检索结果-南通市图书馆

Image enhancement with intensity transformation on embedding space

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 101-115页

作者： Hanul Kim Yeji jeon Yeong Jun Koh Department of Applied Artificial Intelligence Seoul National University of Science and TechnologySeoulSouth Korea Department of Computer Science and Engineering Chungnam National UniversityDaejeonSouth Korea

In recent times,an image enhancement approach,which learns the global transformation function using deep neural networks,has gained ***,many existing methods based on this approach have a limitation:their transformation functions are too simple to imitate complex colour transformations between low-quality images and manually retouched high-quality *** order to address this limitation,a simple yet effective approach for image enhancement is *** proposed algorithm based on the channel-wise intensity transformation is ***,this transformation is applied to the learnt embedding space instead of specific colour spaces and then return enhanced features to *** this end,the authors define the continuous intensity transformation(CIT)to describe the mapping between input and output intensities on the embedding ***,the enhancement network is developed,which produces multi-scale feature maps from input images,derives the set of transformation functions,and performs the CIT to obtain enhanced *** experiments on the MIT-Adobe 5K dataset demonstrate that the authors’approach improves the performance of conventional intensity transforms on colour space ***,the authors achieved a 3.8%improvement in peak signal-to-noise ratio,a 1.8%improvement in structual similarity index measure,and a 27.5%improvement in learned perceptual image patch ***,the authors’algorithm outperforms state-of-the-art alternatives on three image enhancement datasets:MIT-Adobe 5K,Low-Light,and Google HDRþ.

关键词： computer vision deep learning image enhancement image processing

Improvement in the Adhesion Between Electrode of a SOFC and Ag Paste as a Current Collector by Au Deposition

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 Materials Science & Technology 2015年第3期31卷 257-263页

作者： Sang Koo jeon Seung Hoon Nahm Oh Heon Kwon Department of Safety Engineering Pukyong National University Center for Energy Materials Metrology Korea Research Institute or Standards and Science

This paper reports the use of Au films to improve the performance of the stacked solid oxide fuel cell(SOFC) based on the characterization of the interface and the adhesion between the electrodes of the SOFCs and the Ag paste. The specimens were manufactured to perform the experiment as follows. A Si O2 wafer with a 300 mm notch was attached to the electrodes of a SOFC by a Ag paste and Au film, which were deposited on the electrodes by sputtering for 1 min or 5 min deposition time and annealed at300 C for 1 h. The four-point bending test was performed, which resulted in the formation of an extended crack at the tip on the wafer notch, and the crack propagation was observed using a stereo microscope equipped with a charge-coupled device(CCD). Consequently, the interfacial adhesion energy and the effect of the Au film between the each electrode and the Ag paste can be evaluated. On the cathode, the interfacial adhesion energy without Au film was 2.59 J/m2(upper value) and the adhesion energy increased to 11.59 J/m2(upper value) and 15.89 J/m2(lower value) with the Au film. On the anode,the interfacial adhesion energy without Au film was 1.74 J/m2(upper value), which increased to 11.07 J/m2(upper value) and 14.74 J/m2(lower value) with the Au film. In addition, the interface areas were analyzed by scanning electron microscopy(SEM) and energy dispersive spectroscopy(EDS) to estimate the interface delamination.

关键词： Solid oxide fuel cell Au film Interfacial adhesion

Nanocrystalline low-silica X zeolite as an efficient ion-exchanger enabling fast radioactive strontium capture

在线全文

学校读者我要写书评

暂无评论

Frontiers of Chemical Science and Engineering 2024年第9期18卷 15-23页

作者： Hyungmin jeon Susung Lee jeong-Chul Kim Minkee Choi Department of Chemical and Biomolecular Engineering(BK21 Four) Korea Advanced Institute of Science and Technology(KAIST)Daejeon 34141Republic of Korea Center for Nanomaterials and Chemical Reactions Institute for Basic Science(IBS)Daejeon 34141Republic of Korea

