检索结果-内蒙古大学图书馆

International Conference on Unmanned Aircraft Systems (ICUAS)

作者： Leonardo A. Fagundes-Junior Celso O. Barcelos Daniel C. Gandolfo Alexandre S. Brandão Department of Electrical Engineering and Graduate Program on Computer Science Núcleo de Especialização em Robótica Federal University of Viçosa Viçosa MG Brazil Instituto de Automática National University of San Juan Argentine Department of Electrical Engineering Federal University of Viçosa Viçosa MG Brazil

The Flying Robot Trial League (FRTL), from RoboCup Brazil, is a competition that stimulates the development of autonomous and intelligent flying robots for inspection and operation in pipeline lanes and oil installations. In this context, this work presents the system developed by the BDP-UaiFly Team for the 2022 competition, using the off-the-shelf Parrot Bebop 2 to execute the Equipment Transport phase. This paper presents in detail the system platform and the navigation and sensing strategies implemented for autonomous navigation and image processing. In particular, the strategy adopted for cargo transportation based on servo-visual control is presented. Practical experiments validate the proposed solutions for the phases of the challenge.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mathematical representation of emotion using multimodal recognition model with deep multitask learning

IEEJ Transactions on Electronics, Information and Systems

引用

IEEJ Transactions on Electronics, Information and Systems 2020年第12期140卷 1343-1351页

作者： Harata, Seiichi Sakuma, Takuto Kato, Shohei Computer Science Program Department of Engineering Graduate School of Engineering Nagoya Institute of Technology Gokiso-cho Showa-ku Nagoya-city Aichi466-8555 Japan Frontier Research Institute for Information Science Nagoya Institute of Technology Gokiso-cho Showa-ku Nagoya-city Aichi466-8555 Japan

To emulate human emotions in robots, the mathematical representation of emotion is important for each component of affective computing, such as emotion recognition, generation, and expression. In a method that learns DNN from unimodality and represents emotions by vectors of continuous values (Emotional Space), the acquired Emotional Space is likely to depend on the modality, and considering the number of dimensions of Emotional Space is necessary. In this study, we aim at the acquisition of modality independent Emotional Space. We propose a method of acquiring Emotional Space by integrating multimodalities on a DNN and combining the emotion recognition task and unification task of Emotional Space of each modality. Through the experiments with audio-visual data, we confirmed in various dimensions of Emotional Space that there are differences in Emotional Space acquired from unimodality, and the proposed method can acquire a modality independent Emotional Space. We also investigated the compatibility of the recognition and the unification score by changing the number of dimensions of Emotional Space. Finally, we indicate the proposed method can acquire sufficient Emotional Space with a small number of dimensions, such as five or six dimensions, under this paper's experimental conditions. © 2020 The Institute of Electrical Engineers of Japan.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

The Smart Analysis of Performing Scalable Inference for Big Data Analytics

The Smart Analysis of Performing Scalable Inference for Big ...

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Vishakha D Bhandarkar Aruna Sri Rongali Mohamed Dawood Shamout Prof. Sachin Pund Gigih Forda Nama Shrishailappa Patil Applied Mathematics and Humanities Yeshwantrao Chavan College of Engineering India Graduate Doctoral Information Technology/Graduate (Information Technology Emphasis/Information Technology Ph.D.) University of The Cumberlands US Department of Management College of Business Administration University of Sharjah Sharjah United Arab Emirates Department of Industrial Engineering Shri Ramdeobaba College of Engineering and Management Nagpur Maharashtra India Department of Informatics Doctoral Program of Environtmental Science University of Lampung Bandar Lampung Computer engineering Vishwakarma Institute of Technology Pune

This paper examines the reproducibility of massive information analytics under particular factors. The paper proposes the “performing Scalable Inference” technique to cope with scalability troubles and to exploit current big statistics platforms for efficient computing and statistics garage of the statistics. In particular, the paper describes how to perform leak-free, parallelizable visible analytics over massive datasets using present extensive records analytics frameworks such as Apache Flink. This method presents an automated manner to execute analytics that preserves reproducibility and the ability to make adjustments without re-running the entire technique. The paper also demonstrates how these analytics may help several real-world use instances, explore affected person cohorts for studies, and develop stratified patient cohorts for hospital therapy. In the end, the paper observes how the proposed method may be exercised within the real world. Actively scalable inference for massive information analytics is pivotal in optimizing decision-making and allocation of assets. Typically, such inferences are made based on information accumulated from numerous sources, databases, unstructured data, and different digital sources. So one can ensure scalability, a complete cloud-primarily based platform has to be hired. This solution will permit the ***, deploying the essential records series and evaluation algorithms are prime here. It could permit the platform to recognize the styles inside the statistics and discover any ability correlations or traits. Additionally, predictive analytics and system mastering strategies may be incorporated to provide insights into the results of the information. In the long run, by leveraging those techniques, the platform can draw efficient inferences and appropriately compare situations in an agile and green way..

