检索结果-内蒙古大学图书馆

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

作者： Nooruddin Noonari Kaleem Arshid Shamaila Fardous Javed Karim Sathishkumar Duraisamy Department of Computer Science IBA Community College Naushahro Feroze Sindh Pakistan DITEN University of Genova Genova Italy Institute of Technology Beijing Institute of Technology Beijing China Strategic and Security Engineering University of Genova Italy Dept of Mechanical Engineering Kathir College of Engineering Tamilnadu India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

The optimization problem of the Maximum Weighted Independent Set (MWIS) in graph theory is a significant challenge with wide-ranging applications in resource allocation, network design, and scheduling. This paper introduces algorithmic insights using Greedy Heuristics (GH) and Exhaustive Search (ES) methods for MWIS implementation. Implementations are conducted on graphs with varying weights and sizes (12.5%, 25%, 50%), and evaluation parameters include the number of vertices and edges. The study reveals that GH achieves MWIS outcomes with fewer operations and tests compared to ES, demonstrating its efficiency in solving the MWIS problem. The results suggest that GH is a practical alternative for optimizing large graphs efficiently, balancing solution quality and computational effort. These findings have significant implications for real-world applications requiring quick and effective optimization solutions.

关键词： Wireless communication Operations research Heuristic algorithms Approximation algorithms Search problems Graph theory Classification algorithms Resource management Optimization Testing

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Dynamic Compliance Management in Blockchain Supply Chains: An LSTM Perspective

Deep Reinforcement Learning for Dynamic Compliance Managemen...

引用

IoT, Communication and Automation Technology (ICICAT), International Conference on

作者： Jinugu Ranjith Mohammed Al-Farouni R. Anitha Ediga Poornima Kamal Sharma Neelam Sanjeev Kumar Department of CSE CMR College of Engineering & Technology Department of Computers Techniques Engineering College of Technical Engineering The Islamic University Najaf Iraq Department of IT New Prince Shri Bhavani College of Engineering and Technology Chennai Tamil Nadu India Department of AI&ML GRIET Bachupally Hyderabad Telangana India Department of Mechanical Engineering GLA University Mathura Department of Computer Science & Engineering (E.Tech.) SRM Institute of Science & Technology Vadapalani Chennai

ISBN: (数字)9798350368109

ISBN: (纸本)9798350368116

Supply chain management is one of the industries that benefit greatly from implementing blockchain technology since it supplies chains with a high level of transparency, security, and traceability. Nonetheless, keeping up to date with different regulatory requirements or specifications that change frequently and still meeting contract requirements still pose a major problem. In this paper, we introduce a new method in the dynamic compliance management of blockchain implemented supply chain system by the use of deep reinforcement learning (DRL) and Long Short-Term Memory (LSTM) networks. Through DRL, supply chains can obtain real-time insights in learning from the environment and apply the knowledge effectively to satisfy regulatory standards as well as contractual terms. The inclusion of the LSTM component allows the system to capture sequential dependency and long-horizon effects within the supply-chain data. To prove the efficiency of our strategy, we provide simulation results as well as the analysis of real-world applications that discuss the positive shift in percentages and potential increase in productivity.

关键词： Industries Supply chain management Simulation Supply chains Deep reinforcement learning Aerodynamics Blockchains Security Long short term memory Standards

来源：评论

学校读者我要写书评

暂无评论

arXiv

引用

arXiv 2023年

作者： Li, Xisheng Li, Wei Song, Pinhao Zhang, Mingjun Zhou, Jie School of Artificial Intelligence and Computer Science Jiangnan University Jiangsu China Robotics Research Group The Department of Mechanical Engineering KU Leuven Belgium

The inherent characteristics and light fluctuations of water bodies give rise to the huge difference between different layers and regions in underwater environments. When the test set is collected in a different marine area from the training set, the issue of domain shift emerges, significantly compromising the model's ability to generalize. The Domain Adversarial Learning (DAL) training strategy has been previously utilized to tackle such challenges. However, DAL heavily depends on manually one-hot domain labels, which implies no difference among the samples in the same domain. Such an assumption results in the instability of DAL. This paper introduces the concept of Domain Similarity-Perceived Label Assignment (DSP). The domain label for each image is regarded as its similarity to the specified domains. Through domain-specific data augmentation techniques, we achieved state-of-the-art results on the underwater cross-domain object detection benchmark S-UODAC2020. Furthermore, we validated the effectiveness of our method in the Cityscapes dataset. Copyright © 2023, The Authors. All rights reserved.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Breast Cancer Classification: Leveraging CNNs for Early Detection

AI-Powered Breast Cancer Classification: Leveraging CNNs for...

