期刊,Robotics & Machine Learning Daily News 2024年卷Oct.31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

Study Findings on Androids Described by a Researcher at Department of Computer S cience ("You Scare Me": The Effects of Humanoid Robot Appearance, Emotion, and I nteraction Skills on Uncanny Valley Phenomenon)

125-125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 androids have been published. According to news reportingfrom Kaiserslautern, Germany, by Ne wsRx journalists, research stated, "This study investigates the effectsof human oid robot appearance, emotional expression, and interaction skills on the uncann y valleyphenomenon among university students using the social humanoid robot (S HR) Ameca."The news journalists obtained a quote from the research from Department of Compu ter Science: "Twofundamental studies were conducted within a university setting : Study 1 assessed student expectationsof SHRs in a hallway environment, emphas izing the need for robots to integrate seamlessly and engageeffectively in soci al interactions; Study 2 compared the humanlikeness of three humanoid robots, RO MAN,ROBIN, and EMAH (employing the EMAH robotic system implemented on Ameca). T he initial findingsfrom corridor interactions highlighted a diverse range of hu man responses, from engagement and curiosityto indifference and unease. Additio nally, the online survey revealed significant insights into expected nonverbalcommunication skills, continuous learning, and comfort levels during hallway con versations withrobots. Notably, certain humanoid robots evoked stronger emotion al reactions, hinting at varying degreesof humanlikeness and the influence of i nteraction quality."

原文链接:

NETL
NSTL

Nanjing University Reports Findings in Machine Learning (DeepCheck: multitask le arning aids in assessing microbial genome quality)

126-126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 in Nanjing, Peopl e's Republic of China, by NewsRx journalists, research stated,"Metagenomic anal yses facilitate the exploration of the microbial world, advancing our understand ing ofmicrobial roles in ecological and biological processes. A pivotal aspect of metagenomic analysis involvesassessing the quality of metagenome-assembled g enomes (MAGs), crucial for accurate biological insights."Funders for this research include National Key Research and Development Program of China, NationalNatural Science Foundation of China.The news reporters obtained a quote from the research from Nanjing University, " Current machinelearning-based methods often treat completeness and contaminatio n prediction as separate tasks, overlookingtheir inherent relationship and limi ting models' generalization. In this study, we present DeepCheck, amultitasking deep learning framework for simultaneous prediction of MAG completeness and con tamination.DeepCheck consistently outperforms existing tools in accuracy across various experimental settingsand demonstrates comparable speed while maintaini ng high predictive accuracy even for new lineages."

原文链接:

NETL
NSTL

Study Results from Hebei University of Technology in the Area of Fatigue Reporte d (A Cream Model Optimization Method Based On Fatigue Testing Experiments and Ma chine Learning Techniques for Maritime Transportation Applications)

127-127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 Fatigue have been published. According to news originatingfrom Tianjin, People's Republic of China, by NewsRx correspondents, research stated, "Maritime transportationhas a crucial position in world trade, but maritime transportation accidents still o ccur frequently.To assess human errors in maritime transportation more accurate ly by CREAM and thus improve the reliabilityof maritime transportation, the stu dy is the first to obtain the quantitative effects of differentantifatigue capa bility groups on task performance in the field of maritime transportation by com biningfatigue test experiments with machine learning."Funders for this research include National Natural Science Foundation of China ( NSFC), NaturalScience Foundation of Hebei Province.

原文链接:

NETL
NSTL

National and Kapodistrian University of Athens Reports Findings in Machine Learn ing (The Synergy of Machine Learning and Epidemiology in Addressing Carbapenem R esistance: A Comprehensive Review)

128-129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 from Athens, Greece, by NewsR x journalists, research stated, "Carbapenem resistance poses asignificant threa t to public health by undermining the efficacy of one of the last lines of antib iotic defense.Addressing this challenge requires innovative approaches that can enhance our understanding and abilityto combat resistant pathogens."The news correspondents obtained a quote from the research from the National and KapodistrianUniversity of Athens, "This review aims to explore the integration of machine learning (ML) and epidemiologicalapproaches to understand, predict, and combat carbapenem-resistant pathogens. It examines howleveraging large dat asets and advanced computational techniques can identify patterns, predict outbr eaks,and inform targeted intervention strategies. The review synthesizes curren t knowledge on the mechanismsof carbapenem resistance, highlights the strengths and limitations of traditional epidemiological methods,and evaluates the trans formative potential of ML. Real-world applications and case studies are used todemonstrate the practical benefits of combining ML and epidemiology. Technical a nd ethical challenges,such as data quality, model interpretability, and biases, are also addressed, with recommendations providedfor overcoming these obstacle s. By integrating ML with epidemiological analysis, significant improvementscan be made in predictive accuracy, identifying novel patterns in disease transmiss ion, and designing effectivepublic health interventions. Case studies illustrat e the benefits of interdisciplinary collaboration intackling carbapenem resista nce, though challenges such as model interpretability and data biases must bema naged. The combination of ML and epidemiology holds great promise for enhancing our capacity topredict and prevent carbapenem-resistant infections. Future rese arch should focus on overcoming technicaland ethical challenges to fully realiz e the potential of these approaches."

