期刊,Robotics & Machine Learning Daily News 2024年卷Mar.6期_国家学术搜索

期刊信息/Journal information

Robotics & Machine Learning Daily News

NewsRx

主办单位：NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News

正式出版

收录年代

Findings from Lawrence Livermore National Laboratory in the Area of Machine Lear ning Reported (Machine-learning-aided Density Functional Theory Calculations of Stacking Fault Energies In Steel)

95-96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 Machine Learn ing have been published. According to news reporting from Livermore, California, by NewsRx journalists, research stated, "A combined large-scale first principle s approach with machine learning and materials informatics is proposed to quickl y sweep the chemistry-composition space of advanced high strength steels (AHSS). AHSS are composed of iron and key alloying elements such as aluminum and mangan ese." Funders for this research include High Performance Computing for Manufacturing P rogram (HPC4Mfg), United States Department of Energy (DOE), United States Depart ment of Energy (DOE). The news correspondents obtained a quote from the research from Lawrence Livermo re National Laboratory, "A systematic exploration of the distribution of aluminu m and manganese atoms in iron is used to investigate low stacking fault energies configurations using first principles calculations. To overcome the computation al cost of exploring the composition space, this process is sped up using an aut omated machine learning tool: DeepHyper. Our results predict that it is energeti cally favorable for Al to stay away from a stacking fault, but Mn atoms do not a ffect the stacking fault energy and can stay in the vicinity of the fault." According to the news reporters, the research concluded: "The distribution of Al and Mn atoms in systems containing stacking faults and the effects of their int eractions on the equilibrium distribution are systematically analyzed."

原文链接:

NETL
NSTL

University of Michigan Reports Findings in Machine Learning (High-Performance Ir idium-Molybdenum Oxide Electrocatalysts for Water Oxidation in Acid: Bayesian Op timization Discovery and Experimental Testing)

96-96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 from Ann Arbor, Michigan, by NewsRx journalists, research stated, "Ir oxides are costly and scarce catalysts for oxygen evolution reaction (OER) in acid. There has been extensive interest i n developing alternatives that are either Ir-free or require smaller amounts of Ir to drive the reactions at acceptable rates." The news correspondents obtained a quote from the research from the University o f Michigan, "One design strategy is to identify Ir-based mixed oxides that achie ve similar performance while requiring smaller amounts of Ir. The obstacle to th is strategy has been a very large phase space of the Ir-based mixed metal oxides , in terms of the metals combined with Ir and the different crystallographic str uctures of the mixed oxides, which prevents a thorough exploration of possible m aterials. In this work, we developed a workflow that uses machine-learning-aided Bayesian optimization in combination with density functional theory to make the exploration of this phase space plausible. This screening identified Mo as a pr omising dopant for forming acid-tolerant Ir-based oxides for the OER. We synthes ized and characterized the Ir-Mo mixed oxides in the form of thin-film electroca talysts with a known surface area. We show that these mixed oxides exhibited ove rpotentials 30 mV lower than a pure Ir control while maintaining 24% lower Ir dissolution rates than the Ir control."

原文链接:

NETL
NSTL

Studies from University of Vigo Have Provided New Data on Machine Learning (Appl ication of Supervised Learning Algorithms for Temperature Prediction In Nucleate Flow Boiling)

97-97页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Fresh data on Machine Learning are presented in a new report. According to news reporting out of Vigo, Spain, by NewsRx editors, research stated, "This work investigates the use of supervised learning algorith ms to predict temperatures in an experimental test bench, which was initially de signed for studying nucleate boiling phenomena with ethylene glycol/water mixtur es. The proposed predictive model consists of three stages of machine learning." Financial support for this research came from Universidade de Vigo/CISUG. Our news journalists obtained a quote from the research from the University of V igo, "In the first one, a supervised algorithm block is employed to determine wh ether the critical heat flux (CHF) will be reached within the test bench limits. This classification relies on input parameters including bulk temperature, tilt angle, pressure, and inlet velocity. Once the CHF condition is established, ano ther machine learning algorithm predicts the specific heat flux at which CHF wil l occur. Subsequently, based on the classification generated by the first block, the evolution of temperature in response to increases in heat flux is predicted using either the previously estimated heat flux or the physical limits of the e xperimental facility as the stopping criterion. To accomplish all these predicti ons, the study compares the performance of various algorithms including artifici al neural networks, random forest, support vector machine, AdaBoost, and XGBoost . These algorithms were specifically trained using cross-validation and grid sea rch methods to optimize their effectiveness. Results for the CHF classification purpose demonstrate that the support vector machine algorithm performs the best, achieving an F1-score of 0.872 on the testing dataset, while the boosting metho ds (AdaBoost and XGBoost) exhibit signs of overfitting. In predicting the CHF va lue, the artificial neural network achieved the lower nMAE on the testing datase t (6.18%)."

