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

    Study Results from Pontificia University Javeriana Broaden Understanding of Mach ine Learning (Classification of Activities of Daily Living for Older Adults Usin g Machine Learning and Fixed Time Windowing Technique)

    89-90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 Bogota, Colombia, by N ewsRx journalists, research stated, "The classification of activities of daily l iving (ADLs) in the home of older adults makes it possible to identify risk situ ations and changes in behavior that may be associated with some type of problem. This information allows caregivers and health professionals to take action when these types of situations are detected." Financial support for this research came from Pontificia Universidad Javeriana. The news correspondents obtained a quote from the research from Pontificia Unive rsity Javeriana, "Although many machine learning classification techniques have been proposed, the effectiveness of the solution in a real-world context remains unclear in most cases due to the large number of sensors required, the type of sensors used which may pose privacy issues, and the assumption of considering on ly segmented sensor events for each activity before training the models. This ar ticle presents an evaluation of different machine learning techniques using fixe d time windows to extract spatiotemporal features and classify ten human activit ies in a real smart home with unobtrusive sensors using the Aruba CASAS dataset. The three classification techniques that achieved better performance were rando m forest, XGBoost, and support vector machine (SVM), achieving an accuracy of 97 % with our best model, outperforming other approaches from the lit erature that were using the same dataset under similar conditions."
      原文链接:
    • NETL
    • NSTL

    Study Findings on Artificial Intelligence Reported by Researchers at National Co llege of Business Administration and Economics (Identification of kidney stones in KUB X-ray images using VGG16 empowered with explainable artificial intelligen ce)

    90-90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 reporting from National Colleg e of Business Administration and Economics by NewsRx journalists, research state d, "A kidney stone is a solid formation that can lead to kidney failure, severe pain, and reduced quality of life from urinary system blockages." Financial supporters for this research include This Research Work Is Supported B y Qatar National Library.. Our news editors obtained a quote from the research from National College of Bus iness Administration and Economics: "While medical experts can interpret kidney- ureter-bladder (KUB) X-ray images, specific images pose challenges for human det ection, requiring significant analysis time. Consequently, developing a detectio n system becomes crucial for accurately classifying KUB X-ray images. This artic le applies a transfer learning (TL) model with a pre-trained VGG16 empowered wit h explainable artificial intelligence (XAI) to establish a system that takes KUB X-ray images and accurately categorizes them as kidney stones or normal cases. The findings demonstrate that the model achieves a testing accuracy of 97.41% in identifying kidney stones or normal KUB X-rays in the dataset used. VGG16 mod el delivers highly accurate predictions but lacks fairness and explainability in their decision-making process. This study incorporates the Layer-Wise Relevance Propagation (LRP) technique, an explainable artificial intelligence (XAI) techn ique, to enhance the transparency and effectiveness of the model to address this concern."
      原文链接:
    • NETL
    • NSTL

    Study Findings on Machine Learning Reported by a Researcher at Department of Ele ctrical Engineering and Industrial Informatics (Power Factor Modelling and Predi ction at the Hot Rolling Mills' Power Supply Using Machine Learning Algorithms)

    91-91页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Data detailed on artificial intelligence have bee n presented. According to news reporting out of Timisoara, Romania, by NewsRx ed itors, research stated, "The power supply is crucial in the present day due to t he negative impacts of poor power quality on the electric grid." The news journalists obtained a quote from the research from Department of Elect rical Engineering and Industrial Informatics: "In this research, we employed dee p learning methods to investigate the power factor, which is a significant indic ator of power quality. A multi-step forecast was developed for the power factor in the power supply installation of a hot rolling mill, extending beyond the hor izontal line. This was conducted using data obtained from the respective electri cal supply system. The forecast was developed via hybrid RNN (recurrent neural n etworks) incorporating LSTM (long short-term memory) and GRU (gated recurrent un it) layers. This research utilized hybrid recurrent neural network designs with deep learning methods to build several power factor models. These layers have ad vantages for time series forecasting."
      原文链接:
    • NETL
    • NSTL

    Report Summarizes Androids Study Findings from University of Birmingham (Learnin g By Doing: a Dual-loop Implementation Architecture of Deep Active Learning and Human-machine Collaboration for Smart Robot Vision)

