期刊,Robotics & Machine Learning Daily News 2024年卷Oct.4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

Reports Outline Machine Learning Findings from Department of Electronic and Elec trical Engineering (A Rail Wheel Contact Temperature Prediction Model Using Fibe r Bragg Grating Sensor On Test Rig)

143-143页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on Machine Learning are discussed in a new report. According to news reporting originating from Beng aluru, India, by NewsRx correspondents, research stated, "The focus of this rese arch is the development of predictive models for temperature forecasting of rail wheel contact temperature through data collection from experimental setup with Single wheel test rig. Fibre sensing technology and the implementation of machin e learning techniques are used." Financial support for this research came from AICTE RPS. Our news editors obtained a quote from the research from the Department of Elect ronic and Electrical Engineering, "Our approach involves utilizing a dataset con taining crucial variables such as time, speed, weight, and sensor readings in or der to accurately predict temperature changes. To achieve this, we employ a thor ough preprocessing methodology that includes data cleansing, normalization, and feature selection, followed by the implementation of various machine learning al gorithms for regression tasks. The effectiveness of each model is evaluated usin g metrics like Mean Squared Error and R-squared. Experimental results reveal sig nificant findings, including a Linear Regression model with an R-squared value o f 0.9176, indicating it accounts for 91.76% of temperature variati on. Furthermore, Decision Tree and Random Forest models exhibit remarkable accur acy, achieving R-squared values of 0.999997 and 0.999995 respectively. Through e xtensive analysis and discussion, we gain insights into the strengths and limita tions of different models, ultimately identifying the most optimal approach for temperature prediction."

原文链接:

NETL
NSTL

Studies from San Diego State University Describe New Findings in Machine Learning (Separating Injection-driven and Earthquakedriven Induced Seismicity By Combi ning a Fully Coupled Poroelastic Model With Interpretable Machine Learning)

144-145页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating in San Diego, Cal ifornia, by NewsRx journalists, research stated, "In areas of induced seismicity,earthquakes can be triggered by stress changes due to fluid injection and stat ic deformation from fault slip. Here we present a method to distinguish between injection-driven and earthquake-driven triggering of induced seismicity by combi ning a calibrated, fully coupled, poroelastic stress model of wastewater injecti on with interpretation of a machine learning algorithm trained on both earthquak e catalog and modeled stress features." Funders for this research include National Science Foundation (NSF), San Diego S tate University, National Science Foundation (NSF).

原文链接:

NETL
NSTL

Sun Yat-Sen University Reports Findings in Hemodialysis (Interpretable machine l earning models for the prediction of all-cause mortality and time to death in he modialysis patients)

145-146页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Dialysis-Hemodialysi s is the subject of a report. According to news reporting originating in Shenzhe n, People's Republic of China, by NewsRx journalists, research stated, "The elev ated mortality and hospitalization rates among hemodialysis (HD) patients unders core the necessity for the development of accurate predictive tools. This study developed two models for predicting all-cause mortality and time to death-one us ing a comprehensive database and another simpler model based on demographic and clinical data without laboratory tests." The news reporters obtained a quote from the research from Sun Yat-Sen University, "A retrospective cohort study was conducted from January 2017 to June 2023. T wo models were created: Model A with 85 variables and Model B with 22 variables. We assessed the models using random forest (RF), support vector machine, and lo gistic regression, comparing their performance via the AU-ROC. The RF regression model was used to predict time to death. To identify the most relevant factors for prediction, the Shapley value method was used. Among 359 HD patients, the RF model provided the most reliable prediction. The optimized Model A showed an AU -ROC of 0.86 ± 0.07, a sensitivity of 0.86, and a specificity of 0.75 for predic ting all-cause mortality. It also had an R of 0.59 for predicting time to death. The optimized Model B had an AU-ROC of 0.80 ± 0.06, a sensitivity of 0.81, and a specificity of 0.70 for predicting all-cause mortality. In addition, it had an R of 0.81 for predicting time to death. Two new interpretable clinical tools ha ve been proposed to predict all-cause mortality and time to death in HD patients using machine learning models."