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using a Deep Learning Approach

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using ...

引用

International Symposium on Applied science 2024, ISAS 2024

作者： Raza, Aquib Ching, Congo Tak Shing Liu, Peng-Ta Phan, Thien-Luan Tran, Ngoc-Luan Nguyen, Ha Anh T. Rameez, Mohammad Li, Hung-Chung Linh, Dao Nguyen Phuong Van Hieu, Nguyen Tran, Trung Nghia National Taiwan University Taipei City10673 Taiwan Research Center for Information Technology Academia Sinica Taipei City11529 Taiwan Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung402 Taiwan Department of Electrical Engineering National Chi Nan University Nantou County Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan International Doctoral Program in Agriculture National Chung Hsing University Taichung402 Taiwan Fall Prevention Center Department of Physical Medicine & Rehabilitation Changhua Christian Hospital Changhua500 Taiwan Department of Physics and Electronic Engineering University of Science Vietnam National University - Ho Chi Minh City Ho Chi Minh City70000 Viet Nam Department of Computer Science University of York York HeslingtonYO10 5DD United Kingdom Undergraduate Program of Intellectual Creativity Engineering National Chung Hsing University Taichung402 Taiwan Ho Chi Minh City72409 Viet Nam HCMUT Vietnam National University Ho Chi Minh City Thu Duc Ho Chi Minh City71308 Viet Nam

This research introduces a deep learning framework that combines convolutional neural networks with autoencoders to improve the diagnostic accuracy of knee osteoarthritis. The study utilized a publicly available dataset from the Mendeley Data repository, where knee joint images were preprocessed using Contrast Limited Adaptive Histogram Equalization to enhance contrast and ensure consistent image sizing. Initially, an autoencoder was employed in an unsupervised manner to learn compressed representations of the data. These representations were then used to train a CNN to classify knee images into 'healthy' and 'osteoarthritic' categories. The model was trained using an 80:20 split for training and testing data, incorporating early stopping and data augmentation techniques to prevent overfitting and enhance generalization. Performance metrics such as accuracy, precision, recall, and the area under the Receiver Operating Characteristic curve (ROCAUC) were used to evaluate the model, resulting in a high test accuracy of 98.95%. The high precision and recall rates further confirmed the model's robustness in diagnosing KOA. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to identify critical regions in the images that influenced the model's decisions. Additionally, t-Distributed Stochastic Neighbor Embedding (t-SNE) was used to visualize the high-dimensional encoded features in a two-dimensional space, providing deeper insights into how the model differentiates between classes. The promising results of this deep learning approach suggest its potential for broader applications in medical imaging diagnostics. By providing healthcare professionals with a tool that enhances diagnostic accuracy and operational efficiency, this framework lays the foundation for developing scalable, AI-driven diagnostic systems for various complex medical conditions. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Joints (anatomy)

来源：评论

学校读者我要写书评

暂无评论

Preprocessing Techniques for Enhancing Vision-Based Detection System for Tire Sidewall Extraction

Preprocessing Techniques for Enhancing Vision-Based Detectio...

引用

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Jia Hao Loo Veronica Lestari Jauw Chin Seong Lim Khairul-Rijal Sarmin Nunung Nurul Qomariyah Ahmad Nurul Fajar Department of Mechanical Materials and Manufacturing Engineering University of Nottingham Malaysia Malaysia Continental Tyre Technology Centre Malaysia Petaling Jaya Malaysia Computer Science Department School of Computing and Creative Arts Bina Nusantara University Jakarta Indonesia Information System Management Department BINUS Graduate Program-Master Information Systems Bina Nusantara University Jakarta Indonesia

