检索结果-内蒙古大学图书馆

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion and Intensity of Emotion Classes from Meme Images using Single and Multi Modalities 1

学校读者我要写书评

暂无评论

HCILab at Memotion 2.0 2022: Analysis of Sentiment, Emotion ...

1st Workshop on Multimodal Fact-Checking and Hate Speech Detection, DE-FACTIFY 2022

作者： Nguyen, Thanh Tin Pham, Nhat Truong Nguyen, Ngoc Duy Nguyen, Hai Nguyen, Long H. Kim, Yong-Guk Human Computer Interaction Lab Department of Computer Engineering Sejong University Seoul Korea Republic of Division of Computational Mechatronics Institute for Computational Science Ton Duc Thang University Ho Chi Minh City Viet Nam Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Institute for Intelligent Systems Research and Innovation Deakin University Victoria Australia Khoury College of Computer Sciences Northeastern University Boston United States Faculty of Information Technology Ton Duc Thang University Ho Chi Minh City Viet Nam

Nowadays, memes found on internet are overwhelming. Although they are innocuous and sometimes entertaining, there exist memes that contain sarcasm, offensive, or motivational feelings. In this study, several approaches are proposed to solve the multiple modality problem in analysing the given meme dataset. The imbalance issue has been addressed by using a new Auto Augmentation method and the uncorrelation issue has been mitigated by adopting deep Canonical Correlation Analysis to find the most correlated projections of visual and textual feature embedding. In addition, both stacked attention and multi-hop attention network are employed to efficiently generate aggregated features. As a result, our team, i.e. HCILab, achieved a weighted F1 score of 0.4995 for sentiment analysis, 0.7414 for emotion classification, and 0.5301 for scale/intensity of emotion classes on the leaderboard. This results are obtained by using concatenation between image and text model and our code can be found at https://***/JMRa8. © 2022 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). CEUR Workshop Proceedings (***)

关键词： Sentiment analysis

Large magnetocaloric effect and magnetoresistance in ErNi single crystal

学校读者我要写书评

暂无评论

Journal of Materials science & Technology 2021年第27期86卷 56-63页

作者： Xuanwei Zhao Xianming Zheng Xiaohua Luo Fei Gaod Hai Zeng Guang Yu Sajjad Ur Rehman Changcai Chen Shengcan Ma Weijun Ren Zhenchen Zhong Jiangxi Key Laboratory for Rare Earth Magnetic Materials and Devices College of Rare earthsJiangxi University of Science and TechnologyGanzhou 341000People’s Republic of China Ganzhou Key Laboratory for Rare Earth Magnetic Functional Materials and Physics College of Rare earthsJiangxi University of Science and TechnologyGanzhou 341000People’s Republic of China School of Materials Science and Engineering Faculty of Materials Metallurgy and ChemistryJiangxi University of Science and TechnologyGanzhou 341000People’s Republic of China Shenyang National Laboratory for Materials Science Institute of Metal ResearchChinese Academy of SciencesShenyang 110016People’s Republic of China Key Laboratory of Electromagnetic Processing of Materials Northeastern UniversityShenyang110819People’s Republic of China

The magnetic properties,magnetocaloric effect and magnetoresistance in Er Ni single crystal have been investigated in *** decreasing temperature,Er Ni single crystal undergoes two successive magnetic transitions:a paramagnetic to ferromagnetic transition at T_(C)=11 K and a spin-reorientation transition at TS_(R)=5 ***,a sharp field-induced metamagnetic transition is observed below the T_(C)along the a *** Ni single crystal possesses a giant magnetocaloric effect around T_(C).The maximum magnetic entropy change is-36.1 J(kg K)^(-1)along the a axis under the field change of 0-50 k *** particular,the rotating magnetocaloric effect in Er Ni single crystal reaches its maximum under a relatively low field,and the maximum rotating entropy change with a value of 9.3 J(kg K)^(-1)is obtained by rotating the applied field from the[011]to[100]directions under 13 k *** results suggest that Er Ni could be a promising candidate for magnetic refrigeration working at liquid-helium temperature ***,a complicated transport behavior is uncovered in Er Ni single crystal,which is attributed to the complex magnetic states and magnetic polaronic *** positive and negative magnetoresistance are observed.A considerable large magnetoresistance with the value of-34.5%is acquired at 8 K under50 k Oe when the field is along the[100]direction.

