检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data Analysis (ICBDA)

作者： Xinxin Li Tianqi Shang Dezhong Peng Xiaoyu Shi School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China College of Computer Science Sichuan University Chengdu China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

Recently, many websites encourage users to fill in reviews on items and services to improve the quality of personalized recommendation, because of the rich sentiment information hidden in user reviews. However, most existing recommendation methods based on reviews heavily emphasize extracting the rich sentiment information from reviews by using deep learning technologies as far as possible and always ignore the effects of temporal dynamical of user preferences. To address the above issues, we propose DSL- TR, a deep sentiment learning framework for the temporal-aware recommendation, using an intricate combination of bidirectional long short-term memory (BLSTM) and Convolution Neural Network (CNN). It consists of four layers: embedding layer, BLSTM layer, CNN layer and feature fusion layer. In the embedding layer, we explicitly combine the time information in the review embedding layer by regarding the review time as an independent factor. Then, we utilize the BLSTM and CNN networks to extract the long and short-terms of latent features of user and item in parallel. Finally, the factorization machine technique, as a rating predictor, is introduced on the last layer to estimate the rating based on the learned user and item latent features. We conduct extensive experiments on Amazon's four data sets. The results demonstrate that our proposed method outperforms several state-of-art methods consistently.

关键词： Deep learning Convolution Conferences Neural networks Big Data Feature extraction Data mining

来源：评论

学校读者我要写书评

暂无评论

Detection and evaluation of abnormal user behavior based on quantum generation adversarial network

arXiv

引用

arXiv 2022年

作者： Pan, Minghua Wang, Bin Tao, Xiaoling Zheng, Shenggen Situ, Haozhen Li, Lvzhou Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin541004 China Peng Cheng Laboratory Shenzhen518055 China College of Mathematics and Informatics South China Agricultural University Guangzhou510642 China Institute of Quantum Computing and Software School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China

Quantum computing holds tremendous potential for processing high-dimensional data, capitalizing on the unique capabilities of superposition and parallelism within quantum states. As we navigate the noisy intermediate-scale quantum (NISQ) era, the exploration of quantum computing applications has emerged as a compelling frontier. One area of particular interest within the realm of cyberspace security is Behavior Detection and Evaluation (BDE). Notably, the detection and evaluation of internal abnormal behaviors pose significant challenges, given their infrequent occurrence or even their concealed nature amidst vast volumes of normal data. In this paper, we introduce a novel quantum behavior detection and evaluation algorithm (QBDE) tailored for internal user analysis. The QBDE algorithm comprises a Quantum Generative Adversarial Network (QGAN) in conjunction with a classical neural network for detection and evaluation tasks. The QGAN is built upon a hybrid architecture, encompassing a Quantum Generator (GQ) and a Classical Discriminator (DC). GQ, designed as a parameterized quantum circuit (PQC), collaborates with DC, a classical neural network, to collectively enhance the analysis process. To address the challenge of imbalanced positive and negative samples, GQ is employed to generate negative samples. Both GQ and DC are optimized through gradient descent techniques. Through extensive simulation tests and quantitative analyses, we substantiate the effectiveness of the QBDE algorithm in detecting and evaluating internal user abnormal behaviors. Our work not only introduces a novel approach to abnormal behavior detection and evaluation but also pioneers a new application scenario for quantum algorithms. This paradigm shift underscores the promising prospects of quantum computing in tackling complex cybersecurity challenges. Copyright © 2022, The Authors. 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

OSAF_e: One-Stage Anchor Free Object Detection Method Considering Effective Area 9th

OSAF_e: One-Stage Anchor Free Object Detection Method Consid...

