Advances in Computer and Engineering Technology Research

Roadbed continuous compaction quality testing and settlement difference detection "dual control" practice and methods

Tianbao Zhang, Yong Chen, Junsong Chang, Kaiyang Liu — Sun, 01 Dec 2024 00:00:00 +0800

The continuous compaction quality testing technology of roadbed is disturbed by many external factors, and improving the accuracy of testing is the key link of construction quality control. With the background of a reclaimed soil roadbed project, the test method for continuous compaction quality control of roadbed was formulated, including the compaction testing test section division and the combination of rolling number of passes as well as the "dual-control" process system; the linear relationship between the VCV value and the sand filling method of compaction testing was verified; the GPS elevation data were compared with the sand filling method to determine the compaction level. 22.264, correlation coefficient R=0.8781; through the analysis of variance between GPS elevation data and measured elevation data, the stability of GPS automatic elevation data is determined, and the test data proves that the characterization of roadbed compaction by settlement difference value and VCV detection value has good consistency, and that "dual control" of settlement difference method and VCV value is reasonable. "is reasonable, and gives the 96 area sandwiched with gravel particles of dry stiff clay fill soil roadbed rolling reasonable total number of times for 9 times, VCV reasonable threshold value of 65.30.

Analyzing the Spillover Effect of Fed Rate Hikes and Cross-Border Capital Flows Risk using SVAR Model

Yuhan Mao, Yuxin Jin — Fri, 06 Dec 2024 00:00:00 +0800

In March 2023, the collapse of Silicon Valley Bank in the United States was considered the largest bank failure since the 2008 financial crisis. Behind this event, the catalyst for the collapse of Silicon Valley Bank was also the Federal Reserve's interest rate hike. Under the current impact of the Federal Reserve's tightening cycle, it not only caused systemic financial risks on a global scale, but also significantly increased cross-border capital flow risks and uncertainties in exchange rate fluctuations. With the increasing openness of China's financial sector, the continuous interest rate hikes by the Federal Reserve have exerted greater pressure on the renminbi exchange rate and cross-border capital flows. This article analyzes the spillover effects of the Federal Reserve's interest rate hikes, systematically studies their impact on cross-border capital flows, exchange rates, and asset prices, and summarizes practical pathways and feasible experiences for effectively reducing economic volatility and financial risks. The research findings will provide valuable references for domestic enterprises and policymakers in managing systemic financial risks and promoting high-level development of the Chinese economy.

A positioning method for AUV based on guiding light source

Kai Wang, Wenyuan Ren, Yaoquan Duan, Hongwei Du — Fri, 06 Dec 2024 00:00:00 +0800

This paper proposes a method for determining the position of underwater vehicles using light vision guidance. In order to solve the problem of limited perception distance and unclear underwater images, the illumination device is installed on the recovery platform as a light source to enhance the feature information of the recovery platform. The collected underwater light source images are enhanced by the dark channel prior defogging algorithm, and then the YOLOv5 algorithm is used to recognize the targets. Through experiments, it is verified that the image enhancement algorithm and target recognition algorithm are effective. Using the recognition results, the positioning accuracy of the binocular camera ranging algorithm is verified, and the results indicate that the proposed method can accurately determine the distance of the AUV relative to the recovery platform.

Research Progress and Application Prospect Of Microchannel Heat Exchangers

Yongqi Liu, Xiaoling Luo, Shichao Sun, Dongmei Gao — Fri, 06 Dec 2024 00:00:00 +0800

A Micro-channel heat exchanger gradually replaces traditional heat exchanger with the advantages of high heat exchange efficiency, fast heating speed, good controllability, low noise, stable operation, good pressure bearing capacity and cost saving. The thesis summarizes the research progress and development prospects of the microchannel heat exchanger.Summarized and elaborated on the unparalleled advantages of microchannel heat exchangers compared to conventional sized equipment which is compared with the regular size equipment. Moreover application fields and prospects of the microchannel heat exchanger are analyzed from the point of energy saving and space occupancy．The thesis has some reference value for the research of micro heat exchangers.

Fundus Vascular Segmentation Based on Data Enhancement and Invariant Feature Extraction

Lei Cheng, Yumeng Li, Jingyi Han — Fri, 06 Dec 2024 00:00:00 +0800

Deep neural networks have emerged as the predominant method for medical image segmentation, owing to their robust feature learning capabilities, enabling accurate automatic segmentation of target structures within intricate medical images. Fundus images, being crucial in diagnosing ophthalmic diseases, underscore the importance of effective segmentation techniques. However, fundus vascular images pose challenges due to their high complexity and subtle individual differences, necessitating improvement in existing segmentation methodologies for enhanced disease classification accuracy. This paper introduces a fundus blood vessel segmentation model, employing data augmentation and invariant feature extraction, to systematically tackle the core challenges in medical image processing, particularly in fundus blood vessel segmentation. These challenges include limited source domain samples and inadequate model domain generalization. The model adopts a dual-dimensional strategy. Firstly, it delves into data augmentation technology to enhance the diversity and representativeness of samples within the finite source domain. This is achieved through an image enhancement module based on Fourier transform, mitigating the impact of data scarcity on model training effectiveness. Secondly, the research focuses on interdomain invariant feature extraction, aiming to extract feature representations that consistently characterize fundus blood vessel structure and pathology across different data distributions, thereby enhancing model generalization performance in unfamiliar domains. Specifically, the paper designs a fundus image enhancement module based on Fourier transform in the data augmentation dimension. In the feature extraction dimension, it proposes a normalization module based on uncertainty theory, departing from traditional normalization methods. Experimental results demonstrate the efficacy of the proposed method, showcasing superior generalization performance compared to existing techniques in retinal blood vessel and OD/OC segmentation tasks. Experience validates the model-agnostic nature of the learned strategy, indicating its potential for seamless transferability to other models, thereby offering robust support for advancing medical image segmentation research and applications.

ractical Research on Smart Home Interactive Interface Design Based on Heuristics

Qi Liu — Fri, 06 Dec 2024 00:00:00 +0800

The development of IoT, AI and sensor communication technology has led to the emergence of diverse interactive scenarios, with intelligent natural interactive interfaces becoming a common feature of smart home interactive interface design. However, the influence of traditional design methods and systems limits the ability of current designers to fully absorb new technological elements, preventing them from optimising product functions. In order to address this issue, this study has initiated an exploration of smart home interactive interface design methods. The researchers extracted 21 heuristics for smart home interactive interface design (DHS) from exemplary design cases and employed these in practice to assess their efficacy. They then summarised the model of the DHS for smart home interactive interface design.

Study on economic design and construction program of steel-hybrid combined girder bridge

Weidong Zhao, Bing Yang, Yuze Nian — Fri, 06 Dec 2024 00:00:00 +0800

In order to make full use of steel tensile and concrete compressive properties, combined beam cross-section stress-strain distribution characteristics and cross-section characteristics and loading procedures are closely related. At present, the cross-section form of I-beam combined with concrete panel is widely used, and the strength of the upper flange of the steel beam of the supported combined beam and the strength of the concrete panel of the unsupported combined beam have not been fully utilized. Through the theoretical analysis of different loading methods of combined beam strain stress distribution, so as to optimize the cross-section form, the proposed supported combined beam using the lower inverted T-shaped cross-section combined with the form of concrete panels, in the given actual engineering cases can obtain a higher elastic ultimate bearing capacity and can save 9.5% of the amount of steel. The unsupported loading method of I-beam combination beams can use lower grade concrete for better economy. Making full use of the neutral axis position change to design the combined beam cross-section is operable, inverted T-shaped steel beams combined with concrete panel combined beams is a way to save steel and reduce the construction of welded joints, with significant economic benefits.

