期刊,Robotics & Machine Learning Daily News 2024年卷Oct.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

Inner Mongolia Agricultural University Reports Findings in Artificial Intelligen ce (Predicting Lactobacillus delbrueckii subsp. bulgaricus-Streptococcus thermop hilus interactions based on a highly accurate semi-supervised learning method)

77-78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 from Hohhot, People's Republic of China, by NewsRx journalists, research stated, "Lactobacillus delbru eckii subsp. bulgaricus (L. bulgaricus) and Streptococcus thermophilus (S. therm ophilus) are commonly used starters in milk fermentation. Fermentation experimen ts revealed that L. bulgaricus-S. thermophilus interactions (LbStI) substantiall y impact dairy product quality and production." The news correspondents obtained a quote from the research from Inner Mongolia A gricultural University, "Traditional biological humidity experiments are time-co nsuming and labor-intensive in screening interaction combinations, an artificial intelligence-based method for screening interactive starter combinations is nec essary. However, in the current research on artificial intelligence based intera ction prediction in the field of bioinformatics, most successful models adopt su pervised learning methods, and there is a lack of research on interaction predic tion with only a small number of labeled samples. Hence, this study aimed to dev elop a semi-supervised learning framework for predicting LbStI using genomic dat a from 362 isolates (181 per species). The framework consisted of a two-part mod el: a co-clustering prediction model (based on the Kyoto Encyclopedia of Genes a nd Genomes (KEGG) dataset) and a Laplacian regularized least squares prediction model (based on K-mer analysis and gene composition of all isolates datasets). T o enhance accuracy, we integrated the separate outcomes produced by each compone nt of the two-part model to generate the ultimate LbStI prediction results, whic h were verified through milk fermentation experiments. Validation through milk f ermentation experiments confirmed a high precision rate of 85% (17 /20; validated with 20 randomly selected combinations of expected interacting is olates). Our data suggest that the biosynthetic pathways of cysteine, riboflavin , teichoic acid, and exopolysaccharides, as well as the ATP-binding cassette tra nsport systems, contribute to the mutualistic relationship between these starter bacteria during milk fermentation. However, this finding requires further exper imental verification."

原文链接:

NETL
NSTL

Data on Robotics Discussed by Researchers at Fujian University of Technology (In telligent human-robot collaborative handover system for arbitrary objects based on 6D pose recognition)

78-79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 subjec t of a new report. According to news reporting originating from Fuzhou, People's Republic of China, by NewsRx correspondents, research stated, "In daily practic e, there are several instances of diverse object handover between humans. For ex ample, in an automobile production line, workers need to pick up parts and deliv er them to colleagues or acquire parts from them and put the parts in the approp riate position. Similarly, in households, children assist bedridden elderly peop le by passing them a cup of water, and in medical surgeries, assistants take ove r surgical tools used by doctors." Our news journalists obtained a quote from the research from Fujian University o f Technology: "These tasks require a considerable amount of time and manpower. I n these scenarios, it is necessary to deliver the target object efficiently and quickly while prioritizing the safety of the object. Collaborative robots can se rve as human colleagues to perform these simple, time-consuming, and laborious t asks. We expect humans and robots to hand over objects seamlessly in a natural a nd efficient way, just as humans naturally hand over objects to each other. This paper proposes a 6-dimensional (6D) pose recognitionbased human-robot collabor ative handover system to address the problem of inaccurate object grasping cause d by imprecise recognition of object poses during the human-robot collaborative handover process. The main contents are as follows: To solve the 6D pose recogni tion problem, a residual network (ResNet) is introduced to conduct semantic segm entation and key-point vector field prediction on the image, and the random samp le consensus (RANSAC) voting is used to predict key-point coordinates. Further, an improved efficient perspective-n-point (EPnP) algorithm is used to predict th e object pose, which can improve the accuracy. An improved dataset production me thod is proposed by analyzing the advantages and disadvantages of the LineMod da taset and based on the latest 3-dimensional (3D) reconstruction technology. To r ealize the accurate identification of daily objects, which can reduce the time r equired for dataset production. The transformation relationship (from the object to the camera and then to the robot base coordinate systems) is obtained throug h internal parameter calibration and hand-eye calibration methods of the camera. Thus, the pose of the target object in the robot base coordinate system is dete rmined. Further, a grasping method for effective position and orientation calcul ation is proposed to realize precise object pose localization and accurate grasp ing. A handover experiment platform was set up to validate the effectiveness of the proposed human-robot collaborative handover system, with four volunteers con ducting 80 handover experiments."

