检索结果-内蒙古大学图书馆

RadioGAT: A Joint Model-based and data-driven Framework for Multi-band Radiomap Reconstruction via Graph Attention Networks

学校读者我要写书评

暂无评论

arxiv 2024年

作者： Li, xiaojie Zhang, Songyang Li, Hang Li, xiaoyang Xu, Lexi Xu, Haigao Mei, Hui Zhu, Guangxu Qi, Nan xiao, Ming Shenzhen Research Institute of Big Data The Chinese University of Hong Kong-Shenzhen Guangdong China College of Physics Nanjing University of Aeronautics and Astronautics Nanjing210016 China Department of Electrical and Computer Engineering University of Louisiana at Lafayette LafayetteLA70503 United States Research Institute China United Network Communications Corporation Beijing100048 China China Mobile Communications Group Jiangxi Co. Ltd 330038 China Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space Nanjing University of Aeronautics and Astronautics Nanjing210016 China State Key Laboratory of Integrated Services Networks Xidian University Xi'An710071 China Department of Information Science and Engineering School of Electrical Engineering of KTH Royal Institute of Technology Stockholm Sweden

Multi-band radiomap reconstruction (MB-RMR) is a key component in wireless communications for tasks such as spectrum management and network planning. However, traditional machine-learning-based MB-RMR methods, which rely heavily on simulated data or complete structured ground truth, face significant deployment challenges. These challenges stem from the differences between simulated and actual data, as well as the scarcity of real-world measurements. To address these challenges, our study presents RadioGAT, a novel framework based on Graph Attention Network (GAT) tailored for MBRMR within a single area, eliminating the need for multiregion datasets. RadioGAT innovatively merges model-based spatial-spectral correlation encoding with data-driven radiomap generalization, thus minimizing the reliance on extensive data sources. The framework begins by transforming sparse multiband data into a graph structure through an innovative encoding strategy that leverages radio propagation models to capture the spatial-spectral correlation inherent in the data. This graph-based representation not only simplifies data handling but also enables tailored label sampling during training, significantly enhancing the framework's adaptability for deployment. Subsequently, The GAT is employed to generalize the radiomap information across various frequency bands. Extensive experiments using raytracing datasets based on real-world environments have demonstrated RadioGAT's enhanced accuracy in supervised learning settings and its robustness in semi-supervised scenarios. These results underscore RadioGAT's effectiveness and practicality for MBRMR in environments with limited data availability. Copyright © 2024, The Authors. All rights reserved.

关键词： Encoding (symbols)

Crowdsourcing Answer Integration Algorithm For big data Environment

学校读者我要写书评

暂无评论

Crowdsourcing Answer Integration Algorithm For Big Data Envi...

International Conference on Networking and Network Applications (NaNA)

作者： Hong xia YongKang Zhang Han Wang YanPing Chen ZhongMin Wang Shannxi Key Laboratory of Network Data Analysis and Intelligent Progcessing Xi'an University of Posts and Telecommunications Xi'an China School of Computer Science and Technology Xi'an University of Posts and Telecommunications Xi'an China

ISBN: (数字)9781728189543

ISBN: (纸本)9781728189550

Crowdsourcing is an emerging distributed computing model that is widely used. Aiming at the uneven quality of crowdsourcing answers due to different workers' capabilities and attitudes, it is necessary to effectively study the hotspot issue of crowdsourcing answer integration. A crowdsourced answer integration algorithm based on “filter-evaluate-vote” is proposed. This algorithm is implemented using MapReduce parallel programming model in the Hadoop platform, and experiments are performed on multiple data sets. The results show that the proposed algorithm can be effective. It improves the accuracy of crowdsourced answers, and has high computing performance and horizontal scalability, which is suitable for answer integration in a big data environment.

关键词： Crowdsourcing Computational modeling Scalability big data Quality assessment Time factors Task analysis

Cooperative Game Model of Delegation Computing: Verifier Separated from Calculators

学校读者我要写书评

暂无评论

Cooperative Game Model of Delegation Computing: Verifier Sep...

