检索结果-内蒙古大学图书馆

14th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2022

作者： Bifari, Ezdihar Alhalabi, Wadee King Abdulaziz University Computer Science Department Jeddah Saudi Arabia King Abdulaziz University Computer Science Department and Immersive Virtual Reality Research Group Jeddah Saudi Arabia

ISBN: (纸本)9781665487719

Court judgments from several nations have recently been published and made accessible online for study, adding to the growing number of online resources available today. As a recommendation, the legal databases can be incorporated into the training of crime scene investigators and made available as a learning resource. A text mining method was used to identify relevant documents, including crime scenes, and categorize them according to the kind of crime committed. The results from the statistical data support the possibility of useful information about crime scenes and murder cases in legal documents. © 2022 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Multi-Agent Reinforcement Learning for Algorithmic Trading in the Digital Financial Frontier and Enterprise Information Systems

引用

computers, Materials & Continua 2024年第8期80卷 3123-3138页

作者： Saket Sarin Sunil K.Singh Sudhakar Kumar Shivam Goyal Brij Bhooshan Gupta Wadee Alhalabi Varsha Arya Chandigarh College of Engineering and Technology Chandigarh160019India Department of Computer Science and Information Engineering Asia UniversityTaichung413Taiwan Symbiosis Centre for Information Technology(SCIT) Symbiosis International UniversityPune411057India Center for Interdisciplinary Research University of Petroleum and Energy Studies(UPES)Dehradun248007India Department of Computer Science Immersive Virtual Reality Research GroupKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Business Administration Asia UniversityTaichung413Taiwan Department of Electrical and Computer Engineering Lebanese American UniversityBeirut11022801Lebanon UCRD Chandigarh UniversityChandigarh140413India

In the rapidly evolving landscape of today’s digital economy,Financial Technology(Fintech)emerges as a trans-formative force,propelled by the dynamic synergy between Artificial Intelligence(AI)and Algorithmic *** in-depth investigation delves into the intricacies of merging Multi-Agent Reinforcement Learning(MARL)and Explainable AI(XAI)within Fintech,aiming to refine Algorithmic Trading *** meticulous examination,we uncover the nuanced interactions of AI-driven agents as they collaborate and compete within the financial realm,employing sophisticated deep learning techniques to enhance the clarity and adaptability of trading *** AI-infused Fintech platforms harness collective intelligence to unearth trends,mitigate risks,and provide tailored financial guidance,fostering benefits for individuals and enterprises navigating the digital *** research holds the potential to revolutionize finance,opening doors to fresh avenues for investment and asset management in the digital ***,our statistical evaluation yields encouraging results,with metrics such as Accuracy=0.85,Precision=0.88,and F1 Score=0.86,reaffirming the efficacy of our approach within Fintech and emphasizing its reliability and innovative prowess.

关键词： Neurodynamic Fintech multi-agent reinforcement learning algorithmic trading digital financial frontier

来源：评论

学校读者我要写书评

暂无评论

Why Go Full? Elevating Federated Learning Through Partial Network Updates 38

Why Go Full? Elevating Federated Learning Through Partial Ne...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Guo, Wenkai Tang, Shaojie State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Center for AI Business Innovation Department of Management Science and Systems University at Buffalo BuffaloNY United States Zhongguancun Laboratory Beijing China

Federated learning is a distributed machine learning paradigm designed to protect user data privacy, which has been successfully implemented across various scenarios. In traditional federated learning, the entire parameter set of local models is updated and averaged in each training round. Although this full network update method maximizes knowledge acquisition and sharing for each model layer, it prevents the layers of the global model from cooperating effectively to complete the tasks of each client, a challenge we refer to as layer mismatch. This mismatch problem recurs after every parameter averaging, consequently slowing down model convergence and degrading overall performance. To address the layer mismatch issue, we introduce the FedPart method, which restricts model updates to either a single layer or a few layers during each communication round. Furthermore, to maintain the efficiency of knowledge acquisition and sharing, we develop several strategies to select trainable layers in each round, including sequential updating and multi-round cycle training. Our theoretical analysis and experimental results show that the FedPart method significantly outperforms traditional full-network update strategies, achieving faster convergence, greater accuracy, and reduced communication and computational overhead. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synergistic application of neuro-fuzzy mechanisms in advanced neural networks for real-time stream data flux mitigation

引用

Soft Computing 2024年第20期28卷 12425-12437页

作者： Goyal, Shivam Kumar, Sudhakar Singh, Sunil K. Sarin, Saket Priyanshu Gupta, Brij B. Arya, Varsha Alhalabi, Wadee Colace, Francesco Chandigarh College of Engineering and Technology Panjab University Chandigarh160019 India Department of Computer Science and Information Engineering Asia University Taichung413 Taiwan Symbiosis International University Pune India Kyung Hee University 26 Kyungheedae-ro Dongdaemun-gu Seoul Korea Republic of Dehradun India Department of Business Administration Asia University Taichung Taiwan Department of Electrical and Computer Engineering Lebanese American University Beirut Lebanon Department of Computer Science Immersive Virtual Reality Research Group King Abdulaziz University Jeddah Saudi Arabia Department of Industrial Engineering University of Salerno Fisciano Italy

