关键词：
Energy storage system;Micro energy network;Multi-objective optimization;Improved weighted fuzzy method
摘要：
As a terminal type of micro integrated energy system, micro energy network is small in scale and easy to implement, which meets the needs of developing an integrated energy system. Consequently, it has great promotion value. In order to better coordinate the economy, energy conservation and environmental protection of micro energy network, this paper first establishes a multi-objective optimal operation model considering the factors of economy, energy and environment. Second, an improved weighted fuzzy method is proposed to transform the above model into a single-objective one, which can be solved by the particle swarm algorithm. Then, the results and satisfaction of single-objective and multi-objective optimization are compared and analyzed in the example. By optimizing the membership function and multi-objective weight setting method of the traditional weighted fuzzy method, not only the importance of different objectives can be reflected, but also the relationship between single-objective and multi-objective optimization results can be reflected. The proposed improved weighted fuzzy method can improve the comprehensive coordination among multiple objectives and the robustness of the algorithm, optimize the output of each device and realize the coordinated development of energy, environment and economic benefits. It is not only suitable for solving multi-objective optimization problems of micro-energy network, but also for other scenarios. (C) 2023 Published by Elsevier Ltd. This is an open access article under the CCBY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
作者机构：
[Kuang L.-D.; Gui Y.; Li W.] School of Computer and Communication Engineering, Changsha University of Science and Technology, Changsha, 410114, China
会议名称：
29th International Conference on Neural Information Processing, ICONIP 2022
作者机构：
[Yang, Yawen] Hunan Univ, Hunan Int Econ Univ, Changsha, Peoples R China.;[Huang, Linda; Huang, LD; Peng, Junjie] Changsha Univ Sci & Technol, Changsha, Peoples R China.
会议名称：
25th International Conference on Human-Computer Interaction (HCI International)
会议时间：
JUL 23-28, 2023
会议地点：
Copenhagen, DENMARK
会议主办单位：
[Yang, Yawen] Hunan Univ, Hunan Int Econ Univ, Changsha, Peoples R China.^[Huang, Linda;Peng, Junjie] Changsha Univ Sci & Technol, Changsha, Peoples R China.
会议论文集名称：
Lecture Notes in Computer Science
关键词：
Metro;Digital media;Advertising design;Scene
摘要：
With the rise of digital media and the large-scale construction of China's metro, digital media advertising intervenes in the metro space, breaks through traditional advertising forms with strong interactivity and communication capabilities, and provides users with personalized services. This research focuses on 1675 questionnaires on metro advertising scene design and studies the performance characteristics, development trends and user preferences of metro advertising in the digital media era. This paper believes that metro advertising should introduce new technologies brought by digital media, seize the unique advantages of metro scenes, realize the innovation of advertising communication, and improve the situational experience of advertising.
摘要：
Nowadays, the researches of conflict analysis are increasing with the development of three-way decisions, and three-way decisions with rankings and reference tuples provides new perspectives for conflict analysis. In this paper, we first divide a whole set of issues into a bundle of supported issues and a bundle of non-supported issues, and a bundle of opposed issues and a bundle of non-opposed issues, respectively, from the perspectives of support and opposition. Accordingly, we give two ranking orders and two reference tuples. Then, we put forward alliance and conflict measures by considering weights of issues, and develop models of three-way conflict analysis with ideas of rankings and reference tuples. Finally, we show how to compute the alliance, neutral and conflict coalitions with the proposed models. It provides an attempt to study conflict problems with thoughts of rankings and reference tuples.
摘要：
This study simulated the composite regeneration process of a Catalyzed Diesel Particulate Filter (CDPF). The degradation performance was evaluated using the maximum wall temperature as the benchmark. The orthogonal experiment design and fuzzy grey correlation analysis approach were employed to analyze the effect of various factors, including regeneration temperature, NOx mass, catalyst coating amount, SO2 concentration, oxygen concentration, and exhaust flow rate, on the degradation of the CDPF. A comprehensive analysis of the factors was conducted, yielding important insights into the key factors that can be leveraged to optimize the system. The results reveal that these six operating parameters are the primary drivers of the CDPF's performance degradation, with the NOx mass having the greatest impact on the maximum wall temperature. (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
作者机构：
[He, Yi; Hu, Jinbin; Wang, Jin; Luo, Wangqing] Changsha Univ Sci & Technol, Changsha, Peoples R China.;[Huang, Jiawei] Cent South Univ, Changsha, Peoples R China.
