检索结果-内蒙古大学图书馆

2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies, ICIoT 2020

作者： Antoun, Wissam Baly, Fady Achour, Rim Hussein, Amir Hajj, Hazem American University of Beirut Electrical and Computer Engineering Department Beirut Lebanon Graduate Program in Computational Science American University of Beirut Beirut Lebanon

ISBN: (数字)9781728148212

ISBN: (纸本)9781728148212

This paper presents state of the art methods for addressing three important challenges in automated fake news detection: fake news detection, domain identification, and bot identification in tweets. The proposed solutions achieved first place in a recent international competition on fake news. For fake news detection, we present two models. The winning model in the competition combines similarity between the embedding of each article's title and the embedding of the top five corresponding google search results. The new model relies on advances in Natural Language Understanding (NLU) end to end deep learning models to identify stylistic differences between legitimate and fake news articles. This second model was developed after the competition and outperforms the winning approach. For news domain detection, the winning model is a hybrid approach composed of named entity features concatenated with semantic embeddings derived from end to end models. For twitter bot detection, we propose to use the following features: duration between account creation and tweet date, presence of a tweet's link, presence of user's location, other tweet's features, and the tweets' metadata. Experiments include insights into the importance of the different features and the results indicate the superior performances of all proposed models. © 2020 IEEE.

关键词： Competition

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Convolutional Neural Network-Based Tattoo Detection 7

Evaluation of Deep Convolutional Neural Network-Based Tattoo...

引用

7th International Congress on Ambient Intelligence, Software engineering, and e-Health and Mobile Health, AmITIC 2024

作者： Jiménez-Delgado, E. Quesada-López, C. Méndez-Porras, A. Lara-Petitdemange, A. Alfaro-Velasco, J. Graduate Program in Computer Science and Informatics University of Costa Rica Costa Rica Technological Institute of Costa Rica Computer Engineering Department Costa Rica School of Computer Science and Informatics University of Costa Rica Costa Rica

ISBN: (纸本)9798350364538

In this study, two deep learning models for automatic tattoo detection were analyzed;a modified Convolutional Neural Network (CNN) and pre-trained ResNet-50 model. In order to achieve this, ResNet-50 uses transfer learning with fine-tuning. The purpose of this study was to evaluate the accuracy, precision, recall, F1-score, and computational efficiency of the system being considered. To augment the dataset included 1000 photos that were equally divided between those showing tattoos and those that did not show tattoos. A k-fold cross-validation approach was employed in training and testing the models. Although custom CNNs are effective, utilizing pre-trained ones like ResNet-50 can offer even better outcomes. Specifically, ResNet-50 attained a higher accuracy (0.86 compared to 0.79), precision (0.85 versus 0.78), recall (0.91 against 0.86), and F1-score (0.91 vis-a-vis 0.86) as compared to custom CNNs. In selecting these models for examination, two main motivations were considered. The first motivation is to see whether transfer learning with a pre-trained ResNet-50 model does well when compared with a customized CNN designed specifically for tattoo detection. Secondly,the intent of this study is to know what advantages can be derived from each approach and their demerits too. Furthermore, it seeks to determine if transfer learning can provide an alternative in contrast to the common CNN techniques with regards to precision and computational efficiency. In this research, two models will be evaluated in order to answer the question of what is better for tattoo detection: transfer learning or designing custom architectures. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Expanding chiral metamaterials for retrieving fingerprints via vibrational circular dichroism

引用

Light(science & Applications) 2023年第7期12卷 1401-1414页

作者： Cheng Xu Zhihao Ren Hong Zhou Jingkai Zhou Chong Pei Ho Nan Wang Chengkuo Lee Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Center for Inteligent Sensors and MEMS(CISM) National University of SingaporeSingapore 117608Singapore institute of Microelectronics(IME) Agency for ScienceTechnology and Research(A*STAR)Singapore 138634Singapore NUS Graduate School for Integrative Science and Engineering Program(ISEP) National University of SingaporeSingapore 117456Singapore

Circular dichroism(CD)spectroscopy has been widely demonstrated for detecting chiral ***,the determination of chiral mixtures with various concentrations and enantiomeric ratios can be a challenging *** solve this problem,we report an enhanced vibrational circular dichroism(VCD)sensing platform based on plasmonic chiral metamaterials,which presents a 6-magnitude signal enhancement with a selectivity of chiral *** by coupled-mode theory,we leverage both in-plane and out-of-plane symmetry-breaking structures for chiral metamaterial design enabled by a two-step lithography process,which increases the near-field coupling strengths and varies the ratio between absorption and radiation loss,resulting in improved chiral light-matter interaction and enhanced molecular VCD ***,we demonstrate the thin-film sensing process of BSA andβ-lactoglobulin proteins,which contain secondary structures a-helix andβ-sheet and achieve a limit of detection down to zeptomole ***,we also,for the first time,explore the potential of enhanced VCD spectroscopy by demonstrating a selective sensing process of chiral mixtures,where the mixing ratio can be successfully differentiated with our proposed chiral *** findings improve the sensing signal of molecules and expand the extractable information,paving the way toward label-free,compact,small-volume chiral molecule detection for stereochemical and clinical diagnosisapplications.

