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

    Researchers at University of Florence Zero in on Machine Learning (Development a nd machine learning-based calibration of low-cost multiparametric stations for t he measurement of CO2 and CH4 in air)

    28-28页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Data detailed on artificial intelligen ce have been presented. According to news reporting from Firenze, Italy, by News Rx journalists, research stated, “The pressing issue of atmospheric pollution ha s prompted the exploration of affordable methods for measuring and monitoring ai r contaminants as complementary techniques to standard methods, able to produce high-density data in time and space.” Our news reporters obtained a quote from the research from University of Florenc e: “The main challenge of this low-cost approach regards the in-field accuracy a nd reliability of the sensors. This study presents the development of low-cost s tations for high-time resolution measurements of CO2 and CH4 concentrations cali brated via an in-field machine learning-based method. The calibration models wer e built based on measurements parallelly performed with the low-cost sensors and a CRDS analyzer for CO2 and CH4 as reference instrument, accounting for air tem perature and relative humidity as external variables. To ensure versatility acro ss locations, diversified datasets were collected, consisting of measurements pe rformed in various environments and seasons. The calibration models, trained wit h 70 % for modeling, 15 % for validation, and 15 % for testing, demonstrated robustness with CO2 and CH4 predictions achieving R2 v alues from 0.8781 to 0.9827 and 0.7312 to 0.9410, and mean absolute errors rangi ng from 3.76 to 1.95 ppm and 0.03 to 0.01 ppm, for CO2 and CH4, respectively.”
      原文链接:
    • NETL
    • NSTL

    Nanyang Technological University Reports Findings in Machine Learning (RmsdXNA: RMSD prediction of nucleic acid-ligand docking poses using machine-learning meth od)

    29-30页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting originating from Singapore, S ingapore, by NewsRx correspondents, research stated, “Small molecule drugs can b e used to target nucleic acids (NA) to regulate biological processes. Computatio nal modeling methods, such as molecular docking or scoring functions, are common ly employed to facilitate drug design.” Our news editors obtained a quote from the research from Nanyang Technological U niversity, “However, the accuracy of the scoring function in predicting the clos est-to-native docking pose is often suboptimal. To overcome this problem, a mach ine learning model, RmsdXNA, was developed to predict the root-meansquare- devia tion (RMSD) of ligand docking poses in NA complexes. The versatility of RmsdXNA has been demonstrated by its successful application to various complexes involvi ng different types of NA receptors and ligands, including metal complexes and sh ort peptides. The predicted RMSD by RmsdXNA was strongly correlated with the act ual RMSD of the docked poses. RmsdXNA also outperformed the rDock scoring functi on in ranking and identifying closest-to-native docking poses across different s tructural groups and on the testing dataset. Using experimental validated result s conducted on polyadenylated nuclear element for nuclear expression triplex, Rm sdXNA demonstrated better screening power for the RNA-small molecule complex com pared to rDock. Molecular dynamics simulations were subsequently employed to val idate the binding of top-scoring ligand candidates selected by RmsdXNA and rDock on MALAT1. The results showed that RmsdXNA has a higher success rate in identif ying promising ligands that can bind well to the receptor. The development of an accurate docking score for a NA-ligand complex can aid in drug discovery and de velopment advancements.”
      原文链接:
    • NETL
    • NSTL

    Studies from Florida State University Provide New Data on Machine Learning (Ense mble Learning Approach for Developing Performance Models of Flexible Pavement)

    30-31页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in artific ial intelligence. According to news originating from Tallahassee, Florida, by Ne wsRx editors, the research stated, “This research utilizes the Long- Term Pavemen t Performance database, focusing on devel-oping a predictive model for flexible pavement performance in the Southern United States.” The news journalists obtained a quote from the research from Florida State Unive rsity: “Analyzing 367 pavement sections, this study investigates crucial factors influencing asphaltic concrete (AC) pavement deterioration, such as structural and material components, air voids, compaction density, temperature at laydown, traffic load, precipitation, and freeze-thaw cycles. The objective of this study is to develop a predictive machine learning model for AC pavement wheel path cr acking (WpCrAr) and the age at which cracking initiates (WpCrAr) as performance indicators. This study thoroughly investigated three ensemble machine learning m odels, including random forest, extremely randomized trees (ETR), and extreme gr adient boosting (XGBoost). It was observed that XGBoost, optimized using Bayesia n methods, emerged as the most effective among the evaluated models, demonstrati ng good predictive accuracy, with an R2 of 0.79 for WpCrAr and 0.92 for AgeCrack and mean absolute errors of 1.07 and 0.74, respectively.”
      原文链接:
    • NETL
    • NSTL

    Studies from University of Manchester in the Area of Artificial Intelligence Des cribed (Artificial Intelligence In Nursing and Midwifery: a Systematic Review)

