期刊,Robotics & Machine Learning Daily News 2024年卷Oct.3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

Researchers at Tianjin University Report New Data on Computational Intelligence (Optimal Cooperative Control of Multi-agent Systems Through Event-triggered Mode l-free Reinforcement Learning)

67-68页

查看更多>>摘要：2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Machine Learning - Com putational Intelligence is the subject of a report. According to news originatin g from Tianjin, People's Republic of China, by NewsRx correspondents, research s tated, "This paper addresses the optimal cooperative control problem for nonline ar multi-agent systems with completely unknown dynamics and proposes a learning control scheme based on the eventtriggered mechanisms. The problem is reformula ted as a multi-agent differential graphical game, and an off-policy integral rei nforcement learning algorithm is introduced by deriving off-policy Bellman equat ions." Funders for this research include National Key Research & Developm ent Program of China, National Natural Science Foundation of China (NSFC), China Postdoctoral Science Foundation, China Postdoctoral Science Foundation.

原文链接:

NETL
NSTL

Study Findings on Machine Learning Described by a Researcher at Chungbuk Nationa l University (Machine learning regression-based prediction model for the autonom ous control of coagulant dosing in smart water purification plants)

68-68页

查看更多>>摘要：2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on artificial in telligence have been published. According to news originating from Chungbuk, Sou th Korea, by NewsRx editors, the research stated, "ABSTRACT: The global issue of water scarcity is escalating due to urbanization and increased demand." Funders for this research include Ministry of Education. The news reporters obtained a quote from the research from Chungbuk National Uni versity: "This paper proposes a machine learning (ML) regression-based model for automatic coagulant dosing control in smart water purification plants (SWPPs).1 The model uses random forest (RF), light gradient boosting machine (LGBM), extr eme gradient boosting (XGB), and k-nearest neighbors (KNN) algorithms. Performan ce metrics include MAE, MSE, RMSE, MAPE, and R2. The RF algorithm showed superio r performance, with MAE of 0.005, MSE of 0.002, RMSE of 0.05, and MAPE of 0.000 for anion-poly aluminum chloride dosing, and MAE of 0.007, MSE of 0.00, RMSE of 0.02, and MAPE of 0.000 for Polymax dosing. The RF model's performance is due to its robust handling of large datasets and ensemble learning approach."

原文链接:

NETL
NSTL

Study Findings on Robotics Are Outlined in Reports from Beijing University of Te chnology (Multi-source Decision-making Information Fusion Framework for Evaluati ng Coexisting-cooperativecognitive Capabilities of Collaborative Robots Using T ext ...)

69-70页

查看更多>>摘要：2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Robotics is the subjec t of a report. According to news reporting originating from Beijing, People's Re public of China, by NewsRx correspondents, research stated, "To effectively addr ess the requirements of deeply coexisting-cooperative-cognitive (Tri-Co) interac tions among humans, robots, and the environment within the context of Industry 4 .0, it becomes crucial to conduct evaluation research on Tri-Co capabilities (TC Cs) of collaborative robots (cobots), which is a knowledgeintensive task. Howev er, existing research on performance evaluation of cobots has not yet establishe d a common method for constructing a complete performance evaluation index syste m." 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 Beijing University of Technology, "The testing methods lack a design basis and fail to evaluate the performance of cobots through operational tasks in industrial production or dai ly life from the perspective of test tasks. Furthermore, these methods do not fa cilitate the fusion of multi-source subjective and objective decision-making inf ormation, which includes both the knowledge of experts and fundamental parameter s of cobots. To this end, this study proposes a multi-source decision-making inf ormation fusion framework for evaluating the TCCs of cobots. This framework incl udes a construction method for an evaluation index system that fuses subjective and objective elements based on statistics, text clustering, and closed-loop fee dback mechanism. It also incorporates TCCs test tasks, and an improved fuzzy ana lytic network process (IFANP). Additionally, it incorporates a combination weigh ting method that aims to minimise both subjective and objective weights deviatio ns. This framework effectively integrates the subjective knowledge of experts wi th the objective fundamental parameters of cobots. It accomplishes local TCCs ev aluation from the perspective of test tasks. Additionally, it achieves global TC Cs evaluation by combining basic performance evaluation indices and the performa nce of completing the test tasks. A case by Rethink Sawyer (Sawyer) is presented to demonstrate the application process and viability of the developed framework ."