NaA zeolite(Si/Al=1.00)has been commercially applied for capturing radioactive 90Sr^(2+)because of its high surface charge density,effectively stabilizing the multivalent ***,owing to its narrow micropore opening(4.0Å),large micron-sized crystallites,and bulkiness of hydrated Sr^(2+),the Sr^(2+)exchange over NaA has been limited by very slow *** this study,we synthesized nanocrystalline low-silica X by minimizing a water content in a synthesis gel and utilizing a methyl cellulose hydrogel as a crystal growth *** resulting zeolite exhibited high crystallinity and Al-rich framework(Si/Al of approximately 1.00)with the sole presence of tetrahedral Al sites,which are capable of high Sr^(2+)uptake and ion ***,the zeolite with a FAU topology has a much larger micropore opening size(7.4Å)and a much smaller crystallite size(~340 nm)than NaA,which enable significantly enhanced ion-exchange *** to conventional NaA,the nanocrystalline low-silica X exhibited remarkably increased Sr^(2+)-exchange kinetics(>18-fold larger rate constant)in batch *** both the nanocrystalline low-silica X and NaA exhibited comparable Sr^(2+)capacities under equilibrated conditions,the former demonstrated a 5.5-fold larger breakthrough volume than NaA under dynamic conditions,attributed to its significantly faster Sr^(2+)-exchange kinetics.

关键词： Sr^(2+)removal low-silica X zeolite nanocrystal hydrogel methyl cellulose

Towards Collaborative Robotics in Top View Surveillance:A Framework for Multiple Object Tracking by Detection Using Deep 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

IEEE/CAA Journal of Automatica Sinica 2021年第7期8卷 1253-1270页

作者： Imran Ahmed Sadia Din Gwanggil jeon Francesco Piccialli Giancarlo Fortino the Center of excellence in Information Technology Institute of Management SciencesPeshawar 25000Pakistan the Department of Information and Communication Engineering Yeungnam UniversitySouth Korea the School of Electronic Engineering Xidian UniversityXi’an 710071China the Department of Embedded Systems Engineering Incheon National UniversityIncheon 22012Korea the Department of Mathematics and Applications“R.Caccioppoli” University of Naples Federico IINapoli 80138Italy the Department of Informatics ModelingElectronics and SystemsUniversity of CalabriaRendeCS 87036Italy

Collaborative Robotics is one of the high-interest research topics in the area of academia and *** has been progressively utilized in numerous applications,particularly in intelligent surveillance *** allows the deployment of smart cameras or optical sensors with computer vision techniques,which may serve in several object detection and tracking *** tasks have been considered challenging and high-level perceptual problems,frequently dominated by relative information about the environment,where main concerns such as occlusion,illumination,background,object deformation,and object class variations are *** order to show the importance of top view surveillance,a collaborative robotics framework has been *** can assist in the detection and tracking of multiple objects in top view *** framework consists of a smart robotic camera embedded with the visual processing *** existing pre-trained deep learning models named SSD and YOLO has been adopted for object detection and *** detection models are further combined with different tracking algorithms,including GOTURN,MEDIANFLOW,TLD,KCF,MIL,and *** algorithms,along with detection models,help to track and predict the trajectories of detected *** pre-trained models are employed;therefore,the generalization performance is also investigated through testing the models on various sequences of top view data *** detection models achieved maximum True Detection Rate 93%to 90%with a maximum 0.6%False Detection *** tracking results of different algorithms are nearly identical,with tracking accuracy ranging from 90%to 94%.Furthermore,a discussion has been carried out on output results along with future guidelines.

关键词： Collaborative robotics deep learning object detection and tracking top view video surveillance

Cathepsin B-responsive prodrugs for cancer-targeted therapy:Recent advances and progress for clinical translation

在线全文

学校读者我要写书评

暂无评论

Nano Research 2022年第8期15卷 7247-7266页

作者： Seong Ik jeon Suah Yang Man Kyu Shim Kwangmeyung Kim Biomedical Research Institute Korea Institute of Science and Technology(KIST)Seoul 02792Republic of Korea KU-KIST Graduate School of Converging Science and Technology Korea UniversitySeoul 02841Republic of Korea

