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

    Research from University of Leipzig Yields New Study Findings on Machine Learnin g (Marine cloud base height retrieval from MODIS cloud properties using machine learning)

    39-40页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Investigators discuss new findings in artificial intelligence. According to news reporting from Leipzig, Germany, by N ewsRx journalists, research stated, “Clouds are a crucial regulator in the Earth ’s energy budget through their radiative properties, both at the top of the atmo sphere and at the surface; hence, determining key factors like their vertical ex tent is of essential interest.” Financial supporters for this research include H2020 Marie Sklodowska-curie Acti ons. The news editors obtained a quote from the research from University of Leipzig: “While the cloud top height is commonly retrieved by satellites, the cloud base height is difficult to estimate from satellite remote sensing data. Here, we pre sent a novel method called ORABase (Ordinal Regression Autoencoding of cloud Ba se), leveraging spatially resolved cloud properties from the Moderate Resolution Imaging Spectroradiometer (MODIS) instrument to retrieve the cloud base height over marine areas. A machine learning model is built with two components to faci litate the cloud base height retrieval: the first component is an auto-encoder d esigned to learn a representation of the data cubes of cloud properties and to r educe their dimensionality. The second component is developed for predicting the cloud base using ground-based ceilometer observations from the lower-dimensiona l encodings generated by the aforementioned auto-encoder. The method is then eva luated based on a collection of collocated surface ceilometer observations and r etrievals from the CALIOP satellite lidar. The statistical model performs simila rly on both datasets and performs notably well on the test set of ceilometer clo ud bases, where it exhibits accurate predictions, particularly for lower cloud b ases, and a narrow distribution of the absolute error, namely 379 and 328 m for the mean absolute error and the standard deviation of the absolute error, respec tively.”
      原文链接:
    • NETL
    • NSTL

    Research Data from University of Illinois Update Understanding of Machine Learni ng (Fair and Optimal Prediction Via Postprocessing)

    40-41页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Current study results on Machine Learning have be en published. According to news reporting from Urbana, Illinois, by NewsRx edito rs, the research stated, “With the development of machine learning algorithms an d the increasing computational resources available, artificial intelligence has achieved great success in many application domains. However, the success of mach ine learning has also raised concerns about the fairness of the learned models.” Financial support for this research came from Google Incorporated.
      原文链接:
    • NETL
    • NSTL

    Reports Summarize Robotics Research from Feng Chia University (Multiobjective op timization of collaborative robotic task sequence assignment problems under coll ision-free constraints)

    41-42页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on robotics have been published. According to news reporting originating from Taichung, Taiwan, by NewsRx correspondents, research stated, “This paper proposes a multiobjective optimization approach to address the challenge of collaborative manufacturing w ith multiple robot arms.” Funders for this research include National Science And Technology Council. Our news journalists obtained a quote from the research from Feng Chia Universit y: “Given the necessity for multiple robot arms to work together, the potential for collisions between robotic motions is a significant concern, and the automat ed task sequence assignment for robots becomes increasingly complex. Previous re search has either simplified the collision-free conditions in a limited working area, or employed a master-slave approach to obtain only a local solution. Conse quently, we propose a unified global optimization approach for simultaneously ad dressing various collaborative manufacturing issues, including robotic task sequ ence assignment (RTSA), multiple inverse kinematics (IK) selection, joint-space collisionfree operations and multiple manufacturing objectives. As the optimal collaborative RTSA problem is a combinatorial optimization problem with non-dete rministic polynomial-time hard (NP-hard) complexity, this paper presents a hybri d nondominated sorting genetic algorithm III (NSGA-III) method that integrates a Hamming-distance-based method and a greedy strategy within NSGA-III to improve population diversity and solution quality. To validate the efficacy of the propo sed approach, simulation experiments were conducted on cooperative manufacturing scenarios, with two objectives: task completion time and task load balancing. T he experimental results demonstrate that the proposed approach is effective in o btaining collision-free Pareto solutions.”
      原文链接:
    • NETL
    • NSTL