Numerical Simulation of Fire Smoke Transport in Underground Spaces of a Pumped Storage Power Station

Cun Liu, Haoxing Zhang, Ziyao Wang, Hongxin Tian, Kang Sun, Xiong Shen — Fri, 06 Dec 2024 00:00:00 +0800

The present study employs numerical simulation to investigate the transportation of fire smoke within the underground powerhouse of a Pumped Storage Power Station. The obtained results reveal the spatial variation of fire smoke under the smoke exhaust effect inside the facility. For an 8 MW fire occurring on the generator, busbar, and turbine layer floors of the main powerhouse, recommended evacuation times are 86 seconds, 242 seconds, and 298 seconds respectively when utilizing a mechanical exhaust capacity of 85000 m³/h. In case three simultaneous fires occur at these three floor levels, the evacuation time is reduced to 45 seconds. Comparatively, when compared to situations without mechanical smoke exhaust systems, our simulations indicate that escape times for different fire scenarios were extended by only 6 seconds and 91 seconds respectively. These findings underscore the urgent need for optimizing the mechanical smoke exhaust system in order to provide valuable time for personnel evacuation during fire incidents.

Prediction of industrial VOCs based on LSTM for multi- monitoring stations

Zhe Liu, Hui Wu, Shenguo Fang — Fri, 06 Dec 2024 00:00:00 +0800

The prediction technology of VOCs (volatile organic compounds) from industrial sources is very important for monitoring and early warning. At present, few studies have focused on prediction using multi-site VOCs data, and there are few relevant studies on whether the statistics of VOCs monitoring data have an impact on the prediction effect of deep learning model. This study selected the appropriate multi-monitoring-site data to train the LSTM (Long Short-term Memory) model, and statistical data of VOCs for four monitoring stations was used to analyze the correlation between prediction performance, so as to improve the prediction effect of the LSTM model. The results showed that the statistics of VOCs observation stations can provide guidance on the predictive performance of the model to a certain extent, thereby improving the predictive performance of the model.

Research on the application of dangerous driving detection on the highway based on computer vision

Ruixi Liu, Yuxin Xiao, Zhidong Li, Wanqiu Zhang, Yinan Yang — Fri, 06 Dec 2024 00:00:00 +0800

Dangerous driving on the highway is a significant safety hazard, and existing highway cameras are not used to detect whether drivers are fatigued or distracted. To inform the police of dangerous driving vehicles promptly,In this paper, we propose a complex driving detection system on the basis of YOLO network.The YOLOv8s algorithm is used for real-time analysis, effectively improving detection accuracy and caters to the need for lightweight design. The system combines the characteristics of highway camera settings with distributed cluster deployment, solving the defects of detection blindness and target loss and achieving the function of distributed clustering to detect drivers of passing vehicles. The system can provide adequate support for traffic police to intercept dangerous drivers on highways and give theoretical guidance for the future intelligent transformation of road traffic through experimental verification.The technology could also be rolled out to cover urban roads and additional transportation networks to further ensure traffic safety.

Blockchain-based Enterprise Community Data Access Control Methods and Applications

Yang Yang, Li Wang, Tingyezhi Hu, Yuan Wang — Fri, 06 Dec 2024 00:00:00 +0800

Data, as a fundamental resource in the digital economy of enterprise communities, can significantly enhance digital development and enterprise growth if shared securely and orderly. Despite providing detailed control, traditional attribute-based data access control methods face challenges related to privacy protection and data ownership, potentially causing data loss and trust issues. To tackle these challenges, this paper presents a blockchain-based data sharing management system, which merges the decentralized and traceable aspects of blockchain technology with attribute-based access control.

Research on Automatic Detection of Thesis Format Based on Rule Engine

Yangyang Xia, Wei Zhang — Fri, 06 Dec 2024 00:00:00 +0800

With the increasing development of academic research, thesis writing and publication have become important ways to measure scientific research achievements. However, non-standard thesis formats not only affect the reading experience, but may also lead to a decrease in the evaluation of academic achievements. Therefore, this article proposes a rule engine based automatic paper format detection system, aiming to improve the efficiency and accuracy of thesis format review and reduce manual review costs. This system is built on the basis of the Office Open XML document specification, which formulates a series of format checking rules for the basic format requirements of thesis. Then, the rule engine conducts in-depth checks on the thesis based on the preset format specification, automatically identifies format problems that do not comply with the specification, and outputs a detection report. It provides modification suggestions to assist users in quickly correcting format errors.

Dynamic thermal performance of prefabricated temporary exterior wall using cooling water in the cooling season

Fri, 06 Dec 2024 00:00:00 +0800

The acceleration of urbanization has led to a continuous increase in various types of buildings. In the hot season, cooling systems cool buildings and improve their comfort. However, traditional cooling methods require more energy consumption and greenhouse gas emissions. This paper designs a prefabricated building exterior wall with embedded pipes based on water cooling system reduces the output of traditional cooling way in building cooling. The innovation of this research is using the embedded pipe to improve the thermal properties of exterior walls, bonging the embedded pipe and exterior wall structure together. The results show that the embedded prefabricated building exterior walls are designed to control the indoor wall temperature to around 28 ℃ in summer. And the temperature on the surface of the inner liner cavity is always above 25.5 ℃. The overall trend shows a decrease followed by an increase. At noon, the surface temperature on the cavity side of the inner lining plate is the lowest, about 25.8 ℃. The larger the indoor and outdoor temperature difference, the better the cooling effect of the structure on the building. This study's application can help reduce energy consumption and carbon emissions effectively.

Accurate retinal vessel segmentation in OCT-A images based on MsTCG-Net

Sumin Qi, Baoyu Cui, Mengqi Zhang, Jing Meng, Bangqiang Qi — Fri, 06 Dec 2024 00:00:00 +0800

Optical coherence tomography angiography (OCT-A) is a non-invasive visualization imaging technology with high-resolution that can more clearly image tiny blood vessels. Using OCT-A imaging technology, certain ophthalmic diseases can be better diagnosed by the morphological changes of retinal blood vessels. However, the task of segmenting retinal vessels is still very challenging due to the large variation in vessel size and shape and the presence of noise. In this paper, by introducing a transformer with a self-attention mechanism, we propose a novel multi-scale transformer-based channel and global attention network (MsTCG-Net) for segmentation of blood vessels in retinal OCT-A images. In MsTCG-Net, transformer-based channel joint attention (TC) block and transformer-based global joint attention (TG) block are proposed to capture multi-semantic features from spatial and channel dimension and fuse global contextual semantic features from different layers of encoder. Experimental results show that our proposed method achieves better segmentation performance than other state-of-the-art U-Net-based methods.

