检索结果-内蒙古大学图书馆

Autonomous Valet Parking Using Camera Switching and Car Headings

Journal of Institute of Control, Robotics and Systems 2022年第3期28卷 273-279页

作者： Kim, Woo Bin Kim, Ye Bin Hong, Yu Min Hwang, Sung Soo School of Computer Science and Electrical Engineering Handong Global University Korea Republic of

Autonomous valet parking(AVP) is a system that allows a vehicle to detect a parking space and park without any human intervention. This paper explores the efficient use of monocular visual simultaneous localization and mapping(visual-SLAM) in AVP scenarios, while also highlighting several problems arising from current AVP methods. These problems include the difficulties of performing a loop closure in narrow places and the unreliability of the estimated scale between the real-world and SLAM maps. This paper explores two methods for resolving these problems. The first solution is to perform AVP without loop closure. This can be done through a camera switching method that uses the front camera while parking, and the rear camera in return driving scenarios. The second solution involves making use of an alternative automatic parking algorithm that utilizes a car’s heading. Most automatic parking algorithms utilize monocular visual-SLAM, but it is difficult to calculate an accurate scale using this method. The alternative automatic parking algorithm using a car's heading could eliminate these issues with scaling. Each method was tested in three different locations, returning average success rates of 80% in return driving and 93.3% in automatic parking. The methods highlighted in this paper only utilize cameras, which are inexpensive compared to other sensors and are expected to contribute to commercializing the AVP system. © ICROS 2022.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Bert-Based Transformer Model for Hate Speech Detection 5

Bert-Based Transformer Model for Hate Speech Detection

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Vardhan, Puvvadi Harsha Prasad, Hari Swaroop, Bandi Vishnu Reddy, Busa Thanuj Sathwik Venugopalan, Manju Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350376685

Hate speech recognition has emerged as a key problem in social media and should be addressed using multiple models. Machine learning models like CNN and LSTM have been used recently in creating successful hate-speech detection models that have been developed in the recent past but they have not proved to be highly discriminative. The use of BERT or any other transformer model will give increased performance owing to the ability of these models to grasp context. Other potential improvements include using new feature engineering techniques and ensemble methods in conjunction with these models. The datasetused for experimentation in the proposed work is annotated considering three categories hate, offensive, or normal. The proposed methodology has incorporated a data-balancing mechanism and experimented with a range of classifier models that belong to ML and DL models and the best results were reported for Bert based transformer model which is F1-score of 0.76. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Research on the Influence Mechanism of Technological Strength in the Field of Artificial Intelligence Based on Complex Network Theory 3

Research on the Influence Mechanism of Technological Strengt...

引用

3rd IEEE International Conference on Electrical engineering, Big Data and Algorithms, EEBDA 2024

作者： Li, Tong Wang, Ziming School of Computer Engineering and Science Shanghai University Shanghai China School of Management Shanghai University Shanghai China

ISBN: (纸本)9798350380989

The technological strength of a company is crucial for partner selection and investment decisions. A strong technological strength enables the company to seize industry trends and technological frontiers, maintaining a competitive advantage. Open innovation is a method that promotes the development and growth of a company by strengthening connections and collaborative exchanges with the external environment. This study, based on the theory of complex networks, focuses on the research subject of an AI company and explores the relationship between open innovation, network structure, and technological strength. The research findings reveal that open precision has a positive impact on technological strength, while open breadth has a negative impact. Network structural holes negatively moderate the relationship between open precision and technological strength and intensify the negative impact of open breadth on technological strength. On the other hand, network degree centrality positively moderates the influence of open breadth on technological strength. The research results are significant for understanding the mechanism through which open innovation affects the technological strength of a company. © 2024 IEEE.

关键词： Artificial Intelligence Complex Network Theory Network Structure Open Innovation Technological Strength

来源：评论

学校读者我要写书评

暂无评论

QuerySpeak: From Human Language to Database Queries 5

QuerySpeak: From Human Language to Database Queries

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Reddy, Tadi Sai Vishruth Charitha, Talluri Sathwik, T. Samitha, V. Panda, Niharika Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350376685

The project introduces a new Natural Language to SQL Query Converter implemented using Lex and Yacc tools. We aim to bridge the separation between human-readable statements and machine-executable SQL queries. By leveraging Lex for tokenization and Yacc for parsing, the system expertly navigates the conversion process, precisely extracting vital components from input statements. The Lex and Yacc implementations rely heavily on precise grammar rules to convert natural language expressions into SQL queries seamlessly. By encapsulating the semantics of typical database interactions, these rules enable the system to interpret user intentions and translate them into a suitable format for database execution. We will be implementing three main components in this project. The first involves inserting new statements and updating existing statements as needed. And lastly, we will be displaying the requested information. This project will showcase the impressive capabilities of Lex and Yacc as they convert unstructured natural language into structured database queries that can be efficiently executed. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Comparative of SVM and Decision Tree Techniques for Predicting Hydroponic Tomato Growth and Yield Using Deep Water Culture

Comparative of SVM and Decision Tree Techniques for Predicti...

