作者机构：
[Tiancheng Zhang] Bi Shengyun Information Technology Co., LTD;[Hua Yang; Haifeng Zhang; Jie Xiao; Qi Wang; Shenyang Sheng; Chengwu Peng] School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China
会议名称：
2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
会议时间：
15 March 2024
会议地点：
Chongqing, China
会议论文集名称：
2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)
摘要：
With the continuous development of artificial intelligence technology, deep learning methods have been widely used in smart agriculture. With the continuous progress of object detection algorithms, it is a future trend to introduce computer vision methods into smart agriculture. This paper proposes an improved YOLOv8 network model for detecting whether apple is still in a healthy state in smart agriculture systems. By introducing a better backbone network EfficientNet, features can be extracted from the data efficiently. In addition, by introducing a novel WIOU calculation function, the rectangular box can be computed better. In this experiment, the average accuracy of the improved YOLOv8-Enet is mAP0.5 and mAP 0.5:0.95, which are 7.1% and 6.5% higher than that of YOLOv8-base, respectively. The proposed YOLOv8-Enet model can effectively detect apple surface defect and provide theoretical and technical support for future research on vision of smart agriculture
作者机构：
chool of Modern Industry for Selenium Science and Engineering,Wuhan Polytechnic University;ational R&D Center for Se-rich Agricultural Products Processing,Hubei Engineering Research Center for Deep Processing of Green Se-rich Agricultural Products,Wuhan Polytechnic University
会议名称：
2024社会发展与科技创新交流会
会议时间：
2024-04-20
会议地点：
线上会议
关键词：
Food translation;cross-disciplinary;teaching practice
摘要：
Relying on the practical course system of food and translation majors,this course combines the characteristics of the professional courses of the two majors,including the knowledge of food,which is stronger in professional nature,and the knowledge of translation,which is more prominent in practical ability,to cultivate cross-disciplinary talents in food and translation. This paper takes "Food and English Translation" course as an example,analyzes the potential connection between food and translation,creates teaching situations by using modern teaching methods,and promotes the cultivation mode of interdisciplinary composite talents and the innovation of in-depth integration of disciplines and specialties. In order to break down the barriers between disciplines and specialties and strengthen the construction of interdisciplinary innovative talents,we summarize the basic construction and practical experience of the general elective course of interdisciplinary cross-fertilization.
摘要：
A numerical analysis has been done to investigate the effects of different overload conditions on crack propagation behavior of AH32 steel. The tensile overload ratios, overload-underload, underload-overload and underload are investigated in this study. The residual stress distribution in the region near the crack tip under different overload ratios and overload conditions are all the results of plastic deformation of the material near the crack tip during fatigue crack propagation, which shows that applying tensile overload postpone the crack growth, while underload promote the crack growth. Furthermore, it is also observed that the crack closure level shows a fast increase with the increase of overload ratio. Finally, the mechanism of residual stress at the crack tip and the mechanism of plastic deformation at the crack tip controlling the transient crack growth behavior under variable amplitude loading are essentially the same.
摘要：
SSD (Single Shot Multi Box Detector) is one of the commonly used object detection algorithms known for its fast detection speed and high accuracy. However, SSD's performance in detecting objects of different scales is suboptimal. This paper proposes the RSF-SSD network based on multi-level feature enhancement. By improving the backbone network of SSD, skip-connections and channel attention mechanism are introduced into VGG16. This operation enhances the ability of the backbone network to extract detailed features. In the feature fusion module, an improved FPN (Feature Pyramid Networks) + PAN (Path Aggregation Network) module is introduced (referred to as FAN) to achieve comprehensive fusion of deep semantic information and shallow localization information. In testing on the PASCAL VOC07 + 12 dataset, the proposed network achieves a 15.3%mAP improvement in detection accuracy compared to traditional SSD. The experiments demonstrate that the RSF-SSD model effectively enhances the capability of extracting detailed features, and incorporates more semantic information in the shallow layers, leading to improved detection performance for objects of different sizes.