Prediction Method for Pomegranate Chlorophyll Content Based on Multi-feature Fusion of Unmanned Aerial Vehicle

Tengbo Zhao — Fri, 06 Dec 2024 00:00:00 +0800

The aim of this study was to obtain RGB and multispectral images of fruit tree canopy during the flowering period of pomegranate by multispectral unmanned aerial vehicle (UAV) to quickly and accurately predict the chlorophyll content in order to improve the monitoring efficiency of the orchard. A handheld chlorophyll meter was used to obtain the actual chlorophyll values, and image processing techniques were combined to extract parameters such as color features and texture features of the RGB images as well as vegetation index of the multispectral images. A chlorophyll content prediction method based on the support vector regression model and the convolutional neural network model (CNN-Attention) combined with the attention mechanism was established. The results showed that (1) the accuracy of the prediction model was improved by the fusion of RGB image features and multispectral image vegetation index. (2) After model comparison, the CNN-Attention model built under the fused features was the best in chlorophyll content prediction with R2, RE, and RMSE of 0.9699, 0.0052, and 0.6013, respectively.This study provides a more accurate method for fruit tree chlorophyll content prediction using UAVs, which provides a practical reference for orchard management.

SSTar-TransGAN: Transformer-based Unsupervised Multi-modality Hyperspectral Digital Staining Network

Yukun Wang, Yanfeng Gu — Fri, 06 Dec 2024 00:00:00 +0800

Immunohistochemistry (IHC) plays an important role in accurate cancer screening and diagnosis, the clinical application of which has been restricted by complex operation process, high costs and demand of professional skills from pathologists. Digital staining methods based on deep learning provide the possibility for Hematoxylin & Eosin (H&E) stained images to be converted into IHC stained images, but it needs to train multiple staining networks for various modalities of IHC images from different cancers, thus weakening the versatility and convenience of digital staining in the process of practical application. At the same time, microscopic hyperspectral imaging technology can provide abundant spectral information for pathological images, which has been proved effective in digital staining tasks to transform staining modalities from one to many, but microscopic hyperspectral imaging has also been troubled by time-consuming acquisition process and huge data storage. In order to overcome the above challenges, we propose SSTar-TransGAN network for digital staining tasks. With the inhabitation of StarGAN structure, SSTar-TransGAN transfers the training burden of generators into lightweight style encoders between different modalities, while in addition to the introduction of transformer structure into the encoder, the application of spectral super-resolution Swin-Spectral Transformer U-Net (SSTU) network enables the convertion from H&E stained RGB images into hyperspectral images as well, which ensure the spatial structure and color information of IHC images under multiple staining modalities and the further conversion between different staining modalities. Qualitative and quantitative experiments prove the performance of SSTar-TransGAN on digital staining tasks superior to other state-of-the-art digital staining methods.

Research on Minimum Unstick Speed Flight Test Method for Civil Aircraft

Lei Wang — Fri, 06 Dec 2024 00:00:00 +0800

The minimum unstick speed (V_MU) is defined as the calibrated airspeed at which an aircraft can safely lift off and continue its takeoff without any difficulties. The V_MU flight test, characterized by low-speed and high angle of attack under the influence of ground effect, poses significant challenges and high risks, making it one of the most hazardous flight test subjects in civil aircraft flight test. The research on V_MU flight test methods for civil aircraft is of utmost importance in strengthening the foundation of flight test technology, improving flight test efficiency, and ensuring flight test safety.

Research on Airworthiness Requirements for Function and Reliability Flight Test of Civil Aircraft

MingJia Dong, XiaoHu Xi, Fang Zhao — Fri, 06 Dec 2024 00:00:00 +0800

Function and reliability flight testing is an important trial for civil aircraft airworthiness certification, and is a part of the qualified acceptance flight tests that confirm that the aircraft, components, and equipment are reliable and functioning properly. This article studies the airworthiness requirements for function and reliability flight testing in CCAR21 and Appendix B of AC25-7D, and combines practical experience with civil aircraft models to analyze the requirements for flight testing time, configurations, procedures, and problem requirements, and provide recommendations for civil aircraft function and reliability flight testing.

Research on Airworthiness Certification and Risk Control of Minimum Unstick Speed for Civil Aircraft

Mingjia Dong, Chao Zhang, Ting Pan — Fri, 06 Dec 2024 00:00:00 +0800

V_MU is the minimum speed at and above which the aircraft can safely lift off the ground and continue the takeoff, expressed in terms of calibrated airspeed, and is the basis for formulating other takeoff speeds of the aircraft. As a typical high risk flight test subject, the V_MU test is a key concern of the Administrator during airworthiness certification. Based on the takeoff speeds section of CCAR25.107, combined with relevant Advisory Circular, this paper analyzes the requirements of the airworthiness clause of the V_MU, analyzes the characteristics of the V_MU, gives the airworthiness certification concerns, systematically analyzes the risk and the risk reduction measure of the V_MU for civil aircraft. It can provide reference for verifying the airworthiness compliance of the V_MU section of civil aircraft.

Analysis of Human-induced Vibration and Stability Cable of Pedestrian Suspension Bridge on the Influence of Bridge Comfort

Xingshun Liu, Kun Ma, Qiang Zhao, Xiaobiao Jiang, Yuqiong Wu, Yi Sun — Fri, 06 Dec 2024 00:00:00 +0800

In the context of the booming and rapid expansion of the tourism industry, an increasing number of aerial glass landscape bridges with complete transparency have been built in various scenic areas, commonly adopting the structural form of suspension bridges. Of notable concern are incidents of human-induced bridge vibrations that have occurred both domestically and internationally, causing considerable distress among tourists. Therefore, it is of paramount importance to conduct further study into the comfort of pedestrian suspension bridges. Given the above circumstances, a finite element model of the pedestrian suspension bridge is constructed, with a primary objective of simulating and analyzing the responses of tourists engaged in stationary dance, walking and running at different positions and under diverse loading conditions, while additionally exploring the effects of installing various stable cables on bridge vibration and comfort. Subsequently, the relevant conclusions are further verified through physical model experiments.

Stress calculation and strength verification of desulfurization and denitrification tower based on carbon-based catalytic multi-pollutant control technology

Fri, 06 Dec 2024 00:00:00 +0800

The desulfurization and denitrification tower is the core equipment of the carbon-based catalytic multi-pollutant collaborative control technology. Its design strength ensures the pollutant removal effect and stable operation of the system. This paper used ANSYS finite element analysis software to establish a three-dimensional model of the tower and divided it into high-precision grids. Combined with actual load analysis, calculation and working condition combination, the deformation and stress distribution nephogram of the tower and the membrane stress and bending stress of each component were calculated. The strength check and stress assessment were carried out. When the calculation error is ignored, the overall design strength of the tower meets the requirements, but the stress of the local reinforced beams exceeds the limit. It is recommended to replace the steel with a higher allowable stress value.

