检索结果-内蒙古大学图书馆

8th international conference on computer science and Artificial Intelligence, CSAI 2024

作者： Aslam, Iqra Anpilogov, Igor Rausch, Andreas Institute for Software and System Engineering Clausthal University of Technology Clausthal Zellerfeld Germany

ISBN: (纸本)9798400718182

Autonomous driving technology is progressing rapidly, largely due to complex End-To-End systems based on deep neural networks. While these systems are effective, their complexity can make it difficult to understand their behavior, which raises safety concerns. This paper presents a new solution: a Behavior Selector that uses multiple smaller artificial neural networks (ANNs) to manage different driving tasks, such as lane following and turning. Rather than relying on a single large network, which can be burdensome, require extensive training data and is hard to understand. The developed approach allows the system to dynamically select the appropriate neural network for each specific behaviour (i.e. turns) in real time. We focus on ensuring smooth transitions between behaviors and taking into account the vehicle’s current speed and orientation to improve stability and safety. The proposed system has been tested using the AirSim simulation environment, demonstrating its effectiveness. © 2024 Copyright held by the owner/author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on design of image processing and recognition based on deep learning

Research on design of image processing and recognition based...

引用

2024 international conference on Physics, Photonics, and Optical Engineering, ICPPOE 2024

作者： Li, Yanan Wang, Hua Li, Yongbo Guangdong University of Science and Technology Guangdong Dongguan523668 China

ISBN: (数字)9781510689121

ISBN: (纸本)9781510689114

To achieve target detection and defect recognition in power inspection images, an image processing and recognition algorithm based on deep learning is proposed. This algorithm mainly adopts an improved Faster-RCNN model, combined with HSI color feature extraction, for real-time image processing and identification of various conventional faults. Firstly, the collected power inspection images are normalized, converting the RGB colors of the images to HSI colors. By traversing each pixel in HSI space, it is determined whether there is a fault in the pixel based on the color characteristics of the image. Secondly, a DenseNet network is constructed and connected to the RoIAlign layer and prediction layer. Finally, the identification of target defects is achieved through Faster-RCNN. Simulation results show that the algorithm can accurately identify fault defects with a precision of up to 94.60%, indicating a broad application prospect in power equipment defect recognition. © 2025 SPIE.

关键词： RGB color model

来源：评论

学校读者我要写书评

暂无评论

Real-Time Secure Video Streaming System Based on FPGA and CUDA technology 24

Real-Time Secure Video Streaming System Based on FPGA and CU...

引用

14th international conference on Communication and network Security, ICCNS 2024

作者： Liu, Ziyang Wang, Zongxia Tu, Shanshan Wang, Haoran Fan, Jingxuan Ren, Chang College of Computer Science Beijing University of Technology Beijing China The 6th Research Institute of China Electronics Corporation China Electronics Corporation Bejing China

ISBN: (纸本)9798400717994

In recent years, with the growing demand for real-time video transmission, ensuring the security of video stream data has become critical. This paper addresses the secure transmission of real-time video streams by using FPGA technology on the encryption side, where the SM4 algorithm is applied, and GPU-based CUDA acceleration on the decryption side. A simplified transmission protocol ensures both real-time performance and security. The system, tested on a Nexys A7 board and PC, achieved a frame rate of 27.78 fps, demonstrating its potential in applications such as drone video security, surveillance, and intelligent transportation systems. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Unleashing DeFi's Potential with Dharma network: Fusion of Functional Programming and Algorand Blockchain 16

Unleashing DeFi's Potential with Dharma Network: Fusion of F...

引用

16th international conference on ENTERprise Information Systems, CENTERIS 2024 - 12th international conference on Project MANagement, ProjMAN 2024 - 14th international conference on Health and Social Care Information Systems and Technologies, HCist 2024

作者： Macieira, Bruna Mota, Emanuel Ferreira, Luís Polytechnic Institute of Cávado and Ave School of Technology Barcelos4750-810 Portugal Yarilabs Braga4700-314 Portugal 2Ai-Applied Artificial Intelligence Lab School of Technology IPCA Barcelos4750-810 Portugal

Global income and social inequality remain pressing issues, intensified by traditional financial systems with centralized control and exclusionary practices. This study conducted a quantitative investigation into how Decentralized Finance (DeFi) can address these disparities by offering decentralized financial services via smart contracts and blockchain technology. First, an analysis of Dharma network, a decentralized application built on the Algorand blockchain, revealed its potential to reduce inequality by facilitating inclusive lending and borrowing mechanisms, particularly benefiting underserved communities. The study then examined the development and integration of new components in Dharma network using functional programming, which enhances system efficiency and expands its reach. Finally, the research demonstrated that Dharma network promotes a more effective valorization of participation, fostering accessibility and democratic involvement. These findings show that blockchain technology can reshape the financial landscape by advancing inclusivity, diversity, and economic freedom, offering a strategic direction toward a more equitable economic world. © 2025 The Author(s).