    New Findings from Donghua University in the Area of Robotics Reported (A Knowled ge Transfer Method for Human-robot Collaborative Disassembly of End-of-life Powe r Batteries Based On Augmented Reality)

    42-43页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Robotics have been published. According to news originating from Shanghai, People’s Republic of China, by NewsRx correspondents, research stated, “The disassembly of power b atteries poses significant challenges due to their complex sources, diverse type s, variations in design and manufacturing processes, and diverse service conditi ons. Human memory capacity and robot cognitive and understanding capabilities ar e limited when faced with different dismantling tasks for end-of-life power batt eries.” Funders for this research include Municipal Natural Science Foundation of Shangh ai, Priming Scientific Research Foundation for the Junior Researchers of Donghua University, Graduate Student Innovation Fund of Donghua University.
      原文链接:
    • NETL
    • NSTL

    Study Data from School of Science Update Understanding of Machine Learning (Inte rpretable machine learning methods to predict the mechanical properties of ABX3 perovskites)

    43-44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 originating from Sligo, Irela nd, by NewsRx correspondents, research stated, “This paper proposes the utility of interpretable ensemble learning models for predicting the mechanical properti es (bulk, shear and Young moduli) of ABX3 perovskite compounds with the A, B, an d X referring to the 3 elements that make the cubic 3-dimensional framework of t he perovskite compounds. These models consist of 3 ensemble learning techniques namely CatBoost, Random Forest, and XGBoost.”
      原文链接:
    • NETL
    • NSTL

    Researchers’ Work from Xi’an University of Technology Focuses on Machine Learnin g (Application of an Improved Method Combining Machine Learning-Principal Compon ent Analysis for the Fragility Analysis of Cross-Fault Hydraulic Tunnels)

    44-45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 Xi’an, People’s Republic of China, by NewsRx journalists, research stated, “Machine learning (ML) approa ches, widely used in civil engineering, have the potential to reduce computing c osts and enhance predictive capabilities. However, many ML methods have yet to b e applied to develop models that accurately analyze the nonlinear dynamic respon se of cross-fault hydraulic tunnels (CFHTs).” Financial supporters for this research include National Natural Science Foundati on of China. Our news reporters obtained a quote from the research from Xi’an University of T echnology: “To predict CFHT models and fragility curves effectively, we identify the most effective ML techniques and improve prediction capacity and accuracy b y initially creating an integrated multivariate earthquake intensity measure (IM ) from nine univariate earthquake IMs using principal component analysis. Struct ural reactions are then performed using incremental dynamic analysis by a multim edium-coupled interaction system. Four techniques are used to test ML-principal component analysis (PCA) feasibility. Meanwhile, mathematical statistical parame ters are compared to standard probabilistic seismic demand models of expected an d computed values using ML-PCA. Eventually, multiple stripe analysis-maximum lik elihood estimation (MSA-MLE) is applied to assess the seismic performance of CFH Ts. This study highlights that the Gaussian process regression and integrated IM can improve reliable probability and reduce uncertainties in evaluating the str uctural response.”
      原文链接:
    • NETL
    • NSTL

    Researchers from Guangxi Normal University Detail New Studies and Findings in th e Area of Robotics (Robotic Camera Array Motion Planning for Multiple Human Face Tracking Based On Reinforcement Learning)

    45-45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 Guilin, People’s Repub lic of China, by NewsRx correspondents, research stated, “Active camera networks have been widely applied for mobile target sensing. However, traditional model/ rulebased methods run into bottlenecks when dealing with complex dynamic scenar ios due to their lack of long-term planning abilities.” Financial supporters for this research include Shenzhen Key Laboratory of Roboti cs and Computer Vision, Shenzhen Fundamental Research Program, National Natural Science Foundation of China (NSFC).
      原文链接:
    • NETL
    • NSTL