会议名称：
52nd International Conference on Parallel Processing (ICPP)
会议时间：
AUG 07-10, 2023
会议地点：
Salt Lake City, UT
会议主办单位：
[Hu, Jinbin;He, Yi;Wang, Jin;Luo, Wangqing] Changsha Univ Sci & Technol, Changsha, Peoples R China.^[Huang, Jiawei] Cent South Univ, Changsha, Peoples R China.
关键词：
Data Center;Lossless Networks;Load Balancing;Reordering
摘要：
Many existing load balancing mechanisms work effectively in lossy datacenter networks (DCNs), but they suffer from serious packet reordering in lossless Ethernet DCNs deployed with the hop-by-hop Priority-based Flow Control (PFC). The key reason is that the prior solutions are not able to correctly and timely perceive PFC triggering when making load balancing decisions. Once the forwarding path pauses transmission due to PFC triggering, the packets allocated on it are blocked, inevitably leading to out-of-order packets and retransmission. In this paper, we present a Reordering-robust Load Balancing (RLB) scheme with PFC prediction in lossless DCNs. At its heart, RLB leverages the derivative of ingress queue length to predict PFC triggering and proactively notifies the upstream switches to choose an appropriate rerouting path or perform packet recirculation to avoid reordering. As a building block for existing load balancing mechanisms, we have integrated RLB into Presto, LetFlow, Hermes and DRILL. The test results show that the RLB-enhanced solutions deliver significant performance by avoiding packet reordering. For example, it reduces the 99..h percentile flow completion time (FCT) by up to 58%, 67%, 72% and 54% over Presto, LetFlow, Hermes and DRILL, respectively.
摘要：
To analyze the feasibility of soft buton rock asphalt (BRA) as asphalt rejuvenating agent, and taking AC-20C asphalt mixture as the research object, the mix design and test of modified hot recycled asphalt mixture with five different soft BRA contents (1%- 5%) and five different RAP contents (10%-50%) were carried out based on response surface optimization method, so the optimal soft BRA content was determined. Then the pavement performance tests of five kinds of modified hot recycled asphalt mixture with different RAP contents were carried out and compared with common asphalt mixture, so as to determine the suitable RAP content. The results show that the consistency, high-, and low- temperature performance of soft BRA are between those of A-70# matrix asphalt and hard BRA or RAP waste asphalt. The soft BRA has good viscoelasticity and more light components, which can be used as rejuvenating agent. With the increase of soft BRA and RAP content, the optimum oil-stone ratio of modified hot recycled asphalt mixture increases, while the optimum oil-stone ratio of matrix asphalt decreases. The optimal content of soft BRA is recommended to be 3%. Compared with the common asphalt mixture, when the RAP content does not exceed 30%, the mixing of soft BRA can comprehensively improve the high-temperature stability, water stability, low-temperature crack resistance, and impermeability of modified hot recycled asphalt mixture. It is suggested that the suitable content range of RAP is 10%-30%. Therefore, the soft BRA can provide a new economic and green rejuvenating agent for central plant hot-mix asphalt recycling technology.
作者机构：
[Xia, ZQ; Xia, Zhuoqun; Jiang, Qisheng; Hu, Hangyu] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.;[Li, Wenjing] Hunan Normal Univ, Affiliated Hosp 1, Hunan Prov Peoples Hosp, Changsha, Peoples R China.;[Zhu, Chengzhang] Cent South Univ, Mobile Hlth Minist Educ, China Mobile Joint Lab, Coll Literature & Journalism, Changsha, Peoples R China.;[Zou, Ziwei] Cent South Univ, Sch Comp Sci & Engn, Changsha, Peoples R China.
