查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Whether it's a powered prosthesis to a ssist a person who has lost a limb or an independent robot navigating the outsid e world, we are asking machines to perform increasingly complex, dynamic tasks. But the standard electric motor was designed for steady, ongoing activities like running a compressor or spinning a conveyor belt - even updated designs waste a lot of energy when making more complicated movements. Researchers at Stanford University have invented a way to augment electric motor s to make them much more efficient at performing dynamic movements through a new type of actuator, a device that uses energy to make things move. Their actuator , published March 20 in Science Robotics, uses springs and clutches to accomplis h a variety of tasks with a fraction of the energy usage of a typical electric m otor. "Rather than wasting lots of electricity to just sit there humming away and gene rating heat, our actuator uses these clutches to achieve the very high levels of efficiency that we see from electric motors in continuous processes, without gi ving up on controllability and other features that make electric motors attracti ve," said Steve Collins, associate professor of mechanical engineering and senio r author of the paper.
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Data detailed on artificial intelligen ce have been presented. According to news reporting out of Liberec, Czech Republ ic, by NewsRx editors, research stated, "This article looks at how artificial in telligence affects the teaching of accounting in secondary schools." Our news journalists obtained a quote from the research from Technical Universit y of Liberec: "The article is divided into three parts. The first part of the ar ticle is devoted to literature research on the topic of the implementation of ar tificial intelligence in the curriculum within the subject of accounting. In the second part of the article, the methodology for the implementation of the autho r's own research is described. The third part of this article deals with the res earch itself, whether artificial intelligence is implemented in the curriculum o f secondary schools, within the subject of accounting." According to the news reporters, the research concluded: "The pupils are already preparing for their future profession in schools, which has already moved forwa rd thanks to the implementation of artificial intelligence. 43 respondents parti cipated in the research that was conducted in two secondary schools where the su bject of Accounting is taught."
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 reporting out of Shenzhen, People's Republic of China, by NewsRx editors, research stated, "The complexity and diversity of scenarios, alo ng with the presence of environmental noise in factory settings, pose significan t challenges to the implementation of deep learning-based vision-guided robots f or smart manufacturing. In response to these challenges, we introduce a novel Se mi-Supervised Knowledge Distillation (SSKD) framework that has been extensively validated and deployed across numerous real-world production lines." Funders for this research include City University of Hong Kong, Shenzhen Science and Technology Program, PR China.
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 Machine Learning is now available. According to news reporting out of Brussels, Belgium, by NewsRx edit ors, research stated, "Dynamic Thermal Rating (DTR) enhances grid flexibility by adapting line capabilities to weather conditions. For this purpose, DTR-based t echnologies require reliable and continuous measurement of the conductor tempera ture along the line route, which could hinder their wide -scale deployment due t o the prohibitively high number of required sensors." Financial supporters for this research include National Science Foundation, Neth erlands, Service Public de Wallonie, Belgium Recherche, Fonds de la Recherche Sc ientifique - FNRS, Walloon Region, Belgium. Our news journalists obtained a quote from the research from the University libr e of Bruxelles, "Existing machine learning -based DTR methods infer conductor te mperature from weather variables avoiding using complex and expensive measuremen t techniques, but their estimation accuracy greatly relies on the availability o f a comprehensive set of measured data. To face these issues, this paper propose s the usage of transfer learning, a data -driven technique allowing the reductio n of the number of sensors by transferring knowledge from a single calibrated so urce sensor to many target sensors. To the best of the author's knowledge, at th e time of writing, the proposed approach is the first application of Transfer Le arning in the domain of DTR which is validated on real transmission lines data."
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 Vancouver, Canada , by NewsRx journalists, research stated, "The purpose of this study is to inves tigate the variance of women authors, specifically first and senior authorship a mong peer-reviewed artificial intelligence-related articles with a specific focu s in breast imaging. A strategic search was conducted in July 2022 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines to capture all existing and publicly available peer-reviewed articles intersecting AI and breast imaging." The news correspondents obtained a quote from the research from the University o f British Columbia, "Primary outcomes were first and senior authors' gender, whi ch were assigned with the aid of an emailed self-declaration survey. Secondary o utcomes included country of article, journal impact factor, and year of publicat ion. Comparisons were made using logistic regression models and analysis of vari ances. 115 studies were included in the analysis. Women authors represented 35.7 % (41/115) and 37.4% (43/115) of first and senior au thors, respectively. Logistic regression modelling showed a significant increase in women senior authors over time but no changes in women first authors. Impact factor was not associated with female authorship and certain countries had wome n authorship reach over 50%. This study demonstrates that there is a significant authorship gender gap in artificial intelligence breast imaging re search. An increasing temporal trend of senior authors in breast imaging AI-rela ted research is a promising prognosis for more women voices in this field."
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 originating in Shanghai, Pe ople's Republic of China, by NewsRx journalists, research stated, "Quantitative structure-activity relationship (QSAR) analysis, an in silico methodology, offer s enhanced efficiency and cost effectiveness in investigating anti-inflammatory activity. In this study, a comprehensive comparative analysis employing four mac hine learning algorithms (random forest (RF), gradient boosting regression (GBR) , support vector regression (SVR), and artificial neural networks (ANNs)) was co nducted to elucidate the activities of naturally derived compounds from durian e xtraction." Funders for this research include Chulalongkorn University, Thailand Science Res earch and Innovation, Shanghai Municipal Science and Technology Commission of th e Professional and Technical Service Platform for the Designing and Manufacturin g of Advanced Composite Materials, Emerging Industries Research Institute, Shang hai University (Jiaxing, Zhejiang), Thailand Research Fund (TRF), Chulalongkorn University.
