Search

Your search keyword '"Lee, Beom-Jin"' showing total 813 results
Start Over Author "Lee, Beom-Jin"
813 results on '"Lee, Beom-Jin"'

10. Multi-focus Attention Network for Efficient Deep Reinforcement Learning

Author

Choi, Jinyoung, Lee, Beom-Jin, and Zhang, Byoung-Tak

Subjects
Computer Science - Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning
Abstract

Deep reinforcement learning (DRL) has shown incredible performance in learning various tasks to the human level. However, unlike human perception, current DRL models connect the entire low-level sensory input to the state-action values rather than exploiting the relationship between and among entities that constitute the sensory input. Because of this difference, DRL needs vast amount of experience samples to learn. In this paper, we propose a Multi-focus Attention Network (MANet) which mimics human ability to spatially abstract the low-level sensory input into multiple entities and attend to them simultaneously. The proposed method first divides the low-level input into several segments which we refer to as partial states. After this segmentation, parallel attention layers attend to the partial states relevant to solving the task. Our model estimates state-action values using these attended partial states. In our experiments, MANet attains highest scores with significantly less experience samples. Additionally, the model shows higher performance compared to the Deep Q-network and the single attention model as benchmarks. Furthermore, we extend our model to attentive communication model for performing multi-agent cooperative tasks. In multi-agent cooperative task experiments, our model shows 20% faster learning than existing state-of-the-art model., Comment: AAAI 2017 Workshop on What's next for AI in games (WNAIG 2017), 2017

Published
2017

12. Novel pH‐Responsive Structural Rearrangement of Myristic Acid‐Conjugated Quetiapine Nanosuspension for Enhanced Long‐Acting Delivery Performance.

Author

Nguyen, Hy Dinh, Ngo, Hai Van, and Lee, Beom‐Jin

Subjects
BEAGLE (Dog breed), INTRAMUSCULAR injections, PATIENT compliance, QUETIAPINE, PHARMACOKINETICS
Abstract

Quetiapine myristate (QM), an ester‐bonded lipophilic prodrug of quetiapine (QTP), is synthesized and converted into an amphiphilic structure in acidic pH to trigger a novel self‐assembled QM nanosuspension (QMN). Following injection, this QMN rearranges within physiological pH to form nanoaggregates in structure, resulting in enhanced physicochemical properties and in vivo therapeutic performance without an initial burst release. The 200‐nm‐sized QMN exhibits less invasive injection, higher drug content, and better storage stability profile than conventional poly(lactide‐co‐glycolide) (PLGA) nanosuspensions containing QTP or QM. Following a single intramuscular injection to beagle dogs (35 mg kg−1 QTP), QMN undergoes pH‐responsive nanoaggregation to form the lipophilic prodrug, providing esterase‐oriented sustained release for five weeks compared with the two‐week period of PLGA nanosuspensions. Notably, QMN exhibits improved in vivo pharmacokinetic performance with long‐acting delivery while minimizing issues associated with polymeric PLGA formulations, including the initial massive burst release, cellular toxicity, and adverse side effects. These results support the further development of QMN as a novel long‐acting injectable to improve patient compliance and dosing frequency. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

15. Human Body Orientation Estimation using Convolutional Neural Network

Author

Choi, Jinyoung, Lee, Beom-Jin, and Zhang, Byoung-Tak

Subjects
Computer Science - Robotics, Computer Science - Computer Vision and Pattern Recognition, Computer Science - Learning
Abstract

Personal robots are expected to interact with the user by recognizing the user's face. However, in most of the service robot applications, the user needs to move himself/herself to allow the robot to see him/her face to face. To overcome such limitations, a method for estimating human body orientation is required. Previous studies used various components such as feature extractors and classification models to classify the orientation which resulted in low performance. For a more robust and accurate approach, we propose the light weight convolutional neural networks, an end to end system, for estimating human body orientation. Our body orientation estimation model achieved 81.58% and 94% accuracy with the benchmark dataset and our own dataset respectively. The proposed method can be used in a wide range of service robot applications which depend on the ability to estimate human body orientation. To show its usefulness in service robot applications, we designed a simple robot application which allows the robot to move towards the user's frontal plane. With this, we demonstrated an improved face detection rate.

Published
2016

16. Effects of Postprandial Factors and Second Meal Intake Time on Bioequivalence Investigation of Tadalafil-Loaded Orodispersible Films in Human Volunteers.

