检索结果-内蒙古大学图书馆

A stroke detection system based on cincinnati prehospital stroke scale 19

学校读者我要写书评

暂无评论

A stroke detection system based on cincinnati prehospital st...

3rd International Conference on Medical and Health Informatics, ICMHI 2019

作者： Chien, Ting-Ying Chen, Chong-Yi Jin, Guo-Lun Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan Institute of Data Science and Engineering National Chiao Tung University Hsinchu City Taiwan

ISBN: (纸本)9781450371995

Stroke, also known as cerebrovascular events, is mainly caused by the obstruction of blood flow in the brain, which leads to an inability to supply oxygen to the brain. By 2013, stroke had become the second most common cause of death in Taiwan (accounting for about 12% of all deaths). This study used image processing technology and speech recognition, following the Cincinnati Prehospital Stroke Scale, to determine whether or not the user had a stroke. The Cincinnati Prehospital Stroke Scale has three indicators, including facial droop, arm drift, and speech. Patients with 1 of these 3 findings have a 72% probability of having had an ischemic stroke. If all satisfies, the probability of the stroke is more than 85%. In addition, we developed a mobile APP based on this method to detect whether or not the user had a stroke, and hope to reduce stroke hazards. © 2019 ACM.

关键词： Signal detection

Recommender systems based on generative adversarial networks: a problem-driven perspective

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gao, Min Zhang, Junwei Yu, Junliang Li, Jundong Wen, Junhao Xiong, Qingyu Department of Electrical and Computer Engineering Department of Computer Science School of Data Science University of Virginia Charlottesville22904 United States School of Information Technology and Electrical Engineering University of Queensland QLD4072 Australia School of Big Data and Software Engineering Chongqing University Chongqing401331 China

Recommender systems (RS) play a very important role in various aspects of people’s online life. Many companies leverage RS to help users discover new and favored items. Despite their empirical success, these systems still suffer from two main problems: data noise and data sparsity. In recent years, Generative Adversarial Networks (GANs) have received a surge of interests in many fields because of their great potential to learn complex real data distribution, and they also provide new means to mitigate the aforementioned problems of RS. Particularly, owing to adversarial learning, the problem of data noise can be handled by adding adversarial perturbations or forcing discriminators to tell the informative and uninformative data examples apart. As for the mitigation of data sparsity issue, the GAN-based models are able to replicate the real distribution of the user-item interactions and augment the available data. To gain a comprehensive understanding of these GAN-based recommendation models, we provide a retrospective of these studies and organize them from a problem-driven perspective. Specifically, we propose a taxonomy of these models, along with a detailed description of them and their advantages. Finally, we elaborate on several open issues and expand on current trends in the GAN-based RS. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

DoT-Net: Document layout classification using texture-based CNN 15

学校读者我要写书评

暂无评论

DoT-Net: Document layout classification using texture-based ...

15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019

作者： Kosaraju, Sai Chandra Masum, Mohammed Tsaku, Nelson Zange Patel, Pritesh Bayramoglu, Tanju Modgil, Girish Kang, Mingon Department of Computer Science Kennesaw State University Marietta United States Analytics and Data Science Institute Kennesaw State University Kennesaw United States GE Power Atlanta United States

ISBN: (纸本)9781728128610

Document Layout Analysis (DLA) is a segmentation process that decomposes a scanned document image into its blocks of interest and classifies them. DLA is essential in a large number of applications, such as Information Retrieval, Machine Translation, Optical Character Recognition (OCR) systems, and structured data extraction from documents. However, identification of document blocks in DLA is challenging due to variations of block locations, inter-and intra-class variability, and background noises. In this paper, we propose a novel texture-based convolutional neural network for document layout analysis, called DoT-Net. DoT-Net is a multiclass classifier that can effectively identify document component blocks such as text, image, table, mathematical expression, and line-diagram, whereas most related methods have focused on the text vs. non-text block classification problem. DoT-Net can capture textural variations among the multiclass regions of documents. Our proposed method DoT-Net achieved promising results outperforming state-of-the-art document layout classifiers on accuracy, F1 score, and AUC. The open-source code of DoT-Net is available at https://***/datax-lab/DoTNet. © 2019 IEEE.