引用

2024 International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies, 3ICT 2024

作者： Pavan kalyan, B. Surendran, R. Krishnan, Sumathy Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (纸本)9798331533137

The purpose of this research is to evaluate the effectiveness of SVM and Decision Tree techniques in the context of hydroponic tomato cultivation using the Deep Water Culture (DWC) method. We assess the prediction power of various machine learning techniques with respect to tomato growth, yield, and quality characteristics using a variety of inputs relevant to hydroponic systems. We use the DWC approach to collect data from hydroponic tomato farms. The collection includes a wide range of environmental parameters, including pH values, water temperature, illumination, and nutrient concentrations. It also contains measures unique to plants, like yield, fruit size, and leaf area. The dataset's pertinent features, which include growth characteristics, environmental factors, and nutrient levels, are found. After processing, these chosen features are prepared for model training. SVM and Decision Tree techniques are tested in a hydroponic Deep Water Culture (DWC) system to predict tomato growth, production, and quality. The pH, temperature, illumination, and nutrient levels of hydroponic tomato farms were recorded, along with plant parameters like yield, fruit size, and leaf area. Feature selection and preprocessing prepared data for model training. Decision Tree and SVM predicted tomato production metrics well. SVM had better precision in some circumstances, while Decision Tree was easier to interpret and apply. These algorithms can optimize hydroponic tomato growing, and future research should use ensemble methods to improve forecast accuracy and reliability. ©2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

IMM-Based PMBM Filter for Maneuvering Extended Target Tracking

IMM-Based PMBM Filter for Maneuvering Extended Target Tracki...

引用

2024 Sensor Data Fusion: Trends, Solutions, Applications, SDF 2024

作者： Gu, Jiayi Shi, Jiaqi Shi, Kun Yang, Chaoqun Cao, Xianghui School of Automation Southeast University Nanjing China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798331527440

In the real-world scenarios of maneuvering extended target tracking (METT), targets always exhibit complex motion patterns, making it challenging for traditional tracking methods with single motion model to accurately capture their trajectories. To address this challenge, this paper proposes an interacting multiple model (IMM) based Poisson multi-Bernoulli mixture (PMBM) filter to track maneuvering extended targets. In this paper, we first introduce the basic model of the maneuvering extended targets. Then, we present the proposed IMM-based PMBM filter in detail. Finally, simulation experiments are conducted, which demonstrate the superior performance of the proposed filter in the term of tracking multiple maneuvering extended targets. © 2024 IEEE.

关键词： interacting multiple model maneuvering extended target tracking Poisson multi-Bernoulli mixture filter

来源：评论

学校读者我要写书评

暂无评论

CCIL: CONTINUITY-BASED DATA AUGMENTATION FOR CORRECTIVE IMITATION LEARNING 12

CCIL: CONTINUITY-BASED DATA AUGMENTATION FOR CORRECTIVE IMIT...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Ke, Liyiming Zhang, Yunchu Deshpande, Abhay Srinivasa, Siddhartha Gupta, Abhishek Paul G. Allen School of Computer Science and Engineering University of Washington United States

We present a new technique to enhance the robustness of imitation learning methods by generating corrective data to account for compounding errors and disturbances. While existing methods request interactive experts, additional offline datasets, or domain-specific invariances, our approach requires minimal additional assumptions beyond access to expert data. Our key insight is to leverage local continuity in the environment dynamics to generate corrective labels. Our method constructs a dynamics model from expert demonstrations, emphasizing local Lipschitz continuity in the learned model. In regions exhibiting local continuity, our algorithm generates corrective labels within the neighborhood of the demonstrations, extending beyond the actual set of states and actions in the dataset. Training on the augmented data improves the agent's resilience against perturbations and its capability to address compounding errors. To validate the efficacy of our generated labels, we conduct experiments across diverse robotics domains in simulation, encompassing classic control problems, drone flying, navigation with high-dimensional sensor observations, legged locomotion, and tabletop manipulation. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Object Detection Method Based on PVTv2 3

