Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Lee KM
A systematic review and unified multi-perspective conceptual synthesis of contemporary machine learning paradigms
1Department of Computer Science and Engineering, BRAC University, Dhaka, Bangladesh 2Sustainable Communication Technologies Department, SINTEF Digital, Oslo, Norway DOI 10.7717/peerj-cs.3905 Academic Editor Davide Chicco Subject Areas Algorithms and Analysis of Algorithms, Artificial Intelligence, Data Mining and Machine Learning, Data Science, Theory and Formal Methods Keywords Machine learning, Systematic literature review, Machine learning taxonomy, Learning paradigms, Deep learning,...
Robust visual tracking through hedging multiple features
Robust visual tracking through hedging multiple features 1School of Computer Science and Technology, Huaibei Normal University, Huaibei, Anhui, China 2Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, Zhejiang, China 3School of Science, Beijing University of Civil Engineering and Architecture, Beijing, China DOI 10.7717/peerj-cs.3851 Academic Editor Paulo Jorge Coelho Subject Areas Artificial Intelligence, Computer Vision, Robotics Keywords Visual tracking,...
Quantitative image analysis applied to revise the taxonomy of the Palearctic Earophila badiata species group (Lepidoptera: Geometridae: Larentiinae)
We compiled three datasets (wing morphology, genitalia morphology, molecular mtCOI) to examine the morphology and molecular variation within the E. badiata species group. A set of 72 dried and pinned adult specimens from the collections of the Finnish Museum of Natural History, University of Helsinki (coll. FMHM, 53 specimens) and the private research collection of Mikael Englund (coll. Englund, 19 specimens) were selected for a closer examination (Tables 1, S1).
Waist-to-height ratio, body fat, and macronutrient intake as predictors of lipid abnormalities in elite Turkish athletes: a comparative study
Waist-to-height ratio, body fat, and macronutrient intake as predictors of lipid abnormalities in elite Turkish athletes: a comparative study 1Department of Nutrition and Dietetics/Faculty of Health Sciences, Hacettepe University, Ankara, Turkey 2Department of Nutrition and Dietetics/Faculty of Health Sciences, Duzce University, Duzce, Turkey DOI 10.7717/peerj.20743 Academic Editor Gwyn Gould Subject Areas Biochemistry, Nutrition Keywords Athletes, Diet, Endurance exercise, Lipid profile,...
Comparison of the safety and efficacy of remimazolam for sedation during bronchoscopy: a meta-analysis of randomized controlled trials
This meta-analysis provides several novel contributions to the existing body of evidence. While previous reviews have established the general efficacy and safety of remimazolam, our study offers a more granular and contemporary synthesis specifically focused on bronchoscopy, directly comparing remimazolam against all three major sedative alternatives (propofol, dexmedetomidine, and midazolam) within a single analytical framework.
Dense symmetric temporal alignment learning for human pose estimation
Dense symmetric temporal alignment learning for human pose estimation 1Shenyang Aerospace University, Shenyang, China 2Jiushao Institute of AI Algorithm, Jihua Laboratory, Foshan, Guicheng, China DOI 10.7717/peerj-cs.3100 Academic Editor Syed Hassan Shah Subject Areas Artificial Intelligence, Data Mining and Machine Learning, Data Science Keywords Human pose estimation, Global-local symmetry learning, Symmetry feature alignment, Adaptive aggregation Copyright © Licence This is an open access...
Fishing operation type recognition based on multi-branch convolutional neural network using trajectory data
Fishing operation type recognition based on multi-branch convolutional neural network using trajectory data 1East China Sea Fisheries Research Institute, Chinese Academy of Fishery Sciences, Shanghai, China 2Shanghai Ocean University, Shanghai, China DOI 10.7717/peerj-cs.3020 Academic Editor Martina Iammarino Subject Areas Artificial Intelligence, Data Mining and Machine Learning, Spatial and Geographic Information Systems, Neural Networks Keywords Geohash, Vessel trajectory, Deep...
