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

    First Affiliated Hospital of Gannan Medical University Reports Findings in Thymo ma (Application of machine learning for the differentiation of thymomas and thym ic cysts using deep transfer learning: A multi-center comparison of diagnostic . ..)

    107-107页
    查看更多>>摘要：New research on Lymphatic Diseases and Conditions -Thymoma is the subject of a report. According to news originating from Ganzhou, People's Republic of China, by NewsRx correspondents, research sta ted, "This study aimed to evaluate the feasibility and performance of deep trans fer learning (DTL) networks with different types and dimensions in differentiati ng thymomas from thymic cysts in a retrospective cohort. Based on chest-enhanced computed tomography (CT), the region of interest was delineated, and the maximu m cross section of the lesion was selected as the input image." Our news journalists obtained a quote from the research from the First Affiliate d Hospital of Gannan Medical University, "Five convolutional neural networks (CN Ns) and Vision Transformer (ViT) were used to construct a 2D DTL model. The 2D m odel constructed by the maximum section (n) and the upper and lower layers (n -1, n + 1) of the lesion was used for feature extraction, and the features were s elected. The remaining features were pre-fused to construct a 2.5D model. The wh ole lesion image was selected for input and constructing a 3D model. In the 2D m odel, the area under curve (AUC) of Resnet50 was 0.950 in the training cohort an d 0.907 in the internal validation cohort. In the 2.5D model, the AUCs of Vgg11 in the internal validation cohort and external validation cohort 1 were 0.937 an d 0.965, respectively. The AUCs of Inception_v3 in the training coh ort and external validation cohort 2 were 0.981 and 0.950, respectively. The AUC values of 3D_Resnet50 in the four cohorts were 0.987, 0.937, 0.938 , and 0.905."
      原文链接:
    • NETL
    • NSTL

    University of Montreal Reports Findings in Machine Learning (Spatial and spatiot emporal modelling of intra-urban ultrafine particles: A comparison of linear, no nlinear, regularized, and machine learning methods)

    108-108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 Montreal, Ca nada, by NewsRx correspondents, research stated, "Machine learning methods are p roposed to improve the predictions of ambient air pollution, yet few studies hav e compared ultrafine particles (UFP) models across a broad range of statistical and machine learning approaches, and only one compared spatiotemporal models. Mo st reported marginal differences between methods." Our news editors obtained a quote from the research from the University of Montr eal, "This limits our ability to draw conclusions about the best methods to mode l ambient UFPs. To compare the performance and predictions of statistical and ma chine learning methods used to model spatial and spatiotemporal ambient UFPs. Da ily and annual models were developed from UFP measurements from a year-long mobi le monitoring campaign in Quebec City, Canada, combined with 262 geospatial and six meteorological predictors. Various road segment lengths were considered (100 /300/500 m) for UFP data aggregation. Four statistical methods included linear, non-linear, and regularized regressions, whereas eight machine learning regressi ons utilized tree-based, neural networks, support vector, and kernel ridge algor ithms. Nested cross-validation was used for model training, hyperparameter tunin g and performance evaluation. Mean annual UFP concentrations was 13,335 particle s/cm. Machine learning outperformed statistical methods in predicting UFPs. Tree -based methods performed best across temporal scales and segment lengths, with X GBoost producing the overall best performing models (annual R = 0.78-0.86, RMSE = 2163-2169 particles/ cm; daily R = 0.47-0.48, RMSE = 8651-11,422 particles/cm). With 100 m segments, other annual models performed similarly well, but their pr ediction surfaces of annual mean UFP concentrations showed signs of overfitting. Spatial aggregation of monitoring data significantly impacted model performance . Longer segments yielded lower RMSE in all daily models and for annual statisti cal models, but not for annual machine learning models. The use of tree-based me thods significantly improved spatiotemporal predictions of UFP concentrations, a nd to a lesser extent annual concentrations."
      原文链接:
    • NETL
    • NSTL

    Kunming University Details Findings in Robotics (Kinematic Calibration for Seria l Robots Based On a Vector Inner Product Error Model)

    109-109页
    查看更多>>摘要：Investigators publish new report on Ro botics. According to news reporting out of Kunming, People's Republic of China, by NewsRx editors, research stated, "The positioning accuracy of articulated ser ial robots in the workpiece coordinate system (WCS) is vital for practical appli cations, as command positions or planned paths are typically defined in WCS. How ever, conventional error models for kinematic calibration primarily focus on pos itioning accuracy in the base coordinate system (BCS), without adequately fulfil ling the accuracy requirements of WCS." Funders for this research include National Natural Science Foundation of China ( NSFC), Yunnan Major Scientific and Technological Projects.
      原文链接:
    • NETL
    • NSTL

