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

    Findings from Yanshan University in Robotics Reported (Modeling and Robust Adaptive Practical Predefined Time and Precision Tracking Control of Unmanned Fire Fighting Robot)

    57-58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 Robotics. According to news reporting fromQinhuangdao, People’s Republic of Chi na, by NewsRx journalists, research stated, “This article studiesthe modeling a nd tracking control problems for a class of towed unmanned fire fighting robots. Consideringthat no similar modeling results exist, we take the lead in buildin g a novel system model that takes intoconsideration both system uncertainties a nd external disturbances, including unknown friction factors anddrag force.”Financial support for this research came from National Natural Science Foundatio n of China (NSFC).The news correspondents obtained a quote from the research from Yanshan Universi ty, “Then, tocompensate for the adverse effects of system uncertainties and ext ernal disturbances, a novel robustcontrol algorithm is proposed, which utilizes adaptive control and scaling techniques. Moreover, innovativepredefined perfor mance functions are designed to ensure that tracking processes meet predefined t ransientand steady-state requirements. Unlike most of the existing works, our p redefined time performance functionhas the advantage that the convergence time and convergence accuracy can be arbitrarily changed. In theend, a novel robust adaptive control scheme with predefined time and precision tracking is designed usingthe backstepping recursive method. Based on Lyapunov stability theory, it is demonstrated that all signalsin the closed-loop system are ultimately bounde d, and both predefined transient and steady-state processes are never violated. To validate the effectiveness of this proposed control scheme, numerical simulat ionsand practical platform experiments have been conducted.”
      原文链接:
    • NETL
    • NSTL

    Researchers at Baylor University Have Reported New Data on Machine Learning (Mon itoring Covariance In Multivariate Time Series: Comparing Machine Learning and Statistical Approaches)

    58-59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 newsoriginating from Waco, Texas, by News Rx correspondents, research stated, “In complex systems withmultiple variables monitored at high-frequency, variables are not only temporally autocorrelated, b ut theymay also be nonlinearly related or exhibit nonstationarity as the inputs or operation changes. One approachto handling such variables is to detrend the m prior to monitoring and then apply control charts that assumeindependence and stationarity to the residuals.”Financial supporters for this research include United States Department of Energ y (DOE), NationalScience Foundation PFI:BIC, National Science Foundation Engine ering Research Center program, NationalAlliance for Water Innovation (NAWI) - U .S. Department of Energy, Energy Efficiency, and RenewableEnergy Office, Advanc ed Manufacturing Office.
      原文链接:
    • NETL
    • NSTL

    Findings on Artificial Intelligence Discussed by Investigators at National Unive rsity of Mardel Plata (UNMdP) (Artificial Intelligence and Water Quality: From Drinking Water To Wastewater)

    59-60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 reportingout of Mar del Plata, Argenti na, by NewsRx editors, research stated, “The transformative impact of ArtificialIntelligence (AI) technologies, particularly Machine Learning (ML), on the anal ysis of spectroscopicdata in water quality assessment cannot be overstated. We remark the ways in which AI and ML haverevolutionized the analysis and predicti on of water quality parameters.”Funders for this research include MCIN/AEI, European Union (EU).Our news journalists obtained a quote from the research from the National Univer sity of Mar del Plata(UNMdP), “These technologies efficiently process spectral data from various sources, identify contaminants,and support early detection sy stems. However, AI tools have limitations, including the need for alarge and di verse dataset for optimal performance, and some studies used small datasets, lim iting the predictivepower of the models. Open databases can aid in expanding AI applications in water quality controland treatment. The potential of AI and sp ectroscopic techniques reduce costs, promote environmentallysustainable water t reatment, and enhance water and environmental quality.”
      原文链接:
    • NETL
    • NSTL

    New Robotics Findings from University of Science and Technology China Reported (Human-in-the-loop Cooperative Control of a Walking Exoskeleton for Following Time-variable Human Intention)

    60-61页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - A new study on Robotics is now availab le. According to news reporting originatingfrom Hefei, People’s Republic of Chi na, by NewsRx correspondents, research stated, “This article presentsa human-in -the-loop cooperative control of a walking exoskeleton to provide assistance to the user andenhance human mobility. First, a dynamic mathematical model of the human-exoskeleton system is derived,and then, a human-in-the-loop cooperative c ontrol framework is proposed in two ways: separablecooperative control (SCC) an d interactive cooperative control (ICC), respectively.”Financial support for this research came from National Natural Science Foundatio n of China (NSFC).Our news editors obtained a quote from the research from the University of Scien ce and TechnologyChina, “The SCC introduces a space division of the human and t he exoskeleton, while the ICC allowsthe robot to perceive the human intention a nd follows human motor, thereby improving the collaborativeperformance. The ICC formulates the impedance connection between the human and the exoskeleton inth e divided orthogonal subspaces of walking, such that the robot is able to modify its position of centerof mass (COM) when its motor trajectory deviates the one of the human. In addition, a novel adaptationcontrol is proposed to deal with the unmodeled dynamics and trajectory tracking. Finally, to validate theeffecti veness of our proposed controller, a series of experiments are conducted in thre e adults in gait atdifferent speeds.”
      原文链接:
    • NETL
    • NSTL

