期刊,Robotics & Machine Learning Daily News 2024年卷MAY.30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

Study Results from Technical University of Liberec Provide New Insights into Rob otics (Modelling, Analysis and Comparison of Robot Energy Consumption for Three- Dimensional Concrete Printing Technology)

105-106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. According to news originating from Liberec, Czech Republic, by NewsRx ed itors, the research stated, "The technology used for the 3D printing of building s from concrete is currently a very relevant and developing topic and appears to be especially advantageous in terms of sustainable production. An important asp ect of the sustainability assessment is the energy efficiency of the printing ro bots." Financial supporters for this research include Student Grant Competition; Europe an Structural And Investment Funds.

原文链接:

NETL
NSTL

Findings from Leibniz University Hannover in Robotics Reported (Sponge: Open-sou rce Designs of Modular Articulated Soft Robots)

106-107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. According to news reporting originating from Hannover, Germany, by NewsR x correspondents, research stated, "Soft-robot designs are manifold, but only a few are publicly available. Often, these are only briefly described in their pub lications." Financial support for this research came from German Research Foundation (DFG). Our news editors obtained a quote from the research from Leibniz University Hann over, "This complicates reproduction and hinders the reproducibility and compara bility of research results. If the designs were uniform and open source, validat ing researched methods on real benchmark systems would be possible. To address t his, we present two variants of a soft pneumatic robot with antagonistic bellows as open source. Starting from a semi-modular design with multiple cables and tu bes routed through the robot body, the transition to a fully modular robot with integrated microvalves and serial communication is highlighted. Modularity in te rms of stackability, actuation, and communication is achieved, which is the cruc ial requirement for building soft robots with many degrees of freedom and high d exterity for real-world tasks. Both systems are compared regarding their respect ive advantages and disadvantages."

原文链接:

NETL
NSTL

Reports from Nanyang Technological University Advance Knowledge in Machine Learn ing (Variable Taxi-out Time Prediction Based On Machine Learning With Interpreta ble Attributes)

107-108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 Machine Learning. According to news reporting from Singapore, Singapore, by News Rx journalists, research stated, "This paper presents a machine learning-based a pproach for predicting the taxi -out time, with the departure process decomposed into two components: the time taken to travel from the gate to the departure qu eue, and the time spent in the departure queue. Gradient-Boosted Decision Tree ( GBDT) models are trained to predict the two components using different feature s ets, and a comparison of both model shows that they can provide better predictio n accuracy compared with conventional methods, with a Root Mean Squared Error (R MSE) of 1.79 minutes and 0.92 minutes when predicting the taxiing and queuing ti mes respectively, and 78% and 96% of predictions fal ling within a<<2 minute error margin ." Financial support for this research came from Saab AB (publ).

原文链接:

NETL
NSTL

Shanghai University Reports Findings in Machine Learning (Prediction and explana tion for ozone variability using cross-stacked ensemble learning model)

108-109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 Shanghai, People's Repub lic of China, by NewsRx journalists, research stated, "With the development of m onitoring technology, the variety of ozone precursors that can be detected by mo nitoring stations has been increased dramatically. And this has brought a great increment of information to ozone prediction and explanation studies." The news correspondents obtained a quote from the research from Shanghai Univers ity, "This study completes feature mining and reconstruction of multi-source dat a (meteorological data, conventional pollutant data, and precursors data) by usi ng a machine learning approach, and built a cross-stacked ensemble learning mode l (CSEM). In the feature engineering process, this study reconstructed two VOCs variables most associated with ozone and found it works best to use the top seve n variables with the highest contribution. The CSEM includes three base models: random forest, extreme gradient boosting tree, and LSTM, learning the parameters of the model under the integrated training of cross-stacking. The cross-stacked integrated training method enables the second-layer learner of the ensemble mod el to make full use of the learning results of the base models as training data, thereby improving the prediction performance of the model. The model predicted the hourly ozone concentration with R of 0.94, 0.97, and 0.96 for mild, moderate , and severe pollution cases, respectively; mean absolute error (MAE) of 4.48 mg /m, 5.01 mg/m, and 8.71 mg/m, respectively. The model predicted ozone concentrat ions under different NO and VOCs reduction scenarios, and the results show that with a 20 % reduction in VOCs and no change in NO in the study are a, 75.28 % of cases achieved reduction and 15.73 % o f cases got below 200 mg/m. In addition, a comprehensive evaluation index of the prediction model is proposed in this paper, which can be extended to any predic tion model performance comparison and analysis."

