahmad M. Al-Rawashdeh Ziad A. Al-Sharif Mohammed I. Al-Saleh Ahmed S. Shatnawi Dept. of Computer Science Jordan University of Science and Technology Irbid Jordan Dept. of Software Engineering Jordan University of Science and Technology Irbid Jordan

ISBN: (数字)9781728162270

ISBN: (纸本)9781728162287

Mobile devices have become an essential part of our life. These devices are a platform for social media and chat apps that are often designed to assist us retain our connection with old and new online friends. However, regardless of their valuable social influence, these apps are a medium in which criminals and perpetrators can exploit to attack innocent people. Nevertheless, these apps can provide a wealth of digital artifacts for law enforcement agencies. Often, well-established digital forensic techniques are used to determine criminal cases in the court of law. Therefore, this paper presents a post-mortem memory forensics and digital investigations for the popular instant messaging application named Kik Messenger. Kik is designed to assist users to connect quickly and easily with the world around them. Statistics such as the number of installations and active users underlines its importance. Moreover, the Android operating system and its internal memory, including RAM and NAND flash memory are examined. This paper presents our investigation methodology that employs memory dumps for both NAND flash memory as well as the heap memory. Our results of forensic analysis show promising existences for the sent and received messages and contacts in both types of memory dumps; these incidences are valuable to the digital investigator. Various scenarios are studied, experimentation results show that sent and received messages and contact artifacts can be found in both memories even after the chat session is deleted, messages are individually deleted, contacts are deleted, app is closed, and even after the phone is locked.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CrossWalk: Fairness-enhanced Node Representation Learning

arXiv

引用

arXiv 2021年

作者： Khajehnejad, Ahmad Khajehnejad, Moein Babaei, Mahmoudreza Gummadi, Krishna P. Weller, Adrian Mirzasoleiman, Baharan Dept of Computer Engineering Sharif University of Technology Iran Dept of Data Science and AI Monash University Australia Max Planck Institute for Human Development Germany Max Planck Institute for Software Systems Germany University of Cambridge United Kingdom The Alan Turing Institute United Kingdom Dept of Computer Science University of California Los Angeles United States

The potential for machine learning systems to amplify social inequities and unfairness is receiving increasing popular and academic attention. Much recent work has focused on developing algorithmic tools to assess and mitigate such unfairness. However, there is little work on enhancing fairness in graph algorithms. Here, we develop a simple, effective and general method, CrossWalk, that enhances fairness of various graph algorithms, including influence maximization, link prediction and node classification, applied to node embeddings. CrossWalk is applicable to any random walk based node representation learning algorithm, such as DeepWalk and Node2Vec. The key idea is to bias random walks to cross group boundaries, by upweighting edges which (1) are closer to the groups' peripheries or (2) connect different groups in the network. CrossWalk pulls nodes that are near groups' peripheries towards their neighbors from other groups in the embedding space, while preserving the necessary structural properties of the graph. Extensive experiments show the effectiveness of our algorithm to enhance fairness in various graph algorithms, including influence maximization, link prediction and node classification in synthetic and real networks, with only a very small decrease in performance. © 2021, CC BY.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Resolving Conflict of Interests in Recommending Reviewers for Academic Publications Using Link Prediction Techniques 2

Resolving Conflict of Interests in Recommending Reviewers fo...

引用

2nd International Conference on New Trends in Computing sciences, ICTCS 2019

作者： Al-Zboon, Sa'Ad A. Tawalbeh, Saja Khaled Ai-Jarrah, Heba Al-Asa'D, Muntaha Hammad, Mahmoud Al-Smadi, Mohammad Jordan University of Science and Technology Dept. of Computer Science Irbid Jordan Jordan University of Science and Technology Dept. of Software Engineering Irbid Jordan

ISBN: (纸本)9781728128825

An honest peer-review process is a key for producing high quality scientific research. However, this process depends on two main factors: (1) the expertise of reviewers in the topic of a submitted paper and (2) the relationships between reviewers and authors. To satisfy the first factor, editors and conferences chairs manually select reviewers. Whereas to prevent any conflict of interest (CoI) between reviewers and authors to satisfy the second factor, reviewers and authors are asked to declare any CoI manually. Such a solution is tedious to all actors and error-prone. To solve this problem and satisfy those two factors, we have developed a novel framework that (1) recommend expert reviewers and (2) resolve the CoIproblem. To develop our framework, we have represented the DBLP citation network dataset as a graph database using Neo4J. A Cypher queries used to select expert reviewers. Various link prediction algorithms, especially the Adamic Adar and the Common Neighbors algorithms, have been utilized to resolve any notential conflict of interest. © 2019 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Vanadium Redox Lithium Ion Based Multi-Battery Hybrid Energy Storage System for Microgrid

Vanadium Redox Lithium Ion Based Multi-Battery Hybrid Energy...

引用

2019 IEEE PES Asia-Pacific Power and Energy engineering Conference, APPEEC 2019

作者： Adeleke, Oluwatobiloba Ukil, Abhisek Zhang, Xibeng University of Southampton School of Electronics and Computer Science United Kingdom University of Auckland Dept. of Electrical Computer and Software Engineering New Zealand

ISBN: (纸本)9781728108131

Energy Storage System plays a vital role in assisting Microgrids to control fluctuating load demand with intermittent power supply. As well as enabling power quality to monitored and controlled, this paper introduces a power storage device, Vanadium oxide flow battery which would facilitate the expansion and allow flexibility with the Microgrid network. © 2019 IEEE.

关键词： Lithium-ion batteries

来源：评论

学校读者我要写书评

暂无评论

A Summary Evaluation Method Combining Linguistic Quality and Semantic Similarity

A Summary Evaluation Method Combining Linguistic Quality and...

