检索结果-内蒙古大学图书馆

Learning graphon autoencoders for generative graph modeling

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Xu, Hongteng Zhao, Peilin Huang, Junzhou Luo, Dixin Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China Tencent AI Lab United States School of Computer Science and Technology Beijing Institue of Technology China

Graphon is a nonparametric model that generates graphs with arbitrary sizes and can be induced from graphs easily. Based on this model, we propose a novel algorithmic framework called graphon autoencoder to build an interpretable and scalable graph generative model. This framework treats observed graphs as induced graphons in functional space and derives their latent representations by an encoder that aggregates Chebshev graphon filters. A linear graphon factorization model works as a decoder, leveraging the latent representations to reconstruct the induced graphons (and the corresponding observed graphs). We develop an efficient learning algorithm to learn the encoder and the decoder, minimizing the Wasserstein distance between the model and data distributions. This algorithm takes the KL divergence of the graph distributions conditioned on different graphons as the underlying distance and leads to a reward-augmented maximum likelihood estimation. The graphon autoencoder provides a new paradigm to represent and generate graphs, which has good generalizability and transferability. © 2021, CC BY.

关键词： Graphic methods

A Semi-Supervised Generative Adversarial Network for Amodal Instance Segmentation of Piglets in Farrowing Pens

学校读者我要写书评

暂无评论

SSRN

SSRN 2022年

作者： Huang, Endai He, Zheng Mao, Axiu Xu, Weitao Ceballos, Maria Camila Parsons, Thomas D. Liu, Kai Department of Computer Science City University of Hong Kong Hong Kong Department of Infectious Diseases and Public Health City University of Hong Kong Hong Kong Faculty of Veterinary Medicine University of Calgary CalgaryAB Canada Swine Teaching and Research Center School of Veterinary Medicine University of Pennsylvania Kennett SquarePA United States

computer vision technology is applicable for the automated monitoring of animals. However, occlusions are common in complex animal housing environments, such as in farrowing pens in piggeries (where farrowing crates can obscure piglets), and this greatly limits the application of such technology. Amodal instance segmentation (AIS) can predict a complete mask of an occluded target and thus is a promising approach to solve such occlusion problems. However, AIS is usually trained on amodal datasets, which are so challenging to create that very few have been developed. To solve this problem, we devised a novel semi-supervised generative adversarial network for AIS, denoted "the AISGAN," which only requires a regular modal dataset. We adversarially trained a discriminator and a generator, i.e., trained the discriminator to determine whether a mask is occluded, and trained the generator to generate a realistic mask to fool the discriminator. We also added random occlusions onto unoccluded objects to automatically create amodal samples and used the corresponding segmentation loss during adversarial training. We found that the AISGAN achieved a mean Intersection of Union (mIoU) of 0.823, which was greater than the mIoUs of Mask RCNN, Raw, and Convex Hull (0.801, 0.780, and 0.778, respectively). As a semi-supervised method, the mIoU of our AISGAN was further enhanced (by 0.6%) when we fine-tuned it with unlabeled new data. The results demonstrate that the AISGAN can produce realistic masks of piglets, including details of their noses and legs, even under heavily occluded conditions. We also applied the AISGAN to determine the spatial distribution of piglets in a farrowing pen and the results demonstrated that our method is occlusion-resistant. Thus, the AISGAN is a promising tool for automated animal monitoring in complex housing environments. © 2022, The Authors. All rights reserved.

关键词： Generative adversarial networks

Development of software for calculating the results of medicinal substances bioequivalence 2

学校读者我要写书评

暂无评论

Development of software for calculating the results of medic...

2nd International Scientific Conference on Metrological Support of Innovative Technologies, ICMSIT II-2021

作者： Shalaginova, N.V. Mikhlyakova, E.A. Gribkov, D.N. Mikhailina, A.V. Lebedeva, E.V. Department of Applied Mathematics and Computer Science Vyatka State University Kirov Russia Secondary School with In-depth Study of Individual Subjects of Stulovo Kirov Russia Vyatka State University Kirov Russia Department of Informatics and Records Management Orel State Institute of Culture Orel Russia Department of Economics and Management Orel State Institute of Culture Orel Russia Department of Algebra and Mathematical Methods in Economy of Orel State University Named after I.S. Turgenev Orel Russia

International organizations have adopted and recognized drug standards, which should be guided by developers in the field of pharmacology. In practice, there is a problem: how to determine whether a reproduced drug sample really satisfies the world standard for its pharmacological action. It is required to implement an algorithm for checking and confirming the bioequivalence of drugs. The purpose of the study is to automate the verification of standards using an appropriate algorithm, i.e. to develop an application for calculating the results of medicinal substances bioequivalence. The methodology is based on the assumption that the identity in the sense of the created effect of the pharmacokinetic curves of the drug concentration in the blood versus time for the test drug and the standard means their therapeutic equivalence. Research methods include Python programming, use of libraries for data visualization;Visual Studio is an application development environment. The desired algorithm and requirements for the developed application are formulated in the results of the study, based on the study of theoretical issues of determining the medicinal substances bioequivalence. Finally, conclusions about the efficiency of the software are made and options for its improvement are proposed. © Published under licence by IOP Publishing Ltd.

