检索结果-内蒙古大学图书馆

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Zhang, Shuo Xie, Lei Ph.D. Program in Computer Science Graduate Center City University of New York United States Department of Computer Science Hunter College City University of New York United States Helen and Robert Appel Alzheimer's Disease Research Institute Feil Family Brain and Mind Research Institute Weill Cornell Medicine Cornell University United States

ISBN: (纸本)9780999241165

Graph Neural Networks (GNNs) are powerful for the representation learning of graph-structured data. Most of the GNNs use a message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information from its neighbors. To achieve a better expressive capability of node influences, attention mechanism has grown to be popular to assign trainable weights to the nodes in aggregation. Though the attention-based GNNs have achieved remarkable results in various tasks, a clear understanding of their discriminative capacities is missing. In this work, we present a theoretical analysis of the representational properties of the GNN that adopts the attention mechanism as an aggregator. Our analysis determines all cases when those attention-based GNNs can always fail to distinguish certain distinct structures. Those cases appear due to the ignorance of cardinality information in attention-based aggregation. To improve the performance of attention-based GNNs, we propose cardinality preserved attention (CPA) models that can be applied to any kind of attention mechanisms. Our experiments on node and graph classification confirm our theoretical analysis and show the competitive performance of our CPA models. The code is available online: https://***/zetayue/CPA. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Manipulating Fano coupling in an opto-thermoelectric field

arXiv

引用

arXiv 2024年

作者： Lin, Linhan Lepeshov, Sergey Krasnok, Alex Huang, Yu Jiang, Taizhi Peng, Xiaolei Korgel, Brian A. Alu, Andrea Zheng, Yuebing State Key Laboratory of Precision Measurement Technology and Instruments Department of Precision Instrument Tsinghua University Beijing100084 China Department of Electrical and Photonics Engineering DTU Electro Technical University of Denmark Building 343 Kgs. LyngbyDK-2800 Denmark Department of Electrical and Computer Engineering Florida International University MiamiFL33174 United States School of Physics and Electronics Hunan University Changsha410082 China Mc Ketta Department of Chemical Engineering The University of Texas at Austin AustinTX78712 United States Materials Science & Engineering Program Texas Materials Institute The University of Texas at Austin AustinTX78712 United States Department of Electrical and Computer Engineering The University of Texas at Austin AustinTX78712 United States Advanced Science Research Center City University of New York New YorkNY10031 United States Physics Program Graduate Center City University of New York NY10016 United States Walker Department of Mechanical Engineering The University of Texas at Austin AustinTX78712 United States

Fano resonances in photonics arise from the coupling and interference between two resonant modes in structures with broken symmetry. They feature an uneven and narrow and tunable lineshape, and are ideally suited for optical spectroscopy. Many Fano resonance structures have been suggested in nanophotonics over the last ten years, but reconfigurability and tailored design remain challenging. Herein, we propose an all-optical "pick-and-place" approach aimed at assemble Fano metamolecules of various geometries and compositions in a reconfigurable manner. We study their coupling behavior by in-situ dark-field scattering spectroscopy. Driven by a light-directed opto-thermoelectric field, silicon nanoparticles with high quality-factor Mie resonances (discrete states) and low-loss BaTiO3 nanoparticles (continuum states) are assembled into all-dielectric heterodimers, where distinct Fano resonances are observed. The Fano parameter can be adjusted by changing the resonant frequency of the discrete states or the light polarization. We also show tunable coupling strength and multiple Fano resonances by altering the number of continuum states and discrete states in dielectric heterooligomers. Our work offers a general design rule for Fano resonance and an all-optical platform for controlling Fano coupling on demand. Copyright © 2024, The Authors. All rights reserved.