    31-32页
    查看更多>>摘要：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 reporting from Manchester, United Kingd om, by NewsRx journalists, research stated, “Artificial Intelligence (AI) techni ques are being applied in nursing and midwifery to improve decision-making, pati ent care and service delivery. However, an understanding of the real-world appli cations of AI across all domains of both professions is limited.” The news correspondents obtained a quote from the research from the University o f Manchester, “To synthesise literature on AI in nursing and midwifery. CINAHL, Embase, PubMed and Scopus were searched using relevant terms. Titles, abstracts and full texts were screened against eligibility criteria. Data were extracted, analysed, and findings were presented in a descriptive summary. The PRISMA check list guided the review conduct and reporting. One hundred and forty articles wer e included. Nurses’ and midwives’ involvement in AI varied, with some taking an active role in testing, using or evaluating AI-based technologies; however, many studies did not include either profession. AI was mainly applied in clinical pr actice to direct patient care (n = 115, 82.14%), with fewer studies focusing on administration and management (n = 21, 15.00%), or edu cation (n = 4, 2.85%). Benefits reported were primarily potential a s most studies trained and tested AI algorithms. Only a handful (n = 8, 7.14% ) reported actual benefits when AI techniques were applied in real-world setting s. Risks and limitations included poor quality datasets that could introduce bia s, the need for clinical interpretation of AI-based results, privacy and trust i ssues, and inadequate AI expertise among the professions. Digital health dataset s should be put in place to support the testing, use, and evaluation of AI in nu rsing and midwifery. Curricula need to be developed to educate the professions a bout AI, so they can lead and participate in these digital initiatives in health care.”
      原文链接:
    • NETL
    • NSTL

    Data on Artificial Intelligence Reported by Xiaoshuai Hou and Colleagues (Artifi cial intelligence assists identification and pathologic classification of glomer ular lesions in patients with diabetic nephropathy)

    32-33页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Artificial Intelligenc e is the subject of a report. According to news reporting originating in Shangha i, People’s Republic of China, by NewsRx journalists, research stated, “Glomerul ar lesions are the main injuries of diabetic nephropathy (DN) and are used as a crucial index for pathologic classification. Manual quantification of these morp hologic features currently used is semiquantitative and time-consuming.” Financial supporters for this research include National Natural Science Foundati on of China, Medical Scientific Research Project of Jiangsu Provincial Health Co mmission, National Key Research and Development Program of China.
      原文链接:
    • NETL
    • NSTL

    Researchers from Universiti Sains Islam Malaysia Discuss Research in Robotics (A utonomous Person-Following Telepresence Robot Using Monocular Camera and Deep Le arning YOLO)

    33-34页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Research findings on robotics are disc ussed in a new report. According to news originating from the Universiti Sains I slam Malaysia by NewsRx correspondents, research stated, “Telepresence robots (T Rs) are increasingly important for remote communication and collaboration, parti cularly in situations where physical presence is not possible.” The news correspondents obtained a quote from the research from Universiti Sains Islam Malaysia: “One key feature of TRs is person-following, which relies on th e detection and distance estimation of individuals. This study proposes an auton omous person-following TR using a monocular camera and deep-learning YOLO for pe rson detection and distance estimation. To compensate for the monocular camera’s inability to provide depth information, a novel distance estimation algorithm b ased on focal length and person width is introduced. The estimated width informa tion of the detected person is extracted from the bounding box generated by YOLO . A pre-trained model using the MS COCO dataset is employed with YOLO for the pe rson detection task. For robot movement control, a region-based controller is pr oposed to enable the robot to move based on the detected person’s location in th e image captured by the camera.”
      原文链接:
    • NETL
    • NSTL

    Investigators from University of California Berkeley Target Machine Learning (A Machine-learning Enabled Digital-twin Framework for the Rapid Design of Satellit e Constellations for 'planet-x.')

    34-35页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in Machine Learning. According to news reporting from Berkeley, California, by NewsRx edit ors, the research stated, “Worldwide communication bandwidth growth has largely been driven by (1) multimedia demands, (2) multicommunication-point demands and (3) multicommunication-rate demands, and has increased dramatically over the las t two decades due to e-commerce, internet communication and the explosion of cel l-phone use, in particular for in-flight services, all of which necessitate broa dband use and low latency. In order to accommodate this huge surge in demand, ne xt generation ‘mega-constellations’ of satellites are being proposed combining a mix of heterogeneous unit types in LEO, MEO and GEO orbital shells, in order to provide continuous lowerlatency and high-bandwidth service which exploits a wi de-range of frequencies for fast internet connections (broadband, which is not p ossible with single satellite-type orbital shell systems).” Financial support for this research came from UC Berkeley College of Engineering .
      原文链接:
    • NETL
    • NSTL

    Department of Obstetrics and Gynecology Reports Findings in Acute Kidney Injury (Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in C ritically Ill Elderly Patients During Hospitalization: Internet-Based and ...)