The cathepsin B-responsive prodrugs are promising strategies to reduce the serious adverse effects of anticancer drugs by improving the cancer selectivity that can be specifically activated by overexpressed cathepsin B in targeted cancer ***,clinical translation of such therapeutic approaches has been restricted by low antitumor efficacy that is mainly attributable to undesirable pharmacokinetic profiles and inefficient tumor-targeting of cathepsin B-responsive prodrugs,due to their small-molecule *** recent decades,many researchers have widely investigated the drug delivery system(DDS)to improve the in vivo pharmacokinetic profiles and tumor-targeting efficiency of cathepsin B-responsive prodrugs via the application of polymers,dendrimers,antibodies,lipids,and inorganic nanoparticles as drug *** addition,the potential therapeutic efficacy of DDS for cathepsin B-responsive prodrugs is demonstrated in multiple studies and combinatorial treatment with typical therapeutic modalities can effectively overcome the challenges of tumor heterogeneity and multidrug *** this review,recent advances and progress of new DDS for cathepsin B-responsive prodrugs are outlined,and their clinical trials are ***,potential challenges and the outlooks for clinical translation of cathepsin B-responsive prodrugs are highlighted.

关键词： cathepsin B prodrug chemotherapy drug delivery system targeted cancer therapy

Fuzz-classification(p,l)-Angel:An enhanced hybrid artificial intelligence based fuzzy logic for multiple sensitive attributes against privacy breaches

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2023年第5期9卷 1131-1140页

作者： Tehsin Kanwal Hasina Attaullah Adeel Anjum Abid Khan Gwanggil jeon Department of Computer Science COMSATS University IslamabadPakistan Department of Information Technology Quaid-e-Azam University IslamabadPakistan College of Science and Engineering School of Computing and MathsUniversity of DerbyDE221GBUK Department of Embedded Systems Engineering Incheon National UniversitySouth Korea

The inability of traditional privacy-preserving models to protect multiple datasets based on sensitive attributes has prompted researchers to propose models such as SLOMS,SLAMSA,(p,k)-Angelization,and(p,l)-Angelization,but these were found to be insufficient in terms of robust privacy and performance.(p,l)-Angelization was successful against different privacy disclosures,but it was not *** the best of our knowledge,no robust privacy model based on fuzzy logic has been proposed to protect the privacy of sensitive attributes with multiple *** this paper,we suggest an improved version of(p,l)-Angelization based on a hybrid AI approach and privacy-preserving approach like ***-classification(p,l)-Angel uses artificial intelligence based fuzzy logic for classification,a high-dimensional segmentation technique for segmenting quasi-identifiers and multiple sensitive *** demonstrate the feasibility of the proposed solution by modelling and analyzing privacy violations using High-Level Petri *** results of the experiment demonstrate that the proposed approach produces better results in terms of efficiency and utility.

关键词： Generalization Fuzzy-logic MSA Privacy disclosures Membership function (p,l)-Angelization QT HLPN

Integrating digital twins and deep learning for medical image analysis in the era of COVID-19

在线全文

学校读者我要写书评

暂无评论

Virtual Reality & Intelligent Hardware 2022年第4期4卷 292-305页

作者： Imran AHMED Misbah AHMAD Gwanggil jeon School of Computing and Information Science Faculty of Science and EngineeringAnglia Ruskin UniversityEast RoadCambridgeEnglandUK Center of Excellence in IT Institute of Management SciencesHayatabadPeshawarPakistan Department of Embedded Systems Engineering Incheon National UniversityIncheonKorea

Background Digital twins are virtual representations of devices and processes that capture the physical properties of the environment and operational algorithms/techniques in the context of medical devices and *** twins may allow healthcare organizations to determine methods of improving medical processes,enhancing patient experience,lowering operating expenses,and extending the value of *** the present COVID-19 pandemic,various medical devices,such as X-rays and CT scan machines and processes,are constantly being used to collect and analyze medical *** collecting and processing an extensive volume of data in the form of images,machines and processes sometimes suffer from system failures,creating critical issues for hospitals and *** To address this,we introduce a digital-twin-based smart healthcare system in-tegrated with medical devices to collect information regarding the current health condition,configuration,and maintenance history of the device/machine/***,medical images,that is,X-rays,are analyzed by using a deep-learning model to detect the infection of *** designed system is based on the cascade recurrent convolution neural network(RCNN)*** this architecture,the detector stages are deeper and more sequentially selective against small and close false *** architecture is a multi-stage extension of the RCNN model and sequentially trained using the output of one stage for training the *** each stage,the bounding boxes are adjusted to locate a suitable value of the nearest false positives during the training of the different *** this manner,the arrangement of detectors is adjusted to increase the intersection over union,overcoming the problem of *** train the model by using X-ray images as the model was previously trained on another *** The developed system achieves good accuracy during the detection phase of *** experimental o

