Search

Your search keyword '"Shi, Liye"' showing total 150 results
Start Over Author "Shi, Liye"
150 results on '"Shi, Liye"'

1. A Personality-Guided Preference Aggregator for Ephemeral Group Recommendation

Author

Ye, Guangze, Wu, Wen, Shi, Liye, Hu, Wenxin, Chen, Xin, and He, Liang

Subjects
Computer Science - Information Retrieval
Abstract

Ephemeral group recommendation (EGR) aims to suggest items for a group of users who come together for the first time. Existing work typically consider individual preferences as the sole factor in aggregating group preferences. However, they neglect to take into account the importance of the individual inherent factors, such as personality, and thus fail to accurately simulate the group decision-making process. Additionally, these methods often struggle due to insufficient interactive records. To tackle these issues, a Personality-Guided Preference Aggregator (PEGA) is proposed, which guides the preference aggregation of group members based on their personalities, rather than relying solely on their preferences. Specifically, implicit personalities are first extracted from user reviews. Hyper-rectangles are then used to aggregate individual personalities to obtain the "Group Personality", which allows for the learning of personality distributions within the group. Subsequently, a personality attention mechanism is employed to aggregate group preferences, and a preference-based fine-tuning module is used to balance the weights of personality and preferences. The role of personality in this approach is twofold: (1) To estimate the importance of individual users in a group and provide explainability; (2) To alleviate the data sparsity issue encountered in ephemeral groups. Experimental results demonstrate that, on four real-world datasets, the PEGA model significantly outperforms related baseline models in terms of classification accuracy and interpretability. Moreover, empirical evidence supports the idea that personality plays a pivotal role in enhancing the performance of EGR tasks.

Published
2023
Full Text
View/download PDF

2. Self-Attentive Sequential Recommendation with Cheap Causal Convolutions

Author

Chen, Jiayi, Wu, Wen, Shi, Liye, Ji, Yu, Hu, Wenxin, Chen, Xi, Zheng, Wei, and He, Liang

Subjects
Computer Science - Information Retrieval
Abstract

Sequential Recommendation is a prominent topic in current research, which uses user behavior sequence as an input to predict future behavior. By assessing the correlation strength of historical behavior through the dot product, the model based on the self-attention mechanism can capture the long-term preference of the sequence. However, it has two limitations. On the one hand, it does not effectively utilize the items' local context information when determining the attention and creating the sequence representation. On the other hand, the convolution and linear layers often contain redundant information, which limits the ability to encode sequences. In this paper, we propose a self-attentive sequential recommendation model based on cheap causal convolution. It utilizes causal convolutions to capture items' local information for calculating attention and generating sequence embedding. It also uses cheap convolutions to improve the representations by lightweight structure. We evaluate the effectiveness of the proposed model in terms of both accurate and calibrated sequential recommendation. Experiments on benchmark datasets show that the proposed model can perform better in single- and multi-objective recommendation scenarios.

Published
2022

3. DACSR: Decoupled-Aggregated End-to-End Calibrated Sequential Recommendation

Author

Chen, Jiayi, Wu, Wen, Shi, Liye, Ji, Yu, Hu, Wenxin, Zheng, Wei, and He, Liang

Subjects
Computer Science - Information Retrieval
Abstract

Sequential recommendations have made great strides in accurately predicting the future behavior of users. However, seeking accuracy alone may bring side effects such as unfair and overspecialized recommendation results. In this work, we focus on the calibrated recommendations for sequential recommendation, which is connected to both fairness and diversity. On the one hand, it aims to provide fairer recommendations whose preference distributions are consistent with users' historical behaviors. On the other hand, it can improve the diversity of recommendations to a certain degree. But existing methods for calibration have mainly relied on the post-processing on the candidate lists, which require more computation time in generating recommendations. In addition, they fail to establish the relationship between accuracy and calibration, leading to the limitation of accuracy. To handle these problems, we propose an end-to-end framework to provide both accurate and calibrated recommendations for sequential recommendation. We design an objective function to calibrate the interests between recommendation lists and historical behaviors. We also provide distribution modification approaches to improve the diversity and mitigate the effect of imbalanced interests. In addition, we design a decoupled-aggregated model to improve the recommendation. The framework assigns two objectives to two individual sequence encoders, and aggregates the outputs by extracting useful information. Experiments on benchmark datasets validate the effectiveness of our proposed model.

