会议名称:
20th International Symposium on Bioinformatics Research and Applications (ISBRA)
会议时间:
JUL 19-21, 2024
会议地点:
Kunming, PEOPLES R CHINA
会议主办单位:
[Zhou, Jiancun;Kuang, Hulin;Wang, Yahui;Wang, Jianxin] Cent South Univ, Sch Comp Sci & Engn, Hunan Prov Key Lab Bioinformat, Changsha, Hunan, Peoples R China.^[Zhou, Jiancun] Hunan City Univ, Coll Informat & Elect Engn, Yiyang, Hunan, Peoples R China.
会议论文集名称:
Lecture Notes in Bioinformatics
关键词:
Hybrid Network;Low-Complexity Self-Attention;Neoadjuvant Chemoimmunotherapy;Lung Cancer Tumor Prediction
摘要:
Neoadjuvant chemoimmunotherapy is an effective treatment for lung cancer. Accurate prediction of lung cancer tumor after neoadjuvant chemoimmunotherapy from Computed tomography (CT) scans is of significance as it can enable clinicians to quickly select patients who will obtain good outcomes after treatments and evaluate patients' prognosis in advance. Therefore, this study proposes a new hybrid Convolutional Neural Network (CNN) and low-complexity Transformer network with attention-based feature fusion to achieve lung cancer tumor prediction after neoadjuvant chemoimmunotherapy on CT scans. In each stage, we first use channel split to reduce the parameters, then we design both CNN branch and low-complexity Transformer branch to learn the effective local and global features. To reduce the computational complexity of the Transformer, we introduce a novel low-complexity self-attention computation method via feature aggregation and element-wise multiplication. Additionally, to effectively fuse CNN and Transformer features, we design an attention-based feature fusion module with coarse fusion, attention computing and fine fusion. The proposed method is evaluated on a private lung cancer dataset including CT scans of 232 patients undergone neoadjuvant chemoimmunotherapy. Experimental results demonstrate that our proposed method achieves the highest Dice of 47.04% with the fewest parameters of 2.91M and floating point operations (FLOPs) of 52.95G, outperforming several state-of-the-art methods. Diameter analysis shows the predicted diameters of lung cancer tumors are promising to provide support information for treatment planning.
会议名称:
20th International Conference on Intelligent Computing (ICIC)
会议时间:
AUG 05-08, 2024
会议地点:
Tianjin Univ Sci & Tech, Tianjin, PEOPLES R CHINA
会议主办单位:
Tianjin Univ Sci & Tech
会议论文集名称:
Lecture Notes in Bioinformatics
关键词:
Lung Cancer Segmentation;Convolutional Neural Network;Transformer;Hybrid Network;Feature Fusion
摘要:
Segmentation of lung cancer lesions can assist physicians in diagnosing the condition. Transformer typically has high computational complexity, and how to effectively integrate Convolutional Neural Network (CNN) and Transformer for lung cancer segmentation remains an unresolved issue. Therefore, this paper introduces a novel hybrid CNN and Transformer network for lung cancer segmentation. The designed method consists of a CNN encoder, a Transformer encoder, a fusion module, and a CNN decoder. The CNN encoder is employed to extract local features, while the Transformer encoder captures global features. We propose a new self-attention-free Transformer block, which replaces the self-attention mechanism with a combination of shifting operations and depth-wise convolution to reduce computational complexity while maintaining performance. In addition, to enhance the interaction between CNN features and Transformer features, we introduce an innovative local-global attention fusion module, which performs feature fusion from both local and global views, resulting in better feature representations. The proposed approach is evaluated on a lung cancer segmentation dataset. Experimental results show that the proposed method achieves a Dice of 0.714 for lung cancer segmentation, outperforming several state-of-the-art methods.