    92-93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 - Androi ds are discussed in a new report. According to news reporting from Birmingham, U nited Kingdom, by NewsRx journalists, research stated, "To develop vision system s for autonomous robotic disassembly, this paper presents a dual-loop implementa tion architecture that enables a robot vision system to learn from human vision in disassembly tasks. The architecture leverages human visual knowledge through a collaborative scheme named ‘learning-by-doing." Financial supporters for this research include Engineering & Physi cal Sciences Research Council (EPSRC), National Natural Science Foundation of Ch ina (NSFC), China Scholarship Council. The news correspondents obtained a quote from the research from the University o f Birmingham, "In the dual-loop implementation architecture, a human-robot colla borative disassembly loop containing autonomous perception, human-robot interact ion and autonomous execution processes is established to address perceptual chal lenges in disassembly tasks by introducing human operators wearing augmented rea lity (AR) glasses, while a deep active learning loop is designed to use human vi sual knowledge to develop robot vision through autonomous perception, human-robo t interaction and model learning processes. Considering uncertainties in the con ditions of products at the end of their service life, an objective ‘informativen ess' matrix integrating the label information and regional information is design ed for autonomous perception, and AR technology is utilised to improve the opera tional accuracy and efficiency of the human-robot interaction process. By sharin g the autonomous perception and humanrobot interaction processes, the two loops are simultaneously executed. To validate the capability of the proposed archite cture, a screw removal task was studied. The experiments demonstrated the capabi lity to accomplish challenging perceptual tasks and develop the perceptual abili ty of robots accurately, stably, and efficiently in disassembly processes."
      原文链接:
    • NETL
    • NSTL

    University of Oxford Reports Findings in Mycobacterium tuberculosis (Prediction of pyrazinamide resistance in Mycobacterium tuberculosis using structure-based m achine-learning approaches)

    93-94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 Gram-Positive Bacteria - Mycobacterium tuberculosis is the subject of a report. According to news orig inating from Oxford, United Kingdom, by NewsRx correspondents, research stated, "Pyrazinamide is one of four first-line antibiotics used to treat tuberculosis; however, antibiotic susceptibility testing for pyrazinamide is challenging. Resi stance to pyrazinamide is primarily driven by genetic variation in , encoding an enzyme that converts pyrazinamide into its active form." Financial supporters for this research include National Institute for Health Res earch Health Protection Research Unit, Public Health England, National Institute for Health Research, Oxford Biomedical Research Centre, Wellcome Trust, Newton Fund-MRC, Bill and Melinda Gates Foundation, European Commission, South African Medical Research Council, National Institutes of Health, Rhodes Trust, EPSRC, NI HR Senior Investigators, NIHR Academic Clinical Lecturer, TORCH, Flemish Fund fo r Scientific Research, Claude Leon Foundation, NHS, Department of Health, Center s for Disease Control and Prevention, US Department of Health and Human Services .
      原文链接:
    • NETL
    • NSTL

    Study Data from University of Auckland Provide New Insights into Robotics (Human -robot Shared Assembly Taxonomy: a Step Toward Seamless Human-robot Knowledge Tr ansfer)

    94-95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 from Auckland, New Zealand, by NewsRx journa lists, research stated, "Future manufacturing will witness a shift in human-robo t relationships toward collaboration, compassion, and coevolution. This will req uire seamless human-robot knowledge transfer." Financial supporters for this research include University of Auckland FRDF New S taff Research Fund, Industrial AI Research Group at Department of Mechanical and Mechatronics Engineering, The University of Auckland. The news correspondents obtained a quote from the research from the University o f Auckland, "Differences in language and knowledge representation hinder the tra nsfer of knowledge between humans and robots. Thus, a unified knowledge represen tation system that can be shared by humans and robots is essential. Driven by th is need in a product as-sembly scenario, we propose the Human-Robot Shared Assem bly Taxonomy (HR-SAT). With HR-SAT, any comprehensive assembly task can be repre sented as a knowledge graph that both humans and robots can un-derstand. To ensu re consistency in task decomposition and representation, we define the key eleme nts of HR-SAT. HR-SAT incorporates rich assembly information and provides necess ary information for diverse applications, e.g., process planning, quality checki ng, and human-robot collaboration. The usage and practicality of HR-SAT are demo nstrated through two case studies. As a unified assembly process representation schema, HR-SAT constitutes a critical step toward seamless human-robot knowledge transfer."
      原文链接:
    • NETL
    • NSTL

    Harbin Institute of Technology Researcher Yields New Data on Machine Learning (A ccelerated First-Principles Calculations Based on Machine Learning for Interfaci al Modification Element Screening of SiCp/Al Composites)

    95-95页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New study results on artificial intell igence have been published. According to news reporting out of Harbin, People's Republic of China, by NewsRx editors, research stated, "SiCp/Al composites offer the advantages of lightweight construction, high strength, and corrosion resist ance, rendering them extensively applicable across various domains such as aeros pace and precision instrumentation." Funders for this research include National Key R&D Program of China . The news correspondents obtained a quote from the research from Harbin Institute of Technology: "Nonetheless, the interfacial reaction between SiC and Al under high temperatures leads to degradation in material properties. In this study, th e interface segregation energy and interface binding energy subsequent to the in clusion of alloying elements were computed through a first-principle methodology , serving as a dataset for machine learning. Feature descriptors for machine lea rning undergo refinement via feature engineering. Leveraging the theory of machi ne-learning-accelerated first-principle computation, six machine learning models -RBF, SVM, BPNN, ENS, ANN, and RF-were developed to train the dataset, with the ANN model selected based on R2 and MSE metrics. Through this model, the accelera ted computation of interface segregation energy and interface binding energy was achieved for 89 elements. The results indicate that elements including B, Si, F e, Co, Ni, Cu, Zn, Ga, and Ge exhibit dual functionality, inhibiting interfacial reactions while bolstering interfacial binding."
      原文链接:
    • NETL
    • NSTL