    Fourth Military Medical University Reports Findings in COVID-19 (Identification of Age-Related Characteristic Genes Involved in Severe COVID-19 Infection Among Elderly Patients Using Machine Learning and Immune Cell Infiltration Analysis)

    61-62页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Coronavirus - COVID-19 is the subject of a report. According tonews reporting originating from Shaanx i, People’s Republic of China, by NewsRx correspondents, researchstated, “Elder ly patients infected with severe acute respiratory syndrome coronavirus 2 are at higher riskof severe clinical manifestation, extended hospitalization, and inc reased mortality. Those patients aremore likely to experience persistent sympto ms and exacerbate the condition of basic diseases with longCOVID-19 syndrome.”Our news editors obtained a quote from the research from Fourth Military Medical University, “However,the molecular mechanisms underlying severe COVID-19 in th e elderly patients remain unclear. Our studyaims to investigate the function of the interaction between disease-characteristic genes and immune cellinfiltrati on in patients with severe COVID-19 infection. COVID-19 datasets (GSE164805 and GSE180594)and aging dataset (GSE69832) were obtained from the Gene Expression O mnibus database. The combineddifferent expression genes (DEGs) were subjected t o Gene Ontology (GO) functional enrichment analysis,Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway and Diseases Ontology functional enrichmentanalysis , Gene Set Enrichment Analysis, machine learning, and immune cell infiltration a nalysis. GO andKEGG enrichment analyses revealed that the eight DEGs (IL23A, PT GER4, PLCB1, IL1B, CXCR1, C1QB,MX2, ALOX12) were mainly involved in inflammator y mediator regulation of TRP channels, coronavirusdisease-COVID-19, and cytokin e activity signaling pathways. Three-degree algorithm (LASSO, SVM-RFE,KNN) and correlation analysis showed that the five DEGs up-regulated the immune cells of macrophagesM0/M1, memory B cells, gamma delta T cell, dendritic cell resting, a nd master cell resisting.”
      原文链接:
    • NETL
    • NSTL

    Studies from Iowa State University Further Understanding of Machine Learning (A Machine Learning Approach To Improve the Usability of Severe Thunderstorm Wind R eports)

    62-63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 Ma chine Learning. According to news reportingfrom Ames, Iowa, by NewsRx journalis ts, research stated, “Many concerns are known to exist withthunderstorm wind re ports in the National speed, changes in report frequency due to population densi ty,and differences in reporting due to damage tracers. These concerns are espec ially pronounced with reportsthat are not associated with a wind speed measurem ent, but are estimated, which make up almost 90%of the database.”Funders for this research include HWT Program within the NOAA/OAR Weather Progra m Office,Department of Commerce, HPC@ISU equipment at Iowa State University, Na tional Science Foundation(NSF).The news correspondents obtained a quote from the research from Iowa State Unive rsity, “We haveused machine learning to predict the probability that a severe w ind report was caused by severe intensitywind, or wind > = 50 kt (similar to 25 m s-1). A total of six machine learning models were train ed on 11years of measured thunderstorm wind reports, along with meteorological parameters, population density,and elevation. Objective skill metrics such as t he area under the ROC curve (AUC), Brier score, andreliability curves suggest t hat the best performing model is the stacked generalized linear model, whichhas an AUC around 0.9 and a Brier score around 0.1. The outputs from these models h ave many potentialuses such as forecast verification and quality control for im plementation in forecast tools.”
      原文链接:
    • NETL
    • NSTL

    Study Data from Medical University of Warsaw Provide New Insights into Robotics (Utilization of the Reinstein Icl Sizing Formula With Hand-held Ultrasound Biomi croscopy Measurements)

