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

    Data on Machine Learning Discussed by Researchers at School of Aeronautics and A stronautics (Aerodynamic Force Prediction of Compressor Blade Surfaces Based On Machine Learning)

    134-135页
    查看更多>>摘要：Investigators publish new report on Ma chine Learning. According to news reporting originating from Tianjin, People's R epublic of China, by NewsRx correspondents, research stated, "The flow field dis tribution of compressor blades is critical to the performance of aero-engine. To efficiently obtain the aerodynamic loads on the blades, this study employs mach ine learning models to predict the aerodynamic characteristics of compressor bla de surfaces." Funders for this research include National Natural Science Foundation of China ( NSFC), National Natural Science Foundation of China (NSFC), Natural Science Foun dation of Tianjin. Our news editors obtained a quote from the research from the School of Aeronauti cs and Astronautics, "The predictive performances of these models are evaluated by applying random forest, multi-layer perceptron (MLP), one-dimensional convolu tional neural network, and long short-term memory network based on simulation da ta of computational fluid dynamics (CFD). The results indicate that the MLP mode l performs exceptionally well among all test metrics, with its predictions close ly matching the CFD simulation results. Further analysis using SHapley Additive exPlanations methods is performed to interpret the MLP model and reveal the impo rtance of various input features."
      原文链接:
    • NETL
    • NSTL

    Reports Summarize Machine Learning Findings from Rajasthan Technical University (Assessment of Short and Long-term Pozzolanic Activity of Natural Pozzolans Usin g Machine Learning Approaches)

    135-136页
    查看更多>>摘要：Researchers detail new data in Machine Learning. According to news originating from Rajasthan, India, by NewsRx corres pondents, research stated, "This investigation introduces the optimal performanc e models for predicting the compressive strength (CS) and pozzolanic activity in dex (PAI) by comparing the machine learning models. The machine learning models, i.e., multilinear regression (MLR), support vector machine (SVM), gaussian proc ess regression (GPR), decision tree (DT), random forest (RF), and gene expressio n programming (GEP) have been trained (TRN) and tested (TST) by 28 and 7 data po ints." Our news journalists obtained a quote from the research from Rajasthan Technical University, "For the first time, the SiO2, Al2O3, Fe2O3, SiO2 +Al2O3 +Fe2O3, re active SiO2, Blaine specific surface area, and specific gravity have been used a s input variables to compute the CS, and 28 days PAI (28PAI), and 90 days PAI (9 0PAI) of the natural pozzolans. The multicollinearity analysis showed the SiO2, Al2O3, Fe2O3, SiO2 +Al2O3 +Fe2O3, reactive SiO2, and specific gravity have probl ematic multicollinearity (variance inflation factor - VIF > 10). Therefore, the root mean square error (RMSE), mean absolute error (MAE), c orrelation coefficient ®, performance index (PI), and variance accounted for (VA F) metrics have been implemented to evaluate the model's performance and multico llinearity impact. From the comparison of models, it has been recorded that mode l GPR outperformed the MLR, SVM, DT, RF, and GEP models in predicting CS (PI = 1 .29, VAF = 71.31, R = 0.8473, MAE = 0.9390 MPa), 28PAI (PI = 1.87, VAF = 94.88, R = 0.9744, MAE = 0.7295 %), and 90PAI (PI = 1.72, VAF = 88.11, R = 0.9393, MAE = 1.2444 %) in the TST phase, close to ideal values. T he score, generalizability."
      原文链接:
    • NETL
    • NSTL

    Investigators at University of Palermo Detail Findings in Robotics and Machine L earning (Comparison of Different Computer Vision Methods for Vineyard Canopy Det ection Using Uav Multispectral Images)

    136-137页
    查看更多>>摘要：Investigators discuss new findings in Robotics and Machine Learning. According to news reporting originating in Palerm o, Italy, by NewsRx journalists, research stated, "In viticulture, the rapid and accurate acquisition of canopy spectral information through ultra-high spatial resolution imagery is increasingly demanded for decision support. The prevalent practice involves creating vigor maps using spectral data obtained from pure vin e canopy pixels." Financial support for this research came from Ministry of Education, Universitie s and Research (MIUR). The news reporters obtained a quote from the research from the University of Pal ermo, "Based Image Analysis (OBIA) among conventional methods exhibits a reasona ble efficiency in canopy classification due to its feature extraction capabiliti es. In recent years, deep learning (DL) techniques have demonstrated significant potential in orchard monitoring, leveraging their ability to automatically lear n image features. This study assessed the performance of different methodologies , including Mask R-CNN, U-Net, OBIA and unsupervised methods, in identifying pur e canopy pixels. The effectiveness of shadow and background detection methods an d the impact of misclassified pixels on NDVI were compared. Results were compare d with agronomic surveys conducted during the 2021 and 2022 growing seasons, foc using on two distinct phenological stages (BBCH65-BBCH85). Mask R-CNN and U-Net exhibited superior performance in terms of Overall Accuracy (OA), F1-score, and Intersection Over Union (IoU). Among OBIA methods, the Gaussian Mixture Model (G MM) proved to be the most effective classifier for canopy segmentation, and Supp ort Vector Machine (SVM) also demonstrated reasonable stability. Conversely, Ran dom Forest (RF) and K-Means yielded lower accuracy and higher error rates. As a result of the limited accuracy, it is noted for vineyard rows with low vigor can opies that NDVI was overestimated, while for high vigor canopies NDVI was undere stimated. Significantly improved determination coefficients were observed for th e comparison between Total Leaf Area (TLA) and NDVI data derived from Mask R-CNN and U-Net. Positive correlations were also found with NDVI data from GMM and SV M algorithms. Regarding leaf chlorophyll (Chl) and NDVI correlations, Mask R-CNN and U-Net methods showed superior performance.
      原文链接:
    • NETL
    • NSTL

