检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Allagui, Anis Zhang, Di Elwakil, Ahmed Dept. of Sustainable and Renewable Energy Engineering University of Sharjah United Arab Emirates Dept. of Mechanical and Materials Engineering Florida International University MiamiFL33174 United States Dept. of Electrical Engineering and Computer Science Khalifa University United Arab Emirates Dept. of Electrical and Software Engineering University of Calgary Alberta Canada

This study provides new sets of experimental results supporting Westerlund's conjecture that Dead Matter Has Memory [1]. Memory effects in the dynamic response of electric double-layer capacitors (EDLCs) that integrate its prior history of stimulation and state have been experimentally observed and reported in a few recent studies. The different excitation signals used to quantify such effects in these studies aimed at charging a device to the same voltage value and the exact same accumulated charge level but in different manners. Having reached the same unique voltage-charge point, it was observed that different yet repeatable discharge patterns occur, proving the existence of memory. The aim of this work is to provide further experimental evidence of the inherent memory effect in EDLCs in response to time-varying stationary input excitations with different statistical properties. In particular, different sets of charging voltage waveforms composed of fixed dc values with superimposed uniformly-distributed random fluctuations of different amplitudes were created and used to charge the same EDLC device to a unique voltage-charge point. The duration of these signals was the same but with different values of variance around the mean value. We observed different time-charge responses depending on the extent of the noise level in these charging waveforms. This is interpreted and discussed in the context of inherent memory using fractional-order voltage-charge equations of non-ideal capacitors. © 2022, CC BY.

关键词： Supercapacitor

来源：评论

学校读者我要写书评

暂无评论

Multi-label Classification of Commit Messages using Transfer Learning 31

Multi-label Classification of Commit Messages using Transfer...

引用

31st IEEE International Symposium on software Reliability engineering Workshops, ISSREW 2020

作者： Sarwar, Muhammad Usman Zafar, Sarim Mkaouer, Mohamed Wiem Walia, Gursimran Singh Malik, Muhammad Zubair North Dakota State University Dept. of Computer Science Fargo United States Rochester Institute of Technology Dept. of Software Engineering Rochester United States Georgia Southern University Dept. of Computer Science Georgia United States

ISBN: (纸本)9781728198705

Commit messages are used in the industry by developers to annotate changes made to the code. Accurate classification of these messages can help monitor the software evolution process and enable better tracking for various industrial stakeholders. In this paper, we present a state of the art method for commit message classification into categories as per Swanson's maintenance activities i.e. 'Corrective', 'Perfective', and 'Adaptive'. This is a challenging task because not all commit messages are well written and informative. Existing approaches rely on keyword-based techniques to solve this problem. However, these approaches are oblivious to the full language model and do not recognize the contextual relationship between words. State of the art methodology in Natural Language Processing (NLP), is to train a context-aware neural network (Transformer) on a very large data set that encompasses the entire language and then fine-tunes it for a specific task. In this way, the model can learn the language, pay attention to the context, and then transfer that knowledge for better performance at the specific task. We use an off-the-shelf neural network called DistilBERT and fine-tune it for commit message classification task. This step is non-trivial because programming languages and commit messages have unique keywords, jargon, and idioms. This paper presents our effort in training this model and constructing the data set for this task. We describe the rules used to construct the data set. We validate our approach on industrial projects from GitHub, such as Kubernetes, Linux, TensorFlow, Spark, TypeScript, and PyTorch. We were able to achieve 87% F1-score for the commit message classification task, which is an order of magnitude accurate than previous studies. © 2020 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

AGMI: Attention-Guided Multi-omics Integration for Drug Response Prediction with Graph Neural Networks

AGMI: Attention-Guided Multi-omics Integration for Drug Resp...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Feng, Ruiwei Xie, Yufeng Lai, Minshan Chen, Danny Z. Cao, Ji Wu, Jian Zhejiang University Coll. of Computer Science and Technology Hangzhou China Zhejiang University School of Software Technology Hangzhou China Zhejiang University Polytechnic Institute Hangzhou China University of Notre Dame Dept. of Computer Science and Engineering Notre Dame United States Zhejiang University Coll. of Pharmaceutical Sciences Hangzhou China Zhejiang University School of Public Health Hangzhou China

