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

    Findings on Androids Discussed by Investigators at Shenzhen University (Soft Bio inspired Pneumatic Actuator for Adaptive Grasping Based On Direct Ink Writing Me thod)

    51-52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 Robotic s - Androids. According to news reporting from Guangdong, People's Republic of C hina, by NewsRx journalists, research stated, "Soft robots have attractive advan tages of being highly flexible and adaptive to complex environment. The increasi ng demand for grasping diverse objects in unstructured human-machine and environ ment-machine interactions has attracted enormous attentions." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), National Natural Science Foundation of Guangdong Province, S henzhen Science and Technology Program.
      原文链接:
    • NETL
    • NSTL

    Researchers from Federal University of Rio de Janeiro (UFRJ) Describe Research i n Artificial Intelligence (Regulating Artificial Intelligence in Brazil)

    51-51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 artificial intell igence are discussed in a new report. According to news originating from Federal University of Rio de Janeiro (UFRJ) by NewsRx editors, the research stated, "Th is essay discusses how critical social theory in Brazil can contribute to a revi sion of dominant approaches to AI regulation and a regulatory strategy focused o n innovation, legal certainty, and economic development in Brazil." The news reporters obtained a quote from the research from Federal University of Rio de Janeiro (UFRJ): "We explain the origins of the Brazilian Draft Bill on A rtificial Intelligence Regulation and the main critiques during the discussions at the legislative houses in 2022. We argue that critical social theory can enla rge the discussion about which should be the regulatory goals of such legislatio n. Critical theory helps envision new principles that are connected to the struc tural problems of post-colonial societies." According to the news editors, the research concluded: "We intend to advance the project of enlarging the epistemologies of the South and expanding the view of Global Data Justice that relates to the social theory developed in the South."
      原文链接:
    • NETL
    • NSTL

    Studies from Sidi Mohamed Ben Abdellah University Further Understanding of Machi ne Learning (Modelling Stock Prices of Energy Sector using Supervised Machine Le arning Techniques)

    52-53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 originating from Fes, Morocco, by NewsRx editors, the research stated, "This paper aims at comparing the performance of the differ ent state-of-the-art machine learning techniques in anticipating the performance of stock prices of the energy sector." The news editors obtained a quote from the research from Sidi Mohamed Ben Abdell ah University: "The data collected cover the period from January 2020 to Februar y 2023 with a daily frequency for the three most imported refined petroleum prod ucts in Morocco and trained four regression machines learning (linear regression , lasso regression, ridge regression, and SVR) and four classifiers machine lear ning (logistic regression, decision tree, extra tree and Random Forest) so that anticipating one day ahead prices direction can take place no matter whether the y are negative or positive prices. The performance of regression algorithm is th en evaluated using different evaluation metrics, especially MSE, RMSE, MAE, MAPE and R2 to evaluate the performance of regression algorithm while precision, rec all and F1 scores are used to evaluate the performance of classifiers algorithm. The outcomes propose that the performance of linear regression and ridge regres sion takes place equally and outperform other single regression that is lasso re gression and SVR for-one-day predictions as a whole. In addition to that, we hav e come to find that in the classifiers, algorithms group all machine learning di splay similar predictive accuracy, this is on one hand. On the other hand, the b est of them is the logistic regression. In brief, this study suggests that all p erformance metrics are significantly improved by ensemble learning."
      原文链接:
    • NETL
    • NSTL

    New Robotics Study Results from Harbin Institute of Technology Described (Step D isplacement Improving Method of Inertial Actuated Piezoelectric Robot Based On D iagonal Deformation Trajectory)

    53-54页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Robotics. According to news reporting out of Harbin, People's Republic of China, by NewsRx editors, research stated, "For the miniature piezoelectric robots ope rated by inertial driving method, the step displacements were limited by the def ormations of the inertial units. Thus, a diagonal inertial driving method (DIDM) was proposed in this work to increase the step displacement." Funders for this research include National Natural Science Foundation of China ( NSFC), China Postdoctoral Science Foundation, China Postdoctoral Science Foundat ion. Our news journalists obtained a quote from the research from the Harbin Institut e of Technology, "The prominent feature of DIDM was that the inertial force was in diagonal direction by using the designed piezoleg with square cross section. The vertical component of the inertial force reduced the friction force and even made the robot jump to achieve a larger step displacement. The experimental res ults indicated that the proposed DIDM increased the step displacement successful ly. The increase effect was optimal when the vertical component of the inertial force was equal to the horizontal one, and the realized step displacement was as high as 156% to the deformation of the inertial unit in motion di rection. Moreover, the force and displacement responses of the driving foot in v ertical direction were measured, which indicated that the robot realized jumping action to increase the step displacement under DIDM, and the maximum speed real ized by DIDM was 2.3 times of that achieved by the traditional inertial driving method."
      原文链接:
    • NETL
    • NSTL

