检索结果-内蒙古大学图书馆

34th Australasian Conference on Information Systems, ACIS 2023

作者： Chen, Tianwa Demartini, Gianluca Indulska, Marta Sadiq, Shazia School of Electrical Engineering and Computer Science The University of Queensland Brisbane Australia Business School The University of Queensland Brisbane Australia

The rise of data re-purposing has resulted in an unprecedented opportunity to create new value from existing data assets. Unlike previous approaches that relied on well-understood data quality requirements, this open-ended setting demands a discovery-oriented approach. Despite a growing market of tools that assist with data exploration and profiling, data quality discovery continues to drain the time of data workers due to its cognitively demanding and contextual nature. Accordingly, we study data quality discovery through purpose-built experimental platforms that mimic typical data exploration platforms, and explore implicit sensemaking behaviours of data workers when required to write code or use available functions, by exploiting eye-tracking and log data. Our analysis of visual scanning and attention patterns reveals various sensemaking loops amongst data workers with different performance levels in different settings. Our findings provide insights for researchers and tool designers to consider how to support different data workers in data quality discovery. Copyright © 2023 Tianwa Chen, Gianluca Demartini, Marta Indulska, Shazia Sadiq.

关键词： Eye tracking

来源：评论

学校读者我要写书评

暂无评论

Breaking the Boundaries of Oncological Diagnosis: A Holistic Framework for Multi-Cancer Identification and Comprehensive Diagnostic Reporting Utilizing Advanced AI and NLP

Breaking the Boundaries of Oncological Diagnosis: A Holistic...

引用

2023 International Conference on Recent Advances in science and engineering Technology, ICRASET 2023

作者： Sai Santhosh, V.C. Ponraj, Riya Nikhil Eshwar, T. Kiran, K. Easwari Engineering College Computer Science and Engineering Department Chennai India Sri Krishna College of Technology Electrical and Electronics Engineering Department Coimbatore India

ISBN: (纸本)9798350306927

Innovative deep learning models for cancer classification, including VGG-19, DenseNet201, MobileNetV3, ResNet50V2, YOLOv5, and GPT-2, have completely changed the way that doctors diagnose cancer. This study introduces a multi-modal technique for an accurate and speedy cancer diagnosis. With the aid of cutting-edge technology, this system combines object identification (YOLOv5), natural language processing (GPT-2), and picture classification models (VGG-19, DenseNet201, MobileNetV3, ResNet50V2) to provide scientists and medical professionals with a flexible toolkit. It generates thorough reports with tumour images and spots malignant irregularities. Diagnostic accuracy is improved by real-time application, which benefits laboratories by reducing turnaround times and medical practitioners by providing an important decision support tool. Reports with tumour photos enhance the capacity to comprehend results. This study is important because it has the potential to improve cancer detection by using cutting-edge algorithms and models. This research also promises to improve patient care, prediction, and therapy. The practical method presented in this paper ushers in a new age in medical diagnostics by empowering laboratories and doctors. © 2023 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Feature selection strategy optimization for lithium-ion battery state of health estimation under impedance uncertainties

引用

Journal of Energy Chemistry 2025年第2期101卷 87-98,I0003页

作者： Xinghao Du Jinhao Meng Yassine Amirat Fei Gao Mohamed Benbouzid UMR CNRS 6027 IRDL University of BrestBrest 29238France School of Electrical Engineering xi'an Jiaotong UniversityXi'an 710049ShaanxiChina L@bISEN ISEN Yncrea OuestBrest 29200France Schoolof Energy and Computer Science University of Technology of Belfort-MontbeliardBelfort 90000France

Battery health evaluation and management are vital for the long-term reliability and optimal performance of lithium-ion batteries in electric *** impedance spectroscopy(EIS)offers valuable insights into battery degradation analysis and ***,previous studies have not adequately addressed the impedance uncertainties,particularly during battery operating conditions,which can substantially impact the robustness and accuracy of state of health(SOH)*** by this,this paper proposes a comprehensive feature optimization scheme that integrates impedance validity assessment with correlation *** utilizing metrics such as impedance residuals and correlation coefficients,the proposed method effectively filters out invalid and insignificant impedance data,thereby enhancing the reliability of the input ***,the extreme gradient boosting(XGBoost)modeling framework is constructed for estimating the battery degradation *** XGBoost model incorporates a diverse range of hyperparameters,optimized by a genetic algorithm to improve its adaptability and generalization *** validation confirms the effectiveness of the proposed feature optimization scheme,demonstrating the superior estimation performance of the proposed method in comparison with four baseline techniques.