作者机构:
Hunan Provincial Key Laboratory of Remote Sensing, Monitoring of Ecological Environment in Dongting Lake Area, Changsha, Hunan, China;School of Municipal and Surveying Engineering, Hunan City University, Yiyang, Hunan, China;[Zhen Xi; Yun Xue] Hunan Provincial Key Laboratory of Remote Sensing, Monitoring of Ecological Environment in Dongting Lake Area, Changsha, Hunan, China<&wdkj&>School of Municipal and Surveying Engineering, Hunan City University, Yiyang, Hunan, China
会议名称:
2023 4th International Conference on Information Science, Parallel and Distributed Systems (ISPDS)
会议时间:
14 July 2023
会议地点:
Guangzhou, China
会议论文集名称:
2023 4th International Conference on Information Science, Parallel and Distributed Systems (ISPDS)
关键词:
Water quality assessment;Support vector machine;Dongting Lake
摘要:
This paper presents 15 SVM models optimized by machine learning methods in water quality assessment. Through comparative analysis, we found that all the models reached reasonable accuracy during the training and testing process. In particular, SAA-SVM-PI, GWO-SVM-PI, GWO-SVM-TN, PSO-SVM-TP models have the highest accuracy, the highest squared correlation and the lowest mean squared error when testing the three indexes of PI, TN and TP. In order to study the spatial distribution characteristics of water quality in Dongting Lake, GWO-SVM-PI, GWO-SVM-TN and PSO-SVM-TP models were respectively used for single-factor water quality classification. The results showed that: As far as the PI is concerned, the water quality is mainly in grade I and II; As far as TN is concerned, the water quality is mainly of grade IV and V, with the worst water quality in the East Dongting Lake and the outlet profile; In terms of TP, the water quality is mainly of grade III, IV and V, with the best inlet water quality, the worst water quality in the South Dongting Lake.
作者机构:
Hunan City University, Yiyang, Hunan, China;San Yu University, Seoul, South Korea;[Run Zeng] Hunan City University, Yiyang, Hunan, China<&wdkj&>San Yu University, Seoul, South Korea
会议名称:
2023 International Conference on Data Science and Network Security (ICDSNS)
会议时间:
28 July 2023
会议地点:
Tiptur, India
会议论文集名称:
2023 International Conference on Data Science and Network Security (ICDSNS)
关键词:
remote sensing image fusion;urban space design;colour correlation
摘要:
With economic and social development, urbanisation is accelerating and human activities are increasingly interfering with the natural environment, leading to a series of ecological and environmental problems. To solve these problems, rational planning and management of cities is required. One of the important tools is to guide urban construction through urban colour landscapes. At present, many large and medium-sized cities in China have the phenomenon of “a thousand cities in one”, which not only affects people's quality of life, but also restricts the shaping of urban characteristics. Therefore, how to use remote sensing technology to obtain high-resolution satellite images and combine with GIS platform to achieve multi-source data integration application has become one of the current research hotspots. The experimental results show that the composition integrity of urban space design colors based on remote sensing image fusion algorithm can reach up to 94.8%.
作者机构:
ollege of Materials Science and Engineering,Central South University of Forestry and Technology;chool of Civil Engineering,Hunan City University;chool of Civil Engineering,Changsha University of Science and Technology;chool of Civil Engineering,Central South University of Forestry and Technology
会议名称:
2023年第三届高校教育发展与信息技术创新国际学术会议
会议时间:
2023-12-25
会议地点:
中国北京
关键词:
Gluing bamboo arch;In-plane instability mechanism;Experimental study
摘要:
Gluing bamboo arches become the main load-carrying component of modern long-span bamboo structures for its elegant shape and reasonable mechanical behavior.In order to study the in-plane elastic and elastic-plastic instability mechanism and bearing capacity of gluing bamboo arches,the effects of middle-span and quarter-span point loads are considered in this study.The failure mechanism of two-hinge circular gluing bamboo arches made with Douglas fir under different load conditions is analyzed.