    Findings on Artificial Intelligence Discussed by Investigators at Henan Universi ty (Research On Brain and Mind Inspired Intelligence)

    54-55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 Machine Learning - Ar tificial Intelligence have been presented. According to news reporting from Kaif eng, People's Republic of China, by NewsRx journalists, research stated, "To add ress the problems of scientific theory, common technology and engineering applic ation of multimedia and multimodal information computing, this paper is focused on the theoretical model, algorithm framework, and system architecture of brain and mind inspired intelligence (BMI) based on the structure mechanism simulation of the nervous system, the function architecture emulation of the cognitive sys tem and the complex behavior imitation of the natural system. Based on informati on theory, system theory, cybernetics and bionics, we define related concept and hypothesis of brain and mind inspired computing (BMC) and design a model and fr amework for frontier BMI theory." The news correspondents obtained a quote from the research from Henan University , "Research shows that BMC can effectively improve the performance of semantic p rocessing of multimedia and cross-modal information, such as target detection, c lassification and recognition. Based on the brain mechanism and mind architectur e, a semantic-oriented multimedia neural, cognitive computing model is designed for multimedia semantic computing. Then a hierarchical cross-modal cognitive neu ral computing framework is proposed for cross-modal information processing."
      原文链接:
    • NETL
    • NSTL

    Studies from University of Nottingham Have Provided New Data on Robotics (Modell ing of Modular Soft Robots: From a Single To Multiple Building Blocks)

    55-56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 out of Nottingham, United Kingdom, by NewsRx editors, research stated, "Despite the advances in soft robots, their modelling is still one of the research challenges due to the complexity and non-linearity of their soft nature. A novel design of reconfigurable soft robots was recently introduced to bring more maturity to the field of soft robots." Financial support for this research came from Rolls-Royce Holding Group. Our news journalists obtained a quote from the research from the University of N ottingham, "Here, a modelling study of the building blocks and the assembled sof t robot is developed for a deeper understanding of the system and for predicting their behaviours. The model is validated using several sets of individual and m ultiple building blocks and the results show good tracking between the model and the experiments with reasonable errors. Towards adopting the model in robotic a pplications, a grasping setup of 2 assembled soft fingers is demonstrated where the model is used to predict the grasping force and compared to feedback sensing ."
      原文链接:
    • NETL
    • NSTL

    Shandong University Reports Findings in Brain Abscess (Diffusionweighted imagin g-based radiomics model using automatic machine learning to differentiate cerebr al cystic metastases from brain abscesses)

    56-57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 Central Nervous System Diseases and Conditions - Brain Abscess is the subject of a report. According t o news reporting originating in Shandong, People's Republic of China, by NewsRx journalists, research stated, "To develop a radiomics model based on diffusion-w eighted imaging (DWI) utilizing automated machine learning method to differentia te cerebral cystic metastases from brain abscesses. A total of 186 patients with cerebral cystic metastases (n = 98) and brain abscesses (n = 88) from two clini cal institutions were retrospectively included." The news reporters obtained a quote from the research from Shandong University, "The datasets (129 from institution A) were randomly portioned into separate 75% training and 25% internal testing sets. Radiomics features were ex tracted from DWI images using two subregions of the lesion (cystic core and soli d wall). A thorough image preprocessing method was applied to DWI images to ensu re the robustness of radiomics features before feature extraction. Then the Tree -based Pipeline Optimization Tool (TPOT) was utilized to search for the best opt imized machine learning pipeline, using a fivefold cross-validation in the train ing set. The external test set (57 from institution B) was used to evaluate the model's performance. Seven distinct TPOT models were optimized to distinguish be tween cerebral cystic metastases and abscesses either based on different feature s combination or using wavelet transform. The optimal model demonstrated an AUC of 1.00, an accuracy of 0.97, sensitivity of 1.00, and specificity of 0.93 in th e internal test set, based on the combination of cystic core and solid wall radi omics signature using wavelet transform. In the external test set, this model re ached 1.00 AUC, 0.96 accuracy, 1.00 sensitivity, and 0.93 specificity."
      原文链接:
    • NETL
    • NSTL

