检索结果-内蒙古大学图书馆

Automatic facial expression recognition in an image sequence using conditional random field

学校读者我要写书评

暂无评论

Automatic facial expression recognition in an image sequence...

International Symposium on Computational Intelligence and Informatics

作者： Mohamad Roshanzamir Mahdi Roshanzamir Abdolreza Mirzaei Mohammad Tayarani Darbandy Afshin Shoeibi Roohallah Alizadehsani Fahime Khozeimeh Abbas Khosravi Department of Computer Engineering Fasa University Fasa Iran Department of Electrical and Computer Engineering University of Tabriz Tabriz Iran Department of Electrical and Computer Engineering Isfahan University of Technology Isfahan Iran School of Architecture Islamic Azad University Taft Taft Iran Internship in Health Data Analytics Program AI-enabled Processes (AIP) Research Centre Macquarie University Sydney Australia Institute for Intelligent Systems Research and Innovation (IISRI) Deakin University Victoria Australia

ISBN: (纸本)9798350398830

Facial expression recognition is one of the fields that nowadays has attracted the attention of many researchers. It is possible to automate facial expression recognition using artificial intelligence methods. This will be of great help to researchers, especially in areas such as psychology. Automatic facial recognition can be derived from a static image of facial expression, but a better and more efficient way to do this is through a sequence of images. In this paper, a new method is proposed to automatically detect facial expressions from a sequence of images. Each sequence of facial images begins with a face neutral state and ends with one of the six main emotions. Motion vectors are extracted from the sequence using optical flow algorithm. These vectors are then used to train the conditional random field and finally to automatically determine the emotion. In this paper, in addition to the basic conditional random field, the hidden dynamic conditional random field is also investigated. Additionally, the effect of changing some parameters of these algorithms such as different optimization methods has been investigated. Given that a facial expression is recognized during a sequence of images, random field-based methods can be used for efficient classification of facial expressions reaching accuracy (more than 90%) competitive with the best existing methods for facial expression recognition.

关键词： Image recognition Mechatronics Face recognition Heuristic algorithms Psychology Optimization methods Feature extraction

A Systematic Review of Generative AI for Teaching and Learning Practice

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ogunleye, Bayode Zakariyyah, Kudirat Ibilola Ajao, Oluwaseun Olayinka, Olakunle Sharma, Hemlata School of Architecture Technology & Engineering University of Brighton BrightonBN2 4GJ United Kingdom Department of Computing & Mathematics Manchester Metropolitan University ManchesterM1 5GD United Kingdom School of Computer Science The University of Sheffield SheffieldS1 4DP United Kingdom Department of Computing Sheffield Hallam University SheffieldS1 2NU United Kingdom

The use of generative artificial intelligence (GenAI) in academia is a subjective and hotly debated topic. Currently, there are no agreed guidelines towards the usage of GenAI systems in higher education (HE) and, thus, it is still unclear how to make effective use of the technology for teaching and learning practice. This paper provides an overview of the current state of research on GenAI for teaching and learning in HE. To this end, this study conducted a systematic review of relevant studies indexed by Scopus, using the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. The search criteria revealed a total of 625 research papers, of which 355 met the final inclusion criteria. The findings from the review showed the current state and the future trends in documents, citations, document sources/authors, keywords, and co-authorship. The research gaps identified suggest that while some authors have looked at understanding the detection of AI-generated text, it may be beneficial to understand how GenAI can be incorporated into supporting the educational curriculum for assessments, teaching, and learning delivery. Furthermore, there is a need for additional interdisciplinary, multidimensional studies in HE through collaboration. This will strengthen the awareness and understanding of students, tutors, and other stakeholders, which will be instrumental in formulating guidelines, frameworks, and policies for GenAI usage. © 2024, CC BY.