Author

Park, Su-Jun, Gil, Myung-Chul, Lee, Bong-Sang, Jung, Minji, and Lee, Beom-Jin

Subjects
COMPUTATIONAL fluid dynamics, PATIENT compliance, GASTROINTESTINAL contents, POLYETHYLENE glycol, PARTICLE dynamics
Abstract

Tadalafil (TD) has poor water solubility but is well absorbed without affecting food intake when administered orally. Owing to patient adherence and therapeutic characteristics, a TD-loaded orodispersible film (TDF) is preferable. However, the mechanistic role of dietary status on the clinical pharmacokinetic analysis of TDF in human volunteers should be investigated because the gastrointestinal environment varies periodically according to meal intervals, although commercial 20 mg TD-loaded tablets (TD-TAB, Cialis® tablet) may be taken with or without food. TDF was prepared by dispersing TD in an aqueous solution and polyethylene glycol 400 to ensure good dispersibility of the TD particles. In the fasting state, each T/R of Cmax and AUC between TD-TAB and TDF showed bioequivalence with 0.936–1.105 and 1.012–1.153, respectively, and dissolution rates in 1000 mL water containing 0.5% SLS were equivalent. In contrast, TDF was not bioequivalent to TD-TAB under the fed conditions by the Cmax T/R of 0.610–0.798. The increased dissolution rate of TDF via the micronization of drug particles and the reduced viscosity of the second meal content did not significantly affect the bioequivalence. Interestingly, an increase in second meal intake time from 4 h to 6 h resulted in the bioequivalence by the Cmax T/R of 0.851–0.998 of TD-TAB and TDF. The predictive diffusion direction model for physical digestion of TD-TAB and TDF in the stomach after the first and second meal intake was successfully simulated using computational fluid dynamics modeling, accounting for the delayed drug diffusion of TDF caused by prolonged digestion of stomach contents under postprandial conditions. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

48. Transforming pharmaceutical education: A needs-based global analysis for policy development

Author

Afd Pharmacoepi & Clinical Pharmacology, Pharmacoepidemiology and Clinical Pharmacology, PECP - Centre for Pharmaceutical Policy and Regulation, Etukakpan, Alison, Uzman, Nilhan, Ozer, Ozge, Tofade, Toyin, Leite, Silvana Nair, Joda, Arinola, Choonara, Yahya, Mwila, Chiluba, Azzopardi, Lilian M., Mantel-Teeuwisse, Aukje K., Rahal, Mohammad, Darwish, Rula, Lee, Beom Jin, Shakya, Rajani, Gallagher, Paul J., Moreau, Pierre, Lourenço, Luis, McKinnon, Ross A., Altiere, Ralph J., Afd Pharmacoepi & Clinical Pharmacology, Pharmacoepidemiology and Clinical Pharmacology, PECP - Centre for Pharmaceutical Policy and Regulation, Etukakpan, Alison, Uzman, Nilhan, Ozer, Ozge, Tofade, Toyin, Leite, Silvana Nair, Joda, Arinola, Choonara, Yahya, Mwila, Chiluba, Azzopardi, Lilian M., Mantel-Teeuwisse, Aukje K., Rahal, Mohammad, Darwish, Rula, Lee, Beom Jin, Shakya, Rajani, Gallagher, Paul J., Moreau, Pierre, Lourenço, Luis, McKinnon, Ross A., and Altiere, Ralph J.

Published
2023

49. Roles of Fatty Acid Chain Length and Enzyme-Oriented Drug Controlled Release from pH-Triggering Self-Assembled Fatty Acid Conjugated Quetiapine Nanosuspensions

Author

Nguyen,Hy, Ngo,Hai, Nguyen,Van, Gil,Myung-Chul, Lee,Beom-Jin, Nguyen,Hy, Ngo,Hai, Nguyen,Van, Gil,Myung-Chul, and Lee,Beom-Jin