Intermittent horizontal mattress suture in proximal anastomosis for acute type A aortic dissection: a retrospective study
This study aimed to investigate the efficacy of the IHMS technique for proximal anastomosis in ATAAD. The results suggest that the IHMS technique may offer advantages over the sandwich technique in terms of operative time, duration of proximal anastomosis, extent of cardiopulmonary bypass, intraoperative bleeding and blood transfusion, spontaneous heartbeat recovery, and durations of ventilator use, delirium, and hospital stay.
Analysis of biopsies of gastric cancer, intestinal and diffuse, and non-atrophic gastritis: an overview of loss of heterozygosity in Mexican patients
Violeta Larios-Serrato conceived and designed the experiments, analyzed the data, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft. Hilda A. Valdez-Salazar performed the experiments, analyzed the data, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft. Javier Torres performed the experiments, authored or reviewed drafts of the article, and approved the final draft.
Gradient pooling distillation network for lightweight single image super-resolution reconstruction
Gradient pooling distillation network for lightweight single image super-resolution reconstruction School of Electronics and Information Engineering, Wuyi University, Jiangmen City, Guangdong, China DOI 10.7717/peerj-cs.2679 Academic Editor Paulo Jorge Coelho Subject Areas Artificial Intelligence, Computer Vision Keywords Image super-resolution, Computational photography, Image processing Copyright © Licence This is an open access article distributed under the terms of the Creative Commons...
Edge and texture aware image denoising using median noise residue U-net with hand-crafted features
The technique of image denoising involves taking out noise from a source image, which is essential for enhancing image quality in a variety of applications. As y = x + v, where v is additive white Gaussian noise (AWGN) with a standard deviation of sigma, the objective is to recover a clean image (x) from a noisy observation (y). Numerous strategies have been devised to tackle this issue.
Using a natural capital risk register to support the funding of seagrass habitat enhancement in Plymouth Sound
Using a natural capital risk register to support the funding of seagrass habitat enhancement in Plymouth Sound 1School of Biological and Marine Science, University of Plymouth, Plymouth, Devon, United Kingdom 2Tamar Estuaries Consultative Forum, Plymouth, Devon, United Kingdom 3Plymouth City Council, Plymouth, Devon, United Kingdom 4Ocean Conservation Trust, Plymouth, Devon, United Kingdom 5BeZero Carbon, London, United Kingdom DOI 10.7717/peerj.17969 Academic Editor Gregory Verutes Subject...
Pulsed sounds caused by internal oxygen transport during photosynthesis in the seagrass Halophila ovalis
Portions of this text were previously published as part of a preprint (https://doi.org/10.1101/2024.05.14.594143). Dugong (spoon) grass, Halophila ovalis (Hydrocharitaceae) was studied because of its small size compared with other seagrasses in Taiwanese waters and its accessibility for experimentation (Fig. 1A). It occurs in the Indo-Pacific region (Kuo, 2020) and is abundant in Qitou Bay (23°38′55″N 119°36′19″E) Penghu Islands (Fig. 1B).
Single-image super-resolution reconstruction based on phase-aware visual multi-layer perceptron (MLP)
Super-resolution reconstruction is a fundamental task in the field of image processing, aiming to recover high-resolution details from low-resolution ones to enhance image quality and detail presentation. In practical applications, super-resolution reconstruction holds significant importance in areas such as image enhancement, video compression, medical image processing and surveillance.
The real-time hand and object recognition for virtual interaction
In recent years, the rapid advancement of immersive technologies has revolutionized the way humans interact with virtual environments. A fundamental aspect enhancing this interaction is real-time hand and object recognition, crucial for fostering natural and intuitive information exchange. The development of virtual and augmented realities has expanded the scope of virtual interaction beyond traditional human–computer interfaces, enabling users to interact with digital content in unique ways.
A novel approach to recognition of Alzheimer’s and Parkinson’s diseases: random subspace ensemble classifier based on deep hybrid features with a super-resolution image
A novel approach to recognition of Alzheimer’s and Parkinson’s diseases: random subspace ensemble classifier based on deep hybrid features with a super-resolution image Department of Computer Science, College of Computer Engineering and Sciences in Al-kharj, Prince Sattam Bin Abdulaziz University, Al-kharj, Saudi Arabia DOI 10.7717/peerj-cs.1862 Academic Editor Shibiao Wan Subject Areas Artificial Intelligence, Computer Vision, Data Mining and Machine Learning, Data Science, Neural Networks...