Carbon emission prediction of hub airport under dual carbon background-Take a hub airport in southwest China as an example

Yaoguo Fu, Shuzhi Xiong, Dengyu Qiu, Lin Sun, Yu Lei — Fri, 06 Dec 2024 00:00:00 +0800

In order to predict the carbon emissions of civil airports and the possibility of carbon peaking, the influence of key factors of carbon reduction on carbon emissions was studied. This paper takes a large hub airport in southwest China as the research object, sets the terminal energy demand module on the LEAP model of the airport to calculate the energy demand of the airport, and sets the carbon emission of the airport into three different scenarios: baseline scenario, low carbon scenario and zero carbon scenario, so as to predict the carbon emission trend of the airport and the possibility of carbon peaking in the next year. The analysis data in this paper can provide reference for civil airports to make "dual carbon" implementation plan.

A Comparative Analysis of Hotspots in Semiotics Theory Research in China and Abroad: A Knowledge Mapping Analysis Based on CiteSpace

Shujun Luo, Xingfen Chen — Fri, 06 Dec 2024 00:00:00 +0800

Based on literature data with "semiotics theory" as the research topic from the CNKI and WOS databases, this study employs CiteSpace software to conduct a comparative analysis of the relevant research on semiotics theory in China and abroad from 2000 to 2022. The results show that: Domestic and international research on semiotics theory exhibit a multi-centered development trend, gradually forming distinctive and complementary schools of semiotics theory. China's and abroad research focuses differently, with foreign research focusing more on applying semiotics theory in social sciences, educational research, language fields, and biological sciences. In contrast, domestic research tends to focus on introducing and studying foreign semiotics theories, with linguistics being an important research area. Both domestic and international research on semiotics theory have expanded the scope of theoretical research, forming widely applicable categories of semiotics. Hotspots in foreign research include "student";"model"; "future"; "evolution"; "information"; "framework"; "discourse"; and "construction", while hotspots in domestic research include "semiotics", "Peirce", "pragmatism", "Lotman", and "symbols". The development process of domestic and international research on semiotics theory has some differences, with each stage exhibiting different research characteristics. However, both have developed from theoretical to applied research, phenomenon to essence law research, and single-mode to multi-mode research. Domestic researchers should strengthen communication and cooperation with international counterparts, build a research community for semiotics theory, deepen research connotations, and provide more case studies as paradigms; timely summarize the current status and development patterns of domestic research on semiotics theory, and gradually form a Chinese school of semiotics with international influence.

Power forecast of hydro–wind–photovoltaic hybrid system dual-driven by physics and data

Weifeng Xu, Xi Chen, Han Wang, Ze Zhang, Haonan Bai — Fri, 06 Dec 2024 00:00:00 +0800

Short-term power forecast is an important way to guide operation of renewable energy stations and hybrid energy system (HES). The current studies focus on power forecast of single renewable energy station. However, the universality and applicability of power forecast model for HES is not clear. This study proposes a physics and data dual-driven day-ahead power forecast model for hydro–wind–photovoltaic HES. The WRF model and Xinanjiang model are used to drive meteorological and hydrological forecasts respectively. The hybrid variational mode decomposition - principal component analysis method is applied to further extract the features hidden in the meteorology or hydrology factors. The long short-term memory network is used to drive power forecast. China’s Guandi hydro–wind–PV HES is considered as a case study. Results show that the forecast root mean square error of dual-driven model decreases by 4.2% ~ 12.0% compared to single-driven model.

Calculation Method for Equivalent Ejection Mass of Variable Thrust in the Internal Ballistic Equation of Pyrotechnic Folding Rudder

Fri, 06 Dec 2024 00:00:00 +0800

In order to solve the calculation of actuator ejection mass in pyrotechnic folding rudder, this paper investigates the calculation method for equivalent ejection mass of variable thrust in the Internal ballistic equations of pyrotechnic folding rudder, and obtains the fitting curves of equivalent ejection mass and gunpowder thrust in the case of variable forces and calculates the gunpowder thrust curves during the unfolding process by establishing the dynamic simulation model of the pyrotechnic folding rudder. After test verification, the test results are consistent withe the simulation results, indicating that the method is accurate and effective, and provides a theoretical basis for the design of the pyrotechnic folding rudder.

TRFSA-HQS: Transformer-based MRI Compressed Sensing Network with Frequency Domain Self-Attention

Taiping Mo, Mingfeng Zheng, Peng Sun, Jiangtao Li — Fri, 06 Dec 2024 00:00:00 +0800

Compressive sensing (CS) can reconstruct undersampled magnetic resonance images, but its iterative optimization process tends to be computationally intensive and time-consuming. Convolutional neural networks (CNNs) have demonstrated impressive reconstruction performance through non-linear feature extraction and mapping capabilities. However, CNNs often struggle to effectively learn and capture global dependencies in the data. Therefore, constructing a MRI reconstruction method that meets clinical real-time imaging and captures dynamic global correlation is crucial in fast and high-precision MRI tasks. We propose a deep unfolding network (TRFSA-HQS) for fast and accurate CS reconstruction, which combines frequency domain self-attention (FSA) based Transformer and half-quadratic splitting (HQS) iterative optimization scheme. TRFSA-HQS adopts an iterative scheme based on HQS to effectively decouple and update optimization problems. The decoupled data subproblems are updated by minimizing the objective function with competitive terms, while the regularization subproblems are updated using the TRFSA deep prior network. The TRFSA module employs an asymmetric UNet architecture, where the encoder and decoder utilize a frequency-domain discriminative feedforward network (DFFN) and FSA. The DFFN selectively extracts deep features from different frequency components, while the FSA captures global dependencies in the frequency domain. The experiment demonstrate that the proposed model achieves an average reconstruction PSNR of 35.11dB on a 0.2 sampling rate test set on FastMRI knee joint data, with an inference time of 0.74s. It has good reconstruction performance and noise robustness, meeting the clinical real-time imaging requirements.

Forecasting Public Bicycle Utilization in New York City Utilizing the CitiBike Dataset

Xudong Wang, Zile Xu, Yufen Zhang — Fri, 06 Dec 2024 00:00:00 +0800

The integration of public bicycles into urban transportation systems has gained popularity due to their potential to reduce traffic congestion and air pollution, while also addressing the “last kilometer” problem. This study examines the usage patterns and predictive analysis of public bicycles in New York City using the CitiBike dataset from 2013 to 2015. We employ the Spring algorithm for networkx visualization and analyze the loan and return data to understand spatial-temporal usage dynamics. Additionally, clustering techniques, including K-means and DBSCAN, are applied to the dataset to uncover usage trends and patterns. The findings provide valuable insights for the planning and optimization of public bicycle systems, such as CitiBike, and contribute to the promotion of sustainable and environmentally friendly urban transportation.

Architecture Design of Distributed Encrypted Storage and Computing Based on Fog Computing

Qiang Gu — Fri, 06 Dec 2024 00:00:00 +0800

With the progress of informatization, the problems of data transmission delay, untimely response and theft and tampering of user privacy data are becoming increasingly prominent. This paper proposes a distributed encryption storage and computing architecture based on fog computing, which uses the scalability and low latency of fog computing to solve the problems of data silos and response delays. Blockchain technology is introduced to build decentralized storage to prevent data tampering and ensure secure transmission and sharing. Hierarchical privacy protection measures are designed to store data in a hierarchical and classified manner to accurately control the scope of information acquisition. This method has good application characteristics and can effectively solve the problems of government data collection and calculation.

