检索结果-内蒙古大学图书馆

Image Dehazing Algorithm Based on Particle Swarm Optimization for Sky Region Segmentation

学校读者我要写书评

暂无评论

Image Dehazing Algorithm Based on Particle Swarm Optimizatio...

International Symposium on Distributed Computing and Applications to Business, Engineering and science (DCABES)

作者： Hao Zhou Changjiu Yuan Hongbo Pan Yue Yang Ziyan Wang Xiangyang Chen College of Computer and Information Science Southwest University Chongqing China College of Big Data and Artificial Intelligence Chizhou University Chizhou Anhui China College of Big Data and Intelligent Engineering Chongqing College of International Business and Economics Chongqing China Basic Teaching Department Anqing Medical College AnQing Anhui China

ISBN: (纸本)9781665454636

The well-known Dark Channel Prior (DCP) dehazing algorithm does not work well in the sky area, thus, we propose an image dehazing method for segmented sky regions based on Particle Swarm Optimization (PSO). First, we apply PSO to the Otsu segmentation method to accurately segment sky and non-sky regions in the hazy image. Second, the transmission of non-sky regions is derived by DCP. A transmission compensation method is proposed to obtain the transmission for the sky regions. The transmission is then refined by gradient-domain guided filtering. Finally, the restored haze-free image is obtained through the Atmospheric Scattering Model (ASM). Quantitative and qualitative experiments show that the proposed method has a better dehazing effect, especially for hazy images with the sky areas.

关键词： Image segmentation Filtering Atmospheric modeling Scattering Image restoration Particle swarm optimization Distributed computing

Data Mining of Assessments to Generate Learner Remediation Teams: Method, Efficacy, and Perceptions in an Undergraduate Engineering Pilot Offering

学校读者我要写书评

暂无评论

Journal of Educational Technology Systems 2020年第4期48卷 464 - 492页

作者： Ronald F. DeMara Salih S. Bacanli Neda Bidoki Jun Xu Edwin Nassiff Julie Donnelly Damla Turgut Department of Electrical and Computer Engineering University of Central Florida Department of Computer Science University of Central Florida Karen L. Smith Faculty Center for Teaching and Learning University of Central Florida Orlando FL USA

This research developed an approach to integrate the complementary benefits of digitized assessments and peer learning. Its basic premise and associated hypotheses are that by using student assessments of correct and incorrect quiz answers using a fine-grained resolution to pair them into remediation peer-learning cohorts is an effective means of learning. Delivered and scored in a computer-based testing center, the assessment of digitized formative quizzes paired students whose scores indicated a different knowledge skill level so that by the end of the same week as the quiz, the paired students cooperatively took an in-class quiz during a remediation session to determine if there were any learning improvements. This research article discusses this research approach and presents the findings.

关键词： learning analytics computer-based testing peer teaching and learning

Insights into the structural properties of SARS-CoV-2 main protease

学校读者我要写书评

暂无评论

Current Research in Structural Biology 2022年 4卷 349-355页

作者： Akbayrak, Ibrahim Yagiz Caglayan, Sule Irem Kurgan, Lukasz Uversky, Vladimir N. Coskuner-Weber, Orkid Materials Sciences and Technologies Turkish-German University Sahinkaya Caddesi No. 106 Beykoz Istanbul 34820 Turkey Molecular Biotechnology Turkish-German University Sahinkaya Caddesi No. 106 Beykoz Istanbul 34820 Turkey Department of Computer Science Virginia Commonwealth University Richmond 23284 VA United States Molecular Medicine USF Health Byrd Alzheimer's Research Institute Morsani College of Medicine University of South Florida Tampa FL United States Laboratory of New Methods in Biology Institute for Biological Instrumentation of the Russian Academy of Sciences Federal Research Center “Pushchino Scientific Center for Biological Research of the Russian Academy of Sciences” Pushchino Russian Federation

SARS-CoV-2 is the infectious agent responsible for the coronavirus disease since 2019, which is the viral pneumonia pandemic worldwide. The structural knowledge on SARS-CoV-2 is rather limited. These limitations are also applicable to one of the most attractive drug targets of SARS-CoV-2 proteins – namely, main protease M^pro, also known as 3C-like protease (3CL^pro). This protein is crucial for the processing of the viral polyproteins and plays crucial roles in interfering viral replication and transcription. In fact, although the crystal structure of this protein with an inhibitor was solved, M^pro conformational dynamics in aqueous solution is usually studied by molecular dynamics simulations without special sampling techniques. We conducted replica exchange molecular dynamics simulations on M^pro in water and report the dynamic structures of M^pro in an aqueous environment including root mean square fluctuations, secondary structure properties, radius of gyration, and end-to-end distances, chemical shift values, intrinsic disorder characteristics of M^pro and its active sites with a set of computational tools. The active sites we found coincide with the currently known sites and include a new interface for interaction with a protein partner. © 2022 The Authors