关键词： Data visualization

Examinee Behavior Description Method Based on Image Captioning 2

学校读者我要写书评

暂无评论

Examinee Behavior Description Method Based on Image Captioni...

2nd China Symposium on Cognitive Computing and Hybrid Intelligence, CCHI 2019

作者： Ma, Miao Gao, Ziang Key Laboratory of Modern Teaching Technology Ministry of Education School of Computer Science Shaanxi Normal University Xi'an China

ISBN: (纸本)9781728140919

Aiming at the problem of missing report of abnormal situation caused by manual observation of examination room monitoring video, this paper introduces image description in deep learning to construct a data set 'Examinee Activity Captioning Dataset' suitable for examination scene, and proposes a method to describe examinee's behavior based on CNN+LSTM. This method employs a convolutional neural network to automatically extract the characteristics of examinee's behavior, and further generates sentences to describe examinee's behavior through long short-term memory network. The experimental results show that the proposed method can accurately describe five kinds of behaviors, including writing test papers, turning over test papers and looking around, which may play an important role in future smart examination room. © 2019 IEEE.

关键词： Long short-term memory

Multifractal wavelet dynamic mode decomposition modeling for marketing time series

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zidan, Mohamed Elshazli A. Ben Mabrouk, Anouar Ben Abdallah, Nidhal Alanazi, Tawfeeq M. Department of Mathematics Faculty of Science University of Tabuk King Faisal road Tabuk47512 Saudi Arabia Department of Mathematics Higher Institute of Applied Mathematics and Computer Science University of Kairouan Street of Assad Ibn Alfourat Kairouan3100 Tunisia Laboratory of Algebra Number Theory and Nonlinear Analysis Department of Mathematics Faculty of Sciences University of Monastir Avenue of the Environment Monastir5000 Tunisia Department of Quantitative Methods Faculty of Economic Sciences and Management University of Monastir Sidi Messaoud Hiboun Mahdia 5111 Tunisia Laboratoire THEMA de l'ESCT Tunis Université de Carthage Campus Universitaire de Manouba Mannouba Mannouba 2010 Tunisia Department of Marketing Faculty of Business Administration University of Tabuk King Faisal road Tabuk47512 Saudi Arabia

Marketing is the way we ensure our sales are the best in the market, our prices the most accessible, and our clients satisfied, thus ensuring our brand has the widest distribution. This requires sophisticated and advanced understanding of the whole related network. Indeed, marketing data may exist in different forms such as qualitative and quantitative data. However, in the literature, it is easily noted that large bibliographies may be collected about qualitative studies, while only a few studies adopt a quantitative point of view. This is a major drawback that results in marketing science still focusing on design, although the market is strongly dependent on quantities such as money and time. Indeed, marketing data may form time series such as brand sales in specified periods, brand-related prices over specified periods, market shares, etc. The purpose of the present work is to investigate some marketing models based on time series for various brands. This paper aims to combine the dynamic mode decomposition and wavelet decomposition to study marketing series due to both prices, and volume sales in order to explore the effect of the time scale on the persistence of brand sales in the market and on the forecasting of such persistence, according to the characteristics of the brand and the related market competition or competitors. Our study is based on a sample of Saudi brands during the period 22 November 2017 to 30 December *** Codes 65T60, 91B84, 91B55, 37M10 © 2024, CC0.

关键词： Dynamic mode decomposition

Storm Surge Modeling as an Application of Local Time-stepping in MPAS-Ocean

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lilly, Jeremy R. Capodaglio, Giacomo Petersen, Mark R. Brus, Steven R. Engwirda, Darren Higdon, Robert L. Oregon State University Department of Mathematics CorvallisOR97331-4605 United States Computational Physics and Methods Group Los Alamos National Laboratory NM87545 United States Fluid Dynamics and Solid Mechanics Group Los Alamos National Laboratory NM87545 United States Mathematics and Computer Science Division Argonne National Laboratory IL60439 United States

This paper presents the first scientific application of local time-stepping (LTS) schemes in the Model for Prediction Across Scales-Ocean (MPAS-O). We use LTS schemes in a single-layer, global ocean model that predicts the storm surge around the eastern coast of the United States during Hurricane Sandy. The variable-resolution meshes used are of unprecedentedly high resolution in MPAS-O, containing cells as small as 125 meters wide in Delaware Bay. It is shown that a particular, third-order LTS scheme (LTS3) produces sea-surface height (SSH) solutions that are of comparable quality to solutions produced by the classical four-stage, fourth-order Runge-Kutta method (RK4) with a uniform time step on the same meshes. Furthermore, LTS3 is up to 35% faster in the best cases, showing that LTS schemes are viable for use in MPAS-O with the added benefit of substantially less computational cost. The results of these performance experiments inform us of the requirements for efficient mesh design for LTS schemes. In particular, we see that for LTS to be efficient on a given mesh, it is important to have enough cells using the coarse time-step relative to those using the fine time-step, typically at least 1:5. © 2022, CC BY-SA.