Research on Climbing Performance Calculation and Flight Test of Transport Aircraft

Yajuan Zhu — Tue, 16 Jul 2024 00:00:00 +0800

Climbing performance is one of the most critical indicators for evaluating aircraft flight performance and affecting flight safety. In the paper, the airworthiness regulations related to climbing performance in CCAR25 are researched and summarized in detail. An exhaustive method for calculating climb gradient during constant airspeed climb is developed. Meanwhile, the forward and reverse heading sawtooth climb method is designed to execute the climbing performance flight test. Finally, by comparing the calculation results of the climb gradient with the flight test results, it is proved that the aircraft meets the airworthiness requirements and the climb performance calculation model is reliable.

Dynamic simulation analysis of aircraft engine planetary gear system

Minyang Pang, Yuefang Wang, Jinyu Zhai — Fri, 06 Dec 2024 00:00:00 +0800

The Geared Turbofan (GTF) engine is used for aircraft propulsion with fan drive, characterized by its complex structure and operation in challenging environmental conditions. During its operation, variations in gear meshing and loads on the transmission shaft exacerbate vibration within the transmission system, leading to a decline in engine performance. This paper established three-dimensional solid models of the X-type aviation engine planetary gear system, input shaft, and output shaft, and employed ADAMS for multibody dynamics analysis, achieving simulation of engine operational vibrations. Modal and harmonic response analyses were conducted using ANSYS to observe and analyze critical parameters such as vibration displacement, vibration acceleration, gear meshing forces, modal resonance, and harmonic resonance, evaluating the impact of vibration amplitude, frequency, and their effects on system performance and longevity, providing guidance for vibration control and optimization of aviation engine systems.

The study focuses on the development of an intelligent system for measuring carbon emissions and managing carbon assets in thermal power plants

MengLin Zhou, ShiWei Lang, YuTong Li — Fri, 06 Dec 2024 00:00:00 +0800

A reliable carbon measurement system serves as the foundation for effective carbon asset management. This paper presents a sophisticated smart carbon emission measurement and carbon asset management system specifically designed for power plants. Leveraging the operational conditions of a power plant's DCS, it enables real-time carbon emission accounting based on live data. The system seamlessly integrates online monitoring to facilitate accurate carbon emission measurement, automating the calculation, collection and reporting of emissions data while also conducting pre-review checks for compliance with reporting standards. Additionally, it simulates enterprise allocation and conducts predictive analysis to visualize both carbon emission data and quotas. By tracking, analyzing, and predicting trends in carbon trading, the system offers strategies to optimize carbon asset trading. It effectively manages all aspects of carbon assets throughout their lifecycle. The implemented system has demonstrated stability at a specific power plant by successfully measuring emissions, managing monitoring activities, diagnosing emissions data issues, performing indicator analysis and warnings generation, generating comprehensive reports on emissions verification management as well as facilitating compliance with regulations related to carbon trading. This solution helps enterprises ensure the preservation and growth of their valuable carbon assets while promoting revenue growth from efficient carbon trading practices which ultimately showcasing the value of digitalized carbon emission measurement and intelligent carbon asset management for power enterprises.

On the solution of seven-precision-point path synthesis of planar four-bar linkages based on the solution region methodology

Fri, 06 Dec 2024 00:00:00 +0800

This paper makes further research on the application of the solution region synthesis methodology (SRSM) in path synthesis of planar four-bar linkages. Detailed process of establishing the solution region for seven precision-point path synthesis is illustrated. In order to obtain the solution region where one point corresponds to one linkage and the feasible solution region where linkages distributes different zones according to curve types, this paper compares four different solution region schemes and finally establishes the solution region with B₁ as the reference. Compared with the eight-point case, the range of the solution region in this paper is larger and the statistics on the feasible solutions is more than twice of that in the case with eight points. Moreover, the feasible solutions obtained in this case have more curve types.

Comparative study on brightness temperature reconstruction of synthetic aperture based on deep learning

Ziyu Sun, Hao Li — Fri, 06 Dec 2024 00:00:00 +0800

In order to study the effect of deep learning method in the brightness temperature reconstruction of synthetic aperture radiometer, the gray value of remote sensing image with channel amplitude-phase error and random error is used as the original brightness temperature image for simulation experiment to compare the brightness temperature reconstruction images under traditional Fourier transform, CNN inversion, U-net inversion and Resnet inversion. From the view of image visual effect, Resnet inversion method has the best image restoration effect and the weakest background noise. From the evaluation index, the RMSE of Resnet inversion method is the smallest, which is 6.28K, and the PNSR value is the highest, which is 31.62dB. The second is CNN inversion method, RMSE value is 10.93K, PNSR value is 27.09dB. Therefore, Resnet inversion method can better restore bright temperature image, reduce Gibbs effect and improve image resolution.

Research on Emotion Recognition Algorithm of Piano Music Based on Multimodal Learning

Qiaolin Yu, Ying Lin — Fri, 06 Dec 2024 00:00:00 +0800

The purpose of this study is to propose an emotion recognition algorithm for piano music based on multimodal learning. Multi-modal learning is a learning method that combines various types of data. By combining different modal information, learning tasks can be completed more comprehensively and accurately. In the field of music emotion recognition, multimodal learning can extract the emotional features of music from different angles, and improve the recognition accuracy and robustness. In this study, the multi-modal learning method is mainly used, and the representative features are extracted by combining the audio signal, score information and the performance of the piano music, and the machine learning algorithm is used to classify the emotions. The audio signal is preprocessed, including noise reduction, cutting and other operations, and then the features of the audio signal are obtained by feature extraction methods, such as short-time Fourier transform (STFT) and formant analysis (RPA). Digitally convert the score, extract the structure, melody, harmony and other characteristics of the music, and obtain the emotional information of the music by analyzing the relationship between symbols and notes in the score. By analyzing the performance skills, strength, speed and other parameters of the player, the characteristics related to the emotional expression of the player are extracted. Machine learning algorithm is used to train and classify the fusion features, and the emotion recognition of piano music is realized. In this study, the emotion recognition algorithm of piano music based on multimodal learning can mine the emotion information of music at different levels, improve the accuracy and robustness of emotion recognition, and provide useful reference for the field of music emotion calculation.

A Study on the Accurate Equation Inversion Method for Uncoupled Interface Parameters of OA Media Considering Initial Stress

Zihang Fan, Zhaoyun Zong — Fri, 06 Dec 2024 00:00:00 +0800

Underground media are generally affected by the initial stress of the overlying strata. At the same time, the uncoupled interface is an important influencing factor of seismic response, as well as an essential reservoir environment, reservoir space, and migration channel. It is significant to explore the parameters of the uncoupled interface under stress for identifying oil and gas reservoirs. As an effective means of predicting reservoir physical parameters, pre-stack seismic inversion uses information on uncoupled interface fractures under stress to improve the accuracy of reservoir parameter prediction, overcome the problem of insufficient interface parameter prediction methods, and promote oil and gas reservoir exploration and development. Based on the precise equations for directly characterizing uncoupled interface fracture weakness parameters, this paper uses the ANNI inversion method to realize the nonlinear inversion method of uncoupled interface fracture parameters. The feasibility and practicability of predicting underground medium parameters from seismic response characteristics have been verified through model testing and actual work area application.