关键词： Digital twins Deep learning Healthcare COVID-19 Chest X-rays Artificial intelligence

Clinical significance of the neutrophil-lymphocyte ratio as an early predictive marker for adverse outcomes in patients with acute pancreatitis

在线全文

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2017年第21期23卷 3883-3889页

作者： Tae Joo jeon Ji Young Park Division of Gastroenterology Department of Internal Medicine Inje University College of Medicine Sanggye Paik Hospital

AIM To investigated the prognostic value of the neutrophillymphocyte ratio(NLR) in patients with acute pancreatitis and determined an optimal cut-off value for the prediction of adverse outcomes in these *** We retrospectively analyzed 490 patients with acute pancreatitis diagnosed between March 2007 and December 2012. NLRs were calculated at admission and 24, 48, and 72 h after admission. Patients were grouped according to acute pancreatitis severity and organ failure occurrence, and a comparative analysis was performed to compare the NLR between groups. RESULTS Among the 490 patients, 70 had severe acute pancreatitis with 31 experiencing organ failure. The severe acute pancreatitis group had a significantly higher NLR than the mild acute pancreatitis group on all 4 d(median, 6.14, 6.71, 5.70, and 4.00 vs 4.74, 4.47, 3.20, and 3.30, respectively, P < 0.05). The organ failure group had a significantly higher NLR than the group without organ failure on all 4 d(median, 7.09, 6.72, 6.27, and 6.24 vs 4.85, 4.49, 3.35, and 2.34, respectively, P < 0.05). The optimal cut-off value for baseline NLR was 4.76 in predicting severity and 4.88in predicting organ failure in acute pancreatitis. CONCLUSION Elevated baseline NLR correlates with severe acute pancreatitis and organ failure.

关键词： Acute pancreatitis Neutrophil-lymphocyte ratio Organ failure Severe acute pancreatitis

Diagnostic evaluation of endoscopic ultrasonography with submucosal saline injection for differentiating between T1a and T1b early gastric cancer

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

World Journal of Gastroenterology 2022年第46期28卷 6564-6572页

作者： Ji Young Park Tae Joo jeon Department of Internal Medicine Inje University College of MedicineSanggye Paik HospitalSeoul 01757South Korea Department of Internal Medicine Yonsei University College of MedicineSeoul 03722South Korea

BACKGROUND Endoscopic ultrasonography(EUS)has become a reliable method for predicting the invasion depth of early gastric cancer(EGC).However,diagnostic accuracy of EUS is affected by several *** particular,it is difficult to differentiate between T1a and T1b EGC through *** To confirm whether submucosal saline injection(SSI)could improve the accuracy of EUS in distinguishing T1a and T1b lesions in *** Twenty-four patients with EGC were examined by EUS and subsequently by SSI combined EUS to compare the degree of tumor ***,they underwent endoscopic or surgical resection within 7 *** diagnostic accuracy of EUS and SSI combined EUS was evaluated based on the final pathological findings *** injected into the submucosa acted as an echoic contrast enhancing agent and had the effect of distinguishing the mucosal and submucosal layers *** Of total 24 patients,23 were diagnosed with EGC(T1 cancer:13 as T1a,and 10 as T1b).Standard EUS identified 6 of 13 T1a cancer patients and 3 of 10 T1b cancer ***,EUS-SSI identified 12 of 13 T1a cancer patients and 6 of 10 T1b cancer *** this study,SSI combined EUS was more accurate than EUS alone in diagnosing T1a and T1b lesions of EGC(75.0%and 37.5%,respectively).CONCLUSION SSI improved the diagnostic accuracy of EUS in distinguishing between the T1a and T1b stages in EGC.

关键词： Endoscopic ultrasonography Gastric cancer Endoscopy Surgery