检索结果-内蒙古大学图书馆

Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), International Conference on

作者： S. Prabakar Ankit Kumar R Jayakarthik D. Venkatesh Pratheeba R S Bhola Khan Finance and Accounting ISBR Business School Bangalore Department of Computer Application Faculty of Science Swami Vivekanand Subharti University Meerut Dept of Computer science Saveetha College of Liberal Arts and Sciences SIMATS Assistant Professor of Commerce School of Commerce and Management Mohan Babu University Tirupati Department of Computer Science and Engineering Velammal Institute of Technology Panchetti Department of Regional Economics MJP Rohilkhand University Bareilly India

The Stock Market Prediction System using Intelligent Learning Scheme (SMS-ILS) presented in this study integrates advanced methodologies to enhance the accuracy and reliability of stock market predictions. The system encompasses a preprocessing phase, addressing missing data and outliers, followed by feature extraction utilizing Long Short-Term Memory (LSTM) and Recurrent Neural Networks (RNN) to capture intricate temporal dependencies. A Deep Belief Network (DBN) is employed for classification, categorizing stocks based on learned representations from historical and technical indicators. Grey Wolf Optimization (GWO) optimizes the system's parameters, ensuring adaptability to dynamic market conditions. Notably, the system achieves an impressive accuracy of 97%, emphasizing its efficacy in making correct predictions. This multi-model approach, integrating LSTM, RNN, DBN, and GWO, provides a comprehensive and adaptive framework for navigating the complexities of stock market prediction. The study emphasizes the importance of choosing metrics aligned with specific goals and conducting thorough analysis to ensure the robustness of the evaluation results in the challenging and dynamic context of financial markets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeferredGS: Decoupled and Editable Gaussian Splatting with Deferred Shading

arXiv

引用

arXiv 2024年

作者： Wu, Tong Sun, Jia-Mu Lai, Yu-Kun Ma, Yuewen Kobbelt, Leif Gao, Lin Huazhong University of Science and Technology China Institute of Computing Technology Chinese Academy of Sciences China Tsinghua University China Nanyang Technological University Singapore The University of Karlsruhe Germany The Computer Graphics Group The RWTH Aachen University Germany Sichuan University China

Reconstructing and editing 3D objects and scenes both play crucial roles in computer graphics and computer vision. Neural radiance fields (NeRFs) can achieve realistic reconstruction and editing results but suffer from inefficiency in rendering. Gaussian splatting significantly accelerates rendering by rasterizing Gaussian ellipsoids. However, Gaussian splatting utilizes a single Spherical Harmonic (SH) function to model both texture and lighting, limiting independent editing capabilities of these components. Recently, attempts have been made to decouple texture and lighting with the Gaussian splatting representation but may fail to produce plausible geometry and decomposition results on reflective scenes. Additionally, the forward shading technique they employ introduces noticeable blending artifacts during relighting, as the geometry attributes of Gaussians are optimized under the original illumination and may not be suitable for novel lighting conditions. To address these issues, we introduce DeferredGS, a method for decoupling and editing the Gaussian splatting representation using deferred shading. To achieve successful decoupling, we model the illumination with a learnable environment map and define additional attributes such as texture parameters and normal direction on Gaussians, where the normal is distilled from a jointly trained signed distance function. More importantly, we apply deferred shading, resulting in more realistic relighting effects compared to previous methods. Both qualitative and quantitative experiments demonstrate the superior performance of DeferredGS in novel view synthesis and editing tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Lighting

来源：评论

学校读者我要写书评

暂无评论

IoT-Enabled Predictive Healthcare Monitoring Using Machine Learning Models 3rd

IoT-Enabled Predictive Healthcare Monitoring Using Machine L...

引用

3rd International Conference on Universal Threats in Expert Applications and Solutions, UNI-TEAS 2024

作者： Patil, Nitin Jagannath Sharma, Avinash Prasad, K.D.V. Yogi, Kottala Sri Dankan Gowda, V. Department of Instrumentation Engineering D. N. Patel College of Engineering Shahada Maharashtra Untavad India Professor Department of Computer Science and Engineering Chandigarh Engineering College Chandigarh Group of Colleges Punjab Mohali140307 India Pune India Pune India Department of Electronics and Communication Engineering BMS Institute of Technology and Management Karnataka Bengaluru India

ISBN: (纸本)9789819751457

This study explores the capabilities of integrating the Internet of Things (IoT) with machine learning to monitor health in real time. Using IoT-powered devices like heart rate monitors, glucose meters, and blood pressure devices, health metrics were consistently gathered and sent to a cloud-based system. After refining the data for better quality, machine learning techniques were used to create health prediction models. The findings showed significant precision, especially when using neural networks, in predicting health-related events. This combined system can identify and notify healthcare experts about potential health concerns immediately. However, the promise of ongoing health tracking and early detection comes with concerns regarding data protection, data handling, and model reliability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

EL-FAM: Power System Intrusion Detection with Ensemble Learning for False Alarm Mitigation

EL-FAM: Power System Intrusion Detection with Ensemble Learn...

引用

International Conference on computer, Information and Telecommunication Systems (CITS)

作者： Ansh Bhavsar Sezan Agvan Fenil Ramoliya Mohammad S. Obaidiat Rajesh Gupta Sudeep Tanwar Kuei-Fang Hsiao Department of Computer Science and Engineering Institute of Technology Nirma University India Distinguished Professor at the King Abdullah II School of Information Technology The University of Jordan King Abdullah II School of Information Technology The University of Jordan Amman Jordan

ISBN: (数字)9798350359091

ISBN: (纸本)9798350359107

Power systems must be secured against malicious activity and unauthorized access with the help of intrusion detection systems (IDS). Unfortunately, it is often difficult for conventional IDS techniques to correctly identify robust and dynamic threats. The security of the power grid is seriously threatened by the growing frequency of attacks. In this paper an ensemble learning framework is proposed for power system intrusion detection in order to overcome this difficulty. This framework achieving high accuracy by combining the Random Forest, Decision Tree, and Logistic Regression algorithms. The proposed ensemble model is able to achieve an accuracy of 98%, which can be used to improve IDS outcomes [1]. Additionally, this method produces a low false alarm rate, that ensures precise and accurate intrusion detection. The system precisely detects intrusions by continuously observing real-time data for anomalies. Ensemble learning can incorporate data compression methods such as feature selection which reduce the overall memory footprint. This model's evaluation depicts that it has the potential to detect attacks on power systems, making it a useful tool for boosting overall security.

关键词： Support vector machines Logistic regression Accuracy Scalability Intrusion detection Real-time systems Power systems

来源：评论

学校读者我要写书评

暂无评论

Minimal-Perimeter Lattice Animals and the Constant-Isomer Conjecture

arXiv

引用

arXiv 2022年

作者： Barequet, Gill Ben-Shachar, Gil Center for Graphics and Geometric Computing Dept. of Computer Science The Technion—Israel Inst. of Technology Haifa3200003 Israel

We consider minimal-perimeter lattice animals, providing a set of conditions which are sufficient for a lattice to have the property that inflating all minimal-perimeter animals of a certain size yields (without repetitions) all minimal-perimeter animals of a new, larger size. We demonstrate this result on the two-dimensional square and hexagonal lattices. In addition, we characterize the sizes of minimal-perimeter animals on these lattices that are not created by inflating members of another set of minimal-perimeter animals. © 2022, CC BY.

关键词： Isomers

来源：评论

学校读者我要写书评

暂无评论

IoT Enabled Wearable technology Jacket for Tracking Patient Health and Safety System

IoT Enabled Wearable Technology Jacket for Tracking Patient ...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： M. Santhanalakshmi S. Dhanalakshmi M. Radhika G. Kavitha G. Elavel Visuvanathan C. Srinivasan Assistant Professor Department of Computer Science Shrimathi Devkunvar Nanalal Bhatt Vaishnav College for Women Chennai Tamil Nadu India Assistant Professor Department of Electronics and Communication Engineering Sri Muthukumaran Institute of Technology Chennai Tamil Nadu India Assistant Professor Department of Information Technology R.M.D. Engineering College Kavaraipettai Tamil Nadu India Professor Department of Computer Science and Engineering Muthayammal Engineering College (Autonomous) Namakkal Tamil Nadu India Assistant Professor Department of Electronics and Communication Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Adjunct Professor Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

