检索结果-内蒙古大学图书馆

3rd International conference on computer and Communication Engineering, CCCE 2023

作者： Song, Yoojeong Cho, Woo Jin Yoo, Juhan School of Computer Science Semyung University 65 Semyeong-ro Jecheon-si Korea Republic of

ISBN: (纸本)9783031352980

In general, it can suffer from the course of dimensionality in developing machine learning models using high-dimensional data. To solve this problem, various dimensionality reduction algorithms have been developed, and PCA is the most widely used dimensionality reduction algorithm. In this paper, the PCA algorithm is applied to deep learning-based stock price prediction models developed in previous studies and their performance changes are analyzed. The models used data expected to affect stock price fluctuations as input features, and the data consist of 715 and 250 high-dimensional features, respectively. As a result, they not only took a lot of time in the model training and testing but also had the disadvantage of generating noises. Therefore, in this paper, the number of input features used in previous studies was reduced by using the dimension reduction method, and the performance change was analyzed. As a result of the experiment, it was confirmed that the models to which the PCA is applied have improved training speed and performance compared to the model without the PCA. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

A Coarse to Fine Detection Method for Prohibited Object in X-ray Images Based on Progressive Transformer Decoder 24

A Coarse to Fine Detection Method for Prohibited Object in X...

引用

32nd ACM International conference on Multimedia, MM 2024

作者： Ma, Chunjie Du, Lina Gao, Zan Zhuo, Li Wang, Meng Shandong Jinan China School of Computer Science and Technology Shandong Jianzhu University Shandong Jinan China Faculty of Information Technology Beijing University Of Technology Beijing China School of Computer Science and Information Engineering Hefei University of Technology Anhui Hefei China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China

ISBN: (纸本)9798400706868

Currently, Transformer-based prohibited object detection methods in X-ray images appear constantly, but there are still some shortcomings such as poor performance and high computational complexity for prohibited object detection with heavily occlusion. Therefore, a coarse to fine detection method for prohibited object in X-ray images based on progressive Transformer decoder is proposed in this paper. Firstly, a coarse to fine framework is proposed, which includes two stages: coarse detection and fine detection. Through adaptive inference in stages, the computational efficiency of the model is effectively improved. Then, a position and class object queries method is proposed, which improves the convergence speed and detection accuracy of the model by fusing the position and class information of prohibited object with object queries. Finally, a progressive Transformer decoder is proposed, which distinguishes high and low score queries by decreasing confidence thresholds, so that high-score queries are not affected by low-score queries in the decoding stage, and the model can focus more on decoding low-score queries, which usually correspond to prohibited object with severe occlusion. The experimental results on three public benchmark datasets (SIXray, OPIXray, HiXray) demonstrate that compared with the baseline DETR, the proposed method achieves the state-of-the-art detection accuracy with a 21.6% reduction in model computational complexity. Especially for prohibited objects with heavily occlusion, accurate detection can be carried out. © 2024 ACM.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

RTT Algorithm Optimization with Out-of-Order Retransmission Detection 21

RTT Algorithm Optimization with Out-of-Order Retransmission ...

引用

21st International computer conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2024

作者： Wei, Jiang Bin, Zhang Wenyong, Wang Qixun, Zhu School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China China Telecom Sichuan Branch Sichuan Chengdu610012 China International Institute of Next Generation Internet Macau University of Science and Technology 999078 China Sichuan Communication Research Planning & Designing Co. Ltd. China

ISBN: (纸本)9798331519254

Traditional Round-Trip Time (RTT) algorithms often struggle with maintaining accuracy under conditions of packet retransmissions and disorder, resulting in RTT estimations that fall outside the expected range. This can lead to misinterpretations of network health and performance. In response to this challenge, our research introduces an enhanced RTT calculation method designed for implementation within network devices. Our approach involves a bidirectional monitoring mechanism for detecting packet retransmissions during the process of traffic interception. By doing so, we aim to refine the precision of RTT estimations through meticulous packet inspection. Our novel algorithm is rigorously tested under simulated environments that mimic fluctuating network conditions. The outcomes clearly indicate that our methodology successfully screens out anomalous RTT values, which are typically introduced by packet retransmissions or disorder. Consequently, this leads to a substantial enhancement in the accuracy of RTT calculations. Our findings suggest that the adoption of this optimized RTT algorithm could significantly improve the reliability of network performance monitoring systems, making it a promising solution for real-world network management applications. The comparative experimental results of RTT optimization before and after simulating abnormal network environments show that the peak value of sudden abnormal RTT over the family side and the network side after optimization is reduced by about 75.8% and 99.5%, respectively. © 2024 IEEE.

