检索结果-南通市图书馆

Rethinking Polyp Segmentation from An Out-ofdistribution Perspective

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第4期21卷 631-639页

作者： Ge-Peng Ji Jing zhang Dylan Campbell Huan Xiong Nick Barnes Australian National University Canberra 8105Australia Mohamed bin Zayed University of Artificial Intelligence Abu Dhabi 999041UAE

Unlike existing fully-supervised approaches,we rethink colorectal polyp segmentation from an out-of-distribution perspective with a simple but effective self-supervised learning *** leverage the ability of masked autoencoders-self-supervised vision transformers trained on a reconstruction task-to learn in-distribution representations,here,the distribution of healthy colon *** then perform out-of-distribution reconstruction and inference,with feature space standardisation to align the latent distribution of the diverse abnormal samples with the statistics of the healthy *** generate per-pixel anomaly scores for each image by calculating the difference between the input and reconstructed images and use this signal for out-of-distribution(i.e.,polyp)*** results on six benchmarks show that our model has excellent segmentation performance and generalises across *** code is publicly available at https://***/GewelsJI/Polyp-OOD.

关键词： Polyp segmentation anomaly segmentation out-of-distribution segmentation masked autoencoder abdomen.

Bioactivity of silk fibroin peptides on vascular endothelial cells

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Materials Science 2024年第1期18卷 85-94页

作者： Mengnan Dai Meng Li Peixuan Li Boyu zhang Jianmei Xu Jiannan Wang National Engineering Laboratory for Modern Silk College of Textile and Clothing EngineeringSoochow UniversityNo.199 Ren-ai RoadSuzhou Industrial ParkSuzhou 215123China

To determine the contribution of non-repetitive domains to the bioactivity of the heavy chain in silk fibroin(SF)macromolecules,a gene motif f(1)encoding this fragment and its multimers(f(4)and f(8))were biosynthesized from Escherichia coli *** on the positive application potential of SF materials for the vascular tissue engineering,this study focused on examining the active response of these polypeptides to vascular endothelial *** polypeptides F(1),F(4),and F(8)were separately grafted onto the surfaces of bioinert polyethylene terephthalate(PET)films,resulting in remarkable improvements in the spread and proliferation of human umbilical vein endothelial cells(HUVECs).Using the same grafting dose,the activity of cells on polypeptide-modified PET films enhanced with the increase of the molecular weight of those grafted polypeptides from F(1)to F(8).Meanwhile,the growth of cells on the surface of the alkaline-treated PET film was improved,indicating that the hydrophilicity of the surface material had influence on the growth of ***,on surfaces with the same water contact angle,the spread and proliferation activity of cells on PET films were significantly lower than those on polypeptide-modified PET films.

关键词： silk fibroin heavy chain non-repetitive fragment cytoactive endothelial cell

β-Carboline alkaloids from the roots of Peganum harmala L.

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 Natural Medicines 2024年第2期22卷 171-177页

作者： LI Shengge zhang Qin WANG Yuetong LIN bin LI Dahong HUA Huiming HU Xu Henan Key Laboratory of zhang Zhongjing Formulate and Herbs for Immunoregulation Zhang Zhongjing Traditional School of Chinese MedicineNanyang Institute of TechnologyNanyang 473004China Key Laboratory of Structure-Based Drug Design&Discovery Ministry of EducationShenyang Pharmaceutical UniversityShenyang 110016China Wuya College of Innovation Shenyang Pharmaceutical UniversityShenyang 110016China School of Pharmaceutical Engineering Shenyang Pharmaceutical UniversityShenyang 110016China

This study reports the isolation of four newβ-carboline alkaloids(1−4)and six previously identified alkaloids(5−10)from the roots of Peganum harmala *** these compounds,1 and 2 were characterized as rareβ-carboline-quinazoline dimers exhibiting axial *** 3 possessed a unique 6/5/6/7 tetracyclic ring system with an azepine ring,and compound 4 was a novel annomontineβ-*** structures of these compounds were elucidated by spectroscopic data and quantum mechanical *** biosynthetic pathways of 1−3 were ***,the cytotoxicity of some isolates against four cancer cell lines(HL-60,A549,MDA-MB-231,and DU145)was ***,compound 4 exhibited significant cytotoxicity against HL-60,A549,and DU145 cells with IC_(50) values of 12.39,12.80,and 30.65μmol·L^(−1),***,compound 2 demonstrated selective cytotoxicity against HL-60 cells with an IC_(50) value of 17.32μmol·L^(−1).