    Data from Department of Bioengineering Advance Knowledge in Machine Learning (In formation decomposition in complex systems via machine learning)

    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 artificial intelligenc e is the subject of a new report. According to news originating from the Departm ent of Bioengineering by NewsRx editors, the research stated, "One of the fundam ental steps toward understanding a complex system is identifying variation at th e scale of the system's components that is most relevant to behavior on a macros copic scale." Our news correspondents obtained a quote from the research from Department of Bi oengineering: "Mutual information provides a natural means of linking variation across scales of a system due to its independence of functional relationship bet ween observables. However, characterizing the manner in which information is dis tributed across a set of observables is computationally challenging and generall y infeasible beyond a handful of measurements. Here, we propose a practical and general methodology that uses machine learning to decompose the information cont ained in a set of measurements by jointly optimizing a lossy compression of each measurement. Guided by the distributed information bottleneck as a learning obj ective, the information decomposition identifies the variation in the measuremen ts of the system state most relevant to specified macroscale behavior. We focus our analysis on two paradigmatic complex systems: a Boolean circuit and an amorp hous material undergoing plastic deformation."
      原文链接:
    • NETL
    • NSTL

    College of Science Reports Findings in Ischemia (Development and internal valida tion of machine learning-based models and external validation of existing risk s cores for outcome prediction in patients with ischaemic stroke)

    97-97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 Vascular Diseases and Conditions - Ischemia is the subject of a report. According to news reporting fr om Murdoch, Australia, by NewsRx journalists, research stated, "We developed new machine learning (ML) models and externally validated existing statistical mode ls [ischaemic stroke predictive risk score (iScore) and total led health risks in vascular events (THRIVE) scores] for pred icting the composite of recurrent stroke or all-cause mortality at 90 days and a t 3 years after hospitalization for first acute ischaemic stroke (AIS). In adult s hospitalized with AIS from January 2005 to November 2016, with follow-up until November 2019, we developed three ML models [random forest ( RF), support vector machine (SVM), and extreme gradient boosting (XGBOOST)] and externally validated the iScore and THRIVE scores for predicting the composi te outcomes after AIS hospitalization, using data from 721 patients and 90 poten tial predictor variables." The news correspondents obtained a quote from the research from the College of S cience, "At 90 days and 3 years, 11 and 34% of patients, respectiv ely, reached the composite outcome. For the 90-day prediction, the area under th e receiver operating characteristic curve (AUC) was 0.779 for RF, 0.771 for SVM, 0.772 for XGBOOST, 0.720 for iScore, and 0.664 for THRIVE. For 3-year predictio n, the AUC was 0.743 for RF, 0.777 for SVM, 0.773 for XGBOOST, 0.710 for iScore, and 0.675 for THRIVE. The study provided three ML-based predictive models that achieved good discrimination and clinical usefulness in outcome prediction after AIS and broadened the application of the iScore and THRIVE scoring system for l ong-term outcome prediction."
      原文链接:
    • NETL
    • NSTL

    New Robotics Findings Reported from Chongqing University (Research On Robotic Be lt Grinding Method of Blisk for Obtaining High Surface Integrity Features With V ariable Inclination Angle Force Control)

    98-99页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on Robotics have been pr esented. According to news reporting out of Chongqing, People's Republic of Chin a, by NewsRx editors, research stated, "The blisk was a new type of component fo r high-performance aero-engines, which could significantly improve the energy ef ficiency ratio of the engine, however there were also shortcomings such as narro w structure and difficult material removal. Robotic belt grinding was widely use d in the processing of key complex surfaces such as blades, fairings and propell ers, which is due to its large processing space and high flexibility." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), National Science and Tech- nology Major Project, Basic Resea rch Funds for Central Universities. Our news journalists obtained a quote from the research from Chongqing Universit y, "Nevertheless, how to improve the surface integrity of the blisk under the pr emise of ensuring the profile accuracy was a challenging problem. In view of the above problems, this study started with the grinding force, and innovatively pr oposed a robotic belt grinding method for high surface integrity of blisk based on variable inclination angle force control. Firstly, a belt grinding robot base d on macro-micro-end hand structure and electromagnetic forcecontrolled end was designed based on indirect arm-winding control. Secondly, an adaptive variable i mpedance compliance based blisk grinding model was established through the relat ion expression of grinding end and the mathematical formula of inclination conta ct micro-surface control, which effectively coordinates the coupling relationshi p between force control and trajectory under inclined attitude. Lastly, the expe rimental study proved that the normal grinding force of this method was stable a nd the error was 1.14 %, the surface hardness and residual compress ive stress were improved by about 8.57 % and 52.82 % respectively, the surface morphology was uniform and the surface defects are wel l suppressed."
      原文链接:
    • NETL
    • NSTL