关键词： Light polarization

来源：评论

学校读者我要写书评

暂无评论

Performance test of manual wind based water pump in coordination with solar panel based pump

引用

AIP Conference Proceedings 2024年第1期3140卷

作者： A. M. Shiddiq Yunus Musrady Mulyadi Apollo Apollo Fajri Rahardjo Esty Yunus Adeaksa Syamsul Ulan Dari Yusril Yusril Energy Conversion Study Program Politeknik Negeri Ujung Pandang Jalan Perintis Kemerdekaan KM. 10 Makassar 90245 Indonesia Applied Renewable Energy Study Program Politeknik Negeri Ujung Pandang Jalan Perintis Kemerdekaan KM. 10 Makassar 90245 Indonesia Computer and Networking Study Program Politeknik Negeri Ujung Pandang Jalan Perintis Kemerdekaan KM. 10 Makassar 90245 Indonesia

The water requirement for watering the garden is an essential factor, therefore maintaining the continued supply is necessary. Pumping water for gardens using Solar panels has been introduced in many applications. However, there is a drawback of using solar panels alone which the optimum time for radiation for Indonesia is around 5 to 6 hours only. Moreover, cloudy conditions could reduce the number of radiation hitting the solar panel. In this paper, the use of Savonius Turbine to pump water mechanically is employed to maximize the supply of water to the garden. The water supply is fed from the Savonius Turbine while when the wind speed is low enough (less than 3 m/s), water supply will be fed from the water reservoir by opening the tap from 50% when the wind speed between 3 to 6 m/s, or 100% when wind speed less than 3 m/s. The tap will be closed when wind speed achieves 6 m/s. This paper aims to investigate the performance of the coordination between the manual pump that is mechanically operated by Savonius Turbine and the level of the opened tap of the water reservoir. The solar panel is operated based on the level of the water reservoir. If the level of water in the reservoir is below 10cm, the DC water pump will operate to fill the reservoir and stop when it’s full. The coordination and data acquisition are done and collected by a microcontroller. From the performance test, it could be concluded that the whole system could work properly based on the implemented design and manufacture.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved MVDR beamforming using LSTM speech models to clean spatial clustering masks

arXiv

引用

arXiv 2020年

作者： Ni, Zhaoheng Grezes, Felix Trinh, Viet Anh Mandel, Michael I. Computer Science Program Graduate Center City University of New York United States Computer and Information Science Brooklyn College City University of New York United States

Spatial clustering techniques can achieve significant multichannel noise reduction across relatively arbitrary microphone configurations, but have difficulty incorporating a detailed speech/noise model. In contrast, LSTM neural networks have successfully been trained to recognize speech from noise on single-channel inputs, but have difficulty taking full advantage of the information in multi-channel recordings. This paper integrates these two approaches, training LSTM speech models to clean the masks generated by the Model-based EM Source Separation and Localization (MESSL) spatial clustering method. By doing so, it attains both the spatial separation performance and generality of multi-channel spatial clustering and the signal modeling performance of multiple parallel single-channel LSTM speech enhancers. Our experiments show that when our system is applied to the CHiME-3 dataset of noisy tablet recordings, it increases speech quality as measured by the Perceptual Evaluation of Speech Quality (PESQ) algorithm and reduces the word error rate of the baseline CHiME-3 speech recognizer, as compared to the default BeamformIt beamformer. © 2020, CC BY.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

SUPP & MAPP: ADAPTABLE STRUCTURE-BASED REPRESENTATIONS FOR MIR TASKS 21

SUPP & MAPP: ADAPTABLE STRUCTURE-BASED REPRESENTATIONS FOR M...

引用

21st International Society for Music Information Retrieval Conference, ISMIR 2020

作者： Savard, Claire Bugbee, Erin H. McGuirl, Melissa R. Kinnaird, Katherine M. Department of Physics University of Colorado Boulder United States Department of Biostatistics Brown University United States Division of Applied Mathematics Brown University United States Department of Computer Science and Program in Statistical and Data Sciences Smith College United States

ISBN: (纸本)9780981353708

Accurate and flexible representations of music data are paramount to addressing MIR tasks, yet many of the existing approaches are difficult to interpret or rigid in nature. This work introduces two new song representations for structure-based retrieval methods: Surface Pattern Preservation (SuPP), a continuous song representation, and Matrix Pattern Preservation (MaPP), SuPP’s discrete counterpart. These representations come equipped with several user-defined parameters so that they are adaptable for a range of MIR tasks. Experimental results show MaPP as successful in addressing the cover song task on a set of Mazurka scores, with a mean precision of 0.965 and recall of 0.776. SuPP and MaPP also show promise in other MIR applications, such as novel-segment detection and genre classification, the latter of which demonstrates their suitability as inputs for machine learning problems. © Claire Savard, Erin H. Bugbee, Melissa R. McGuirl, Katherine M. Kinnaird.