关键词： β-Carboline alkaloids Peganum harmala Structure elucidation Cytotoxic activity

Boosting Multi-modal Ocular Recognition via Spatial Feature Reconstruction and Unsupervised Image Quality Estimation

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第1期21卷 197-214页

作者： Zihui Yan Yunlong Wang Kunbo zhang Zhenan Sun Lingxiao He Center for Research on Intelligent Perception and Computing National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing 100190China JD ai Research Beijing 100176China

In the daily application of an iris-recognition-at-a-distance(IAAD)system,many ocular images of low quality are *** the iris part of these images is often not qualified for the recognition requirements,the more accessible periocular regions are a good complement for *** further boost the performance of IAAD systems,a novel end-to-end framework for multi-modal ocular recognition is *** proposed framework mainly consists of iris/periocular feature extraction and matching,unsupervised iris quality assessment,and a score-level adaptive weighted fusion ***,ocular feature reconstruction(OFR)is proposed to sparsely reconstruct each probe image by high-quality gallery images based on proper feature ***,a brand new unsupervised iris quality assessment method based on random multiscale embedding robustness is *** from the existing iris quality assess-ment methods,the quality of an iris image is measured by its robustness in the embedding *** last,the fusion strategy exploits the iris quality score as the fusion weight to coalesce the complementary information from the iris and periocular *** experi-mental results on ocular datasets prove that the proposed method is obviously better than unimodal biometrics,and the fusion strategy can significantly improve therecognition performance.

关键词： Iris recognition periocular recognition spatial feature reconstruction fully convolutional network flexible matching unsupervised iris quality assessment adaptive weight fusion

Semantic Segmentation and YOLO Detector over Aerial Vehicle 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

Computers, Materials & Continua 2024年第8期80卷 3315-3332页

作者： Asifa Mehmood Qureshi Abdul Haleem Butt Abdulwahab Alazeb Naif Al Mudawi Mohammad Alonazi Nouf Abdullah Almujally Ahmad Jalal Hui Liu Faculty of Computing and ai Air UniversityIslamabad44000Pakistan Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Information Systems College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Cognitive Systems Lab University of BremenBremen28359Germany

Intelligent vehicle tracking and detection are crucial tasks in the realm of highway ***,vehicles come in a range of sizes,which is challenging to detect,affecting the traffic monitoring system’s overall *** learning is considered to be an efficient method for object detection in vision-based *** this paper,we proposed a vision-based vehicle detection and tracking system based on a You Look Only Once version 5(YOLOv5)detector combined with a segmentation *** model consists of six *** the first step,all the extracted traffic sequence images are subjected to pre-processing to remove noise and enhance the contrast level of the *** pre-processed images are segmented by labelling each pixel to extract the uniform regions to aid the detection phase.A single-stage detector YOLOv5 is used to detect and locate vehicles in *** detection was exposed to Speeded Up Robust Feature(SURF)feature extraction to track multiple *** on this,a unique number is assigned to each vehicle to easily locate them in the succeeding image frames by extracting them using the feature-matching ***,we implemented a Kalman filter to track multiple *** the end,the vehicle path is estimated by using the centroid points of the rectangular bounding box predicted by the tracking *** experimental results and comparison reveal that our proposed vehicle detection and tracking system outperformed other state-of-the-art *** proposed implemented system provided 94.1%detection precision for Roundabout and 96.1%detection precision for Vehicle Aerial Imaging from Drone(VaiD)datasets,respectively.

关键词： Semantic segmentation YOLOv5 vehicle detection and tracking Kalman filter SURF

Promoting interactions between cognitive science and large language models

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 Innovation 2024年第2期5卷 9-10页

作者： Youzhi Qu Penghui Du Wenxin Che Chen Wei Chi zhang Wanli Ouyang Yatao Bian Feiyang Xu bin Hu Kai Du Haiyan Wu Jia Liu Quanying Liu Department of Biomedical Engineering Southern University of Science and TechnologyShenzhen 518055China Shanghai ai Laboratory Shanghai 200232China Tencent ai Lab Shenzhen 518057China iFLYTEK ai Research Hefei 230088China School of Medical Technology Beijing Institute of TechnologyBeijing 100081China Institute for Artificial Intelligence Peking UniversityBeijing 100871China Centre for Cognitive and Brain Sciences and Department of Psychology University of MacaoMacao 999078China Department of Psychology Tsinghua UniversityBeijing 100084China

Large language models(LLMs)have made unprecedented progress,demonstrating human-like language proficiency and an extraordinary ability to encode complex *** emergence of high-level cognitive capabilities in LLMs,such as in-context learning and complex reasoning,suggests a path toward the realization of artificial general intelligence(AGI).However,we lack scientific theories and tools to assess and interpret such an emergence of the advanced intelligence of *** intelligence(ai)has been extensively applied in various areas of fundamental science to accelerate scientific research.