原文链接:

NETL
NSTL

City University of Macau Researcher Publishes New Study Findings on Artificial I ntelligence (How and when artificial intelligence usage facilitates task perform ance)

79-79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 reporting out of Macao, People's Republic of China, by NewsRx editors, research stated, "This study investigated how the inc reasing usage of artificial intelligence (AI) in diverse business applications h as affected task performance." Our news correspondents obtained a quote from the research from City University of Macau: "Building on the job demands-resources model, we employed moderated me diation modeling to investigate the association between AI usage and the task pe rformance of delivery drivers. Participants comprised 251 delivery drivers who c ompleted online surveys over a 1-month period. Hierarchical regression analysis revealed that work engagement played a mediating role in the association between AI usage and the task performance of delivery drivers. Moreover, the mediating role of work engagement was moderated by an individual's concept of their future work self. When an individual had a stronger sense of their future work self, t he mediating role of work engagement became more pronounced."

原文链接:

NETL
NSTL

Findings in Machine Learning Reported from University of Wisconsin Madison (Vali d Inference for Machine Learning-assisted Genomewide Association Studies)

80-80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 from Madison, Wisconsin, by NewsRx j ournalists, research stated, "Machine learning (ML) has become increasingly popu lar in almost all scientific disciplines, including human genetics. Owing to cha llenges related to sample collection and precise phenotyping, ML-assisted genome -wide association study (GWAS), which uses sophisticated ML techniques to impute phenotypes and then performs GWAS on the imputed outcomes, have become increasi ngly common in complex trait genetics research." Financial supporters for this research include Office of the Administrator (NIH) , National Institutes of Health (NIH) - USA, Graduate Education, Wisconsin Alumn i Research Foundation - National Institute on Aging (NIA) Center Grant.

原文链接:

NETL
NSTL

New Robotics Study Results Reported from Chiang Mai University (A New Active-thr ust Tool Spindle and Integrated Force Measurement Technique for Robotic Drilling )

81-81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 subjec t of a report. According to news originating from Chiang Mai, Thailand, by NewsR x correspondents, research stated, "A new concept for a smart drill spindle with active magnetic thrust bearing has been developed to enhance the monitoring and control capabilities of robotic drilling systems. This article reports on the r ealization and evaluation of an integrated thrust-force sensing technique for th e spindle unit." Financial support for this research came from Fundamental Fund 2023, Chiang Mai University. Our news journalists obtained a quote from the research from Chiang Mai Universi ty, "The proposed technique uses a model-based state estimation scheme with cali brated nonlinear model of the spindle bearing forces. The method requires only o ne axial displacement sensor for real-time tool-force estimation and position co ntrol. A speed-dependent disturbance model is further defined and incorporated w ithin the estimation scheme to compensate for spindle rotation effects. A method of using robot end-effector acceleration measurements to decouple the force est imate from both robot motion and gravity effects is also shown. Experiments are performed with a 7-axis lightweight industrial manipulator to assess the system' s ability to provide accurate thrust force information under varied drilling con ditions, while simultaneously controlling the motion of the drilling tool relati ve to the robot end-effector."

原文链接:

NETL
NSTL

Studies from Port-Said University Reveal New Findings on Robotics (Are nurses an d patients willing to work with service robots in healthcare? A mixed-methods st udy)

82-82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 Port-Said Universi ty by NewsRx correspondents, research stated, "Scholars have become increasingly interested in incorporating robots into healthcare. While there is a growing bo dy of research examining nurses' and patients' attitudes towards using robots in healthcare, no prior research has specifically explored their willingness to in tegrate service robots within the Egyptian healthcare context." Financial supporters for this research include Port Said University. The news journalists obtained a quote from the research from Port-Said Universit y: "The aim of this study was twofold: (a) to explore the behavioral intentions of nurses to accept robots in their workplace, and (b) to examine the willingnes s of patients to use service robots in healthcare settings. A mixedmethods stud y was conducted. Quantitative data were collected from 301 nurses using the Beha vioral Intention to Accept Robots in the Workplace Scale and from 467 patients u sing the Service Robot Integration Willingness Scale through convenience samplin g at three tertiary public hospitals in Port Said, Egypt. Qualitative data were obtained through in-depth, semi-structured interviews with 16 nurses, focusing o n their perspectives and concerns regarding robot integration. Descriptive analy ses were used to analyze quantitative data, and thematic analysis was used to an alyze qualitative data. Quantitative results indicated a moderate level of behav ioral intention to use robots among nurses. Patients demonstrated low willingnes s to use service robots. In the qualitative analysis of the data obtained from t he interviews with nurses, three categories (Concerns about Robots, Roles and Co mpetencies, and Potential Benefits) and eight themes (interaction and emotions, maintenance and reliability, job insecurity, role clarity, competence in critica l care, trustworthiness, reducing physical strain, and specialized applications) were identified."