Research on the approximate equation inversion method for the physical properties parameters of OA media with decoupling of stress and fracture effects

Zihang Fan, Zhaoyun Zong — Fri, 06 Dec 2024 00:00:00 +0800

Pre-stack seismic inversion is an effective method for predicting reservoir physical parameters. At the same time, azimuth seismic data is a reliable source of information for predicting underground reservoir elastic parameters, fracture parameters, and interface parameters and has rich underground information. However, it is difficult to determine whether the anisotropy of the reservoir is caused by stress or the original fractures. Therefore, distinguishing the influence of fractures and initial stress in the reservoir from azimuth seismic data is the key to predicting reservoir parameters. Because of the problem of insufficient consideration of the influence of stress and fracture weakness in OA media, based on Born's first-order scattering theory and Bayesian inversion framework, an approximate equation for the reflection coefficient decoupling fracture anisotropy and stress-induced anisotropy was constructed, and a linear inversion method based on the approximate equation was developed, realizing the exploration of methods for predicting fracture weakness and stress action parameters. Model testing and actual work area application have verified the feasibility and practicability of predicting underground medium parameters from seismic response characteristics.

Forecasting Public Bicycle Utilization in New York City Utilizing the CitiBike Dataset

Xudong Wang, Zile Xu, Yufen Zhang — Fri, 06 Dec 2024 00:00:00 +0800

Neural network-based logistics and distribution cost prediction of maintenance equipment

Shufei Hou, Bing Wang — Fri, 06 Dec 2024 00:00:00 +0800

Accurate prediction of maintenance equipment logistics and distribution costs can help enhance the competitiveness of enterprises. In order to obtain higher accuracy prediction results, a neural network logistics and distribution cost prediction method of maintenance equipment was proposed, based on historical data, the learning sample of maintenance equipment logistics distribution cost prediction was established through transformation technology, and the BP neural network was introduced to train the learning sample. The change characteristics of maintenance equipment logistics and distribution cost were fitted, so as to realize the cost prediction. The results show that the prediction accuracy of the BP neural network is not only more than 5% higher than that of the gray model on average, but also the prediction stability is better.

Simulation Study of Dual Source Heat Exchange Evaporator

Dan Wang, Qi Zhao, Shijie Gu, Shuang Ma, Hongwen Jin, Huinan Chang — Fri, 06 Dec 2024 00:00:00 +0800

This article proposes a dual source heat exchange (DSHE) evaporator, which adopts a sleeve type heat exchanger design with external fins.A dual source heat exchange evaporator was simulated using Fluent software under different inlet velocity and temperature parameters,Analyzed the simulation results under typical working conditions,The temperature difference between the inlet and outlet of antifreeze is 1.93℃~4.28℃,The temperature difference between the inlet and outlet of the refrigerant is 6.39℃~12.53℃,The temperature difference between the inlet and outlet of air is 0.66℃~1.7℃.

TDF-YOLOv8 : An Enhanced UAV Object Detection Method Based on Triplet Attention and Dynamic Scaling

Bo Tan, Yuyong Cui — Fri, 06 Dec 2024 00:00:00 +0800

In this paper, challenges in object detection based on UAV imagery are addressed. The focus is on high-resolution imagery, varied perspectives, and dense arrangements of small objects. The YOLOv8s model is enhanced by integrating Triplet Attention into its C2f module to improve recognition precision of densely distributed targets. A novel Detect_Dyhead structure is introduced to dynamically adjust detection strategies across different scales and shapes. Additionally, the FocalerShapeIoU loss function is employed to refine bounding box accuracy. Experimental results on the VisDrone2019 dataset show that Precision, Recall, mAP@0.5, and mAP@0.5:0.95 metrics are enhanced by 2.1%, 1.4%, 1.4%, and 1.2%, respectively, while the model size is reduced by 0.5MB. Strong performance is also demonstrated on the WiderPerson and custom Tanks datasets, underscoring the generalizability of the proposed TDF-YOLOv8 model.

Discriminating Homecoming Visitors Using Mobile Signaling Data

Yonggang Tang, Huijie Lin, Huijie Lin, Mingjian Mo — Fri, 06 Dec 2024 00:00:00 +0800

This study utilizes mobile signal data as an emerging data source, aiming to construct a framework that can efficiently distinguish homecoming visitors from other types of tourists. The rich behavioral features contained in mobile signal data are deeply analyzed. A two-stage clustering method based on machine learning, which integrates multiple aspects such as feature engineering, model construction, and performance evaluation is designed to ensure the accuracy and generalization ability of classification results. The main data source is the signaling data of the three major telecommunications operators in China. Using the signaling data from China's three major telecommunications carriers as the primary data source, this study verified the number of tourists in the Guangxi, as well as in Nanning, Guilin, and Yulin cities during the 2019 National Day Golden Week. The results indicate that the method presented in this paper offers a viable new approach for the statistical analysis and data mining of large-scale tourism figures.

Case report and literature review of DYNC1H1 gene in Chinese literature

Qingsong Peng, Hui Yuan — Fri, 06 Dec 2024 00:00:00 +0800

This paper presents an analysis of 15 cases (families) of Dync1h1-related genetic disorders reported in Chinese literature. The study focuses on the clinical manifestations, genetic mutations, and potential mechanisms underlying these diseases. Through a comprehensive review of the cited literature, they aim to provide insights into the spectrum of Dync1h1 gene disorders and their impact on patient health. The analysis highlights the importance of accurate genetic diagnosis in guiding clinical management and genetic counseling for affected individuals and their families.

Freight Volume Prediction for Logistics Sorting Centers Using an Integrated GCN-BiLSTM- Transformer Model

Weiyan Tan, Shujia Wu, Ke Ma — Fri, 06 Dec 2024 00:00:00 +0800

In this paper, a comprehensive learning model is proposed for predicting cargo volume at sorting centers, which integrates GCN (Graph Convolutional Network), BiLSTM (Bidirectional Long Short-Term Memory Network), ARIMA (Autoregressive Integrated Moving Average model), and Transformer models. To achieve this, a directed weighted graph is constructed considering the transport network and average cargo volume of each sorting center. The GCN model is employed to extract spatial features from the transport connection information of the sorting centers and these features are then fed into the BiLSTM network. The BiLSTM network leverages bidirectional information flow to learn the temporal characteristics of the data. Subsequently, the GCN-BiLSTM model, which combines spatial and temporal features, is used to predict the daily cargo volume for the next 30 days. The results demonstrate that the GCN-BiLSTM model and the ARIMA-BiLSTM integrated model significantly enhance prediction performance compared to single-model approaches.

Exploration and Practice on the “Symbiotic Integration of the Three Vitalities” Talent Cultivation Model

Yonghong Shui, Rong Li, Fangqian Huang, Jianmin Zhou — Fri, 06 Dec 2024 00:00:00 +0800

It is a vital necessity to explore high-quality talent cultivation models in vocational colleges in order to cultivate qualified and skilled talents. Based on the integration of "teachers and students & production & ecology," a "Symbiotic Integration of the Three Vitalities" (SITV) talent cultivation model is proposed in this paper. Years of practices have shown that this model is able to achieve significant effects and promote the development of vocational education.