ISBN: (数字)9798331519643

ISBN: (纸本)9798331519650

This study aims to develop a system for extracting crucial information from tire sidewalls using Optical Character Recognition (OCR). Initially, images of tire were captured manually by smartphone cameras, including Redmi 9T, iPhone 11, and Galaxy S23 Ultra. The captured images are then transferred to a computer for storage. Subsequently, these images were cropped according to the boundaries identified by Hough Circle Transform (HCT). The cropped images were then further pre-processed. During the pre-processing phase, geometrical transformation and image sharpening techniques are applied to enhance the clarity and readability of the text images. The text is then extracted using Google Vision, with the extracted text categorized by size, DOT, brand and pattern. The results indicated that the effectiveness of image pre-processing was constrained by the accuracy of circle detection, which reached a maximum rate of 87.1%. This causes parts of the text to be cut out inaccurately, leading to a suboptimal extraction accuracy of 55.65%. It is also observed that the Redmi 9T camera produced inconsistent results compared to other devices. Specifically, the iPhone 11 and Samsung Galaxy S23 Ultra demonstrated superior extraction accuracies of 69.71% and 66.37%, respectively, whereas the Redmi 9T achieved a lower extraction accuracy of 37.76%.

关键词： Accuracy Optical character recognition Text categorization Lighting Transforms US Department of Transportation Cameras Tires Internet Data mining

来源：评论

学校读者我要写书评

暂无评论

Theoretical Modelling of Smart Meter Privacy Protection with Multi-meter Energy Routing 4

Theoretical Modelling of Smart Meter Privacy Protection with...

引用

4th IEEE International Conference on Smart Internet of Things, SmartIoT 2020

作者： Ergen, Cankut Gulbahar, Burhan Ozyegin University Graduate School of Engineering and Science MSc Program of Computer Science Istanbul34794 Turkey Ozyegin University Applied Research Center of Technology Products Istanbul34794 Turkey

ISBN: (纸本)9781728165141

Potential of intrusion during smart meter data collection is an important problem for household privacy in next-generation smart homes. There are various privacy protection methods such as hiding the real usage with renewable batteries (RBs) and encrypted communication. There are privacy threats due to the detection of the energy transfer through RBs while encryption-based methods result in high computational complexity. In this study, a novel privacy improvement mechanism is proposed based on the routing of energy through multiple smart meters among multiple houses in a neighborhood. The optimization of privacy based on uniform randomization is theoretically modeled and some heuristic solutions are presented. In this method, energy transfer is randomly distributed among multiple smart meters, real usage of a house is buffered with the RB and smart meter indices are randomly selected. In numerical simulations, privacy improvement is shown by utilizing the random selection of smart meter indices for randomizing the energy routing and the buffers of RBs. Furthermore, energy privacy (EP) metric validating the simulation results is defined. Energy routing with multiple smart meters provides a practical and low complexity privacy protection mechanism for next-generation smart grid architectures. © 2020 IEEE.

关键词： Smart meters

来源：评论

学校读者我要写书评

暂无评论

Tunable Source of Quantum-Correlated Photons with Integrated Pump Rejection in a Silicon CMOS Platform

Tunable Source of Quantum-Correlated Photons with Integrated...

引用

Frontiers in Optics + Laser science 2021, FiO+LS 2021 - Part of Frontiers in Optics, FiO 2021

作者： Fargas Cabanillas, Josep M. Kramnik, Danielius Ramesh, Anirudh Gentry, Cale M. Stojanović, Vladimir Kumar, Prem Popović, Miloš A. Department of Electrical and Computer Engineering Photonics Center Boston University BostonMA02215 United States Department of Electrical Engineering and Computer Science UC Berkeley BerkeleyCA94720 United States Graduate Program in Applied Physics Northwestern University EvanstonIL60208 United States Department of Electrical Computer and Energy Engineering University of Colorado BoulderCO80309 United States Center for Photonic Communication and Computing Dept. of Electrical and Computer Eng. Northwestern University EvanstonIL60208 United States

ISBN: (纸本)9781557528209

A wavelength-tunable, silicon photon-pair source based on spontaneous four-wave mixing, integrated with a pump rejection filter in a single, flip-chip packaged CMOS chip, is demonstrated with a coincidence-to-accidentals ratio of 9.1 with no off-chip pump filtering. Frontiers in Optics / Laser science © Optica Publishing Group 2021.

关键词： CMOS integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Enhancing UAV Spraying Efficiency through Payload Sensor Integration

Enhancing UAV Spraying Efficiency through Payload Sensor Int...