关键词： Bidirectional RTT Tracking Disorderly order Retransmission

来源：评论

学校读者我要写书评

暂无评论

ALISA: An Adaptive Learned Index Structure for Spatial Data on Solid-State Drives 24

ALISA: An Adaptive Learned Index Structure for Spatial Data ...

引用

43rd International conference on computer-Aided Design, ICCAD 2024

作者： Lin, Che-Wei Wu, Chun-Feng Department of Computer Science National Yang Ming Chiao Tung University Taiwan

ISBN: (纸本)9798400710773

Spatial learned index is becoming popular as a solution to relieve the intense storage demands and high I/O costs of spatial databases. LISA, the original and most prominent spatial learned index structure, is tailored for HDD-resident spatial data and comes with strict data arrangement requirements. Given that direct SSD migration may drastically impair SSD durability especially when page utilization is low, this work aims to adapt this innovative index structure to SSDs to leverage the faster performance and expand application possibilities. We propose an Adaptive Learned Index structure for Spatial dAta on SSDs (ALISA), with mechanisms to persistently monitor updated data distribution and adaptively restructure to align with SSD access characteristics. The evaluation results show that ALISA can significantly extend SSD lifespan and improve low page utilization, thereby enhancing query performance. © 2024 Copyright is held by the owner/author(s).

关键词： Dynamic random access storage

来源：评论

学校读者我要写书评

暂无评论

Active Contrastive Learning With Noisy Labels in Fine-Grained Classification

Active Contrastive Learning With Noisy Labels in Fine-Graine...

引用

2024 International conference on Electronics, Information, and Communication, ICEIC 2024

作者： Kim, Byeong-Il Ko, Byung Chul Keimyung University Dept. of Computer Engineering Korea Republic of

ISBN: (纸本)9798350371888

In real-world scenarios mirroring fine-grained datasets, labeling may result in noisy labels due to ambiguous data characteristics. This study introduces a new classification approach that integrates active and contrastive learning to address the issue of highly noisy labels in fine-grained datasets. We strategically employ active learning to select boundary points near class-dependent decision boundaries, effectively expanding the distances between classes in the data space. By combining contrastive learning and active learning, we successfully extract robust features from the data. Our experiments consistently achieve high average performance across various levels of label noise, highlighting the potential of our approach in fine-grained datasets. This underscores the method's capability to maintain reliable performance even in the presence of label noise, contributing to the field of fine-grained classification and noisy label mitigation. This innovative approach provides promising insights for enhancing the performance of machine learning models in fine-grained classification tasks. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

performance Evaluation of DL Models of Low-Size Datasets for AMC in MIMO System

Performance Evaluation of DL Models of Low-Size Datasets for...

引用

2024 IEEE International conference on Consumer Electronics, ICCE 2024

作者： Helmy, Islam Choi, Wooyeol Chosun University Dept. of Computer Engineering Gwangju Korea Republic of

ISBN: (纸本)9798350324136

Automatic modulation classification (AMC) is one of the foremost challenges in multi-input multi-output (MIMO) systems. In literature, various approaches have been presented where the deep learning (DL) models show remarkable performance. However, the existing methods mainly focus on training using large datasets, which is insignificant in high-mobility environments where rapid changes occur. In this study, we investigate the performance of existing DL models for small datasets and reduce the complexity by eliminating the equalizer. We apply two DL models to estimate the channel modulation among four modulation techniques. We also vary the number of transmitters for different datasets where the number of receiver antennas is 4 and 8, respectively. Furthermore, we verify the signal-To-noise ratio (SNR) of 0 to 40 dB. The results show that the convolutional neural network (CNN) performs better than the multi-layer perceptron (MLP) applied to the different datasets. © 2024 IEEE.

关键词： Automatic modulation classification deep learning MIMO

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Real-Time Multi-Person Pose Detection in Electrical Industrial Safety Scenarios Using YOLOv8-Pose and OpenPose 4

Comparative Analysis of Real-Time Multi-Person Pose Detectio...