会议名称：
18th International Conference on Bio-Inspired Computing: Theories and Applications (BIC-TA)
会议时间：
DEC 15-17, 2023
会议地点：
Changsha, PEOPLES R CHINA
会议主办单位：
[Yang, Hua;Li, Jian;Liu, Neng;Yi, Kecheng;Wang, Jing;Fu, Rou;Zhang, Jun;Xiang, Yunzhu;Yang, Pengcheng;Hang, Tianyu] Wuhan Polytech Univ, Sch Math & Comp Sci, Wuhan 430040, Peoples R China.^[Zhang, Tiancheng;Wang, Siyi] Wuhan BisiCloud Technol Co Ltd, Wuhan 430015, Peoples R China.
会议论文集名称：
Communications in Computer and Information Science
关键词：
GA-BP neural network;Prediction model;Rice processing loss
摘要：
Food is closely related to national economy and people's livelihood. Rice is the largest grain crop in China, it is crucial to predict the loss rate of rice during processing to reduce food waste and ensure food security. This study first obtained the loss rate of rice processing through the recovery survey form of enterprises. Then, prediction was carried out using two common models: the BP neural network and multiple linear regression. Finally, the genetic algorithm was applied to optimize the BP neural network for further prediction and com-pared with the original models. The experimental results showed that the GA-BP model had higher prediction accuracy and smaller error compared to the first two models. It is valuable in reducing processing losses and maintaining food security.
作者机构：
School of Electrical and Electronic Engineering, Wuhan Polytechnic University
会议名称：
第43届中国控制会议
会议时间：
2024-07-28
会议地点：
中国云南昆明
关键词：
Artificial potential field algorithm;COLREGS;Path planning;USV
摘要：
Path planning is a core issue of autonomous navigation for unmanned surface vehicles(USVs). To guarantee navigation safety, this paper proposes an Improved Artificial Potential Field(IAPF) algorithm for path planning of USVs. On the one hand, to solve the local optimal problem of artificial potential field(APF) algorithm, an adjustment factor is introduced in the repulsive potential field function. On the other hand, to ensure the collision avoidance safety in complex encounter scenarios, the International Regulations for Preventing Collisions at Sea(COLREGS) is utilized in the IAPF algorithm. The simulation experiments verify that the path planned via the IAPF algorithm is safer and more efficient than APF algorithm.
关键词：
Artificial intelligence;Construction of big data platforms;Management monitoring
摘要：
The introduction of big data technology can bring significant changes to engineering project management, greatly improving the efficiency of various aspects of project management, providing reference for scientific decision-making, and thus achieving the improvement of project benefits. In the analysis of engineering construction, the significance of monitoring in engineering construction involves the application of many new technologies, while analysis and prediction involve many interdisciplinary methods and theories. This article conducts research on the construction and management monitoring of big data platforms based on AI (Artificial Intelligence). This article applies DL (Deep Learning) to the research of this article. The research results show that the average relative error rates of interval 1 and interval 39 are 18.3%, respectively. It can be concluded that the average relative error of the quality distribution of each particle size grading in engineering filling stone mining based on AI is <= 25%. It can effectively optimize the blasting parameters of sand and stone mining, control the particle size grading of stone materials, and meet the mining grading requirements. It provides technical reference for the design of filling stone mining in embankment engineering and ensures the quality of embankment engineering. Through the construction and management monitoring of this platform, it is beneficial to reduce resource waste during the construction process and reduce construction costs for enterprises.
作者：
Li Qingming;Tang Huiming;Zhang Rongtang;Zhao Nenghao
作者机构：
[Li Qingming] Shenzhen Municipal Design & Res Inst Co Ltd, Shenzhen, Peoples R China.;[Tang Huiming] China Univ Geosci, Wuhan, Peoples R China.;[Zhao Nenghao; Zhang Rongtang] Wuhan Polytech Univ, Wuhan, Peoples R China.
会议名称：
14th Congress of the International-Association-for-Engineering-Geology-and-the-Environment (IAEG)
会议时间：
SEP 21-27, 2023
会议地点：
Chengdu, PEOPLES R CHINA
会议主办单位：
[Li Qingming] Shenzhen Municipal Design & Res Inst Co Ltd, Shenzhen, Peoples R China.^[Tang Huiming] China Univ Geosci, Wuhan, Peoples R China.^[Zhang Rongtang;Zhao Nenghao] Wuhan Polytech Univ, Wuhan, Peoples R China.
