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

    New Robotics Study Findings Recently Were Reported by Researchers at University of Nantes (Decentralized Control and State Estimation of a Flying Parallel Robot Interacting With the Environment)

    95-96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 Robotics. According to news reporting originating from Nantes, France, by NewsRx correspondents, research stated, “Unmanned Aerial Vehicles (UAVs) have great potential to achieve a variety of tasks remotely such as aerial grasping, transporting and manipulating objects. Architectures with multiple UAVs have further enhanced the payload capacity and manipulability of these robots, for instance a Flying Parallel Robot (FPR) where a moving platform is cooperatively supported by multiple quadrotors with passive rigid links.” Funders for this research include French Infrastructure in Robotics, French Infrastructure in Robotics.Our news editors obtained a quote from the research from the University of Nantes, “In this paper, we address the vision-based state estimation and decentralized control applied to the multi-UAV parallel robot, taking the FPR as an example. An ArUco marker system is applied to estimate the relative pose of each UAV with respect to the common platform frame, along with the Extended Kalman Filter to reconstruct the robot state without the dependence on any external localization system. The interaction controller is then deployed in a decentralized manner, which is potentially more robust to communication delays or interruptions.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Researchers from Carnegie Mellon University Report Recent Findings in Machine Learning (On Tilted Losses In Machine Learning: Theory and Applications)

    96-97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 Pittsburgh, Pennsylvania, by NewsRx journalists, research stated, “Exponential tilting is a technique com- monly used in fields such as statistics, probability, information theory, and optimization to create parametric distribution shifts. Despite its prevalence in related fields, tilting has not seen widespread use in machine learning.” The news correspondents obtained a quote from the research from Carnegie Mellon University, “In this work, we aim to bridge this gap by exploring the use of tilting in risk minimization. We study a simple extension to ERM-tilted empirical risk minimization (TERM)-which uses exponential tilting to flexibly tune the impact of individual losses. The resulting framework has several useful properties: We show that TERM can increase or decrease the influence of outliers, respectively, to enable fairness or robustness; has variance-reduction properties that can benefit generalization; and can be viewed as a smooth approximation to the tail probability of losses. Our work makes connections between TERM and related objectives, such as Value-at-Risk, Conditional Value-at-Risk, and distributionally robust optimization (DRO). We develop batch and stochastic first-order optimization methods for solving TERM, provide convergence guarantees for the solvers, and show that the framework can be efficiently solved relative to common alternatives. Finally, we demonstrate that TERM can be used for a multitude of applications in machine learning, such as enforcing fairness between subgroups, mitigating the effect of outliers, and handling class imbalance.”
      原文链接:
    • NETL
    • NSTL

    Department of Gastroenterology Reports Findings in Personalized Medicine (Deciphering complex antibiotic resistance patterns in Helicobacter pylori through whole genome sequencing and machine learning)

    97-98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 Drugs and Therapies - Personalized Medicine is the subject of a report. According to news reporting out of Beijing, People’s Republic of China, by NewsRx editors, research stated, “Helicobacter pylori (H.pylori, Hp) affects billions of people worldwide. However, the emerging resistance of Hp to antibiotics challenges the effectiveness of current treatments.” Our news journalists obtained a quote from the research from the Department of Gastroenterology, “In- vestigating the genotype-phenotype connection for Hp using next-generation sequencing could enhance our understanding of this resistance. In this study, we analyzed 52 Hp strains collected from various hospitals. The susceptibility of these strains to five antibiotics was assessed using the agar dilution assay. Whole- genome sequencing was then performed to screen the antimicrobial resistance (AMR) genotypes of these Hp strains. To model the relationship between drug resistance and genotype, we employed univariate statistical tests, unsupervised machine learning, and supervised machine learning techniques, including the develop- ment of support vector machine models. Our models for predicting Amoxicillin resistance demonstrated 66% sensitivity and 100% specificity, while those for Clarithromycin resistance showed 100% sensitivity and 100% specificity. These results outperformed the known resistance sites for Amoxicillin (A1834G) and Clarithromycin (A2147), which had sensitivities of 22.2% and 87%, and specificities of 100% and 96%, respectively. Our study demonstrates that predictive modeling using supervised learning algorithms with feature selection can yield diagnostic models with higher predictive power compared to models relying on single single-nucleotide polymorphism (SNP) sites. This approach significantly contributes to enhancing the precision and effectiveness of antibiotic treatment strategies for Hp infections.”
      原文链接:
    • NETL
    • NSTL
    • Frontiers Media Sa

    VU Amsterdam Reports Findings in Hemophilia A (A Generative and Causal Pharmacokinetic Model for Factor Ⅷ in Hemophilia A: A Machine Learning Framework for Continuous Model Refinement)