关键词： Information retrieval

来源：评论

学校读者我要写书评

暂无评论

Smart cane as a tool for the blind with sensors for the detection of fire, hole and obstacles

引用

AIP Conference Proceedings 2023年第1期2865卷

作者： Nur Hudha Wijaya Muhammad Irfan Wisnu Kartika Kais Ismail Ibraheem Pandu Risky Adhitya Department of Medical Electronics Technology Vocational Program Universitas Muhammadiyah Yogyakarta Yogyakarta Indonesia Department of Computer Science College of Education for Pure Science University of Mosul Mosul Iraq

The level of blindness can be divided into total blindness or is still able to see dimly (Low Vision). It is often found that blind people have difficulty in carrying out daily activities due to the loss of the function of the sense of sight. With this deficiency, blind people try to maximize other sensory functions. Most blind people use a cane as a walking aid. Despite using the cane, there are often problems such as falling into a hole or hitting an obstacle. Accordingly, a tool for the visually impaired was made, a cane that is able to guide users to find out objects, holes and fire in front of them when walking, thereby reducing the number of potential accidents for blind road users. This cane is equipped with 2 ultrasonic sensors to detect obstacles in the form of objects, 1 fire sensor and 1 hole sensor. With the direct design and manufacture method, the data from the stick was tested 30 times on each sensor. The fire sensor uses an optical method to detect fire with a distance of 0-20 cm, while this sensor can only be used at night or indoors. The hole sensor detects obstacles by utilizing the nature of light by detecting a hole depth of 0-50 cm, and immediately a buzzer sound alarms the user. These data prove that the cane can function properly in accordance with the purpose of the research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Negative photo conductivity triggered with visible light in wide bandgap oxide-based optoelectronic crossbar memristive array for photograph sensing and neuromorphic computing applications

npj Unconventional Computing

引用

npj Unconventional Computing 2024年第1期1卷 1-9页

作者： Dayanand Kumar Hanrui Li Manoj Kumar Rajbhar Abdul Momin Syed Nazek El-Atab Amit Singh Hoonkyung Lee Smart Advanced Memory Devices and Applications (SAMA) Laboratory Electrical and Computer Engineering Program Computer Electrical Mathematical Science and Engineering Division King Abdullah University of Science and Technology (KAUST) Thuwal Saudi Arabia Department of Physics and Astronomy University of Manchester Manchester UK Department of Physics Konkuk University Seoul Republic of Korea

Photoresponsivity studies of wide-bandgap oxide-based devices have emerged as a vibrant and popular research area. Researchers have explored various material systems in their quest to develop devices capable of responding to illumination. In this study, we engineered a mature wide-bandgap oxide-based bilayer heterostructure synaptic memristor to emulate the human brain for applications in neuromorphic computing and photograph sensing. The device exhibits advanced electric and electrophotonic synaptic functions, such as long-term potentiation (LTP), long-term depression (LTD), and paired-pulse facilitation (PPF), by applying successive electric and photonic pulses. Moreover, the device exhibits exceptional electrical SET and photonic RESET endurance, maintaining its stability for a minimum of 1200 cycles without any degradation. Density functional theory calculations of the band structures provide insights into the conduction mechanism of the device. Based on this memristor array, we developed an autoencoder and convolutional neural network for noise reduction and image recognition tasks, which achieves a peak signal-to-noise ratio of 562 and high accuracy of 84.23%, while consuming lower energy by four orders of magnitude compared with the Tesla P40 GPU. This groundbreaking research not only opens doors for the integration of our device into image processing but also represents a significant advancement in the realm of in-memory computing and photograph-sensing features in a single cell.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Behavior Tree Designing Tool for Online Evaluation