原文链接:

NETL
NSTL

Researchers from State University Maringa Report Recent Findings in Machine Lear ning (Interactive Search-based Product Line Architecture Design)

129-129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 originatingfrom Maringa, Brazil, by NewsRx co rrespondents, research stated, "Software Product Line (SPL) is anapproach deriv ed from other engineering fields that use reuse techniques for a family of produ cts in a givendomain. An essential artifact of SPL is the Product Line Architec ture (PLA), which identifies elementscharacterized by variation points, variabi lity, and variants."Our news journalists obtained a quote from the research from State University Ma ringa, "The PLA aimsto anticipate design decisions to obtain features such as r eusability and modularity. Nevertheless, gettinga reusable and modular PLA and following pre-defined standards can be a complex task involving severalconflict ing objectives. In this sense, PLA can be formulated as a multiobjective optimiz ation problem.This research presents an approach that helps DMs (Decision Maker s) to interactively optimize the PLAsthrough several strategies such as interac tive optimization and Machine Learning (ML) algorithms. Theinteractive multiobj ective optimization approach for PLA design (iMOA4PLA) uses specific metrics forthe PLA optimization problem, implemented through the OPLA-Tool v2.0. In this a pproach, the architectassumes the role of DM during the search process, guiding the evolution of PLAs through various strategiesproposed in previous works. Tw o quantitative and one qualitative experiments were performed to evaluatethe iM OA4PLA. The results showed that this approach can assist the PLA optimization pr ocess bymeeting more than 90% of DM preferences."

原文链接:

NETL
NSTL

Investigators from Northeastern University Report New Data on Robotics and Autom ation (Mgs-slam: Monocular Sparse Tracking and Gaussian Mapping With Depth Smoot h Regularization)

130-130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 - Robotics and Automation is now available. According tonews reporting out of Shenyang, Peopl e's Republic of China, by NewsRx editors, research stated, "Thisletter introduc es a novel framework for dense Visual Simultaneous Localization and Mapping (VSL AM)based on Gaussian Splatting. Recently, SLAM based on Gaussian Splatting has shown promising results."Funders for this research include National Natural Science Foundation of China ( NSFC), LiaoningProvincial Natural Science Foundation Joint Fund, Ministry of In dustry and Information TechnologyProject, Scientific Research Foundation of Lia oning Provincial Education Department, Fundamental ResearchFunds for the Centra l Universities.

原文链接:

NETL
NSTL

Research from Department of CSE Provides New Data on Machine Learning (Carbon Ca pture and Storage Optimization with Machine Learning)

131-131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 artific ial intelligence. According to news reportingfrom the Department of CSE by News Rx journalists, research stated, "This study examines the potentialfor enhancin g carbon capture and storage (CCS) processes by machine learning to markedly imp roveperformance across diverse capture methods, including as absorption, adsorp tion, membrane separation,and cryogenic distillation."Our news editors obtained a quote from the research from Department of CSE: "Thr ough the systematicadjustment of critical operating parameters, including tempe rature, pressure, flow rates, and sorbentcharacteristics using machine learning algorithms, we saw significant improvements in CO collection efficiency.The us e of optimum operating parameters, namely a temperature range of 40-60°C for abs orptionand a pressure range of 3-5 bar for adsorption, resulted in a 30% enhancement in capture efficiency. Moreover,machine learning models, namely Ran dom Forest and Support Vector Machines (SVM), achieved amaximum enhancement of 20% in forecasting ideal operating parameters for membrane separat ion andcryogenic systems. Reduced cycle durations in adsorption processes, faci litated by predictive modeling,resulted in a 15% improvement in C O removal rates. The models' capacity to forecast sorbent regenerationcondition s led to a 10% decrease in energy use. Machine learning algorithms adeptly optimized processspecificparameters, including material composition a nd flow dynamics, enhancing membrane performanceby 18% and cryoge nic systems by 12%."

原文链接:

NETL
NSTL

Sun Yat-sen University Reports Findings in miRNA-Based Therapy (Screening Model for Bladder Cancer Early Detection With Serum miRNAs Based on Machine Learning: A Mixed-Cohort Study Based on 16,189 Participants)

