检索结果-内蒙古大学图书馆

DeepMerge: Deep-learning-based Region-Merging for Image Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lv, Xianwei Persello, Claudio Li, Wangbin Huang, Xiao Ming, Dongping Stein, Alfred School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao066004 China Hebei Key Laboratory of Marine Perception Network and Data Processing Northeastern University Qinhuangdao066004 China Dept. of Earth Observation Science Faculty ITC University of Twente Enschede7500AE Netherlands State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China The Department of Geosciences University of Arkansas FayettevilleAR United States Beijing100083 China

Image segmentation aims to partition an image according to the objects in the scene and is a fundamental step in analysing very high spatial-resolution (VHR) remote sensing imagery. Current methods struggle to effectively consider land objects with diverse shapes and sizes. Additionally, the determination of segmentation scale parameters frequently adheres to a static and empirical doctrine, posing limitations on the segmentation of large-scale remote sensing images and yielding algorithms with limited interpretability. To address the above challenges, we propose a deep-learning-based region merging method dubbed DeepMerge to handle the segmentation of complete objects in large VHR images by integrating deep learning and region adjacency graph (RAG). This is the first method to use deep learning to learn the similarity and merge similar adjacent super-pixels in RAG. We propose a modified binary tree sampling method to generate shift-scale data, serving as inputs for transformer-based deep learning networks, a shift-scale attention with 3-Dimension relative position embedding to learn features across scales, and an embedding to fuse learned features with hand-crafted features. DeepMerge can achieve high segmentation accuracy in a supervised manner from large-scale remotely sensed images and provides an interpretable optimal scale parameter, which is validated using a remote sensing image of 0.55 m resolution covering an area of 5,660 km2. The experimental results show that DeepMerge achieves the highest F value (0.9550) and the lowest total error TE (0.0895), correctly segmenting objects of different sizes and outperforming all competing segmentation methods. © 2023, CC BY.

关键词： Image segmentation

Numerical Simulation Study on Supercritical Co2 Flooding and Storage Applied in a Complex Tight Oil Reservoir

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Li, Huan Tan, Yongsheng Zhou, Xiang Jiang, Qi Pu, Hongbin He, Jie Petroleum Engineering Department Southwest Petroleum University Sichuan Chengdu610500 China State Key Laboratory of Geomechanics and Geotechnical Engineering Institute of Rock and Soil Mechanics Chinese Academy of Sciences Hubei Wuhan430071 China Schulich School of Engineering University of Calgary CalgaryABT2N 1N4 Canada Data Company of Xinjiang Oilfield Company Xinjiang Karamay834000 China Huainan Mining Group Coal Bed Methane Development and Utilization Co. Ltd Anhui Huainan232046 China

In this study, a heterogeneous numerical simulation model was developed to study the supercritical CO2（ScCO2） flooding process applied in tight oil reservoir. The sensitivity analysis was conducted to ensure the developed numerical model is suitable for the production prediction process. By comparing the production performances, concentration C30+, distribution of ScCO2 in the reservoir, etc., the effects of injection parameters such as injection pressure, injection rate, injection volume and injection method were studied and optimized. The mechanisms of light components extraction, miscible flooding in the targeted reservoir was analyzed. The results indicated that ScCO2-EOR is an effective approach to boost tight oil recovery factor in the targeted oil reservoirs, and the mechanisms shew important influences in this flooding process. Using the numerical simulation method, the optimization of the injection parameters was implemented, the oil recovery factor was increased up to 46.37% after pressure depletion and water flooding processes under the optimized injection parameters. In order to reduce the influence of gas channeling, the ScCO2-WAG process was also developed. Compared with ScCO2 flooding process, with ScCO2-WAG application the light components extraction and miscible flooding became weaker, thus lower oil recovery factors were obtained. The CO2 storage was a potential benefit in the ScCO2EOR approach applied in the tight formation. The fruits of this study can be applied to guide the field application. © 2024, The Authors. All rights reserved.

关键词： Carbon dioxide

Balanced Audiovisual dataset for Imbalance Analysis

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xia, Wenke Zhao, Xu Pang, Xincheng Zhang, Changqing Hu, Di Gaoling School of Artificial Intelligence Renmin University of China Beijing China School of Computer Science and Engineering Northeastern University Shenyang China College of Intelligence and Computing Tianjin University Tianjin China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China