关键词： Dynamics Replica exchange MD simulations SARS-CoV-2 main protease

Wavefronts for degenerate diffusion-convection reaction equations with sign-changing diffusivity

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Berti, Diego Corli, Andrea Malaguti, Luisa Department of Sciences and Methods for Engineering University of Modena and Reggio Emilia Italy Department of Mathematics and Computer Science University of Ferrara Italy

We consider in this paper a diffusion-convection reaction equation in one space dimension. The main assumptions are about the reaction term, which is monostable, and the diffusivity, which changes sign once or even more than once;then, we deal with a forward-backward parabolic equation. Our main results concern the existence of globally defined traveling waves, which connect two equilibria and cross both regions where the diffusivity is positive and regions where it is negative. We also investigate the monotony of the profiles and show the appearance of sharp behaviors at the points where the diffusivity degenerates. In particular, if such points are interior points, then the sharp behaviors are new and *** Codes 35K65 (Primary) 35C07, 34B40, 35K57 (Secondary) © 2020, CC BY.

关键词： Diffusion

Data-driven, structure-preserving approximations to entropy-based moment closures for kinetic equations

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Porteous, William A. Paul Laiu, M. Hauck, Cory D. Department of Mathematics University of Texas at Austin AustinTX78712 United States Multiscale Methods and Dynamics Group Computer Science and Mathematics Division Oak Ridge National Laboratory Oak RidgeTN37831 United States

We present a data-driven approach to construct entropy-based closures for the moment system from kinetic equations. The proposed closure learns the entropy function by fitting the map between the moments and the entropy of the moment system, and thus does not depend on the space-time discretization of the moment system and specific problem configurations such as initial and boundary conditions. With convex and C2 approximations, this data-driven closure inherits several structural properties from entropy-based closures, such as entropy dissipation, hyperbolicity, and H-Theorem. We construct convex approximations to the Maxwell-Boltzmann entropy using convex splines and neural networks, test them on the plane source benchmark problem for linear transport in slab geometry, and compare the results to the standard, optimization-based MN closures. Numerical results indicate that these data-driven closures provide accurate solutions in much less computation time than the MN closures. © 2021, CC BY.

关键词： Kinetic energy

Hackers vs. Security: Attack-Defence Trees as Asynchronous Multi-agent Systems 22nd

学校读者我要写书评

暂无评论

Hackers vs. Security: Attack-Defence Trees as Asynchronous M...

22nd International Conference on Formal Engineering methods, ICFEM 2020

作者： Arias, Jaime Budde, Carlos E. Penczek, Wojciech Petrucci, Laure Sidoruk, Teofil Stoelinga, Mariëlle LIPN CNRS UMR 7030 Université Sorbonne Paris Nord Sorbonne Paris Cité Villetaneuse France Formal Methods and Tools University of Twente Enschede Netherlands Institute of Computer Science Polish Academy of Sciences Warsaw Poland Department of Software Science Radboud University Nijmegen Netherlands Warsaw University of Technology Warsaw Poland

ISBN: (纸本)9783030634056

Attack-Defence Trees (ADTrees) are a well-suited formalism to assess possible attacks to systems and the efficiency of counter-measures. This paper extends the available ADTree constructs with reactive patterns that cover further security scenarios, and equips all constructs with attributes such as time and cost to allow for quantitative analyses. We model ADTrees as (an extension of) Asynchronous Multi-Agents Systems: EAMAS. The ADTree–EAMAS transformation allows us to quantify the impact of different agents configurations on metrics such as attack time. Using EAMAS also permits parametric verification: we derive constraints for property satisfaction, e.g. the maximum time a defence can take to block an attack. Our approach is exercised on several case studies using the Uppaal and IMITATOR tools. We developed the open-source tool adt2amas implementing our transformation. © 2020, Springer Nature Switzerland AG.

关键词： Multi agent systems

Shooting-projection method for a small object moving under the influence of a force 10

学校读者我要写书评

暂无评论

Shooting-projection method for a small object moving under t...

