检索结果-内蒙古大学图书馆

32nd International Florida Artificial Intelligence Research Society Conference, FLAIRS 2019

作者： Sedighi, Zeinab Ebrahimpour-Komleh, Hossein Bagheri, Ayoub Kosseim, Leila Dept. of Computer Engineering Faculty of Computer and Electrical Engineering University of Kashan Kashan Iran Dept. of Methodology and Statistics Faculty of Social Sciences Utrecht University Utrecht Netherlands Dept. of Computer Science and Software Engineering Concordia University Montreal Canada

ISBN: (纸本)9781577358053

Fake opinion attacks, consisting of the malicious dissemination of fake reviews, can be detrimental to both customers as well as organizations. Several methods have been proposed to automatically detect deceptive reviews;however, these rely on manual feature engineering methods to build classifiers based on labeled data. Deep Neural Networks coupled with an Attention mechanism have recently been shown to improve the performance of many classification tasks, as it enables the model to learn and focus automatically on the most the important features. This paper describes our approach to apply an attention based deep neural network for the detection of truthful versus fake reviews. The evaluation of our model shows that its performance is significantly better than traditional models, and requires no hand feature engineering. © 2019, Association for the Advancement of Artificial Intelligence (***). 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

Information visualization program for analysis and education of power systems - part 1: Drawing and editing functions

引用

Transactions of the Korean Institute of Electrical Engineers 2020年第9期69卷 1295-1302页

作者： Cha, Hyo-Won Kim, Byoung-Ho Hong, Min Kim, Kyu-Ho Kim, Hongrae Dept. of Electronics and Information Engineering Soonchunhyang University Korea Republic of Dept. of Electrical and Robot Engineering Soonchunhyang University Korea Republic of Dept. of Electronics and Information Engineering Soonchunhyang University Korea Republic of Dept. of Computer software Engineering Soonchunhyang University Korea Republic of Dept. of Electrical Engineering Hankyong University Korea Republic of

In modern power systems, the data for the analysis, monitoring, and operation has become massive. In order to provide the present operating states of the power systems, it is required to have effective visualization methods. In this paper, we present the software to monitor and analyze the power system operations and to show the operating information of the power systems. The program includes the functions for drawing and editing the power system configuration and related information. Automatic drawing function of one line diagram for the power systems is included in the software program, using the geographical information of the buses. The information on buses, lines, transformers and shunt devices can be modified on the diagram and also in the text-based files. The developed software will be used to analyze the operating conditions of the power systems, and also to educate the power system operators. © The Korean Institute of Electrical Engineers. This is an Open-Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://***/licenses/by-nc/4.0/) which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

IEEE ICCI*CC Series in Year 20: Latest Advances in Cognitive Computing (Plenary Panel Report-II) 20

IEEE ICCI*CC Series in Year 20: Latest Advances in Cognitive...

引用

20th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2021

作者： Kinsner, Witold Zhu, Haibin Baciu, George Luo, Guiming Rubio, Fernando Sui, Jie Huang, Runhe Hiraishi, Hironori Peng, Jun Chen, Liang Univ. of Manitoba FI2CICC Dept of ECE Winnipeg Canada Nipissing University FI2CICC ON Canada Hong Kong Polytechnic University FI2CICC Dept. of Computing Hong Kong Tsinghua University FI2CICC Software Institute Beijing China Complutense Univ. of Madrid FI2CICC Dept. of Computer Systems and Computation Spain Aberdeen University FI2CICC Aberdeen United Kingdom Hosei University FI2CICC Faculty of Computer and Information Sciences Japan Ashikaga University Faculty of Engineering Tochigi326-8558 Japan Chongqing Univ. of Science and Technology FI2CICC School of AI Chongqing China Univ. of Northern British Columbia Dept. of Computer Science BC Canada

