查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ma chine Learning - Support Vector Machines.According to news reporting originatin g from Shenzhen, People’s Republic of China, by NewsRx correspondents,research stated, “Support vector machine (SVM), as a supervised learning method, has different kinds of varieties with significant performance. In recent years, more res earch focused on nonparallelSVM, where twin SVM (TWSVM) is the typical one.” Funders for this research include National Natural Science Foundation of China ( NSFC), ShenzhenMunicipal Science and Technology Innovation Council.Our news editors obtained a quote from the research from Shenzhen University, “I n order to reducethe influence of outliers, more robust distance measurements a re considered in these methods, but thediscriminability of the models is neglec ted. In this article, we propose robust manifold twin bounded SVM(RMTBSVM), whi ch considers both robustness and discriminability. Specifically, a novel norm, t hat is,capped L-1-norm, is used as the distance metric for robustness, and a ro bust manifold regularization isadded to further improve the robustness and clas sification performance. In addition, we also use the kernelmethod to extend the proposed RMTBSVM for nonlinear classification. We introduce the optimization problems of the proposed model. Subsequently, effective algorithms for both linear and nonlinear cases areproposed and proved to be convergent. Moreover, the exp eriments are conducted to verify the effectivenessof our model.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Current study results on Robotics have been published. According to news reportingoriginating from Edinburg, Texas, b y NewsRx correspondents, research stated, “As service robots becomeincreasingly common in the marketplace, more research is necessary to better understand cust omer perceptionsof and responses to those robots, especially in the context of service failures. This paper investigatesservice robots from the perspective of a customer as a third-party observer, specifically examining the effectof the customer’s empathy toward the robot on downstream customer responses and the mod erating roleof robot eeriness on that effect.”Our news editors obtained a quote from the research from the University of Texas Rio Grande Valley,“Namely, we find that for a low eeriness robot (e.g., a robo tic ‘arm’), customer responses generally become more desirable as empathy increa ses (i.e., complaint intentions and dissatisfaction are lower, andsatisfaction is higher). Meanwhile, for a high eeriness robot (e.g., a humanoid robot), those same customerresponses generally become less desirable as empathy increases.”According to the news editors, the research concluded: “The findings have implic ations for scholarshipon robotic automation in services marketing and for marke ters seeking to implement service robots incustomer-facing contexts.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on ar tificial intelligence. According to news reportingout of Jinan, People’s Republ ic of China, by NewsRx editors, research stated, “The world is being reshapedun der global economic development driven by new advances in information technology .”Financial supporters for this research include Shandong Provincial Social Scienc e Planning ResearchProject; National Natural Science Foundation of China.Our news editors obtained a quote from the research from Shandong University: “A rtificial intelligence,an essential potential technology, will play a vital rol e in technological change and industrial upgrades.Exploring the relationship be tween government subsidies, green innovation, and total factor productivitywill help us analyze government decisions’ effects and better promote artificial int elligence’s technologicalinnovation process. Based on data from China’s listed artificial intelligence companies from 2011 to2020, this study uses the Levinso hn-Petrin method to measure the total factor productivity of companiesand analy zes the impact of government subsidies on the total factor productivity of AI co mpanies, themediating effect of green innovation, and the moderating effect of intellectual property protection intensity.The research results show that (1) g overnment subsidies can promote the total factor productivity of AIenterprises; (2) green innovation capabilities play a mediating role between government subs idies and enterprise total factor productivity, and government subsidies can ind irectly promote green innovation topromote the improvement of total factor prod uctivity effectively; (3) in the AI industry, the promotion effectof government subsidies on total factor productivity is more significant among state-owned en terprises,while the impact mechanism of government subsidies on private enterpr ises is not significant; and (4)the intensity of intellectual property protecti on has played a positive moderating role in the impact ofgovernment subsidies f or artificial intelligence enterprises on total factor productivity.