Published
2022
Full Text
View/download PDF

8. Mitochondria-Rich Extracellular Vesicles Rescue Patient-Specific Cardiomyocytes From Doxorubicin Injury Insights Into the SENECA Trial

Author

O’Brien, Connor G, Ozen, Mehmet Ozgun, Ikeda, Gentaro, Vaskova, Evgeniya, Jung, Ji Hye, Bayardo, Nathan, Santoso, Michelle Rai, Shi, Liye, Wahlquist, Christine, Jiang, Zewen, Jung, Yunshin, Zeng, Yitian, Egan, Elizabeth, Sinclair, Robert, Gee, Adrian, Witteles, Ronald, Mercola, Mark, Svensson, Katrin J, Demirci, Utkan, and Yang, Phillip C

Subjects
Medical Biotechnology, Biomedical and Clinical Sciences, Cardiovascular, Regenerative Medicine, Clinical Research, Heart Disease, Stem Cell Research, Development of treatments and therapeutic interventions, 5.2 Cellular and gene therapies, anthracycline, cardiomyopathy, heart failure, AIC, anthracycline induced cardiomyopathy, DOX, doxorubicin, DZR, dexrazoxane, EV, extracellular vesicle, L-EV, large extracellular vesicle, MPP+, 1-methyl-4-phenylpyrindinium, MSC, mesenchymal stem cell, MSC-EV, mesenchymal stem cell derived extracellular vesicle, MTDR, MitoTracker Deep Red, MTG, MitoTracker Green, RBC, red blood cell, ROS, reactive oxygen species, S-EV, small extracellular vesicle, iCM, induced cardiomyocyte, Cardiovascular medicine and haematology, Oncology and carcinogenesis
Abstract

BackgroundAnthracycline-induced cardiomyopathy (AIC) is a significant source of morbidity and mortality in cancer survivors. The role of mesenchymal stem cells (MSCs) in treating AIC was evaluated in the SENECA trial, a Phase 1 National Heart, Lung, and Blood Institute-sponsored study, but the mechanisms underpinning efficacy in human tissue need clarification.ObjectivesThe purpose of this study was to perform an in vitro clinical trial evaluating the efficacy and putative mechanisms of SENECA trial-specific MSCs in treating doxorubicin (DOX) injury, using patient-specific induced pluripotent stem cell-derived cardiomyocytes (iCMs) generated from SENECA patients.MethodsPatient-specific iCMs were injured with 1 μmol/L DOX for 24 hours, treated with extracellular vesicles (EVs) from MSCs by either coculture or direct incubation and then assessed for viability and markers of improved cellular physiology. MSC-derived EVs were separated into large extracellular vesicles (L-EVs) (>200 nm) and small EVs (

Published
2021

12. PMAR: Multi-aspect Recommendation Based on Psychological Gap

Author

Shi, Liye, Wu, Wen, Ji, Yu, Feng, Luping, He, Liang, Goos, Gerhard, Founding Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Woeginger, Gerhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Bhattacharya, Arnab, editor, Lee Mong Li, Janice, editor, Agrawal, Divyakant, editor, Reddy, P. Krishna, editor, Mohania, Mukesh, editor, Mondal, Anirban, editor, Goyal, Vikram, editor, and Uday Kiran, Rage, editor

Published
2022
Full Text
View/download PDF

23. Abstract 14859: Mesenchymal Stem Cells Rescue Patient-Specific Cardiomyocyte Viability and Function Following Doxorubicin Injury via Microvesicle Mediated Mitochondrial Transfer to Recapitulate Human Clinical Trial Results

Author

OBrien, Connor G, Ozen, Mehmet O, Vaskova, Evgeniya, Jung, Jihye, Santoso, Michelle, Shi, Liye, Wahlquist, Christine A, Jiang, Zewen, Jung, Yunshin, Ikeda, Gentaro, Zeng, Yitian, Sinclair, Robert, Gee, Adrian, Witteles, Ronald M, Mercola, Mark, Svensson, Katrin, Demirci, Utkan, and Yang, Phillip C

Published
2020
Full Text
View/download PDF

26. The protease inhibitor E64d improves ox-LDL-induced endothelial dysfunction in human aortic endothelial cells

Author

Chen, Min, Ren, Lina, Meng, Yanyan, Shi, Liye, Chen, Ling, Yu, Bo, Wu, Qianqian, and Qi, Guoxian