引用

International Conference on Information science and Communications Technologies (ICISCT)

作者： Vishnu Kant Deepak Gupta Srinivas Aluvala Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Department of Mechanical Engineering Graphic Era Hill University Dehradun Graphic Era Deemed to be University Dehradun School of Computer Science & Artificial Intelligence SR University Warangal

ISBN: (数字)9798331527921

ISBN: (纸本)9798331527938

Among the most common and fatal diseases afflicting women throughout is breast cancer. Early detection greatly increases survival rates, hence reliable and effective diagnostic instruments are rather important for patient treatment. Although conventional screening techniques like mammography are efficient, false positives and false negatives present problems that can cause treatment delays. Using deep learning methods to enhance diagnosis accuracy and provide scalable screening systems, this work investigates the application of Convolutional Neural Networks (CNNs) for breast cancer categorization. CNNs provide great accuracy in spotting anomalies and automatically recognize patterns and characteristics, hence improving medical imaging. This work created and trained a proprietary CNN model using a dataset obtained from the Kaggle platform comprising 549 photos encompassing both malignant and non-cancerous samples. With an accuracy of 89%, the proposed model shows promise to help radiologists in early breast cancer detection, so improving healthcare outcomes and supporting the worldwide goals of improving health and well-being, so lowering inequalities in medical access, and so promoting innovation in healthcare technologies. In line with more general goals for excellent healthcare systems worldwide, our work helps the continuous endeavor to provide more sustainable and scalable options for early diagnosis of breast cancer.

关键词： Accuracy Image recognition Instruments Medical treatment Breast cancer Data models Convolutional neural networks Character recognition Artificial intelligence Medical diagnostic imaging

来源：评论

学校读者我要写书评

暂无评论

Moving Vehicle Registration Plate Detection Using Machine Learning

Moving Vehicle Registration Plate Detection Using Machine Le...

引用

Trends in Quantum Computing and Emerging Business Technologies (TQCEBT), International Conference on

作者： B Sreedhar Gowtham Prasad T V S Sivudu Macherla K. S. Raghuram M. Sunil Kumar Dept of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram A.P India Dept of Electronics and Mohan Babu University (erstwhile Sree Vidyanikethan Engineering College) Tirupathi AP India Department of IT PACE Institute of Technology and Sciences Ongole AP India Department of Mechanical Engineering Vignan's Institute of Information Technology (A) Visakhapatnam A. P. India Department of Computer Science and Engineering School of Computing Mohan Babu University (erstwhile Sree Vidyanikethan Engineering College) Tirupathi AP India

ISBN: (数字)9798350384277

ISBN: (纸本)9798350384284

This research investigates the application of machine learning techniques in the detection of moving vehicle registration plates. The study explores the effectiveness of various algorithms in accurately identifying and localizing license plates in dynamic and real-time scenarios. By utilizing image processing and pattern recognition methods, the research aims to develop a robust and efficient system capable of detecting license plates under challenging conditions, such as varying lighting conditions and different vehicle orientations. The proposed approach offers potential benefits for law enforcement, traffic monitoring, and parking management systems. Through empirical evaluations, the study aims to validate the effectiveness and reliability of the machine learning-based approach for moving vehicle registration plate detection, providing insights for future research and development in this field.

关键词： Quantum computing Heuristic algorithms Machine learning Real-time systems Pattern recognition Reliability Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

Efficient Implicit Neural Reconstruction Using LiDAR

Efficient Implicit Neural Reconstruction Using LiDAR

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Dongyu Yan Xiaoyang Lyu Jieqi Shi Yi Lin School of Mechanical Engineering and Automation Harbin Institute of Technology (Shenzhen). Department of Electrical and Electronic Engineering The University of Hong Kong. Department of Electronic and Computer Engineering Hong Kong University of Science and Technology. Dji Co.

