检索结果-内蒙古大学图书馆

SSRN 2023年

作者： Sadeghi, Zahra Alizadehsani, Roohallah Cifci, Mehmet Akif Kausar, Samina Rehman, Rizwan Mahanta, Priyakshi Bora, Pranjal Kumar Almasri, Ammar Alkhawaldeh, Rami S. Hussain, Sadiq Alatas, Bilal Shoeibi, Afshin Moosaei, Hossein Hladík, Milan Nahavandi, Saeid Pardalo, Panos M. Institute for Big Data Analytics Faculty of Computer Science Dalhousie University Canada Deakin University Geelong Australia The Institute of Computer Technology Tu Wien University Vienna1040 Austria University of Kotli Azad Jammu and Kashmir Azad Kashmir Kotli Pakistan Centre for Computer Science and Applications Dibrugarh University Assam India Department of Management Information Sys Al-Balqa Applied University Salt19117 Jordan Department of Computer Information Systems The University of Jordan Aqaba77110 Jordan Examination Branch Dibrugarh University Assam Dibrugarh India Department of Software Eng. Firat University Elazig23100 Turkey Data Science and Computational Intelligence Institute University of Granada Spain Department of Informatics Faculty of Science Jan Evangelista Purkyně University in Ústí nad Labem Czech Republic Department of Applied Mathematics School of Computer Science Faculty of Mathematics and Physics Charles University Prague Czech Republic Harvard Paulson School of Engineering and Applied Sciences Harvard University AllstonMA02134 United States Swinburne University of Technology HawthornVIC3122 Australia Center for Applied Optimization Department of Industrial and Systems Engineering University of Florida Gainesville32611 United States

XAI refers to the techniques and methods for building AI applications which assist end users to interpret output and predictions of AI models. Black box AI applications in high-stakes decision-making situations, such as medical domain have increased the demand for transparency and explainability since wrong predictions may have severe consequences. Model explainability and interpretability are vital successful deployment of AI models in healthcare practices. AI applications' underlying reasoning needs to be transparent to clinicians in order to gain their trust. This paper presents a systematic review of XAI aspects and challenges in the healthcare domain. The primary goals of this study are to review various XAI methods, their challenges, and related machine learning models in healthcare. The methods are discussed under six categories: Features-oriented methods, global methods, concept models, surrogate models, local pixel-based methods, and human-centric methods. Most importantly, the paper explores XAI role in healthcare problems to clarify its necessity in safety-critical applications. The paper intends to establish a comprehensive understanding of XAI-related applications in the healthcare field by reviewing the related experimental results. To facilitate future research for filling research gaps, the importance of XAI models from different viewpoints and their limitations are investigated. © 2023, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence to Detect Image Spam Using Convolutional Neural Network

arXiv

引用

arXiv 2022年

作者： Zhang, Zhibo Damiani, Ernesto Hamadi, Hussam Al Yeun, Chan Yeob Taher, Fatma C2PS Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi United Arab Emirates Department of Computing and Applied Technology Zayed University Dubai United Arab Emirates

Image spam threat detection has continually been a popular area of research with the internet's phenomenal expansion. This research presents an explainable framework for detecting spam images using Convolutional Neural Network (CNN) algorithms and Explainable Artificial Intelligence (XAI) algorithms. In this work, we use CNN model to classify image spam respectively whereas the post-hoc XAI methods including Local Interpretable Model Agnostic Explanation (LIME) and Shapley Additive Explanations (SHAP) were deployed to provide explanations for the decisions that the black-box CNN models made about spam image detection. We train and then evaluate the performance of the proposed approach on a 6636 image dataset including spam images and normal images collected from three different publicly available email corpora. The experimental results show that the proposed framework achieved satisfactory detection results in terms of different performance metrics whereas the model-independent XAI algorithms could provide explanations for the decisions of different models which could be utilized for comparison for the future study. © 2022, CC BY.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

engineering the directionality of hot carrier tunneling in plasmonic tunneling structures

arXiv

引用

arXiv 2023年

作者： Abbasi, Mahdiyeh Liao, Shusen Zhu, Yunxuan Natelson, Douglas Department of Electrical and Computer Engineering Rice University HoustonTX77005 United States Applied Physics Graduate Program Smalley-Curl Institute Rice University HoustonTX77005 United States Department of Physics and Astronomy Engineering Rice University HoustonTX77005 United States Department of Materials Science and Nanoengineering Rice University HoustonTX77005 United States

