首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    Study Data from Hokkaido University Update Knowledge ofRobotics (Development of Assistance Level Adjustment Functionfor Variable Load on a Forearm-Supported R obotic Walker)

    11-11页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews – Research findings on robotics are discussed in a new report. According to news originating fromSapporo, Japan, by NewsRx corresp ondents, research stated, “With the progression of an aging society,the importa nce of walking assistance technology has been increasing.”Funders for this research include Jst Spring.The news journalists obtained a quote from the research from Hokkaido University : “The researchand development of robotic walkers for individuals requiring wal king support are advancing. However,there was a problem that the conventional c onstant support amount did not satisfy the propulsion forcerequired for the wal king speed that users wanted. In this study, in order to solve this problem, we proposean algorithm for determining the support amount to maintain the walking speed when the average walkingspeed of each user is set as the target speed. A robotic walker was developed by attaching BLDC motorsto an actual walker, along with a control algorithm for assistance based on sampling-type PID control.The effectiveness of the assistance determination algorithm and the usefulness of t he parameters weredemonstrated through experiments using weights loaded on the forearm support and target speeds.”
      原文链接:
    • NETL
    • NSTL

    Findings from China Iron and Steel Research Institute GroupBroaden Understandin g of Machine Learning (Prediction of OpticalProperties of Oxide Glass Combined With Autoencoder andMachine Learning)

    12-12页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Fresh data on Machine Learning are pre sented in a new report. According to newsoriginating from Beijing, People’s Rep ublic of China, by NewsRx correspondents, research stated, “Thecomposition of o xide glasses is characterized by high dimensionality and sparsity, making it cha llengingto establish high-precision predictive models. Therefore, feature extra ction is essential.”Financial support for this research came from National Key Research & Development Program of China.Our news journalists obtained a quote from the research from China Iron and Stee l Research InstituteGroup, “This study focuses on the optical properties of oxi de glasses (refractive index and Abbe number),utilizing autoencoder (AE) and ma chine learning techniques to achieve automated feature extraction.The results i ndicate that compared to standalone neural networks (NN), AE-NN transforms unsup ervisedlearning into supervised learning, reducing feature dimensions while imp roving model accuracy. Specifically,for the refractive index dataset, the dimen sionality was reduced from 63 to 25, with a corresponding testset coefficient o f determination (R2) of 0.95. For the Abbe number dataset, the dimensionality wa sreduced from 61 to 30, with a corresponding test set R2 of 0.97, demonstrating the effectiveness of thefeature extraction method. Regarding interpretability, analyzing the encoder weight matrix of the AE-NNidentified the importance of o riginal features, with Co and Y being the most significant for both refractivei ndex and Abbe number. Additionally, the application of the feature extraction me thod in machinelearning models shows its generality in improving model performa nce, particularly for nonensemble modelssuch as Support Vector Regression (SVR) or k-Nearest Neighbors (KNN), exhibiting significant accuracyenhancements.”
      原文链接:
    • NETL
    • NSTL

    Study Results from National Water Research Center Broaden Understandingof Machi ne Learning (An Integrated Machine LearningApproach for Evaluating Critical Suc cess Factors InfluencingProject Portfolio Management Adoption In the Constructi on ...)

    13-13页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Current study results on Machine Learn ing have been published. According to newsreporting from Alexandria, Egypt, by NewsRx journalists, research stated, “PurposeIn today’s intricate anddynamic co nstruction sector, traditional project management techniques, which view project s in isolation,are no longer sufficient. Project Portfolio Management (PPM) has proven to be an efficient alternativesolution for handling multiple constructi on projects.”Financial support for this research came from Umm Al Qura University.The news correspondents obtained a quote from the research from National Water R esearch Center,“As such, based on a Machine Learning (ML) approach, this study aims to explore the Critical SuccessFactors (CSFs) influencing the adoption of PPM, Afterward, exploratory data analysis is conducted to understandCSF-PPM relationships. Preprocessing techniques ensure uniformity in variable m agnitudes. Lastly,ML techniques, namely Linear Discriminant Analysis (LDA), Log istic Regression (LR) and Extra TreesClassifier (ETC) are developed to model an d investigate CSFs’ impact on PPM adoption.FindingsThefindings pointed out that the ETC model marginally outperforms other ML models with a classificationaccu racy of 93%.”
      原文链接:
    • NETL
    • NSTL

    Harbin Institute of Technology Researcher Highlights Research inRobotic Systems (A fast collision detection method based on pointclouds and stretched primitiv es for manipulator obstacle-avoidancemotion planning)