关键词： cognitive such language

Manipulating Nb-doped SrFeO_(3−δ)with excellent performance for proton-conducting solid oxide fuel cells

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Advanced Ceramics 2024年第5期13卷 579-589页

作者： Hailu Dai Hongzhe Du Samir Boulfrad Shoufu Yu Lei Bi Qinfang zhang School of Materials Science and Engineering Yancheng Institute of TechnologyYancheng 224051China College of Science&Engineering Hamad Bin Khalifa UniversityDoha 34110Qatar School of Resource Environment and Safety Engineering University of South ChinaHengyang 421001China

Nb-doped SrFeO_(3−δ)(SFO)is used as a cathode in proton-conducting solid oxide fuel cells(H-SOFCs).First-principles calculations show that the SrFe0.9Nb0.1O_(3−δ)(SFNO)cathode has a lower energy barrier in the cathode reaction for H-SOFCs than the Nb-free SrFeO_(3−δ)*** experimental studies show that Nb doping substantially enhances the performance of the SrFeO_(3−δ)***,oxygen vacancies(VO)were introduced into SFNO using the microwave sintering method,further improving the performance of the SFNO *** mechanism behind the performance improvement owing to VO was revealed using first-principles calculations,with further optimization of the SFNO cathode achieved by developing a suitable wet chemical synthesis route to prepare nanosized SFNO *** method significantly reduces the grain size of SFNO compared with the conventional solid-state reaction method,although the solid-state reaction method is generally used for preparing Nb-containing *** a result of defect engineering and synthesis approaches,the SFNO cathode achieved an attractive fuel cell performance,attaining an output of 1764 mW·cm−2 at 700℃ and operating for more than 200 *** manipulation of Nb-doped SrFeO_(3−δ)can be seen as a“one stone,two birds”strategy,enhancing cathode performance while retaining good stability,thus providing an interesting approach for constructing high-performance cathodes for H-SOFCs.

关键词： SrFeO_(3−δ)-(SFO) cathode proton conductor solid oxide fuel cells(SOFCs)

Diabetic Retinopathy Detection: A Hybrid Intelligent Approach

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第9期80卷 4561-4576页

作者： Atta Rahman Mustafa Youldash Ghaida Alshammari Abrar Sebiany Joury Alzayat Manar Alsayed Mona Alqahtani Noor Aljishi Department of Computer Science(CS) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam31441Saudi Arabia Department of Computer Engineering(CE) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal University(IAU)P.O.Box 1982Dammam31441Saudi Arabia

Diabetes is a serious health condition that can cause several issues in human body organs such as the heart and kidney as well as a serious eye disease called diabetic retinopathy(DR).Early detection and treatment are crucial to prevent complete blindness or partial vision *** detection methods,which involve ophthalmologists examining retinal fundus images,are subjective,expensive,and ***,this study employs artificial intelligence(ai)technology to perform faster and more accurate binary classifications and determine the presence of *** this regard,we employed three promising machine learning models namely,support vector machine(SVM),k-nearest neighbors(KNN),and Histogram Gradient Boosting(HGB),after carefully selecting features using transfer learning on the fundus images of the Asia Pacific Tele-Ophthalmology Society(APTOS)(a standard dataset),which includes 3662 images and originally categorized DR into five levels,now simplified to a binary format:No DR and DR(Classes 1-4).The results demonstrate that the SVM model outperformed the other approaches in the literature with the same dataset,achieving an excellent accuracy of 96.9%,compared to 95.6%for both the KNN and HGB *** approach is evaluated by medical health professionals and offers a valuable pathway for the early detection of DR and can be successfully employed as a clinical decision support system.

关键词： Diabetic retinopathy transfer learning machine learning fundus images binary classification APTOS

Ada-FFL:Adaptive computing fairness federated 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

CAai Transactions on Intelligence Technology 2024年第3期9卷 573-584页

作者： Yue Cong Jing Qiu Kun zhang Zhongyang Fang Chengliang Gao Shen Su Zhihong Tian The Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhouChina Pengcheng Lab ShenzhenChina Carnegie Mellon University PittsburghPennsylvaniaUSA Mohamed bin Zayed University of Artificial Intelligence Abu DhabiUnited Arab Emirates

As the scale of federated learning expands,solving the Non-IID data problem of federated learning has become a key challenge of *** existing solutions generally aim to solve the overall performance improvement of all clients;however,the overall performance improvement often sacrifices the performance of certain clients,such as clients with less *** fairness may greatly reduce the willingness of some clients to participate in federated *** order to solve the above problem,the authors propose Ada-FFL,an adaptive fairness federated aggregation learning algorithm,which can dynamically adjust the fairness coefficient according to the update of the local models,ensuring the convergence performance of the global model and the fairness between federated learning *** integrating coarse-grained and fine-grained equity solutions,the authors evaluate the deviation of local models by considering both global equity and individual equity,then the weight ratio will be dynamically allocated for each client based on the evaluated deviation value,which can ensure that the update differences of local models are fully considered in each round of ***,by combining a regularisation term to limit the local model update to be closer to the global model,the sensitivity of the model to input perturbations can be reduced,and the generalisation ability of the global model can be *** numerous experiments on several federal data sets,the authors show that our method has more advantages in convergence effect and fairness than the existing baselines.

关键词： adaptive fariness aggregation fairness federated learning non-IID