Stream mining, especially with concept drift, presents significant challenges across various domains. As data streams evolve over time, initial models become less effective. We present a novel approach using fuzzy ARTMAP’s adaptability and neural networks’ robustness to address concept drift. Our method dynamically updates models based on changing data distributions, enabling real-time adap- tation. By integrating fuzzy ARTMAP with backpropagation, it facilitates agile learning and accurate predictions in evolving scenarios. Through rigorous exper- iments, we demonstrate the effectiveness of our method in managing concept drift and achieving substantial performance improvements. The achieved accu- racy of 85.07% and F1 score of 72.47 demonstrate the effectiveness of the approach in real-time classification tasks. This research extends beyond just performance metrics. By leveraging the interpretability of fuzzy ARTMAP, we gain valuable insights into the mechanisms that enable our model to adapt to concept drift. This deeper understanding paves the way for further advancements in this area. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Comparison of Image Interpolation Methods for Image Zooming 11

Comparison of Image Interpolation Methods for Image Zooming

引用

11th International Conference on System Modeling and Advancement in Research Trends, SMART 2022

作者： Krishnamoorthy Goswami, Subhashish Department of Animation and Virtual Reality Bangalore India Dev Bhoomi Uttarakhand University Dept of Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665487320

The primary approach in the realm of digital image processing is zooming. Image When using zooming, a high-quality image is required in order to enlarge the image to the specified magnification factor [1]. When enlarging images, or zooming in, digital image interpolation techniques are commonly employed. They are also becoming more and more popular for creating product applications with digital still cameras. While shrinking is considered under-sampling, zooming is considered over-sampling. In this study, we upscale the image using linear methods and contrast them against one another. However, all of these techniques have problems with blocking, aliasing, blurring, and other artefacts. We'll try to get beyond the objects indicated above. © 2022 IEEE.

关键词： Image processing

来源：评论

学校读者我要写书评

暂无评论

virtual Exhibition Hall as a Solution for Promoting City Profiles with the Integration of Avatars and Non-Player Characters based on Metaverse Technology

Virtual Exhibition Hall as a Solution for Promoting City Pro...

引用

Technology, Engineering, and Computing Applications (ICTECA), International Conference on

作者： Aulia Akhrian Syahidi Kiyoshi Kiyokawa Department of Electrical Engineering Augmented Reality and Virtual Reality Laboratory Politeknik Negeri Banjarmasin Banjarmasin Indonesia Cybernetics and Reality Engineering Laboratory Division of Information Science Nara Institute of Science and Technology Ikoma Nara Japan

In recent years, metaverse technology has become popular as a virtual environment. This has created new opportunities to showcase cities in innovative ways. This research aims to introduce MetaCityProfile, a virtual exhibition hall application that integrates avatars and intelligent Non-Player Characters (NPC) to promote city profiles using metaverse. Our focus is on the city profiles of South Kalimantan Province, Indonesia. We will also confirm the impact of the behavioral design techniques of intelligent NPCs interacting with avatars in virtual spaces. This will provide a more engaging and informative user experience. We used justification techniques to measure the impact of the application on users’ knowledge and interests. Additionally, we evaluated the immersive user experience. The research results show that the use of virtual exhibition hall integrated with avatars and intelligent NPCs can significantly increase knowledge and interest in city profiles and encourage public participation. The use of metaverse provides a dynamic and engaging platform to visually promote city assets and attractions. Users report a more satisfying and immersive experience when exploring each city profile while interacting with intelligent, informative NPCs. This research provides a basis for developing more effective city promotion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An approach towards Real-Time Object Detector Using Open CV 11

An approach towards Real-Time Object Detector Using Open CV

引用

11th International Conference on System Modeling and Advancement in Research Trends, SMART 2022

作者： Kumar, Muthu Bhatt, Rahul Department of Animation and Virtual Reality Bangalore India Dev Bhoomi Uttarakhand University Dept of Computer Science and Engineering Uttarakhand Dehradun India

ISBN: (纸本)9781665487320

Object detection has drawn a lot of academic focus in recent years due to its tight relationship with video analysis and picture intelligence. A computer vision technique called object detection is used to find and identify things in images and videos. Object detection accurately draws bounding boxes around discovered objects, informing us of the location of the requested object in the video or image. Before continuing, it is crucial to understand the difference between object detection and picture analysis because they are two concepts that are primarily confused by one another. Object detection works in tandem with other computer vision techniques like image segmentation and detection to help us comprehend and analyse images and videos. The project's major objective is to create a system that can identify items such as people, bicycles, cars, buses, and boats from an image or a stream of images that are fed to it in the form of previously recorded video or real-time input from the camera. The system will draw bounding boxes around the things it has detected. This article outlines a strategy for rationally using OpenCV, the Yolo algorithm, and Python to get decent machine learning results. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

PointHGN: Point Heterogeneous Graph Neural Network for Point Cloud Learning

PointHGN: Point Heterogeneous Graph Neural Network for Point...