作者机构:
[Weizhen Ji] School of Municipal and Surveying Engineering, Hunan City University, Yiyang, Hunan, China;Hunan Provincial Key Laboratory of Remote Sensing, Monitoring of Ecological Environment in Dongting Lake Area, Changsha, Hunan, China;Hunan Provincial Natural Resources Affairs Center, Changsha, Hunan, China;[Zhong-man Duan] Hunan Provincial Key Laboratory of Remote Sensing, Monitoring of Ecological Environment in Dongting Lake Area, Changsha, Hunan, China<&wdkj&>Hunan Provincial Natural Resources Affairs Center, Changsha, Hunan, China;[Yun Xue] Hunan Provincial Key Laboratory of Remote Sensing, Monitoring of Ecological Environment in Dongting Lake Area, Changsha, Hunan, China<&wdkj&>School of Municipal and Surveying Engineering, Hunan City University, Yiyang, Hunan, China
会议名称:
2023 4th International Conference on Information Science, Parallel and Distributed Systems (ISPDS)
会议时间:
14 July 2023
会议地点:
Guangzhou, China
会议论文集名称:
2023 4th International Conference on Information Science, Parallel and Distributed Systems (ISPDS)
关键词:
Water quality assessment;Support vector machine;Gray wolf optimization algorithm;Dongting Lake
摘要:
Water quality assessment is an essential part of water resource management. This paper presents a new GWO-SVM method for water quality assessment. Through comparison with GS-SVM and GA-SVM, we found that GWO-SVM model has the highest accuracy, the highest squared correlation and the lowest mean squared error when testing the three indexes of PI, TN and TP.The GWO-SVM model proposed in this paper was used to analyze the water quality data of Dongting Lake from 1993 to 2012. The results showed that: As far As the PI is concerned, the water quality is mainly in grade I and II, with the best water quality in autumn and 2008-2012.As far As TN is concerned, the water quality is mainly of grade IV and V,With the best water quality in autumn and the worst in spring, water quality was the best from 2003 to 2007 and the worst from 2008 to 2012.In terms of TP, the water quality is mainly of grade III,IV and V, with the best inlet water quality, the worst water quality In the south dongting lake, the best water quality In summer,The best water quality between 1993 and 1997, and the worst water quality between 2003 and 2007.
摘要:
This paper studies the mechanical principle and combined application of shear wall and swing wall in the seismic design of high-rise buildings.Shear wall is a longitudinal wall perpendicular to the plane of a building,which resists the shear force generated by an earthquake through shear resistance,flexural stiffness,and contribution stiffness.Swing wall is a kind of seismic wall that can produce large horizontal displacement.Its mechanical principle is to improve the seismic resistance through flexible design,energy absorption and stiffness control.Shear wall and sway wall have advantages respectively,but they also have limitations respectively.By optimizing the layout and combination of shear walls and swing walls,give full play to their advantages and improve the overall seismic performance of the building.The effectiveness of the combined application is verified by the buildings with different seismic grades and structure types.However,this study has some limitations,such as the failure of the references to fully cover all relevant studies.Future research can further explore more new seismic structure systems,and combine with the latest materials and technology,and constantly improve the seismic design theory and practice of high-rise buildings.To sum up,shear wall and swing wall are a common structural system in the seismic design of high-rise buildings.By studying the mechanical principles and combined application,we provide new ideas and methods for the seismic design of high-rise buildings,which helps to improve the seismic performance and ensure the safety of personnel and property.
作者:
Wei Zhang;Zhe Liang;Hai Lin;Jinkai Shu;Aihe Wang
期刊:
E3S Web of Conferences,2022年350:01016 ISSN:2555-0403
通讯作者:
Liang, Z.