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

Paired Transmission in networks

Paired Transmission in Networks

引用

international conference on Computational Engineering, ICCE 2023

作者： Sujana G, Jessy Sharon, Jane Olive Anitha, J. Department of Computer Science SRM Institute of Science and Technology Vadapalani Chennai India Department of Computing Technologies SRM Institute of Science and Technology Chennai India Department of Mathematics Rajalakshmi Institute of Technology Chennai India

ISBN: (纸本)9783031777639

The transmission of a vertex is defined as the sum of the lengths of all shortest paths between the chosen vertex and all other vertices in G. The transmission of a graph G is the sum of the transmissions of all its vertices which is nothing but twice its Wiener index. In location theory, sets of vertices, with the minimum (or maximum) distance in a graph, play a special role because they form target sets for locations of facilities. The framework is made more general by considering the sum of distances to a specified multiset of vertices referred to as profiles. In this paper, we have defined paired transmission of vertices for a network as a special case of profiles, referred to as a paired facility location. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： network theory (graphs)

来源：评论

学校读者我要写书评

暂无评论

The application of artificial intelligence seismic inversion techniques in sandstone and shale reservoir studies 3

The application of artificial intelligence seismic inversion...

引用

3rd international conference on Geographic Information and Remote Sensing technology, GIRST 2024

作者： Lin, Yaoting Liang, Lin Zhou, Wei School of Computer Science and Engineering Guangdong Ocean University Yangjiang529500 China Kunlun Digital Technology Co. Ltd. Beijing Beijing100043 China

ISBN: (纸本)9781510689077

Artificial Intelligence Probabilistic Neural networks are a type of neural network based on the theory of probability density functions, widely applicable in areas such as pattern recognition. Addressing the current issue of low prediction accuracy in seismic lithology inversion, the authors propose a specific probabilistic neural network method, including the construction of network models and steps for prediction and identification. The primary target layer in the study area is the lower part of the Sha-1 Member of the Shaximiao Formation, characterized by lakeshore and river channel sands. The reservoirs are thin-layered with significant lateral lithological variations, making conventional reservoir prediction using seismic data challenging. Therefore, leveraging the correlation between well log responses, seismic attributes, and geological lithological characteristics of the reservoirs in the area, the probabilistic neural network method is employed to transform seismic attribute data for predicting and identifying stratigraphic features. This approach has achieved good results in practical data processing. © 2025 SPIE.

关键词： Stratigraphy

来源：评论

学校读者我要写书评

暂无评论

Immoral post detection using a one-dimensional convolutional neural network-based LSTM network

引用

Multimedia Tools and Applications 2025年 1-20页

作者： Saqia, Bibi Khan, Khairullah Rahman, Atta Ur Khan, Aurangzeb Jain, Deepak Kumar Department of Computer Science University of Science and Technology Bannu28100 Pakistan Riphah Institute of Systems Engineering Riphah International University Islamabad46000 Pakistan Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China Symbiosis Institute of Technology Symbiosis International University Pune India

In text mining and Natural Language Processing (NLP), extracting emotions from textual data is gaining rapid attraction. The proliferation of online content and the freedom of expression on social media platforms has compelled the advancement of more sophisticated methods for the automatic identification of unwanted content. The One-Dimensional Convolutional Neural network (1D-CNN) performs best for feature extraction, while the Long Short-Term Memory network (LSTM) is well-known for extracting sequential features and classification of textual data. This study proposes a novel solution by combining 1D-CNN with LSTM. Utilizing a context-aware model, this study aims to enhance the detection of immoral posts, including hate speech and other forms of immoral content on social media platforms. Various posts are extracted from social media, which are then processed using Glove word embedding models. It depicts the word representations in the text, which yields the form of a real-valued vector determining the words' meaning. The 1D convolution utilizes a filter window over the input time-series data to extract features. Relying on the acquired parameters of the filters, they act as feature extractors. This feature extraction technique allows the model to distinguish detailed patterns and nuances from the textual contents of posts. The sequential processing capabilities of the LSTM network enable an in-depth examination of the text, capturing temporal relationships and context, which is critical for successful content categorization. To validate the proposed model, we utilized a benchmark dataset, called the Twitter dataset. The proposed model achieved the highest accuracy of 95.37% and outperforms state-of-the-art works. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on Financial Time Series Prediction based on Neural network 24

Research on Financial Time Series Prediction based on Neural...

