期刊,Robotics & Machine Learning Daily News 2024年卷Oct.9期_国家学术搜索

期刊信息/Journal information

Robotics & Machine Learning Daily News

NewsRx

主办单位：NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News

正式出版

收录年代

Findings in Robotics and Automation Reported from Harbin Institute of Technology (Neds-slam: a Neural Explicit Dense Semantic Slam Framework Using 3d Gaussian S platting)

1-2页

查看更多>>摘要：New research on Robotics - Robotics an d Automation is the subject of a report. According to news reporting out of Harb in, People's Republic of China, by NewsRx editors, research stated, "We propose NEDS-SLAM, a dense semantic SLAM system based on 3D Gaussian representation, tha t enables robust 3D semantic mapping, accurate camera tracking, and high-quality rendering in realtime. In the system, we propose a Spatially Consistent Featur e Fusion model to reduce the effect of erroneous estimates from pre-trained segm entation head on semantic reconstruction, achieving robust 3D semantic Gaussian mapping." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Youth Talent Support Program of the China.

原文链接:

NETL
NSTL

New Robotics Research from AMOLF Described (Bio-inspired autonomy in soft robots )

1-1页

查看更多>>摘要：Research findings on robotics are disc ussed in a new report. According to news reporting from AMOLF by NewsRx journali sts, research stated, "Soft robotic actuation concepts meet and sometimes exceed their natural counterparts." Financial supporters for this research include Ec | Horizon 2020 Framework Progr amme; This Work Is Part of The Dutch Research Council (Nwo) And Was Performed At The Research Institute Amolf.. Our news journalists obtained a quote from the research from AMOLF: "In contrast , artificially recreating natural levels of autonomy is still an unmet challenge . Here, we come to this conclusion after defining a measure of energy- and contr ol-autonomy and classifying a representative selection of soft robots. We argue that, in order to advance the field, we should focus our attention on interactio ns between soft robots and their environment, because in nature autonomy is also achieved in interdependence."

原文链接:

NETL
NSTL

Reports Outline Machine Learning Study Findings from Zhejiang University (Identi fication of Potent Cdk9 Inhibitors With Novel Skeletons Via Virtual Screening, B iological Evaluation, and Molecular Dynamics Simulation)

2-3页

查看更多>>摘要：2024 OCT 09 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Investigators publish new report on Machine Learn ing. According to news reporting originating from Hangzhou, People's Republic of China, by NewsRx correspondents, research stated, "Cyclin-dependent kinase 9 (C DK9) is a pivotal therapeutic target for acute myeloid leukemia (AML), a hematol ogic malignancy characterized by limited effective treatments. In this study, we introduced an innovative virtual screening strategy combines machine learning m odels with molecular docking techniques." Financial support for this research came from ICE Bioscience Inc.

原文链接:

NETL
NSTL

New Machine Learning Study Findings Reported from Chinese University of Hong Kon g (Gradient Descent Provably Escapes Saddle Points In the Training of Shallow Re lu Networks)

3-4页

查看更多>>摘要：Researchers detail new data in Machine Learning. According to news reporting out of Shenzhen, People's Republic of Chi na, by NewsRx editors, research stated, "Dynamical systems theory has recently b een applied in optimization to prove that gradient descent algorithms bypass so- called strict saddle points of the loss function. However, in many modern machin e learning applications, the required regularity conditions are not satisfied." Funders for this research include Eric and Wendy Schmidt AI in Science Postdocto ral Fellowship, European Union (ERC, MONTECARLO), German Research Foundation (DF G). Our news journalists obtained a quote from the research from the Chinese Univers ity of Hong Kong, "In this paper, we prove a variant of the relevant dynamical s ystems result, a center-stable manifold theorem, in which we relax some of the r egularity requirements. We explore its relevance for various machine learning ta sks, with a particular focus on shallow rectified linear unit (ReLU) and leaky R eLU networks with scalar input. Building on a detailed examination of critical p oints of the square integral loss function for shallow ReLU and leaky ReLU netwo rks relative to an affine target function, we show that gradient descent circumv ents most saddle points."