ISBN: (纸本)9781665421195

Cognitive Computing (CC) is a contemporary field of fundamental intelligence theories and general AI technologies triggered by the transdisciplinary development in intelligence, computer, brain, knowledge, cognitive, robotic, and cybernetic sciences for engineering implementations. This paper presents a summary of the plenary panel (Part II) on the theoretical foundations of CI/CC and recent breakthroughs in AI engineering reported in the 20th IEEE International ICCI*CC Conference (ICCI*CC'21). The latest advances in CI and CC towards general AI are presented by twenty-Two distinguished panelists. Strategic AI engineering applications in CI, CC, and cognitive systems are elaborated for abstract intelligence, cognitive robots, autonomous systems, intelligent vehicles, and safety-And-mission-critical systems. © 2021 IEEE.

关键词： Cognitive systems

来源：评论

学校读者我要写书评

暂无评论

Reducing Ambiguity in Requirements Elicitation via Gamification

Reducing Ambiguity in Requirements Elicitation via Gamificat...

引用

IEEE International Conference on Requirements engineering

作者： Hafsa Shareef Dar Dept. of Computer Science and Software Engineering Int. Islamic University Islamabad Islamabad Pakistan

ISBN: (数字)9781728174389

ISBN: (纸本)9781728174396

The overall quality and success of software highly depends on the involvement of stakeholders. Requirements elicitation supports RE analyst to gather requirements from the stakeholders based on their needs. There are multiple elicitation techniques present in literature and used by the practitioners. Some of them are questionnaires, interviews, prototyping, and user stories etc. However, these techniques are based on textual representation of requirements. These techniques are quite common among the requirement engineers yet problems of ambiguity, inconsistency, incompleteness still exist mostly due to their textual nature and lack of stakeholder involvement. Lack of clarity about the system increases the ambiguity of what exactly are the system requirements. Since elicitation is carried at an early stage of development the users are not sure of what they want, as requirements tend to evolve with the help of discussions and interactions among various stakeholders and technical team. Furthermore, the conventional elicitation methods are limited when it comes to stakeholders' participation and involvement, thus leaving a space for more ambiguous and incomplete requirements. In this work, Gamification, a game-based context will be used in non-gaming context for user involvement in fun ways. During elicitation, gamification would help to involve and interact with the stakeholders, with an intention to develop their interest in eliciting and finalizing system requirements. The goal of this paper is to reduce ambiguity during requirements elicitation. This would help in reducing the cost and time of development. Furthermore, we will elicit software requirements using gamification by developing a gamification tool with a focus to elicit unambiguous requirements by ensuring users' participation and maintaining interest. The validation of tool would be done using multiple confirmatory case studies from software industry.

关键词： Stakeholders Tools software Requirements engineering Games Unified modeling language Interviews

来源：评论

学校读者我要写书评

暂无评论

IEEE Workshop NEXTA 2021: The Next Level of Test Automation - Welcome Message

Proceedings - 2021 IEEE 14th International Conference on Sof...

引用

Proceedings - 2021 IEEE 14th International Conference on software Testing, Verification and Validation Workshops, ICSTW 2021 2021年 XIX页

作者： Eldh, Sigrid Garousi, Vahid Tahvili, Sahar Felderer, Michael Sandahl, Kristian Business Unit Networks Standards and Technology Software Computer Science Ericsson AB Stockholm Sweden School of EEECS Queen's University Belfast Bahar Software Engineering Consulting Corporation Belfast United Kingdom Group Function Technology Global AI Accelerator Ericsson AB Stockholm Sweden Dept. of Computer Science University of Insbruck Innsbrück Austria Dept. of Computer and Information Science Linköping University Linköping Sweden

来源：评论

学校读者我要写书评

暂无评论

SecMeanshift: FSS-based privacy-preserving mean-shift clustering

引用

Information Sciences 2025年 719卷

作者： Min Ma Yu Fu Fei Zheng Zhihong Zhang Taotao Liu Kai Huang Dept. of Information Security Naval University of Engineering Wuhan China College of Software Engineering Hubei Open University Wuhan China College of Computer Science Zhejiang University Hangzhou China College of Joint Operation National Defense University Shijiazhuang China