Assessment of land use efficiency under carbon emission constraint: An empirical study of Pearl River Delta, China

Jinrong Zeng, Qiangqiang Rong, Wuyang Hong, Fan Wen — Fri, 06 Dec 2024 00:00:00 +0800

Land use efficiency (LUE) is the comprehensive reflection of the input and output in the process of land resource utilization. However, carbon emission during this process will lead to a decrease in LUE. It is necessary to evaluate LUE under carbon emission constraint for urban sustainable development. Although the carbon emission and efficiency of land use have been extensively studied, few researches considered the uncertainties in carbon emissions when evaluating LUE. In this study, a comprehensive assessment model of LUE was proposed. Interval parameter is introduced to a super efficiency slack-based measurement (SBM) model, leading to an assessment method of interval LUE, which can analyze the impact of carbon emission on LUE. A case study in Pearl River Delta (PRD) was conducted from 2005 ~2020. Results revealed that the overall carbon emissions of land use in the PRD increased significantly during the study period. Particularly, Zhuhai and Huizhou had a relatively larger increase. In terms of the total amount of carbon emission, it was relatively higher in Guangzhou and Shenzhen than the other cities in the region. Taking the carbon emission into account, the LUE of PRD still improved, especially in Shenzhen, Guangzhou, Foshan, and Jiangmen. However, an opposite trend was found for the LUE of Huizhou and Zhaoqing, changing from effective to ineffective. The LUE of Zhuhai and Zhongshan was always effective, while that of Dongguan was ineffective during the study period. In conclusion, the assessment method of LUE considering carbon emissions should be used to promote the efficient use of land resource. The results of the case study in this research can also provide decision-making reference for PRD and other urban agglomerations to improve LUE.

Exploration and Practice of a Graded, Flat, and Flexible Teaching Model for Cultivating Cyber Defense and Offense Capabilities

Hui Shu, Yuntian Zhao, Fei Kang, Wenjuan Bu — Fri, 06 Dec 2024 00:00:00 +0800

In alignment with the educational requirements for the multifaceted nature of knowledge, the comprehensiveness of skills, the adversarial nature of practice, and the specificity of thinking in cyber defense and offense capabilities, this paper adopts a student-centric pedagogical philosophy. Guided by educational theories such as constructivism, connectivism, and group dynamics, we have established a graded, flat, and flexible teaching model. This model is characterized by a progressively challenging teaching framework, the construction of contextually linked case scenarios through a flat knowledge network, the organization of a multidimensional and elastic teaching process, and the support of skill training through multimodal hybrid collaboration. It synergistically transforms the relationship between teaching and learning across four dimensions: framework structure, content arrangement, process organization, and training methods. This systematic shift has led to a significant increase in the knowledge capacity and diversity of the curriculum, an optimization of the flexibility and adaptability of teaching organization, an enhancement of students' understanding and learning capabilities, an improvement in students' comprehensive skills and practical combat effectiveness, and the stimulation of innovative thinking and specific cognitive traits.

Optimal allocation of low-impact development facilities for urban runoff reduction

Fan Wen, Qiangqiang Rong, Zhihui Gu, Jinrong Zeng — Fri, 06 Dec 2024 00:00:00 +0800

In the context of global climate change and urbanization development, the intensity and frequency of extreme rainfall events have increased significantly, while the proportion of impermeable surfaces in cities has been increasing. These changes have led to frequent urban flooding, which seriously affects the safety of people's lives and properties and restricts the high-quality development of urbanization. Low-impact development (LID) is an important way to effectively mitigate urban flooding. How to obtain the optimal runoff control effect through the deployment of LID facilities in the construction of sponge cities is an urgent problem to be solved. This study proposed a novel implementation framework for LID optimization based on SCS-CN model and used data from Shenzhen to verify the effects. The results shows that the optimization of LID facilities proves to be effective in flooding mitigation. The results of this study can support decision-making for urban flood mitigation and sponge city construction.

Prediction of Thin Pre-Salt Reservoir in PL Gas Field, Sichuan Basin

Yuhan Li, Song Tang, Shun Li, Yang Yang, Linhao Su, Yuchen Liang — Fri, 06 Dec 2024 00:00:00 +0800

In this paper, the reservoir characteristics and favorable exploration zones of Jialingjiang Formation in Triassic Jialingjiang Formation in PL gas field, Sichuan Basin are studied in depth. By means of geophysical processing and prediction techniques such as seismic attribute analysis, inversion and structural interpretation, this paper focuses on the sedimentary facies, structure, fractures, reservoir thickness and physical properties of the porous reservoir in Jialingjiang Formation, in order to define the spatial distribution of the reservoir and the favorable exploration zones. The research results show that the development of Baiyun rock beach facies reservoir in Jiawumember is mainly concentrated in well area JT1-PS7-PY1, where the local deposition thickness increases and it is a favorable tidal beach facies zone. Based on multi-attribute analysis and phase-controlled p-wave velocity inversion, this paper predicts the lithology and gas distribution of carbonate and gypsum rocks in the Jiawu Member, revealing that the reservoir thickness of the Jiawu 1 submember is between 5 and 22 meters, and gradually thinning in the southeast direction. Based on paleogeomorphology analysis and fracture development characteristics, six favorable exploration areas with a total area of 48 square kilometers are selected, and three proposed well locations are proposed, which provide guidance for future exploration evaluation and deployment.

Study on Development Characteristics and Reservoir Formation Model of Lower Ordovician Reservoirs in Central Sichuan

Fri, 06 Dec 2024 00:00:00 +0800

Sichuan Basin is a large superimposed petroliferous basin, which has experienced multi-stage extension-convergence cycle and has great potential of oil and gas resources. In recent years, the lower combination oil and gas exploration in the middle Sichuan area has made great breakthroughs in the Sinian Dengying Formation and the Lower Cambrian Longwangmiao Formation, but has not achieved good results in the Ordovician. At present, a number of Wells in the middle Sichuan area show varying degrees of oil and gas in the Lower Ordovician strata, suggesting that the Ordovician strata in this area have the basic conditions for the formation of large-scale oil and gas reservoirs. However, no consensus has been reached on the paleogeographic pattern of Ordovician lithofacies and the distribution of favorable facies zones in this area, and the understanding of reservoir types and reservoir properties is quite different. Therefore, the weak basic research on the geological conditions of reservoir formation has severely restricted the hydrocarbon exploration of the Ordovician in this area. In this paper, the Lower Ordovician lithofacies paleogeography reconstruction and reservoir characteristics analysis are carried out by systematically combing the drilling and field profile data in the central Sichuan area, combined with core observation, thin section identification and reservoir analysis, and finally the Ordovician oil and gas accumulation model is established. The results show that the lithofacies paleogeography distribution of the Lower Ordovician Tongzi-Honghuayuanstage in the central Sichuan area is from the paleo-uplift to the east in the order of platform tidal flat to platform shoal to limited platform. The Lower Ordovician reservoir types in the middle Sichuan area include karst reservoir and dolomite reservoir, among which the karst reservoir is heavily filled and the reservoir performance is limited. The Ordovician reservoir-forming model in the middle Sichuan area reveals a new exploration model of dolomite superimposed bedding under karst in the epicontinental platform, which provides important geological basis for the new breakthrough of Ordovician oil and gas exploration.