ISBN: (纸本)9781665401265

Accurate drug response prediction (DRP) is a crucial yet challenging task in precision medicine. This paper presents a novel Attention-Guided Multi-omics Integration (AGMI) approach for DRP, which first constructs a Multiedge Graph (MeG) for each cell line, and then aggregates multi-omics features to predict drug response using a novel structure, called Graph edge-aware Network (GeNet). For the first time, our AGMI approach explores gene constraint based multi-omics integration for DRP with the whole-genome using GNNs. Empirical experiments on the CCLE and GDSC datasets show that our AGMI largely outperforms state-of-the-art DRP methods by 8.3%-34.2% on four metrics. Our data and code are available at https://***/yivan-WYYGDSG/AGMI. © 2021 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Information Leakage from Optical Emanations

arXiv

引用

arXiv 2023年

作者： Loughry, Joe Umphress, David A. Lockheed Martin Space Systems Dept. 3740 Mail Stop X3741 P.O. Box 179 DenverCO80201 United States Auburn University Department of Computer Science and Software Engineering 215 Dunstan Hall AL36849 United States

A previously unknown form of compromising emanations has been discovered. LED status indicators on data communication equipment, under certain conditions, are shown to carry a modulated optical signal that is significantly correlated with information being processed by the device. Physical access is not required;the attacker gains access to all data going through the device, including plaintext in the case of data encryption systems. Experiments show that it is possible to intercept data under realistic conditions at a considerable distance. Many different sorts of devices, including modems and Internet Protocol routers, were found to be vulnerable. A taxonomy of compromising optical emanations is developed, and design changes are described that will successfully block this kind of "Optical Tempest" attack. Categories and Subject Descriptors: C.2.0 [computer Systems Organization]: computer-COMMUNICATION NETWORKS—General, Security and protection (e.g., firewalls);D.4.6 [software]: OPERATING SYSTEMS—Security and Protection, Invasive software (e.g., viruses, worms, Trojan horses);E.3 [Data]: DATA ENCRYPTION—Code breaking;K.6.5 [Computing Milieux]: MANAGEMENT OF COMPUTING AND INFORMATION SYSTEMS—Security and Protection, Unauthorized Access (e.g., hacking, phreaking) Copyright © 2023, The Authors. All rights reserved.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

TIMBERT: Toponym Identifier For The Medical Domain Based on BERT 28

TIMBERT: Toponym Identifier For The Medical Domain Based on ...

引用

28th International Conference on Computational Linguistics, COLING 2020

作者： Davari, MohammadReza Kosseim, Leila Bui, Tien D. Dept. Computer Science and Software Engineering Concordia University MontrealQCH3G 1M8 Canada

ISBN: (纸本)9781952148279

In this paper, we propose an approach to automate the process of place name detection in the medical domain to enable epidemiologists to better study and model the spread of viruses. We created a family of Toponym Identification Models based on BERT (TIMBERT), in order to learn in an end-to-end fashion the mapping from an input sentence to the associated sentence labeled with toponyms. When evaluated with the SemEval 2019 task 12 test set (Weissenbacher et al., 2019), our best TIMBERT model achieves an F1 score of 90.85%, a significant improvement compared to the state-of-the-art of 89.13% (Wang et al., 2019). © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

How much data analytics is enough? The ROI of machine learning classification and its application to requirements dependency classification

arXiv

引用

arXiv 2021年

作者： Deshpande, Gouri Ginde Ruhe, Guenther Saunders, Chad Dept. Computer Science University of Calgary Dept. Electrical and Software Engineering University of Calgary Haskayne School of Business University of Calgary

