Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been ...Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.展开更多
Artificial intelligence technologies are being studied to provide scientific evidence in the medical field and developed for use as diagnostic tools.This study focused on deep learning models to classify degenerative ...Artificial intelligence technologies are being studied to provide scientific evidence in the medical field and developed for use as diagnostic tools.This study focused on deep learning models to classify degenerative arthritis into Kellgren–Lawrence grades.Specifically,degenerative arthritis was assessed by X-ray radiographic images and classified into five classes.Subsequently,the use of various deep learning models was investigated for automating the degenerative arthritis classification process.Although research on the classification of osteoarthritis using deep learning has been conducted in previous studies,only local models have been used,and an ensemble of deep learning models has never been applied to obtain more accurate results.To address this issue,this study compared the classification performance of deep learning models,includingVGGNet,DenseNet,ResNet,TinyNet,EfficientNet,MobileNet,Xception,and ViT,on a dataset commonly used for osteoarthritis classification tasks.Our experimental results verified that even without applying a separate methodology,the performance of the ensemble was comparable to that of existing studies that only used the latest deep learning model and changed the learning method.From the trained models,two ensembles were created and evaluated:weight and specialist.The weight ensemble showed an improvement in accuracy of 1%,and the proposed specialist ensemble improved accuracy,precision,recall,and F1 score by 5%,6%,6%,and 6%,respectively,compared with the results of prior studies.展开更多
Background: The proportion of never?smokers with non?small cell lung cancer(NSCLC) is increasing, but that in Korea has not been well addressed in a large population. We aimed to evaluate the proportion and clinical f...Background: The proportion of never?smokers with non?small cell lung cancer(NSCLC) is increasing, but that in Korea has not been well addressed in a large population. We aimed to evaluate the proportion and clinical features of never?smokers with NSCLC in a large single institution.Methods: We analyzed clinical data of 1860 consecutive patients who were newly diagnosed with NSCLC between June 2011 and December 2014.Results: Of the 1860 NSCLC patients, 707(38.0%) were never?smokers. The proportions of women(83.7% vs. 5.6%) and adenocarcinoma(89.8% vs. 44.9%) were higher among never?smokers than among ever?smokers. Significantly more never?smokers were diagnosed at a younger median age(65 vs. 68 years, P < 0.001) and earlier stage(stage I–II, 44.5% vs. 38.9%, P < 0.001) a= 0.015) compared with ever?smokers. Epidermal growth factor receptor mutations(57.8% vs. 24.4%, Pnd anaplastic lymphoma kinase rearrangements(7.8% vs. 2.8%, P < 0.001) were more common in never?smokers, whereas Kirsten rat sarcoma viral oncogene homolog mutations(5.8% vs. 9.6%, P ntly encountered in never?smokers than in ever?smokers. Never?smokers showed longer su= 0.021) were less frequervival after adjust?ing for the favorable effects of younger age, female sex, adenocarcinoma histology, better performance status, early stage disease, being asymptomatic at diagnosis, received antitumor treatment, and the presence of driver mutations(hazard ratio, 0.624; 95% confidence interval, 0.460–0.848; P = 0.003).Conclusions: More than one?third of the Korean patients with NSCLC were never?smokers. NSCLC in never?smokers had different clinical characteristics and major driver mutations and resulted in longer overall survival compared with NSCLC in ever?smokers.展开更多
The development of the fast tool servo (FTS) for precision machining was investigated.The micron machining performance of a piezoelectric-assisted FTS on copper alloy was evaluated.The results indicate that the qualit...The development of the fast tool servo (FTS) for precision machining was investigated.The micron machining performance of a piezoelectric-assisted FTS on copper alloy was evaluated.The results indicate that the quality of the microstructure depends mainly on two important factors:the cutting speed (or spindle speed) and the driving frequency of the FTS.The excessive driving frequency increases the formation of burrs.The effect of the clearance angle of the diamond tool on the microstructure machining precision was also investigated.展开更多
Ultra-precision diamond machining with piezoelectric-assisted fast tool servo (FTS) was used to produce various free-form surfaces.A low cost,rapid and large area fabrication of uniform hydrophobic surface at room tem...Ultra-precision diamond machining with piezoelectric-assisted fast tool servo (FTS) was used to produce various free-form surfaces.A low cost,rapid and large area fabrication of uniform hydrophobic surface at room temperature which transfers the FTS fabricated sinusoidal grid surface to the flat film with UV-moulding process was described.A piezoelectric-assisted FTS with high band width of 2 kHz,travel range up to 16 μm and the compact mechanism structure was designed for the sinusoidal grid surface machining and the dynamic performance testing of FTS was described in detail.Machining results indicate that the dimensions of sinusoidal grid change with the variation of the FTS machining condition.Wetting properties of UV-moulded surface were evaluated,the best contact angle was measured to be 120.5° on the sinusoidal grid surface with profile wavelength of 350 μm and peak-to-valley amplitude of about 16 μm.展开更多