关键词： chiral vibrational circular

来源：评论

学校读者我要写书评

暂无评论

Magnetic resonance imaging of irreversible electroporation in tubers

Magnetic resonance imaging of irreversible electroporation i...

引用

12th Mediterranean Conference on Medical and Biological engineering and Computing, MEDICON 2010

作者： Hjouj, Mohammad Rubinsky, Boris Center for Bioengineering School of Computer Science Engineering Hebrew University of Jerusalem Israel Department of Mechanical Engineering Graduate Program in Biophysics University of California Berkeley United States

ISBN: (纸本)9783642130380

Purpose: A preliminary study on the magnetic resonance (MRI) characteristics of (vegetable) tissue NTIRE is an emerging minimally invasive surgery technique for tissue ablation in which, microsecond, high electrical field pulses form permanent nano-scale defects in the cell membrane. Materials and Methods: The potato is used as the simplest conceivable first order tissue model for studying the MRI characteristics of electroporation, because while made of structured cells it does not have blood flow, it is relatively homogeneous and cell damage is readily visible through a natural oxidation process of the intracellular enzymes.. Clinical NTIRE sequences were applied to potato tubers and MRI sequences of the treated area were compared with colorimetric photographs. Results: A comparison of T1 weighted, T2 weighted, fluid attenuation inversion recovery (FLAIR) and short TI inversion recovery (STIR) of NTIRE shows that T1 weighted signals, such as FLAIR, produce brighter images of the treated areas. In contrast the images of the treated areas are completely lost with liquids enhancing and fat eliminating sequences, such as STIR. Conclusion: MRI can image tissue treated by NTIRE. A possible explanation for the findings is that by producing nanoscale defects in the cell membrane lipid bilayer, NTIRE causes an enhanced signal from the cell membrane lipids that in the treated cells are not bound anymore in a restrictive liquidgel membrane structure and have more degrees of freedom. © 2010 International Federation for Medical and Biological engineering.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

programmable threshold sensing in wireless devices using Ising dynamics

引用

Nature Electronics 2025年 1-8页

作者： Nicolas Casilli Hussein M. E. Hussein Ryan Tetro Luca Colombo Matteo Rinaldi Cristian Cassella Seunghwi Kim Andrea Alù Philip X.-L. Feng Institute for Nano Systems Innovation (NanoSI) Department of Electrical and Computer Engineering Northeastern University Boston MA USA Photonics Initiative Advanced Science Research Center City University of New York New York City NY USA Physics Program Graduate Center City University of New York New York City NY USA Department of Electrical and Computer Engineering University of Florida Gainesville FL USA

Ising machines—comprising dissipatively coupled nodes capable of emulating the behaviour of ferromagnetic spins—can form analogue computing engines that surpass the sequential processing constraints of von Neumann architectures. However, the incorporation of Ising dynamics into radio-frequency wireless technologies remains limited, especially in terms of their potential to enhance wireless sensing capabilities. Here we report a passive wireless sensor that uses Ising dynamics to accurately implement threshold sensing. The device correlates the occurrence of violations in a sensed parameter with transitions in the coupling state of two parametric oscillators acting as Ising spins. As a result, the accuracy of the device is unaffected by distortions in its input and output signals due to multipath and is less prone to clutter caused by co-site interference. We illustrate the potential of the approach in temperature threshold sensing using a microfabricated lithium niobate microelectromechanical temperature sensor to couple two radio-frequency parametric oscillators, and show that such a system allows the sensor threshold to be wirelessly reprogrammed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Voltage Levels and Reactive Power in Distribution Networks with High Integration of Distributed Photovoltaic Generation

Voltage Levels and Reactive Power in Distribution Networks w...

引用

2019 IEEE PES Conference on Innovative Smart Grid Technologies, ISGT Latin America 2019

作者： Darui, Caroline B. F. Lucca, Tiago G. Abaide, Alzenira Da R. Da Veiga, Matheus F. Da Cruz, Matheus S. Knak Neto, Nelson Wüst, Lucas L. Figueiró, Iuri C. Federal University of Santa Maria Graduate Program in Electrical Engineering Santa Maria Brazil URI Santo Ângelo Department of Engineering and Computer Science Santo Ângelo Brazil

ISBN: (纸本)9781538695678

The Brazilian electrical system is undergoing many changes due to the exponential growth of photovoltaic systems connected to the grid (PV). This increase may affect power quality parameters, such as reduction of power factor and increase of voltage levels. This work aims to model and simulate a low voltage distribution network with high levels of integration of PV systems in order to verify how the voltage and reactive parameters behave in these cases. It was used new load curve models, the Monte Carlo method and the OpenDSS software. © 2019 IEEE.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Particle Swarm Optimization with Crossover and Mutation of Genetic Algorithm for Solving the Wide Constraint Problem

A Hybrid Particle Swarm Optimization with Crossover and Muta...