原文链接:

NETL
NSTL

Investigators from National Institute of Standards and Technology Release New Da ta on Robotics (Embodied Ai for Dexterity-capable Construction Robots: Dexbot Fr amework)

146-146页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Robotics have been published. According to news reporting from Boulder, Colorado, by NewsRx j ournalists, research stated, "The construction industry is integrating robots in to critical tasks at an accelerated pace, with the aim of enhancing efficiency, safety, and productivity. However, construction tasks requiring dexterity remain a challenge due to the need for precise movements, accurate perception, real-ti me decision-making, and a comprehensive understanding of the environment." Financial support for this research came from National Science Foundation (NSF). The news correspondents obtained a quote from the research from the National Ins titute of Standards and Technology, "To address these challenges, the introducti on of embodied artificial intelligence (AI) represents a significant shift in ro botic capabilities to enhance their alignment with the broader spectrum of const ruction settings. Rooted in cognitive science, embodied AI emphasizes the integr ation of an agent's physical form into its computational intelligence processes. It resembles how humans develop motor skills by interacting with physical world . This paper introduces DEXBOT, an exploratory framework for designing construct ion robots capable of high dexterity using embodied AI principles that mimics hu man strategies in complex tasks. The framework outlines six key perspectives for solving high-dexterity tasks with embodied AI: scene understanding, localizatio n and motion planning, position-based control, force-based control, sequence pla nning, and correction decision-making. By presenting preliminary test cases for each perspective, the paper emphasizes the role of embodied AI in advancing dext erity level of construction robots."

原文链接:

NETL
NSTL

Studies from Sun Yat-sen University Describe New Findings in Machine Learning (Flexible Artificial Tactility With Excellent Robustness and Temperature Tolerance Based On Organohydrogel Sensor Array for Robot Motion Detection and Object Shap e ...)

147-148页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on Machine Learning is now available. According to news reporting out of Guangzhou, People's Republic of C hina, by NewsRx editors, research stated, "Hydrogel-based flexible artificial ta ctility is equipped to intelligent robots to mimic human mechanosensory percepti on. However, it remains a great challenge for hydrogel sensors to maintain flexi bility and sensory performances during cyclic loadings at high or low temperatur es due to water loss or freezing." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from Sun Yat-sen Univers ity, "Here, a flexible robot tactility is developed with high robustness based o n organohydrogel sensor arrays with negligent hysteresis and temperature toleran ce. Conductive polyaniline chains are interpenetrated through a poly(acrylamide-co-acrylic acid) network with glycerin/water mixture with interchain electrostat ic interactions and hydrogen bonds, yielding a high dissipated energy of 1.58 MJ m-3, and ultralow hysteresis during 1000 cyclic loadings. Moreover, the binary solvent provides the gels with outstanding tolerance from -100 to 60 degrees C a nd the organohydrogel sensors remain flexible, fatigue resistant, conductive (0. 27 S m-1), highly strain sensitive (GF of 3.88) and pressure sensitive (35.8 MPa -1). The organohydrogel sensor arrays are equipped on manipulator finger dorsa a nd pads to simultaneously monitor the finger motions and detect the pressure dis tribution exerted by grasped objects. A machine learning model is used to train the system to recognize the shape of grasped objects with 100% acc uracy. The flexible robot tactility based on organohydrogels is promising for no vel intelligent robots. The robust and flexible artificial tactility enabled by a tough, low-hysteresis organohydrogel sensor array ensures precise detection of robot motion and external pressure over broad temperature range."

原文链接:

NETL
NSTL

New Robotics Data Have Been Reported by Investigators at Huazhong University of Science and Technology (Tool Path Correction for Robotic Deburring Using Local N on-rigid 3d Registration)

148-149页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on Ro botics. According to news reporting from Wuhan, People's Republic of China, by N ewsRx journalists, research stated, "The presence of residual burrs on the surfa ce of workpieces not only affects the surface quality but also reduces their per formance. The position and orientation of the cutting tool in the deburring proc ess are crucial for effective burr removal." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Natural Science Foundation of Hubei Province. The news correspondents obtained a quote from the research from the Huazhong Uni versity of Science and Technology, "Due to the interference caused by the burrs uncertainty or the manufacturing deformation, the off-line path from the workpie ce CAD model is difficult to ensure the processing quality in robotic deburring. To solve that, a correction strategy for the robotic deburring paths is develop ed based on a visual feedback model registration. Firstly, by applying CAM softw are, the nominal tool path is generated from the workpiece CAD model. Secondly, by conducting global rigid registration, followed by a local non -rigid registra tion with burr height constraint, the transformation matrix between the measurin g data and CAD model can precisely calculate to mitigate the impact of local sha pe deformations on registration precision. Finally, the actual tool path is obta ined by using the transformation matrix to correct the nominal tool path."