关键词： Artificial intelligence

A Generalized Density Dissipation for Weakly-compressible SPH

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Bo Xue Cai, Zhi Wen Zhao, Pei Dong Xu, Xiao Yang Chan, Tak Shing Yu, Peng Guangdong Provincial Key Laboratory of Turbulence Research and Applications Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Shenzhen518055 China Department of Mathematics University of Oslo Oslo0851 Norway China Ship Scientific Research Center Wuxi214082 China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China School of Naval Architecture and Ocean Engineering Dalian University of Technology Dalian116024 China School of Computer Science and Technology Xi’an University of Science and Technology Xi’an710054 China Center for Complex Flows and Soft Matter Research Southern University of Science and Technology Shenzhen518055 China

The weakly compressible Smoothed Particle Hydrodynamics (SPH) is known to suffer from the pressure oscillation, which would undermine the simulation stability and accuracy. To address this issue, we propose a generalized density dissipation scheme suitable for both single-phase and multiphase flow simulations. Our approach consists of two components. Firstly, we replace the basic density dissipation with the density increment dissipation to enable numerical dissipation crossing the interfaces of different fluids in multiphase flow. Secondly, based on the dissipation volume conservation, we utilize dissipation volume correction factor (VCF) to stabilize the simulations for multiphase flows with large density ratio. We demonstrate the accuracy, stability, and robustness of our method through four three-dimensional benchmarks, i.e., the sloshing under external excitations, the single and double bubbles rising, Rayleigh-Taylor instability, and Kelvin-Helmholtz instability. Additionally, our study reveals the relationship between SPH with the density dissipation and the approximate Riemann solver. Copyright © 2023, The Authors. All rights reserved.

关键词： Multiphase flow

A Generalized Density Dissipation for Weakly-Compressible Sph

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Zheng, Bo Xue Cai, Zhi Wen Zhao, Pei Dong Xu, Xiao Yang Chan, Tak Shing Yu, Peng Department of Mathematics University of Oslo Oslo0851 Norway Guangdong Provincial Key Laboratory of Turbulence Research and Applications Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Shenzhen518055 China China Ship Scientific Research Center Wuxi214082 China School of Mechanical Engineering Shanghai Jiao Tong University Shanghai200240 China School of Naval Architecture and Ocean Engineering Dalian University of Technology Dalian116024 China School of Computer Science and Technology Xi’an University of Science and Technology Xian710054 China Center for Complex Flows and Soft Matter Research Southern University of Science and Technology Shenzhen518055 China

Weakly compressible Smoothed Particle Hydrodynamics (SPH) is known to suffer from numerical pressure noise, which can significantly undermine simulation stability and accuracy. In response, this study introduces a novel density dissipation scheme aimed at suppressing such unphysical noise. The proposed scheme overcomes the limitations of conventional density dissipation schemes, which are ineffective at fluid interfaces in multiphase flow simulations. As a result, the novel scheme is generally applicable to the entire computational domain, encompassing both single-phase flow and multiphase flow. This advancement is achieved through two key components. Firstly, the traditional density dissipation is replaced with a density increment dissipation approach that enables dissipation to cross interfaces separating different fluids. Secondly, based on dissipation volume conservation, we employ a dissipation volume correction factor (VCF) to stabilize simulations characterized by large density ratios. We demonstrate the accuracy, stability, and robustness of our method through four three-dimensional benchmarks: sloshing under external excitations, the rising of single and double bubbles, Rayleigh-Taylor instability, and Kelvin-Helmholtz instability. Additionally, this study reveals the relationship between SPH utilizing density dissipation and the approximate Riemann solver. © 2023, The Authors. All rights reserved.

关键词： Multiphase flow

Unit Test Generation in a Cluster Using Parallel Computations and Control Flow Graph Analysis 15

学校读者我要写书评

暂无评论

Unit Test Generation in a Cluster Using Parallel Computation...

15th IEEE International Scientific and Technical Conference on computer Sciences and Information Technologies, CSIT 2020

作者： Bazylevych, Roman Czarnul, Pawel Franko, Andrii Ukraine University of Information Technology and Management Department of Software Lviv Polytechnic National University Lviv Rzeszow Poland University of Technology Faculty of Electronics Telecommunications and Informatics Gdansk Department of Computer Architecture Gdansk Poland Lviv Polytechnic National University Department of Software Lviv Ukraine

ISBN: (纸本)9781728174433

A parallelization approach implemented in a cluster with a shared file system has been considered in the paper. The study presents metrics of parallelization for running tasks of C language nested loops analysis in a cluster and subsequent unit test code generation for the given data. The parallelization method used the shared file system and ran in a decentralized mode without a master node. The results are useful for testing the integration of third-party components and negative testing of safety-critical systems. © 2020 IEEE.