    Findings from Georgia Institute of Technology Update Knowledge of Machine Learni ng (Screening Environmentally Benign Ionic Liquids for Co2 Absorption Using Repr esentation Uncertainty-based Machine Learning)

    110-110页
    查看更多>>摘要：Current study results on Machine Learn ing have been published. According to news originating from Atlanta, Georgia, by NewsRx correspondents, research stated, "Screening ionic liquids (ILs) with low viscosity, low toxicity, and high CO2 absorption using machine learning (ML) mo dels is crucial for mitigating global warming. However, when candidate ILs fall into the extrapolation zone of ML models, predictions may become unreliable, lea ding to poor decision-making." Funders for this research include United States Department of Agriculture (USDA) , National Science Foundation (NSF), National Science Foundation-U.S. Department of Agriculture, National Natural Science Foundation of China (NSFC).
      原文链接:
    • NETL
    • NSTL

    New Findings from Arizona State University Update Understanding of Machine Learn ing (Comprehensive Study of Medications Solubility In Supercritical Co2 With and Without Co-solvent; Laboratory, Theoretical, and Intelligent Approaches)

    111-112页
    查看更多>>摘要：Current study results on Machine Learn ing have been published. According to news reporting originating in Phoenix, Ari zona, by NewsRx journalists, research stated, "Determining the dissolution chara cteristics of medicines in supercritical CO2 is vital for formulating innovative drug delivery systems through an efficient supercritical process. This study in vestigates the solubility of three poorly bioavailable drugs -Topiramate, Mecliz ine, and Dimenhydrinate-in supercritical CO2, both with and without ethanol co-solvent, over a temperature range of 308 K to 348 K and pressures from 17 MPa to 41 MPa." The news reporters obtained a quote from the research from Arizona State Univers ity, "The solubility of these medicines in supercritical CO2 (binary system) is notably low, ranging from 2.5 x 10-6 4.54 x 10-6, 0.26 x 10-5 -2.3 x 10-5, and 0.20 x 10-5 -1.91 x 10-5 in mole fraction, respectively. However, in the presen ce of ethanol (ternary system), their supercritical solubility significantly inc reases by factors of 2.75-5.84, 1.40-3.20, and 2.04-4.85, respectively. The supe rcritical solubility of the mentioned compounds are theoretically evaluated usin g several approaches, including empirical models, a machine learning methodology employing a multilayer perceptron neural network, thermodynamic models based on two cubic equations of state (Peng-Robinson (PR) and Soave-Redlich-Kwong (SRK)) , and a non-cubic equation of state (perturbed chain-statistical associating flu id theory (PC-SAFT)), as well as two expanded liquid models (UNIQUAC and Wilson) . The findings revealed that all the specified models demonstrate acceptable acc uracy in correlating the experimental data of the specified drugs in both binary and ternary systems. Among these, the PR and SRK thermodynamic models, along wi th some empirical models, show the best results."
      原文链接:
    • NETL
    • NSTL

    New Data from University of Seville Illuminate Findings in Machine Learning (Cha llenges Reconciling Theory and Experiments In the Prediction of Lattice Thermal Conductivity: the Case of Cu-based Sulvanites)

    112-112页
    查看更多>>摘要：Investigators publish new report on Ma chine Learning. According to news reporting out of Seville, Spain, by NewsRx edi tors, research stated, "The exploration of large chemical spaces in search of ne w thermoelectric materials requires the integration of experiments, theory, simu lations, and data science. The development of high-throughput strategies that co mbine DFT calculations with machine learning has emerged as a powerful approach to discovering new materials." Financial supporters for this research include European Union Next Generation EU /PRTR, Comunidad de Madrid, MICIU/AEI, Red Espanola de Supercomputacion, RES. Our news journalists obtained a quote from the research from the University of S eville, "However, experimental validation is crucial to confirm the accuracy of these workflows. This validation becomes especially important in understanding t he transport properties that govern the thermoelectric performance of materials since they are highly influenced by synthetic, processing, and operating conditi ons. In this work, we explore the thermal conductivity of Cu-based sulvanites by using a combination of theoretical and experimental methods. Previous discrepan cies and significant variations in reported data for Cu3VS4 and Cu3VSe4 are expl ained using the Boltzmann Transport Equation for phonons and by synthesizing wel l-characterized defect-free samples."
      原文链接:
    • NETL
    • NSTL

