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 Beihang University in the Area of Machine Learning Reported (Estimation of Stress Intensity Factor for Surface Cracks In the Firtree Groove Structure of a Turbine Disk Using Pool-based Active Learning With Gaussian Process …)

    87-88页
    查看更多>>摘要：Researchers detail new data in Machine Learning. According to news reporting out of Beijing, People's Republic of China, by NewsRx editors, research stated, "Calculation of the stress intensity factor K is a crucial and difficult task in linear elastic fracture mechanics. With the capacity to solve complex input-output problems of an underlying system, machine learning is especially useful in the calculation of K. However, when faced with complex systems, such as the firtree groove structure of a turbine disk, the data-consuming issue has always been a thorny problem in K -solutions combined with machine learning studies for a long time." Funders for this research include National Major Science and Technology Project, Fundamental Research Funds for the Central Universities. Our news journalists obtained a quote from the research from Beihang University, "In this paper, a novel K -solution method called PA-GPR (Pool -based Active learning with Gaussian Process Regression) for the calculation of the stress intensity factor for surface cracks in the firtree groove structure of a turbine disk is proposed. Using the pool -based active learning strategy, the proposed K -solution method could make the GPR model have a great regression performance with a few samples required. In the pool -based active learning strategy analysis, the learning function based on greedy sampling is proposed to select samples with a high contribution to the training of the GPR model. The calculation of K for a semi -elliptical surface crack in the firtree groove structure is evaluated to verify the accuracy and effectiveness of the proposed method."
      原文链接:
    • NETL
    • NSTL

    New Machine Learning Study Findings Reported from University of Colombo (webdraw: a Machine Learning-driven Tool for Automatic Website Prototyping)

    88-89页
    查看更多>>摘要：Investigators discuss new findings in Machine Learning. According to news reporting from Colombo, Sri Lanka, by NewsRx journalists, research stated, "To overcome the time-consuming nature and improve the cost-effectiveness of classical web development, being automatic is the most convenient alternative recent researchers suggest. Over the years, researchers have been working on inventing new approaches to generating websites automatically." The news correspondents obtained a quote from the research from the University of Colombo, "In this paper, a novel approach is presented that automates the website generation process by incorporating web designer best practices and driving new prototype websites without the significant effort of redesigning websites. It takes high-fidelity mock-up design artifacts such as screen captures of real-world websites, and generates functional websites similar to the input websites, which involves three steps: GUI element detection, classification, and code generation. First, image processing techniques are applied to detect atomic web GUI elements from a mock-up design artifact of a real-world website. Second, a Convolutional Neural Network (CNN) is trained to classify the extracted web GUI elements into their domain-specific types such as headings, paragraphs, images, etc. A Graphical User Interface (GUI) is typically represented in code as a hierarchical tree, with nested GUI elements bundled together within one another to construct a tree. A recursive algorithm is proposed that constructs the appropriate Document Object Model (DOM) hierarchy for a website by recursively grouping classified web GUI elements within each other. Finally, the constructed DOM is converted to the accurate native code. The approach was implemented as a tool called WebDraw. Design science research evaluation shows that WebDraw achieves an average of 90% web GUI element classification and generates website prototypes that are visually similar to the target website design mock-up artifact while producing functional GUI code."
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    King's College Hospital Reports Findings in Artificial Intelligence (Generative pretrained transformer-4, an artificial intelligence text predictive model, has a high capability for passing novel written radiology exam questions)