Modeling scene geometry using implicit neural representation has revealed its advantages in accuracy, flexibility, and low memory usage. Previous approaches have demonstrated impressive results using color or depth images but still have difficulty handling poor light conditions and large-scale scenes. Methods taking global point cloud as input require accurate registration and ground truth coordinate labels, which limits their application scenarios. In this paper, we propose a new method that uses sparse LiDAR point clouds and rough odometry to reconstruct fine-grained implicit occupancy field efficiently within a few minutes. We introduce a new loss function that supervises directly in 3D space without 2D rendering, avoiding information loss. We also manage to refine poses of input frames in an end-to-end manner, creating consistent geometry without global point cloud registration. As far as we know, our method is the first to reconstruct implicit scene representation from LiDAR-only input. Experiments on synthetic and real-world datasets, including indoor and outdoor scenes, prove that our method is effective, efficient, and accurate, obtaining comparable results with existing methods using dense input.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Study of Different Types of Battery of Electric Vehicles Using MATLAB Simulink

Performance Study of Different Types of Battery of Electric ...

引用

IEEE International WIE Conference on Electrical and computer engineering (WIECON-ECE)

作者： Md. Sohel Siddequy Sheik Erfan Ahmed Himu Arafat Ibne Ikram Fahim Abrar S. M. Shahriar Iqbal Md. Ziaur Rahman Tasnia Fahrin Choity Department of Electrical and Electronic Engineering International Islamic University Chittagong Chattogram Bangladesh Department of Electrical and Mechanical Engineering Nagoya Institute of Technology Nagoya Japan Department of Computer Science and Engineering International Islamic University Chittagong Chattogram Bangladesh

Since the advent of the Industrial Revolution, fossil fuels and internal combustion engines have played a fundamental role in meeting transportation and energy needs. However, the extensive reliance on fossil fuels over the past two centuries has resulted in dire consequences, such as global warming, environmental disruption, glacier melting, rising sea levels, and droughts. Consequently, scientists have been actively exploring alternative solutions to replace fossil fuel-based transportation systems. Electric vehicles (EVs) have emerged as a pivotal solution to address the existing challenges in transportation systems. Although the concept of EV s has existed for some time, the widespread production and adoption of fully electric cars was hindered until the early 21st century owing to the unavailability of suitable batteries or energy storage systems. The efficacy of EVs relies heavily on their energy storage systems. In this article, we evaluate various battery types (including nickel metal hydrate, zinc hybrid cathode, lead acid, and lithium-ion) in the context of EV performance, using MAT LAB Simulink. A MATLAB Simulink-based electric vehicle model was employed to assess battery performance. Our analysis reveals that lithium-ion batteries demonstrate superior performance metrics, including a specific energy ranging from 100–275 WH/kg, energy density of 200–235 Wh/L, specific power of 350–3000 W/kg, cell voltage of 3.6V, and cycle durability of 500–3000. Furthermore, we consider the typical cost of these batteries, noting that lead-acid batteries are relatively more affordable than other options available in the market.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Solving Reach-Avoid-Stay Problems Using Deep Deterministic Policy Gradients

arXiv

引用

arXiv 2024年

作者： Chenevert, Gabriel Li, Jingqi Kannan, Achyuta Bae, Sangjae Lee, Donggun The Department of Mechanical and Aerospace Engineering North Carolina State University Raleigh United States The Department of Electrical Engineering and Computer Sciences University of California Berkeley United States The Department of Computer Science North Carolina State University Raleigh United States Honda Research Institute United States

Reach-Avoid-Stay (RAS) optimal control enables systems such as robots and air taxis to reach their targets, avoid obstacles, and stay near the target. However, current methods for RAS often struggle with handling complex, dynamic environments and scaling to high-dimensional systems. While reinforcement learning (RL)-based reachability analysis addresses these challenges, it has yet to tackle the RAS problem. In this paper, we propose a two-step deep deterministic policy gradient (DDPG) method to extend RL-based reachability method to solve RAS problems. First, we train a function that characterizes the maximal robust control invariant set within the target set, where the system can safely stay, along with its corresponding policy. Second, we train a function that defines the set of states capable of safely reaching the robust control invariant set, along with its corresponding policy. We prove that this method results in the maximal robust RAS set in the absence of training errors and demonstrate that it enables RAS in complex environments, scales to high-dimensional systems, and achieves higher success rates for the RAS task compared to previous methods, validated through one simulation and two high-dimensional experiments. © 2024, CC BY.