关键词： Lithium-ion battery Stateof health Electrochemical impedance spectroscopy Extreme gradient boosting

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning Aided Malicious Network Traffic Detection Based on EDE Framework

Adversarial Learning Aided Malicious Network Traffic Detecti...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Zhang, Lanping Wang, Yu Ohtsuki, Tomoaki Adebisi, Bamidele Wu, Hsiao-Chun Gui, Guan Njupt College of Telecommunications and Information Engineering Nanjing China Keio University Department of Information and Computer Science Yokohama Japan Manchester Metropolitan University Faculty of Science and Engineering Manchester United Kingdom Louisiana State University School of Electrical Engineering and Computer Science United States

ISBN: (纸本)9798350345384

With the increasing number of new malicious software and network attacks, anomalous network traffic detection technology needs to continuously identify unknown attacks in order to adapt to complex network environments. In this paper, we propose a novel adversarial learning aided malicious network traffic detection (AMD) method based on encoder-decoder-encoder (EDE) framework. The proposed AMD method detects unknown anomalies in a single type of semi-supervised form and converts network traffic data into pictures for later processing. First, an anomalous network traffic detection model consisting of two encoders, a decoder and a discriminator is introduced. Second, by using the visibility of normal samples and the unrecognizability of unknown anomaly samples, the difference between the two samples is enlarged to facilitate effective sample detection. Finally, experiments show that the proposed model detects anomalies in targeted space and is robust to complex and noisy network environments. At the same time, compared to traditional machine learning methods, AMD's shows performance improvement of up to 40%. © 2023 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Vertical Interconnect Technology in Silicon, Package, and Printed Circuit Board (PCB) with Coaxial Structure

Vertical Interconnect Technology in Silicon, Package, and Pr...

引用

2024 IEEE International Symposium on Electromagnetic Compatibility, Signal and Power Integrity, EMC+SIPI 2024

作者： Park, Junyong Li, Chaofeng Mok, Eddie Dickson, Joe Tourne, Joan Kim, Donghyun Missouri University of Science and Technology Electrical and Computer Engineering RollaMO United States Co. Ltd Kunshan China NextGin Technology Netherlands

ISBN: (纸本)9798350360394

This paper introduces vertical interconnect technology in silicon, package, and printed circuit board (PCB) levels with a coaxial structure, respectively. The coaxial structure has been known to be advantageous in terms of signal integrity (SI) compared to the non-coaxial structure. The coaxial structure is easy to control the characteristic impedance Z0 and robust to crosstalk. The silicon-level interconnect includes the wire bonding (WB) and through-silicon via (TSV) technology, the package-level interconnect includes an elastomer package test socket. The PCB-level interconnect includes the vias, and vertical conductive structure (VeCS). For each level, the non-coaxial and coaxial interconnects are compared with the measurement results in the frequency domain. In conclusion, this paper successfully shows the improvement of the coaxial structure at silicon, package, and PCB levels. © 2024 IEEE.

关键词： Three dimensional integrated circuits

来源：评论

学校读者我要写书评

暂无评论

DECENTRALIZED VOLTAGE CONTROL IN ACTIVE DISTRIBUTION SYSTEMS COMBINING ON-LOAD TAP CHANGERS AND DEMAND RESPONSE 13

DECENTRALIZED VOLTAGE CONTROL IN ACTIVE DISTRIBUTION SYSTEMS...

引用

13th Mediterranean Conference on Power Generation, Transmission, Distribution and Energy Conversion, MEDPOWER 2022

作者： Nikolaidis, Vassilis C. Maropoulos, Michael Konstantinou, Charalambos Department of Electrical and Computer Engineering Democritus University of Thrace Xanthi Greece Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia

ISBN: (纸本)9781839538445

This paper presents a voltage control method for active distribution systems, which is based on the operation of on-load tap changers of the distribution transformers, in conjunction with a demand response program. Both on-load tap changers and demand response operations are initiated when pre-determined voltage criteria are fulfilled, making the approach completely decentralized. Several scenarios considering time-varying consumption of loads and variable electricity production from distributed generation units are simulated. The proposed voltage control method is tested against those scenarios, whereas also severe contingencies, such as the sudden loss of a distributed generation unit, are additionally considered. The simulation results show that the proposed method efficiently controls voltage within the permissible distribution levels, even under extreme system conditions. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Voltage control

来源：评论

学校读者我要写书评

暂无评论

Improved Design and Comparison of a Low Power CNTFET based on D Flip-Flop 3

Improved Design and Comparison of a Low Power CNTFET based o...

引用

3rd International Conference on electrical, computer and Communication engineering, ECCE 2023

作者： Ridoy, Jahid Hasan Rahman, Atik Yasir Saquib, Fahad Raihan Ahsanullah University of Science and Technology Department of Electrical & Electronic Engineering Dhaka Bangladesh The University of Tennessee Knoxville Department of Electrical Engineering and Computer Science KnoxvilleTN United States University of Scholars Department of Electrical and Electronic Engineering Dhaka Bangladesh

ISBN: (纸本)9798350345360

Carbon nanotube field effect transistors (CNTFETs) are auspicious nanoscale devices for realizing high performance with very thick and low power circuits. In this paper, different parameters of CNTFET from previous works have been studied and analyzed. Then, leakage current and leakage power of the proposed D flip-flop were compared with different reference circuits. The main goal is to improve, develop and design a CNTFET based D flip-flop. CNTFET's leakage current and leakage power consumption reduced drastically by decreasing diameter of CNT and number of CNT used in the CNTFET, which affected overall CNTFET's power consumption obviously. The proposed D flip-flop exhibited exquisite performance in case of leakage power consumption, having an average of 10.306 nW only, which is extremely low compared to the contemporary circuits. The chosen thickness of oxide and CNT's length for all the CNTFETs are 5 nm and 16 nm respectively. These CNTFETs are based on the results gathered from so that not only they can act as a D flip-flop correctly but also total power consumption of the device would be reduced as much as possible. © 2023 IEEE.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Towards Chipless RFID Based Temperature Sensing for IoT Applications

Towards Chipless RFID Based Temperature Sensing for IoT Appl...