原文链接:

NETL
NSTL

Studies in the Area of Robotics Reported from Beihang University (Composite Dist urbance Filtering for Interaction Force Estimation With Online Environmental Sti ffness Exploration)

149-149页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on Robotics have been pr esented. According to news originating from Hangzhou, People's Republic of China,by NewsRx correspondents, research stated, "The primary focus of this article is the interaction force estimation of robotic manipulators with environmental s tiffness identification and exploration. This issue is particularly crucial in m inimally invasive surgery, where the interaction force between the end effector and the soft tissues needs to be estimated." Funders for this research include National Natural Science Foundation of China ( NSFC), Natural Science Foundation of Zhejiang Province, Defense Industrial Techn ology Development Program of China, Key Research and Development Program of Zhej iang Province. Our news journalists obtained a quote from the research from Beihang University, "Existing methods primarily focus on observer design, exploiting only the infor mation from the robot dynamics. To utilize more information, a unified force est imation framework is proposed in this article, where the robot dynamics and forc e generation model are simultaneously taken into account. Specifically, a robot- environment coupled system model is established by regarding the interaction for ce as a state-coupled disturbance of the robot system. Based on this, a separabi lity analysis for the interaction force is conducted. To cope with the unknown s tiffness parameter and stochastic uncertainties, a novel composite disturbance f iltering scheme is developed. An expectation-maximization-based environmental st iffness exploration force observer (EEFO) is constructed for simultaneous enviro nmental stiffness identification and interaction force estimation. The performan ce of the proposed EEFO is evaluated via numerical simulations and experimental tests on a surgical robot platform."

原文链接:

NETL
NSTL

Investigators from Tongji University Target Machine Learning (The Association Be tween Urban Density and Multiple Health Risks Based On Interpretable Machine Lea rning: a Study of American Urban Communities)

150-150页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning is th e subject of a report. According to news reporting originating from Shanghai, Pe ople's Republic of China, by NewsRx correspondents, research stated, "With the g rowing complexity in urban areas, cities have become unprecedentedly intricate s ystems. This paper aims to develop interpretable machine learning (ML) approache s to unravel the sophisticated associations." Financial supporters for this research include Peking University Lincoln Institu te Funds, Ministry of Housing and Urban-Rural Development Research Project, Shan ghai Rising-Star Program. Our news editors obtained a quote from the research from Tongji University, "In a case study of American urban communities, we apply interpretable ML methods to identify the associations between urban density and multiple health risks. We d efine urban density from three dimensions of population, built environment, and activity and measure multiple health risks based on categories of physical disea ses, mental diseases and health burden. Initially, we conduct cluster analysis t o control socioeconomic variables and select study samples. Then we build severa l ML models of multiple linear regression, decision trees, random forests, and e xtreme gradient boosting. Interpretable methods, including feature importance, p artial dependence plots, individual conditional expectations, and Shapley additi ve explanations, are used to interpret the models by identifying important facto rs, non-linear relationships, the interactions between variables. The results sh ow the advantages of interpretable ML methods in efficiency and transparency. Ou r findings verify that the associations between urban density and multiple healt h risks are complicated."

原文链接:

NETL
NSTL

Study Findings on Robotics Are Outlined in Reports from Northeast Forestry Unive rsity (Path Planning for Wall-Climbing Robots Using an Improved Sparrow Search A lgorithm)

151-151页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New study results on robotics have been published . According to news reporting from Harbin, People's Republic of China, by NewsRx journalists, research stated, "Traditional path planning algorithms typically f ocus only on path length, which fails to meet the low energy consumption require ments for wall-climbing robots in bridge inspection." Financial supporters for this research include Fundamental Research Funds For Th e Central Universities. The news correspondents obtained a quote from the research from Northeast Forest ry University: "This paper proposes an improved sparrow search algorithm based o n logistic-tent chaotic mapping and differential evolution, aimed at addressing the issue of the sparrow search algorithm's tendency to fall into local optima, thereby optimizing path planning for bridge inspection. First, the initial popul ation is optimized using logistic-tent chaotic mapping and refracted opposition- based learning, with dynamic adjustments to the population size during the itera tive process. Second, improvements are made to the position updating formulas of both discoverers and followers. Finally, the differential evolution algorithm i s introduced to enhance the global search capability of the algorithm, thereby r educing the robot's energy consumption."

原文链接:

NETL
NSTL

Investigators at Gdansk University of Technology Report Findings in Machine Lear ning (Machine-learning Methods for Estimating Compressive Strength of High-perfo rmance Alkali-activated Concrete)

151-152页

原文链接:

NETL
NSTL