    98-99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 Hematologic Diseases and Conditions - Hemophilia A is the subject of a report. According to news reporting originating in Amsterdam, Netherlands, by NewsRx journalists, research stated, “In rare diseases, such as hemophilia A, the development of accurate population pharmacokinetic (PK) models is often hindered by the limited availability of data. Most PK models are specific to a single recombinant factor Ⅷ (rFVIII) concentrate or measurement assay, and are generally unsuited for answering counterfactual (‘what-if’) queries.” The news reporters obtained a quote from the research from VU Amsterdam, “Ideally, data from multiple hemophilia treatment centers are combined but this is generally difficult as patient data are kept private. In this work, we utilize causal inference techniques to produce a hybrid machine learning (ML) PK model that corrects for differences between rFVIII concentrates and measurement assays. Next, we augment this model with a generative model that can simulate realistic virtual patients as well as impute missing data. This model can be shared instead of actual patient data, resolving privacy issues. The hybrid ML-PK model was trained on chromogenic assay data of lonoctocog alfa and predictive performance was then evaluated on an external data set of patients who received octocog alfa with FVIII levels measured using the one-stage assay. The model presented higher accuracy compared with three previous PK models developed on data similar to the external data set (root mean squared error = 14.6 IU/dL vs. mean of 17.7 IU/dL). Finally, we show that the generative model can be used to accurately impute missing data (<18% error).”
      原文链接:
    • NETL
    • NSTL
    • Wiley

    Data on Artificial Intelligence Reported by Yi Zhao and Colleagues (Artificial intelligence applied to magnetic resonance imaging reliably detects the presence, but not the location, of meniscus tears: a systematic review and meta-analysis)

    99-100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 Intelligence is the subject of a report. According to news originating from London, United Kingdom, by NewsRx correspondents, research stated, “To review and compare the accuracy of convolutional neural networks (CNN) for the diagnosis of meniscal tears in the current literature and analyze the decision-making processes utilized by these CNN algorithms. PubMed, MEDLINE, EMBASE, and Cochrane databases up to December 2022 were searched in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analysis (PRISMA) statement.” Our news journalists obtained a quote from the research, “Risk of analysis was used for all identified articles. Predictive performance values, including sensitivity and specificity, were extracted for quantitative analysis. The meta-analysis was divided between AI prediction models identifying the presence of meniscus tears and the location of meniscus tears. Eleven articles were included in the final review, with a total of 13,467 patients and 57,551 images. Heterogeneity was statistically significantly large for the sensitivity of the tear identification analysis (I = 79%). A higher level of accuracy was observed in identifying the presence of a meniscal tear over locating tears in specific regions of the meniscus (AUC, 0.939 vs 0.905). Pooled sensitivity and specificity were 0.87 (95% confidence interval (CI) 0.80-0.91) and 0.89 (95% CI 0.83-0.93) for meniscus tear identification and 0.88 (95% CI 0.82-0.91) and 0.84 (95% CI 0.81-0.85) for locating the tears. AI prediction models achieved favorable performance in the diagnosis, but not location, of meniscus tears. Further studies on the clinical utilities of deep learning should include standardized reporting, external validation, and full reports of the predictive performances of these models, with a view to localizing tears more accurately. Meniscus tears are hard to diagnose in the knee magnetic resonance images.”
      原文链接:
    • NETL
    • NSTL

    Investigators at Singapore University of Technology and Design Describe Findings in Robotics (Younger, Not Older, Children Trust an Inaccurate Human Informant More Than an Inaccurate Robot Informant)

    100-101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 Robotics is the subject of a report. According to news reporting originating from Singapore, Singapore, by NewsRx correspondents, research stated, “This study examined preschoolers’ trust toward accurate and inaccurate robot informants versus human informants. Singaporean children aged 3-5 years (N = 120, 57 girls, mostly Asian; data collected from 2017 to 2018) viewed either a robot or a human adult label familiar objects either accurately or inaccurately.” Financial supporters for this research include Singapore University of Technology & Design, Safari House Preschool, MacPherson Sheng Hong Childcare Centre. Our news editors obtained a quote from the research from the Singapore University of Technology and Design, “Children’s trust was assessed by examining their subsequent willingness to accept novel object labels provided by the same informant. Regardless of age, children trusted accurate robots to a similar extent as accurate humans. However, while older children (dis)trusted inaccurate robots and humans comparably, younger children trusted inaccurate robots less than inaccurate humans.”According to the news editors, the research concluded: “The results indicate a developmental change in children’s reliance on informants’ characteristics to decide whom to trust.” This research has been peer-reviewed.
      原文链接:
    • NETL
    • NSTL
    • Wiley

    New Robotics Findings from Sun Yat-sen University Described (Hotel Guest-robot Interaction Experience: a Scale Development and Validation)

    101-102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 Robotics is the subject of a report. According to news reporting from Guangzhou, People’s Republic of China, by NewsRx journalists, research stated, “Service robots is an emerging topic in tourism and hospitality industry. The success of service robots’ adoption primarily lies in effective tourist-robot interaction.” Financial supporters for this research include China Postdoctoral Science Foundation, National Natural Science Foundation of China (NSFC), National Natural Science Foundation of China (NSFC). The news correspondents obtained a quote from the research from Sun Yat-sen University, “However, little research has fully explored tourist perception of interaction with service robots. This study aimed to develop a scale for measuring guest-robot interaction experience in hotel context. We utilized a rigorous scale development procedure. First, the construct domain was specified. Second, items were generated by literature review and interviews and then estimated by content validity. Third, data was collected to test the measures: 345 respondents were used for item purification and 307 respondents for scale validation. Ultimately, a four-dimensional (perceived competence, sense of closeness, interaction comfort, and pleasant experience) scale with 18 items was confirmed. This study contributes by providing a useful tool for comprehensively understanding hotel guests’ perception of interaction with service robots and future related research.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Patent Issued for Generating credit building recommendations through machine learning analysis of user activity-based feedback (USPTO 11900451)