原文链接:

NETL
NSTL

Recent Findings from China University of Petroleum Provides New Insights into Ma chine Learning (On the Evaluation of Coal Strength Alteration Induced By Co2 Inj ection Using Advanced Black- Box and White- Box Machine Learning ...)

109-110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 out of Beijing, People's Republic of C hina, by NewsRx editors, research stated, "The injection of carbon dioxide (CO2) into coal seams is a prominent technique that can provide carbon sequestration in addition to enhancing coalbed methane extraction. However, CO2 injection into the coal seams can alter the coal strength properties and their long-term integ rity." Our news journalists obtained a quote from the research from the China Universit y of Petroleum, "In this work, the strength alteration of coals induced by CO2 e xposure was modeled using 147 laboratorymeasured unconfined compressive strengt h (UCS) data points and considering CO2 saturation pressure, CO2 interaction tem perature, CO2 interaction time, and coal rank as input variables. Advanced white -box and black-box machine learning algorithms including Gaussian process regres sion (GPR) with rational quadratic kernel, extreme gradient boosting (XGBoost), categorical boosting (CatBoost), adaptive boosting decision tree (AdaBoost-DT), multivariate adaptive regression splines (MARS), K-nearest neighbor (KNN), gene expression programming (GEP), and group method of data handling (GMDH) were used in the modeling process. The results demonstrated that GPR-Rational Quadratic p rovided the most accurate estimates of UCS of coals having 3.53%, 3 .62%, and 3.55% for the average absolute percent rela tive error (AAPRE) values of the train, test, and total data sets, respectively. Also, the overall determination coefficient (R-2) value of 0.9979 was additiona l proof of the excellent accuracy of this model compared with other models. More over, the first mathematical correlations to estimate the change in coal strengt h induced by CO2 exposure were established in this work by the GMDH and GEP algo rithms with acceptable accuracy. Sensitivity analysis revealed that the Spearman correlation coefficient shows the relative importance of the input parameters o n the coal strength better than the Pearson correlation coefficient. Among the i nputs, coal rank had the greatest influence on the coal strength (strong nonline ar relationship) based on the Spearman correlation coefficient. After that, CO2 interaction time and CO2 saturation pressure have shown relatively strong nonlin ear relationships with model output, respectively. The CO2 interaction temperatu re had the smallest impact on coal strength alteration induced by CO2 exposure b ased on both Pearson and Spearman correlation coefficients."

原文链接:

NETL
NSTL

Bangladesh University of Engineering and Technology Reports Findings in Machine Learning (The Rohingya refugee crisis in Bangladesh: assessing the impact on lan d use patterns and land surface temperature using machine learning)

110-111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 in Dhaka, Banglad esh, by NewsRx journalists, research stated, "Bangladesh, a thirdworld country with the seventh highest population density in the world, has always struggled t o ensure its residents' basic needs. But in recent years, the country is going t hrough a serious humanitarian and financial crisis that has been imposed by the neighboring country Myanmar which has forced the government to shelter almost a million Rohingya refugees in less than 3 years (2017-2020)." The news reporters obtained a quote from the research from the Bangladesh Univer sity of Engineering and Technology, "The government had no other option but to a cquire almost 24.1 km of forest areas only to construct refugee camps for the Ro hingyas which has led to catastrophic environmental outcomes. This study has ana lyzed the land use and land surface temperature pattern change of the Rohingya c amp area for the course of 1997 to 2022 with a 5-year interval rate. Future pred iction of the land use and temperature of Teknaf and Ukhiya was also done in thi s process using a machine learning algorithm for the years 2028 and 2034. The an alysis says that in the camp area, from 1997 to 2017, percentage of settlements increased from 5.28 to 11.91% but in 2022, it reached 70.09% . The same drastically changing trend has also been observed in the land surface temperature analysis. In the month of January, the average temperature increase d from 18.86 to 21.31 °C between 1997 and 2017. But in 2022. it was found that t he average temperature had increased up to 25.94 °C in only a blink of an eye."

