检索结果-南通市图书馆

Transferable adversarial slow feature extraction network for few-shot quality prediction in coal-to-ethylene glycol process

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2024年第7期71卷 258-271页

作者： Cheng Yang Chao Jiang Guo Yu jun Li Cuimei bo School of Electrical Engineering and Control Science Nanjing Tech UniversityNanjing 211816China Department of Intelligent Manufacturing Nanjing Tech UniversityNanjing 210009China

In the coal-to-ethylene glycol(CTEG)process,precisely estimating quality variables is crucial for process monitoring,optimization,and control.A significant challenge in this regard is relying on offline laboratory analysis to obtain these variables,which often incurs substantial monetary costs and significant time *** resulting few-shot learning scenarios present a hurdle to the efficient development of predictive *** address this issue,our study introduces the transferable adversarial slow feature extraction network(TASF-Net),an innovative approach designed specifically for few-shot quality prediction in the CTEG ***-Net uniquely integrates the slowness principle with a deep Bayesian framework,effectively capturing the nonlinear and inertial characteristics of the CTEG ***,the model employs a variable attention mechanism to identify quality-related input variables adaptively at each time step.A key strength of TASF-Net lies in its ability to navigate the complex measurement noise,outliers,and system interference typical in CTEG *** learning strategy using a min-max game is adopted to improve its robustness and ability to model irregular industrial data accurately and ***,an incremental refining transfer learning framework is designed to further improve few-shot prediction performance achieved by transferring knowledge from the pretrained model on the source domain to the target *** effectiveness and superiority of TASF-Net have been empirically validated using a real-world CTEG *** with some state-of-the-art methods,TASF-Net demonstrates exceptional capability in addressing the intricate challenges for few-shot quality prediction in the CTEG process.

关键词： Chemical process Neural networks Slowness principle Transfer learning Prediction

Retinal vascular morphological characteristics in diabetic retinopathy: an artificial intelligence study using a transfer learning system to analyze ultra-wide field images

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Ophthalmology(English edition) 2024年第6期17卷 1001-1006页

作者： Xin-Yi Deng Hui Liu zheng-Xi Zhang Han-Xiao Li jun Wang Yi-Qi Chen Jian-bo Mao Ming-Zhai Sun Li-jun Shen Center for Rehabilitation Medicine Department of OphthalmologyZhejiang Provincial People’s Hospital(Affiliated People’s HospitalHangzhou Medical College)Hangzhou 310014Zhejiang ProvinceChina Department of Precision Machinery and Instrumentation University of Science and Technology of ChinaHefei 230026Anhui ProvinceChina Department of Retina Eye Hospital of Wenzhou Medical UniversityWenzhou 325027Zhejiang ProvinceChina

AIM:To investigate the morphological characteristics of retinal vessels in patients with different severity of diabetic retinopathy(DR)and in patients with or without diabetic macular edema(DME).METHODS:The 239 eyes of DR patients and 100 eyes of healthy individuals were recruited for the *** severity of DR patients was graded as mild,moderate and severe non-proliferative diabetic retinopathy(NPDR)according to the international clinical diabetic retinopathy(ICDR)disease severity scale classification,and retinal vascular morphology was quantitatively analyzed in ultra-wide field images using RU-net and transfer learning *** presence of DME was determined by optical coherence tomography(OCT),and differences in vascular morphological characteristics were compared between patients with and without ***:Retinal vessel segmentation using RU-net and transfer learning system had an accuracy of 99%and a Dice metric of *** with the healthy group,the DR group had smaller vessel angles(33.68±3.01 vs 37.78±1.60),smaller fractal dimension(Df)values(1.33±0.05 vs 1.41±0.03),less vessel density(1.12±0.44 vs 2.09±0.36)and fewer vascular branches(206.1±88.8 vs 396.5±91.3),all P<*** the severity of DR increased,Df values decreased,P=*** significant difference between the DME and non-DME groups were observed in vascular morphological ***:In this study,an artificial intelligence retinal vessel segmentation system is used with 99%accuracy,thus providing with relatively satisfactory performance in the evaluation of quantitative vascular *** patients have a tendency of vascular occlusion and *** presence of DME does not compromise the integral retinal vascular pattern.

关键词： diabetic retinopathy vascular morphology deep learning ultra-wide field imaging diabetic macular edema

Bidirectional position attention lightweight network for massive MIMO CSI feedback

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

The Journal of China Universities of Posts and Telecommunications 2024年

作者： Li jun Wang Yukai Zhang Zhichen He bo zheng Wenjing Lin Fei School of Information Science and Engineering Shandong University School of Information and Automation Qilu University of Technology (Shandong Academy of Sciences)

In frequency-division duplex massive multiple-input multiple-output (MIMO) systems， a bidirectional positional attention network (BPANet) is proposed to address the high computational complexity and low accuracy of existing deep learning-based channel state information (CSI) feedback methods. Specifically， a bidirectional position attention module (BPAM) is designed in the proposed BPANet to improve the network performance. The BPAM captures the distribution characteristics of the CSI matrix by integrating channel and spatial dimension information， thereby enhancing the feature representation of the CSI matrix. Furthermore， channel attention is decomposed into two one-dimensional feature encoding processes， which effectively reduce computational costs. Simulation results demonstrate that， compared with the existing representative method CLNet， BPANet reduces computational complexity by an average of 19.4% and improves accuracy by an average of 7.1%. Additionally， it performs better in terms of running time delay and cosine similarity.