    102-106页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Chime Financial Inc. (San Francisco, California, United States) has been issued patent number 11900451, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors. The patent’s inventors are Ducker, Michael (San Francisco, CA, US), King, Ryan Alexander (San Francisco, CA, US), Sloboda, Tilo (San Jose, CA, US), Smith, Zachary Vaughn (San Francisco, CA, US). This patent was filed on September 15, 2020 and was published online on February 13, 2024. From the background information supplied by the inventors, news correspondents obtained the fol- lowing quote: “Modern financial institutions and their clients conduct the vast majority of their financial transactions through digital channels. Modern day consumers have access to a variety of tools, both digital and non-digital, that allow them to build credit, such as secured credit cards. A good credit score can help consumers negotiate loans at favorable rates and otherwise provides greater financial flexibility. However, the particular manner in which these credit building tools must be used to actually improve a consumer’s credit score is determined by various credit bureaus; consumers are often not provided with clear knowledge as to how their use of the tools, or their own activity, directly or indirectly affects their credit scores. As a result, even well-intentioned consumers often use these credit tools in a disadvantageous or suboptimal manner. Therefore, automated, digitally-focused solutions that facilitate positive credit activity without increasing workload to financial institutions are generally desired.
      原文链接:
    • NETL
    • NSTL

    Researchers Submit Patent Application, 'Leveraging Machine Learning Models to Identify Missing or Incorrect Labels in Training or Testing Data', for Approval (USPTO 20240054390)

    106-108页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – From Washington, D.C., NewsRx journalists report that a patent application by the inventors Beltrao Colaco Costa, Lauro Ivo (Kirkland, WA, US); Koukoumidis, Emmanouil (Kirkland, WA, US); Tata, Sandeep (San Francisco, CA, US); Wendt, James Bradley (San Francisco, CA, US), filed on August 19, 2022, was made available online on February 15, 2024. No assignee for this patent application has been made. News editors obtained the following quote from the background information supplied by the inventors: “Machine learning is a field of computer science in which models are learned or trained using training data and tested using testing data. In many instances, training or testing data can be generated by humans. For example, a training example can be provided to a human labeler and the human can chose to apply one or more labels to the training example. The labeled data can then be used to train and/or test a machine learning model. “However, humans often make mistakes or miss labels within the training data. These mistakes lead to inaccuracies in machine-learning model training and/or testing, which in turn leads to reduced performance of the model outside of the training data (e.g., when deployed to production) and/or incorrect assessments of model performance.” As a supplement to the background information on this patent application, NewsRx correspondents also obtained the inventors’ summary information for this patent application: “Aspects and advantages of embodiments of the present disclosure will be set forth in part in the following description, or can be learned from the description, or can be learned through practice of the embodiments.
      原文链接:
    • NETL
    • NSTL

    Patent Application Titled 'Methods And Systems For Polymeric Fingerprint Analysis And Identification' Published Online (USPTO 20240054388)

    108-111页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – According to news reporting originating from Washington, D.C., by NewsRx journalists, a patent application by the inventors Acharya, Saurav (Naperville, IL, US); Andrick, Ray (Pittsburgh, PA, US); Cochran, Dermot (Sturbridge, MA, US); Ibrahim-Rana, Annie (Mt. Prospect, IL, US); Mehdiyev, Rashid (Lake Forest, IL, US); Mitra, Shubhankar (Chicago, IL, US); Sodhi, Karan (Laramie, WY, US), filed on August 12, 2022, was made available online on February 15, 2024. No assignee for this patent application has been made. Reporters obtained the following quote from the background information supplied by the inventors: “Polymers, such as plastics, may be evaluated and analyzed using various tests and analyses. For example, polymers, such as plastics, may be analyzed using flammability tests, mechanical strength tests, etc. Other processes may be performed on a sample to analyze the chemical or other properties of a plastic. For example, thermogravimetric (TGA) analyses, differential scanning calorimetry (DSC) analyses, and/or infrared spectroscopy (IR) analyses may be used as identification analyses to measure inherent properties of a polymer, such as a plastic. The results of those analyses may therefore be used to identify a type of polymer, such as a plastic, as a polymer sample of the same type, because, for example, they may have similar TGA, DSC, and IR analyses results. In this way, a polymer sample may be identified as being the same as a previously analyzed sample based on the results of such prior analyses, for example, by a trained chemist skilled at comparing results of analyses such as TGA, DSC, and IR.”
      原文链接:
    • NETL
    • NSTL