The imbalance problem is widespread in the field of machine learning, whichalso exists in multimodal learning areas caused by the intrinsic discrepancybetween modalities of samples. Recent works have attempted to solve themodality imbalance problem from algorithm perspective, however, they do notfully analyze the influence of modality bias in datasets. Concretely, existingmultimodal datasets are usually collected under specific tasks, where onemodality tends to perform better than other ones in most conditions. In thiswork, to comprehensively explore the influence of modality bias, we first splitexisting datasets into different subsets by estimating sample-wise modalitydiscrepancy. We surprisingly find that: the multimodal models with existingimbalance algorithms consistently perform worse than the unimodal one onspecific subsets, in accordance with the modality bias. To further explore theinfluence of modality bias and analyze the effectiveness of existing imbalancealgorithms, we build a balanced audiovisual dataset, with uniformly distributedmodality discrepancy over the whole dataset. We then conduct extensiveexperiments to re-evaluate existing imbalance algorithms and draw someinteresting findings: existing algorithms only provide a compromise betweenmodalities and suffer from the large modality discrepancy of samples. We hopethat these findings could facilitate future research on the modality imbalanceproblem. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

Secrecy Energy Efficiency Maximization for UAV-Enabled FDMA systems

学校读者我要写书评

暂无评论

Secrecy Energy Efficiency Maximization for UAV-Enabled FDMA ...

IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

作者： Jie Sun Zhichao Sheng Ali A. Nasir Yanzan Sun Yong Fang Key Laboratory of Specialty Fiber Optics and Optical Access Networks Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Department of Electrical Engineering and Center for Communication Systems and Sensing King Fahd University of Petroleum and Minerals (KFUPM) Dhahran Saudi Arabia

In this paper, we consider an unmanned aerial vehicle (UAV), which serves multiple legitimate ground users with frequency division multiple access (FDMA) approach in the presence of a potential eavesdropper (EV) with uncertain location information. We also assume that UAV must also avoid flying over the no-fly-zone (NFZ). We aim to maximize the secrecy energy efficiency (SEE) by the robust joint design of the rotary-wing UAV three dimensional (3D) trajectory, bandwidth allocation, and transmit power. However, the optimization problem becomes challenging to solve optimally due to the non-convexity of the problem and the imperfect location information of the EV. We develop an efficient iterative algorithm to obtain its high-quality suboptimal solution. The numerical results indicate that our proposed joint optimization algorithm outperforms the benchmark schemes, resulting in significant enhancement of the energy efficiency of the system.

关键词：

Efficient meta neural heuristic for multi-objective combinatorial optimization 23

学校读者我要写书评

暂无评论

Efficient meta neural heuristic for multi-objective combinat...

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Jinbiao Chen Jiahai Wang Zizhen Zhang Zhiguang Cao Te Ye Siyuan Chen School of Computer Science and Engineering Sun Yat-sen University P.R. China School of Computer Science and Engineering Sun Yat-sen University P.R. China and Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Sun Yat-sen University P.R. China and Guangdong Key Laboratory of Big Data Analysis and Processing Guangzhou P.R. China School of Computing and Information Systems Singapore Management University Singapore

Recently, neural heuristics based on deep reinforcement learning have exhibited promise in solving multi-objective combinatorial optimization problems (MOCOPs). However, they are still struggling to achieve high learning efficiency and solution quality. To tackle this issue, we propose an efficient meta neural heuristic (EMNH), in which a meta-model is first trained and then fine-tuned with a few steps to solve corresponding single-objective subproblems. Specifically, for the training process, a (partial) architecture-shared multi-task model is leveraged to achieve parallel learning for the meta-model, so as to speed up the training; meanwhile, a scaled symmetric sampling method with respect to the weight vectors is designed to stabilize the training. For the fine-tuning process, an efficient hierarchical method is proposed to systematically tackle all the subproblems. Experimental results on the multi-objective traveling salesman problem (MOTSP), multi-objective capacitated vehicle routing problem (MOCVRP), and multi-objective knapsack problem (MOKP) show that, EMNH is able to outperform the state-of-the-art neural heuristics in terms of solution quality and learning efficiency, and yield competitive solutions to the strong traditional heuristics while consuming much shorter time.

关键词：

Speaker Extraction with Co-Speech Gestures Cue

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Pan, Zexu Qian, Xinyuan Li, Haizhou The Integrative Sciences and Engineering Programme The Institute of Data Science National University of Singapore 119077 Singapore The Department of Electrical and Computer Engineering National University of Singapore 119077 Singapore The Guangdong Provincial Key Laboratory of Big Data Computing The Chinese University of Hong Kong Shenzhen518172 China The School of Data Science The Chinese University of Hong Kong Shenzhen518172 China The University of Bremen 28359 Germany

Speaker extraction seeks to extract the clean speech of a target speaker from a multi-talker mixture speech. There have been studies to use a pre-recorded speech sample or face image of the target speaker as the speaker cue. In human communication, co-speech gestures that are naturally timed with speech also contribute to speech perception. In this work, we explore the use of co-speech gestures sequence, e.g. hand and body movements, as the speaker cue for speaker extraction, which could be easily obtained from low-resolution video recordings, thus more available than face recordings. We propose two networks using the co-speech gestures cue to perform attentive listening on the target speaker, one that implicitly fuses the co-speech gestures cue in the speaker extraction process, the other performs speech separation first, followed by explicitly using the co-speech gestures cue to associate a separated speech to the target speaker. The experimental results show that the co-speech gestures cue is informative in associating with the target speaker. Copyright © 2022, The Authors. All rights reserved.