会议名称：
International Joint Conference on Neural Networks (IJCNN)
会议时间：
JUN 18-23, 2023
会议地点：
Broadbeach, AUSTRALIA
会议主办单位：
[Xia, Zhuoqun;Hu, Hangyu;Jiang, Qisheng] Changsha Univ Sci & Technol, Sch Comp & Commun Engn, Changsha, Peoples R China.^[Li, Wenjing] Hunan Normal Univ, Affiliated Hosp 1, Hunan Prov Peoples Hosp, Changsha, Peoples R China.^[Zhu, Chengzhang] Cent South Univ, Mobile Hlth Minist Educ, China Mobile Joint Lab, Coll Literature & Journalism, Changsha, Peoples R China.^[Zou, Ziwei] Cent South Univ, Sch Comp Sci & Engn, Changsha, Peoples R China.
会议论文集名称：
IEEE International Joint Conference on Neural Networks (IJCNN)
关键词：
DR diagnosis;deep learning;multi-level patch attention mechanism;lesion localization;DDR dataset
摘要：
In order to solve the problem that the existing methods in the field of diabetic retinopathy (DR) intelligent diagnosis have not fully exploited the effective DR lesion information in the fundus map, as well as the problem that the traditional attention mechanism have not fully explored the influencing factors of different lesion category in DR grading. This paper proposed a diagnostic method that fuses multi-level patch attention and lesion location. The method contains a multi-level patch lesion attention generator (MPAG) and lesion location module (LLM). The MPAG generates a attention map containing the lesion level imformation of different fundus patches, which is weighted with the fundus map and classified by a global network. The LLM is able to indicate lesion and generate a localization-based global attention and increasing the weights of lesion details in the classification network. This paper demonstrated the effectiveness of the proposed method through extensive experiments on the DDR dataset, obtained an accuracy of 0.8064.
会议名称：
11th ACM Workshop on Information Hiding and Multimedia Security (IH and MMSec)
会议时间：
JUN 28-30, 2023
会议地点：
Loyola Univ Chicago, Water Tower Campus, Chicago, IL
会议主办单位：
Loyola Univ Chicago, Water Tower Campus
关键词：
video frame interpolation;multi-scale;kernel-based;deep learning
摘要：
Video frame interpolation is a challenging task in the video processing field. Benefiting from the development of deep learning, many video frame interpolation methods have been proposed, which focus on sampling pixels with useful information to synthesize each output pixel using their own sampling operation. However, these works have data redundancy limitations and fail to sample the correct pixel of complex motions. To solve these problems, we propose a new warping framework to sample called multi-scale expandable deformable convolution(MSEConv) which employs a deep fully convolutional neural network to estimate multiple smallscale kernel weights with different expansion degrees and adaptive weight allocation for each pixel synthesis. MSEConv covers most prevailing research methods as special cases of it, thus MSEConv is also possible to be transferred to existing works for performance improvement. To further improve the robustness of the whole network to occlusion, we also introduce a data preprocessing method for mask occlusion in video frame interpolation. Quantitative and qualitative experiments show that our method shows a robust performance comparable to or even superior to the state-of-the-art method. Our source code and visual comparable results are available at https://github.com/Pumpkin123709/MSEConv.
摘要：
As more agencies move toward implementing the balanced mix design (BMD) of asphalt mixtures, laboratory performances, including resistance to cracking, will be required to meet established criteria during mix design. There may be cases when several candidate mixes with different components need to be evaluated for fatigue cracking resistance prior to final mix design selection, which can be time-consuming and sometimes non-practical. To reduce the number of laboratory tests, a quick prediction method to identify the mixtures with better cracking resistance without need to complete the test is required. Artificial neural network has shown potential to predict certain properties of asphalt mixtures in recent research. This study investigated implementing one type of artificial neural network-convolutional neural network (CNN), to predict the cracking resistance of asphalt mixtures, represented by the overlay test based on the material properties and test setup parameters. The architecture of the CNN was established and optimized, with predicting capability tested and evaluated. The predicting quality of the CNN was slightly better than the linear regression model, demonstrating potential to preliminarily predict the cracking resistance so the laboratory testing effort can be reduced.