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Researchers detail new data in Robotics. Accordin g to news reporting originating from Lincoln, United Kingdom, by NewsRx correspo ndents, research stated, "Accurate crop row detection is often challenged by the varying field conditions present in real-world arable fields. Traditional colou r based segmentation is unable to cater for all such variations." Our news editors obtained a quote from the research from the University of Linco ln, "The lack of comprehensive datasets in agricultural environments limits the researchers from developing robust segmentation models to detect crop rows. We p resent a dataset for crop row detection with 11 field variations from sugar beet and maize crops. We also present a novel crop row detection algorithm for visua l servoing in crop row fields. The proposed method uses deep learning based crop row skeleton segmentation method followed by a crop row scanning algorithm that identifies the central crop row which the robot then follows. The unique datase t we used with skeleton representations for crop row detection enables robust cr op row detection in challenging real world field conditions. Our algorithm can d etect crop rows against varying field conditions such as curved crop rows, weed presence, discontinuities, growth stages, tramlines, shadows and light levels. D ense weed presence within inter-row space and discontinuities in crop rows were the most challenging field conditions for our crop row detection algorithm." According to the news editors, the research concluded: "An End-of Row detector a lgorithm was developed to detect the end of the crop row and navigate the robot towards the headland area when it reaches the end of the crop row."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Surgery - Arthroplasty is the subject of a report. According to news reporting from Beijing, People's Republic of China, by NewsRx journalists, research stated, "There is an increasi ng number of different brands of robotic total knee arthroplasty (TKA) systems. Most robotic TKA systems share the same coronal alignment, while the definitions of sagittal alignment vary." The news correspondents obtained a quote from the research, "The purpose of this study was to investigate whether these discrepancies impact the sagittal alignm ent of the lower extremity. A total of seventy-two lower extremity computed tomo graphy (CT) scans were included in our study, and threedimensional models were obtained using software. A total of seven brands of robotic TKA systems were inc luded in the study. The lower extremity axes were defined based on the surgical guide for each implant. We also set the intramedullary axis as a reference to ev aluate the discrepancies in sagittal alignment of each brand of robotic system. On the femoral side, the axis definition was the same for all seven robotic TKA systems. The robotic TKA axes showed a 2.41° (1.58°, 3.38°) deviation from the i ntramedullary axis. On the tibial side, the seven robots had different axis defi nitions. The tibial mechanical axis of six of the TKA systems was more flexed th an that of the intramedullary axis, which means the posterior tibial slope was d ecreased while the tibial mechanical axis of the remaining system was more exten ded. The sagittal alignment of the lower extremity for seven different brands of robotic TKA systems differed from each other and all deviated from the intramed ullary axis."
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 da ta intelligence. According to news reporting out of Palermo, Italy, by NewsRx ed itors, research stated, "ABSTRACT: Image segmentation is a crucial step in vario us image analysis pipelines and constitutes one of the cutting-edge areas of dig ital pathology." Our news reporters obtained a quote from the research from University of Palermo : "The advent of quantitative analysis has enabled the evaluation of millions of individual cells in tissues, allowing for the combined assessment of morphologi cal features, biomarker expression, and spatial context. The recorded cells can be described as a point pattern process. However, the classical statistical appr oaches to point pattern processes prove unreliable in this context due to the pr esence of multiple irregularly-shaped interstitial cell-devoid spaces in the dom ain, which correspond to anatomical features (e.g. vessels, lipid vacuoles, glan dular lumina) or tissue artefacts (e.g. tissue fractures), and whose coordinates are unknown. These interstitial spaces impede the accurate calculation of the d omain area, resulting in biased clustering measurements. Moreover, the mistaken inclusion of empty regions of the domain can directly impact the results of hypo thesis testing. The literature currently lacks any introduced bias correction me thod to address interstitial cell-devoid spaces."
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 Kaohsiung City, Ta iwan, by NewsRx correspondents, research stated, "There is a lack of research th at proposes a complete and interoperable robotics experimental design method to improve students' learning outcomes. Therefore, this study proposes a student-or iented method based on the plan-do-check-act (PDCA) concept to design robotics e xperiments." Funders for this research include National Science And Technology Council (Nstc) of The Republic of China. The news correspondents obtained a quote from the research from National Sun Yat -Sen University: "The proposed method is based on our teaching experience and mu ltiple practical experiences of allowing students to do hands-on experiments. It consists of eight steps, mainly including experimental goals, experimental acti vities, robot assembly, robot control, in-class evaluation criteria, and after-c lass report requirements. The after-class report requirements designed in the pr oposed method can help students improve their report-writing abilities. A wall-f ollowing robotics experiment designed using the PDCA method is proposed, and som e students' learning outcomes and after-class reports in this experiment are pre sented to illustrate the effectiveness of the proposed method. This experiment a lso helps students to understand the fundamental application of multi-sensor fus ion technology in designing an autonomous mobile robot. We can see that the prop osed reference examples allow students to quickly assemble twowheeled mobile ro bots with four different sensors and to design programs to control these assembl ed robots. In addition, the proposed in-class evaluation criteria stimulate stud ents' creativity in assembling different wall-following robots or designing diff erent programs to achieve this experiment. We present the learning outcomes of t hree stages of the wall-following robotics experiment."
NETL
NSTL