检索结果-内蒙古大学图书馆

2023 International Conference on Advancement in Computation and computer Technologies, InCACCT 2023

作者： Kantapalli, Bhaskar Meruga, Siva Gnani Polagani, Prasanthi Pingali, Venu Babu Seelam, Surya Teja Seshadri Rao Gudlavalleru Engineering College Dept. of Computer Science and Engineering Gudlavalleru India Seshadri Rao Gudlavalleru Engineering College Dept. of Computer Science and Engineering Mandavalli India Seshadri Rao Gudlavalleru Engineering College Dept. of Computer Science and Engineering Vijayawada India Seshadri Rao Gudlavalleru Engineering College Dept. of Computer Science and Engineering Machilipatnam India

ISBN: (纸本)9798350396485

Data security is a major issue for computer users these days. So, we conceal the textual data using steganography, the art and science of concealing information. In this case, we conceal both the message's content and the fact that it is being sent. In order to make it challenging to Figure out that a hidden message is present in a specific film, this technique involves concealing secret data within a conventional, non-secret file. At its destination, the secret data is subsequently removed. Several uses of steganographic technology have distinct requirements. Here, we suggest a method for concealing data, including reverse data hiding for data extraction. The textual data will be secured in different frames of the video and audio using the Least Significant Bit (LSB) and related algorithms. We can conclude that the original data will never change the characteristics of video or audio even after applying steganography techniques. © 2023 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

Robust Line-Convex Polygon Intersection Computation in E2 using Projective Space Representation

引用

Machine Graphics and Vision 2023年第3-4期32卷 3-16页

作者： Skala, Vaclav Dept. of Computer Science and Engineering Faculty of Applied Sciences University of West Bohemia Pilsen Czech Republic

This paper describes modified robust algorithms for a line clipping by a convex polygon in E2 and a convex polyhedron in E3. The proposed algorithm is based on the Cyrus-Beck algorithm and uses homogeneous coordinates to increase the robustness of computation. The algorithm enables computation fully in the projective space using the homogeneous coordinates and the line can be given in the projective space, in general. If the result can remain in projective space, no division operation is needed. It supports the use of vector-vector operations, SSE/AVX instructions, and GPU. © 2023 Institute of Information Technology, Warsaw University of Life sciences - SGGW. All rights reserved.

关键词： computer graphics

来源：评论

学校读者我要写书评

暂无评论

Comparison of Faster RCNN and YOLO V3 for Video Anomaly Localization

Comparison of Faster RCNN and YOLO V3 for Video Anomaly Loca...

引用

2023 International Conference on Power, Instrumentation, Control and Computing, PICC 2023

作者： Anoopa, S. Salim, A. Nadera Beevi, S. College of Engineering Trivandrum Dept. of Computer Science and Engineering Kerala India Government Engineering College Thrissur Dept. of Computer Science and Engineering Kerala India Tkm College of Engineering and Technology Dept. of Computer Applications Kerala India

ISBN: (纸本)9798350334463

Video Anomaly Localization techniques are interesting and emerging tasks in computer vision that is used to locate the position of an anomalous object with bounding boxes. Convolutional neural network-based object localization methods have been developed which detect and classify objects with high precision and accuracy. Many algorithms have been developed for object detection and localization with excellent outcomes. These algorithms are fast RCNN, faster RCNN, and YOLO. In this paper, a comprehensive analysis of faster RCNN and YOLO V3 algorithms for anomaly localization is performed based on the parameters FPS, mAP, Precision, Recall and F1 Score. © 2023 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Beamforming and Phased Arrays: Elevating MIMO-OFDM Systems for Next-Generation Wireless Networks

Beamforming and Phased Arrays: Elevating MIMO-OFDM Systems f...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Upadhyay, Deepak Sharma, Kunj Bihari Gupta, Mridul Upadhyay, Abhay Yadav, Satya Prakash Graphic Era Hill University Dept. of Computer Science and Engineering Dehradun India Graphic Era Deemed to be University Dept. of Computer Science and Engineering Dehradun India Graphic Era Deemed to be University Dept. of Electronics and Communication Engineering Dehradun India Bennett University School of Computer Science Engineering and Technology Greater Noida India

ISBN: (纸本)9798350378092

This study explores the optimisation of Multiple Input Multiple Output-Orthogonal Frequency Division Multiplexing (MIMO-OFDM) systems through the use of phased arrays and advanced beamforming methods. With a focus on overcoming the challenges that come with 5G wireless communication, like high data rate needs, interference resistance, and efficient spectrum usage, this work presents a novel approach that combines dynamic beam steering and adaptive precoding to significantly enhance system performance. Through thorough modelling, we demonstrate considerable improvements in bit error rates (BER), throughput, and spectrum efficiency compared to traditional MIMO-OFDM configurations. The results demonstrate a 25% improvement in throughput and a 40% reduction in BER in densely populated metropolitan environments, underscoring the potential of phased arrays and beamforming to further improve 5G network performance. This work not only validates the efficacy of the proposed enhancements but also establishes a foundation for future advancements in wireless communication systems by highlighting the critical roles that phased arrays and beamforming will play in achieving the maximum potential of 5G technology. © 2024 IEEE.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

Dynamic View Synthesis of Thin Structures with Short-term Movements from Monocular Videos Using Neural Radiance Fields 25

Dynamic View Synthesis of Thin Structures with Short-term Mo...