关键词： Rare-earth transition-metal intermetallics Magnetic refrigeration Magnetocaloric effect Magnetocrystalline anisotropy Magnetoresistance

Distributed Constrained Online Nonconvex Optimization with Compressed Communication

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Kunpeng Xu, Lei Yi, Xinlei Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Mechanical Engineering University of Victoria VictoriaBCV8W 2Y2 Canada Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai201210 China Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper considers distributed online nonconvex optimization with time-varying inequality constraints over a network of agents. For a time-varying graph, we propose a distributed online primal–dual algorithm with compressed communication to efficiently utilize communication resources. We show that the proposed algorithm establishes an O(T max{1−θ1,θ1}) network regret bound and an O(T 1−θ1/2) network cumulative constraint violation bound, where T is the number of iterations and θ1 ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds (i.e, there is a point that strictly satisfies the inequality constraints at all iterations), the network cumulative constraint violation bound is reduced to O(T 1−θ1). These bounds are comparable to the state-of-the-art results established by existing distributed online algorithms with perfect communication for distributed online convex optimization with (time-varying) inequality constraints. Finally, a simulation example is presented to validate the theoretical results. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

An Adaptive Decoupling Algorithm-Based Image Reconstruction Model For Rapid Golden-Angle Radial Dce-Mri

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Chen, Zhifeng Yuan, Zhenguo Cheng, Junying Liu, Jinhai Liu, Feng Chen, Zhaolin Monash Biomedical Imaging Monash University ClaytonVIC Australia Department of Data Science & AI Faculty of IT Monash University ClaytonVIC Australia Department of Radiology Shandong Provincial Hospital Affiliated to Shandong First Medical University Jinan China Department of Radiology Shandong Provincial Hospital Cheeloo College of Medicine Shandong University Jinan China Department of MRI The First Affiliated Hospital of Zhengzhou University Zhengzhou China College of Information Science and Engineering Northeastern University Shenyang China School of Electrical Engineering and Computer Science The University of Queensland BrisbaneQLD Australia

The acceleration of magnetic resonance imaging (MRI) acquisition holds significant importance in clinical and research applications, particularly in dynamic MRI. Compressed sensing has proven to be an effective approach for fast imaging. However, existing compressed sensing schemes have limitations, such as the requirement of incoherence in sampling and residual noise, which hinder their practical application for rapid MRI. To address these challenges, we propose a novel image reconstruction framework that combines MRI physical model with a flexible self-adjusted decoupling data-driven model. To validate the proposed method, we have conducted experiments using both simulated and in vivo dynamic contrast enhanced (DCE) MRI datasets. The results demonstrate the superior performance of the proposed scheme in achieving high spatial and temporal resolution reconstructions. Furthermore, compared to the state-ofthe-art image reconstruction approaches, the proposed scheme exhibits substantially enhanced acceleration capabilities. This enables sparse and fast imaging with a high spatial and temporal resolution for dynamic MRI, making it a promising solution for real-time imaging and image-guided radiation therapy applications. © 2024, The Authors. All rights reserved.

关键词： Magnetic resonance imaging

Shape-Adaptive Planning and Control for a Deformable Quadrotor

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wu, Yuze Han, Zhichao Wu, Xuankang Zhou, Yuan Wang, Junjie Fang, Zheng Gao, Fei State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou310027 China Huzhou Institute Zhejiang University Huzhou313000 China Faculty of Robot Science and Engineering Northeastern University Shenyang110819 China

Drones have become essential in various applications, but conventional quadrotors face limitations in confined spaces and complex tasks. Deformable drones, which can adapt their shape in real-time, offer a promising solution to overcome these challenges, while also enhancing maneuverability and enabling novel tasks like object grasping. This paper presents a novel approach to autonomous motion planning and control for deformable quadrotors. We introduce a shape-adaptive trajectory planner that incorporates deformation dynamics into path generation, using a scalable kinodynamic A* search to handle deformation parameters in complex environments. The backend spatio-temporal optimization is capable of generating optimally smooth trajectories that incorporate shape deformation. Additionally, we propose an enhanced control strategy that compensates for external forces and torque disturbances, achieving a 37.3% reduction in trajectory tracking error compared to our previous work. Our approach is validated through simulations and real-world experiments, demonstrating its effectiveness in narrow-gap traversal and multi-modal deformable tasks. Copyright © 2025, The Authors. All rights reserved.