关键词：

Intelligent diagnostic model for pterygium by combining attention mechanism and MobileNetV2

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

International Journal of Ophthalmology(English edition) 2024年第7期17卷 1184-1192页

作者： Mao-Nian Wu Kai He Yi-Bei Yu bo zheng Shao-jun Zhu Xiang-Qian Hong Wen-Qun Xi Zhe Zhang School of Information Engineering Huzhou UniversityHuzhou 313000Zhejiang ProvinceChina Zhejiang Province Key Laboratory of Smart Management and Application of Modern Agricultural Resources Huzhou UniversityHuzhou 313000Zhejiang ProvinceChina School of Mathematical Information Shaoxing UniversityShaoxing 312000Zhejiang ProvinceChina Shenzhen Eye Institute Shenzhen Eye HospitalJinan UniversityShenzhen 518040Guangdong ProvinceChina

AIM:To evaluate the application of an intelligent diagnostic model for ***:For intelligent diagnosis of pterygium,the attention mechanisms—SENet,ECANet,CBAM,and Self-Attention—were fused with the lightweight MobileNetV2 model structure to construct a tri-classification *** study used 1220 images of three types of anterior ocular segments of the pterygium provided by the Eye Hospital of Nanjing Medical *** classification models—VGG16,ResNet50,MobileNetV2,and EfficientNetB7—were trained on the same dataset for *** evaluate model performance in terms of accuracy,Kappa value,test time,sensitivity,specificity,the area under curve(AUC),and visual heat map,470 test images of the anterior segment of the pterygium were ***:The accuracy of the MobileNetV2+Self-Attention model with 281 MB in model size was 92.77%,and the Kappa value of the model was 88.92%.The testing time using the model was 9ms/image in the server and 138ms/image in the local *** sensitivity,specificity,and AUC for the diagnosis of pterygium using normal anterior segment images were 99.47%,100%,and 100%,respectively;using anterior segment images in the observation period were 88.30%,95.32%,and 96.70%,respectively;and using the anterior segment images in the surgery period were 88.18%,94.44%,and 97.30%,***:The developed model is lightweight and can be used not only for detection but also for assessing the severity of pterygium.

关键词： deep learning attention mechanism pterygium intelligent diagnosis

Understanding adversarial attacks on observations in deep reinforcement learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 69-83页

作者： You QIAOBEN Chengyang YING Xinning ZHOU Hang SU jun ZHU bo ZHANG Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua-Bosch Joint Center for Machine Learning Institute for Artificial Intelligence Tsinghua University Peng Cheng Laboratory

Deep reinforcement learning models are vulnerable to adversarial attacks that can decrease the cumulative expected reward of a victim by manipulating its observations. Despite the efficiency of previous optimization-based methods for generating adversarial noise in supervised learning, such methods might not achieve the lowest cumulative reward since they do not generally explore the environmental ***, a framework is provided to better understand the existing methods by reformulating the problem of adversarial attacks on reinforcement learning in the function space. The reformulation approach adopted herein generates an optimal adversary in the function space of targeted attacks, repelling them via a generic two-stage framework. In the first stage, a deceptive policy is trained by hacking the environment and discovering a set of trajectories routing to the lowest reward or the worst-case performance. Next, the adversary misleads the victim to imitate the deceptive policy by perturbing the observations. Compared to existing approaches, it is theoretically shown that our adversary is strong under an appropriate noise level. Extensive experiments demonstrate the superiority of the proposed method in terms of efficiency and effectiveness, achieving state-of-the-art performance in both Atari and MuJoCo environments.

关键词： deep learning reinforcement learning adversarial robustness adversarial attack

An innovative classification system for ranking the biological effects of marine aromatic hydrocarbons based on fish embryotoxicity

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Acta Oceanologica Sinica 2024年第6期43卷 153-162页

作者： Ronghui zheng Chao Fang Fukun Hong Min Zhang Fulong Gao Yusheng Zhang jun bo Key Laboratory of Marine Ecological Conservation and Restoration Third Institute of OceanographyMinistry of Natural ResourcesXiamen 361005China Observation and Research Station of Coastal Wetland Ecosystem in Beibu Gulf Ministry of Natural ResourcesBeihai 536015China