Machine Learning (ML) can substantially improve the efficiency and effectiveness of organizations and is widely used for different purposes within software engineering. However, the selection and implementation of ML techniques rely almost exclusively on accuracy criteria. Thus, for organizations wishing to realize the benefits of ML investments, this narrow approach ignores crucial considerations around the anticipated costs of the ML activities across the ML life-cycle, while failing to account for the benefits that are likely to accrue from the proposed activity. We present findings for an approach that addresses this gap by enhancing the accuracy criterion with return on investment (ROI) considerations. Specifically, we analyze the performance of the two state-of-the-art ML techniques: Random Forest and Bidirectional Encoder Representations from Transformers (BERT), based on accuracy and ROI for two publicly available data sets. Specifically, we compare decision-making on requirements dependency extraction (i) exclusively based on accuracy and (ii) extended to include ROI analysis. As a result, we propose recommendations for selecting ML classification techniques based on the degree of training data used. Our findings indicate that considering ROI as additional criteria can drastically influence ML selection when compared to decisions based on accuracy as the sole criterion. © 2021, CC BY.

关键词： Data Analytics

来源：评论

学校读者我要写书评

暂无评论

Innovative Poverty Estimation through Machine Learning Approaches

Innovative Poverty Estimation through Machine Learning Appro...

引用

International Conference on Emerging Technologies, ICET

作者： Ahmad Mashhood Zain ul Abideen Usama Arshad Raja Hashim Ali Ammad Aslam Khan Bahram Khan Faculty of Computer Science & Engineering GIK Institute of Engg. Sciences & Technology Topi Pakistan BCMaterials Basque Center for Materials Applications & Nanostructure Leioa Basque Country Spain Dept. of Technology & Software Engineering University of Europe for Applied Sciences Berlin Germany Dept. of Biological Sciences M.A. Road Satellite Town Virtual University of Pakistan Rawalpindi Pakistan

This paper delves into the application and capabilities of machine learning methodologies in forecasting poverty scenarios, underlining the importance of varied data sources, along with the interpretability and explainability of models to refine the precision and transparency of poverty prediction mechanisms. It primarily utilizes an iteration of the LightGBM algorithm to infer poverty stages premised on household variables. This investigation showcases the potential of machine learning methodologies in poverty estimation, elucidating the relevance of additional, diverse data resources, and the critical role of model interpretability in enhancing model accuracy and clarity. The LightGBM version employed in our study demonstrated high efficiency on the validation set, affirming its effectiveness in projecting poverty conditions based on household features. In analyzing SHAP values, we unearthed crucial insights into the contributing elements to poverty. These findings can aid in shaping policies aimed at poverty alleviation and elevating social welfare. Our work provides the basis for future research into poverty prediction and affirms the potential of machine learning methodologies in tackling intricate social challenges.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Class Clinical Text Annotation and Classification Using Bert-Based Active Learning

SSRN

引用

SSRN 2022年

作者： Afzal, Muhammad Hussain, Jamil Abbas, Asim Hussain, Maqbool Dept. of Software Sejong University Seoul05006 Korea Republic of Dept. of Data Science Sejong University Seoul05006 Korea Republic of Dept. of Computer Science ST. JHON’S University United States School of Computing and Engineering University of Derby United Kingdom

Data-driven approaches require labeled data for autonomous decision-making, but medical data is recorded in structured and unstructured form mostly with no label specified. Manual labeling is an arduous task, and variations in the notes at different levels, including section, sentence, and terms, add to the challenge. Creating well-structured and accurate data to use as a training dataset for a machine learning (ML) model increases the chance of getting meaningful results from the ML models. This paper proposes a multi-class annotation and classification framework that uses four classes: subjective, objective, assessment, and plan, adopted from a well-known medical protocol called SOAP. The SOAP classes capture a clinical context and help reduce misinterpretations when a concept of a similar type is used in different sections of the same clinical document. To illustrate the effectiveness of the proposed methodology, we conduct a set of experiments on clinical notes acquired from a public dataset (i2b2). We observe that our proposed model has eased the onerous job of annotation and achieved a better performance than competitors. The encouraging results of this research demonstrate the potential of combining active learning, transfer learning, and deep learning for automatic annotation to get accurate text classification. © 2022, The Authors. All rights reserved.