会议论文集名称：
IEEE International Symposium on Geoscience and Remote Sensing IGARSS
摘要：
Multi-baseline (MB) Phase Unwrapping (PU) technology is an important step in Synthetic Aperture Radar Interferometry (InSAR). The related method of MBPU aims to improve the noise robustness of the Chinese Remainder Theorem (CRT). As one of the popular methods of MBPU, the existing MBPU method based on cluster analysis (CA) has some challenges that need to be improved in practical applications. For example, the clustering results are inaccurate, the time required to process large-scale interferograms is too long, and the noise clusters in the clustering results are not processed further. To address the above issues, this paper proposes a WaveCluster-based fast and large scale MBPU method (WCFLS). Firstly, the InSAR data set is preprocessed, and then the WaveCluster algorithm is used to process the data set. Finally, the noise clusters in the clustering results are firstly identified accurately, and then the cluster numbers are reassigned to the noise clusters. Theoretical analysis and experiments show that the proposed method has a better improvement in noise robustness and efficiency.
会议名称：
47th IEEE-Computer-Society Annual International Conference on Computers, Software, and Applications (COMPSAC)
会议时间：
JUN 27-29, 2023
会议地点：
Univ Torino, Torino, ITALY
会议主办单位：
Univ Torino
会议论文集名称：
Proceedings International Computer Software and Applications Conference
关键词：
deep clustering;implicit transformation;K-means;orthogonal transformation matrix
摘要：
The deep clustering algorithm can learn the latent embedded features of the data through the autoencoder, and cluster the data according to the similarity of the latent features. However, the feature information obtained by the autoencoder may not have a better value for the clustering algorithm and is not suitable for clustering, which greatly reduces the clustering effect. This paper proposes a deep K-means clustering algorithm with implicitly embedded space transformation to answer this question. We implicitly transform the latent feature space into a new type of space that is more friendly to the clustering task, which preserves space invariance. This implicit transformation is done through an orthogonal transformation matrix. The orthogonal transformation matrix is composed of the eigenvectors of the intra-class scattering matrix and the inter-class scattering matrix. In the new space, clusters can be better separated by cluster cohesion and inter-cluster difference. We alternately optimize feature acquisition and clustering to adjust the embedding space and disperse the embedding points, to enrich the clustering information in the latent feature space. Experimental results show that our proposed algorithm can produce better high-quality clusters than many current correlation clustering algorithms on the same experimental dataset.
关键词：
Urban intersection;asphalt pavement;rutting;disease-prone area;pavement maintenance quality index;Gumbel distribution
摘要：
The asphalt pavement disease-prone area refers to the areas where diseases such as ruts, cracks, and other diseases are prone to occur due to traffic channelization, repeated braking and stopping of vehicles at urban intersection, and the performance of asphalt pavement in this area is often poor. Taking several typical intersections in Changsha urban area as the research object, the multi-functional road condition rapid detection device was used to detect the outer second lane of each driving direction of intersection, and the pavement indexes including pavement surface condition index (PCI), pavement riding quality index (RQI), pavement rutting depth index (RDI), pavement surface wearing index (PWI), pavement bumping index (PBI), etc. were obtained with 10 m as the unit. The 35 sets of data obtained were normalized and analyzed in correlation. The pavement maintenance quality index (PQI) was calculated, and the probability distribution model was used to study the range of disease-prone area at urban intersection. The results show that all pavement indexes in the range of intersection decrease significantly. The length of the disease-prone area of the upstream lane of the stop line is significantly greater than that of the downstream lane. RDI has the strongest correlation with other indexes, and rutting is the most important disease form of asphalt pavement at intersection. The PQI conforms to the characteristics of Gumbel distribution model within the range of intersection. The PQI at 7.44 m away from the stop line of the upstream lane obtains a minimum value, and the maximum value of PQI is obtained at infinite distance from the stop line. The area in the first 40 m and back 125 m of the stop line can be identified as the disease-prone area.