Object Detection Method Based on PVTv2

引用

3rd IEEE International Conference on Electronic Technology, Communication and Information, ICETCI 2023

作者： Chen, Yuzhe Zhuang, Zhe Chen, Cheng Air Force Engineering University Aviation Engineering School Xi'an China Zhuhai College of Science and Technology School of Computer Science Zhuhai China Shanghai Institute of Technology School of Computer Science & Information Engineering Shanghai China

ISBN: (纸本)9798350398410

Ship detection is the first barrier to ensure the safe operation of ships, to ensure that there are no serious technical loopholes or safety problems in the process of navigation. With the progress of remote sensing technology, the use of deep learning as a method for target detection has become a hot topic. Compared with the traditional manual detection method, the target detection algorithm based on deep learning has the following advantages of no need for manual feature design, good feature expression ability and excellent detection accuracy. At present, most of the methods used for ship detection are traditional methods, which are not robust to illumination, morphological direction changes, occlusion and so on. In this paper, three improvements are made to solve the above problems. Firstly, Transformer backbone network - PVTv2 is adopted. PVTv2 uses convolution to extract local continuous features, position coding with zero-padding, and attention layer with linear complexity of mean pooling, which can extract features more fully. Then, the width and depth of the pvt are increased to further extract features;Finally, the Cutout technology is used, which can improve the robustness and overall performance of the convolutional neural network, and improve the generalization ability of the model. Experimental results show that, compared with the original model, the average accuracy mean (mAP) is improved by 4. 39% on the HRSC2016 dataset, the validity of the model is proved. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Adaptive Frequency Enhancement Network for Single Image Deraining

Adaptive Frequency Enhancement Network for Single Image Dera...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Yan, Fei He, Yuhong Chen, Keyu Cheng, En Ma, Jikang School of Informatics Xiamen University Xiamen China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9781665410205

Image deraining aims to improve the visibility of images damaged by rainy conditions, targeting the removal of degradation elements such as rain streaks, raindrops, and rain accumulation. While numerous single image deraining methods have shown promising results in image enhancement within the spatial domain, real-world rain degradation often causes uneven damage across an image's entire frequency spectrum, posing challenges for these methods in enhancing different frequency components. In this paper, we introduce a novel end-to-end Adaptive Frequency Enhancement Network (AFENet) specifically for single image deraining that adaptively enhances images across various frequencies. We employ convolutions of different scales to adaptively decompose image frequency bands, introduce a feature enhancement module to boost the features of different frequency components and present a novel interaction module for interchanging and merging information from various frequency branches. Simultaneously, we propose a feature aggregation module that efficiently and adaptively fuses features from different frequency bands, facilitating enhancements across the entire frequency spectrum. This approach empowers the deraining network to eliminate diverse and complex rainy patterns and to reconstruct image details accurately. Extensive experiments on both real and synthetic scenes demonstrate that our method not only achieves visually appealing enhancement results but also surpasses existing methods in performance. The source code is available at https://***/yanfefei/AFENet. © 2024 IEEE.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

A survey on deep learning for polyp segmentation: techniques, challenges and future trends

引用

Visual Intelligence 2025年第1期3卷 1-20页

作者： Mei, Jiaxin Zhou, Tao Huang, Kaiwen Zhang, Yizhe Zhou, Yi Wu, Ye Fu, Huazhu PCA Lab Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Computer Science and Engineering Southeast University Nanjing China Institute of High Performance Computing A*STAR Singapore Singapore

Early detection and assessment of polyps play a crucial role in the prevention and treatment of colorectal cancer (CRC). Polyp segmentation provides an effective solution to assist clinicians in accurately locating and segmenting polyp regions. In the past, people often relied on manually extracted lower-level features such as color, texture, and shape, which often had problems capturing global context and lacked robustness to complex scenarios. With the advent of deep learning, more and more medical image segmentation algorithms based on deep learning networks have emerged, making significant progress in the field. This paper provides a comprehensive review of polyp segmentation algorithms. We first review some traditional algorithms based on manually extracted features and deep segmentation algorithms, and then describe benchmark datasets related to the topic. Specifically, we carry out a comprehensive evaluation of recent deep learning models and results based on polyp size, taking into account the focus of research topics and differences in network structures. Finally, we discuss the challenges of polyp segmentation and future trends in the field. © The Author(s) 2025.

关键词： Comprehensive evaluation Deep learning Medical imaging Polyp segmentation

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：