原文链接:

NETL
NSTL

Study Findings from Old Dominion University Broaden Understanding of Artificial Intelligence (Shift of Ambidexterity Modes: an Empirical Investigation of the Im pact of Artificial Intelligence In Customer Service)

111-112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 in Norfolk, Virgi nia, by NewsRx journalists, research stated, "To manage the trade-offs between e xploration and exploitation, customer service organizations typically choose a s pecific ambidexterity mode, such as structural separation or behavioral integrat ion, that suits their context. However, recent research suggests that organizati ons need to dynamically change their ambidexterity modes to better align with ch anging environmental and organizational contexts." Financial support for this research came from US Army Research Laboratory (ARL). The news reporters obtained a quote from the research from Old Dominion Universi ty, "This study examines the impact of AI in facilitating the shift across vario us modes of ambidexterity in customer service organizations. Our findings reveal that achieving shifts in ambidexterity modes is challenging, and organizations must overcome technology, business process, and stakeholder related barriers. Ba sed on our findings, we develop a set of propositions for further investigation. "

原文链接:

NETL
NSTL

Research Results from Georgia Institute of Technology Update Understanding of Ma chine Learning (Ensemble Machine Learning Classification Models for Predicting P avement Condition)

112-113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 originating from Atlanta, Georgia, by NewsRx correspondents, research stated, "Forecasting pavement performance condi tion is essential within the pavement management system to optimize decisions wi th regard to planning maintenance and rehabilitation projects. Accurate forecast s facilitate timely interventions and assist in formulating cost-effective asset management plans." The news correspondents obtained a quote from the research from Georgia Institut e of Technology: "Data-driven machine learning models that utilize historical da ta to improve forecasting precision have gained attention in the field of asset management. Although numerous studies have employed regressionbased models to f orecast pavement condition, transportation asset management often operates accor ding to condition index ranges rather than exact values. Therefore, classificati on models are suitable for predicting pavement condition grades and determining the appropriate maintenance type for pavement assets. This research focuses on d eveloping five machine learning classification models to predict pavement condit ion: random forest; gradient boost; support vector machine; k-nearest neighbors; and artificial neural network. To enhance prediction performance, these models are integrated using ensemble methods, including voting and stacking. The classi fication models are developed using a dataset from the Georgia Department of Tra nsportation that documented the condition of asphalt pavements for predefined ma intenance sections between 2017 and 2021. A voting ensemble model constructed wi th the two bestperforming individual classification models reached the highest accuracy rate at 83%."

原文链接:

NETL
NSTL

Researchers Submit Patent Application, "Systems And Methods For Baby Bottle Manu facturing", for Approval (USPTO 20240161399)

113-115页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-From Washington, D.C., NewsRx journalists report that a patent application by the inventors Amiel, Hagai (Las Vegas, NV, US); Zee v, Shilo Ben (Las Vegas, NV, US), filed on November 17, 2023, was made available online on May 16, 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: "Feeding devices, such as baby bottles, are often used to f eed babies from newborns to toddlers for various reasons. Reasons for using a fe eding device include, but are not limited to: latching difficulties by the baby, inability for the mother to produce enough milk, feeding by a caregiver or phys ician other than the mother, inability for the mother to breastfeed for health r easons, weaning of the baby, etc." As a supplement to the background information on this patent application, NewsRx correspondents also obtained the inventors' summary information for this patent application: "The summary is a high-level overview of various aspects of the in vention and introduces some of the concepts that are further detailed in the Det ailed Description section below. This summary is not intended to identify key or essential features of the claimed subject matter, nor is it intended to be used in isolation to determine the scope of the claimed subject matter. The subject matter should be understood by reference to the appropriate portions of the enti re specification, any or all drawings, and each claim.

原文链接:

NETL
NSTL

Patent Issued for Trolley and method for loading and unloading cleaning robots i nto and out of a trolley (USPTO 11980331)

115-117页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Miele & Cie. Kg (Gutersl oh, Germany) has been issued patent number 11980331, according to news reporting originating out of Alexandria, Virginia, by NewsRx editors. The patent's inventors are Budke, Mathis (Bielefeld, DE), Stroop, Nicolas (Biele feld, DE). This patent was filed on May 3, 2022 and was published online on May 14, 2024. From the background information supplied by the inventors, news correspondents o btained the following quote: "In particular, for cleaning larger commercial floo r areas such as retail areas in fashion stores, a cleaning system is used that h as a fleet of multiple autonomous or self-propelled cleaning robots and one or m ore base stations that are designed to empty and supply power to the cleaning ro bots. The following problems arise here: During the non-active cleaning time, wh en the cleaning robots are not performing any cleaning tasks, a fleet or the ind ividual cleaning robots of the fleet together with their base station(s) take up a lot of space. In the commercial application context, this high space requirem ent of the cleaning system is problematic. In retail areas in particular, every occupied square meter represents a direct intervention in the profitability of t he business in question. In addition, the appearance of the goods can be adverse ly affected by the robots standing around. There is also a risk that robots will be stolen or damaged outside of the active cleaning time."

原文链接:

NETL
NSTL