    New Robotics Findings Reported from South China University of Technology (Model Optimization and Acceleration Method Based On Meta-learning and Model Pruning fo r Laser Vision Weld Tracking System)

    46-46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 reporting from Guangzhou, People’s Repu blic of China, by NewsRx journalists, research stated, “PurposeThis paper aims t o propose a lightweight, high-accuracy object detection model designed to enhanc e seam tracking quality under strong arcs and splashes condition. Simultaneously ” Financial support for this research came from National Natural Science Foundatio n of Guangdong Province.
      原文链接:
    • NETL
    • NSTL

    Zhongnan Hospital of Wuhan University Reports Findings in Carcinomas (Somatic mu tation of targeted sequencing identifies risk stratification in advanced ovarian clear cell carcinoma)

    47-47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 Oncology - Carcinomas is the subject of a report. According to news originating from Hubei, People’s R epublic of China, by NewsRx correspondents, research stated, “Ovarian clear cell carcinoma (OCCC) is a unique subtype of epithelial ovarian cancer. Advanced OCC C display a poor prognosis.” Our news journalists obtained a quote from the research from the Zhongnan Hospit al of Wuhan University, “Therefore, we aimed to make risk stratification for pre cise medicine. We performed a large next generation sequencing (NGS) gene panel on 44 patients with OCCC in FIGO stage II-IV. Then, by machine learning algorith ms, including extreme gradient boosting (XGBoost), random survival forest (RSF), and Cox regression, we screened for feature genes associated with prognosis and constructed a 5-gene panel for risk stratification. The prediction efficacy of the 5-gene panel was compared with FIGO stage and residual disease by receiver o perating characteristic curve and decision curve analysis. The feature mutated g enes related to prognosis, selected by machine learning algorithms, include MUC1 6, ATM, NOTCH3, KMT2A, and CTNNA1. The 5-gene panel can effectively distinguish the prognosis, as well as platinum response, of advanced OCCC in both internal a nd external cohorts, with the predictive capability superior to FIGO stage and r esidual disease. Mutations in genes, including MUC16, ATM, NOTCH3, KMT2A, and CT NNA1, were associated with the poor prognosis of advanced OCCC.”
      原文链接:
    • NETL
    • NSTL

    Studies from Shanghai Jiao Tong University Provide New Data on Robotics (A Robot ic Manipulation Framework for Industrial Human-robot Collaboration Based On Cont inual Knowledge Graph Embedding)

    48-48页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Robotics have been published. According to news reporting out of Shanghai, People’s Republic of China, by NewsRx editors, research stated, “Hybrid robots can assist human wo rkers in various tasks due to their integration of mobility and manipulability. The rapid diffusion of these robots in factories has significantly elevated the automation and intelligence level of manufacturing, while also brings challenges to human-robot collaboration.” Financial support for this research came from National Key R&D Prog ram of China. Our news journalists obtained a quote from the research from Shanghai Jiao Tong University, “Traditionally, human workers need to instruct robots to perform a r ange of tasks by explicitly demonstrating these operations. However, this proces s imposes excessive burdens on workers as the tasks and environment for robots b ecome more and more diversified and complex. To alleviate this issue, we propose an innovative robotic manipulation framework based on continual knowledge graph embedding. This framework enables hybrid robots to break free from the constrai nts of fixed rules set by human demonstrations, instead endowing them with infer ring capability. The core idea is to utilize semantic information related to obj ects (such as category, material, and components) and tasks assigned to infer ap propriate operational parameters for robots via a knowledge graph. These operati onal parameters include the suitable type of gripper, the proper area for object manipulation, and the reasonable force range for effective grasping. We conduct an experimental analysis of the proposed framework with a real-world hybrid rob ot, which performed 158 different tasks involving 46 objects commonly seen in in dustry, achieving a success rate of up to 96.8%. Furthermore, our f ramework can continuously enhance the adaptability of robotic operations and eff ectively balance the learning of new and old knowledge.”
      原文链接:
    • NETL
    • NSTL