关键词： Hurricanes

Creation of a software and hardware product of a real-time system for collecting, accounting and managing data transmission of an intelligent transport system in context of the IoT 3

学校读者我要写书评

暂无评论

Creation of a software and hardware product of a real-time s...

3rd International Scientific Conference on Applied Physics, Information Technologies and Engineering, APITECH-III 2021

作者： Zolkin, A.L. Munister, V.D. Lavrov, E.A. Aygumov, K.G. Saradzheva, O.V. Computer and Information Sciences Department Povolzhskiy State University of Telecommunications and Informatics 23 L.Tolstogo Street Samara443010 Russia Department of Mathematical Methods and Computer-Aided Design Private Educational Institution Donetsk Academy of Transport 7 Dzerzhinsky Street Donetsk83086 Ukraine Department of Enterprise Economics State Educational Institution of Higher Professional Education Donetsk National Technical University 2 Shibankova Street Donetsk region Pokrovsk85300 Ukraine Computer Science Department Sumy State University 2 Rymskogo-Korsakova Street Sumy40007 Ukraine FSBEI HE «Dagestan State Technical University» 70 I. Shamyl Ave. Makhachkala367030 Russia Economic Security Controlling and Audit Department Russian State University named after A.N. Kosygin 33 Sadovnicheskaya Street Moscow115035 Russia

Some aspects of the functioning of modern microcontrollers of the Internet of Things in conditions that are close to real-time systems are reviewed in the article. Attention is paid to the aspects of the theory of physical data transmission, the significance of the delay metrics in the data transmission path is substantiated and emphasized. These delays (in view of the generalization of measurement results) determine the control accuracy and controllability of the data processing system as a whole, and also affect the reliability of the results. The process of formalization of the architectural template of a data collecting and accounting system for a control device (which is widespread in intelligent transport systems and the Internet of things) is described. The practical application of the approach in synchronous control through the implementation of a web interface and a control language in a microprocessor system (which can be possible at low traffic transmission rates) is substantiated. In conclusion, a generalization of the scope of application of the developed specialized computer system in transport field is given. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Real time systems

An efficient polynomial-time approximation scheme for parallel multi-stage open shops

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Dong, Jianming Jin, Ruyan Lin, Guohui Su, Bing Tong, Weitian Xu, Yao Department of Mathematics Zhejiang Sci-Tech University Zhejiang Hangzhou310018 China Public course teaching and Research Office Taizhou Vocational and Technical College Zhejiang Taizhou318000 China Department of Computing Science University of Alberta EdmontonABT6G 2E8 Canada School of Economics and Management Xi'an Technological University Xi'An China Department of Computer Science Georgia Southern University StatesboroGA30458 United States

Various new scheduling problems have been arising from practical production processes and spawning new research areas in the scheduling field. We study the parallel multi-stage open shops problem, which generalizes the classic open shop scheduling and parallel machine scheduling problems. Given m identical k-stage open shops and a set of n jobs, we aim to process all jobs on these open shops with the minimum makespan, i.e., the completion time of the last job, under the constraint that job preemption is not allowed. We present an efficient polynomial-time approximation scheme (EPTAS) for the case when both m and k are constant. The main idea for our EPTAS is the combination of several categorization, scaling, and linear programming rounding techniques. Jobs and/or operations are first scaled and then categorized carefully into multiple types so that different types of jobs and/or operations are scheduled appropriately without increasing the makespan too much. Copyright © 2022, The Authors. All rights reserved.

关键词： Linear programming

Model for Analysis of High-Frequency Modulated Random Signals

学校读者我要写书评

暂无评论

Model for Analysis of High-Frequency Modulated Random Signal...

International Conference on Advanced computer Information Technologies (ACIT)

作者： Ihor Javorskyj Roman Yuzefovych Oleh Lychak Pavlo Semenov Roman Sliepko Yulia Romanyshyn Department of Methods and Facilities for Acquisition and Processing Diagnostic Signals Karpenko Physico-mechanical Institute of NAS of Ukraine Lviv Ukraine Institute of Telecommunication and Computer Sciences Bydgoszcz University of Science and Technology Bydgoszcz Poland Department of Applied Mathematics Lviv Polytechnic National University Lviv Ukraine Department of Hoisting and Transport Machines and Engineering of Port Technological Equipment Odesa National Maritime University Odesa Ukraine Department of Records Management and Information Activity Ivano-Frankivsk National Technical University of Oil and Gas Ivano-Frankivsk Ukraine

The use of the Hilbert transform for the analysis of periodically non-stationary random signals (PNRSs), whose carrier harmonics are modulated by jointly stationary high-frequency random processes is discussed. A representation of the signal in the form of a superposition of high-frequency components is obtained and it is shown that these components are jointly periodically non-stationary random processes. The properties of the band-pass filtered signals are examined, and it is shown that band-pass filtering can reduce both the number of signal variance cyclic harmonics and their amplitudes. We show that it is possible to extract the quadratures of narrow-band high-frequency modulation processes using the Hilbert transform.

关键词：