A Behavior Tree Designing Tool for Online Evaluation

引用

Annual Conference of Industrial Electronics Society

作者： Alexander S. Barbosa Patricia D. M. Plentz Edson R. De Pieri Automation and Sys. Graduate Program Federal University of Santa Catarina Florianopólis Brazil Computer Science Graduate Program Federal University of Santa Catarina Florianopólis Brazil

ISBN: (数字)9781728154145

ISBN: (纸本)9781728154152

First presented as a tool to develop intelligent agents in computer games, Behavior Trees (BTs) are an alternative to Finite State Machines that later gained popularity in robotics, due to its modularity and how easy it makes to create intelligent reactive behaviors. Even with BTs being popular, the available tools to design it still lack features that allow validation without the end-application, whether it is a game or a robot. In this paper, a novel tool for BTs design is presented. This tool allows us to create BTs and also to evaluate then without any external software, making it easy to check all possible behaviors during the design stage. Also, the BTs created in the software can be directly used in ***, a popular behavior tree library for robotics.

关键词： Tools Software Robots Games Libraries Visualization Service robots

来源：评论

学校读者我要写书评

暂无评论

COVID-19 detection in computed tomography images with 2D and 3D approaches

arXiv

引用

arXiv 2021年

作者： Ali Ahmed, Sara Atito Can Yavuz, Mehmet Umut Sen, Mehmet Gulsen, Fatih Tutar, Onur Korkmazer, Bora Samancı, Cesur Şirolu, Sabri Hamid, Rauf Eryürekli, Ali Ergun Mammadov, Toghrul Yanikoglu, Berrin Sabanci University Istanbul34956 Turkey Urbanstat The Istanbul University-Cerrahpaşa Cerrahpaşa Faculty of Medicine Turkey The Computer Science and Engineering Program Sabanci University Istanbul34956 Turkey The Sabanci University Center of Excellence in Data Analytics

Detecting COVID-19 in computed tomography (CT) or radiography images has been proposed as a supplement to the definitive RT-PCR test. We present a deep learning ensemble for detecting COVID-19 infection, combining slice-based (2D) and volume-based (3D) approaches. The 2D system detects the infection on each CT slice independently, combining them to obtain the patient-level decision via different methods (averaging and long-short term memory networks). The 3D system takes the whole CT volume to arrive to the patient-level decision in one step. A new high resolution chest CT scan dataset, called the IST-C dataset, is also collected in this work. The proposed ensemble, called IST-CovNet, obtains 90.80% accuracy and 0.95 AUC score overall on the IST-C dataset in detecting COVID-19 among normal controls and other types of lung pathologies;and 93.69% accuracy and 0.99 AUC score on the publicly available MosMed dataset that consists of COVID-19 scans and normal controls only.. The system is deployed at Istanbul University Cerrahpaşa School of Medicine. Copyright © 2021, The Authors. All rights reserved.

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Parallel 3D temperature image reconstruction using multi-color magnetic particle imaging (MPI)

引用

AIP Conference Proceedings 2024年第1期3230卷

作者： Klaus N. Quelhas Mark-Alexander Henn Ricardo Farias Weston L. Tew Solomon I. Woods National Institute of Standards and Technology (NIST) 100 Bureau Drive Gaithersburg MD USA Systems Engineering and Computer Science Program (PESC) Federal University of Rio de Janeiro Rio de Janeiro RJ Brazil College of Computer Mathematical & Natural Sciences University of Maryland 7998 Regents Dr College Park MD USA

Magnetic Particle Imaging (MPI) is a novel technique developed for remotely detecting magnetic nanoparticle (MNP) tracers, with great potential for biomedical imaging (as an alternative to traditional methods like MRI or CT), cell tracking, targeted drug delivery and magnetic hyperthermia. More recently, MPI has been studied as a potential method of non-contact temperature measurement. This work presents a simulation study of the multi-color MPI method tailored for 3D temperature imaging, discusses the feasibility of the method for 3D temperature measurements, and shows a parallel implementation of the multi-color T-MPI reconstruction algorithm in graphics processing unit (GPU). While the use of the parallel algorithm resulted in executions about 40x faster when compared to the serial implementation, the method exhibited serious limitations in accurately resolving particle temperatures between the calibration temperatures by interpolation.

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：