Subjects
Atherosclerosis -- Prevention, Endothelium -- Diseases -- Physiological aspects, Protease inhibitors -- Physiological aspects, Cysteine -- Physiological aspects, Biological sciences
Abstract

Oxidized low-density lipoprotein (ox-LDL)-induced endothelial dysfunction in human vascular endothelial cells contributes to the development of atherosclerosis. E64d, a cysteine protease inhibitor, blocks the elastolytic activity of cathepsin essential for vascular matrix remodeling and reduces neurovascular endothelial apoptosis. The objective of this study was to investigate the effects and the underling mechanisms of E64d on ox-LDL-induced endothelial dysfunction in human aortic endothelial cells (HAECs). HAECs were treated with various concentrations of ox-LDL (0-200 mg/L) for 24 h with or without E64d. The results showed that E64d attenuated ox-LDL-induced increase in soluble intercellular adhesion molecule-1 (sICAM-1) concentration and reduction in endothelial nitric oxide synthase (eNOS) expression, prevented ox-LDL-induced reduction in cell viability and migration ability of HAECs. E64d decreased the protein expression of cathepsin B (CTSB), Beclin 1, and microtubuleassociated protein light chain 3 (LC3)-II, but not p62. LC3 puncta and autophagosome formation were also reduced by E64d in HAECs. Moreover, E64d decreased the production of MDA and increased the activity of SOD. The results showed that E64d ameliorated ox-LDL-induced endothelial dysfunction in HAECs. Key words: E64d, endothelial dysfunction, ox-LDL, autophagy, HAECs, atherosclerosis, oxidative stress. Le dysfonctionnement endothelial provoque par les lipoproteines de basse densite oxydees (ox-LDL) dans les cellules endotheliales vasculaires humaines contribue a la formation de l'atherosclerose. L'E64d, un inhibiteur de la cysteine protease, entraine une inhibition de l'activite elastolytique de la cathepsine essentielle au remodelage de la matrice vasculaire et l'attenuation de l'apoptose endotheliale neurovasculaire. Ces travaux avaient comme objectif d'etudier les effets et les modes d'action sous-jacents de l'E64d sur le dysfonctionnement endothelial provoque par les ox-LDL dans des cellules endotheliales d'aortes humaines (ou HAEC Pour << human aortic endothelial cells >>). Nous avons expose les HAEC a diverses concentrations d'ox-LDL (0 a 200 mg/L) pendant 24 h avec ou sans E64d. Les resultats ont montre que l'E64d attenuait l'augmentation des concentrations de molecule 1 d'adherence intercellulaire soluble (ou sICAM-1 pour << soluble intercellular adhesion molecule-1 >>) provoquee par les ox-LDL et la diminution de l'expression de l'oxyde nitrique synthase endotheliale (ou eNOS pour << endothelial nitric oxide synthase >>), prevenait la reduction de la viabilite des cellules provoquee par les ox-LDL et la capacite de migration des HAEC. L'E64d entrainait une diminution de l'expression proteique de cathepsine B (CTSB), de la proteine Becline 1 et de la proteine LC3-II (<< light chain 3 >>) associee aux microtubules, mais pas de la proteine p62. L'E64d entrainait aussi une diminution de la formation d'autophagosomes et de punctas de LC3 dans les HAEC. De plus, l'E64d entrainait une diminution de la production de MDA et une augmentation de l'activite de la SOD. Les resultats ont montre que l'E64d permettait d'attenuer le dysfonctionnement endothelial provoque par les ox-LDL dans les HAEC. [Traduit par la Redaction] Mots-cles: E64d, dysfonctionnement endothelial, ox-LDL, autophagie, HAEC, atherosclerose, stress oxydatif., Introduction Atherosclerosis, the leading cause of death and morbidity worldwide, is a disease characterized by imbalanced lipid metabolism and chronic inflammation (Weber and Noels 2011). Endothelial cells cover the inner [...]