关键词： Extraction

Research progress of CDT 8

学校读者我要写书评

暂无评论

Research progress of CDT

8th International Conference on Bioinformatics and Biomedical Science, ICBBS 2019

作者： Yuting, Gao Shutong, Shen Sanhong, Deng School of Information Management Nanjing University China Key Laboratory of Data Engineering and Knowledge Services in Jiangsu China

ISBN: (纸本)9781450372510

With the high mortality rate for the cases of malignant tumors, the discovery and early treatment of cancer is critical to improving the 5-year survival rate of cancer. The biggest challenge in control and prevention is how to detect tumors as early as possible, so that the most effective means can be used for treatment. With the help of the WOS database, researchers found that liquid biopsy, genetic material/protein expression and computer imaging play an important role in cancer detection. Through analysis of the history and current status of cancer detection technology development, this paper also aims to provide guidance for the clinical practice of current cancer screening and provide inspiration for future technological development. © 2019 Association for Computing Machinery.

关键词： Gene expression

Joint Covert and Secure Communications for Intelligent Reflecting Surface (IRS)-Aided Wireless Networks

学校读者我要写书评

暂无评论

Joint Covert and Secure Communications for Intelligent Refle...

International Conference on Networking and Network Applications (NaNA)

作者： Yihuai Yang Shikai Shen Yumei She Wu Wang Bin Yang Yangshui Gao School of Information and Technology Kunming University Kunming China Yunnan Collegiate Key Laboratory for Data Governance and Intelligent Decision Kunming China School of Mathmatics and Computer Science Yunnan Minzu University Kunming China School of Computer and Information Engineering Chuzhou University Chuzhou China

This work investigates joint covert and secure communications via intelligent reflecting surface (IRS) in a non-line-of-sight (NLOS) wireless network in the presence of an eavesdropper and a warden. We consider a coordinator of Ben communicates with two users, where one user requires secure communication and the other seeks covert communication. An optimization problem is proposed to maximize the covert rate subject to the constraints of covert requirement, secure communication rate, amplitudes and phase shifts of reflecting elements, and transmit powers of secure and covert communications. We use the successive convex approximation(SCA) method to solve this problem. The numerical results illustrate the effectiveness of utilizing an IRS and highlight the impact of the number of reflecting elements on enhancing communication quality.

关键词：

Joint User Association and Transmission Scheduling in Integrated mmWave Access and Terahertz Backhaul Networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Lei Ai, Bo Niu, Yong Jiang, Haiyan Mao, Shiwen Zhong, Zhangdui Wang, Ning The State Key Laboratory of Advanced Rail Autonomous Operation The Beijing Engineering Research Center of High-Speed Railway Broadband Mobile Communications Beijing Jiaotong University Beijing100044 China The State Key Laboratory of Advanced Rail Autonomous Operation Beijing Jiaotong University Beijing100044 China The Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen518055 China The Henan Joint International Research Laboratory of Intelligent Networking and Data Analysis Zhengzhou University Zhengzhou450001 China The National Mobile Communications Research Laboratory Southeast University Nanjing211189 China The Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States The School of Information Engineering Zhengzhou University Zhengzhou450001 China

Terahertz wireless backhaul is expected to meet the high-speed backhaul requirements of future ultra-dense networks using millimeter-wave (mmWave) base stations (BSs). In order to achieve higher network capacity with limited resources and meet the quality of service (QoS) requirements of more users in the integrated mmWave access and terahertz backhaul network, this paper formulates a problem of maximizing the number of users successfully served in both the access and backhaul links. Since the problem is a non-linear integer optimization problem, a minimum rate ratio user association and transmission scheduling algorithm is proposed to obtain a suboptimal solution. The proposed algorithm takes the minimum rate ratio as the user association criterion and schedules first the users with fewer backhaul transmission slots. In addition, the algorithm will update the number of access transmission slots allocated to users and the access scheduling results after the backhaul scheduling phase. Numerical results show that the proposed algorithm outperforms several benchmark algorithms in terms of the number of served users and system throughput, and it can cope with a large number of bursty user requests. Copyright © 2023, The Authors. All rights reserved.

关键词： Millimeter waves