原文链接:

NETL
NSTL

Findings from Hainan Normal University Has Provided New Data on Machine Learning (Thermal and Electronic Properties of Borophene In Two-dimensional Lateral Grap hene-borophene Heterostructures Empowered By Machine-learning Approach)

4-5页

查看更多>>摘要：Researchers detail new data in Machine Learning. According to news reporting originating from Haikou, People's Republi c of China, by NewsRx correspondents, research stated, "Due to its electron-defi cient character and complicated banding mechanism, two-dimensional (2D) borophen e has gain more attentions recently. The polymorphism of 2D borophene provides m ore room for forming the 2D lateral heterostructures." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), China's Central Government Funds for Guiding Local Scientifi c and Technological Development Projects. Our news editors obtained a quote from the research from Hainan Normal Universit y, "However, the effects of confined circumstance on many properties of the boro phene are unknown. In this work, using first-principles calculations and molecul ar simulations based on the machine learning interatomic potential, we investiga ted the electronic structures and thermal properties of 2D lateral graphene-boro phene heterostructures (GBHs). We found that the graphene-borophene heterostruct ure promotes the thermal transport of borophene, and different concentrations of borophene hardly affect the lattice thermal conductivity of the interface. We a lso found the charge transfer induced thermal conductivity change in borophene d omain of GBH, compared with that of bulk borophene."

原文链接:

NETL
NSTL

Zhejiang Chinese Medical University Reports Findings in Stroke (Effect and optim al exercise prescription of robot-assisted gait training on lower extremity moto r function in stroke patients: a network meta-analysis)

5-6页

查看更多>>摘要：New research on Cerebrovascular Diseas es and Conditions - Stroke is the subject of a report. According to news reporti ng originating in Zhejiang, People's Republic of China, by NewsRx journalists, r esearch stated, "This study aimed to evaluate the effectiveness of robot-assiste d gait training (RAGT) and explore the optimal exercise prescription using a net work meta-analysis approach. A comprehensive search was conducted on randomized controlled trials comparing robotic and conventional rehabilitation published up to January 2024 in PubMed, Web of Science, Cochrane Library, Embase, CNKI, VIP, Wanfang, and SinoMed databases." The news reporters obtained a quote from the research from Zhejiang Chinese Medi cal University, "The evaluation parameters included Fugl-Meyer Assessment of Low er Extremity (FMA-LE), Functional Ambulation Category (FAC), Berg Balance Scale (BBS), and 6-Minute Walk Test (6MWT). Two investigators independently performed study screening, data extraction, and bias evaluation. Data were merged, analyze d, and plotted using Review Manager 5.4.1 and Stata 18.0 software. A total of 21 articles involving 822 subjects were included in the analysis. RAGT positively influenced FMA-LE score (MD = 3.74, 95 %CI 3.02-4.46, P<0.05), FAC score (MD = 0.31, 95%CI 0.1-0.53, P<0.05), BBS score (MD = 3.63, 95 %CI 2.46-4.80, P<0.05), and 6MWT score (MD = 23.73, 95%CI 15.31-32.14, P<0.05). Surface under the cumulative ranking curve (SUCRA) values indicated that an exercise time of 40-60 min/training (97.4 %), exercise frequency of 2-5 times/week (87.6%), and exercise duration of 8-12 weeks (78 .1%) were most effective in improving the FMA-LE score. RAGT can ef fectively improve lower limb motor function, walking function, balance function, and walking endurance in stroke patients."

原文链接:

NETL
NSTL

Researchers from Saveetha University Detail Findings in Machine Learning (Therma l Modeling and Machine Learning for Optimizing Heat Transfer In Smart City Infra structure Balancing Energy Efficiency and Climate Impact)

6-7页

查看更多>>摘要：Current study results on Machine Learn ing have been published. According to news reporting originating in Chennai, Ind ia, by NewsRx journalists, research stated, "The paper proposes a framework base d on deep learning, transfer learning, and multi-objective optimisation to model and optimise heat transfer in smart city infrastructure to make them energy eff icient and thermally comfortable. The framework in the paper contains a building thermal dynamics prediction model developed using hybrid CNN-LSTM on an extensi ve dataset (12.56 metric tonnes) of Indian buildings covering various characteri stics, which is then fine-tuned with data from five major Indian cities." Financial supporters for this research include Princess Nourah bint Abdulrahman University, Princess Nourah bint Abdulrahman University.