    89-90页
    查看更多>>摘要：New research on Artificial Intelligence is the subject of a report. According to news reporting originating in London, United Kingdom, by NewsRx journalists, research stated, "AI-image interpretation, through convolutional neural networks, shows increasing capability within radiology. These models have achieved impressive performance in specific tasks within controlled settings, but possess inherent limitations, such as the inability to consider clinical context." The news reporters obtained a quote from the research from King's College Hospital, "We assess the ability of large language models (LLMs) within the context of radiology specialty exams to determine whether they can evaluate relevant clinical information. A database of questions was created with official sample, author written, and textbook questions based on the Royal College of Radiology (United Kingdom) FRCR 2A and American Board of Radiology (ABR) Certifying examinations. The questions were input into the Generative Pretrained Transformer (GPT) versions 3 and 4, with prompting to answer the questions. One thousand seventy-two questions were evaluated by GPT-3 and GPT-4. 495 (46.2%) were for the FRCR 2A and 577 (53.8%) were for the ABR exam. There were 890 single best answers (SBA), and 182 true/false questions. GPT-4 was correct in 629/890 (70.7%) SBA and 151/182 (83.0%) true/false questions. There was no degradation on author written questions. GPT-4 performed significantly better than GPT-3 which selected the correct answer in 282/890 (31.7%) SBA and 111/182 (61.0%) true/false questions. Performance of GPT-4 was similar across both examinations for all categories of question. The newest generation of LLMs, GPT-4, demonstrates high capability in answering radiology exam questions. It shows marked improvement from GPT-3, suggesting further improvements in accuracy are possible."
      原文链接:
    • NETL
    • NSTL

    New Findings from South China University of Technology in the Area of Robotics Described (Online Fault Diagnosis of Harmonic Drives Using Semisupervised Contrastive Graph Generative Network Via Multimodal Data)

    90-91页
    查看更多>>摘要：New research on Robotics is the subject of a report. According to news reporting out of Guangzhou, People's Republic of China, by NewsRx editors, research stated, "Harmonic drive is a core component of the industrial robot, its failure will directly affect the robot's performance. Moreover, as the harmonic drive often works with excessive speed and load, it may fail unpredictably." Financial supporters for this research include National Natural Science Foundation of China (NSFC), International Cooperation Projects of Guangzhou Development Zone, Opening Project of National and Local Joint Engineering Research Center for Industrial Friction and Lubrication Technology, National Natural Science Foundation of Guangdong Province, KEY Laboratory of Robotics and Intelligent Equipment of Guangdong Regular Institutions of Higher Education, Innovation Center of Robotics and Intelligent Equipment. Our news journalists obtained a quote from the research from the South China University of Technology, "Therefore, online fault diagnosis is quite significant. In this article, we propose an online intelligent fault diagnosis method for harmonic drives using a semisupervised contrastive graph generative network (SCGGN) via multimodal data. First, multimodal data (including motor current signals and encoder signals) of the harmonic drive are collected online. The Euclidean distance is used to analyze the similarity of the data in the frequency domain. Second, multiple graph convolution network and hierarchical graph convolution network are used to obtain complementary fault features from local and global views, respectively. Third, the contrastive learning network is constructed to obtain high-level information through unsupervised learning and perform data clustering to obtain the multiclassification output. Finally, a combination of learnable loss functions is used to optimize the SCGGN. The presented method is tested on an industrial robot."
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Studies from University of the Mediterranean in the Area of Artificial Intelligence Published (The benefits of using IPA in relation to RPA for the cryptocurrency sector, in making decisions on their sale and purchase in the stock market)

    91-92页
    查看更多>>摘要：Fresh data on artificial intelligence are presented in a new report. According to news reporting originating from the University of the Mediterranean by NewsRx correspondents, research stated, "Since 2009 when the first cryptocurrency Bitcoin began to be inserted into the market of electronic currencies, today in 2023 there are more than 19,850 electronic cryptocurrencies [1]." The news journalists obtained a quote from the research from University of the Mediterranean: "According to information from the coinecko website, the cryptocurrency market has expanded dramatically from a market capitalization of $1 million in 2013 to $3 trillion in November 2021 [2]. Referring to the latest statistical data, 3 are the cryptocurrencies that rule the e-commerce market in November 2023, Bitcoin,Ethereum AND Tether USDt [3]. Robotic Process Automation (RPA) is a growing trend in the restructuring of business processes, combined with digital transformation. This technology can be applied in different areas of business processes and by organizations from any activity sector [4].With continuous advances in automated processes through RPA, mechanisms involving Artificial Intelligence (AI) were incorporated to influence real-life decision-making [5]. Artificial Intelligence (AI) allows improving the accuracy and execution of RPA processes in extracting information and recognizing, classifying, predicting and optimizing processes [6].Nowadays, artificial intelligence is affecting the way people process computer data, televisions have started to create avatars that they use for news reporting."
      原文链接:
    • NETL
    • NSTL