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Duo Zhang Youliang Tian Linjie Wang Sheng Gao Jianfeng Ma State Key Laboratory of Public Big Data College of Computer Science and Technology College of Mathematics and Statistics Guizhou University Guiyang China State Key Laboratory of Public Big Data College of Computer Science and Technology Institute of Cryptography and Date Security Guizhou University Guiyang China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Information Central University of Finance and Economics Beijing China School of Cyber Engineering College of Computer Science and Technology Xi'dian University Xi'an China

ISBN: (数字)9781728186955

ISBN: (纸本)9781728186962

In cloud computing, the delegation computation service is required because end users usually are resource-constrained, and at the same time the correctness of computing results needs to be verified. However, all the existing and available technologies have a high cost to verify which is the main problem faced by the delegation computing under the cloud platform. In order to address this issue, based on the game theory and a smart contract, we construct three protocols. The client and the calculator sign the Prisoner's Protocol to incentivize correct computation by asking the calculator to pay a deposit upfront; The client and the verifier sign the Long-acting Mechanism Protocol to ensure the validity of the verification results; The calculator and the verifier sign the Collusion Protocol to make collusion the most profitable strategy for all colluding parties. Through the combination of these protocols, the work is realized by separation the computing task and the verification task, and the heavy verification task is avoided. Finally, the performance analysis of the results shows that the combination of all the protocols not only solves the problem of verification complexity in the traditional delegation computing, but also guarantees the benefit of the honest player.

关键词： Calculators Contracts Protocols Task analysis Computational modeling Cloud computing Security

An algorithm of crowdsourcing answer integration based on specialty categories of workers 5th

学校读者我要写书评

暂无评论

An algorithm of crowdsourcing answer integration based on sp...

5th Euro-China Conference on intelligent data Analysis and Applications, ECC 2018

作者： Chen, Yanping Wang, Han xia, Hong Gao, Cong Wang, Zhongmin School of Computer Science and Technology Xi’an University of Posts and Telecommunications Xi’an China Shannxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi’an University of Posts and Telecommunications Xi’an China

ISBN: (纸本)9783030037659

The effective integration of crowdsourcing answers has become research hot spots in crowdsourcing quality control. Taking into account the influence of the specialty categories of workers on the accuracy of crowdsourced answers, a crowdsourced answer integration algorithm based on the specialty categories of workers is proposed(SCAI). Firstly, SCAI use the crowdsourced answer set to determine the difficulty of the task. Secondly calculate the accuracy of each crowdsourced answer, then obtain the professional classification of the workers and update the professional accuracy. Experiments were conducted on real data sets and compared with classical majority voting method(MV) and expectation maximization evaluation algorithm(EM). The results show that the proposed algorithm can effectively improve the accuracy of crowd-sourced answer. © Springer Nature Switzerland AG 2019.

关键词： Quality control

A Dynamic Adaptive Search Algorithm for CoSpace Rescue Robot

学校读者我要写书评

暂无评论

A Dynamic Adaptive Search Algorithm for CoSpace Rescue Robot

International Conference on Robotics and Automation Engineering (ICRAE)

作者： Li Chengbo Wang xiaoming Huang Zixi Pang Guangyao Han xinyu Lin Yaguang Dalian Free Trade Zone No. 1 High School Dalian China Key Laboratory of Modern Teaching Technology Ministry of Education Xi'an China School of Computer Science Shaanxi Normal University Xi'an China Shenzhen Middle School Shenzhen China School of Data Science and Software Engineering Wuzhou University Wuzhou China Advanced Robotics and Intelligent Control Centre Singapore Polytechnic Singapore

ISBN: (纸本)9781665406987

The application of robots to assist humans in earthquake rescue has always been an important topic that researchers are constantly studying. CoSpace Rescue is an abstract modeling and simulation of earthquake rescue and a simulation platform for studying robot rescue search algorithms. Its mathematical model is a multi-objective optimization problem. In this paper, we propose a search algorithm design framework for the CoSpace Rescue robot. Based On this framework and the idea of the heuristic search algorithm, we design and implement the “Multi-objective Optimal Dynamic Adaptive On-Demand Search Algorithm”. The results of the experiment show that the algorithm can dynamically adapt to the changes in the environment and significantly improve the search efficiency of the rescue robot.

关键词： Automation Heuristic algorithms Earthquakes Mathematical models Scheduling Optimization Rescue robots

Deep learning for depression recognition with audiovisual cues: A review

学校读者我要写书评

暂无评论

arxiv 2021年

作者： He, Lang Niu, Mingyue Tiwari, Prayag Marttinen, Pekka Su, Rui Jiang, Jiewei Guo, Chenguang Wang, Hongyu Ding, Songtao Wang, Zhongmin Pan, xiaoying Dang, Wei School of Computer Science and Technology Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Shaanxi Key Laboratory of Network Data Analysis and Intelligent Processing Xi'an University of Posts and Telecommunications Shaanxi Xi'an710121 China Beijing100190 China Beijing100049 China Department of Computer Science Aalto University Espoo Finland School of Foreign Languages Northwest University Shaanxi Xi'an China School of Electronic Engineering Xi'an University of Posts and Telecommunications Xi'an China School of Electronics and Information Northwestern Polytechnical University Shaanxi Xi'an China Shaanxi Mental Health Center Shaanxi Xi'an710061 China