A hybrid attention network with convolutional neural network and transformer for underwater image restoration
With the progressive acceleration of marine resource exploration and study as well as the promotion of strategic analysis of ocean development, humanity has just entered a phase of extensive ocean development and use. In the fields of marine energy exploration, marine environmental protection, and marine species analysis, underwater images contain a large amount of visual information about marine resources and are an important carrier for people to observe and explore the ocean.
Improved deep learning image classification algorithm based on Swin Transformer V2
Improved deep learning image classification algorithm based on Swin Transformer V2 1College of Information Engineering, Sichuan Agricultural University, Ya’an, Sichuan, China 2College of Mechanical and Electrical Engineering, Sichuan Agricultural University, Ya’an, Sichuan, China DOI 10.7717/peerj-cs.1665 Academic Editor Jyotismita Chaki Subject Areas Artificial Intelligence, Computer Vision, Data Mining and Machine Learning, Neural Networks Keywords Image classification, Convolutional neural...
Random pruning: channel sparsity by expectation scaling factor
Random pruning: channel sparsity by expectation scaling factor 1North University of China, State Key Laboratory of Dynamic Measurement Technology, Taiyuan, Shanxi, China 2North University of China, School of Electrical and Control Engineering, Taiyuan, Shanxi, China 3Chongqing University, State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing, China DOI 10.7717/peerj-cs.1564 Academic Editor Arun Somani Subject Areas Artificial Intelligence, Computer Vision, Neural Networks...
Recognition of opinion leaders in blockchain-based social networks by structural information and content contribution
The centralized social networks have problems such as data privacy leakage and unrestricted spreading of fake news, which greatly violate user privacy security and affect their ability to discern information (Cadwalladr & Graham-Harrison, 2018).
A federated learning framework based on transfer learning and knowledge distillation for targeted advertising
Introduction The emergence of the internet has revolutionized the landscape of advertising, offering an unprecedented speed and reach for delivering promotions to a global audience (Liu et al., 2019). As compared to traditional mediums, internet advertising boasts higher interactivity and visual appeal, making it a favored tool among marketers.
Protein arginine methyltransferase 5 (PRMT5) is an actionable therapeutic target in CDK4/6 inhibitor-resistant ER+/RB-deficient breast cancer
This is a preprint. It has not yet been peer reviewed by a journal. The National Library of Medicine is running a pilot to include preprints that result from research funded by NIH in PMC and PubMed. Res Sq. Display options Format doi: 10.21203/rs.3.rs-2966905/v1. Preprint PMID: 37502925 PMCID: PMC10371097 DOI: 10.21203/rs.3.rs-2966905/v1 Item in Clipboard Display options Abstract CDK4/6 inhibitors (CDK4/6i) have improved survival of patients with estrogen receptor-positive (ER+) breast cancer.
Developing and Evaluating Deep Learning Algorithms for Object Detection: Key Points for Achieving Superior Model Performance
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
A genetically supported drug repurposing pipeline for diabetes treatment using electronic health records
doi: 10.1016/j.ebiom.2023.104674. Online ahead of print. Affiliations Affiliations 1 Division of Genetic Medicine, Department of Medicine, Vanderbilt University Medical Center, Nashville, TN, USA; Vanderbilt Genetics Institute, Vanderbilt University Medical Center, Nashville, TN, USA. 2 VA Informatics and Computer Infrastructure, VA Salt Lake City Health Care System, Salt Lake City, UT, USA.