    63-63页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Researchers detail new data in Robotic s. According to news reporting out of Warsaw,Poland, by NewsRx editors, researc h stated, “To evaluate the accuracy of the Reinstein formula withhand-held ultr asound biomicroscopy (UBM) measurements for sizing of the Implantable Collamer L ens(ICL). A total of 107 myopic eyes of 57 patients implanted with the ICL were included in the study.”Our news journalists obtained a quote from the research from the Medical Univers ity of Warsaw,“The size of the ICL was selected based on the manufacturer’s rec ommendations. Agreement betweenthe vault predicted by the Reinstein formula and the vault measured postoperatively was analyzed withBland-Altman plots. A tota l of 95% and 81% of patients had a postoperative vau lt ranging from 150to 1,000 and 250 to 750 mu m, respectively. The mean vault p redicted by the Reinstein formula and thepostoperative vault in the current stu dy were 580 +/- 181 and 547 +/- 200 mu m, respectively. Thesize recommendations of the Reinstein formula and the formula provided by the manufacturer, the Koji maformula, and the Dougherty formula overlapped in 50%, 57% , and 49% of eyes, respectively. The resultsshow that the Reinste in formula combined with a hand-held UBM provides reliable sizing predictions ofthe ICL.”
      原文链接:
    • NETL
    • NSTL

    Chinese Academy of Sciences Details Findings in Robotics and Automation (A Mm Wave Radar Slam Method In Subterranean Tunnel for Low Visibility and Degradation)

    64-64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 - Robotics and Automation. According tonews reporting originating from B eijing, People’s Republic of China, by NewsRx correspondents, researchstated, “ A novel mmWave radar SLAM method is proposed to integrate multi-dimensional info rmation,including velocity, spatial, RCS, and semantics to enable autonomous na vigation in subterranean tunnelenvironments, which are characterized by low vis ibility and degraded conditions.”Our news editors obtained a quote from the research from the Chinese Academy of Sciences, “By combiningdoppler odometry, scan matching, and feature matching mo dules, the proposed method effectivelymitigates environmental degradation. Expe rimental results from various subterranean tunnel trajectoriesshow that the pro posed method achieves superior localization and mapping accuracy compared to exi stingradar SLAM methods, and even outperforms state-of-the-art Lidar SLAM methods.”
      原文链接:
    • NETL
    • NSTL

    New Robotics and Mechatronics Research from University of Tokyo Described (Data Fusion for Sparse Semantic Localization Based on Object Detection)

    64-65页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - A new study on robotics and mechatroni cs is now available. According to newsoriginating from Tokyo, Japan, by NewsRx correspondents, research stated, “Semantic information hasstarted to be used in localization methods to introduce a non-geometric distinction in the environmen t.”Our news editors obtained a quote from the research from University of Tokyo: “H owever, efficientways to integrate this information remain a question. We propo se an approach for fusing data from different object classes by analyzing the po sterior for each object class to improve robustness and accuracyfor self-locali zation. Our system uses the bearing angle to the objects’ center and objects’ cl ass namesas sensor model input to localize the user on a 2D annotated map consi sting of objects’ class names andcenter coordinates. Sensor model input is obta ined by an object detector on equirectangular images ofa 360° field of view cam era. As object detection performance varies based on location and object class,different object classes generate different likelihoods.”
      原文链接:
    • NETL
    • NSTL

    Studies from Tsinghua University Reveal New Findings on Machine Learning (Machine Learning-enhanced Interpolation of Gravityassisted Magnetic Data)

    65-66页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Researchers detail new data in Machine Learning. According to news reporting originatingin Beijing, People’s Republic of China, by NewsRx journalists, research stated, “The acquisition ofmagnetic anomaly data is generally considered a process of information degradation, with its content significantlyimpacting subsequent tasks involving data processing, inversion, and interpretation. Traditionalinterpolation methods often rely on t he spatial distribution and sampling density of data, thus strugglingto handle complex nonlinear relationships effectively.”Financial support for this research came from National Natural Science Foundatio n of China (NSFC).The news reporters obtained a quote from the research from Tsinghua University, “To address thesechallenges, this study employs deep learning algorithms for in terpolating magnetic anomaly data, aimingto enhance the resolution of magnetic data. Additionally, gravity data are incorporated as supplementaryinformation t o improve the quality of magnetic anomaly data interpolation. Similar to magneti c data,gravity data also exhibit a certain degree of spatial correlation, as a single geological source may produceanomalies in both gravity and magnetic resp onses simultaneously. Through the training and predictionof deep learning netwo rks, it is observed that the intelligent interpolation retains the subtle featur es ofmagnetic anomaly data in space while avoiding staircase-like erroneous ano malies generated by linear interpolation. Furthermore, gravity data assist in co nstraining the results of magnetic anomaly interpolation,enhancing their accura cy. Finally, the trained network is applied to measured data, with the input dat abeing downsampled.”
      原文链接:
    • NETL
    • NSTL