引用

25th International Conference on Digital Image Computing: Techniques and Applications, DICTA 2024

作者： Rajapaksha, Uchitha Laga, Hamid Diepeveen, Dean Bennamoun, Mohammed Sohel, Ferdous School of Information Technology Murdoch University MurdochWA Australia The University of Western Australia Dept. of Computer Science and Software Engineering CrawleyWA Australia

ISBN: (纸本)9798350379037

Learning to generate motions of thin structures such as plant leaves in dynamic view synthesis is challenging. This is because thin structures usually undergo small but fast, non-rigid motions as they interact with air and wind. When given a set of RGB images or videos of a scene with moving thin structures as input, existing methods that map the scene to its corresponding canonical space for rendering novel views fail as the object movements are too subtle compared to the background. Disentangling the objects with thin parts from the background scene is also challenging when the parts show fast and rapid motions. To address these issues, we propose a Neural Radiance Field (NeRF)-based framework that accurately reconstructs thin structures such as leaves and captures their subtle, fast motions. The framework learns the geometry of a scene by mapping the dynamic images to a canonical scene in which the scene remains static. We propose a ray masking network to further decompose the canonical scene into foreground and background, thus enabling the network to focus more on foreground movements. We conducted experiments using a dataset containing thin structures such as leaves and petals, which include image sequences collected by us and one public image sequence. Experiments show superior results compared to existing methods. Video outputs are available at https://***/. © 2024 IEEE.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Reference-based Burst Super-resolution 24

Reference-based Burst Super-resolution

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Ko, Seonggwan Koh, Yeong Jun Cho, Donghyeon Dept. of Electronics Engineering Chungnam National University Daejeon Korea Republic of Dept. of Computer Science & Engineering Chungnam National University Daejeon Korea Republic of Dept. of Computer Science Hanyang University Seoul Korea Republic of

ISBN: (纸本)9798400706868

Burst super-resolution (BurstSR) utilizes signal information from multiple adjacent frames successively taken to restore rich textures. However, due to hand tremors and other image degradation factors, even recent BurstSR methods struggle to reconstruct finely textured images. On the other hand, reference-based super-resolution (RefSR) leverages the high-fidelity reference (Ref) image to recover detailed contents. Nevertheless, if there is no correspondence between the Ref and the low-resolution (LR) images, the degraded output is derived. To overcome the limitations of existing BurstSR and RefSR methods, we newly introduce a reference-based burst super-resolution (RefBSR) that utilizes burst frames and a high-resolution (HR) external Ref image. The RefBSR can restore the HR image by properly fusing the benefits of burst frames and a Ref image. To this end, we propose the first RefBSR framework that consists of Ref-burst feature matching and burst feature-aware Ref texture transfer (BRTT) modules. In addition, our method adaptively integrates features with better quality between Ref and burst features using Ref-burst adaptive feature fusion (RBAF). To train and evaluate our method, we provide a new dataset of Ref-burst pairs collected by commercial smartphones. The proposed method achieves state-of-the-art performance compared to both existing RefSR and BurstSR methods, and we demonstrate its effectiveness through comprehensive experiments. The source codes and the dataset are available at https://***/SeonggwanKo/RefBSR. © 2024 ACM.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Deep Analysis of Machine Learning Techniques for the Effective Retrieval of Images Based on Content 2

Deep Analysis of Machine Learning Techniques for the Effecti...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Jain, Ashish Varshney, Sudeep Set Sharda University Dept. of Computer Science and Engineering Greater Noida India G L Bajaj Institute of Technology and Management Dept. of Computer Science and Engineering Greater Noida India

ISBN: (纸本)9798350371055

Our research aims to investigate how machine learning techniques can be applied for efficient image retrieval based on content. It is a very difficult process to obtain accurate images from vast digital image collections. CBIR has been particularly interested in this area. It has been shown that content- or feature-based approaches are more effective than text-based query techniques. Research has shown that the performance of these methods varies depending on the type and size of the data set analyzed, with some algorithms performing well for specific small data sets and others for larger data sets. This article provides a comprehensive and systematic review of effective methods for obtaining the image. The paper's objective is to examine different ML classifiers that are applied via the researchers and compare their results based on accuracy and performance. These algorithms include SVM, KNN, random forest, BoVW, Naive Bayes, and LDA. This review paper can assist researchers in selecting the best classifier for their research, as well as in improving existing classifiers by combining them with other algorithms. © 2024 IEEE.

