Add BrightSurf on Google Email

Beijing Zhongke Journal Publising Co. Ltd.


Evaluating the impact of database choice and confidence score on metagenomic taxonomic classification using Kraken2

The study evaluated the impact of database choice and confidence score on Kraken2's classification performance. Higher confidence scores generally decreased classification rates in smaller databases, while larger databases maintained higher rates and showed improved precision and F1 scores with increasing confidence.

Recent development of multimodal sentiment recognition and understanding

Researchers have made significant strides in multimodal sentiment recognition, leveraging self-supervised learning and large models to capture correlations between modalities and emotional information. The study emphasizes the importance of addressing data scarcity and exploring transfer learning methods to develop robust models.

SourceBeijing Zhongke Journal Publising Co. Ltd.·JournalJournal of Image and Graphics·DateJul 10, 2024

Unveiling the correlations between common triggers, comorbidities, and treatment approaches in Atopic Dermatitis patients

This nationwide study found that allergic rhinitis and hypertension are the most prevalent comorbidities among AD patients, while dietary triggers and seasonal changes exacerbate disease severity. The study also highlights the need for improved management strategies tackling these factors.

SourceBeijing Zhongke Journal Publising Co. Ltd.·JournalChinese Medical Journal·DateMay 30, 2024

Visible light-induced photocatalysis–self-Fenton degradation of P-Clphoh over graphitic carbon nitride by a polyethylenimine bifunctional catalyst

A novel bifunctional catalyst, Fe-PEI-CN, was synthesized to degrade p-chlorophenol through photocatalysis and Fenton reaction. The catalyst exhibited high photocatalytic activity due to enhanced light absorption and reduced electron-hole recombination.

SourceBeijing Zhongke Journal Publising Co. Ltd.·JournalTransactions of Tianjin University·DateMay 29, 2024

C-terminal frameshift mutations generate viable knockout mutants with developmental defects for three essential protein kinases

Researchers successfully generated viable and heritable knockout mutants for three essential protein kinases using CRISPR/Cas9 genome editing. These mutants displayed severe developmental defects and enhanced disease resistance, providing valuable resources for gene function studies and signaling network regulation.

Harnessing plant viruses for the delivery of genome editing reagents in diverse plant species

Genome editing holds promise for molecular breeding, but delivery methods are hindered by tissue culture processes. RNA and DNA viruses have been employed to overcome these challenges. Geminiviruses offer a high copy number for delivering repair donors, while new vector systems and compact nuclease delivery are being explored.

Acquiring weak annotations for tumor localization in temporal and volumetric data

Researchers propose a novel annotation strategy called Drag&Drop, which enables manual labeling based on a single 2D annotation in high-dimensional volumetric data. The proposed framework achieves a comparable tumor detection rate to per-pixel annotations and higher rates than alternative weak annotation strategies.

SourceBeijing Zhongke Journal Publising Co. Ltd.·JournalMachine Intelligence Research·DateMay 12, 2024

Selective sampling with Gromov–Hausdorff metric: Efficient dense-shape correspondence via Confidence-based sample consensus

This study introduces selective sampling with the Gromov–Hausdorff metric to improve dense-shape correspondence. It proposes a novel method that filters out unsatisfactory features during training and testing, improving alignment accuracy and reducing computation time.

SourceBeijing Zhongke Journal Publising Co. Ltd.·JournalVirtual Reality & Intelligent Hardware·DateApr 17, 2024

Personalized assessment and training of neurosurgical skills in virtual reality: An interpretable machine learning approach

This study investigates the potential of machine learning to identify skill levels of participants performing virtual reality neurosurgery. It also explores the interpretability of machine learning models to understand the performance of each metric for each participant.

SourceBeijing Zhongke Journal Publising Co. Ltd.·JournalVirtual Reality & Intelligent Hardware·DateApr 17, 2024

Exploring variational auto-encoder architectures, configurations, and datasets for generative music explainable AI

Researchers investigate how different VAE model architectures, latent space configurations, and training datasets impact the performance of generative music models with explainable features. They find that measureVAE has higher reconstruction accuracy but lower musical attribute independence.

SourceBeijing Zhongke Journal Publising Co. Ltd.·JournalMachine Intelligence Research·DateMar 27, 2024

Fusion of a rice endogenous N-methylpurine DNA glycosylase to a plant adenine base transition editor ABE8e enables A-to-K base editing in rice plants

Researchers developed four plant-based A-to-K base editors, rAKBEs, that enable simultaneous adenine transition and transversion base editing in rice. The rAKBEs, including rAKBE03 and rAKBE04, showed improved efficiency and capacity for different editing products.

A dual-function selection system enables positive selection of multigene CRISPR mutants and negative selection of Cas9-free progeny in Arabidopsis

A new dual-function selection system enables both positive selection of multigene CRISPR mutants and negative selection of Cas9-free progeny in Arabidopsis. This system leverages a DAO-based surrogate selection marker to facilitate efficient multiplex CRISPR editing in plants.

Different roles of two H3K36 methyltransferasesin transcriptional regulation and association with facultativeheterochromatin

Researchers identified two H3K36 methyltransferases, Ash1 and Set2, that regulate transcriptional activity and facultative heterochromatin formation in the rice blast fungus. The study reveals distinct roles for Ash1 and Set2 in promoting repressed and activated transcription, respectively.

Mining salt stress-related genes in Spartina alterniflora via analyzing coevolution signal across 365 plant species using phylogenetic profiling

Researchers developed a novel gene mining strategy using phylogenetic profiling and machine learning to identify salt stress-related genes in Spartina alterniflora. The study found that highly co-evolved genes were involved in ion transport, detoxification metabolism, and response to toxic substances.

Deep-reinforcement-learning-based robot motion strategies for grabbing objects from human hands

A new robot grasping algorithm based on deep reinforcement learning (RGRL) is proposed to safely grasp objects from users' hands. The algorithm incorporates domain randomization and a multi-objective reward function, eliminating the need for manual labeling of data and reducing computational costs.

SourceBeijing Zhongke Journal Publising Co. Ltd.·JournalVirtual Reality & Intelligent Hardware·DateDec 13, 2023