引用

9th International Conference on Artificial Intelligence and Mobile Services, AIMS 2020, held as part of the Services Conference Federation, SCF 2020

作者： Zhang, Yong Zhang, Lizong Rao, Zhihong Duan, Guiduo Wang, Chunyu School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China China Electronic Technology Cyber Security Co. Ltd. Chengdu610000 China Trusted Cloud Computing and Big Data Key Laboratory of Sichuan Province Chengdu611731 China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu610054 China

ISBN: (纸本)9783030596040

The task of object detection is to identify the bounding box of the object and its corresponding category in images. In this paper, we propose a new one-stage anchor free object detection algorithm OSAF_e, with the consideration of effective mapping area. A feature extraction network is used to obtain high level feature, and the true bounding box of the object in the original image is mapped to the grid of feature map, in order to perform category prediction and bounding box regression. The proposed algorithm is evaluated with the Pascal Voc dataset, and the experiments indicate that it has a better result. © 2020, Springer Nature Switzerland AG.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Green IoT using UAVs in B5G networks: A review of applications and strategies

arXiv

引用

arXiv 2021年

作者： Alsamhi, Saeed H. Afghah, Fatemeh Sahal, Radhya Hawbani, Ammar Al-Qaness, A.A. Lee, B. Guizani, Mohsen Software Research Institute Athlone Institute of Technology Athlone Ireland IBB University Ibb Yemen School of Informatics Computing and Cyber Systems Northern Arizona University United States Hudaidah University Hudaida Yemen School of Computer Science and Technology University of Science and Technology of China Hefei China State Key Laboratory for Information Engineering in Surveying Mapping and Remote Sensing Wuhan University China Department of Computer Science and Engineering Qatar University Qatar

Recently, Unmanned Aerial Vehicles (UAVs) present a promising advanced technology that can enhance people life quality and smartness of cities dramatically and increase overall economic efficiency. UAVs have attained a significant interest in supporting many applications such as surveillance, agriculture, communication, transportation, pollution monitoring, disaster management, public safety, healthcare, and environmental preservation. Industry 4.0 applications are conceived of intelligent things that can automatically and collaboratively improve beyond 5G (B5G). Therefore, the Internet of Things (IoT) is required to ensure collaboration between the vast multitude of things efficiently anywhere in real-world applications that are monitored in real-time. However, many IoT devices consume a significant amount of energy when transmitting the collected data from surrounding environments. Due to a drone's capability to fly closer to IoT, UAV technology plays a vital role in greening IoT by transmitting collected data to achieve a sustainable, reliable, eco-friendly Industry 4.0. This survey presents an overview of the techniques and strategies proposed recently to achieve green IoT using UAVs infrastructure for a reliable and sustainable smart world. This survey is different from other attempts in terms of concept, focus, and discussion. Finally, various use cases, challenges, and opportunities regarding green IoT using UAVs are presented. © 2021, CC BY.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Learning to See in the Dark with Events 16th

Learning to See in the Dark with Events

引用

16th European Conference on computer Vision, ECCV 2020

作者： Zhang, Song Zhang, Yu Jiang, Zhe Zou, Dongqing Ren, Jimmy Zhou, Bin State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Peng Cheng Laboratory Shenzhen China SenseTime Research Beijing China Tsinghua University Beijing China

ISBN: (纸本)9783030585228

Imaging in the dark environment is important for many real-world applications like video surveillance. Recently, the development of Event Cameras raises promising directions in solving this task thanks to its High Dynamic Range (HDR) and low requirement of computational sources. However, such cameras record sparse, asynchronous intensity changes of the scene (called events), instead of canonical images. In this paper, we propose learning to see in the dark by translating HDR events in low light to canonical sharp images as if captured in day light. Since it is extremely challenging to collect paired event-image training data, a novel unsupervised domain adaptation network is proposed that explicitly separates domain-invariant features (e.g. scene structures) from the domain-specific ones (e.g. detailed textures) to ease representation learning. A detail enhancing branch is proposed to reconstruct day light-specific features from the domain-invariant representations in a residual manner, regularized by a ranking loss. To evaluate the proposed approach, a novel large-scale dataset is captured with a DAVIS240C camera with both day/low light events and intensity images. Experiments on this dataset show that the proposed domain adaptation approach achieves superior performance than various state-of-the-art architectures. © 2020, Springer Nature Switzerland AG.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Progressive Real-time Visualization Method for Earthquake Big Data

引用

Journal of computers (Taiwan) 2022年第1期33卷 87-100页

作者： Shan, Weifeng Li, Jianqiao Teng, Yuntian Chen, Huiling Li, Zhiyang Wang, Maofa School of Emergency Management Institute of Disaster Prevention Sanhe065201 China Institute of Geophysics China Earthquake Administration Beijing100081 China College of Computer Science and Artificial Intelligence Wenzhou University Wenzhou325035 China Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guilin541004 China

As the volume of seismic observation time-series data grows larger, web-based visualization schemes suffer from longer system response times. Although big data visualization schemes based on sampling and filtering can greatly reduce the data scale and shorten transmission time, what it gains in speed it loses in information. Progressive visualization has become an increasingly popular scheme because it can quickly "see" some results without having to wait for all the data, thus enabling users to grasp a data-change trend quickly and perceive the rules behind it. In this paper, a Cloudberry-based progressive real-time visualization schema for earthquake big data (PVSEBD) is proposed for the first time. It greatly shortens the transmission time of each data slice, improves the user interaction experience, and meets the long-term, large-scale visualization needs of earthquake consultation business. Because the correctness of average aggregation function (AVG) in progressive visualization is often not guaranteed, this paper proposes an innovative AVG translation rule solution based on the accumulability of the COUNT and SUM aggregation functions. The experimental results showed that PVSEBD automatically adjusts the amount of data returned each time according to size and has a shorter response time for each interaction compared with the solution based on the web-based visualization toolkit Portable Progressive Parallel Processing Pipeline (P5). © 2022 computer Society of the Republic of China. All rights reserved.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

Distributed Task-Oriented Communication Networks with Multimodal Semantic Relay and Edge Intelligence

arXiv

引用

arXiv 2024年

作者： Guo, Jie Chen, Hao Song, Bin Chi, Yuhao Yuen, Chau Yu, Fei Richard Li, Geoffrey Ye Niyato, Dusit The State Key Laboratory of Integrated Services Networks Xidian University Xi’an710071 China The Hangzhou Institute of Technology Xidian University Hangzhou311231 China The School of Electrical and Electronics Engineering The School of Computer Science and Engineering Respectively Nanyang Technological University 639798 Singapore The Department of Systems and Computer Engineering Carleton University OttawaK1S 5B6 Canada The Faculty of Engineering Imperial College London LondonSW7 2AZ United Kingdom

In this article, we present a novel framework, named distributed task-oriented communication networks (DTCN), based on recent advances in multimodal semantic transmission and edge intelligence. In DTCN, the multimodal knowledge of semantic relays and the adaptive adjustment capability of edge intelligence can be integrated to improve task performance. Specifically, we propose the key techniques in the framework, such as semantic alignment and complement, a semantic relay scheme for deep joint source-channel relay coding, and collaborative device-server optimization and inference. Furthermore, a multimodal classification task is used as an example to demonstrate the benefits of the proposed DTCN over existing methods. Numerical results validate that DTCN can significantly improve the accuracy of classification tasks, even in harsh communication scenarios (e.g., low signal-to-noise regime), thanks to multimodal semantic relay and edge intelligence. © 2024, CC BY-NC-SA.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Fusion of Super-Resolution and Semantic Segmentation Deep Models for Building Footprint Extraction From Aerial Images

引用

The Photogrammetric Record 2025年第190期40卷

作者： Ziyi Chen Yuhua Luo Jiaying Zhang Ronggang Guo Liai Deng Jinghua Liu Dilong Li Yongtao Yu Ammar Abulibdeh Cheng Wang Department of Computer Science and Technology Fujian Key Laboratory of big Data Intelligence and Security Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Xiamen FJ China Guojiao Spatial Information Technology (Beijing) co. Ltd Beijing China Faculty of Computer and Software Engineering Huaiyin Institute of Technology Huaian JS China Department of Humanities College of Arts and Sciences Qatar University Doha Qatar School of Informatics Xiamen University Xiamen FJ China