引用

2020 International Conference on Computational science and Computational Intelligence, CSCI 2020

作者： Wang, Xingwen Liu, Bo Shen, Libin Li, Yong Gu, Rentao Qu, Guangzhi Beijing University of Technology School of Software Engineering Faculty of Information Technology Beijing100124 China Beijing University of Posts and Telecommunications School of Information and Communication Engineering Beijing Laboratory of Advanced Information Networks Beijing100876 China Oakland University Computer Science and Engineering Dept. RochesterMI48309 United States

ISBN: (纸本)9781728176246

Summary evaluation method is crucial to promote the development of summarization technologies. However, most of the existing summary evaluation methods seldom consider the content integrity and readability of summaries simultaneously. This paper proposed a Linguistic Quality and Semantic Similarity Model (LQSSM) to evaluate generated summaries more comprehensively. Considering the readability of summaries, a linguistic quality evaluation network (LQEN) is proposed to evaluate summaries automatically. Meanwhile, a semantic similarity evaluation network (SSEN) is introduced to directly measure the informativeness between the summary and original . Additionally, there is also a comprehensive evaluation using fusion indicators. The LQSSM and Recall-Oriented Understudy for Gisting Evaluation (ROUGE) methods were used to score the summaries generated by five models. The results showed that the proposed method gave further feedback from different angles on the basis of reaching the level of other methods. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Manifold regularized dynamic network pruning

arXiv

引用

arXiv 2021年

作者： Tang, Yehui Wang, Yunhe Xu, Yixing Deng, Yiping Xu, Chao Tao, Dacheng Xu, Chang Dept. of Machine Intelligence Peking University China Noah’s Ark Lab Huawei Technologies China Central Software Institution Huawei Technologies China School of Computer Science Faculty of Engineering University of Sydney Australia

Neural network pruning is an essential approach for reducing the computational complexity of deep models so that they can be well deployed on resource-limited devices. Compared with conventional methods, the recently developed dynamic pruning methods determine redundant filters variant to each input instance which achieves higher acceleration. Most of the existing methods discover effective sub-networks for each instance independently and do not utilize the relationship between different inputs. To maximally excavate redundancy in the given network architecture, this paper proposes a new paradigm that dynamically removes redundant filters by embedding the manifold information of all instances into the space of pruned networks (dubbed as ManiDP). We first investigate the recognition complexity and feature similarity between images in the training set. Then, the manifold relationship between instances and the pruned sub-networks will be aligned in the training procedure. The effectiveness of the proposed method is verified on several benchmarks, which shows better performance in terms of both accuracy and computational cost compared to the state-of-the-art methods. For example, our method can reduce 55.3% FLOPs of ResNet-34 with only 0.57% top-1 accuracy degradation on ImageNet. Copyright © 2021, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

A Systematic Review on Application of Deep Learning Techniques for software Quality Predictive Modeling

A Systematic Review on Application of Deep Learning Techniqu...

引用

Computational Performance Evaluation (ComPE), International Conference on

作者： Ruchika Malhotra Shreya Gupta Tanishq Singh Dept. of Computer Science and Engineering Delhi Technological University Delhi India Dept. of Software Engineering Delhi Technological University Delhi India

ISBN: (数字)9781728166445

ISBN: (纸本)9781728166452

software quality prediction is the process of evaluating the software developed for various metrics like defect prediction, bug localisation, effort estimation etc. To evaluate these metrics a myriad of techniques have been developed in the literature, from manual assessment to application of machine learning and statistical testing. These methodologies, however, had lower accuracy in determining SQPMs due to their inability to model the complex relationships in the training data. With the wide emergence of deep learning, not only has the accuracy of the pre-existing models enhanced, but it has also opened doors for new metrics that could be evaluated and automated. This study performs a systematic literature review of research papers published from January 1990 to January 2019 that used deep learning to evaluate software quality prediction metrics (SQPM). The paper identifies 20 primary studies and 7 categories of application of deep learning in SQPM. Models using deep learning techniques significantly outperform other traditional methodologies in almost all studies. The concept and external threats to the models are limited, however the time taken to train these models is large. The techniques, currently predominantly applied for defect prediction, have shown promising results in other diverse software engineering fields like code search and effort estimation by modeling the source code efficiently. There is, hence, scope for incorporating deep learning further with pragmatic use and diverse application. The need to find scalable solutions, however, still persists.

关键词： Machine learning Measurement Systematics Predictive models Quality assessment software Estimation

来源：评论

学校读者我要写书评

暂无评论

E-learning in the COVID-19 context - Epidemiological and educational challenges

E-learning in the COVID-19 context - Epidemiological and edu...

引用

2020 International Conference Automatics and Informatics, ICAI 2020

作者： Stefanov, Radkov Rosen Desislava Ivanova, Vankova Grigorova, Radkova Zhaneta Yulka Petkova, Petkova Technical University of Varna Dept. of Software and Internet Technologies Varna Bulgaria Medical University of Varna Dept. of Social Medicine and Healthcare Organisation Varna Bulgaria Medical University of Varna Publising Dept. Varna Bulgaria Technical University of Varna Dept. of Computer Science and Engineering Varna Bulgaria

ISBN: (纸本)9781728193083

The Coronavirus pandemic has created a number of challenges in all areas of life. In particular, continuing education in distance form, in conditions of social isolation. Both social and learning problems in the context of COVID-19 are *** challenges in e-learning are considered from an objective and subjective point of view, as well as from a technological point of view. Good examples from the practice of dealing with situations depending on the specifics of the studied disciplines are *** proposals for the construction of an appropriate infrastructure for the purposes of e-learning are presented. © 2020 IEEE.

关键词： Public health

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：