关键词： Textures

A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Di Wang, Moyang Mango, Joseph Li, Xiang Xu, Xianrui Key Laboratory of Geographic Information Science Ministry of Education School of Geographic Sciences East China Normal University Shanghai200241 China Department of Transportation and Geotechnical Engineering University of Dar es Salaam Dar es salaam Tanzania United Republic of Shanghai Key Lab for Urban Ecological Processes and Eco-Restoration East China Normal University Shanghai200241 China Key Laboratory of Spatial-Temporal Big Data Analysis and Application of Natural Resources in Megacities Ministry of Natural Resources East China Normal University Shanghai200241 China School of Economics and Management Shanghai University of Sport Shanghai200438 China

The challenge of spatial resource allocation is pervasive across various domains such as transportation, industry, and daily life. As the scale of real-world issues continues to expand and demands for real-time solutions increase, traditional algorithms face significant computational pressures, struggling to achieve optimal efficiency and real-time capabilities. In recent years, with the escalating computational power of computers, the remarkable achievements of reinforcement learning in domains like Go and robotics have demonstrated its robust learning and sequential decision-making capabilities. Given these advancements, there has been a surge in novel methods employing reinforcement learning to tackle spatial resource allocation problems. These methods exhibit advantages such as rapid solution convergence and strong model generalization abilities, offering a new perspective on resolving spatial resource allocation problems. Therefore, this paper aims to summarize and review recent theoretical methods and applied research utilizing reinforcement learning to address spatial resource allocation problems. It provides a summary and comprehensive overview of its fundamental principles, related methodologies, and applied research. Additionally, it highlights several unresolved issues that urgently require attention in this direction for the future. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

AlphaCrystal: Contact map based crystal structure prediction using deep learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Hu, Jianjun Zhao, Yong Li, Qin Song, Yuqi Dong, Rongzhi Yang, Wenhui Siriwardane, Edirisuriya M.D. Department of Computer Science and Engineering University of South Carolna ColumbiaSC29201 United States College of Big Data and Statistics Guizhou University of Finance and Economics Guiyang550050 China School of Mechanical Engineering Guizhou University Guiyang550050 China Department of Physics University of Colombo Colombo 3 Sri Lanka

Crystal structure prediction is one of the major unsolved problems in materials science. Traditionally, this problem is formulated as a global optimization problem for which global search algorithms are combined with first principle free energy calculations to predict the ground state crystal structure given only material composition. These ab initio algorithms are currently too slow for predicting complex material structures. Inspired by the AlphaFold algorithm for protein structure prediction, herein we propose AlphaCrystal, a crystal structure prediction algorithm that combines a deep residual neural network model for predicting the atomic contact map of a target material followed by 3D structure reconstruction using genetic algorithms. Extensive experiments on 20 benchmark structures showed that our AlphaCrystal algorithm can predict structures close to the ground truth structures, which can significantly speed up the crystal structure prediction and handle relatively large systems. © 2021, CC BY-NC-ND.

关键词： Neural network models

Towards adversarial patch analysis and certified defense against crowd counting

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wu, Qiming Zou, Zhikang Zhou, Pan Ye, Xiaoqing Wang, Binghui Li, Ang School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan China Baidu Inc. Shenzhen China The Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Department of Computer Science Illinois Institute of Technology Chicago United States Department of Electrical and Computer Engineering Duke University Durham United States