Over the years, there have been ongoing efforts to use clothing as a vehicle for distributing digital capabilities. Information technology (IT) is being incorporated into garments to enable people to work more quickly. Because of their increasing availability, accessibility, and, most significantly, cost, wireless body area networks (WBANs) will undoubtedly be used in healthcare to enhance medical data utilization. Whether it has to do with post-operative recovery or Monitoring, applications for their function in the medical field are already being looked into. Wearable technology allows users to complete activities more efficiently by enhancing one or more of their senses with artificial information. The system proposes a method that displays critical information for doctors on a particular cloud for data analysis. In this concept, sensors are attached to someone's coat to collect real-time data. This data is analyzed, uploaded to the cloud using IoT Medium, and notified in the case of an alarming condition. The data access to real-time data, a website built into this module, and an alert notification system to warn the hospital and the family if the numbers are abnormal. A live stream is recorded using the camera, while the GPS module tracks the location. The doctor can take the proper step based on the patient's health.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FluidPlaying: Efficient Adaptive Simulation for Highly Dynamic Fluid

FluidPlaying: Efficient Adaptive Simulation for Highly Dynam...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Sinuo Liu Xiaojuan Ban Sheng Li Haokai Zeng Xiaokun Wang Yanrui Xu Fei Zhu Guoping Wang Graphics & Interaction Lab National Biomedical Imaging Center School of Computer Science Peking University School of Intelligence Science and Technology University of Science and Technology Beijing Beijing Engineering Technology Research Center of Virtual Simulation and Visualization Peking University Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)

We present FliudPlaying, a novel dynamic level-based spatially adaptive simulation method that can handle highly dynamic fluid efficiently. To capture the subtle detail of the fluid surface, the high-resolution simulation is performed not only at the free surface but also at those regions with high vorticity levels and velocity difference levels. To minimize the density error, an online optimization scheme is used when increasing the resolution by particle splitting. We also proposed a neighbor-based splash enhancement to compensate for the loss of dynamic details. Compared with the high-resolution simulation baseline, our method can achieve over 3× speedups while consuming only less than 10% computational resources. Furthermore, our method can make up for the loss of high-frequency details caused by the spatial adaptation, and provide more realistic dynamics in particle-based fluid simulation.

关键词： Solid modeling Adaptation models Three-dimensional displays Fluid dynamics Computational modeling Conferences Virtual reality

来源：评论

学校读者我要写书评

暂无评论

RaliSense: Extending WiFi Respiratory Detection Range by Rapid Alignment of Dynamic Components

引用

IEEE Transactions on Mobile Computing 2025年

作者： Gui, Linqing Zheng, Siyi Guo, Zhengxin Li, Zhetao Gao, Ming Dustdar, Schahram Xiao, Fu Nanjing University of Posts and Telecommunications School of Computer Science Nanjing210023 China Jinan University College of Information Science and Technology Guangzhou510632 China TU Wien Research Division of Distributed Systems Vienna1040 Austria UPF ICREA Research Professor Barcelona Spain

WiFi based respiratory detection has attracted increasing attentions due to its ubiquity and convenience. In Non-Line-of-Sight (NLoS) scenarios, WiFi signals reflected from human target are blocked by obstacles and become much weaker, thus limiting the sensing range and hindering the practical deployment. The existing best respiratory detection system extended the sensing range by scaling and aligning dynamic components in WiFi signals. However, its dynamic component scaling causes the amplification of noise, while its dynamic component alignment increases computation complexity due to the traversal on all possible rotation angles. To address the above issues, in this paper we first build WiFi sensing range models for respiratory detection in NLoS scenario, find factors that limit the sensing range, and then propose a new respiratory detection system named RaliSense which can further rapidly extend the sensing range in NLoS scenario. The main idea of RaliSense is rapidly aligning dynamic components without amplifying noise, based on change direction vector and CSI ratio sum polarity of dynamic components. The proposed change direction vector is obtained by calculating the direction on which the noisy dynamic components have the maximum variance, and CSI ratio sum polarity is then obtained by summing the dynamic components which have been rotated by the change direction vector. According to the CSI ratio sum polarity, the rotation angle is quickly adjusted for aligning dynamic components. Extensive simulation and experiment results verify the effectiveness of our proposed sensing range models. The results also demonstrate that our proposed system RaliSense can effectively extend sensing range in NLoS scenario, achieving a 22.7% improvement over the best existing work but spending only a quarter of its computation time. © 2002-2012 IEEE.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Secure UAV-assisted Battlefield Operation underlying 5G

Blockchain-based Secure UAV-assisted Battlefield Operation u...