关键词： Optimal control systems

来源：评论

学校读者我要写书评

暂无评论

Tight Collision Probability for UAV Motion Planning in Uncertain Environment

Tight Collision Probability for UAV Motion Planning in Uncer...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Tianyu Liu Fu Zhang Fei Gao Jia Pan Department of Mechanical Engineering The University of Hong Kong Institute of Cyber-Systems and Control Zhejiang University Department of Computer Science The University of Hong Kong

Operating unmanned aerial vehicles (UAVs) in complex environments that feature dynamic obstacles and external disturbances poses significant challenges, primarily due to the inherent uncertainty in such scenarios. Additionally, inaccurate robot localization and modeling errors further exacerbate these challenges. Recent research on UAV motion planning in static environments has been unable to cope with the rapidly changing surroundings, resulting in trajectories that may not be feasible. Moreover, previous approaches that have addressed dynamic obstacles or external disturbances in isolation are insufficient to handle the complexities of such environments. This paper proposes a reliable motion planning framework for UAVs, integrating various uncertainties into a chance constraint that characterizes the uncertainty in a probabilistic manner. The chance constraint provides a probabilistic safety certificate by calculating the collision probability between the robot's Gaussian-distributed forward reachable set and states of obstacles. To reduce the conservatism of the planned trajectory, we propose a tight upper bound of the collision probability and evaluate it both exactly and approximately. The approximated solution is used to generate motion primitives as a reference trajectory, while the exact solution is leveraged to iteratively optimize the trajectory for better results. Our method is thoroughly tested in simulation and real-world experiments, verifying its reliability and effectiveness in uncertain environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimized Dilated Convolutional Neural Network with Quantum Self-Attention Based on Hyper Spectral Remote Sensing Image Classification

Optimized Dilated Convolutional Neural Network with Quantum ...

引用

International Conference on ICT in Business Industry & Government (ICTBIG)

作者： T. Santhosha H. Mohammed Ali Seeniappan K Nagendar Yamsani R Maranan S. Kaliappan Department of Artificial Intelligence & Machine Learning Geetanjali College of Engineering and Technology T.S Department of Mechanical Engineering SRM Institute of Science and Technology Chennai Department of Mechanical Engineering Amity University Dubai United Arab Emirates School of Computer Science & Artificial Intelligence SR University Warangal Telangana Department of Research and Innovation Saveetha School of Engineering SIMATS Chennai Tamil Nadu India Division of Research and Development Lovely Professional University Phagwara Punjab India

ISBN: (数字)9798331518981

ISBN: (纸本)9798331518998

Hyperspectral remote sensing (RS) involves capturing and analyzing data across numerous, narrow spectral bands in the electromagnetic spectrum. With this technology, it is possible to identify what has been on the Earth surface with unprecedented depth that cannot be done with the mere multispectral images. A Hyperspectral sensor is able to capture hundreds of bands of data, and is therefore able to distinguish between very small differences in surface materials that we cannot even see or conventional multispectral sensors. Hyperspectral remote sensing is widely used in applications like agriculture, environmental monitoring, geology, and defence. To overcome the limitations of current approaches, new strategies are needed. In this manuscript Optimized Dilated Convolutional Neural Network with Quantum Self-Attention Based on Hyper Spectral Remote Sensing Image Classification (DCNN-QSA-PDOA) is proposed. The Indian Pine dataset is where the data is first gathered. The multidirectional shearlet transform based feature extraction (MDST) model is then utilized to extract the hyperspectral image (HSI) features. Following the completion of the feature extraction procedure, the Dilated Convolutional Neural Network with Quantum Self-Attention (DCNN-QSA) is trained on the feature extracted images and used to classify the category information. Here, (PDOA) is utilized for tuning hyper parameters of DCNN-QSA. The proposed DCNN-QSA-PDOA method provides 37.23%, 18.74% and 24.84% higher accuracy compared with existing method like Classifying images from hyper spectral RS using a DCNN-HIS, Dense residual three-dimensional convolutional neural networks are used for hyper spectral RS picture classification (DR-3DCNN-HIS), Fully convolutional neural networks are used for the categorization of hyper spectral remote sensing pictures (CNN-HIS) respectively.

关键词： Accuracy Transforms Feature extraction Sensors Convolutional neural networks Data mining Tuning Optimization Hyperspectral imaging Image classification

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：