    Studies in the Area of Artificial Intelligence Reported from INAIL (Prosthetist- Specific Rectification Templates Based on Artificial Intelligence for the Digita l Fabrication of Custom Transtibial Sockets)

    137-138页
    查看更多>>摘要：New study results on artificial intell igence have been published. According to news originating from INAIL by NewsRx c orrespondents, research stated, "The socket is the most important, patient-speci fic element of a prosthesis." Financial supporters for this research include Assistant Secretary of Defense Fo r Health Affairs; Inail. The news correspondents obtained a quote from the research from INAIL: "Conventi onally, the process of making a custom socket involves manually rectifying a pla ster model of the residual limb. This process is time-consuming and often incons istent among prosthetists because it is based on implicit knowledge. Hence, the aim of this work was to describe a novel process of generating a prosthetist-spe cific, digital "global" template and to illustrate that it can be automatically applied to rectify the shape of a transtibial residual limb. The process involve d (1) the acquisition of a "training" dataset of unrectified and rectified posit ive models through manual data collection and digital 3D scanning, and (2) the u nsupervised learning of the prosthetist's rectifications by an artificial intell igence (AI) algorithm. The assessment of the process involved (1) evaluating whe ther the rectification rule learned by the AI was consistent with the prosthetis t's expectations, and (2) evaluating the template feasibility by applying the AI rectification process to a new residual limb and comparing the results to the p rosthetist's manual rectification for the same residual limb. The results sugges t that the AI-rectified positive was consistent with the approach described by the prosthetist, with only small radial and angle errors and similar dimensions ( volume and cross-sectional perimeters) as the hand-rectified positive."
      原文链接:
    • NETL
    • NSTL

    New Findings from University of Vigo in the Area of Machine Learning Described ( On the Machine Learning-assisted Identification of the Fundamental Parameters of Nonstandard Microfin Arrays To Assess Their Heat Transfer Performance)

    138-139页
    查看更多>>摘要：Investigators publish new report on Ma chine Learning. According to news reporting originating in Vigo, Spain, by NewsR x journalists, research stated, "Microfin design for industrial applications has been extensively studied in the past, but the use of innovative techniques that can reveal hitherto unfamiliar morphologies realizable with novel additive manu facturing techniques has not yet been fully exploited. Here, an attempt is made to develop a structured methodology for the assessment of various randomly gener ated geometries, with the purpose of identifying the most significant geometrica l parameters for their thermohydraulic performance." Funders for this research include University of Vigo, Universidade de Vigo/CISUG .
      原文链接:
    • NETL
    • NSTL

    Studies Conducted at University of Technology-Iraq on Intelligent Systems Recent ly Published (Optimal design of linear and nonlinear PID controllers for speed c ontrol of an electric vehicle)

    139-140页
    查看更多>>摘要：Current study results on intelligent s ystems have been published. According to news reporting from Baghdad, Iraq, by N ewsRx journalists, research stated, "Electric vehicles (EVs) as a sustainable sa fety system are being increasingly used and receiving attention from researchers for several reasons including optimal performance, affordability for consumers, and environmental safety. EV speed control is a crucial issue that requires rel iable and intelligent controllers for maintaining this matter." Our news editors obtained a quote from the research from University of Technolog y-Iraq: "The primary goal of this research is to design the linear and nonlinear Proportional, Integral, and Derivative (PID) controllers to control EV speed ba sed on the minimum value of ITAE plus ISU (integral square of control signal) as well as satisfy the constrain on response overshoot. All the proposed PID contr ollers, conventional PID controller, arc tan PID controller, and nonlinear PID c ontroller (NL-PID) are used in cascade with EV model. In all these PID controlle rs, a filter is used with the derivative term to avoid the effect of the noise. The tuning of the proposed controller gains is achieved using Aquila Optimizatio n algorithm. The controllers' parameter tuning is primarily determined by reduci ng the Integral Time Absolute Error (ITAE) and integral square control signal. N umerical simulation, system modelling, and controller design are done using MATL AB. By comparing the results, the proposed controllers' efficacy is demonstrated ."
      原文链接:
    • NETL
    • NSTL