会议论文集名称：
Environmental Science and Engineering
关键词：
Rock-soil strata;Standard sequence of rock-soil strata;Particles of rock-soil;Special components;Compactness
摘要：
In the current rock or soil classification schemes, lots of fuzzy zones are caused among various rock or soil types due to the fragmentation of classification standards. The general classification of rock and soil should be based on the basic material composition: solid, liquid and gas. Normally, the combination scheme of special components, grain size, porosity and degree of saturation can be adopted. In this paper, special components include organic matter and special minerals which include lamellar minerals represented by montmorillonite, soluble salts and carbonate minerals. The general classification index should be applied to various kinds of rock and soil, but some parameters only suitable for a specific rock or soil can be used as the secondary classification index. Special components, grain sizes and composition are adopted to classify particles of rock and soil, porosity to measure the absolute compactness among particles and degree of saturation to measure moisture state. A rock-soil stratum is defined as the stratum with the same geological age, the same genesis and the same special components, grain sizes and composition, compactness and degree of saturation. The standard sequence of rock-soil strata is defined as all combinations of rock and soil strata with a specific geological era and a specific genetic type in a region. It is an important foundation of a large database to establish the standard sequence of rock-soil strata for all the geological ages and genetic types in a region, a nation or the whole world.
摘要：
<正>引言/目的副猪嗜血杆菌(Glaesserella parasuis,GPS)是巴氏杆菌科嗜血杆菌属的革兰氏阴性菌,在临床上可引起血管内皮屏障损伤。课题组前期发现,副猪嗜血杆菌感染猪血管内皮细胞后,能激活Panx-1通道,刺激细胞外排核苷酸类"find-me"信号物质ATP和UTP,UTP可引起嘌呤能受体P2Y6下游通路激活,促进细胞炎症和细胞骨架重组的发生。但分化簇(Cluster of differentiation,CD)分子功能在副猪嗜血杆菌病的研究尚未有报道。本试验采取体外方法探究猪血管内皮细胞感染GPS后细胞凋亡相关的CD分子表达情况,同时还研究黄芩苷对CD分子的调控作用。
摘要：
The segmentation of CT images of pancreatic tumors is of great significance for the diagnosis and treatment of pancreatic tumors. Due to the small size and irregular shape of pancreatic tumors, precise segmentation of pancreatic tumor CT images using neural networks remains a challenge in machine learning. At present, the dice coefficient, MIoU coefficient, and Precision coefficient of neural network for pancreatic tumor CT image segmentation are only 50%, 30%, and 50% at most, respectively. There is a lot of room to improve the segmentation effect. This paper proposes a CT image segmentation method for pancreatic tumors based on a 3D U-Net network and integrating Densely Connected Atrous Spatial Pyramid Module (DenseASP Module) and Attention Module (AM). In order to effectively extract small target feature information, this network adds DenseASP to each layer of the downsampling section; At the same time, in order to filter irrelevant information and enhance the extraction of target area information, we add Attention Gates (AG) to each layer of the upsampling section, and Channel Attention Module (CAM) to the skip connection section. The Attention Gates and Channel Attention Modules together constitute the Attention Module (AM) of our network. This paper selects dice coefficient, MIoU coefficient, Precision coefficient as the evaluation index of segmentation effect, and uses the pancreas dataset MSD Pancreas to evaluate our model. The experimental results show that the various segmentation evaluation indicators of the model in this paper have improved by about 2 percentage points compared to the current neural network.
期刊：
E3S Web of Conferences,2023年385:02016 ISSN：2555-0403
通讯作者：
Li, S.