引用

2019 International Congress on Applied Information Technology, AIT 2019

作者： Herlawati, H. Heryadi, Yaya Lukas, L. BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Cognitive Engineering Research Group Faculty of Engineering Universitas Katolik Indonesia Atma Jaya Jakarta12930 Indonesia

ISBN: (纸本)9781728158624

When optimizing the spatial data, a lot of constraints should be handled. Some constraints might be too wide for a metaheuristic algorithm, e.g. particle swarm optimization, to allocate the candidate locations outside a wide constraint. However, particle swarm optimization notably has fast computation characteristic and many researchers used this method for optimizing their spatial data. In the other hand, genetic algorithm has not only better exploitation-characteristic performance in searching but also has mutation and crossover that was proven in this study can be overcome the wide constraint problem. To minimize the drawback of genetic algorithm, i.e. need many computation resources, the hybrid particle swarm optimization with genetic algorithm through the use of crossover and mutation was used. Half of lower fitness values from particle swarm optimization were optimized using crossover and mutation in genetic algorithm. After merging the results of both methods, the optimum location showed that the proposed method was able to allocate the land use in a case study area outside the wide constraint. © 2019 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Initial explorations on using CRFs for turkish named entity recognition

Initial explorations on using CRFs for turkish named entity ...

引用

24th International Conference on Computational Linguistics, COLING 2012

作者： Şseker, Gökhan Akin Eryǐgit, Güļsen ITU Informatics Institute Graduate Program in Computer Science Istanbul Technical University Istanbul 34469 Turkey Department of Computer Engineering Istanbul Technical University Istanbul 34469 Turkey

This paper reports the highest results (95% in MUC and 92% in CoNLL metric) in the literature for Turkish named entity recognition;more specifically for the task of detecting person, location and organization entities in general news texts. We give an in depth analysis of the previous reported results and make comparisons with them whenever possible. We use conditional random fields (CRFs) as our statistical model. The paper presents initial explorations on the usage of rich morphological structure of the Turkish language as features to CRFs together with the use of some basic and generative gazetteers. © 2012 The COLING.

关键词： Random processes

来源：评论

学校读者我要写书评

暂无评论

Back propagation neural network experiment on team matchmaking MOBA game 1

Back propagation neural network experiment on team matchmaki...

引用

1st International Conference on Information and Communications Technology, ICOIACT 2018

作者： Tanuar, Evawaty Abbas, Bahtiar Saleh Trisetyarso, Agung Kang, Chul-Ho Gaol, Ford Lumban Suparta, Wayan Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program - Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia Department of Electrical Engineering Sanata Dharma University Yogyakarta55282 Indonesia

ISBN: (纸本)9781538609545

Backpropagation is one of the famous method for learning, Implementing Backpropagation techniques in games is part of AI in game. This paper aim to analyzed the best team composition in a Moba Game type in learning using neural network. Mobile Legend: Bang Bang is one of MOBA game for mobile phone. In this experiment, the 2 hidden layers back-propagation neural network algorithm is used to analyze the Mobile Legend game. 5000 training steps was done to reach the stability. This also a way of learning to find the best composition in a team played. Research in area AI and game is very wide and open, a huge opportunity to be explore in future. The objective of this research is to produce the good combination of team which can be resulted in a greater winning chance. © 2018 IEEE.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Configurable clutter models for radar simulation

Configurable clutter models for radar simulation

引用

International Waveform Diversity and Design Conference, WDD 2012

作者： Jezak, Joseph A. Gadola, Guy Berdanier, Charles Levitan, Steven P. Chiarulli, Donald M. Computer Engineering Graduate Program University of Pittsburgh United States Department of Electrical Engineering Wright State University United States Department of Electrical and Computer Engineering University of Pittsburgh United States Department of Computer Science University of Pittsburgh United States

ISBN: (纸本)9781509005987

In this paper we describe an extension to the MATLAB Phased Array Toolkit that adds a configurable clutter object to model clutter signals returned along a specified signal path. The clutter model is based on the Simkins Unified Clutter Model[1]. The current implementation supports sea clutter in any of five sea states with configurable polarization, grazing angle, and beam width. We describe the implementation and give examples of modeled clutter returns. © 2012 IEEE.

关键词： MATLAB

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：