    14-14页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators publish new report on ro botic systems. According to news originatingfrom Harbin, People’s Republic of C hina, by NewsRx correspondents, research stated, “It is essentialto efficiently perform collision detection for robotic manipulators obstacle-avoidance plannin g. Existingmethods are excellent when manipulator links are simple and obstacle s are convex.”Financial supporters for this research include Natural Science Foundations of Ch ina; Yunnan PowerGrid Company.The news reporters obtained a quote from the research from Harbin Institute of T echnology: “Butthey cannot keep the accuracy and the efficiency at the same tim e when manipulator links or obstaclesare nonconvex. To decrease the computing t ime and keep a high accuracy, this article presents a collisiondetection method based on point clouds and stretched primitives (PCSP). In traditional methods, obstaclesare often represented either by a convex body or enormous amounts of p oints. But this needs a trade-offbetween the accuracy and the computing time wh en obstacles are concave. In the proposed method, werepresent obstacles and com plex manipulator links as stretched geometric bodies while simple manipulatorli nks are enclosed by capsules with different sizes. The stretched body is constru cted by the original pointcloud from sensors but it only requires a small numbe r of points to approximate the original object.”
      原文链接:
    • NETL
    • NSTL

    Capital Medical University Reports Findings in Stroke (Predicting 3-month poor f unctional outcomes of acute ischemic stroke in youngpatients using machine lear ning)

    15-15页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – New research on Cerebrovascular Diseas es and Conditions - Stroke is the subject ofa report. According to news reporti ng from Beijing, People’s Republic of China, by NewsRx journalists,research sta ted, “Prediction of short-term outcomes in young patients with acute ischemic st roke (AIS)may assist in making therapy decisions. Machine learning (ML) is incr easingly used in healthcare due toits high accuracy.”The news correspondents obtained a quote from the research from Capital Medical University, “Thisstudy aims to use a ML-based predictive model for poor 3-month functional outcomes in young AIS patientsand to compare the predictive perform ance of ML models with the logistic regression model. We enrolledAIS patients a ged between 18 and 50 years from the Third Chinese National Stroke Registry (CNS R-III),collected between 2015 and 2018. A modified Rankin Scale (mRS) 3 was a p oor functional outcome at 3months. Four ML tree models were developed: The extr eme Gradient Boosting (XGBoost), Light GradientBoosted Machine (lightGBM), Rand om Forest (RF), and The Gradient Boosting Decision Trees (GBDT),compared with l ogistic regression. We assess the model performance based on both discrimination andcalibration. A total of 2268 young patients with a mean age of 44.3 ± 5.5 y ears were included. Amongthem, (9%) had poor functional outcomes. The mRS at admission, living alone conditions, and highNational Institutes of H ealth Stroke Scale (NIHSS) at discharge remained independent predictors of poor3-month outcomes. The best AUC in the test group was XGBoost (AUC = 0.801), foll owed by GBDT,RF, and lightGBM (AUCs of 0.795, 0, 794, and 0.792, respectively). The XGBoost, RF, and lightGBMmodels were significantly better than logistic re gression (P <0.05). ML outperformed logistic regression,w here XGBoost the boost was the best model for predicting poor functional outcome s in young AISpatients.”
      原文链接:
    • NETL
    • NSTL

    University of Parma Researcher Reports Research in Artificial Intelligence(An I ntegrated Artificial Intelligence Approach for BuildingEnergy Demand Forecastin g)

    16-16页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators publish new report on ar tificial intelligence. According to news reportingfrom Parma, Italy, by NewsRx journalists, research stated, “Buildings are complex assets, characterized byen vironments and uses that change over time, variable occupancies, and long life c ycles.”The news reporters obtained a quote from the research from University of Parma: “They have highoperational costs, mostly due to their energy requirements, and account for 30% to 40% of global greenhousegas emis sions. Consequently, substantial effort has been made to forecast their energy n eeds, withthe scope of optimizing their economic and environmental impact. In t his regard, the available literaturefocuses mainly on short-term modeling throu gh the implementation of sets of physics-based equations (i.e.,white-box), func tional relationships between input and output variables (i.e., black-box), or a combinationof both (i.e., grey-box). On the other hand, more research is requir ed on long-term forecast models withthe aim of reducing the energy needs. Withi n this context, this article presents an original automaticprocedure for foreca sting the energy needs of buildings in short- and long-term time horizons. This isaccomplished by scaling an unknown facility from a similar facility that is a lready known and by executinga black-box approach based on machine learning alg orithms.”
      原文链接:
    • NETL
    • NSTL

    Investigators from Beihang University Release New Data onRobotics (A Code-free Interactive Task Programming Interface forRobot Skill Construction)

    17-17页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators publish new report on Ro botics. According to news reporting originatingin Beijing, People’s Republic of China, by NewsRx journalists, research stated, “To enhance productionefficienc y and quality, there is a rising interest in integrating robots into small manuf acturing entities(SMEs) to enable flexible and agile production processes, ther eby reducing redundancy. This poseschallenges for robots as they must perform v arious tasks in unstructured environments without necessitatingspecialized prog ramming training for workshop workers.”Financial supporters for this research include national key research and develop ment of china program,National Key Research & Development Program of China.
      原文链接:
    • NETL
    • NSTL

    Wuhan University of Science and Technology Reports Findings inMachine Learning (Phase Stability of CH4 and CO2 Hydrates underConfinement Predicted by Machine Learning)