Published
2018
Full Text
View/download PDF

29. PEGA: Personality-Guided Preference Aggregator for Ephemeral Group Recommendation

Author

Ye, Guangze, Wu, Wen, Shi, Liye, Hu, Wenxin, Chen, Xin, He, Liang, Ye, Guangze, Wu, Wen, Shi, Liye, Hu, Wenxin, Chen, Xin, and He, Liang

Abstract

Recently, making recommendations for ephemeral groups which contain dynamic users and few historic interactions have received an increasing number of attention. The main challenge of ephemeral group recommender is how to aggregate individual preferences to represent the group's overall preference. Score aggregation and preference aggregation are two commonly-used methods that adopt hand-craft predefined strategies and data-driven strategies, respectively. However, they neglect to take into account the importance of the individual inherent factors such as personality in the group. In addition, they fail to work well due to a small number of interactive records. To address these issues, we propose a Personality-Guided Preference Aggregator (PEGA) for ephemeral group recommendation. Concretely, we first adopt hyper-rectangle to define the concept of Group Personality. We then use the personality attention mechanism to aggregate group preferences. The role of personality in our approach is twofold: (1) To estimate individual users' importance in a group and provide explainability; (2) to alleviate the data sparsity issue that occurred in ephemeral groups. The experimental results demonstrate that our model significantly outperforms the state-of-the-art methods w.r.t. the score of both Recall and NDCG on Amazon and Yelp datasets.

Published
2023

32. Additional file 4 of Promoter hypermethylation analysis of host genes in cervical intraepithelial neoplasia and cervical cancers on histological cervical specimens

Author

Shi, Liye, Yang, Xue, He, Ling, Zheng, Chunying, Ren, Zhen, Warsame, Juweria Abdisamad, Suye, Suye, Yan, Lei, Cai, Haiyi, Xiao, Xiao, and Fu, Chun

Abstract

Additional file 4: Table S3. Intra-group comparison of GynTect® and ZNF671 methylation positive rate in cervical precancerous and cancerous lesions.

Published
2023
Full Text
View/download PDF

34. Additional file 2 of Promoter hypermethylation analysis of host genes in cervical intraepithelial neoplasia and cervical cancers on histological cervical specimens

Author

Shi, Liye, Yang, Xue, He, Ling, Zheng, Chunying, Ren, Zhen, Warsame, Juweria Abdisamad, Suye, Suye, Yan, Lei, Cai, Haiyi, Xiao, Xiao, and Fu, Chun

Abstract

Additional file 2: Table S1. The demographic characteristics of patients in cervical precancerous lesions and cervical cancer.

Published
2023
Full Text
View/download PDF

35. Additional file 5 of Promoter hypermethylation analysis of host genes in cervical intraepithelial neoplasia and cervical cancers on histological cervical specimens

Author

Shi, Liye, Yang, Xue, He, Ling, Zheng, Chunying, Ren, Zhen, Warsame, Juweria Abdisamad, Suye, Suye, Yan, Lei, Cai, Haiyi, Xiao, Xiao, and Fu, Chun

Abstract

Additional file 5: Table S4. Diagnosis performance of single methylation marker in GynTect® assay for detection of CIN2+ and CIN3+

Published
2023
Full Text
View/download PDF

41. Mitochondria-Rich Extracellular Vesicles Rescue Patient-Specific Cardiomyocytes From Doxorubicin Injury: Insights Into the SENECA Trial

Author

O'Brien, Connor G, Ozen, Mehmet Ozgun, Ikeda, Gentaro, Vaskova, Evgeniya, Jung, Ji Hye, Bayardo, Nathan, Santoso, Michelle Rai, Shi, Liye, Wahlquist, Christine, Jiang, Zewen, Jung, Yunshin, Zeng, Yitian, Egan, Elizabeth, Sinclair, Robert, Gee, Adrian, Witteles, Ronald, Mercola, Mark, Svensson, Katrin J, Demirci, Utkan, and Yang, Phillip C

Subjects
large extracellular vesicle, MSC-EV, MTDR, heart failure, red blood cell, S-EV, anthracycline, Cardiovascular, Regenerative Medicine, doxorubicin, RBC, MitoTracker Deep Red, iCM, MSC, MitoTracker Green, Clinical Research, AIC, small extracellular vesicle, mesenchymal stem cell, DOX, reactive oxygen species, induced cardiomyocyte, 5.2 Cellular and gene therapies, ROS, Stem Cell Research, dexrazoxane, anthracycline induced cardiomyopathy, L-EV, MPP+, Heart Disease, MTG, mesenchymal stem cell derived extracellular vesicle, DZR, extracellular vesicle, 1-methyl-4-phenylpyrindinium, Development of treatments and therapeutic interventions, cardiomyopathy, EV
Abstract