    Research Data from Tongji University Update Understanding of Machine Learning (Machine-learning Assisted Screening of Double Metal Catalysts for Co2 Electroreduction To Ch4)

    92-93页
    查看更多>>摘要：Researchers detail new data in Machine Learning. According to news reporting originating in Shanghai, People's Republic of China, by NewsRx journalists, research stated, "Electrochemical CO2 reduction reaction (CO2RR) has become a promising application in addressing energy challenges and environmental crises. However, the scaling relationship between the reaction intermediates constrains the successful deep reduction of CO2." Funders for this research include National Natural Science Foundation of China (NSFC), National Key Research and Development Project, Fundamental Research Funds for the Central Universities. The news reporters obtained a quote from the research from Tongji University, "Dual-metal-site catalysts (DMSCs) have emerged as potential electrocatalysts for CO2RR by breaking the scaling relationship due to their more adaptable active sites. Herein, this study aims to investigate the correlation between the adsorption energies of essential intermediates in CO2RR catalysis with double transition metal atoms anchored on graphdiyne monolayer (TM1-TM2@GDY) through machine-learning (ML) assisted density functional theory (DFT) calculations. The results reveal the important descriptors of CO2RR catalyzed by TM1-TM2@GDY, and demonstrate that the heteronuclear TM1TM2@GDY have great potential for deep CO2 reduction. Especially, Co-Mo@GDY and Co-W@GDY show low limiting potential (-0.60 V and -0.39 V, respectively) and high selectivity on the reaction from CO2 to CH4 based on the free energy diagrams. This study indicates that the two TM atoms on GDY act cooperatively for the catalysis of CO2RR."
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    New Artificial Intelligence Study Findings Have Been Reported from University of Sao Paulo (Fostering Artificial Intelligence To Face Misinformation: Discourses and Practices of Automated Factchecking In Brazil)

    93-94页
    查看更多>>摘要：Investigators publish new report on Artificial Intelligence. According to news reporting originating in Sao Paulo, Brazil, by NewsRx editors, the research stated, "This article examines the advancement of automated fact-checking in Brazil and investigates how artificial intelligence (AI) products shape publishers' discourses and practices. First, it maps the field to identify how it has evolved throughout the years." Financial support for this research came from Fundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP). The news reporters obtained a quote from the research from the University of Sao Paulo, "Next, it draws on 30 official statements published by journalists and their tech partners, and seven semi-structured interviews with representatives from five websites. This article shows an emerging automation landscape in the Brazilian fact-checking venture supported by the tech industry." According to the news reporters, the research concluded: "Nonetheless, AI has challenged fact-checkers' authority and increased the technologists' influence over journalism." This research has been peer-reviewed.
      原文链接:
    • NETL
    • NSTL
    • Sage

    Researchers at Shahid Bahonar University of Kerman Release New Data on Algorithms (A New Hybrid Filter-Wrapper Feature Selection using Equilibrium Optimizer and Simulated Annealing)