    Recent Findings from Shanghai University Highlight Research in Robotics (Autonom ous mobile construction robots in built environment: A comprehensive review)

    140-141页
    查看更多>>摘要：Data detailed on robotics have been pr esented. According to news reporting originating from Shanghai, People's Republi c of China, by NewsRx correspondents, research stated, "Combined robotic arms an d mobile platforms, mobile construction robots(MCRs) are providing an energizing choice for the digitalization of the building industry." Funders for this research include Nsfc. Our news reporters obtained a quote from the research from Shanghai University: "To enhance the comprehension of the research trajectory towards MCR application s and technologies in building construction, we focus on the following aspect: C urrent representative applications of MCRs in built environments and critical te chnologies involved. This comprehensive review identified 184 publications in th e last 15 years to unravel MCRs in construction applications, scrutinized the cr ucial technologies involved, and deliberated on challenges and opportunities. Re sults indicate that MCRs are a growing application field, although the majority are still confined to laboratory settings. To further expand the application of MCR in construction scenarios, this paper proposes corresponding research roadma ps to address the challenges identified."
      原文链接:
    • NETL
    • NSTL

    University of California Researcher Publishes Findings in Machine Learning (Simu lation-Based Optimization for Vertiport Location Selection: A Surrogate Model Wi th Machine Learning Method)

    141-142页
    查看更多>>摘要：New study results on artificial intell igence have been published. According to news reporting originating from Berkele y, California, by NewsRx correspondents, research stated, "We present Vertiport- informed Surrogate-Based Optimization with Machine Learning Surrogates (VinS), a novel framework for solving the vertiport location problem for urban air mobili ty operations." Our news journalists obtained a quote from the research from University of Calif ornia: "The primary focus of this work is on the optimization of vertiport locat ions to facilitate efficient urban air transportation. Our framework helps choos e not only the optimal vertiport locations but also the optimal number of vertip orts. We develop a simulation model to analyze the impacts of various vertiport location configurations on the efficiency of the transportation network. To expe dite the simulation process, a surrogate model is trained using machine learning algorithms, effectively reducing the computational time for evaluating a given vertiport location configuration. With the machine learning surrogate models, we apply a genetic algorithm to find the optimal set of vertiport locations."
      原文链接:
    • NETL
    • NSTL

    Researcher at Beijing Institute of Technology Zeroes in on Robotics (Multi-scale deep learning and clustering-based tabletop object instance segmentation for ro bot manipulation)

    142-142页
    查看更多>>摘要：Data detailed on robotics have been pr esented. According to news reporting originating from Beijing, People's Republic of China, by NewsRx correspondents, research stated, "3D object instance segmen tation plays a vital role in various applications such as autonomous driving, ro botics and virtual reality." Financial supporters for this research include National Natural Science Foundati on of China; Beijing Natural Science Foundation; National Key Laboratory of Huma n Factors Engineering; Beijing Institute of Technology Research Fund Program For Young Scholars.
      原文链接:
    • NETL
    • NSTL

    Tsinghua University Reports Findings in Machine Learning (Dual cross-linked magn etic gelatin/carboxymethyl cellulose cryogels for enhanced Congo red adsorption: Experimental studies and machine learning modelling)

    143-143页
    查看更多>>摘要：New research on Machine Learning is th e subject of a report. According to news reporting originating from Beijing, Peo ple's Republic of China, by NewsRx correspondents, research stated, "To achieve highly efficient and environmentally degradable adsorbents for Congo red (CR) re moval, we synthesized a dual-network nanocomposite cryogel composed of gelatin/c arboxymethyl cellulose, loaded with FeO nanoparticles. Gelatin and sodium carbox ymethylcellulose were cross-linked using transglutaminase and calcium chloride, respectively." Our news editors obtained a quote from the research from Tsinghua University, "T he cross-linking process enhanced the thermal stability of the composite cryogel s. The CR adsorption process exhibited a better fit to the pseudo-second-order m odel and Langmuir model, with maximum adsorption capacity of 698.19 mg/g at pH o f 7, temperature of 318 K, and initial CR concentration of 500 mg/L. Thermodynam ic results indicated that the CR adsorption process was both spontaneous and end othermic. The performance of machine learning model showed that the Extreme Grad ient Boosting model had the highest test determination coefficient (R = 0.9862) and the lowest root mean square error (RMSE = 10.3901 mg/g) among the 6 models. Feature importance analysis using SHapley Additive exPlanations (SHAP) revealed that the initial concentration had the greatest influence on the model's predict ion of adsorption capacity. Density functional theory calculations indicated tha t there were active sites on the CR molecule that can undergo electrostatic inte ractions with the adsorbent."
      原文链接:
    • NETL
    • NSTL