作者机构：
[Zhao Z.; Song G.; Tu L.] Wuhan Polytechnic University, Hubei, Wuhan, 430023, China;Pilot Plant of Eco-Environment Chemical Industry and Carbon-Neutral Transformative Technologies, Hubei, Wuhan, 430023, China;Hubei Provincial Engineering Research Center of Soil and Groundwater Pollution Prevention and Control, Hubei, Wuhan, 430023, China;[Li S.] Wuhan Polytechnic University, Hubei, Wuhan, 430023, China, Hubei Provincial Engineering Research Center of Soil and Groundwater Pollution Prevention and Control, Hubei, Wuhan, 430023, China;[Zhang H.; Ding S.; Chen P.; Zhang Y.] Wuhan Polytechnic University, Hubei, Wuhan, 430023, China, Pilot Plant of Eco-Environment Chemical Industry and Carbon-Neutral Transformative Technologies, Hubei, Wuhan, 430023, China
通讯机构：
[Li, S.] W;Wuhan Polytechnic University, Hubei, China
会议名称：
2023 8th International Symposium on Energy Science and Chemical Engineering, ISESCE 2023
作者机构：
[Jiahao Li; Fangxiu Wang; Jiaqi An; Yongkai Song; Qingwei Qiu; Jiarong Tian] School of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, China
会议名称：
2023 38th Youth Academic Annual Conference of Chinese Association of Automation (YAC)
会议时间：
27 August 2023
会议地点：
Hefei, China
会议论文集名称：
2023 38th Youth Academic Annual Conference of Chinese Association of Automation (YAC)
关键词：
Character substitution;Table tail insertion method;Shared stack operation
摘要：
In view of the slow speed of fractal graph drawing with character substitution method, this paper gives two methods to increase the speed of fractal graph drawing. First, the string is stored in two sequential tables instead of one, and the new string is generated by table tail insertion method, thus avoiding a large number of element movements during insertion. Second, new strings are generated by a shared stack operation on a single sequential table, again avoiding the problem of a large number of element movements during new string generation. The test results show that using the two methods designed in this paper can greatly improve the speed of fractal graph drawing.
摘要：
Skin cancer is one of the most common malignant tumors. In order to completely remove tumors and accurately identify and segment lesion areas, this paper proposes a skin lesion segmentation method based on U2Net. Firstly, deep separable convolution is used to replace conventional convolution for feature extraction of RSU blocks. Embedded branch structures are added at skip connections, and Receptive Field Block(RFB) modules are used to integrate semantic information at different scales. Then, Add Attention Gates (AG) and Normalization-based Attention Modules (NAM), which together form the NAM-Gate Attention mechanism can redistribute image feature weights to reduce the loss of spatial feature information. This article selects Dice, Accuracy, and F1 Score as evaluation indicators and uses the ISIC2018 Task 1 dataset to evaluate our model. The experimental results show that the methods Dice, Accuracy, and F1 Score in this paper have improved by 2.06%, 1.01%, and 1.50%, respectively.
关键词：
College English;Translation teaching;Multimodal construction;Cross-cultural perspective
摘要：
College English translation teaching essentially helps non-English major students master translation skills,improve translation competence, and integrate translation with their respective majors. As for translation activities, language is the starting point while culture is the endpoint. In order to effectively improve teaching quality and students' satisfaction, translation courses should be placed in the perspective of cross-cultural communication. Therefore, this research paper principally explores and analyzes the multimodal construction of college English translation teaching from six aspects: values, linguistic proficiency, cross-cultural competence,translation competence, teaching materials and methods, teachers and technology. It concludes with the following claims: 1) inspiring students to love Chinese culture and serving as ambassadors for China's cultural exchanges on the global stage are the core values for effective translation teaching; 2) the constant improvement of linguistic proficiency in both English and Chinese is a fundamental guarantee for learning and excelling in translation; 3) being immersed into culture to appreciate the language differences as well as learning to view Chinese culture from the perspective of the English culture serves as a boost to translation quality; 4) teachers should combine translation theories, strategies and methods to help students better understand the relationship between theory and practice, leading them to guide their own practice with theory and further develop theory through practice; 5) teachers are also expected to continuously diversify their teaching methods, compile and use interesting, informative and inspiring textbooks; 6) the application of translation technology will help align teaching with the translation market, sufficiently enabling students to meet job requirements upon graduation.
摘要：
Depression is a chronic mental disease that seriously harms human health and has a variety of complications.A rising body of evidence indicated that communication between intestinal microorganisms and their hosts potentially play an important role in disease and health concerns.Intestinal flora exists in human digestive tract and is abundant,as well as a significant environmental component in the transformation of human physiology.Dysregulation of intestinal flora is related to depression,and its mechanism includes hypothalamic-pituitary-adrenal(HPA) axis,inflammatory response,monoamine neurotransmitter imbalance,neurotrophic factor imbalance,cross-reaction mechanism and so on.This paper summarizes the mechanism and influence of intestinal microflora in depression in recent years,so as to provide some reference for revealing the mechanism of depression.