引用

IEEE Latin American Robotics Symposium, LARS

作者： Celso O. Barcelos Leonardo A. Fagundes-Júnior Daniel C. Gandolfo Martin Saska Alexandre S. Brandão Department of Electrical Engineering Graduate Program in Computer Science Núcleo de Especialização em Robótica (NERo) Universidade Federal de Viçosa Viçosa MG Brazil Instituto de Automática National University of San Juan San Juan Argentine Department of Cybernetics Czech Technical University in Prague Prague Czech Republic

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

The use of UAVs has grown in recent years, leading to the prominence of various applications such as monitoring and inspection, search and rescue operations, dam and civil structure inspection, military applications, among others. One of the most relevant applications today is related to Precision Agriculture, which is the subject of this work. Our study analyzes the behavior of an Unmanned Autonomous Vehicle (UAV) used for spraying tasks. The variation of the payload is measured through a load sensor. This information indicates to the UAV the right time to return to the base for refueling or completion of the application. Experimental validation is carried out to assess the functionality of the payload sensor during flight operations. In addition, the dynamic compensation controller improves the navigation of the UAV, even in the presence of payload variations during the entire mission duration.

关键词： Precision agriculture Navigation Spraying Inspection Robot sensing systems Autonomous aerial vehicles Vehicle dynamics Monitoring Payloads Diseases

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services

TechRxiv

引用

TechRxiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Huang, Huawei Mao, Shiwen School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore School of Software Engineering Sun Yat-Sen University Zhuhai China Department of Electrical and Computer Engineering Auburn University Auburn United States

As Metaverse emerges as the next-generation Internet paradigm, the ability to efficiently generate content is paramount. AI-Generated Content (AIGC) emerges as a key solution, yet the resource-intensive nature of large Generative AI (GAI) models presents challenges. To address this issue, we introduce an AIGC-as-a-Service (AaaS) architecture, which deploys AIGC models in wireless edge networks to ensure broad AIGC services accessibility for Metaverse users. Nonetheless, an important aspect of providing personalized user experiences requires carefully selecting AIGC Service Providers (ASPs) capable of effectively executing user tasks, which is complicated by environmental uncertainty and variability. Addressing this gap in current research, we introduce the AI-Generated Optimal Decision (AGOD) algorithm, a diffusion model-based approach for generating the optimal ASP selection decisions. Integrating AGOD with Deep Reinforcement Learning (DRL), we develop the Deep Diffusion Soft Actor-Critic (D2SAC) algorithm, enhancing the efficiency and effectiveness of ASP selection. Our comprehensive experiments demonstrate that D2SAC outperforms seven leading DRL algorithms. Furthermore, the proposed AGOD algorithm has the potential for extension to various optimization problems in wireless networks, positioning it as a promising approach for future research on AIGC-driven services. The implementation of our proposed method is available at: https://***/Lizonghang/AGOD. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Identification of Features in ANN's Black Box using Dimensional Reduction and Correlation Analysis: A Case Study of Cardiovascular Disease Dataset

Identification of Features in ANN's Black Box using Dimensio...

引用

International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA)

作者： Boby Siswanto Yaya Heryadi Wayan Suparta Antoni Wibowo Haryono Soeparno Lukas Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research Group (CERG) Atma Jaya University Jakarta Indonesia

ISBN: (纸本)9781665499705

Artificial Neural Network (ANN) is a machine learning algorithm that can perform classification. ANN has limitations; namely, it has a black box working principle, which is unsure which feature is the most influential. This study is to identify the most influential features inside the ANN's black box using a classification model by applying Principal Component Analysis (PCA) dimension reduction combined with Pearson correlation analysis. The result of the proposed model can identify the name of the main features of the data inside the ANN's black box. This study uses two public Kaggle cardiovascular datasets. The first dataset consists of 13 features, and the second dataset consists of 12 features. The result is height and gender are the most influential features in the first dataset with the correlation value of 0.734; sex and smoking are the most influential features in the second dataset with the correlation value of 0.728. Black box model result with 2 PCA's features against a model with height and gender features in the first dataset resulting from the same accuracy on the test dataset of the classification prediction results with the value of 49.90%, while on the second dataset 58.30%.

关键词： Dimensionality reduction Analytical models Correlation Mechatronics Machine learning algorithms Artificial neural networks Predictive models

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：