The spatial resolution of remotely sensed images has seen significant improvements; higher resolution facilitates the understanding of remote sensing images and improves the accuracy of building footprint extraction. Thus, this paper introduces a novel approach that combines super-resolution reconstruction with semantic segmentation deep models for building footprint extraction. To begin, a super-resolution reconstruction deep model is employed to enhance the resolution of the target images. Subsequently, training samples are generated using various data augmentation techniques based on the reconstructed images. Finally, a semantic segmentation deep model is trained to perform the final building footprint extraction. For validation, our proposed framework was tested on two publicly available aerial image datasets: the WHU building dataset and the Massachusetts building dataset. The results obtained from these datasets demonstrated the effectiveness of our method, achieving high Intersection over Union (IoU) scores of 90.57% and 75.02%, respectively. Furthermore, our approach outperformed seven other competing methods, showcasing its superior performance.

关键词： aerial image building footprint extraction deep learning semantic segmentation super-resolution

来源：评论

学校读者我要写书评

暂无评论

Learning-based Event-triggered Adaptive Optimal Output Regulation of Linear Discrete-time Systems 10

Learning-based Event-triggered Adaptive Optimal Output Regul...

引用

10th IEEE Data Driven Control and Learning Systems Conference, DDCLS 2021

作者： Zhao, Fuyu Gao, Weinan Liu, Tengfei Jiang, Zhong-Ping State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China College of Engineering and Science Florida Institute of Technology Department of Mechanical and Civil Engineering MelbourneFL32901 United States New York University Six MetroTech Center Department of Electrical and Computer Engineering BrooklynNY11201 United States

ISBN: (纸本)9781665424233

In this paper, a data-driven event-triggered output-feedback control approach is proposed to solve the problem of adaptive optimal output regulation for uncertain discrete-time linear systems when only the output information is available. A crucial strategy is to develop a novel co-design scheme for the event-triggering mechanism and the data-driven optimal controller. Theoretical analysis and an application to a LCL coupled inverter-based distributed generation system demonstrate the effectiveness of the proposed learning-based, event-triggered, adaptive optimal controller design with output-feedback. © 2021 IEEE.

关键词： Digital control systems

来源：评论

学校读者我要写书评

暂无评论

Sensor-Generated In Situ Data Management for Smart Grids: Dynamic Optimization Driven by Double Deep Q-Network with Prioritized Experience Replay

引用

Applied sciences 2025年第11期15卷 5980-5980页

作者： Peiying Zhang Siyi Li Dandan Li Qingyang Ding Lei Shi Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao 266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao 266580 China School of Management Beijing Union University Beijing 100101 China State Key Laboratory of Media Convergence and Communication Communication University of China Beijing 100024 China

According to forecast data from the state Grid Corporation of China, the number of terminal devices connected to the power grid is expected to reach the scale of 2 billion within the next five years. With the continuous growth in the number and variety of terminal devices in the smart grid, traditional cloud-edge-end architecture will face the increasing issue of response latency. In this context, in situ computing, as a paradigm for local or near-source data processing within cloud-edge-end architecture, is gradually becoming a key technological pathway in industrial systems. The in situ server system, by deploying servers near terminals, enables the near-data-source processing of terminal-generated in situ data, representing an important implementation of in situ computing. To enhance the processing efficiency and response capability of in situ data in smart grid scenarios, this study designs an in situ data processing mechanism and an access demand management framework. Due to the heterogeneity of in situ server performance, there are variations in response capabilities for access demands across rounds. This study introduces a double deep Q-network with prioritized experience replay to assist in response decision-making. Simulation experiments show that the proposed method reduces waiting latency and response latency by an average of 67.69% and 68.77%, respectively, compared to traditional algorithms and other reinforcement learning algorithms, verifying its effectiveness in in situ data management. This scheme can also be widely applied to in situ computing scenarios with low-latency data management, such as smart cities and industrial IoT.

关键词： smart grid in situ data in situ server system data management double deep Q-network

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：