Clinical Outcomes of Calcium-Channel Blocker vs Beta-Blocker: From the Korean Acute Myocardial Infarction Registry
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
Integration of statistical shape modeling and alternating interpolation-based model tracking technique for measuring knee kinematics in vivo using clinical interleaved bi-plane fluoroscopy
Discussion The current study aimed to evaluate in vivo the accuracy of 3D skeletal kinematics of the knee obtained using a validated AIMT technique for 2D interleaved fluoroscopy/3D model-based image registration (Lin et al., 2020) with SSM-reconstructed bone models from asynchronous fluoroscopy images (Lu et al., 2021) and to quantify the effects of the number of the asynchronous fluoroscopic image pairs on the kinematic measurement accuracy.
Improvement in Radiative Efficiency Via Intramolecular Charge Transfer in ortho-Carboranyl Luminophores Modified with Functionalized Biphenyls
Skip to main page content Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software doi: 10.1021/acs.inorgchem.3c01242. Online ahead of print.
Agent Orange exposure and prostate cancer risk in the Million Veteran Program
This is a preprint. It has not yet been peer reviewed by a journal. The National Library of Medicine is running a pilot to include preprints that result from research funded by NIH in PMC and PubMed. Display options Abstract Purpose: Exposure to Agent Orange, a known carcinogen, might increase risk of prostate cancer (PCa).
Retrospective study of transcriptomic profiling identifies Thai triple-negative breast cancer patients who may benefit from immune checkpoint and PARP inhibitors
Discussion The aggressive TNBC is attributed to approximately 15% of breast cancer cases in Thailand, also diagnosed at a younger age than other populations (Ding et al., 2019; Niyomnaitham et al., 2019). Current treatments for all TNBC patients are similar, mainly relying on anthracycline- and taxane-based chemotherapy, despite known heterogeneity within the tumor and between patients.
Role of Dual-Acquisition Noninvasive Cardiac CT Imaging for the Detection of Vasospastic Angina
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
The Multifunctional Protein Syntenin-1: Regulator of Exosome Biogenesis, Cellular Function, and Tumor Progression
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
Statin therapy reduces dementia risk in atrial fibrillation patients receiving oral anticoagulants
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
High radiative efficiency based on intramolecular charge transfer in a 9,9'-bianthracene- ortho-carboranyl luminophore
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
Reconstructing 3D human pose and shape from a single image and sparse IMUs
Comparisons with fusion-based methods As mentioned above, the work on fusing sparse IMUs and a single-view camera is hardly addressed in the community. To provide a reference of our approach to other methods, the experiment follows the protocol of train and test partitions introduced by Trumble et al. (2017) on the Total Capture dataset. The comparison is regardless of the same number of IMUs or multiple viewpoints and employs the MPJPE in mm as the evaluation metric.
Upregulation of the ERRγ-VDAC1 axis underlies the molecular pathogenesis of pancreatitis
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
Few-shot short utterance speaker verification using meta-learning
Author Contributions Weijie Wang conceived and designed the experiments, performed the experiments, analyzed the data, performed the computation work, prepared figures and/or tables, authored or reviewed drafts of the article, and approved the final draft. Hong Zhao conceived and designed the experiments, analyzed the data, authored or reviewed drafts of the article, and approved the final draft.
Adaptive visual detection of industrial product defects
Introduction Industrial surface defect detection is intuitively important for industrial production, which can not only help enterprises to improve product quality to meet the growing needs of consumers, but also help enterprises to locate problems in a timely manner to reduce production costs (Xiao et al., 2021). Only relying on human power to complete visual inspection cannot guarantee efficient industrial production requirements.
A super-resolution network using channel attention retention for pathology images
Related Work As mentioned in the previous section, Ledig et al. (2017) used residual structures in SRGAN for the first time and built the SRResNet as their network’s generator. The SRResNet enables the network to support the inpainting of higher frequency image details, compensating the decrease in objective metrics caused by SRGAN’s perceptual loss.
Hospital-Based Health Care Worker Perceptions of Personal Risk Related to COVID-19
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
Spatial distribution of elements during osteoarthritis disease progression using synchrotron X-ray fluorescence microscopy
Save citation to file Format: Add to My Bibliography Your saved search Name of saved search: Search terms: Frequency: Which day? Which day? Report format: Send at most: Send even when there aren't any new results Optional text in email: Create a file for external citation management software
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Lee
Contact Lee, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack