检索结果-内蒙古大学图书馆

Advancement in Computation & Computer Technologies (InCACCT), International Conference on

作者： Divyabarathi P Anbarasan R. Vasanthi R B. Leena Akshya J M. Sundarrajan Mani Deepak Choudhry Department of Artificial Intelligence and Data Science Bannari Amman Institute of Technology Erode Tamil Nadu India Department of Information Technology KGiSL Institute of Technology Coimbatore Tamil Nadu India Department of Computer Science and Engineering Bharathidasan Engineering College Thirupathur Tamil Nadu India Department of Electronics and Communication Engineering KGiSL Institute of Technology Coimbatore Tamil Nadu India Department of Computational Intelligence SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Networking and Communications SRM Institute of Science and Technology Chennai Tamil Nadu India Department of Computing Technologies SRM Institute of Science and Technology Chennai Tamil Nadu India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

The autonomous decision-making capabilities of cyber-physical systems (CPS) establish key elements that optimize the management of resources while distributing tasks and maximizing system operational efficiency. Deep Q-Learning (DQN) represents one approach along with Twin Delayed Deep Deterministic Policy Gradient (TD3) and Multi-Agent Proximal Policy Optimization (PPO) that demonstrates capability in handling decision tasks. The existing models face multiple implementation challenges including inaccurate Q-value estimations weak multi-agent relationships and restricted scalability for dynamic systems. The inadequate performance of present methods for energy efficiency and latency alongside poor collaborative coordination led to the necessity of developing a new approach. The new framework DDQN-MAC takes double-deep Q-Learning and combines it with multi-agent collaboration technology to enhance decision-making abilities specific to challenging environments. The method solves overestimation bias through separate action selection and evaluation processes that use multi-agent collaboration for dynamic task distribution and resource control. The designed model demonstrates enhanced performance in multiple critical evaluation measures. Benchmarks indicate that DDQN-MAC attained a superior completion rate of 95.4% while demonstrating reduced latency performance at 12.5 ms versus the other methods DQN (18.7 ms) and Multi-Agent PPO (92.3%). The research provides fundamental groundwork to guide upcoming investigations in hybrid model development while advancing complex multi-agent system capabilities for enhanced autonomous navigational choices within variable operational environments.

关键词： Q-learning Decision making Collaboration Estimation Cyber-physical systems Dynamic scheduling Energy efficiency Resource management Vehicle dynamics Optimization

来源：评论

学校读者我要写书评

暂无评论

Optimal-rate error estimates and a twice decoupled solver for a backward Euler finite element scheme of the Doyle-Fuller-Newman model of lithium-ion batteries

arXiv

引用

arXiv 2024年

作者： Xu, Shu Cao, Liqun School of Mathematical Sciences Peking University Beijing100871 China Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China State Key Laboratory of Scientific and Engineering Computing Beijing100190 China National Center for Mathematics and Interdisciplinary Sciences Chinese Academy of Sciences Beijing100190 China

We investigate the convergence of a backward Euler finite element discretization applied to a multi-domain and multi-scale elliptic-parabolic system, derived from the Doyle-Fuller-Newman model for lithium-ion batteries. We establish optimal-order error estimates for the solution in the norms l2(H1) and l2(L2(Hrq)), q = 0,1. To improve computational efficiency, we propose a novel solver that accelerates the solution process and controls memory usage. Numerical experiments with realistic battery parameters validate the theoretical error rates and demonstrate the significantly superior performance of the proposed solver over existing solvers. Copyright © 2024, The Authors. All rights reserved.

关键词： computational efficiency

来源：评论

学校读者我要写书评

暂无评论

An Efficient Method for Seeds Classification and Quality Testing Using Fast R-CNN

An Efficient Method for Seeds Classification and Quality Tes...