    94-94页
    查看更多>>摘要：Investigators discuss new findings in algorithms. According to news reporting from Kerman, Iran, by NewsRx journalists, research stated, "Data dimensions and networks have grown exponentially with the Internet and communications." The news reporters obtained a quote from the research from Shahid Bahonar University of Kerman: "The challenge of high-dimensional data is increasing for machine learning and data science. This paper presents a hybrid filter-wrapper feature selection method based on Equilibrium Optimization (EO) and Simulated Annealing (SA). The proposed algorithm is named Filter-Wrapper Binary Equilibrium Optimizer Simulated Annealing (FWBEOSA). We used SA to solve the local optimal problem so that EO could be more accurate and better able to select the best subset of features. FWBEOSA utilizes a filtering phase that increases accuracy as well as reduces the number of selected features. The proposed method is evaluated on 17 standard UCI datasets using Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) classifiers and compared with ten state-of-the-art algorithms (i.e., Binary Equilibrium Optimizer (BEO), Binary Gray Wolf Optimization (BGWO), Binary Swarm Slap Algorithm (BSSA), Binary Genetic Algorithm (BGA), Binary Particle Swarm Optimization (BPSO), Binary Social Mimic Optimization (BSMO), Binary Atom Search Optimization (BASO), Modified Flower Pollination Algorithm (MFPA), Bar Bones Particle Swarm Optimization (BBPSO) and Two-phase Mutation Gray Wolf Optimization (TMGWO))."
      原文链接:
    • NETL
    • NSTL

    Data on Machine Learning Discussed by Researchers at Guizhou Normal University (The Rational Co-doping Strategy of Transition Metal and Non-metal Atoms On G-cn for Highly Efficient Hydrogen Evolution By Dft and Machine Learning)

    95-95页
    查看更多>>摘要：Researchers detail new data in Machine Learning. According to news reporting originating from Guiyang, People's Republic of China, by NewsRx correspondents, research stated, "As a clean energy source, hydrogen has attracted high interest in developing efficient hydrogen evolution reaction (HER) catalysts due to its sustainable and renewable characteristics. In this work, we have systematically investigated the HER activity of the g-CN two-dimensional materials." Financial supporters for this research include National Natural Science Foundation of China (NSFC), Guizhou Provincial Basic Research Program (Natural Science), Top scientific and technological talents in Guizhou Province, Guizhou Normal University Academic New Talent Fund, Guizhou Normal New Talent, Functional Materials and Devices Technology Innovation Team of Guizhou Province University. Our news editors obtained a quote from the research from Guizhou Normal University, "The catalytic activity in HER is enhanced by doping non-metallic atoms (C, N, B, Si) and transition metal atoms (Sc, Ti, V, Cr, Mn, Fe, Co, Ni, Cu, Zn) in the vacancies of g-CN. Based on the first principle calculation, we screened 40 structures and found that the Delta G(H*) of Sc@C-3-CN, V@C-3-CN, Mn@C-3-CN, Sc@N-3- CN, and Ti@Si-3-CN was close to zero. Among them, Ti@Si-3-CN has the lowest Gibbs free energy change (-0.01 eV) and has excellent HER performance. In addition, we explored HER activity's origin by using machine learning (ML) algorithms."
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    New Robotics Study Findings Have Been Reported from Chengdu University of Technology (Research On Design and Trajectory Tracking Control of a Variable Size Lower Limb Exoskeleton Rehabilitation Robot)

    96-96页
    查看更多>>摘要：Current study results on Robotics have been published. According to news reporting from Leshan, People's Republic of China, by NewsRx journalists, research stated, "Aiming at the problems of poor size adjustability and low joint tracking accuracy of lower limb exoskeleton rehabilitation robot (LLERR), a variable size lower limb exoskeleton rehabilitation robot (VSLLERR) was designed by UG NX software based on human body size data. Then, the kinematics model of VSLLERR was established by DH method, and the motion space of VSLLERR was analyzed." Financial support for this research came from Science And Technology Bureau Of Leshan Town, China. The news correspondents obtained a quote from the research from the Chengdu University of Technology, "In addition, the dynamics model of VSLLERR was established by Lagrangian energy method, and the general nonlinear friction model was designed to modify and improve the accuracy of dynamics model. Then, the PID and reaching law (RL) controllers of VSLLERR were designed by SIMULINK. Furthermore, the joint tracking accuracy of the two controllers and the influence of RL controller parameters on tracking accuracy were studied by simulation experiment. The results indicate that the joint angle and joint angular velocity tracking accuracy of RL controller are higher than that of PID controller."
      原文链接:
    • NETL
    • NSTL
    • Korean Soc Mechanical Engineers