关键词： Shape optimization

Distributed Event-Triggered Bandit Convex Optimization with Time-Varying Constraints

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Kunpeng Yi, Xinlei Wen, Guanghui Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China The Laboratory for Information and Decision Systems Massachusetts Institute of Technology CambridgeMA02139 United States The Department of Mathematics Southeast University Nanjing210096 China The Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper considers the distributed bandit convex optimization problem with time-varying inequality constraints over a network of agents, where the goal is to minimize network regret and cumulative constraint violation. Existing distributed online algorithms require that each agent broadcasts its decision to its neighbors at each iteration. To better utilize the limited communication resources, we propose a distributed event-triggered online primal-dual algorithm with two-point bandit feedback. Under several classes of appropriately chosen decreasing parameter sequences and non-increasing event-triggered threshold sequences, we establish dynamic network regret and network cumulative constraint violation bounds. These bounds are comparable to the results achieved by distributed event-triggered online algorithms with full-information feedback. Finally, a numerical example is provided to verify the theoretical results. Copyright © 2024, The Authors. All rights reserved.

关键词： Convex optimization

Quantum estimation for improving optomechanical coupling strength

学校读者我要写书评

暂无评论

Physical Review A 2025年第1期111卷 012607-012607页

作者： Jia-Xin Peng P. Djorwe H. T. Cui Naeem Akhtar Inaam Ul Haq Chengsong Zhao Dongke Li School of Physics and Technology Nantong University Nantong 226019 People's Republic of China Department of Physics Faculty of Science University of Ngaoundéré P. O. Box 454 Ngaoundere Cameroon School of Physics and Optoelectronic Engineering Ludong University Yantai 264025 People's Republic of China Department of Physics Jiangsu University Zhenjiang 212013 People's Republic of China Department of Physics COMSATS University Islamabad Islamabad Campus 45550 Pakistan College of Sciences Northeastern University Shenyang 110819 People's Republic of China ZJU-Hangzhou Global Scientific and Technological Innovation Center State Key Laboratory of Silicon and Advanced Semiconductor Materials & School of Materials Science and Engineering Zhejiang University Hangzhou 311200 People's Republic of China

Enhanced quantum metrology is of vital importance for revealing the distinct features of quantum phenomena. Here we propose an effective scheme to significantly improve the quantum estimation of optomechanical coupling strength (OCS) with the assistance of two-level atoms, coherent feedback loop, and squeezed vacuum injection. Our results indicate that, by selecting appropriate atomic, quantum feedback and squeezing parameters, the estimation error of the OCS parameter can be greatly reduced. We explain the physical mechanisms behind these factors enhancing estimation precision of OCS parameter and explore the ideal parameter regions for estimating it. More importantly, the estimation precision obtained by our scheme exhibits stronger robustness against mechanical damping and ambient temperature in comparison with the unassisted case. In addition, we evaluate the performance of heterodyne detection, indicating that the measurement precision obtained through this method can approach the estimation precision obtained by our scheme. Further, the experimental feasibility of our scheme is discussed. The proposed scheme for enhancing quantum sensing is quite general and can also be applied to high-precision estimation of other physical parameters.