引用

4th IEEE International conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Tsai, Shang-Te Wu, Zong-Rong Lin, Pin-Hsuan Chen, Chin-Hsiung Chien, Wei Chang, Yu-Cheng School of Art and Design Sanming University Fujian365004 China National Yunlin University of Science and Technology Department of Technical and Vocational Program in Artificial Intelligence Yunlin Taiwan National Central University Department of Business Administration Taoyuan Taiwan Commercial Industrial Vocational Senior High School Department of Electrical Engineering New Taipei Municipal Tamsui New Taipei Taiwan Lunghwa University of Science and Technology Department of Computer Information and Network Engineering Taoyuan Taiwan National Taipei University of Technology Department of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350360721

We reviewed the application of modern technology for rapid and accurate multi-person real-time pose detection in the hazardous field of electrical engineering. We focused on two leading pose detection technologies: YOLOv8 and OpenPose. To optimize performance, we integrated these two techniques into the LSTM model for training and investigated frame rates and accuracy. © 2024 IEEE.

关键词： Accident prevention

来源：评论

学校读者我要写书评

暂无评论

Anti-Dynamic SSDF Attack Scheme Based on Credit Mechanism 4

Anti-Dynamic SSDF Attack Scheme Based on Credit Mechanism

引用

4th International conference on Electronic Information Engineering and computer Technology, EIECT 2024

作者： Zhi, Xijie Cao, Yuanyao Liu, Xinyi Chang'an University Xi'an China Shanghai Shixi High School Shanghai China

ISBN: (纸本)9798331528850

In order to mitigate the effects of multi-path fading and solve the hidden terminal problem, cooperative spectrum sensing (CSS) is seen as an effective method to improve detection accuracy. However, CSS systems are themselves vulnerable to attacks by malicious nodes, especially spectrum sensing data falsification (SSDF) attacks. These attacks can cause damage to its performance. Thus, a dynamic SSDF attack security scheme based on credit mechanism is proposed in this paper. The core of this scheme is that the fusion center uses beta reputation system to assign reputation values to secondary users (SUs) according to their current and historical sensing behavior. On this basis, a punishment scheme to modify reputation is designed. This overall strategy not only significantly reduces the interference of malicious behaviors on the decision-making process but also greatly enhances the fairness and robustness of the system, providing a more stable and reliable environment for CSS. © 2024 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

high performance Computing for Science and Engineering in the Department of Defense

引用

COMPUTING IN SCIENCE & ENGINEERING 2021年第6期23卷 58-62页

作者： Barton, Joseph Army Res Lab Aberdeen Proving Ground MD 21005 USA

Computing has changed science and engineering since the introduction of the first general-purpose scientific computer in 1946, the Electronic Numerical Integrator and computer (ENIAC), produced by the University of Pennsylvania for the Army. The ENIAC was created for studying the science of ballistics and for the development, testing, and fielding of Army ordnance. Since that time computing has provided access to larger parameter spaces for design, more cases analyzed in a given unit of time or budget, and access to phenomena not measurable or to conditions not accessible to experimentation. Science and engineering continue to change computing, creating demand for ever larger and faster platforms, illuminating new phenomena that lead to new materials, components, fabrication techniques, architectures, and entirely new types of computing. We describe the Department of Defense high performance Computing modernization program, its impact on problem solving, and on our primary customer, the Warfighter.

关键词： US Department of Defense high performance computing Software Hip Computational modeling Benchmark testing Tools I6 Simulation Modeling and Visualization J2 Physical Sciences and Engineering K2 History of Computing

来源：评论

学校读者我要写书评

暂无评论

Holographic visualization of neuronal volume images based on layered angular spectrum theory 4

Holographic visualization of neuronal volume images based on...

引用

4th International conference on Image Processing and Intelligent Control, IPIC 2024

作者： Gao, Ziqin Wang, Yimin School of Computer Engineering and Science Shanghai University Shanghai China Guangdong Institute of Intelligence Science and Technology Hengqin China

ISBN: (纸本)9781510682313

computer-generated holography (CGH) has undergone significant advancements in recent years. However, there are limited CGH methods designed for volume data. The realization of holographic visualization of volume image data with precise depth perception remains a challenging task. In this work, we propose a layered angular spectrum CGH method tailored for volume image data to achieve neuronal holographic visualization with accurate depth perception. The experimental results demonstrate that the proposed method enables holographic visualization of neuronal volume images with accurate depth perception. Moreover, we harness GPU parallel processing for hologram generation, achieving satisfactory temporal performance. © 2024 SPIE.

关键词： Neurons

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：