BACKGROUND Delusional parasitosis is characterized by a false belief of being infested with parasites,insects,or worms.This illness is observed in patients with Parkinson’s disease and is usually related to dopaminer...BACKGROUND Delusional parasitosis is characterized by a false belief of being infested with parasites,insects,or worms.This illness is observed in patients with Parkinson’s disease and is usually related to dopaminergic treatment.To our knowledge,no cases of delusional parasitosis have been reported as a premotor symptom or nonmotor symptom of Parkinson’s disease.CASE SUMMARY A 75-year-old woman presented with a complaint of itching that she ascribed to the presence of insects in her skin,and she had erythematous plaques on her trunk,arms,buttocks,and face.These symptoms started two months before the visit to the hospital.She took medication,including antipsychotics,with a diagnosis of delusional parasitosis,and the delusion improved after three months.A year later,antipsychotics were discontinued,and anxiety and depression were controlled with medication.However,she complained of bradykinesia,masked face,hand tremor,and mild rigidity,and we performed fluorinated N-3-fluoropropyl-2β-carbomethoxy-3β-(4-iodophenyl)nortropane positron emission tomography(PET),which showed mildly decreased DAT binding in the right anterior putamen and caudate nucleus.Parkinson’s disease was diagnosed on the basis of PET and clinical symptoms.CONCLUSION In conclusion,delusional parasitosis can be considered a non-motor sign of Parkinson’s disease along with depression,anxiety,and constipation.展开更多
The entrapment behavior of Ar bubbles onto the solidifying front of molten steel in the continuous casting mold was investigated. The dynamic model of bubble and particle entrapment was developed in order to consider ...The entrapment behavior of Ar bubbles onto the solidifying front of molten steel in the continuous casting mold was investigated. The dynamic model of bubble and particle entrapment was developed in order to consider the effect of surface tension gradient induced forces(Marangoni force) due to the gradient of sulfur concentration and temperature. The numerical analysis and water model experiment were performed to apply the present model for various conditions. The calculation result is compared with experimental results and plant data in continuous casting mold as well. It shows that the thermal Marangoni force could play an important role and this model predicts the bubble behavior in the vicinity of solid/liquid interface more precisely.展开更多
基金This work was supported by the Kyonggi University Research Grant 2022.
文摘Recommendation Information Systems(RIS)are pivotal in helping users in swiftly locating desired content from the vast amount of information available on the Internet.Graph Convolution Network(GCN)algorithms have been employed to implement the RIS efficiently.However,the GCN algorithm faces limitations in terms of performance enhancement owing to the due to the embedding value-vanishing problem that occurs during the learning process.To address this issue,we propose a Weighted Forwarding method using the GCN(WF-GCN)algorithm.The proposed method involves multiplying the embedding results with different weights for each hop layer during graph learning.By applying the WF-GCN algorithm,which adjusts weights for each hop layer before forwarding to the next,nodes with many neighbors achieve higher embedding values.This approach facilitates the learning of more hop layers within the GCN framework.The efficacy of the WF-GCN was demonstrated through its application to various datasets.In the MovieLens dataset,the implementation of WF-GCN in LightGCN resulted in significant performance improvements,with recall and NDCG increasing by up to+163.64%and+132.04%,respectively.Similarly,in the Last.FM dataset,LightGCN using WF-GCN enhanced with WF-GCN showed substantial improvements,with the recall and NDCG metrics rising by up to+174.40%and+169.95%,respectively.Furthermore,the application of WF-GCN to Self-supervised Graph Learning(SGL)and Simple Graph Contrastive Learning(SimGCL)also demonstrated notable enhancements in both recall and NDCG across these datasets.
基金support of the Korea Research Foundation and was funded by the Ministry of Education of Korea in 2020 (No.2020R1A6A1A03040583)Kyonggi University’s Graduate Research Assistantship 2022.
文摘Artificial intelligence technologies are being studied to provide scientific evidence in the medical field and developed for use as diagnostic tools.This study focused on deep learning models to classify degenerative arthritis into Kellgren–Lawrence grades.Specifically,degenerative arthritis was assessed by X-ray radiographic images and classified into five classes.Subsequently,the use of various deep learning models was investigated for automating the degenerative arthritis classification process.Although research on the classification of osteoarthritis using deep learning has been conducted in previous studies,only local models have been used,and an ensemble of deep learning models has never been applied to obtain more accurate results.To address this issue,this study compared the classification performance of deep learning models,includingVGGNet,DenseNet,ResNet,TinyNet,EfficientNet,MobileNet,Xception,and ViT,on a dataset commonly used for osteoarthritis classification tasks.Our experimental results verified that even without applying a separate methodology,the performance of the ensemble was comparable to that of existing studies that only used the latest deep learning model and changed the learning method.From the trained models,two ensembles were created and evaluated:weight and specialist.The weight ensemble showed an improvement in accuracy of 1%,and the proposed specialist ensemble improved accuracy,precision,recall,and F1 score by 5%,6%,6%,and 6%,respectively,compared with the results of prior studies.