引用

5th international conference on computer science and Management technology, ICCSMT 2024

作者： Xiang, Chengye Finance Columbia University Los AngelesCA United States

ISBN: (纸本)9798400709999

At present, financial time series forecasting analyzes and predicts future movements in financial markets through the use of various technical means. However, financial time series data often exhibit significant nonlinear characteristics, which brings many challenges to forecasting future development. The model initiates the preprocessing of the input financial time series data with the objective of removing noise and standardising the data. Subsequently, the model employs a hierarchical long-short-term memory (LSTM) neural network structure, wherein the long-short-term units of each layer are designed to capture dependencies at varying time scales. The underlying LSM unit is primarily responsible for capturing short-term dependencies, while the upper LSM unit is tasked with extracting long-term trends and global patterns. Furthermore, the model incorporates an attention mechanism that enables it to adaptively modulate the level of attention at distinct time points, thereby facilitating more precise identification and accentuation of the temporal instances that are most pivotal to the prediction outcome. To enhance the precision of the model's predictions, an adaptive learning rate optimiser is employed, enabling the model to autonomously calibrate the training procedure in accordance with the data's complexity. In the experimental analysis, the proposed model is compared with the benchmark model, and the results demonstrate that it is more effective in capturing the intricate patterns of financial time series data. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

BiMA: Bidimensional multi-level attention embedded network for single-frame infrared small target detection

BiMA: Bidimensional multi-level attention embedded network f...

引用

2025 IEEE international conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Deng, He Yin, Xiaojie Lan, Xianmin School of Computer Science and Technology Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9798350368741

As the depth of the detection network increases, features of small targets become less pronounced, and the model may inadvertently favor background clutter, thereby reducing the efficiency of target detection. Hence, a bidimensional multilevel attention-embedded network, named BiMA, is designed to simultaneously tackle original images rich in detail and filtered images that remove superfluous non-target elements, serving as its dual-input framework. Subsequently, a multi-scale fusion is raised to harness multi-scale properties of these images, offering a thorough grasp of both high-level and low-level features. In addition, a multi-level attention is integrated to further improve the detection capability. Extensive qualitative and quantitative experiments prove that BiMA not only surpasses contemporary approaches in robustly detecting small targets across a range of challenging scenarios but also has superior performance, e.g., higher probabilities of detection, reduced false alarm rates, and broader areas under receiver operating characteristic curves. © 2025 IEEE.

关键词： infrared small target detection multi-level attention multi-scale fusion single frame

来源：评论

学校读者我要写书评

暂无评论

Demand Forecasting in Transportation: A Graph Attention networks for Predicting Bus Ridership 27

Demand Forecasting in Transportation: A Graph Attention Netw...

引用

27th international conference on Advanced Communications technology, ICACT 2025

作者： Munkhbayar, Tsetsentsengel Dashdorj, Zolzaya Jargalsaikhan, Zoljargal Tae-Koo, Kang Altangerel, Erdenebaatar Department of Computer Science Mongolian University of Science and Technology Ulaanbaatar Mongolia Department of Human Intelligence and Robot Engineering Sangmyung University Seoul Korea Republic of

ISBN: (纸本)9791188428137

Demand prediction in transportation systems plays a critical role in optimizing resources and improving service efficiency. This study explores demand prediction for Ulaanbaatar's public transportation network using Graph Attention networks (GATs), Convolutional Neural networks (CNNs), and Generative Adversarial networks (GANs). GATs effectively capture spatial relationships, achieving the best performance while GANs struggle with stability and convergence issues. The findings emphasize the potential of using graph-based methods that incorporate key stations in the analysis of public transportation networks for predicting transit demand. Copyright 2025 Global IT Research Institute (GIRI). 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：