关键词：
Power selling company;FAHP;Dynamic adjustment model of performance guarantee quota;Medium/long-term transaction decision-making
摘要：
The existing mode of the fixed performance guarantee quota, which is susceptible to subjective determination, results in a lack of objectivity in the cost calculations of power selling companies, and has an impact on the calculation of their trading profits. Thus, it negatively impacts the stability of power market transactions as well as the operating enthusiasm of power selling company. Therefore, a dynamic adjustment strategy for performance guarantee quota is proposed, taking into account assessment criteria for the economic benefit of power selling companies, such as the degree of credit overdraft, the level of market share impact and national policies. Based on the fuzzy analytic hierarchy process (FAHP), the proposed dynamic adjustment model of the performance guarantee quota of power selling companies is established. To maximize the profit of power selling companies, the optimization decision of multiple types of transactions based on the proposed dynamic adjustment model of performance guarantee quota is carried out, such as decision-making of the medium/long-term transactions. Based on numerical simulations in MATLAB, the dynamic adjustment range of the performance guarantee quota is given. The suitability and effectiveness of the adjusted performance guarantee quota are verified by comparing and analyzing the differences, in the cost of power selling company in multiple scenarios. (c) 2023 The Author(s). Published by Elsevier Ltd. This is an open access article under theCCBY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
会议论文集名称：
IEEE International Joint Conference on Neural Networks (IJCNN)
关键词：
Block term decomposition (BTD);weighted spatial pooling;orthonormality;fMRI data
摘要：
The rank-(L,L,1,1) block term decomposition (BTD) with spatial orthonormality (BTD-O) applied to 4-way multi-subject fMRI data achieves good performance due to preserving higher spatial structure and reducing crosstalk between components. However, the high rank L value (e.g., 35) of BTD-O for fMRI data leads to high computation complexity. Moreover, multi-subject fMRI data contains high noise nature. Although an accelerated BTD-O (accBTD-O) was proposed, it showed similar performance to BTD-O. Inspired by the compression, smoothing, and spatial structure invariance features of the pooling scheme, we respectively propose weighted spatial 3D and 2D pooling preprocessing for BTD-O of fMRI data. These two methods give higher weight to meaningful in-brain voxels and reduce the size and noise of fMRI data. Specifically, weighted spatial 3D pooling compresses weighted 3D brain images of a 5-way fMRI tensor, then transforms pooled 5-way fMRI tensor into a 4-way fMRI tensor. In contrast, for weighted spatial 2D pooling, the 5-way weighted fMRI data is first transformed into a 4-way tensor, and then 2D brain images of 4-way fMRI tensor are compressed by 2D pooling. The pooled 4-way fMRI tensor is separated by BTD-O to extract shared spatial maps, shared time courses, and subject intensities. Results of simulated and experimental fMRI data analyses both demonstrate that these two proposed methods achieve obviously better task-related component than compared methods. Moreover, the proposed 3D pooling is about 2.243 times faster than accBTD-O.
期刊：
International Conference on Network Protocols. Proceedings,2023年:1-11 ISSN：1092-1648
通讯作者：
Hu, JB
作者机构：
[Hu, Jinbin; Hu, JB] Changsha Univ Ssci & Technol, Changsha, Peoples R China.;[Zeng, Chaoliang; Hu, Jinbin; Hu, JB; Wang, Zilong; Zhang, Junxue; Chen, Kai] Hong Kong Univ Sci & Technol, Hong Kong, Peoples R China.;[Guo, Kun] Fuzhou Univ, Fuzhou, Peoples R China.;[Xu, Hong] Chinese Univ Hong Kong, Hong Kong, Peoples R China.;[Huang, Jiawei] Cent South Univ, Changsha, Peoples R China.