Crowd counting has drawn much attention due to its importance in safety-critical surveillance systems. Especially, deep neural network (DNN) methods have significantly reduced estimation errors for crowd counting missions. Recent studies have demonstrated that DNNs are vulnerable to adversarial attacks, i.e., normal images with human-imperceptible perturbations could mislead DNNs to make false predictions. In this work, we propose a robust attack strategy called Adversarial Patch Attack with Momentum (APAM) to systematically evaluate the robustness of crowd counting models, where the attacker's goal is to create an adversarial perturbation that severely degrades their performances, thus leading to public safety accidents (e.g., stampede accidents). Especially, the proposed attack leverages the extreme-density background information of input images to generate robust adversarial patches via a series of transformations (e.g., interpolation, rotation, etc.). We observe that by perturbing less than 6% of image pixels, our attacks severely degrade the performance of crowd counting systems, both digitally and physically. To better enhance the adversarial robustness of crowd counting models, we propose the first regression model-based Randomized Ablation (RA), which is more sufficient than Adversarial Training (ADT) (Mean Absolute Error of RA is 5 lower than ADT on clean samples and 30 lower than ADT on adversarial examples). Extensive experiments on five crowd counting models demonstrate the effectiveness and generality of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Network security

Record Acceleration of the Two-Dimensional Ising Model Using a High-Performance Wafer-Scale Engine

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Shi, Wei Van Essendelft, Dirk Saidi, Wissam Abdo Almolyki, Hayl Jordan, Terry Wang, Mei-Yu The National Energy Technology Laboratory 3610 Collins Ferry Rd MorgantownWV26505 United States Department of Computer Science and Engineering Tandon School of Engineering New York University 6 MetroTech Center BrooklynNY11201 United States The National Energy Technology Laboratory 626 Cochrans Mill Rd PittsburghPA15236 United States HPC AI and Big Data Group Pittsburgh Supercomputing Center Carnegie Mellon University 300 S. Craig St. PittsburghPA15213 United States The National Energy Technology Laboratory 626 Cochrans Mill Rd PittsburghPA15236 United States

The versatility and wide-ranging applicability of the Ising model, originallyintroduced to study phase transitions in magnetic materials, have made it a cornerstonein statistical physics and a valuable tool for evaluating the performanceof emerging computer hardware. Here, we present a novel implementation of thetwo-dimensional Ising model on Cerebras Wafer-Scale Engine (WSE) – a revolutionaryprocessor that is opening new frontiers in computing. In our deploymentof the checkerboard algorithm, we optimized the Ising model to take advantage of the unique WSE architecture. Specifically, we employed a compressed bit representationstoring 16 spins on each int16 word, and efficiently distributed the spinsover the processing units enabling seamless weak scaling and limiting communicationsto only immediate neighboring units. Our implementation can handleup to 754 simulations in parallel, achieving an aggregate of over 61.8 trillion flipattempts per second for Ising models with up to 200 million spins. This representsa gain of up to 148 times over previously reported single-devices with a highlyoptimized implementation on NVIDIA V100 and up to 88 times in productivitycompared to NVIDIA H100. Our findings highlight the significant potential ofthe WSE in scientific computing, particularly in the field of materials modeling. © 2024, The Authors. All rights reserved.

关键词： Ising model

Vanadia as an electron-hole recombination inhibitor on fibrous silica-titania for selective hole oxidation of ciprofloxacin and Congo red photodegradation