关键词： CBIR classifier feature extraction Random Forest SVM

来源：评论

学校读者我要写书评

暂无评论

TSPvis: A Temperature Sensitive Paint Formulation Visual Design System 6

TSPvis: A Temperature Sensitive Paint Formulation Visual Des...

引用

6th IEEE International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2023

作者： Liao, Jing Wu, Yadong Wang, Guijuan Wang, Fupan Chen, Huarong Long, Li Southwest University of Science and Technology Dept. Computer Science and Technology Mianyang China Sichuan University of Science and Engineering Dept. Computer Science and Engineering Yibin China

ISBN: (纸本)9798350325485

The composition and proportion parameters of temperature sensitive paint formulation are complex. The current methods have a long development cycle and low efficiency. We design a visual formulation design system for temperature sensitive paint, helps desingers use historical data to improve the efficiency of formulation design. TSPvis provides a visual formulation design function, implements the proportion decision of formulation based on decision tree, and recommends reference for ingredients proportion to the formulation designer. We use the DPC clustering algorithm to quickly obtain the radial basis center, and use the Adam algorithm to improve the weight calculation from the hidden layer to the output layer, to improve RBF neural network. TSPvis use this RBF as a model to predict performance of the formulation which designed before, and feeds back to the designer to improve the formulation designing of temperature sensitive paint. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Real-Time Flow Scheduling in Industrial 5G New Radio 44

Real-Time Flow Scheduling in Industrial 5G New Radio

引用

44th IEEE Real-Time Systems Symposium, RTSS 2023

作者： Zhang, Tianyu Wang, Jiachen Hu, Xiaobo Sharon Han, Song University of Connecticut Dept. of Computer Science and Engineering United States University of Notre Dame Dept. of Computer Science and Engineering United States

ISBN: (纸本)9798350328578

Among the many industrial wireless solution candidates, 5G New Radio (NR) has drawn significant attention in recent years due to its capabilities to support ultra-high-speed communication, ultra-low latency, and massive connectivity. Despite its great potential, 5G NR also brings significant complexity in scheduling industrial data flows to meet their hard real-time requirements. In this paper, we first leverage a real-world 5G RAN testbed to benchmark the downlink throughput and explore the impact of modulation and coding scheme (MCS) selection on the network performance. We then formulate a real-time flow scheduling problem in industrial 5G NR, which features per-flow real-time schedulability guarantees through time-frequency-space resource allocation. We propose a novel two-phase scheduling framework, named 5G-TPS, to construct the schedule that meets the deadlines of all the flows. To adapt to dynamic channel conditions, 5G-TPS enables online schedule adjustment for affected flows to meet their timing requirements. To evaluate the performance of 5G-TPS, we present a case study of a motion control panel use case and perform extensive experiments. The results show that 5G-TPS can achieve schedulability ratios comparable to the Satisfiability Modulo Theory (SMT)-based exact solution and outperform many other state-of-the-art scheduling approaches, including the built-in 5G NR schedulers. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Text Filtering Insignificant Word (TFIW) Readability Framework Model to Explain NLP in Sentiment Analysis Using Reinforcement Machine Learning 2

Text Filtering Insignificant Word (TFIW) Readability Framewo...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Kandakatla, Rajesh Kumar, V Dhilip Vel Tech Rangarajan Dr. Sagunthala R & D Institute of Science and Technology Dept. Computer Science and Engineering Chennai India BVRIT HYDERABAD College of Engineering for Women Dept. Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350366570

Reading of a text in a given sentence have lot of parameters to consider for expressing an opinion on a given text to conclude nature of the text. The data which need to be formed in the form of data sets based on specific constrains. The Natural Language Processing (NLP) will always presume that Text readability made as the considerable measure for better round spread of any newspaper. The data related to these documents must be collected and store them in data sets. During this process of measuring text readability at the granular level of the text reading is a cumbersome task. This will always implicate a problem of machine readability of the text and explainability of the text taken from the documents mentioned above. In this context human readability will act an important role in predicting the text reading at granular level where the text-based sentiment analysis have been predicted through a machine learning model. The text reading has been evaluated in order to improve the readability through explainable system. The explainable systems will capture and explain the predictions of text reading. In this technical work an explainable system Text Filtering Insignificant Word (TFIW) is introduced where it improves the textual reading at the granule level based on sentiments by prediction the words which need to be filtered. This will improve the explainability of text and text reading and improve the fast text and explainability of the document. © 2024 IEEE.

关键词： Reinforcement learning

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：