原文链接:

NETL
NSTL

Studies from Liaocheng University Have Provided New Data on Robotics (Command Fi ltered Adaptive Control for Flexible-joint Robots With Full-state Quantization)

70-70页

查看更多>>摘要：2024 OCT 03 (NewsRx)-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 originating in Liaocheng, People's Republic of China, by NewsRx journalists, research stated, "This article further investigates the tracking control problem of flexible-joint robot systems. Comp ared with existing results, all states are assumed to be quantized by a uniform quantizer, which results in discontinuous quantized signals." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Guangyue Young Scholar Innovation Team of Liaocheng Universi ty.

原文链接:

NETL
NSTL

New Findings Reported from Federal University of Tecnology Parana Describe Advan ces in Robotics (Climbing Robot for Advanced Hightemperature Weld Bead Inspecti on)

71-71页

查看更多>>摘要：2024 OCT 03 (NewsRx)-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 originating from Curitiba, Brazil, by NewsRx correspondents, research stated, "High-temperature industrial inspecti on has several challenges, especially if it is an autonomous inspection through mobile robots. This paper introduces the mobile robot CRAS (Climbing Robot for A dvanced inSpection) for autonomous non-destructive testing (NDT) of weld beads f rom industrial super-duplex stainless steel vessels." Financial supporters for this research include Petrobras, Development and Innova tion Center (CENPES), Presidente Getulio Vargas Refinery (REPAR-PETROBRAS), Cons elho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPQ).

原文链接:

NETL
NSTL

University of Beira Interior Researcher Adds New Study Findings to Research in M achine Learning (Toward Automated Fabric Defect Detection: A Survey of Recent Co mputer Vision Approaches)

72-72页

查看更多>>摘要：2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on artificial in telligence have been published. According to news reporting from the University of Beira Interior by NewsRx journalists, research stated, "Defect detection is a crucial part of the pipeline in many industries." Funders for this research include Nextgenerationeu Program; Fct/mctes. The news journalists obtained a quote from the research from University of Beira Interior: "In the textile industry, it is especially important, as it will affe ct the quality and price of the final product. However, it is mostly performed b y human agents, who have been reported to have poor performance, along with requ iring a costly and time-consuming training process. As such, methods to automate the process have been increasingly explored throughout the last 20 years. While there are many traditional approaches to this problem, with the advent of deep learning, machine learning-based approaches now constitute the majority of all p ossible approaches. Other articles have explored traditional approaches and mach ine learning approaches in a more general way, detailing their evolution over ti me."

原文链接:

NETL
NSTL

Findings in Machine Learning Reported from Zhejiang University (Enhancing Spectr oscopy-based Fruit Quality Control: a Knowledge-guided Machine Learning Approach To Reduce Model Uncertainty)

72-73页

查看更多>>摘要：2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on Machine Learning have been presented. According to news report-ing originating from Zhejiang, People's Republic of China, by NewsRx correspondents, research stated, "Spectroscopy-bas ed techniques have made remarkable advancements in their application to fruit qu ality control but encounter challenges of high model uncertainty arising from bi ological variability. Minor changes in spectral measurement orientations or posi tions significantly altered the model prediction for fruit quality, which severe ly affects the reliability of online fruit grading systems."

原文链接:

NETL
NSTL

New Machine Learning Study Findings Recently Were Reported by a Researcher at Ho pe College (Predicting newborn birth outcomes with prenatal maternal health feat ures and correlates in the United States: a machine learning approach using arch ival ...)