学校读者我要写书评

暂无评论

Chemosphere 2023年第1期338卷 139502页

作者： Hassan, N.S. Jalil, A.A. Fei, I.C.M. Razak, M.T.A. Khusnun, N.F. Bahari, M.B. Riwayati, Y.I. Suprapto, S. Prasetyoko, D. Firmansyah, M.L. Salleh, N.F.M. Rajendran, Saravanan Centre of Hydrogen Energy Institute of Future Energy UTM Johor Johor Bahru81310 Malaysia Faculty of Chemical and Energy Engineering Universiti Teknologi Malaysia UTM Johor Johor Bahru81310 Malaysia Faculty of Science Universiti Teknologi Malaysia UTM Johor Johor Bahru81310 Malaysia Department of Chemistry Faculty of Science and Data Analytics Institut Teknologi Sepuluh Nopember Keputih Sukolilo Surabaya60111 Indonesia Nanotechnology Engineering Faculty of Advanced Technology and Multidiscipline Airlangga University Jl. Dr. Ir. H. Soekarno Surabaya60115 Indonesia Environmental and Occupational Health Programme School of Health Sciences Health Campus Universiti Sains Malaysia Kubang Kerian Kelantan 16150 Malaysia Faculty of Engineering Department of Mechanical Engineering University of Tarapacá Avda General Velasquez Arica1775 Chile

Vanadia (V2O5)-incorporated fibrous silica-titania (V/FST) catalysts, which were successfully synthesized using a hydrothermal method followed by the impregnation of V2O5. The catalysts were then characterized using numerous techniques, including X-ray diffraction, field emission scanning electron microscopy, transmission electron microscopy, nitrogen adsorption–desorption analyses, ultraviolet–visible diffuse reflectance spectroscopy, Fourier-transform infrared, X-ray photoelectron spectroscopy, and photoluminescence (PL) analyses. The study found that varying the amount of V2O5 (1–10 wt%) had a significant impact on the physicochemical properties of the FST, which in turn improved the photodegradation efficiency of two organic compounds, ciprofloxacin (CIP) and congo red (CR). 5V/FST demonstrated the best performance in degrading 10 mg L−1 of CIP (83%) and CR (100%) at pH 3 using 0.375 g L−1 catalyst under visible light irradiation within 180 min. The highest photoactivity of 5V/FST is mainly due to higher crystallinity and the highest number of V2O5-FST interactions. Furthermore, as demonstrated by PL analysis, the 5V/FST catalyst has the most significant impact on interfacial charge transfer and reduces electron-hole recombination. The photodegradation of both contaminants follows the Langmuir-Hinshelwood pseudo-first-order model, according to the kinetic study. The scavenger investigation demonstrated that hydroxyl radicals and holes dominated species in the system, indicating that the catalyst effectively generated reactive species for pollutant degradation. A possible mechanism was also identified for FST and 5V/FST. Interestingly, V2O5 acts as an electron-hole recombination inhibitor on FST for selective hole oxidation of ciprofloxacin and congo red photodegradation. Finally, the degradation efficiency of the catalyst remained relatively stable even after five cyclic experiments, indicating its potential for long-term use in environmental remediation. © 2023

关键词： Catalysts

Multistep sintering: its role on density, phase homogeneity, microstructure and electrical properties of (1-x-y)BaTiO3-xPbZrO3-yNaVO3 System

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2021年第1期1825卷

作者： M Absa F Latief S Suasmoro Department of Physics Faculty of Science and Data Analytics Sepuluh Nopember Institute of Technology Surabaya 60111 Indonesia

Barium Titanate synthesized by the oxalate coprecipitation method was doped by other perovskite-based material PbZrO3 and NaVO3 to obtain a system of (1-x-y)BaTiO3-xPbZrO3-yNaVO3 with x = 0.15 and y = 0.025. TGA characterization shows an important weight loss that starts at 400°C and finished at 650°C. XRD analysis of calcined powder at 650°C shows that the samples mostly consist of single-phase BaTiO3 perovskite. Sintering process was carried out in two ways; first, a single step sintering up to 1250°C for 2 hours shows increasing secondary phases, until the BaTiO3 phase becomes the minority. Secondly, multistep sintering starting at 1050°C, holding for 2 hours, down to room temperature, and then repeated with similar processes for 1150°C and 1250°C. Characterizations including XRD, SEM for microstructure, and permittivity analysis of the sample after this thermal treatment shows that the majority phase is BaTiO3 with minor secondary BaVO2.9 phase and its electrical properties are enhanced.

关键词：