文摘Background: The proportion of never?smokers with non?small cell lung cancer(NSCLC) is increasing, but that in Korea has not been well addressed in a large population. We aimed to evaluate the proportion and clinical features of never?smokers with NSCLC in a large single institution.Methods: We analyzed clinical data of 1860 consecutive patients who were newly diagnosed with NSCLC between June 2011 and December 2014.Results: Of the 1860 NSCLC patients, 707(38.0%) were never?smokers. The proportions of women(83.7% vs. 5.6%) and adenocarcinoma(89.8% vs. 44.9%) were higher among never?smokers than among ever?smokers. Significantly more never?smokers were diagnosed at a younger median age(65 vs. 68 years, P < 0.001) and earlier stage(stage I–II, 44.5% vs. 38.9%, P < 0.001) a= 0.015) compared with ever?smokers. Epidermal growth factor receptor mutations(57.8% vs. 24.4%, Pnd anaplastic lymphoma kinase rearrangements(7.8% vs. 2.8%, P < 0.001) were more common in never?smokers, whereas Kirsten rat sarcoma viral oncogene homolog mutations(5.8% vs. 9.6%, P ntly encountered in never?smokers than in ever?smokers. Never?smokers showed longer su= 0.021) were less frequervival after adjust?ing for the favorable effects of younger age, female sex, adenocarcinoma histology, better performance status, early stage disease, being asymptomatic at diagnosis, received antitumor treatment, and the presence of driver mutations(hazard ratio, 0.624; 95% confidence interval, 0.460–0.848; P = 0.003).Conclusions: More than one?third of the Korean patients with NSCLC were never?smokers. NSCLC in never?smokers had different clinical characteristics and major driver mutations and resulted in longer overall survival compared with NSCLC in ever?smokers.
基金Project(2010-0008-277)supported by NCRC(National Core Research Center)Program of the Ministry of Education,Science and Technology,KoreaProject supported by"Development of Micro Feature Machining System on Large Surface and Core Technologies for Measurement & Inspection"of Ministry of Knowledge Economy,Korea
文摘The development of the fast tool servo (FTS) for precision machining was investigated.The micron machining performance of a piezoelectric-assisted FTS on copper alloy was evaluated.The results indicate that the quality of the microstructure depends mainly on two important factors:the cutting speed (or spindle speed) and the driving frequency of the FTS.The excessive driving frequency increases the formation of burrs.The effect of the clearance angle of the diamond tool on the microstructure machining precision was also investigated.
基金supported by NCRC(National Core Research Center)program of the Ministry of Education,Science and Technology(2010-0008-277)"Development of next generation multi-functional machining systems for eco/bio components" project of ministry of knowledge economy
文摘Ultra-precision diamond machining with piezoelectric-assisted fast tool servo (FTS) was used to produce various free-form surfaces.A low cost,rapid and large area fabrication of uniform hydrophobic surface at room temperature which transfers the FTS fabricated sinusoidal grid surface to the flat film with UV-moulding process was described.A piezoelectric-assisted FTS with high band width of 2 kHz,travel range up to 16 μm and the compact mechanism structure was designed for the sinusoidal grid surface machining and the dynamic performance testing of FTS was described in detail.Machining results indicate that the dimensions of sinusoidal grid change with the variation of the FTS machining condition.Wetting properties of UV-moulded surface were evaluated,the best contact angle was measured to be 120.5° on the sinusoidal grid surface with profile wavelength of 350 μm and peak-to-valley amplitude of about 16 μm.
文摘BACKGROUND Delusional parasitosis is characterized by a false belief of being infested with parasites,insects,or worms.This illness is observed in patients with Parkinson’s disease and is usually related to dopaminergic treatment.To our knowledge,no cases of delusional parasitosis have been reported as a premotor symptom or nonmotor symptom of Parkinson’s disease.CASE SUMMARY A 75-year-old woman presented with a complaint of itching that she ascribed to the presence of insects in her skin,and she had erythematous plaques on her trunk,arms,buttocks,and face.These symptoms started two months before the visit to the hospital.She took medication,including antipsychotics,with a diagnosis of delusional parasitosis,and the delusion improved after three months.A year later,antipsychotics were discontinued,and anxiety and depression were controlled with medication.However,she complained of bradykinesia,masked face,hand tremor,and mild rigidity,and we performed fluorinated N-3-fluoropropyl-2β-carbomethoxy-3β-(4-iodophenyl)nortropane positron emission tomography(PET),which showed mildly decreased DAT binding in the right anterior putamen and caudate nucleus.Parkinson’s disease was diagnosed on the basis of PET and clinical symptoms.CONCLUSION In conclusion,delusional parasitosis can be considered a non-motor sign of Parkinson’s disease along with depression,anxiety,and constipation.
文摘The entrapment behavior of Ar bubbles onto the solidifying front of molten steel in the continuous casting mold was investigated. The dynamic model of bubble and particle entrapment was developed in order to consider the effect of surface tension gradient induced forces(Marangoni force) due to the gradient of sulfur concentration and temperature. The numerical analysis and water model experiment were performed to apply the present model for various conditions. The calculation result is compared with experimental results and plant data in continuous casting mold as well. It shows that the thermal Marangoni force could play an important role and this model predicts the bubble behavior in the vicinity of solid/liquid interface more precisely.