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Artificial Intelligenc e is the subject of a report. According to newsreporting out of Sydney, Austral ia, by NewsRx editors, research stated, “Can artificial intelligence (AI)improv e the efficiency and efficacy of sperm searches in azoospermic samples? This two -phase proofof-concept study began with a training phase using eight azoospermi c patients (>10,000 sperm images)to provide a variety o f surgically collected samples for sperm morphology and debris variation to trai na convolutional neural network to identify spermatozoa. Second, side-by-side t esting was undertaken ontwo cohorts of non-obstructive azoospermia patient samp les: an embryologist versus the AI identifyingall the spermatozoa in the still images (cohort 1, n = 4), and a side-by-side test with a simulated clinicaldepl oyment of the AI model with an intracytoplasmic sperm injection microscope and t he embryologistperforming a search with and without the aid of the AI (cohort 2 , n = 4).”Our news journalists obtained a quote from the research from the University of T echnology Sydney,“In cohort 1, the AI model showed an improvement in the time t aken to identify all the spermatozoa perfield of view (0.02 ± 0.30 x 10s versus 36.10 ± 1.18s, P<0.0001) and improved recall (91.95 ± 0.8 1%versus 86.52 ± 1.34%, P<0.00 1) compared with an embryologist. From a total of 2660 spermatozoa tofind in al l the samples combined, 1937 were found by an embryologist and 1997 were found b y the AI inless than 1000th of the time. In cohort 2, the AI-aided embryologist took significantly less time per droplet(98.90 ± 3.19 s versus 168.7 ± 7.84 s, P<0.0001) and found 1396 spermatozoa, while 1274 were fou ndwithout AI, although no significant difference was observed.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ro botics. According to news reporting out ofXi’an, People’s Republic of China, by NewsRx editors, research stated, “Monocular depth inference is afundamental pr oblem for scene perception of robots.”Financial support for this research came from National Natural Science Foundatio n of China (NSFC).Our news journalists obtained a quote from the research from Xi’an Jiaotong Univ ersity, “Specificrobots may be equipped with a camera plus an optional depth se nsor of any type and located in variousscenes of different scales, whereas rece nt advances derived multiple individual sub-tasks. It leads toadditional burden s to fine-tune models for specific robots and thereby high-cost customization in largescaleindustrialization.”According to the news editors, the research concluded: “This article investigate s a unified task ofmonocular depth inference, which infers high-quality depth m aps from all kinds of input raw data fromvarious robots in unseen scenes.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Robotics is the subjec t of a report. According to news reportingout of Tianjin, People’s Republic of China, by NewsRx editors, research stated, “Service robot technologyis increasi ngly gaining prominence in the field of artificial intelligence. However, persis tent limitationscontinue to impede its widespread implementation.”Our news journalists obtained a quote from the research from the Hebei Universit y of Technology,“In this regard, human motion pose estimation emerges as a cruc ial challenge necessary for enhancingthe perceptual and decision-making capacit ies of service robots. This paper introduces a groundbreakingmodel, YOLOv8-Apex Net, which integrates advanced technologies, including Bidirectional Routing Attention (BRA) and Generalized Feature Pyramid Network (GFPN). BRA facilitates the capture of interkeypointcorrelations within dynamic environments by introduci ng a bidirectional information propagationmechanism. Furthermore, GFPN adeptly extracts and integrates feature information across different scales,enabling th e model to make more precise predictions for targets of various sizes and shapes . Empiricalresearch findings reveal significant performance enhancements of the YOLOv8-ApexNet model across theCOCO and MPII datasets. Compared to existing me thodologies, the model demonstrates pronouncedadvantages in keypoint localizati on accuracy and robustness. The significance of this research lies inproviding an efficient and accurate solution tailored for the realm of service robotics, e ffectively mitigatingthe deficiencies inherent in current approaches.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - A new study on Robotics is now availab le. According to news reporting out ofWuhan, People’s Republic of China, by New sRx editors, research stated, “Understanding whether andhow encountering servic e robots influences hospitality consumption emotions helps identify the psychological effects and appropriate scenarios of robotic adoption. Anthropomorphic and humanlike features arewidely applied to strengthen the social impact of robots , but they are still considered non-human socialagents.”Financial support for this research came from National Social Science Founda- ti on, PRC.Our news journalists obtained a quote from the research from the Zhongnan Univer sity of Economics& Law, “We argue that customers have dehumanized cognition of service robots, which induces fewersocial constraints and greater perceived autonomy in hospitality service encounters. Five experimentalstudies were adopted to test the underlying mechanism through which service robots infl uence customers’consumption emotions by increasing their perceived autonomy und er various boundary conditions. Ourresults illustrate that, compared with human servants, customers experienced more positive consumptionemotions with service robots. This effect is eliminated when interpersonal pressure from peer customersis perceived.