Petroleum hydrocarbon pollution is a global concern,particularly in coastal *** aromatic hydrocarbons(PAHs) are regarded as the most toxic components of petroleum *** this study,the biomonitoring and ranking effects of petroleum hydrocarbons and PAHs on the marine fish model Oryzias melastigma embryos were determined in the Jiulong River Estuary(JRE) and its adjacent waters in *** results showed that the levels of petroleum hydrocarbons from almost all sites met the primary standard for marine seawater quality,and the concentrations of the 16 priority PAHs in the surface seawater were lower compared with those in other coastal areas worldwide.A new fish expert system based on the embryotoxicity of ***(OME-FES) was developed and applied in the field to evaluate the biological effects of petroleum hydrocarbons and *** selected physiological index and molecular indicators in OME-FES were appropriate biomarkers for indicating the harmful effects of petroleum hydrocarbons and *** outcome of OME-FES revealed that the biological effect levels of the sampling sites ranged from level Ⅰ(no stress) to level Ⅲ(medium stress),which is further corroborated by the findings of nested analysis of variance(ANOVA) *** results suggest that the OME-FES is an effective tool for evaluating and ranking the biological effects of marine petroleum hydrocarbons and *** method may also be applied to evaluate other marine pollutants based on its framework.

关键词： petroleum hydrocarbons polycyclic aromatic hydrocarbons fish expert system integrated biomarker response nested one-way analysis of variance

维普期刊数据库

Skin-inspired interface modification strategy toward a structurefunction integrated hybrid smart fabric system with self-powered sensing property for versatile applications

在线全文

学校读者我要写书评

暂无评论

Nano Research 2024年第9期17卷 8200-8208页

作者： Xiang Cheng Teng Chen De Gong Pengcheng Ma bo Chen jun Cai Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100190China School of Mechanical Engineering and Automation Beihang UniversityBeijing 100191China Beijing U-Precision Tech Co. Ltd.Beijing 100176China University of Chinese Academy of Sciences Beijing 100049China

Fabric-based composites with superior mechanical properties and excellent perceptive function are highly ***,it remains a huge challenge to attain structure-function integration,especially for hybrid fabric ***,a skin-inspired interface modification strategy is proposed toward this target by constructing a hybrid smart fabric system consisting of two types of smart fabrics:carbon nanotube(CNT)/MXene-modified aramid fabrics and zinc oxide nanorod(ZnO NR)-modified carbon *** on that,flexible piezoelectric pressure sensors with skin-like hierarchical perception interfaces are fabricated,which demonstrate superb sensitivity of 2.39 V·kPa^(-1)and are capable of various wearable monitoring ***,the interface-modified hybrid fabric reinforced plastics can also be fabricated,which are proven to possess 13.6%higher tensile strength,10.1%elastic *** impressively,their average energy absorption can be improved by 111.9%,accompanied with inherent damage alert *** offers a paradigm to fabricate structure-function integrated hybrid smart fabric composites for the smart clothing and intelligent aerial vehicles.

关键词： hybrid fabrics interface modification piezoelectric pressure sensors self-diagnostic composites structure-function integration

Special Unipotent Representations of Simple Linear Lie Groups of Type A

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Mathematica Sinica,English Series 2024年第3期40卷 707-716页

作者： Dan BARBASCH Jia jun MA Bin Yong SUN Chen bo ZHU Department of Mathematics Cornell UniversityIthacaNY 14853USA School of Mathematical Sciences Xiamen UniversityXiamen 361005P.R.China Department of Mathematics Xiamen University Malaysia CampusSepangSelangor Darul Ehsan43900Malaysia Institute for Advanced Study in Mathematics&New Cornerstone Science Laboratory Zhejiang UniversityHangzhou 310058P.R.China Department of Mathematics National University of Singapore10 Lower Kent Ridge RoadSingapore 119076

Let G be a special linear group over the real,the complex or the quaternion,or a special unitary *** this note,we determine all special unipotent representations of G in the sense of Arthur and Barbasch-Vogan,and show... 详细信息

关键词： Special unipotent representations unitary representations coherent continuation Weyl group representations

维普期刊数据库

High-temperature wetting behavior between slag and refractory

在线全文

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research(International) 2024年第6期31卷 1304-1319页

作者： Yong-xin Wang Ya-ge Li Ya-bo Gao Zhong Huang Hai-jun Zhang The State Key Laboratory of Refractories and Metallurgy Wuhan University of Science and TechnologyWuhan 430081HubeiChina

Slag corrosion is one of the main factors of the damage of refractory,and its primary manifestations involve the melting of refractory in slag and the slag penetration into refractory,both of which are highly related to the wetting behavior between slag and *** high-temperature wettability could be characterized by parameters including the surface tension,adhesion work,and spreading coefficient of the slag on refractory surface,and it could be suppressed by altering the slag/refractory interface,thus resulting in an improved anti-corrosion *** this,the key knowledges of the slag corrosion,theory of wetting behavior and test of high-temperature contact angle were firstly ***,the major factors influencing the high-temperature slag wetting behavior were discussed based on the aspects of slag composition,refractory composition,and surface ***,the future research direction was proposed in this field.

关键词： High-temperature wetting Refractory Slag corrosion Surface tension