原文链接:

NETL
NSTL

Kyungpook National University Researcher Provides New Study Findings on Machine Learning (A Comparative Analysis of Machine Learning Techniques for Predicting t he Performance of Microchannel Gas Coolers in CO2 Automotive Air-Conditioning Sy stems)

83-83页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Investigators publish new report on artificial in telligence. According to news reporting from Daegu, South Korea, by NewsRx journ alists, research stated, "The automotive industry is increasingly focused on dev eloping more energy-efficient and eco-friendly air-conditioning systems." Financial supporters for this research include Korea Institute of Energy Technol ogy Evaluation And Planning. The news editors obtained a quote from the research from Kyungpook National Univ ersity: "In this context, CO2 microchannel gas coolers (MCGCs) have emerged as p romising alternatives due to their low global warming potential (GWP) and enviro nmental benefits. This paper explores the application of machine learning (ML) a lgorithms to predict the thermohydraulic performance of MCGCs in automotive air- conditioning systems. Using data generated from an experimentally validated nume rical model, this study compares various ML techniques, including both linear an d nonlinear regression models, to forecast key performance metrics such as refri gerant outlet temperature, pressure drop, and heat transfer rate. Spearman's cor relation was employed to develop performance maps, whereas the R2 and MSE metric s were used to evaluate the models' predictive accuracy. The linear models gave around 70% forecasting accuracy for pressure drop across the gas c ooler and 97% accuracy for refrigerant outlet temperature, whereas the nonlinear models achieved more accurate predictions, with an accuracy rangi ng from 71% to 99%."

原文链接:

NETL
NSTL

Reports Outline Machine Learning Findings from Northwestern University (Predicti ng Partial Atomic Charges In Metal-organic Frameworks: an Extension To Ionic Mof s)

84-84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 originating from Evanston, Illinois, by NewsRx correspondents, research stated, "Molecular simulation is an invaluable tool to predict and understand the usage of metal-organic frameworks (MOFs) for gas sto rage and separation applications. Accurate partial atomic charges, commonly obta ined from density functional theory (DFT) calculations, are often required to mo del the electrostatic interactions between the MOF and adsorbates, especially wh en the adsorbates have dipole or quadrupole moments, such as water and CO2." Financial supporters for this research include United States Department of Energ y (DOE), NERSC, United States Department of Energy (DOE).

原文链接:

NETL
NSTL

Nanyang Technological University Reports Findings in Artificial Intelligence (Co nfronting the data deluge: How artificial intelligence can be used in the study of plant stress)

85-85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 originating from Singapore, Sing apore, by NewsRx correspondents, research stated, "The advent of the genomics er a enabled the generation of high-throughput data and computational methods that serve as powerful hypothesis-generating tools to understand the genomic and gene functional basis of plant stress resilience. The proliferation of experimental and analytical methods used in biology has resulted in a situation where plentif ul data exists, but the volume and heterogeneity of this data has made analysis a significant challenge." Our news journalists obtained a quote from the research from Nanyang Technologic al University, "Current advanced deep-learning models have displayed an unpreced ented level of comprehension and problem-solving ability, and have been used to predict gene structure, function and expression based on DNA or protein sequence , and prominently also their use in high-throughput phenomics in agriculture. Ho wever, the application of deep-learning models to understand gene regulatory and signalling behaviour is still in its infancy. We discuss in this review the ava ilability of data resources and bioinformatic tools, and several applications of these advanced ML/AI models in the context of plant stress response, and demons trate the use of a publicly available LLM (ChatGPT) to derive a knowledge graph of various experimental and computational methods used in the study of plant str ess."

原文链接:

NETL
NSTL

Ural Federal University Named after the First President of Russia B.N. Yeltsin R esearchers Describe Findings in Machine Learning (Application of SHAP and Multi- Agent Approach for Short-Term Forecast of Power Consumption of Gas Industry ...)

86-86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 artificial in telligence have been published. According to news originating from Ekaterinburg, Russia, by NewsRx correspondents, research stated, "Currently, machine learning methods are widely applied in the power industry to solve various tasks, includ ing short-term power consumption forecasting." Funders for this research include Ministry of Science And Higher Education of Th e Russian Federation. The news editors obtained a quote from the research from Ural Federal University Named after the First President of Russia B.N. Yeltsin: "However, the lack of i nterpretability of machine learning methods can lead to their incorrect use, pot entially resulting in electrical system instability or equipment failures. This article addresses the task of short-term power consumption forecasting, one of t he tasks of enhancing the energy efficiency of gas industry enterprises. In orde r to reduce the risks of making incorrect decisions based on the results of shor t-term power consumption forecasts made by machine learning methods, the SHapley Additive exPlanations method was proposed. Additionally, the application of a m ulti-agent approach for the decomposition of production processes using self-gen eration agents, energy storage agents, and consumption agents was demonstrated. It can enable the safe operation of critical infrastructure, for instance, adjus ting the operation modes of self-generation units and energy-storage systems, op timizing the power consumption schedule, and reducing electricity and power cost s. A comparative analysis of various algorithms for constructing decision tree e nsembles was conducted to forecast power consumption by gas industry enterprises with different numbers of categorical features."

原文链接:

NETL
NSTL