原文链接:

NETL
NSTL

Reports Outline Machine Learning Findings from Tianjin University (Multifunction al Analysis of Construction Contracts Using a Machine Learning Approach)

98-98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 Ma chine Learning. According to news reporting out of Tianjin, People's Republic of China, by NewsRx editors, research stated, "In the intricate domain of construc tion contracts, precise descriptions and measurements of contract structures are crucial. This study provides an objective analysis of the structure of construc tion contracts from a multifunctional perspective." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from Tianjin University, "A deep learningbased machine coding model was trained using 17 standard contr acts and 35 actual contracts. The model was then used to code an additional 117 actual contracts. Statistical analysis was conducted to compare the distribution of the three functions (i.e., control, coordination, and adaptation) between st andard and actual contracts. The results revealed that coordination has the high est contribution among the three functions. Moreover, actual contracts exhibit i ncreased complexity compared with standard contracts, often containing additiona l control and coordination provisions related to project-specific obligations an d tasks. The 117 actual contracts were further classified based on project deliv ery systems (PDSs) and pricing methods, and the impact of PDSs and pricing metho ds on the functional distribution was examined. The results showed more flexible adaptation and more complex control provisions specified in design-build/engine ering, procurement, and construction (DB/EPC) and lump sum contracts. Theoretica lly, this study provides insights into objective measures in contract research a nd enriches the body of knowledge on the structure of construction contracts fro m a multifunctional perspective."

原文链接:

NETL
NSTL

Studies from Zhengzhou University Add New Findings in the Area of Robotics (Comp lex Dynamics of the Passive Biped Robot With Flat Feet: Gait Bifurcation, Interm ittency and Crisis)

99-99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 in Zhengzhou, People's Republic of China, by NewsRx journalists, research stated, "During the past deca des, the walking dynamics of different types of passive biped robots have garner ed significant attention. This paper investigates the complex dynamics of a pass ive flat-footed robot, encompassing both the local bifurcation of limit cycles a nd global bifurcation, resulting in significant changes in the system's walking pattern." The news reporters obtained a quote from the research from Zhengzhou University, "To identify the robot's dynamic behavior, the Lyapunov Exponents (LEs) are cal culated using the small orthogonal perturbation vectors method. The obtained LEs diagram also unveils several subtle periodic windows scattered within the chaot ic region, where interior crisis and intermittency occur. Moreover, two new kind s of gaits that coexist with the traditional period-1 ones are found. Of particu lar significance is the discovery of the double boundary crisis that caused by t he critical period-3 unstable periodic orbit, and this crisis serves as the fund amental reason to the falling down on slopes of the flat-footed robots."

原文链接:

NETL
NSTL

Researcher at Meiji University Zeroes in on Robotics and Mechatronics (One-Way-S ignal-Based Localization Method of Multiple Autonomous Underwater Vehicles for D istributed Ocean Surveys)

100-100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 ro botics and mechatronics. According to news reporting from Kanagawa, Japan, by Ne wsRx journalists, research stated, "This study proposes a simultaneous localizat ion method of a group of autonomous underwater vehicles (AUVs) based on one-way signals to realize distributed oceanographic surveys." Our news editors obtained a quote from the research from Meiji University: "Each AUV group consists of a single high-performance AUV (parent AUV) and the other AUVs (child AUVs). The child AUVs estimate their states (position and heading) b ased on the parent AUV as a positioning reference. By assuming a situation in wh ich many AUV groups are deployed, the child AUVs can receive positioning signals from multiple parent AUVs. Although only the direction information of the paren t AUV can be obtained from a signal from one parent AUV, the child AUVs can esti mate their states by receiving signals from different parent AUVs."