132-133页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News-New research on Biotechnology - miRNA- Based Therapy is the subject of a report.According to news reporting originatin g from Guangdong, People's Republic of China, by NewsRx correspondents,research stated, "Early detection of bladder cancer (BCa) can have a positive impact onpatients' prognosis. However, there is currently no widely accepted method for e arly screening of BCa."Financial supporters for this research include Natural Science Foundation of Gua ngdong Province,National Natural Science Foundation of China.Our news editors obtained a quote from the research from Sun Yat-sen University, "We aimed todevelop an efficient, clinically applicable, and noninvasive metho d for the early screening of BCa bydetecting specific serum miRNA levels. A mix ed-cohort (including BCa, 12 different other cancers, benigndisease patients, a nd health population) study was conducted using a sample size of 16,189. Five ma chinelearning algorithms were utilized to develop screening models for BCa usin g the training dataset. Theperformance of the model was evaluated using receive r operating characteristic curve and decision curveanalysis on the testing data set, and subsequently, the model with the best predictive power was selected.Fu rthermore, the selected model's screening performance was evaluated using both t he validation set andexternal set. The BCaS3miR model, utilizing only three ser um miRNAs (miR-6087, miR-1343-3p, andmiR-5100) and based on the KNN algorithm, is the superior screening model chosen for BCa. BCaS3miRconsistently performed well in both the testing, validation, and external sets, exceeding 90% sensitivityand specificity levels. The area under the curve was 0.990 (95% CI: 0.984-0.991), 0.964 (95% CI: 0.936-0.984), and 0.917 (95% CI: 0.836-0.953) in the testing, validation, and external set. The subgroup analysis revealed that the BCaS3miR model demonstrated outstanding screening accurac y in various clinicalsubgroups of BCa. In addition, we developed a BCa screenin g scoring model (BCaSS) based on thelevels of miR-1343-3p/miR-6087 and miR-5100 /miR-6087. The screening effect of BCaSS is investigatedand the findings indica te that it has predictability and distinct advantages. Using a mixed cohort withthe largest known sample size to date, we have developed effective screening mo dels for BCa, namelyBCaS3miR and BCaSS."

原文链接:

NETL
NSTL

New Machine Learning Study Findings Have Been Reported by Investigators at Depar tment of Architectural Engineering (Construction of Virtual Simulation Experimen t Platform for Intelligent Construction Based On Statistical Machine Learning Sy stem ...)

133-134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 reportingoriginating from Hebei, People's Rep ublic of China, by NewsRx editors, the research stated, "In the constructionof a virtual simulation experiment platform for intelligent construction, cutting-e dge technologiesconverge to revolutionize traditional project management method ologies. By harnessing the power of virtualreality, statistical modeling, and m achine learning, this platform empowers stakeholders to predict,optimize, and s imulate construction projects with unprecedented accuracy and efficiency."Our news editors obtained a quote from the research from the Department of Archi tectural Engineering,"This paper introduces the Virtual Statistical Machine Lea rning (VS-ML) platform and demonstrates itsapplication in intelligent construct ion processes. Through comprehensive experimentation and simulation,the VS-ML p latform accurately estimates construction project parameters, optimizes resource utilization,schedules tasks efficiently, and classifies project outcomes with high accuracy. Numerical results from ourstudy showcase the platform's effectiv eness in various aspects of construction project management. Forinstance, in co nstruction projects estimation, scenarios ranging from Scenario 1 to Scenario 10 exhibitproject durations between 100 to 150 days, cost estimates ranging from $470,000 to $550,000, and safetyratings varying from ‘Good' to ‘Excellent'. Furthermore, labor efficiency and material waste estimati onsacross scenarios demonstrate percentages ranging from 85% to 9 3% and 3% to 7%, respectively, with corresponding safety ratings. Additionally, task computations elucidate the duratio ns, start dates, end dates,and resource allocations for individual tasks within construction projects. Lastly, classification results exhibitthe predicted pro babilities and class labels for samples, showcasing the platform's ability to ac curatelypredict project outcomes."

原文链接:

NETL
NSTL

Shenzhen University Researchers Discuss Research in Robotics (Enhancing Trajecto ry Tracking and Vibration Control of Flexible Robots With Hybrid Fuzzy ADRC and Input Shaping)

134-135页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews-New research on robotics is the subject of a new report. According to news originating fromShenzhen, People's Republic of China, by NewsRx correspondents, research stated, "Flexible robot systemsare importan t in a variety of academic and industrial settings. Introducing innovative ideas for improvingtheir performance is always valuable due to their wide range of p ractical applications."Funders for this research include Middle East University, Jordan; National Natur al Science Foundationof China; Guangdong Province Basic And Applied Research Ma jor Project Fund; Shenzhen University2035 Program For Excellent Research; Equip ment Development Project of Shenzhen University.The news reporters obtained a quote from the research from Shenzhen University: "Compared totraditional methods, the utilization of soft computing techniques c an improve the overall performance bypredicting and optimizing the outcomes. Th is research proposes a hybrid control method that combinesinput shaping with fu zzy active disturbance rejection control for a flexible joint robotic manipulato rwith unknown perturbations and parametric uncertainties. The suggested algorit hm's control objectiveis to adapt and learn in different real-world scenarios t o accurately follow the required trajectories whiledampening the system's vibra tions. Overshoot is reduced, and reaction time is increased by employing aninpu t shaping approach, while the extended state observer is built to handle unexpec ted perturbations anduncertainties in parameters. Additionally, fuzzy logic adj usts the linear feedback control law gains onlineto boost the control system's dynamic capability. Compared with active disturbance rejection controller,inter val type-2 fuzzy logic controller, input shaping-active disturbance rejection co ntroller, modified linearactive disturbance rejection controller, genetic algor ithm-fuzzy logic controller, and fuzzy-tuned PID, theexperimental results indic ate that the hybrid input shaping enhanced fuzzy based active disturbance rejection controller control law is efficient and resilient."

原文链接:

NETL
NSTL