    35-36页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Kidney Diseases and Co nditions - Acute Kidney Injury is the subject of a report. According to news rep orting from Dalian, People’s Republic of China, by NewsRx journalists, research stated, “Acute kidney disease (AKD) affects more than half of critically ill eld erly patients with acute kidney injury (AKI), which leads to worse short-term ou tcomes. We aimed to establish 2 machine learning models to predict the risk and prognosis of AKD in the elderly and to deploy the models as online apps.” The news correspondents obtained a quote from the research from the Department o f Obstetrics and Gynecology, “Data on elderly patients with AKI (n=3542) and AKD (n=2661) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) dat abase were used to develop 2 models for predicting the AKD risk and in-hospital mortality, respectively. Data collected from Xiangya Hospital of Central South U niversity were for external validation. A bootstrap method was used for internal validation to obtain relatively stable results. We extracted the indicators wit hin 24 hours of the first diagnosis of AKI and the fluctuation range of some ind icators, namely delta (day 3 after AKI minus day 1), as features. Six machine le arning algorithms were used for modeling; the area under the receiver operating characteristic curve (AUROC), decision curve analysis, and calibration curve for evaluating; Shapley additive explanation (SHAP) analysis for visually interpret ing; and the Heroku platform for deploying the best-performing models as web-bas ed apps. For the model of predicting the risk of AKD in elderly patients with AK I during hospitalization, the Light Gradient Boosting Machine (LightGBM) showed the best overall performance in the training (AUROC=0.844, 95% CI 0.831-0.857), internal validation (AUROC=0.853, 95% CI 0.841- 0.865 ), and external (AUROC=0.755, 95% CI 0.699-0.811) cohorts. In addi tion, LightGBM performed well for the AKD prognostic prediction in the training (AUROC=0.861, 95% CI 0.843-0.878), internal validation (AUROC=0.86 8, 95% CI 0.851-0.885), and external (AUROC=0.746, 95% CI 0.673-0.820) cohorts. The models deployed as online prediction apps allowed u sers to predict and provide feedback to submit new data for model iteration. In the importance ranking and correlation visualization of the model’s top 10 influ encing factors conducted based on the SHAP value, partial dependence plots revea led the optimal cutoff of some interventionable indicators. The top 5 factors pr edicting the risk of AKD were creatinine on day 3, sepsis, delta blood urea nitr ogen (BUN), diastolic blood pressure (DBP), and heart rate, while the top 5 fact ors determining in-hospital mortality were age, BUN on day 1, vasopressor use, B UN on day 3, and partial pressure of carbon dioxide (PaCO). We developed and val idated 2 online apps for predicting the risk of AKD and its prognostic mortality in elderly patients, respectively.”
      原文链接:
    • NETL
    • NSTL

    Study Results from Umm Al-Qura University Provide New Insights into Machine Lear ning (Strategies for overcoming data scarcity, imbalance, and feature selection challenges in machine learning models for predictive maintenance)

    36-37页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Research findings on artificial intelligence are discussed in a new report. According to news reporting originating from Umm Al-Q ura University by NewsRx correspondents, research stated, “Predictive maintenanc e harnesses statistical analysis to preemptively identify equipment and system f aults, facilitating cost- effective preventive measures.” The news editors obtained a quote from the research from Umm Al-Qura University: “Machine learning algorithms enable comprehensive analysis of historical data, revealing emerging patterns and accurate predictions of impending system failure s. Common hurdles in applying ML algorithms to PdM include data scarcity, data i mbalance due to few failure instances, and the temporal dependence nature of PdM data. This study proposes an ML-based approach that adapts to these hurdles thr ough the generation of synthetic data, temporal feature extraction, and the crea tion of failure horizons. The approach employs Generative Adversarial Networks t o generate synthetic data and LSTM layers to extract temporal features.”
      原文链接:
    • NETL
    • NSTL

    Findings from Chinese University of Hong Kong Broaden Understanding of Robotics and Automation (A Selectively Controllable Triple-helical Micromotor)

    37-38页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in Robotic s - Robotics and Automation. According to news reporting from Guangdong, People’ s Republic of China, by NewsRx journalists, research stated, “Selective control mechanisms of microrobots have attracted significant attention from researchers. So far, selective control within multiple/swarm magnetic microrobots has been a chieved with many strategies, such as utilizing locally specified magnetic field s, applying electrostatic anchoring, taking the advantages of geometry/wettabili ty heterogeneity of the microrobots, etc.” Financial support for this research came from Shenzhen Institute of Artificial I ntelligence and Robotics for Society.
      原文链接:
    • NETL
    • NSTL