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ro botics. According to news reporting originatingfrom Xi’an, People’s Republic of China, by NewsRx correspondents, research stated, “Robotic machiningsystems ha ve been widely implemented in the assembly sites of large components of aircraft , such aswings, aircraft engine rooms, and wing boxes. Milling is the first ste p in aircraft assembly.”Financial supporters for this research include Key Research and Development Prog ram of ShaanxiProvince, China Postdoctoral Science Foundation.Our news editors obtained a quote from the research from Northwestern Polytechni c University, “It isconsidered one of the most significant processes because th e quality of the subsequent drilling, broaching,and riveting steps depend stron gly on the milling accuracy. However, the chatter phenomenon mayoccur during th e milling process because of the low rigidity of the components of the robotic m illingsystem (i.e., robots, shape-preserving holders, and rod parts). This may result in milling failure or evenfracture of the robotic milling system. This p aper presents a feasible spindle speed interval identificationmethod for large aeronautical component milling systems to eliminate the chatter phenomenon. It i sbased on the chatter stability model and the analysis results of natural frequ ency and harmonic response.Firstly, the natural frequencies and harmonics of th e main components of the robot milling system areanalyzed, and the spindle spee d that the milling system needs to avoid is obtained. Then, a flutter stabilitymodel considering the instantaneous cutting thickness is established, from which the critical cutting depthcorresponding to the spindle speed can be obtained. Finally, the spindle speed interval of the robotic millingsystem could be optim ized based on the results obtained from the chatter stability model and the analysis result of the natural frequency and harmonic response of the milling system.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Data detailed on Machine Learning have been presented. According to news reportingfrom Los Alamos, New Mexico, by New sRx journalists, research stated, “Underground hydrogen (H2)storage (UHS) has e merged as a promising technology to facilitate the widespread adoption of fluctu atingrenewable energy sources. However, the current UHS experience primarily fo cuses on salt caverns, withno working examples of storing pure H2 in porous res ervoirs.”Funders for this research include Los Alamos National Laboratory, Laboratory Dir ected Research andDevelopment (LDRD) program.The news correspondents obtained a quote from the research from Earth and Enviro nmental SciencesDivision, “A key challenge in UHS within porous rocks is the un certainty in evaluating storage performancedue to complicated geological and op erational conditions. While physics -based reservoir simulationsare commonly us ed to quantify H2 injection and withdrawal processes during storage cycles, they arecomputationally demanding and unsuitable for providing rapid support to UHS operations. In this study,we develop efficient reduced -order models (ROMs) fo r UHS in depleted natural gas reservoirs using deepneural networks (DNNs) based on comprehensive reservoir simulation data sets. The ROMs can accuratelyforeca st UHS performance metrics (H2 withdrawal efficiency, produced H2 purity, produc ed gas -waterratio) across various geological and operational conditions and ar e over 22000 times faster than physics-based simulations. Then, we employ the R OMs for sensitivity analysis to assess the impact of geologicaland operational parameters on UHS performance and conduct uncertainty quantification to characte rizepotential performance and associated probabilities. Lastly, we present a fi eld case study from the Dakotaformation of the Basin field in the Intermountain -West (I -WEST) region, USA. Based on the ROMs’predictions, Dakota formation i s favorable for UHS due to its high H2 withdrawal efficiency and purity,and low water production risk. By optimizing operational parameters, we can further imp rove the storageperformance in Dakota formation and reduce the uncertainty in U HS performance prediction.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - A new study on Robotics is now availab le. According to news reporting out of Beijing,People’s Republic of China, by N ewsRx editors, research stated, “It is important to obtain real-timeleaf densit y of fruit-tree canopies for the precision spray control of plant-protection rob ots. However,conventional detection techniques for the characteristics of fruit -tree canopies cannot acquire the canopyinternal information, which may provide an unsatisfactory accuracy of detection of leaf densities.”Funders for this research include National Natural Science Foundation of China ( NSFC), Yantai Localityand University Cooperation Development Project.Our news journalists obtained a quote from the research from China Agricultural University, “Thispaper proposes a method for estimating canopy leaf density of fruit trees based on wind-excited audio. Awind-exciting implement was used to f orce fruit-tree canopy leaves vibrating to produce audio. Then, somecorrelation analysis methods were used to extract key characteristic parameters of wind-exc ited audio thatwere significantly correlated with leaf density. Finally, based on the data set of wind-excited audio, a fewmachine-learning methods were used to develop leaf-density estimation models. Test results showed that:(1) there w ere five key feature parameters of wind-excited audio that were significantly co rrelated withleaf density: the short-time energy, spectral centroid, the freque ncy average energy, the peak frequency,and the standard deviation of frequency. (2) the estimation model of leaf density developed based onbackpropagation neu ral network for fruit-tree canopy showed the optimal estimation results, which c anachieve the estimation of leaf density of fruit-tree canopies accurately. The overall correlation coefficient® of the estimation model was more than 0.84, t he root-mean-square error was less than 0.73 m2 m-3,and the mean absolute error was less than 0.53 m2 m-3.”
NETL
NSTL