202 10th International Conference on Engineering Mathematics and Physics, ICEMP 2021

作者： Filipov, S.M. Faragó, I. Avdzhieva, A. Department of Computer Science Faculty of Chemical and System Engineering University of Chemical Technology and Metallurgy 8 St. Kliment Ohridski Blvd. Sofia1756 Bulgaria Department of Differential Equations Institute of Mathematics Budapest University of Technology and Economics MTA-ELTE Research Group Egry József u. 1 Budapest1111 Hungary Department of Numerical Methods Faculty of Mathematics and Informatics Sofia University St. Kliment Ohridski 5 James Bourchier Blvd. Sofia1164 Bulgaria

We consider a small object in 3D moving under the influence of a force that may depend explicitly on time, on the position of the object, and on its velocity. The equations of motion of classical mechanics are assumed to hold. If the position of the object is specified at some initial and some final time, obtaining the trajectory of the object requires the solution of a two-point boundary value problem. To solve the problem various numerical technics can be applied. This paper extends the recently proposed shooting-projection method to 3D. We introduce a Lagrangian from which, applying the principle of least action, the projection trajectory is derived. Analysis of the action reveals the meaning of the projection trajectory. Using the shooting-projection method, the considered two-point boundary value problem is solved for the case of a projectile motion in the presence of air resistance and wind. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Trajectories

Occlusion-Resistant Instance Segmentation of Piglets in Farrowing Pens Using Center Clustering Network

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Huang, Endai Mao, Axiu Hou, Junhui Wu, Yongjian 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 Department of Production Animal Health 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 enables the development of new approaches to monitor the behavior, health, and welfare of animals. Instance segmentation is a high-precision method in computer vision for detecting individual animals of interest. This method can be used for in-depth analysis of animals, such as examining their subtle interactive behaviors, from videos and images. However, existing deep-learning-based instance segmentation methods have been mostly developed based on public datasets, which largely omit heavy occlusion problems;therefore, these methods have limitations in real-world applications involving object occlusions, such as farrowing pen systems used on pig farms in which the farrowing crates often impede the sow and piglets. In this paper, we adapt a Center Clustering Network originally designed for counting to achieve instance segmentation, dubbed as CClusnet-Inseg. Specifically, CClusnet-Inseg uses each pixel to predict object centers and trace these centers to form masks based on clustering results, which consists of a network for segmentation and center offset vector map, Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm, Centers-to-Mask (C2M), and Remain-Centers-to-Mask (RC2M) algorithms. In all, 4,600 images were extracted from six videos collected from three closed and three half-open farrowing crates to train and validate our method. CClusnet-Inseg achieves a mean average precision (mAP) of 84.1 and outperforms other methods compared in this study. We conduct comprehensive ablation studies to demonstrate the advantages and effectiveness of core modules of our method. In addition, we apply CClusnet-Inseg to multi-object tracking for animal monitoring, and the predicted object center that is a conjunct output could serve as an occlusion-resistant representation of the location of an object. Copyright © 2022, The Authors. All rights reserved.

关键词： computer vision

Who Said What (WSW 2.0)? Enhanced Automated Analysis of Preschool Classroom Speech

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Sun, Anchen Feng, Tiantian Gutierrez, Gabriela Londono, Juan J. Xu, Anfeng Elbaum, Batya Narayanan, Shrikanth Perry, Lynn K. Messinger, Daniel S. Department of Electrical and Computer Engineering University of Miami Coral GablesFL United States Department of Computer Science Viterbi School of Engineering University of Southern California Los AngelesCA United States Department of Psychology University of Miami Coral GablesFL United States Department of Teaching Learning University of Miami Coral GablesFL United States

This paper introduces an automated framework (WSW 2.0) for analyzing vocal interactions in preschool classrooms, enhancing both accuracy and scalability through the integration of wav2vec2-based speaker classification and Whisper (large-v2 and large-v3) speech transcription. A total of 235 minutes of audio recordings (160 minutes from 12 children and 75 minutes from 5 teachers), were used to compare system outputs to expert human annotations. WSW 2.0 achieves a weighted F1 score of .845, accuracy of .846, and an error-corrected kappa of .672 for speaker classification (child vs. teacher). Transcription quality is moderate to high with word error rates of .119 for teachers and .238 for children. WSW 2.0 exhibits relatively high absolute agreement intraclass correlations (ICC) with expert transcriptions for a range of classroom language features. These include teacher and child mean utterance length, lexical diversity, question asking, and responses to questions and other utterances, which show absolute agreement intraclass correlations between .64 and .98. To establish scalability, we apply the framework to an extensive dataset spanning two years and over 1,592 hours of classroom audio recordings, demonstrating the framework’s robustness for broad real-world applications. These findings highlight the potential of deep learning and natural language processing techniques to revolutionize educational research by providing accurate measures of key features of preschool classroom speech, ultimately guiding more effective intervention strategies and supporting early childhood language development. © 2025, CC BY-NC-ND.

关键词： Natural language processing systems