BackgroundAnthracycline-induced cardiomyopathy (AIC) is a significant source of morbidity and mortality in cancer survivors. The role of mesenchymal stem cells (MSCs) in treating AIC was evaluated in the SENECA trial, a Phase 1 National Heart, Lung, and Blood Institute-sponsored study, but the mechanisms underpinning efficacy in human tissue need clarification.ObjectivesThe purpose of this study was to perform an invitro clinical trial evaluating the efficacy and putative mechanisms of SENECA trial-specific MSCs in treating doxorubicin (DOX) injury, using patient-specific induced pluripotent stem cell-derived cardiomyocytes (iCMs) generated from SENECA patients.MethodsPatient-specific iCMs were injured with 1μmol/L DOX for 24 hours, treated with extracellular vesicles (EVs) from MSCs by either coculture or direct incubation and then assessed for viability and markers of improved cellular physiology. MSC-derived EVs were separated into large extracellular vesicles (L-EVs) (>200nm) and small EVs (

Published
2021

45. Efficacy of adjunctive azithromycin versus single-dose cephalosporin prophylaxis for caesarean scar defect: study protocol for a randomised controlled trial

Author

Cai, Yanqing, primary, Pan, Hongjie, additional, Zhang, Jian, additional, Cheng, Weiwei, additional, Shi, Yiru, additional, Zeng, Min, additional, Shi, Liye, additional, Yu, Jin, additional, Shen, Ying, additional, Chen, Shan, additional, Zhu, Qian, additional, Mol, Ben W, additional, and Huang, Ding, additional

Published
2020
Full Text
View/download PDF

46. Invasive versus conservative strategy in the very elderly with non‐ST‐elevation acute coronary syndrome: A meta‐analysis of randomized controlled trials.

Author

Wang, Haiyan, Shi, Liye, Tian, Wen, and Zhao, Shijie

Subjects
*TREATMENT of acute coronary syndrome, *ONLINE information services, *META-analysis, *MEDICAL information storage & retrieval systems, *MEDICAL databases, *INFORMATION storage & retrieval systems, *CONFIDENCE intervals, *STROKE, *OPERATIVE surgery, *SYSTEMATIC reviews, *MYOCARDIAL infarction, *TREATMENT effectiveness, *DESCRIPTIVE statistics, *MYOCARDIAL revascularization, *MEDLINE, *DEATH, *HEMORRHAGE, *OLD age, DISEASE relapse prevention
Abstract

Aim: To investigate the optimal treatment strategy in patients older than 80 years with non‐ST‐segment elevation acute coronary syndrome (NSTE‐ACS). Methods: All published randomized, placebo‐controlled trials (RCTs) reporting on comparisons between invasive and conservative strategies for patients aged 80 years or older with NSTE‐ACS were identified. The literature search was performed using PubMed, EMBASE, Cochrane Library, and the ISI Web of Science, from their establishment to July 2021 with no language restriction. The pooled risk ratios (RRs) with 95% confidence intervals (CI) for dichotomous outcomes were calculated. Results: Three RCTs involving a total of 893 cases met the inclusion criteria. Compared with the conservative group, the invasive strategy could significantly improve the incidence rate of composite endpoint (I2 = 21.9%; RR 0.727, 95% CI 0.619 to 0.855, P < 0.001), recurrent myocardial infarction (MI) (I2 = 0.0%; RR 0.585, 95% CI 0.441 to 0.776, P < 0.001) and revascularization (I2 = 0.0%; RR 0.239, 95% CI 0.126 to 0.455, P < 0.001). However, no benefits were observed on outcomes of all‐cause death (I2 = 0.0%; RR 0.888, 95% CI 0.681 to 1.160, P = 0.384), cardiac death (I2 = 0.0%; RR 0.769, 95% CI 0.412 to 1.433, P = 0.408) and stroke (I2 = 0.0%; RR 0.778, 95% CI 0.392 to 1.543, P = 0.473). The major bleeding events were comparable between the two groups (I2 = 0.0%; RR 1.582, 95% CI 0.622 to 4.025, P = 0.336). Conclusions: Compared with a conservative strategy, the invasive treatment could reduce the incidence of composite endpoint, recurrent MI, and revascularization in the very elderly with NSTE‐ACS. However, no benefits were observed on mortality. Geriatr Gerontol Int 2022; 22: 36–41. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results