引用

International Conference on Inventive Research in computing Applications (ICIRCA)

作者： S. Ashwini B. Srinivasa Rao Anil Shirgire K. R. Kannan T Ch Anil Kumar G. Sivashankar Department of Computing Technologies School of Computing SRM Institute of Science and Technology Chennai India Department of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering and Technology Hyderabad Telangana India Dr D Y Patil Institute of Technology Pune Maharashtra India Department of ECE Hindusthan Institute of Technology Coimbatore Tamilnadu India Department of Mechanical Engineering Vignan's Foundation for Science Technology and Research Guntur Andhra Pradesh India Department of Computational Intelligence SRM University Chennai Tamilnadu India

Research into agriculture is gaining an increasing attention in recent years. The newest innovations use a variety of computational technology to make agricultural tasks easier. Seed quality is the most important of many factors that determine agricultural output. Further insights into quality manufacturing, seed quality control, and impurity discovery can be gained by proper seed classification. Seeds have traditionally been sorted into different categories based on their appearance (including their color, texture, and shape). This is often done by experts who must visually inspect each sample, which is a laborious and time-consuming process. Seed sorting is a labor-intensive process that can be greatly improved by automating the inspection process. This study presents a classification system for seeds using Fast RCNN, inspired by the success of computational intelligence methods in other image classification challenges. The suggested method includes five stages: wiener filter preprocessing; HE image enhancement; binarization; adaptive watershed segmentation; and Rapid R-CNN model training. The proposed approach outperforms other two models such as CNN and RNN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Precision Enhanced Breast Cancer Prediction Using Deep Learning Models

Precision Enhanced Breast Cancer Prediction Using Deep Learn...

引用

Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), International Conference on

作者： Abhiram Kunchapu I.R. Oviya Balu Bhasuran Amrita Vishwa Vidyapeetham Computer Science and Engineering - AI Amrita School of Computing Chennai India Bakar Computational Health Sciences Institute (BCHSI) University of California San Francisco Mission Bay CA USA

Breast cancer is still a major worldwide health con- cern, which emphasises how important it is to have accurate and trustworthy diagnostic techniques. Our goal is to improve breast cancer identification in this scenario by utilizing mammography pictures from the RSNA Breast Cancer dataset. Leveraging the power of deep learning, our methodology integrates the SEResNet and ConvNeXtV2 models, simultaneously exploring and comparing various methods. To enhance the performance of our models, we incorporated changes in activation functions by replacing ReLU with GELU, an alternative activation function. Furthermore, we improved downsampling by introducing sepa- rate downsampling layers in the model architecture, optimizing spatial downsampling, and employing 3×3 convolutions with a stride of 2 at the start of each stage and 1×1 convolutions with a stride of 2 at the shortcut connection. The results achieved are highly promising, with a remarkably low loss of 0.0445 and impressive performance metrics. The F1 score stands impressively high at 0.96, complemented by a recall score of 0.95 and a precision of 0.97, showcasing exceptional performance, The accuracy score is also impressive at 92.5. These findings underscore the pivotal role of precision in elevating breast cancer detection accuracy, providing a path for more accurate diagnoses and ultimately improving patient outcomes. These enhancements significantly contributed to the overall performance of our breast cancer detection models, reinforcing the importance of precision in healthcare. This research strengthens the diagnostic tools available in the ongoing fight against breast cancer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of the second-order BDF scheme with variable steps for the molecular beam epitaxial model without slope selection

引用

science China Mathematics 2021年第5期64卷 887-902页

作者： Hong-Lin Liao Xuehua Song Tao Tang Tao Zhou Department of Mathematics Nanjing University of Aeronautics and AstronauticsNanjing 211101China Department of Mathematics and International Center for Mathematics Southern University of Science and TechnologyShenzhen 518055China Division of Science and Technology BNU-HKBU United International CollegeZhuhai 519087China NCMIS&LSEC Institute of Computational Mathematics and Scientific Engineering ComputingAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China

In this work,we are concerned with the stability and convergence analysis of the second-order backward difference formula(BDF2)with variable steps for the molecular beam epitaxial model without slope *** first show that the variable-step BDF2 scheme is convex and uniquely solvable under a weak time-step *** we show that it preserves an energy dissipation law if the adjacent time-step ratios satisfy r_(k):=τ_(k)/τ_(k-1)<***,with a novel discrete orthogonal convolution kernels argument and some new estimates on the corresponding positive definite quadratic forms,the L^(2)norm stability and rigorous error estimates are established,under the same step-ratio constraint that ensures the energy stability,i.e.,0