Tunneling metal-insulator-metal (MIM) junctions can exhibit an open-circuit photovoltage (OCPV) response under illumination that may be useful for photodetection. One mechanism for photovoltage generation is hot carrier tunneling, in which photoexcited carriers generate a net photocurrent that must be balanced by a drift current in the open-circuit configuration. We present experiments in electromigrated planar MIM structures, designed with asymmetric plasmonic properties using Au and Pt electrodes. Decay of optically excited local plasmonic modes preferentially creates hot carriers on the Au side of the junction, leading to a clear preferred directionality of the hot electron photocurrent and hence a preferred polarity of the resulting OCPV. In contrast, in an ensemble of symmetric devices constructed from only one Au, polarity of the OCPV has no preferred direction. Copyright © 2023, The Authors. All rights reserved.

关键词： Plasmonics

来源：评论

学校读者我要写书评

暂无评论

Studying Risks of Hybrid Reengineering on Air-Transportation Systems Management “A Case Study on Jordanian Civil Aviation Regulatory Commission (CARC)”

Studying Risks of Hybrid Reengineering on Air-Transportation...

引用

Information Technology (ACIT)

作者： Al Refai Mohammed N. Taani M.K. K. Ahmed Ali Otoom Ghassan Samara Hanandeh E. S Hayel Khafajeh Software Engineering Dep. Zarqa University Zarqa Jordan Cybersecurity and Cloud Computing Dep. Applied Science Private University Amman Jordan Department of Computer Science Zarqa University Zarqa Jordan Artificial Intelligence Dep. Zarqa University Zarqa Jordan

This study examines decision-making in software re-engineering within businesses, focusing on the challenges and considerations involved. Financial constraints, time, and staff efforts are critical factors in these decisions. The study identifies difficulties faced by top-level management with legacy systems, existing systems, underused systems, and packaged software due to user resistance and customer dissatisfaction. The primary goal of the study is to assess the importance of software quality factors, especially from the users' perspective, in making re-engineering decisions. It uses the ISO 9126 Model to analyze quality elements in the case study software, aiming to provide guidance for deciding whether to proceed with re-engineering. The study explores functionality, reliability, usability, efficiency, maintainability, and portability as factors influencing re-engineering decisions, based on the ISO 9126 model. To understand user interactions and program performance, the study used unstructured participant observation in the case study software, highlighting the challenges faced by top management due to user resistance. These findings were further confirmed through face-to-face interviews with software users and department employees, offering insights into their perspectives on software quality elements. The results reveal that, despite some flaws, the system has valuable features and capabilities. Most employees express a desire to undergo re-engineering to enhance service quality, align with ISO 9126 standards, and leverage the expertise of competent staff for re-engineering activities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AI

arXiv

引用

arXiv 2024年

作者： Papamarkou, Theodore Skoularidou, Maria Palla, Konstantina Aitchison, Laurence Arbel, Julyan Dunson, David Filippone, Maurizio Fortuin, Vincent Hennig, Philipp Hernández-Lobato, José Miguel Hubin, Aliaksandr Immer, Alexander Karaletsos, Theofanis Khan, Mohammad Emtiyaz Kristiadi, Agustinus Li, Yingzhen Mandt, Stephan Nemeth, Christopher Osborne, Michael A. Rudner, Tim G.J. Rügamer, David Teh, Yee Whye Welling, Max Wilson, Andrew Gordon Zhang, Ruqi Department of Mathematics The University of Manchester Manchester United Kingdom Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge United States Spotify London United Kingdom Computational Neuroscience Unit University of Bristol Bristol United Kingdom Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University United States Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany Department of Computer Science Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge United Kingdom Department of Mathematics University of Oslo Oslo Norway Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative CA United States Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London United Kingdom Department of Computer Science UC Irvine Irvine United States Department of Mathematics and Statistics Lancaster University Lancaster United Kingdom Department of Engineering Science University of Oxford Oxford United Kingdom Center for Data Science New York University New York United States Department of Statistics LMU Munich Munich Germany DeepMind London United Kingdom Department of Statistics University of Oxford Oxford United Kingdom Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences Center for Data Science Computer Science Department New York University New York United States Department of Computer Science Purdue University West Lafayette United States

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential. © 2024, CC BY-NC-ND.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Automatic near real-time quality control tests for biofouling effect on measurement data

Automatic near real-time quality control tests for biofoulin...