引用

Conference on Information and Knowledge technology

作者： Dhruvi Pancholi Nilesh Kumar Jadav Sudeep Tanwar Deepak Garg S. Mohammadali Zanjani Department of Computer Science and Engineering Institute of Technology Nirma University Ahmedabad India Distinguished Professor School of Computer Science and Artificial Intelligence SR University Warangal India Department of Electrical Engineering Najafabad Branch Islamic Azad University Najafabad Iran

The use of unmanned aerial vehicles (UAVs) has significantly increased during the past few years. UAVs have a wide range of applications, but their employment in the defense sector has grown significantly in recent years as a result of their exceptional effectiveness in reducing casualties and enabling the accomplishment of high-profile as well as time-sensitive operations. UAVs are helpful for numerous defense-related operations, such as border patrol, surveillance, emergency management, damage assessment, delivery of medical supplies and armaments, and many others. However, because wireless communication is open, UAVs can be used to undermine the effectiveness of military operations. In this paper, we developed a blockchain-based framework to mitigate security threats from UAVs operating in a combat scenario. The MATLAB virtual environment is used to simulate a battlefield scenario, including UAVs, sensors, enemies, and friendly nodes. The UAV scenario also includes an enemy that continuously manipulates the UAVs to endanger battlefield operations. The suggested framework employs machine learning algorithms to find malicious UAVs. Further, the proposed framework uses blockchain technology to increase security and lessen data tampering attempts. A smart contract (for data validation) is deployed on an IPFS-based public blockchain. In addition, 5G technology is used, which makes it possible for UAVs and the control station to communicate effectively with lower packet error rates and latency. The proposed framework is evaluated by considering evaluation metrics, such as 5G packet error rate, latency, and transaction and execution costs for the blockchain.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CLASSIFICATION OF LUNG CANCER SUBTYPES ON CT IMAGES WITH SYNTHETIC PATHOLOGICAL PRIORS

arXiv

引用

arXiv 2023年

作者： Zhu, Wentao Jin, Yuan Ma, Gege Chen, Geng Egger, Jan Zhang, Shaoting Metaxas, Dimitris N. Research Center for Healthcare Data Science Zhejiang Lab Hangzhou311121 China School of Computer Science and Engineering Northwestern Polytechnical University Shaanxi Xi’an710072 China Institute of Computer Graphics and Vision Graz University of Technology Graz8010 Austria Shanghai Artificial Intelligence Laboratory Shanghai200120 China Department of Computer Science Rutgers University PiscatawayNJ08854 United States

The accurate diagnosis on pathological subtypes for lung cancer is of significant importance for the follow-up treatments and prognosis managements. In this paper, we propose self-generating hybrid feature network (SGHF-Net) for accurately classifying lung cancer subtypes on computed tomography (CT) images. Inspired by studies stating that cross-scale associations exist in the image patterns between the same case’s CT images and its pathological images, we innovatively developed a pathological feature synthetic module (PFSM), which quantitatively maps cross-modality associations through deep neural networks, to derive the "gold standard" information contained in the corresponding pathological images from CT images. Additionally, we designed a radiological feature extraction module (RFEM) to directly acquire CT image information and integrated it with the pathological priors under an effective feature fusion framework, enabling the entire classification model to generate more indicative and specific pathologically related features and eventually output more accurate predictions. The superiority of the proposed model lies in its ability to self-generate hybrid features that contain multi-modality image information based on a single-modality input. To evaluate the effectiveness, adaptability, and generalization ability of our model, we performed extensive experiments on a large-scale multi-center dataset (i.e., 829 cases from three hospitals) to compare our model and a series of state-of-the-art (SOTA) classification models. The experimental results demonstrated the superiority of our model for lung cancer subtypes classification with significant accuracy improvements in terms of accuracy (ACC), area under the curve (AUC), and F1 score. © 2023, CC0.

关键词： Classification (of information)

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：