作者机构:
Hunan City University, College of Municipal and Geomatics Engineering, 413000 Yiyang, China;Hunan City University, Hunan Rural Drinking Water Quality Safety Engineering Technology Research Center, 413000 Yiyang, China;Shenyang Jianzhu University, College of Municipal and Environmental Engineering, 110168 Shenyang, China;Yiyang Commodity Quality Supervision and Inspection Institute, 413000 Yiyang, China;[Wang A.; Shu J.; Zhang W.] Hunan City University, College of Municipal and Geomatics Engineering, Yiyang, 413000, China, Hunan City University, Hunan Rural Drinking Water Quality Safety Engineering Technology Research Center, Yiyang, 413000, China
通讯机构:
[Liang, Z.] S;Shenyang Jianzhu University, China
会议名称:
2022 International Conference on Environment, Renewable Energy and Green Chemical Engineering, EREGCE 2022
摘要:
<jats:p>Glyphosate is a typical dissolved organic phosphorus that can cause adverse effects on plants, animals, and humans. Modified shell powder/Ce-N-TiO<jats:sub>2</jats:sub> was synthesized by high-temperature doping, and the prepared modified shell powder/Ce-N-TiO<jats:sub>2</jats:sub> was characterized and used response surface methodology to find out the optimum condition for adsorption removal rate. The zeta characterization indicates that the doping of Ce shifts the isotropic potential of the material to the right. The FT-IR and XPS characterization indicated that glyphosate was successfully adsorbed, and the two-two interactions of pH, contact time and dosing amount had a more obvious effect on adsorption by response surface analysis. The process of glyphosate adsorption by modified shell powder/Ce-N-TiO<jats:sub>2</jats:sub> was consistent with the quasi-secondary kinetic model and Langmuir model, and the maximum adsorption amount was 66.98 mg/g. The above results may be useful for the study of other systems of glyphosate wastewater treatment.</jats:p>
摘要:
In order to get the best mix proportion of recycled concrete with super plasticizer, an experimental research method of mix proportion of recycled concrete with super plasticizer is designed. The whole experimental scheme and steps are described in detail. By adding a kind of additive, i.e. super plasticizer, into recycled concrete of different strength grades (prepared with waste concrete and mixed with part of natural concrete), and testing the performance of recycled concrete in laboratory, the best mix proportion of recycled concrete with super plasticizer is obtained, which lays a foundation for realizing the best parameters of high performance of recycled concrete.
摘要:
In this paper, a regression analysis method of compressive strength curve of recycled concrete is proposed. Firstly, the compressive strength of recycled aggregate concrete at different ages is measured through laboratory tests. Then, based on the regression analysis method, the cubic function is used to simulate and analyze the compressive strength change of recycled aggregate concrete, and the age and comprehensive strength development law of recycled aggregate concrete are obtained.
摘要:
The most important factor in restricting safe and efficient is the unfavorable geological conditions ahead of the tunnel face during tunnel construction in karst area. To avoid the occurrence of geological disasters, advanced geological forecast technology is widely used to detect the development of unfavorable geological bodies. In order to better explain the time-frequency characteristics of GPR signals of tunnel cavern fillings, the Gaussian window function is selected according to the uncertainty principle, and the short-time Fourier transform is used to analyze and process the GPR signals of cavern fillings with different properties based on forward simulation. The results show that the time-frequency spectrum based on short-time Fourier transform can meticulously describe the process of change that takes places in time and frequency plane of GPR signals, which is beneficial to accurately extract the time-frequency characteristic parameters in GPR signals. When the electromagnetic wave wavelength of the GPR transmitting antenna is shorter than the detection depth of cavern fillings, two target reflectors which reflect the upper and lower reflecting interfaces of the fillings will appear in the spectrum of forward simulation signal. The relative errors of recognition results obtained according to the reflection time interval are all less than 5%, which provides a reference for the quantitative interpretation of GPR signals of tunnel cavern fillings.
作者:
Tao Chen;Xinjian Li;Zhemeng Zhang;Tongguang Yang;Shengtao He;...
期刊:
E3S Web of Conferences,2021年256:02035 ISSN:2555-0403
通讯作者:
Chen, T.
作者机构:
[Liao J.; He S.; Zhang Z.; Shao X.; Chen T.] College of Electrical and Information Engineering, Hunan University, Changsha, Hunan Province, 410082, China;[Li X.] Yiyang Power Supply Company, State Grid Hunan Electric Power Company, Yiyang, Hunan Province, 413000, China;[Yang T.] College of Machinery and Electrical Engineering, Hunan City University, Yiyang, Hunan Province, 413049, China
通讯机构:
[Chen, T.] C;College of Electrical and Information Engineering, China
会议名称:
2021 International Conference on Power System and Energy Internet, PoSEI 2021