引用

OCEANS

作者： Astrid Marie Skålvik Anders Tengberg Kjell-Eivind Frøysa Ranveig N. Bjørk Camilla Saetre Department of Physics and Technology University of Bergen Bergen Norway Aanderaa Data Instruments AS Bergen Norway Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences/NORCE Norwegian Research Centre Bergen Norway NORCE Norwegian Research Centre Bergen Norway

The reliability of water quality measurement is crucial for sustainable use of ocean resources, climate and ecosystem models, and industrial applications. However, measurement stations in remote locations face limitations in terms of power, communication, and maintenance, posing challenges for data quality. Even though some basic (near) real-time automatic tests are proposed in oceanographic measurement guidelines, time- and resource consuming Delayed Mode Quality Control is still required before using measurement data in forecasting, models, or decision-making. To design effective quality control tests for more autonomous sensors with self-validating capabilities in real-time, a good understanding of expected environmental effects or errors on sensor signals is *** paper focuses on the effect of biofouling on the measurement of selected water quality parameters such as conductivity, oxygen, and turbidity. Biofouling remains a major issue despite research on biofouling protection and anti-biofouling sensor design. Biofouling growth on underwater sensors can increase measurement errors and uncertainty, result in shorter operation times, and require costly manual work related to retrieval, cleaning, and re-deployment. For some measurement technologies, biofouling can result in noise, while for others, it may cause systematic drift or delay signal ***, we propose quality control tests designed to automatically detect and assess the impact of biofouling on sensor signals. These tests are applied to measurement data sets with a known presence of biofouling from Austevoll (Norway). We comment on the challenges of designing tests and setting adequate *** show that a detailed understanding of biofouling effect on sensors is crucial for designing effective near real-time quality control procedures. Automatic, in-situ tests can save costs related to manual data quality control and increase data quality, thereby enabling well-informed decisions i

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Complexity of the Storyplan Problem

arXiv

引用

arXiv 2022年

作者： Binucci, Carla Di Giacomo, Emilio Lenhart, William J. Liotta, Giuseppe Montecchiani, Fabrizio Nöllenburg, Martin Symvonis, Antonios Department of Engineering University of Perugia Italy Department of Computer Science Williams College United States Algorithms and Complexity Group Tu Wien Vienna Austria School of Applied Mathematical & Physical Sciences Ntua Greece

Motivated by dynamic graph visualization, we study the problem of representing a graph G in the form of a storyplan, that is, a sequence of frames with the following properties. Each frame is a planar drawing of the subgraph of G induced by a suitably defined subset of its vertices. Between two consecutive frames, a new vertex appears while some other vertices may disappear, namely those whose incident edges have already been drawn in at least one frame. In a storyplan, each vertex appears and disappears exactly once. For a vertex (edge) visible in a sequence of consecutive frames, the point (curve) representing it does not change throughout the sequence. Note that the order in which the vertices of G appear in the sequence of frames is a total order. In the StoryPlan problem, we are given a graph and we want to decide whether there exists a total order of its vertices for which a storyplan exists. We prove that the problem is NP-complete, and complement this hardness with two parameterized algorithms, one in the vertex cover number and one in the feedback edge set number of G. Also, we prove that partial 3-trees always admit a storyplan, which can be computed in linear time. Finally, we show that the problem remains NP-complete in the case in which the total order of the vertices is given as part of the input and we have to choose how to draw the frames. © 2022, CC BY.

关键词： Hardness

来源：评论

学校读者我要写书评

暂无评论

A Robust KPI Framework for Smart Energy Systems of Different Scales

A Robust KPI Framework for Smart Energy Systems of Different...