关键词： C (programming language)

YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multi-Branch Feature Interaction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Lin, Ziyu Wu, Yunfan Ma, Yuhang Chen, Junzhou Zhang, Ronghui Wu, Jiaming Yin, Guodong Lin, Liang Guangdong Key Laboratory of Intelligent Transportation System School of intelligent systems engineering Sun Yat-sen University Guangzhou510275 China Department of Architecture and Civil Engineering Chalmers University of Technology Sven Hultins gata 6 GothenburgSE-412 96 Sweden School of Mechanical Engineering Southeast University Nanjing211189 China School of Computer Science and Engineering Sun Yat-sen University Guangzhou510275 China

Detecting traffic signs effectively under low-light conditions remains a significant challenge. To address this issue, we propose YOLO-LLTS, an end-to-end real-time traffic sign detection algorithm specifically designed for low-light environments. Firstly, we introduce the High-Resolution Feature Map for Small Object Detection (HRFM-TOD) module to address indistinct small-object features in low-light scenarios. By leveraging high-resolution feature maps, HRFM-TOD effectively mitigates the feature dilution problem encountered in conventional PANet frameworks, thereby enhancing both detection accuracy and inference speed. Secondly, we develop the Multi-branch Feature Interaction Attention (MFIA) module, which facilitates deep feature interaction across multiple receptive fields in both channel and spatial dimensions, significantly improving the model’s information extraction capabilities. Finally, we propose the Prior-Guided Enhancement Module (PGFE) to tackle common image quality challenges in low-light environments, such as noise, low contrast, and blurriness. This module employs prior knowledge to enrich image details and enhance visibility, substantially boosting detection performance. To support this research, we construct a novel dataset, the Chinese Nighttime Traffic Sign Sample Set (CNTSSS), covering diverse nighttime scenarios, including urban, highway, and rural environments under varying weather conditions. Experimental evaluations demonstrate that YOLO-LLTS achieves state-of-the-art performance, outperforming the previous best methods by 2.7% mAP50 and 1.6% mAP50:95 on TT100K-night, 1.3% mAP50 and 1.9% mAP50:95 on CNTSSS, and achieving superior results on the CCTSDB2021 dataset. Moreover, deployment experiments on edge devices confirm the real-time applicability and effectiveness of our proposed approach. Copyright © 2025, The Authors. All rights reserved.

关键词： Feature extraction

Robotic additive construction of bar structures: Unified sequence and motion planning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Huang, Yijiang Garrett, Caelan R. Ting, Ian Parascho, Stefana Mueller, Caitlin T. Building Technology Program Department of Architecture Massachusetts Institute of Technology CambridgeMA02139 United States Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology CambridgeMA02139 United States Princeton University CREATE Laboratory School of Architecture PrincetonNJ08544 United States

Additive robotic construction of building-scale discrete bar structures, such as trusses and space frames, is increasingly attractive due to the potential improvements in efficiency, safety, and design possibilities. However, programming complex robots, such as manipulators with seven degrees of freedom, to successfully complete construction tasks can be tedious, challenging, or impossible for a human to do manually. Namely, the structure must be constructed in a sequence that preserves structural properties, such as stiffness, at each step. At the same time, this sequence must allow for the robot to precisely manipulate elements within the in-progress structure while respecting geometric constraints that, for example, ensure the robot does not collide with what it has built. In this work, we present an automated and newly generalized planning approach for jointly finding a construction sequence and robot motion plan for additive construction that satisfies these requirements. Our approach can be applied in a variety of additive construction processes, and we demonstrate it specifically on spatial extrusion and discrete bar assembly in this paper. We demonstrate the effectiveness of our approach on several simulated and real-world extrusion and assembly tasks, including a human-scale physical prototype, for which our algorithm is deployed for the first time to plan the assembly of a complicated double tangent bar system design. © 2021, CC BY.