Clustering is an unsupervised learning method that groups data based on similar characteristics. They have broad applications in various fields, such as image processing, text clustering, and recommendation systems. However, in practical scenarios, clustering often involves sensitive data from multiple data owners, which raises significant privacy concerns. Therefore, addressing the challenge of performing efficient clustering while preserving data privacy is critical. Existing privacy-preserving clustering methods often encounter challenges such as high computational overhead or reliance on auxiliary information. Consequently, we propose SecMeanshift, a privacy-preserving mean-shift framework based on function secret sharing. SecMeanshift leverages an offline–online paradigm to enhance efficiency by offloading some operations to the offline phase. We design basic protocols, including secure negative exponential, secure select, and secure sampling for the proposed framework, and design private protocols for each phase of the mean-shift. Theoretical analysis confirms the security and correctness of the proposed protocols. Furthermore, extensive experiments on diverse datasets demonstrate that SecMeanshift achieves significantly higher efficiency than HE-Meanshift, making it a promising solution for privacy-preserving clustering.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ThunderGBM: fast GBDTs and random forests on GPUs

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2020年第1期21卷 4389-4393页

作者： Zeyi Wen Hanfeng Liu Jiashuai Shi Qinbin Li Bingsheng He Jian Chen Dept. of Computer Science and Software Engineering Uni. of Western Australia Australia School of Computing National University of Singapore Singapore School of Software Engineering South China University of Technology Guangzhou China

Gradient Boosting Decision Trees (GBDTs) and Random Forests (RFs) have been used in many real-world applications. They are often a standard recipe for building state-of-the-art solutions to machine learning and data mining problems. However, training and prediction are very expensive computationally for large and high dimensional problems. This article presents an efficient and open source software toolkit called ThunderGBM which exploits the high-performance Graphics Processing Units (GPUs) for GBDTs and RFs. ThunderGBM supports classification, regression and ranking, and can run on single or multiple GPUs of a machine. Our experimental results show that ThunderGBM outperforms the existing libraries while producing similar models, and can handle high dimensional problems where existing GPU-based libraries fail. Documentation, examples, and more details about ThunderGBM are available at https://***/xtra-computing/thundergbm.

关键词： gradient boosting decision trees random forests GPUs efficiency

来源：评论

学校读者我要写书评

暂无评论

On the development of a web extension for text authentication on Google Chrome 2

On the development of a web extension for text authenticatio...

引用

2nd International Conference on Electrical, computer and Communication engineering, ECCE 2019

作者： Kabir, Muhammad Nomani Tayan, Omar Alginahi, Yasser Hasan, Md Munirul Rahman, Md Arafatur Faculty of Computer Systems Software Engineering University Malaysia Pahang Kuantan Pahang Malaysia Dept. of Computer Engineering NOOR Research Center College of Computer Science and Engineering Taibah University Madinah Saudi Arabia Dept. of Electrical and Computer Engineering University of Windsor Windsor Canada

ISBN: (纸本)9781538691113

Web extension is a software that can be installed on a web browser. A web-extension link is displayed as an icon on the toolbar of the browser. Based on browsing activity, the extension works automatically or by clicking the extension icon depending on the functionalities made in the extension software. In this work, we developed a web extension on Google Chrome browser to verify online texts by simply clicking on an extension button. Upon clicking the button, the underlying algorithm in the extension software retrieves the texts from the current web-page being displayed. Verification and authentication of texts are performed by comparing the retrieved texts with text database. According to the comparison, texts are highlighted in colors. We consider authentication of Arabic Hadith texts for a case study. The authentic Hadith texts are highlighted by green color;authentic texts with partial diacritics, by yellow;and unauthentic texts, by red. This technique can also be used to authenticate laws, constitutions and Government documents in any language. © 2019 IEEE.

关键词： Authentication

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 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

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：