With the acceleration of the pace of work and life, people have to face more and more pressure, which increases the possibility of suffering from depression. However, many patients may fail to get a timely diagnosis due to the serious imbalance in the doctor-patient ratio in the world. Promisingly, physiological and psychological studies have indicated some differences in speech and facial expression between patients with depression and healthy individuals. Consequently, to improve current medical care, many scholars have used deep learning to extract a representation of depression cues in audio and video for automatic depression detection. To sort out and summarize these works, this review introduces the databases and describes objective markers for automatic depression estimation (ADE). Furthermore, we review the deep learning methods for automatic depression detection to extract the representation of depression from audio and video. Finally, this paper discusses challenges and promising directions related to automatic diagnosing of depression using deep learning technologies. © 2021, CC BY.

关键词： Diagnosis

Identifying Differentially Expressed Genes Based on Differentially Expressed Edges 1

学校读者我要写书评

暂无评论

15th International Conference on intelligent Computing, ICIC 2019

作者： Chen, Bolin Gao, Li Shang, Xuequn School of Computer Science Northwestern Polytechnical University Xi’an China Key Laboratory of Big Data Storage and Management Ministry of Industry and Information Technology Northwestern Polytechnical University Xi’an China

ISBN: (数字)9783030269692

ISBN: (纸本)9783030269685

Identification of differentially expressed (DE) genes under different experimental conditions is an important task in many microarray-based studies. There are many methods developed to detect DE genes based on either fold-change (FC) strategy or statistical test. However, majority of those methods identify DE genes by calculating the expression values of individual genes, without taking interactions between genes into consideration. In this study, we consider the interaction and importance of genes in the network and believe that the edges in the network also contribute a lot to DE genes. Therefore, we propose three new ideas for calculating the expression values of edges by considering mean expression, minimal expression and partial expression, respectively. Those methods were implemented and evaluated on the microarray data and were compared with existing methods. The results show that the proposed edge-based methods can identify more biologically relevant genes and have high computational efficiency. More importantly, the Min-Edge method outperforms the other methods when feasibility and specificity are considered simultaneously. © 2019, Springer Nature Switzerland AG.

关键词： Gene expression

Semantics-Guided Contrastive Network for Zero-Shot Object Detection

学校读者我要写书评

暂无评论

arxiv 2021年

作者： Yan, Caixia Chang, xiaojun Luo, Minnan Liu, Huan Zhang, xiaoqin Zheng, Qinghua The Ministry of Education Key Lab of Intelligent Networks and Network Security National Engineering Lab for Big Data Analytics School of Electronic and Information Engineering Xi'an Jiaotong University Shaanxi710049 China The ReLER Lab AAAI Faculty of Engineering and Information Technology University of Technology Sydney Australia The College of Computer Science and Artificial Intelligence Wenzhou University China

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories;2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks. © 2021, CC BY.

关键词： Object detection

XTQA: Span-Level Explanations for Textbook Question Answering

学校读者我要写书评

暂无评论

arxiv 2020年

作者： Ma, Jie Chai, Qi Liu, Jun Yin, Qingyu Wang, Pinghui Zheng, Qinghua Ministry of Education of Key Lab for Intelligent Networks and Network Security School of Cyber Science and Engineering Xi’an Jiaotong University Shaanxi Xi’an710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering The School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Xi’an710049 China Amazon United States

Textbook Question Answering (TQA) is the task of correctly answering diagram or non-diagram questions given large multi-modal contexts consisting of abundant essays and diagrams. In real-world scenarios, an explainable TQA system plays a key role in deepening humans’ understanding of learned knowledge. However, there is no work to investigate how to provide explanations currently. To address this issue, we devise a novel architecture towards span-level eXplanations for TQA (XTQA). In this paper, spans are the combinations of sentences within a paragraph. The key idea is to consider the entire textual context of a lesson as candidate evidence, and then use our proposed coarse-to-fine grained Explanation Extracting (EE) algorithm to narrow down the evidence scope and extract the span-level explanations with varying lengths for answering different questions. The EE algorithm can also be integrated into other TQA methods to make them explainable and improve the TQA performance. Experimental results show that XTQA obtains the best overall explanation result (mIoU) of 52.38% on the first 300 questions of CK12-QA test splits, demonstrating the explainability of our method (non-diagram: 150 and diagram: 150). The results also show that XTQA achieves the best TQA performance of 36.46% and 36.95% on the aforementioned splits respectively. We have released our code in https://***/dr-majie/*** Codes 68T07 Copyright © 2020, The Authors. All rights reserved.

关键词： Textbooks