原文链接:

NETL
NSTL

Heart Institute (InCor) Reports Findings in Artificial Intelligence (Explainable artificial intelligence in deep learning-based detection of aortic elongation o n chest X-ray images)

7-8页

查看更多>>摘要：New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating in Sao Pau lo, Brazil, by NewsRx journalists, research stated, "Aortic elongation can resul t from age-related changes, congenital factors, aneurysms, or conditions affecti ng blood vessel elasticity. It is associated with cardiovascular diseases and se vere complications like aortic aneurysms and dissection." The news reporters obtained a quote from the research from Heart Institute (InCo r), "We assess qualitatively and quantitatively explainable methods to understan d the decisions of a deep learning model for detecting aortic elongation using c hest X-ray (CXR) images. In this study, we evaluated the performance of deep lea rning models (DenseNet and EfficientNet) for detecting aortic elongation using t ransfer learning and fine-tuning techniques with CXR images as input. EfficientN et achieved higher accuracy (86.7% 2.1), precision (82.7% 2.7), specificity (89.4% 1.7), F1 score (82.5% 2.9), and area under the receiver operating characteristic (92.7% 0.6) but lower sensitivity (82.3% 3.2) compared with DenseNet. To gain insights into the decision-making process of these models, we employed gradient- weighted class activation mapping and local interpretable model-agnostic explana tions explainability methods, which enabled us to identify the expected location of aortic elongation in CXR images. Additionally, we used the pixel-flipping me thod to quantitatively assess the model interpretations, providing valuable insi ghts into model behaviour. Our study presents a comprehensive strategy for analy sing CXR images by integrating aortic elongation detection models with explainab le artificial intelligence techniques."

原文链接:

NETL
NSTL

Study Results from Prince Mohammad Bin Fahd University Update Understanding of M achine Learning (Analyzing the effectiveness of Nields constraint and stratifica tion on dynamics of non-Newtonian fluid by executing numerical and machine learn ing ...)

8-9页

查看更多>>摘要：2024 OCT 09 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Investigators publish new report on artificial in telligence. According to news originating from Al-Khobar, Saudi Arabia, by NewsR x correspondents, research stated, "Stratified flows are commonly observed in nu merous industrial processes. For example, a gas-condensate pipeline typically us es a stratified flow regime." Funders for this research include European Commission. The news correspondents obtained a quote from the research from Prince Mohammad Bin Fahd University: "However, this flow arrangement is stable only under a spec ific set of operating conditions that allows the formation of stratification. In this study, the authors analyzed the flow attributes of Prandtl Eyring liquid p ast an inclined sheet immersed in a stratified medium. The flow also characteriz es the features of the magnetic field along with a first-order chemical reaction . Convective boundary constraints associated with the thermosolutal exchange at the extremity of the domain are also prescribed. The fundamental equations of th e study are formulated in dimensional PDEs and converted into dimensionless ODEs via similar variables. The numerical solution of the modelled setup is acquired by executing computations using shooting and RK-4 methods. The intelligent comp uting paradigm working on the mechanism of the back-propagated Levenberg-Marquar dt strategy is also capitalized to forecast the behavior of related physical qua ntities. Graphs and tables are drawn to elaborate the impression of pertinent fa ctors on flow distributions. It is perceived that the momentum profile diminishe s with the magnetic field effect, whereas the opposite behavior is observed for the skin friction coefficient."

原文链接:

NETL
NSTL

Findings in the Area of Artificial Intelligence Reported from Federal University Santa Catarina (Artificial Intelligence Applications In Dentistry a Bibliometri c Review With an Emphasis On Computational Research Trends Within the Field)

9-10页

查看更多>>摘要：Investigators publish new report on Ar tificial Intelligence. According to news reporting originating in Florianopolis, Brazil, by NewsRx journalists, research stated, "The aim of this study was to u nderstand the trends regarding the use of artificial intelligence in dentistry t hrough a bibliometric review. Types of Studies Reviewed." Financial supporters for this research include Coordenaco de Aperfeicoamento de Pessoal de Nivel Superior-Brazil, Conselho Nacional de Desenvolvimento Cientific o e Tecnologico (CNPQ). The news reporters obtained a quote from the research from Federal University Sa nta Catarina, "The authors performed a literature search on Web of Science. They collected the following data: articlesnumber and density of citations, year, k ey words, language, document type, study design, and theme (main objective, diag nostic method, and specialties); journals-impact factor; authors-country, contin ent, and institution. The authors used Visualization of Similarities Viewer soft ware (Leiden University) to analyze the data and Spearman test for correlation a nalysis. After selection, 1,478 articles were included. The number of citations ranged from 0 through 327. The articles were published from 1984 through 2024. M ost articles were characterized as proof of concept (979). Definition and classi fication of structures and diseases was the most common theme (550 articles). Th ere was an emphasis on radiology (333 articles) and radiographic-based diagnosti c methods (715 articles). China was the country with the most articles (251), an d Asia was the continent with the most articles (871). The Charit & eacute;-University of Medicine Berlin was the institution with the most articles (42), and the author with the most Practical Implications."

原文链接:

NETL
NSTL