原文链接:

NETL
NSTL

Studies from Scientific Department Further Understanding of Robotics (Determinan ts of Performance for Robotics Teleoperated Activities: From Emergency Response to Decommissioning)

100-101页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on robotics is now availab le. According to news originating from the Scientific Department by NewsRx corre spondents, research stated, "After the nuclear accidents of Chernobyl and Fukush ima, several countries concerned with nuclear energy production set up robotic a ccident intervention groups with the aim to intervene in place of humans in host ile environments with high levels of contamination or irradiation." Our news editors obtained a quote from the research from Scientific Department: "It is the case of France. The operational feedback of such robotic groups may b e of interest for teams performing decommissioning on nuclear facilities." According to the news editors, the research concluded: "In this aim, a comparati ve analysis of robotic intervention contexts was undertaken between training con texts and a real operating situation. This allowed us to confirm determinants of performance already identified in the literature and highlighted new determinan ts of performance for intervention in nuclear environments."

原文链接:

NETL
NSTL

Researchers Submit Patent Application, "Universal self-learning system and self- learning method based on universal self-learning system", for Approval (USPTO 20 240054359)

101-105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 journali sts report that a patent application by the inventor HU, SHANGFENG (Shenzhen, CN ), filed on August 8, 2023, 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 suppli ed by the inventors: "At present, in the field of artificial intelligence, const ructed artificial intelligence systems substantially can only be applied to a ce rtain technical field and can only solve technical problems in a certain technic al field. Building a universal artificial intelligence system that can implement independent learning in any field and solve technical problems in multiple tech nical fields is an urgent technical problem to be solved. "In addition, the present disclosure is an improved solution of the technical so lution described in the U.S. Pat. No. 9,639,523B2.

原文链接:

NETL
NSTL

"Observation Device And Observation Method" in Patent Application Approval Proce ss (USPTO 20240053723)

105-109页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A patent application by the inventor L IU, Sichen (Yamanashi-ken, JP), filed on January 5, 2022, was made available onl ine on February 15, 2024, according to news reporting originating from Washingto n, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background informa tion supplied by the inventors: "In JP H03-251066 A, a field balancer is disclos ed. The field balancer is a device for observing a state of balance (balance sta te) in rotation of a rotationally driven observation target. The observation tar get, for example, is a motor (a motor shaft)." In addition to the background information obtained for this patent application, NewsRx journalists also obtained the inventor's summary information for this pat ent application: "A machine tool is equipped with a rotating body that is rotati onally driven. The rotating body, for example, is a spindle (main shaft) or a fa ce plate. An operator of the machine tool installs the field balancer on the mac hine tool in order to measure a balance state of the rotating body. Based on the balance state of the rotating body that has been measured, the operator can per form an operation in order to correct the balance state of the rotating body.

原文链接:

NETL
NSTL

Patent Issued for Artificial intelligence (AI) models to improve image processin g related to pre and post item deliveries (USPTO 11900686)

109-113页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A patent by the inventors Kafai, Mehra n (Bellevue, WA, US), Papadimitriou, Dimitris (Berkeley, CA, US), Sharma, Anthon y (Kenmore, WA, US), Sherwin, Jarrod (Kent, WA, US), Wang, Zheshen (Bellevue, WA , US), filed on November 4, 2020, was published online on February 13, 2024, acc ording to news reporting originating from Alexandria, Virginia, by NewsRx corres pondents. Patent number 11900686 is assigned to Amazon Tecnologies Inc. (Seattle, Washingt on, United States). The following quote was obtained by the news editors from the background informa tion supplied by the inventors: "Different computing services are available to i mprove the user experience with item deliveries. For instance, a driver can rece ive a map of the delivery location on their device. Also, the driver can take an image of an item that is dropped off at a delivery location. The image taken by the driver can also be sent to a device of a user that is associated with the d elivery location." In addition to the background information obtained for this patent, NewsRx journ alists also obtained the inventors' summary information for this patent: "In the following description, various embodiments will be described. For purposes of e xplanation, specific configurations and details are set forth in order to provid e a thorough understanding of the embodiments. However, it will also be apparent to one skilled in the art that the embodiments may be practiced without the spe cific details. Furthermore, well-known features may be omitted or simplified in order not to obscure the embodiment being described.

原文链接:

NETL
NSTL