关键词： Heterodyne detection

Accelerating Environmental Research to Achieve Sustainable Development Goals

学校读者我要写书评

暂无评论

ENVIRONMENTAL science & TECHNOLOGY LETTERS 2023年第11期10卷 961-962页

作者： Mihelcic, James R. Barra, Ricardo O. Brooks, Bryan W. Diamond, Miriam L. Eckelman, Matthew J. Gibson, Jacqueline MacDonald Guidotti, Sunny Ikeda-Araki, Atsuko Kumar, Manish Maiga, Ynoussa McConville, Jennifer Miller, Shelly L. Pizarro, Valeria Rosario-Ortiz, Fernando Wang, Shuxiao Zimmerman, Julie B. Department of Civil & Environmental Engineering University of South Florida 4202 E Fowler Ave ENG 030 Tampa Florida 33620 United States Faculty of Environmental Sciences and EULA Chile Centre University of Concepcion Barrio Universitario s/n Concepción 4070386 Chile Department of Environmental Science Baylor University One Bear Place #97266 Waco Texas 76798-7266 United States Department of Earth Sciences and School of the Environment University of Toronto Toronto M5S 1A1 ON Canada College of Engineering Northeastern University Boston Massachusetts 02115 United States Department of Civil Construction and Environmental Engineering North Carolina State University Fitts-Woolard Hall Room 3253 915 Partners Way Raleigh North Carolina 27695-7908 United States UNICEF Latin America and Caribbean Regional Office Building 102 Alberto Tejada Street City of Knowledge 0843 Republic of Panama Faculty of Health Sciences Hokkaido University Kita 12 Nishi 5 Kitaku Sapporo 060-0812 Japan Sustainability Cluster School of Engineering University of Petroleum & Energy Studies Dehradun Uttarakhand 248007 India Escuela de Ingenieria y Ciencias Tecnologico de Monterrey Campus Monterey Monterrey 64849 Nuevo León Mexico Laboratory of Microbiology and Microbial Biotechnology UFR SVT University Joseph KI-ZERBO 03 BP 7021 Ouagadougou Burkina Faso Department of Energy and Technology Swedish University of Agricultural Sciences Box 7032 Uppsala SE-750 07 Sweden Department of Mechanical Engineering University of Colorado Boulder 427 UCB Boulder Colorado 80309-0427 United States Perry Institute for Marine Science Windsor School (Albany Campus) Frank Watson Boulevard Adelaide The Bahamas Department of Civil Environmental and Architectural Engineering Environmental Engineering Program University of Colorado Boulder Colorado 80309 United States State Key Joint Laboratory of Environment Simulation and Pollution Control School of Environment Tsinghua University Beijing 100084

From Knowledge Generation to Knowledge Verification: Examining the BioMedical Generative Capabilities of ChatGPT

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hamed, Ahmed Abdeen Crimi, Alessandro Misiak, Magdalena M. Lee, Byung Suk MGEN College of Engineering Northeastern University Miami MiamiFL33127 United States Department of Computer Science University of Vermont BurlingtonVT05405 United States CASCI Laboratory Binghamtom University BinghamtonNY13902 United States AGH University of Krakow Faculty of Informatics Krakow30-059 Poland Department of Physiology and Biophysics Howard University WashingtonDC20059 United States

The generative capabilities of LLM models offer opportunities for accelerating tasks but raise concerns about the authenticity of the knowledge they produce. To address these concerns, we present a computational approach that evaluates the factual accuracy of biomedical knowledge generated by an LLM. Our approach consists of two processes: generating disease-centric associations and verifying these associations using the semantic framework of biomedical ontologies. Using ChatGPT, as the selected LLM, we designed prompt-engineering processes to establish linkages between diseases and related drugs, symptoms, and genes, and assessed consistency across multiple ChatGPT models (e.g., GPT-turbo, GPT-4, etc.) Experimental results demonstrate high accuracy in identifying disease terms (88%–97%), drug names (90%–91%), and genetic information (88%–98%). However, symptom term identification was notably lower (49%–61%), due to the informal and verbose nature of symptom descriptions, which hindered effective semantic matching with the formal language of specialized ontologies. Verification of associations reveals literature coverage rates of 89%–91% for disease-drug and disease-gene pairs, while symptom-related associations exhibit lower coverage (49%–62%). Despite the high accuracy in identifying term names, our observations revealed that the generated term IDs were invalid and, in some cases, redundant. This issue may impede knowledge integration across multiple ontologies, as term IDs are essential for establishing cross-references. Overall, these findings suggest that GenAI tools (e.g., ChatGPT) can generate more reliable biomedical knowledge if extra care is taken. Employing strategies such as Retrieval Augmented Generation (RAG) and incorporating knowledge from literature or ontology terms, as supervised in-context prompting, may further enhance the accuracy and reliability of GenAI-generated biomedical knowledge. Further work is needed to investigate these directions. ©

关键词： Gene Ontology