    Singidunum University Researcher Has Provided New Data on Machine Learning (Expl oring Metaheuristic Optimized Machine Learning for Software Defect Detection on Natural Language and Classical Datasets)

    113-113页
    查看更多>>摘要：Investigators publish new report on ar tificial intelligence. According to news reporting from Belgrade, Serbia, by New sRx journalists, research stated, "Software is increasingly vital, with automate d systems regulating critical functions. As development demands grow, manual cod e review becomes more challenging, often making testing more time-consuming than development." Funders for this research include Science Fund of The Republic of Serbia; Charac terizing Crises-caused Air Pollution Alternations Using An Artificial Intelligen ce-based Framework. The news correspondents obtained a quote from the research from Singidunum Unive rsity: "A promising approach to improving defect detection at the source code le vel is the use of artificial intelligence combined with natural language process ing (NLP). Source code analysis, leveraging machine-readable instructions, is an effective method for enhancing defect detection and error prevention. This work explores source code analysis through NLP and machine learning, comparing class ical and emerging error detection methods. To optimize classifier performance, m etaheuristic optimizers are used, and algorithm modifications are introduced to meet the study's specific needs. The proposed two-tier framework uses a convolut ional neural network (CNN) in the first layer to handle large feature spaces, wi th AdaBoost and XGBoost classifiers in the second layer to improve error identif ication. Additional experiments using term frequency-inverse document frequency (TF-IDF) encoding in the second layer demonstrate the framework's versatility."
      原文链接:
    • NETL
    • NSTL

    Findings from University of Belgrade Update Knowledge of Machine Learning (Machi ne and Deep Learning Methods for Concrete Strength Prediction: a Bibliometric an d Content Analysis Review of Research Trends and Future Directions)

    114-114页
    查看更多>>摘要：Investigators publish new report on Ma chine Learning. According to news reporting originating from Belgrade, Serbia, b y NewsRx correspondents, research stated, "This review paper provides a detailed evaluation of the existing landscape and future trends in applying machine lear ning and deep learning approaches for predicting concrete strength in constructi on engineering. The study contextualizes the investigation of machine learning a nd deep learning in concrete strength prediction, emphasizing the need for preci se strength forecasting in construction." Financial support for this research came from Deanship of Scientific Research at King Khalid University, Abha, Saudi Arabia.
      原文链接:
    • NETL
    • NSTL

    Studies from Southeast University in the Area of Robotics Described (Magnetic To rque-driven All-terrain Microrobots)

    115-115页
    查看更多>>摘要：Investigators publish new report on Ro botics. According to news originating from Nanjing, People's Republic of China, by NewsRx correspondents, research stated, "All-terrain microrobots possess sign ificant potential in modern medical applications due to their superior maneuvera bility in complex terrains and confined spaces. However, conventional microrobot s often struggle with adaptability and operational difficulties in variable envi ronments." Funders for this research include National Natural Science Foundation of China ( NSFC), Natural Science Foundation of Jiangsu Province, Fundamental Research Fund s for the Central Universities.
      原文链接:
    • NETL
    • NSTL

    New Support Vector Machines Study Findings Have Been Reported by Investigators a t University of Monastir (Attack Detection In Iot Network Using Support Vector M achine and Improved Feature Selection Technique)

    116-116页
    查看更多>>摘要：Researchers detail new data in Support Vector Machines. According to news originating from Monastir, Tunisia, by NewsR x correspondents, research stated, "As a result of the rapid advancement of tech nology, the Internet of Things (IoT) has emerged as an essential research questi on, capable of collecting and sending data through a network between linked item s without the need for human interaction. However, these interconnected devices often encounter challenges related to data security, encompassing aspects of con fidentiality, integrity, availability, authentication, and privacy, particularly when facing potential intruders." Our news journalists obtained a quote from the research from the University of M onastir, "Addressing this concern, our study propose a novel host-based intrusio n detection system grounded in machine learning. Our approach incorporates a fea ture selection (FS) technique based on the correlation between features and a ra nking function utilizing Support Vector Machine (SVM). The experimentation, cond ucted on the NSL-KDD dataset, demonstrates the efficacy of our methodology. The results showcase superiority over comparable approaches in both binary and multi -class classification scenarios, achieving remarkable accuracy rates of 99.094% and 99.11%, respectively."
      原文链接:
    • NETL
    • NSTL