引用

IEEE International Symposium on Industrial Electronics (ISIE)

作者： Nikolaos Efkarpidis Martin Geidl Chen-Wei Yang Andrija Goranović Stefan Wilker Thilo Sauter Ingo Herbst Institute of Electric Power Systems University of Applied Sciences and Arts Northwestern Switzerland Windisch Switzerland Department of Computer Science Electrical and Space Engineering Lule&#x00E5 University of Technology TU Wien Institute of Computer Technology Department of Smart Infrastructure Siemens Switzerland

ISBN: (数字)9781665482400

ISBN: (纸本)9781665482417

Nowadays, an increasing focus is placed on the development of smart energy systems (SESs) that combine a variety of heterogeneous sub-systems with largely varying applications. Due to their multidisciplinary nature, there are no universally accepted standards assessing their performance. Previous efforts typically define Key Performance Indicators (KPIs) only for specific SES types and application areas. This paper presents a robust KPI framework that can be applied to any SES type regardless of the application area. The proposed framework consists of four layers following the top-down approach. The layers define the application area, SES requirements, main stakeholders involved specifying their objectives and finally, the KPIs for each of the stakeholders' objectives. The proposed KPI framework is applied on the use cases of a European research project with different application areas showing its features.

关键词： Industrial electronics Key performance indicator Europe Stakeholders Standards

来源：评论

学校读者我要写书评

暂无评论

Explainable Artificial Intelligence to Detect Image Spam Using Convolutional Neural Network

Explainable Artificial Intelligence to Detect Image Spam Usi...

引用

Cyber Resilience (ICCR), International Conference on

作者： Zhibo Zhang Ernesto Damiani Hussam Al Hamadi Chan Yeob Yeun Fatma Taher Department of Electrical Engineering and Computer Science C2PS Khalifa University Abu Dhabi United Arab Emirates Department of Computing and Applied Technology Zayed University Dubai United Arab Emirates

ISBN: (数字)9781665461221

ISBN: (纸本)9781665461238

Image spam threat detection has continually been a popular area of research with the internet's phenomenal expansion. This research presents an explainable framework for detecting spam images using Convolutional N eural Network (CNN) algorithms and Explainable Artificial Intelligence (XAI) algorithms. In this work, we use CNN model to classify image spam respectively whereas the post-hoc XAI methods including Local Interpretable Model Agnostic Explanation (LIME) and Shapley Additive Explanations (SHAP) were deployed to provide explanations for the decisions that the black-box CNN models made about spam image detection. We train and then evaluate the performance of the proposed approach on a 6636 image dataset including spam images and normal images collected from three different publicly available email corpora. The experimental results show that the proposed framework achieved satisfactory detection results in terms of different performance metrics whereas the model-independent XAI algorithms could provide explanations for the decisions of different models which could be utilized for comparison for the future study.

关键词： Measurement Additives Unsolicited e-mail Closed box Classification algorithms Convolutional neural networks Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

An electrical model characterization of an electronic nose chemical sensor using a programmable system-on-a-chip based AFE

An electrical model characterization of an electronic nose c...

引用

2022 International Young Engineers Forum in Electrical and computer engineering, YEF-ECE 2022

作者： Santos, Joao J.M. Palma, Susana I.C.J. Esteves, Carina Gamboa, Hugo Oliveira, Joao Pedro Roque, Ana C.A. Department of Electrical and Computer Engineering Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal Associate Laboratory i4HB Institute for Health and Bioeconomy Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal Ucibio Applied Molecular Biosciences Unit Department of Chemistry Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal LIBPhys - Laboratory for Instrumentation Biomedical Engineering and Radiation Physics Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal Uninova Nova School of Science and Technology Nova University of Lisbon Caparica2829-516 Portugal

ISBN: (纸本)9781665467315

The diagnosis of many diseases involves invasive detection methods, which are both painful and stressing for patients. In the last decades, the ever-growing development in electronic nose (E-Nose) technology made them great candidates for non-invasive disease detection methods. Such devices mimic the human olfactory system through a set of sensors which produce signals that can be associated with diseases. Recently, a class of low-cost and innovative ionogel sensors, developed by our group demonstrated their full applicability in E-Nose systems, opening a new and promising approach to the field. However, the operation of such sensor needs a background calibration phase which relies on the correct characterization and parameterization of the corresponding electrical sensor *** paper proposes a model characterization methodology based on a set of frequency responses acquisitions of the sensor, under several humidity conditions. To obtain a flexible acquisition tool capable of acquiring accurate results, an analog front-end (AFE) circuit to interface with the interdigitated electrode (IDE) sensors is presented. Such AFE circuit is fully implemented using a programmable system-on-a-chip (PSoC), helping to reduce system size and cost. Lastly, a comparison between the electrical model and data acquired with the proposed system is presented. © 2022 IEEE.

关键词： System-on-chip

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：