Abstract

Hy D Nguyen,1 Hai V Ngo,1 Van Hong Nguyen,2 Myung-Chul Gil,1,3 Beom-Jin Lee1,4 1College of Pharmacy, Ajou University, Suwon, 16499, Republic of Korea; 2Department of Life Sciences, University of Science and Technology of Hanoi, Vietnam Academy of Science and Technology, Hanoi, 10000, Vietnam; 3PLUTO Inc, Seongnam, 13453, Republic of Korea; 4Institute of Pharmaceutical Science and Technology, Ajou University, Suwon, 16499, Republic of KoreaCorrespondence: Beom-Jin Lee, College of Pharmacy, Ajou University, Suwon, 16499, Republic of Korea, Tel +82 31 219 3442, 3430, Fax +82 31 212 3653, Email bjl@ajou.ac.krBackground: Quetiapine (QTP) is a first-line antipsychotic drug, but its therapeutic druggability and patient adherence were limited due to high oral dose strength, low bioavailability and physicochemical/biopharmaceutical issues.Purpose: To investigate the roles of fatty acid chain length and enzyme-oriented QTP controlled release from pH-triggering self-assembled fatty acid conjugated QTP nanosuspensions (NSPs).Methods: QTP was conjugated with different chain length fatty acids (C10–decanoic acid, C14–myristic acid, C18–stearic acid) to obtain QTP-fatty acid conjugates (QFCs: QD, QM, QS) by exploiting 1-ethyl-3-(3-dimethylaminopropyl) carbodiimide/4-dimethylaminopyridine (EDC/DMAP) conjugation chemistry. Then, the solubility, partitioning coefficient (log P), cell viability and cleavage kinetics of QFCs were evaluated. The pH-triggering self-assembled behaviors of QFCs to form QTP-fatty acid NSPs (QDN, QMN, QSN) by varying pH, QFC concentration and proton-to-QTP ratios were characterized. The morphological images, critical micelle concentration (CMC), physicochemical properties and enzyme-oriented QTP controlled release of NSPs were examined.Results: Three QFCs were synthesized with different chain length fatty acids from QTP after desalting fumarate from QTP fumarate. The pH, QFC concentration and proton-to-quetiapine molar ratio could influence physicochem

Published
2023

50. Physicochemical and Biopharmaceutical Controllability of New Self-Assembled Fatty Acid Conjugated Leuprolide for the Enhanced Anticancer Activity

Author

Ngo,Hai V, Bak,Hye-Eun, Nguyen,Hy D, Lee,Kye Wan, Park,Chulhun, Lee,Beom-Jin, Ngo,Hai V, Bak,Hye-Eun, Nguyen,Hy D, Lee,Kye Wan, Park,Chulhun, and Lee,Beom-Jin

Abstract

Hai V Ngo,1 Hye-Eun Bak,1 Hy D Nguyen,1 Kye Wan Lee,2 Chulhun Park,3 Beom-Jin Lee1 1College of Pharmacy, Ajou University, Suwon, 16499 Republic of Korea; 2Dongkook Pharmaceutical Co., Ltd., Seoul, 06072 Republic of Korea; 3College of Pharmacy, Jeju National University, Jeju, 63243 Republic of KoreaCorrespondence: Beom-Jin Lee, College of Pharmacy, Ajou University, Suwon, 16499, Republic of Korea, Email bjl@ajou.ac.krBackground: Leuprolide (LEU), a synthetic nonapeptide analog of naturally occurring gonadotropin-releasing hormone (GnRH), could exert a direct inhibitory activity on the proliferation of prostate cancer cells. However, the short half-life in blood and the biopharmaceutical problem of LEU limit this anticancer activity.Purpose: To improve its druggability for improving anticancer activity, the amine-group targeted LEU was conjugated with different chain lengths of saturated fatty acids (FAs).Methods: LEU–fatty acid conjugates (LFCs) were synthesized by exploiting N-hydroxysuccinimidyl (NHS) conjugation chemistry. The physicochemical properties and the self-assembled behaviors of the conjugates were extensively investigated. The in vitro anticancer activity of three LFCs was extensively studied in both 2D monolayer and 3D spheroid culture models of a prostate cancer cell line, PC3.Results: Three LFCs could be readily self-assembled into nanoparticles (LFNs) with a small size of around 100 nm, positive charges, and exhibited greater permeability rates compared to the same concentration of LEU, excluding LSN. The chain length of FA in conjugate was positively related to the selectivity index between cancer cells and non-cancerous cell lines. All LFCs showed a superior direct antiproliferative effect on cancer cells in the following order: LSC (98.9%) > LPC (86.7%) > LLC (75.0%) > LEU (8.9%) after repeat daily of the same dose strength of LEU for 4 days. In addition, the 3D spheroid model study indicates that all LFCs with a one-time treatment per

Published
2023

Catalog

Books, media, physical & digital resources
See catalog results