关键词： Additives

Joint high-resolution feature learning and vessel-shape aware convolutions for efficient vessel segmentation

学校读者我要写书评

暂无评论

computers in Biology and Medicine 2025年 191卷 109982-109982页

作者： Zhang, Xiang Zhu, Qiang Hu, Tao Guo, Song Bian, Genqing Dong, Wei Hong, Rao Lin, Xia Ling Wu, Peng Zhou, Meili Yan, Qingsen Mohi-ud-din, Ghulam Ai, Chen Li, Zhou College of Information and Control Engineering Xi'an University of Architecture and Technology Xi'an China Shaanxi Provincial Key Lab of Bigdata of Energy and Intelligence Processing School of Physics and Electronic Information Yanan University Yanan China School of Computer Science and Engineering Northwestern Polytechnical University Xi'an China School of Software Nanchang University Nanchang China School of Cyber Security Zhejiang University Hangzhou China Department of Basic Education and Research Jiangxi Police College Nanchang China Northwestern Polytechnical University China

Clear imagery of retinal vessels is one of the critical shreds of evidence in specific disease diagnosis and evaluation, including sophisticated hierarchical topology and plentiful-and-intensive capillaries. In this work, we propose a new topology- and shape-aware model named Multi-branch Vessel-shaped Convolution Network (MVCN) to adaptively learn high-resolution representations from retinal vessel imagery and thereby capture high-quality topology and shape information thereon. Two steps are involved in our pipeline. The former step is proposed as Multiple High-resolution Ensemble Module (MHEM) to enhance high-resolution characteristics of retinal vessel imagery via fusing scale-invariant hierarchical topology thereof. The latter is a novel vessel-shaped convolution that captures the retinal vessel topology to emerge from unrelated fundus structures. Moreover, our MVCN of separating such topology from the fundus is a dynamical multiple sub-label generation via using epistemic uncertainty, instead of manually separating raw labels to distinguish definitive and uncertain vessels. Compared to other existing methods, our method achieves the most advanced AUC values of 98.31%, 98.80%, 98.83%, and 98.65%, and the most advanced ACC of 95.83%, 96.82%, 97.09%,and 96.66% in DRIVE, CHASE_DB1, STARE, and HRF datasets. We also employ correctness, completeness, and quality metrics to evaluate skeletal similarity. Our method's evaluation metrics have doubled compared to previous methods, thereby demonstrating the effectiveness thereof. © 2025 Elsevier Ltd

关键词： Ophthalmology

A Smart Capacity Enhancement and Estimation Model for Hybrid Buildings by using Light Weight Deep Learning Model

学校读者我要写书评

暂无评论

A Smart Capacity Enhancement and Estimation Model for Hybrid...

Disruptive Technologies (ICDT), International Conference on

作者： Senthil Kumar Nageswara Rao Atyam Khadar Nawas K Shashank Awasthi M. Kotteeswaran K. S. Thirunavukkarasu KL School of Architecture Koneru Lakshmanan Education Foundation Guntur Andhra Pradesh India Electrical and Electronics Department CMR Institute of Technology Bengaluru Karnataka India School of Computing Science and Engineering Vellore Institute of Technolog Chennai Tamil Nadu India Department of Computer Science and Engineering GL Bajaj Institute of Technology and Management Greater Noida Uttar Pradesh India School of Management and Commerce Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai Tamil Nadu India School of Computing Science Vels Institute of Science Technology and Advanced Studies (VISTAS) Pallavaram Chennai Tamil Nadu India

Generally, for the buildings constructed in our areas, the conventional foundation known as 'shallow', i.e. from the ground level downwards, is set up in three dimensions such as length, width and depth. Foundations are not the same for all types of structures. The size and structure of the foundation varies depending on the nature of the prevailing soil, ground water level of the plot, type of building, and total load of the structure. In this paper an innovation estimation model was proposed based on light weigth deep learning technique. The proposed model introduces capacity estimation and energy efficiency plans and designs. These are all relating to commercial buildings, craft facilities and mass housing projects to enable design, construction. It also maintains the buildings under minimum energy consumption without stressing the operation of buildings. The health and comfort of the occupants are establishing compliance standards and ensure the maximum standards for energy efficiency in the plans or designs of commercial buildings. The proposed model also focuses the capacity estimation and energy efficiency programs beyond maximum standards.

关键词：