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Combating Deepfakes: Multi-LSTM and Blockchain as Proof of Authenticity for Digital Media

Combating Deepfakes: Multi-LSTM and Blockchain as Proof of A...

引用

2020 IEEE / ITU International Conference on Artificial Intelligence for Good, AI4G 2020

作者： Ki Chan, Christopher Chun Kumar, Vimal Delaney, Steven Gochoo, Munkhjargal Chaoyang University of Technology Dept. of Information Management Taichung Taiwan Ryerson University and Capital Blockchain Inc. Dept. of Computer Science Toronto Canada Dept. of Computer Science and Software Engineering Al Ain United Arab Emirates

ISBN: (纸本)9781728170312

Malicious use of deep learning algorithms has allowed the proliferation of high realism fake digital content such as text, images, and videos, to exist on the internet as readily available and accessible consumable content. False information provided through algorithmically modified footage, images, audios, and videos (known as deepfakes), coupled with the virality of social networks, may cause major social unrest. The emergence of misinformation from fabricated digital content suggests the necessity for anti-disinformation methods such as deepfake detection algorithms or immutable metadata in order to verify the validity of digital content. Permissioned blockchain, notably Hyperledger Fabric 2.0, coupled with LSTMs for audio/video/descriptive captioning is a step towards providing a feasible tool for combating deepfake media. Original content would require the original artist attestation of untampered data. The smart contract combines a varied multiple LSTM networks into a process that allows for the tracing and tracking of a digital content's historical provenance. The result is a theoretical framework that enables proof of authenticity (PoA) for digital media using a decentralized blockchain using multiple LSTMs as a deep encoder for creating unique discriminative features;which is then compressed and hashed into a transaction. Our work assumes we trust the video at the point of reception. Our contribution is a decentralized blockchain framework of deep discriminative digital media to combat deepfakes. © 2020 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Evaluation of Android ICC Resolution Techniques

arXiv

引用

arXiv 2021年

作者： Yan, Jiwei Zhang, Shixin Liu, Yepang Deng, Xi Yan, Jun Zhang, Jian Tech. Center of Software Engineering Institute of Software CAS China Univ. of Chinese Academy of Sciences Beijing China School of Software Engineering Beijing Jiaotong University Beijing China Dept. of Computer Science and Engr. Southern University of Sci. and Tech Shenzhen China State Key Lab. of Computer Science Institute of Software CAS China

Inter-component communication (ICC) is a widely used mechanism in mobile apps, which enables message-based control flow transferring and data passing between Android components. Effective ICC resolution requires precisely identifying entry points, analyzing data values of ICC fields, modeling related framework APIs, etc. Due to various control-flow- and data-flow-related characteristics involved and the lack of oracles for real-world apps, the comprehensive evaluation of ICC resolution techniques is challenging. To fill this gap, we collect multiple-type benchmark suites with 4,104 apps, covering hand-made apps, open-source, and commercial ones. Considering their differences, various evaluation metrics, e.g., number count, graph structure, and reliable oracle based metrics, are adopted on-demand. As the oracle for real-world apps is unavailable, we design a dynamic analysis approach to extract the real ICC links triggered during GUI exploration. By auditing the code implementations, we carefully check the extracted ICCs and confirm 1,680 ones to form a reliable oracle set, in which each ICC is labeled with 25 code characteristic tags. The evaluation performed on six state-of-the-art ICC resolution tools shows that 1) the completeness of static ICC resolution results on real-world apps is not satisfactory, as up to 38%-85% ICCs are missed by tools;2) many wrongly reported ICCs are sent from or received by only a few components and the graph structure information can help the identification;3) the efficiency of fundamental tools, like ICC resolution ones, should be optimized in both engineering and research aspects. By investigating both the missed and wrongly reported ICCs, we discuss the strengths of different tools for users and summarize eight common FN/FP patterns in ICC resolution for tool developers. © 2021, CC BY-NC-SA.

关键词： Graphic methods

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：