Sonar Image Augmentation for Underwater Bridge Piers Via Cyclic GANS

Jianbin Luo — Fri, 06 Dec 2024 00:00:00 +0800

Underwater bridge pier structures are frequently exposed to stressors like water flow scour, ship collisions, and wave forces, leading to defects such as cracks, exposed rebar, and holes. Timely detection of these defects is critical to preventing catastrophic failures. Recent advancements in sonar imaging have improved underwater inspections, but the resulting images often suffer from noise and lower quality compared to optical images, complicating defect detection. Additionally, the scarcity of publicly available sonar datasets presents challenges in training accurate detection models.This paper addresses these challenges by proposing a novel data augmentation method using CycleGAN, which converts optical images of underwater piers into sonar images. This approach leverages the power of Generative Adversarial Networks (GANs) for effective sample augmentation, overcoming the limitations of traditional data augmentation techniques. This method significantly improves the robustness and accuracy of deep learning models for detecting defects in underwater bridge piers, providing a novel solution for augmenting limited sonar image datasets and advancing automated defect detection.

Design of Fish Restocking Station for a Water Diversion Project in Guangdong

Deye Chen, Kunlun Shen, Shengzhe Wu — Fri, 06 Dec 2024 00:00:00 +0800

According to ‘Environmental Impact Report of the Water Diversion Project in Guangdong’ and its reply of the Ministry of Ecology and Environment, a fish restocking station is required to be constructed. The fish restocking station locates in the vicinity of Xijiang River in Yunfu City, Guangdong Province. The primary species for breeding include Gan, Siniperca chuatsi, Channa maculata, Snakehead mullet and Spinibarbus with an annual scale of 450,000 tails. The station is equipped with parent fish pools, hatchery workshop, fry workshop, outdoor fish breeding pool, ancillary circulating water treatment rooms and wastewater treatment facilities. Recirculating aquaculture pattern is adopted. This paper gives a thorough introduction on technical design of fish restocking station, thus providing reference for similar projects.

Methods of treating partial dryness of stroke with massage combined with acupuncture technology

Bingchen Li, Haowei Ti, Chang Liu — Fri, 06 Dec 2024 00:00:00 +0800

Metabacteria is a neurological disease primarily involving degenerative changes in motor neurons. Its pathogenesis factors include genetics, environment and immunity, etc. Its main manifestations are muscle atrophy, myotonia, myoclonus, etc.This article uses a combination of massage technology and acupuncture technology to carry out different acupuncture treatment plans with reference to the Brunnstrom classification.

Research on the visualized monitoring method of particulate matter in the building construction environment

Fri, 06 Dec 2024 00:00:00 +0800

Particulate matter pollution in the building construction environment is very serious. It produces such tiny particulate matter as dust and bacteria. The prolonged inhalation can lead to respiratory infections and lung diseases. In China, there are relative few studies on the concentration distribution of particulate matter in construction sites. And there is a lack of in-depth analyses on the spatial and temporal characteristics of particulate matter dispersion. In this paper, the vertical profile of particulate matter is studied in the campus construction lot. The sensors are carried on the UAV. The distribution characteristics of the particulate matter are restored to establish a visual three-dimensional model of the concentration of particulate matter in the studied region. It effectively makes up for the shortcomings of the traditional near-earth detection in the spatial dimensions. Also the research results could provide technological support for the prevention of fumes and dusts in construction environments.

Research on the Integration and Development of Strengthening the Consciousness of the Chinese Nation Community and Ideological and Political Education in Engineering Major Courses

Xiangqun Li, Wen Zhang, Mingliang Gao — Fri, 06 Dec 2024 00:00:00 +0800

This paper explores the integration of strengthening the consciousness of the Chinese nation community with ideological and political education in engineering major courses, an important issue in higher education reform. Strengthening the consciousness of the Chinese nation community emphasizes the unity and common progress of all ethnic groups, aiming to enhance national cohesion and harmonious social development. Ideological and political education in engineering courses incorporates core socialist values and scientific methods into professional knowledge to cultivate students' sense of social responsibility and innovation spirit. This paper proposes specific integration strategies in terms of curriculum design, practical teaching, and the combination of craftsmanship and scientific spirit. It also suggests innovative teaching methods through interactive teaching, interdisciplinary integration, and multimedia tools. Furthermore, the establishment of a scientific evaluation and feedback mechanism is recommended to ensure teaching effectiveness and to nurture innovative engineering talents with a strong sense of social responsibility and patriotism.

Review of research and application on digital twin technology

Yunqi Chen — Fri, 06 Dec 2024 00:00:00 +0800

Digital twin is a new technical means to realize the interactive integration of the physical world and the information world. It has been widely used in many business fields and has received more and more attention. Based on the analysis of the connotation and architecture system of digital twin, this paper discusses its key technologies in model construction, data collection and analysis, virtual-reality interaction and visualization, summarizes the research progress of digital twin technology in hot fields such as intelligent manufacturing, smart cities, mining, power monitoring and water conservancy projects, summarizes the existing deficiencies and future development trends, in order to provide reference and inspiration for the development of digital twin technology.

BCVKG：Research on Knowledge graph for BCV viruses

Fri, 06 Dec 2024 00:00:00 +0800

As the global economy has expanded, animal diseases have become significant obstacles to the sustainable development of animal husbandry. Among these diseases, bovine rotavirus coronavirus (BCV or BCoV) exhibits clinical symptoms such as diarrhea, dehydration, and gastroenteritis. The prevention and control of BCV virus remain the primary concern in managing bovine viral diarrheal diseases. We using crawler technology to search for key words of "bovine coronavirus" and "BCV" in the PubMed database, 1410 articles were obtained, and after screening, 927 related articles were obtained. A knowledge graph construction pipeline method called BcvKG has been proposed to convert unstructured data into structured data. We obtained 1422 entities and 584 pairs of valid entity triplets, and visualized them using the Neo4j graph database. Finally, presented in the form of a knowledge graph. Compared with previous methodological methods, this article has completed the information extraction of literature related to bovine viral diarrhea disease for the first time, aiming to construct a knowledge graph.

An IMM Algorithm for Tracking Maneuvering Space Target under Low-Rate Data

Peiyun Wu, Jing Li, Jintao Chen, Yan Zhang — Fri, 06 Dec 2024 00:00:00 +0800

Under low data rates, the observational data is sparse, and the noise have a significant impact. Under such circumstance, filtering algorithms tend to rely more heavily on predictions. However, the absence of maneuver information usually results in significant model errors, ultimately affecting the accuracy of states estimation and potentially leading to filter divergence. To address this issue, we have constructed a model set specific to satellite maneuvers and proposed an Improved Interacting Multiple Model (IMM) algorithm based on a designed maneuver detection model and estimation model. We have developed a maneuver estimation model to estimate the maneuvers, and to perform pruning on the maneuver models before estimation. The algorithm dynamically controls the introduction of maneuver models via the detection model and estimation model. When a maneuver is detected, the algorithm introduces the maneuver model set for fusion estimation; otherwise, it degrades into a Kalman filter based on a non-maneuver model. Simulation results indicate that the proposed algorithm effectively tracks targets in low data rate scenarios while maintaining high estimation accuracy.