通讯机构：
[Hu, JB ] C;Changsha Univ Ssci & Technol, Changsha, Peoples R China.;Hong Kong Univ Sci & Technol, Hong Kong, Peoples R China.
会议名称：
31st IEEE International Conference on Network Protocols (ICNP)
会议时间：
OCT 10-13, 2023
会议地点：
Reykjavik, ICELAND
会议主办单位：
[Hu, Jinbin] Changsha Univ Ssci & Technol, Changsha, Peoples R China.^[Hu, Jinbin;Zeng, Chaoliang;Wang, Zilong;Zhang, Junxue;Chen, Kai] Hong Kong Univ Sci & Technol, Hong Kong, Peoples R China.^[Guo, Kun] Fuzhou Univ, Fuzhou, Peoples R China.^[Xu, Hong] Chinese Univ Hong Kong, Hong Kong, Peoples R China.^[Huang, Jiawei] Cent South Univ, Changsha, Peoples R China.
会议论文集名称：
IEEE International Conference on Network Protocols Proceedings
关键词：
Datacenter;Lossless Networks;Load Balancing
摘要：
Various datacenter network (DCN) load balancing schemes have been proposed in the past decade. Unfortunately, most of these solutions designed for lossy DCNs do not work well for Priority Flow Control (PFC) enabled lossless DCNs, primarily due to the reason that the individual congestion signals used in these solutions, e.g., link load, queue length, Round Trip Time (RTT) and Explicit Congestion Notification (ECN), may not be able to correctly or timely reflect the hop-by-hop PFC pausing. This paper first reveals the above problems via extensive experiments, and then based on the insights learned, we present Proteus, a PFC-aware load balancing scheme that is resilient to PFC pausing by exploring a combination of multi-level congestion signals. At its heart, Proteus leverages RTT-Ievel signals (i.e., RTT and link utilization) to detect path status for initial routing decision, and exploits sub-RTT level signal (i.e., cumulative sojourn time) to reflect instantaneous PFC pausing and make timely rerouting choices based on the idea of better-late-than-never. We have implemented Proteus in the hardware programmable switch. Our testbed experiments as well as large-scale simulations show that Proteus can effectively handle PFC pausing under realistic workloads and achieve up to 35 %, 31 %, 28%, 22% and 46 %, 42 %, 34 %, 29 % better average FCT and 99 th percentile FCT than CONGA, DRILL, Hermes and MP-RDMA, respectively.
会议论文集名称：
IEEE International Conference on Intelligent Transportation Systems-ITSC
关键词：
Collaborative Machine Learning;Target recognition;channel state information
摘要：
The introduction of orthogonal frequency division multiplexing (OFDM) and multiple input multiple output (MIMO) technology enables the new generation of the Internet of Vehicles to have the ability to integrate wireless communication and target tracking. Based on the new Internet of Vehicles, a cooperative convolutional neural network with data-importance-aware (DIA) is proposed.We use wireless channel state information (CSI) to construct a micro Doppler feature data set. A distributed collaborative machine learning method of DIA is proposed to realize the target recognition of the vehicle. Experimental results show that the vehicle recognition accuracy of the proposed method is higher than 95%, and the convergence speed of the machine learning model is improved.
作者机构：
[Hu, Junxuan; Liu, Yuhan] PowerChina Zhongnan Engineering Corporation Limited, Changsha, China;[Peng, Yuyao; Chen, Chun; Wan, Jinjin; Cao, Bozhong] School of Electrical & Information Engineering, Changsha University of Science and Technology, Changsha, China
会议名称：
10th China International Conference on Electricity Distribution, CICED 2022
作者机构：
[Ni, Yanru; Yu, Kun; Cheng, Xinxiang; Tang, Yuhang; Zeng, Xiangjun] Changsha University of Science and Technology, Changsha, China;[Han, Wei] State Grid Taiyuan Power Supply Company, Taiyuan, China
会议名称：
10th China International Conference on Electricity Distribution, CICED 2022