关键词： molecular beam epitaxial growth variable-step BDF2 scheme discrete orthogonal convolution kernels energy stability convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Quantized Constant-Envelope Waveform Design for Massive MIMO DFRC Systems

arXiv

引用

arXiv 2024年

作者： Wu, Zheyu Liu, Ya-Feng Chen, Wei-Kun Masouros, Christos The State Key Laboratory of Scientific and Engineering Computing Institute of Computational Mathematics and Scientific/Engineering Computing Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing100190 China The School of Mathematics and Statistics Beijing Key Laboratory on MCAACI Beijing Institute of Technology Beijing100081 China The Department of Electronic and Electrical Engineering University College London Torrington Place LondonWC1E 7JE United Kingdom

Both dual-functional radar-communication (DFRC) and massive multiple-input multiple-output (MIMO) have been recognized as enabling technologies for 6G wireless networks. This paper considers the advanced waveform design for hardware-efficient massive MIMO DFRC systems. Specifically, the transmit waveform is imposed with the quantized constant-envelope (QCE) constraint, which facilitates the employment of low-resolution digital-to-analog converters (DACs) and power-efficient amplifiers. The waveform design problem is formulated as the minimization of the mean square error (MSE) between the designed and desired beampatterns subject to the constructive interference (CI)-based communication quality of service (QoS) constraints and the QCE constraint. To solve the formulated problem, we first utilize the penalty technique to transform the discrete problem into an equivalent continuous penalty model. Then, we propose an inexact augmented Lagrangian method (ALM) algorithm for solving the penalty model. In particular, the ALM subproblem at each iteration is solved by a custom-built block successive upper-bound minimization (BSUM) algorithm, which admits closed-form updates, making the proposed inexact ALM algorithm computationally efficient. Simulation results demonstrate the superiority of the proposed approach over existing state-of-the-art ones. In addition, extensive simulations are conducted to examine the impact of various system parameters on the trade-off between communication and radar performances. Copyright © 2024, The Authors. All rights reserved.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Oral Cancer Detection and Classification Using Deep Learning with DenseNet121-CatBoost Classifier

Oral Cancer Detection and Classification Using Deep Learning...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： D Anitha Thota Soujanya Subhra Chakraborty Ahmad Alkhayyat R Revathi Department of Computational Intelligence School of Computing SRM Institute of Science and Technology Kattankulathur India School of Agricultural Sciences SR University Warangal India Department of ECE Nitte Meenakshi Institute of Technology Bengaluru India Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of Computer Science Karpagam Academy of Higher Education Coimbatore India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

Oral cancer is a growing universal health challenge, which is rising in the current situation. Early detection is vital for effective treatment and better patient results. However, current diagnostic methods, notably manual histopathological analysis, suffer from subjectivity and time limitations due to classifying the images according to their type. The dependence on manual analysis can lead to delays in accurately diagnosing oral cancer. The proposed method DenseNet121-CatBoost classifier addresses this challenge by using the Histopathological Images dataset. The DenseNet121 for the extracting process and the CatBoost classifier for classifying the images according to their classes. DenseNet121 is utilized to extract features and patterns from images and the CatBoost classifier in the classification process helps to classify the dataset according to its classes using the extracted information. The performance of the DenseNet121-CatBoost method is analyzed using accuracy, specificity, sensitivity, f1score, precision, and Area Under Curve (AUC). This paper shows that the proposed DenseNet121-CatBoost outperforms the existing methods such as ResNet50+CatBoost, DenseNet201+SVM (Support Vector Machine), and GoogLeNet+XGBoost in terms of accuracy of 97.62%, specificity of 98.96%, sensitivity of 94.55%, f1-score of 93.87%, precision of 98.65%, and AUC of 95.26%.