引用

2023 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio science Meeting, AP-S/URSI 2023

作者： Rahman, Md Mirazur Mitra, Dipankar Dey, Shuvashis North Dakota State University Department of Electrical and Computer Engineering FargoND United States University of Wisconsin-La Crosse Department of Computer Science WI United States

ISBN: (纸本)9781665442282

This paper presents a novel technique to measure temperature by using a chipless RFID tag and smart material in view of loT application. The proposed technique incorporates a unique design of a chipless RFID resonator and a novel chipless technique for sensing temperature by combining ETFE fluroploymer with the resonator. The simulated material is placed on the top of the tag and dielectric parameters are varied. Initially, the original RCS response of the resonator is simulated which is then observed while varying the values of permittivity to obtain a correlation between different frequencies and dielectric constants. This correlation is further compared with the dielectric parameters of the material and the corresponding temperatures found from the literature. Finally, a calibration curve obtained where any temperature within the range can be measured by simply mapping the frequency of operation of the chipless resonator. © 2023 IEEE.

关键词： Resonators

来源：评论

学校读者我要写书评

暂无评论

RETHINKING SYMBOLIC REGRESSION: MORPHOLOGY AND ADAPTABILITY FOR EVOLUTIONARY ALGORITHMS 11

RETHINKING SYMBOLIC REGRESSION: MORPHOLOGY AND ADAPTABILITY ...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Fong, Kei Sen Wongso, Shelvia Motani, Mehul Department of Electrical and Computer Engineering National University of Singapore Singapore Institute of Data Science National University of Singapore Singapore

Symbolic Regression (SR) is the well-studied problem of finding closed-form analytical expressions that describe the relationship between variables in a measurement *** this paper, we rethink SR from two perspectives: morphology and ***: Current SR algorithms typically use several man-made heuristics to influence the morphology (or structure) of the expressions in the search *** man-made heuristics may introduce unintentional bias and data leakage, especially with the relatively few equation-recovery benchmark problems available for evaluating SR *** address this, we formulate a novel minimalistic approach, based on constructing a depth-aware mathematical language model trained on terminal walks of expression trees, as a replacement to these ***: Current SR algorithms tend to select expressions based on only a single fitness function (e.g., MSE on the training set).We promote the use of an adaptability framework in evolutionary SR which uses fitness functions that alternate across *** leads to robust expressions that perform well on the training set and are close to the true functional *** demonstrate this by alternating fitness functions that quantify faithfulness to values (via MSE) and empirical derivatives (via a novel theoretically justified fitness metric coined MSEDI).Proof-of-concept: We combine these ideas into a minimalistic evolutionary SR algorithm that outperforms a suite of benchmark and state of-the-art SR algorithms in problems with unknown constants added, which we claim are more reflective of SR performance for real-world *** claim is then strengthened by reproducing the superior performance on real-world regression datasets from *** researchers interested in equation-recovery problems, we also propose a set of conventions that can be used to promote fairness in comparison across SR methods and to reduce unintentional bias. © 2023 11th Internation

关键词： Morphology

来源：评论

学校读者我要写书评

暂无评论

WASTE HEAT RECOVERY IN REMOTE RENEWABLE ENERGY HUBS 37

WASTE HEAT RECOVERY IN REMOTE RENEWABLE ENERGY HUBS

引用

37th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems, ECOS 2024

作者： Dauchat, Liam Dachet, Victor Fonteneau, Raphaël Ernst, Damien Department of Electrical Engineering and Computer Science University of Liège Liège Belgium Telecom Paris Institut Polytechnique de Paris Palaiseau France

ISBN: (纸本)9798331307660

This paper delves into the investigation of the potential valorisation of waste heat generated inside a Remote Renewable Energy Hub (RREH).The RREH concept involves harvesting renewable energy where it is most abundant and producing synthetic fuels for export to energy demand *** case study explored in this work is an RREH located in the Sahara Desert, exporting 10 TWh of synthetic methane per year to *** primary aim of this study is to examine the impacts on costs resulting from the incorporation of waste heat recovery techniques into the *** results suggest a cost reduction of up to 3.88% by using waste heat recovery techniques, confirming their potential in reducing infrastructure size and optimizing the cost efficiency of the overall power-to-gas supply chain in RREH. © 2024 37th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems, ECOS 2024. All rights reserved.

关键词： Clean energy

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：