引用

IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

作者： Zhiying Leng Shun-cheng Wu Frederick W. B. Li Federico Tombari Xiaohui Liang State Key Laboratory of Virtual Reality Technology and Systems Beihang University China Chair for Computer Aided Medical Procedures & Augmented Reality Technical University of Munich Germany Department of Computer Science Durham University U.K.

Point cloud learning has gained significant attention in 3D multimedia. However, existing methods learn point-wise features in a homogeneous manner, disregarding the heterogeneity that inherently exists in point clouds. Embedding the heterogeneity into feature learning is favorable to learning more discriminative point-wise features with rich geometric structures. In this work, we are the first to analyze and utilize the heterogeneity of point clouds, namely geometric heterogeneity and category heterogeneity. We hence propose two general heterogeneous graph convolutions to exploit such heterogeneity, including Geometric Heterogeneous Graph Convolution (GHGC) and Category Heterogeneous Graph Convolution (CHGC). We implement a point heterogeneous graph neural network (PointHGN) based on classical MLP-based point cloud pipelines, without altering network configurations. Experimental results on point cloud semantic segmentation tasks manifest that our PointHGN achieves commendable performance on public datasets. Our proposed method provides an effective and alternative approach for point cloud learning that researchers can explore further.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning-Based Outlier Rejection for Keypoint Matching

Learning-Based Outlier Rejection for Keypoint Matching

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Wissam Alkhadour Jamal Zraqou Jawad Alkhateeb E-Commerce Department University of Petra Amman Jordan CS/ Virtual & Augmented Reality Department University of Petra Amman Jordan Computer Engineering Department Prince Mohammad Bin Fahd University Alkhobar KSA

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Matching features are integral to computer vision and can be used in image fusion, object recognition, or 3D model construction. Although conventional solutions are good, such as feature detection using SIFT with FLANN or brute-force and subsequent descriptor matching, they have severe problems when applying scale, rotation, or noise transformations. Other techniques, such as RANSAC, have also been used intensively to reduce match reliability by removing outliers. Nonetheless, the authors also discussed RANSAC when it has shortcomings; they stated that RANSAC has some drawbacks, such as being sensitive to parameter values, and when used with big data, it is very computationally expensive. To overcome these challenges, we suggest that SVMs be introduced into the feature-matching process in the SIFT framework. Matches are labeled inliers or outliers using detected training examples based on the SVM's descriptor similarity and geometrical consistency. This is an efficient replacement to the conventional LOS techniques because it includes probabilistic decisions, makes complex transformations plug-in with the methodology or the measurement system employed, as well as minimizing the critical dependence on the adjustment of the parameter values. A comparison of the performance of several theories shows that SVM-based filtering yields better match reliability, higher feature coverage, and a faster processing time than existing feature-matching approaches, and hence, it complements existing feature-matching solutions appropriately.

关键词： Training Support vector machines Solid modeling Three-dimensional displays Filtering Noise Reliability theory Probabilistic logic Object recognition Image fusion

来源：评论

学校读者我要写书评

暂无评论

Panting Traditional Musical Instruments Through virtual reality Environment with Leap Motion Control: Immersive User Experience, Usage Challenges, and Preservation Efforts

Panting Traditional Musical Instruments Through Virtual Real...

引用

Information Technology and Computing (ICITCOM), International Conference on

作者： Aulia Akhrian Syahidi Kiyoshi Kiyokawa Department of Electrical Engineering Politeknik Negeri Banjarmasin Augmented Reality and Virtual Reality Laboratory Banjarmasin Indonesia Cybernetics and Reality Engineering Laboratory Division of Information Science Nara Institute of Science and Technology Ikorna Nara Japan

This research investigates the use of traditional musical instruments based on virtual reality (VR) with leap motion control. This technology enables users to virtually interact with Panting instruments and aims to explore immersive user experiences, challenges, and cultural preservation. We collected data through a questionnaire consisting of both open and closed questions, and analyzed the data using descriptive statistics and textual analysis. We can confirm that the proposed modern technology has the potential to promote and preserve traditional Panting musical instruments, especially for the younger generation, but alignment with cultural values and holistic education needs to be considered. In conclusion, VR technology with leap motion control promises to preserve Panting's music, but overcoming technical and cultural challenges is critical to long-term success.

关键词：

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：