74-74页

查看更多>>摘要：2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on ar tificial intelligence. According to news originating from Hope College by NewsRx correspondents, research stated, "Newborns are shaped by prenatal maternal expe riences. These include a pregnant person's physical health, prior pregnancy expe riences, emotion regulation, and socially determined health markers." The news journalists obtained a quote from the research from Hope College: "We u sed a series of machine learning models to predict markers of fetal growth and d evelopment-specifically, newborn birthweight and head circumference (HC). We use d a pre-registered archival data analytic approach. These data consisted of mate rnal and newborn characteristics of 594 maternal-infant dyads in the western U.S . Participants also completed a measure of emotion dysregulation. In total, ther e were 22 predictors of newborn HC and birthweight. We used regularized regressi on for predictor selection and linear prediction, followed by nonlinear models i f linear models were overfit. HC was predicted best with a linear model (ridge r egression). Newborn sex (male), number of living children, and maternal BMI pred icted a larger HC, whereas maternal preeclampsia, number of prior preterm births , and race/ethnicity (Latina) predicted a smaller HC. Birthweight was predicted best with a nonlinear model (support vector machine). Occupational prestige (a m arker similar to socioeconomic status) predicted higher birthweight, maternal ra ce/ethnicity (non-White and non-Latina) predicted lower birthweight, and the num ber of living children, prior preterm births, and difficulty with emotional clar ity had nonlinear effects."

原文链接:

NETL
NSTL

Data on Arthroplasty Reported by Ishaan Jagota and Colleagues (Robotic-Assisted Total Knee Arthroplasty Results in Shorter Navigation Working Time With Similar Clinical Outcomes Compared to Computer-Navigated Total Knee Arthroplasty)

75-76页

查看更多>>摘要：2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Surgery - Arthroplasty is the subject of a report. According to news reporting out of Sydney, Australi a, by NewsRx editors, research stated, "Early clinical data is important in the appraisal of newly introduced robotic-assisted surgery (RAS) systems in total kn ee arthroplasty (TKA). However, there are few studies to date comparing one-year clinical outcomes between RAS and computer-assisted navigation (CAS), the forer unner in reducing alignment outliers." Our news journalists obtained a quote from the research, "The aim of this study was to determine if there was a difference between these two groups in early cli nical outcomes, including functional outcome and patient-reported outcome measur es (PROMs). A total of 158 propensity score-matched patients who underwent prima ry TKA with either CAS or RAS were retrospectively analyzed. Perioperative outco mes (navigation time, length of stay, complications, readmissions, transfusions, and technical failure), as well as functional outcome measures (range of motion , sit to stand test, timed up and go test, single leg stance test, calf raises, and step count), and patient-reported outcome measures (Oxford Knee Score, Knee Injury and Osteoarthritis Outcome Score, 12-item Short Form Survey, Forgotten Jo int Score-12, and satisfaction) were compared between those who underwent CAS an d those who underwent RAS. Navigation time was shorter in the RAS group compared to the CAS group (mean difference, 15.4 minutes; P<0.001) . There were two complications reported in the CAS group (1 patellar clunk, 1 pe riprosthetic joint infection), but none in the RAS group. There were no other re admissions, transfusions, or technical failures in either group. Postoperatively , there were no clinical differences in function between groups. Clinically mean ingful improvement in PROMs was observed in both groups, with no differences. Th e use of RAS resulted in shorter navigation time compared to CAS in TKA."

原文链接:

NETL
NSTL

Ruhr-University Bochum Researchers Publish New Studies and Findings in the Area of Brain-Based Devices (Human in the collaborative loop: a strategy for integrat ing human activity recognition and non-invasive brain-machine interfaces to cont rol ...)

75-75页

查看更多>>摘要：2024 OCT 03 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators publish new report on br ain-based devices. According to news originating from Bochum, Germany, by NewsRx correspondents, research stated, "Human activity recognition (HAR) and brain-ma chine interface (BMI) are two emerging technologies that can enhance human-robot collaboration (HRC) in domains such as industry or healthcare." Our news reporters obtained a quote from the research from Ruhr-University Bochu m: "HAR uses sensors or cameras to capture and analyze the movements and actions of humans, while BMI uses human brain signals to decode action intentions. Both technologies face challenges impacting accuracy, reliability, and usability. In this article, we review the state-of-the-art techniques and methods for HAR and BMI and highlight their strengths and limitations. We then propose a hybrid fra mework that fuses HAR and BMI data, which can integrate the complementary inform ation from the brain and body motion signals and improve the performance of huma n state decoding."

原文链接:

NETL
NSTL