    18-18页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – New research on Machine Learning is th e subject of a report. According to newsreporting originating from Hubei, Peopl e’s Republic of China, by NewsRx correspondents, research stated,“Understanding the phase stability of gas hydrates under confinement is fundamental to the geo logicalstability evolutions of gas hydrate systems on Earth. Herein, the phase stability of CH and CO hydratesunder confinement is predicted by machine learni ng.”Our news editors obtained a quote from the research from the Wuhan University of Science andTechnology, “Three machine learning models, including support vecto r machine, random forest, andgradient boosting decision tree, are constructed t o predict the phase stability of CH and CO hydratesunder confinement. Our machi ne learning results show that the prediction accuracy of the support vectormach ine model is highest, yet the prediction accuracy of the random forest model is lowest among thosemachine learning models in determining the phase stability of confined gas hydrates. Based on theirperformance in predicting the phase stabi lity of confined gas hydrates, the support vector machine modelwith a training set fraction of 0.7 is finally chosen to deal with the unknown phase stability o f confinedgas hydrates. Importantly, the average accuracy of the support vector machine model can reach more than90% in predicting the unknown p hase stability of both CH and CO hydrates.”
      原文链接:
    • NETL
    • NSTL

    Recent Findings from Anhui University Provides New Insights intoRobotics (High- linearity Capacitive 3-d Force-flexible Tactile SensorInspired By Mushroom Stru cture for Human Motion Monitoringand Robotic Gripping)

    19-19页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Research findings on Robotics are disc ussed in a new report. According to newsreporting originating from Hefei, Peopl e’s Republic of China, by NewsRx correspondents, research stated,“To improve th e grasping perception capability of robotic hands, this article explores the des ign of ahigh-linear 3-D force-flexible tactile sensor inspired by mushroom stru ctures.”Financial supporters for this research include National Natural Science Foundati on of China (NSFC),Natural Science Foundation of Anhui Province, University Syn ergy Innovation Program of Anhui Province,Central Government Will Guide Local S pecial Funds for Scientific and Technological Development.Our news editors obtained a quote from the research from Anhui University, “Diff erent from traditional3-D force tactile sensor structures, this sensor adopts a novel biomimetic mushroom symmetrical structure,significantly enhancing the se nsor’s performance. Through theoretical calculations, finite element modeling(F EM) simulation, and dynamic/static experimental measurements, the experimental o utcomes indicatethat the sensor possesses a linearity coefficient of 0.965 acro ss the entire scale spectrum with a minimalhysteresis of merely 2.65% , coupled with a response time of 62 ms at a substantial pressure of 6.5 kPa.”
      原文链接:
    • NETL
    • NSTL

    Researchers from SRM Institute of Science and Technology DiscussFindings in Mac hine Learning (Predicting Thermal Performance InSolar Air Heaters With V-corrug ated, Shot-blasted Absorber Plate,and Black Pebble-based Sensible Heat Storage: a ...)

    20-21页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News – Investigators discuss new findings in Machine Learning. According to news reportingfrom Tamil Nadu, India, by NewsRx journalists, research stated, “The construction of the solar air heater(SAH) sy stem is associated with enhancing the absorber plates’ surface area through the incorporationof V-corrugation, shot-blasting processes, nano-coated, and black pebble stone (BPS) integration. Shotblasting (SB) is a surface treatment proces s that impacts the bombarding of the surface with high-speedabrasive particles. ”Financial support for this research came from Deputyship for Research and Innova tion, Ministry ofEducation in Saudi Arabia.The news correspondents obtained a quote from the research from the SRM Institut e of Science andTechnology, “After the SB process, the surface is coated with a ctivated carbon (AC)-based nanomaterialsdispersed in matt paint. The augmented contact area owing to the roughened and corrugated absorberplate allows more he at to be transferred to the air and subsequently to the BPS. BPS can impact as athermal mass, storing grasped heat and releasing it slowly, which helps preserv e a consistent temperatureand enhances the overall efficiency of the SAH. This augmented absorption capacity permits the plate toefficiently transfer the abso rbed heat to the black pebble stones. In this study, experimental findings arec ompared with machine learning (ML) models to evaluate the thermal transfer effic iency of conventionaland surface-modified absorbers in the SAH system. The expe rimental data is subjected to predictionusing diverse ML techniques, namely ran dom forest regression (RFR), linear regression (LR), and supportvector regressi on (SVR). By comparing the experimental results with predictions from LR, RFR, a nd SVRmodels, the study effectively evaluates the impacts of surface modificati ons and BPS incorporations onthe SAH thermal efficiency. The efficacy of the ML -based thermal efficiency and ‘Nu’ models is comparedusing mean squared error a nd root mean squared error. Amongst the algorithms estimated, LR, RFR,and SVR p roduced the highest correlation coefficient of 0.997, 0.993, 0.972 for conventio nal SAH and0.9976, 0.999, and 0.975 for SAH in estimating the ‘Nu’, respectivel y.”
      原文链接:
    • NETL
    • NSTL