关键词： Support vector machines Accuracy Sensitivity Image color analysis Manuals Feature extraction Cancer detection Gabor filters Data mining Cancer

来源：评论

学校读者我要写书评

暂无评论

Opportunities and Challenges from Using Animal Videos in Reinforcement Learning for Navigation

arXiv

引用

arXiv 2022年

作者： Giammarino, Vittorio Queeney, James Carstensen, Lucas C. Hasselmo, Michael E. Paschalidis, Ioannis Ch. Division of Systems Engineering Boston University BostonMA02215 United States Center for Systems Neuroscience Department of Psychological and Brain Sciences Graduate Program for Neuroscience Boston University BostonMA02215 United States College of Engineering Hariri Institute for Computing & Computational Science & Engineering Boston University BostonMA02215 United States

We investigate the use of animal videos (observations) to improve Reinforcement Learning (RL) efficiency and performance in navigation tasks with sparse rewards. Motivated by theoretical considerations, we make use of weighted policy optimization for off-policy RL and describe the main challenges when learning from animal videos. We propose solutions and test our ideas on a series of 2D navigation tasks. We show how our methods can leverage animal videos to improve performance over RL algorithms that do not leverage such observations. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Pyramidal Relaxation Method of AC OPF

A Dynamic Pyramidal Relaxation Method of AC OPF

引用

Power and Electrical engineering (ACPEE), 5th Asia Conference on

作者： Yu-Yang Tang Liang Chen Hongbo Du Sheng-Jie Chen Caixia Kou Xiaomeng Ai Bo Zhou Academy of Mathematics and Systems Science Chinese Academy of Sciences Institute of Computational Mathematics and Scientific/Engineering Computing Beijing China College of Sciences Beijing University of Posts and Telecommunications Beijing China Academy of Mathematics and Systems Science Chinese Academy of Sciences Institute of Applied Mathematics Beijing China School of Electrical and Electronic Engineering Huazhong University of Science and Technology Wuhan China Department of Industrial and Operations Engineering University of Michigan Ann Arbor United States

ISBN: (数字)9798350309638

ISBN: (纸本)9798350309645

The Alternating Current Optimal Power Flow (AC OPF) is crucial for power system analysis, yet existing algorithms face challenges in meeting the diverse requirements of practical applications. This paper presents a Pyramidal Relaxation (PR) formulation of the Branch Flow Model (BFM) for AC OPF, where surface conical constraints are approximated through a union of tetrahedrons in a Mixed Integer Linear Programming (MILP) relaxation. To reduce problem size and to enhance computational efficiency, we proposed a Dynamic Pyramidal Relaxation (DPR) method, where the cuts (inner approximation and outer approximation) are adaptively added. In practice, the DPR method is embedded into a MILP commercial solver based on the branch-and-cut framework. Case studies in different test systems validate the effectiveness in terms of feasibility, accuracy, and efficiency of our proposed method.

关键词： Electrical engineering computational modeling Power system dynamics Asia Linear approximation Relaxation methods Mixed integer linear programming

来源：评论

学校读者我要写书评

暂无评论

Context-aware Multimodal AI Reveals Hidden Pathways in Five Centuries of Art Evolution

arXiv

引用

arXiv 2025年

作者： Kim, Jin Lee, Byunghwee You, Taekho Yun, Jinhyuk Department of Intelligent Semiconductors Soongsil University Seoul06978 Korea Republic of School of Digital Humanities & Computational Social Sciences Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States Institute for Social Data Science Pohang University of Science and Technology Pohang37673 Korea Republic of Center for Digital Humanities & Computational Social Sciences Korea Advanced Institute of Science and Technology Daejeon34141 Korea Republic of School of AI Convergence Soongsil University Seoul06978 Korea Republic of

The rise of multimodal generative AI is transforming the intersection of technology and art, offering deeper insights into large-scale artwork. Although its creative capabilities have been widely explored, its potential to represent artwork in latent spaces remains underexamined. We use cutting-edge generative AI, specifically Stable Diffusion, to analyze 500 years of Western paintings by extracting two types of latent information with the model: formal aspects (e.g., colors) and contextual aspects (e.g., subject). Our findings reveal that contextual information differentiates between artistic periods, styles, and individual artists more successfully than formal elements. Additionally, using contextual keywords extracted from paintings, we show how artistic expression evolves alongside societal changes. Our generative experiment, infusing prospective contexts into historical artworks, successfully reproduces the evolutionary trajectory of artworks, highlighting the significance of mutual interaction between society and art. This study demonstrates how multimodal AI expands traditional formal analysis by integrating temporal, cultural, and historical contexts. Copyright © 2025, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：