    Studies from University of Salamanca Reveal New Findings on Artificial Intellige nce (A Platform for Swimming Pool Detection and Legal Verification Using a Multi -agent System and Remote Image Sensing)

    57-58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 Machine Learning - Artificial Intelligence are discussed in a new report. According to news repor ting out of Salamanca, Spain, by NewsRx editors, research stated, "Spain is the second country in Europe with the most swimming pools. However, the legal litera ture estimates that 20% of swimming pools are not declared or irre gularThe administration has a corps of people who manually analyze satellite or drone images to detect illegal or irregular structures." Funders for this research include Ministry of Science and Innovation through the AvisSA project, National Natural Science Foundation of China (NSFC), Shenzhen S pecial Foundation of Central Government to Guide Local Science & T echnology Development, Postgraduate Education Reform and Quality Province Improv ement Project of Henan Province, Intelligent Systems for Industrial Systems rese arch group of Mondragon Unibertsitatea - department of Education, Universities a nd Research of the Basque Country, Semantic Knowledge Integration for Content-Ba sed Spam Filtering from SMEIC, Sugar Research Australia, European Union (EU), Fu ndacao para a Ciencia e a Tecnologia (FCT), MSIT (Ministry of Science and ICT), Korea, under the Innovative Human Resource Development for Local Intellectualiza tion support program, National Natural Science Foundation of China (NSFC), Europ ean Union (EU), Spanish Ministry of Economy and Competitiveness (MINECO) under A EI Project, Grant Agency of Excellence, University of Hradec Kralove, Faculty of Informatics and Management, Czech Republic, Spanish Ministry of Universities (F PU Fellowship, USAL, Banco Santander, Spanish Government, University of Vigo, Sp anish Government, European Social Fund - COBRA project - Spanish Ministry of Def ence, SCORPION project - Seneca Foundation of the Region of Murcia, Spain.
      原文链接:
    • NETL
    • NSTL

    Findings on Machine Learning Detailed by Investigators at University of Technolo gy Sydney (On Taking Advantage of Opportunistic Meta-knowledge To Reduce Configu ration Spaces for Automated Machine Learning)

    58-59页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Machine Learning. According to news reporting originating from Ultimo, Australia , by NewsRx correspondents, research stated, "The optimisation of a machine lear ning (ML) solution is a core research problem in the field of automated machine learning (AutoML). This process can require searching through complex configurat ion spaces of not only ML components and their hyperparameters but also ways of composing them together, i.e. forming ML pipelines." Financial support for this research came from CASLab, University of Technology S ydney (UTS). Our news editors obtained a quote from the research from the University of Techn ology Sydney, "Optimisation efficiency and the model accuracy attainable for a f ixed time budget suffer if this pipeline configuration space is excessively larg e. A key research question is whether it is both possible and practical to preem ptively avoid costly evaluations of poorly performing ML pipelines by leveraging their historical performance for various ML tasks, i.e. meta-knowledge. This pa per approaches the research question by first formulating the problem of configu ration space reduction in the context of AutoML. Given a pool of available ML co mponents, it then investigates whether previous experience can recommend the mos t promising subset to use as a configuration space when initiating a pipeline co mposition/optimisation process for a new ML problem, i.e. running AutoML on a ne w dataset. Specifically, we conduct experiments to explore (1) what size the red uced search space should be and (2) which strategy to use when recommending the most promising subset. The previous experience comes in the form of classifier/r egressor accuracy rankings derived from either (1) a substantial but non-exhaust ive number of pipeline evaluations made during historical AutoML runs, i.e. ‘opp ortunistic' meta-knowledge, or (2) comprehensive crossvalidated evaluations of classifiers/regressors with default hyperparameters, i.e. ‘systematic' meta-know ledge. Overall, numerous experiments with the AutoWeka4MCPS package, including o nes leveraging similarities between datasets via the relative landmarking method , suggest that (1) opportunistic/systematic meta-knowledge can improve ML outcom es, typically in line with how relevant that meta-knowledge is, and (2) configur ation-space culling is optimal when it is neither too conservative nor too radic al. However, the utility and impact of meta-knowledge depend critically on numer ous facets of its generation and exploitation, warranting extensive analysis; th ese are often overlooked/underappreciated within AutoML and meta-learning litera ture. In particular, we observe strong sensitivity to the ‘challenge' of a datas et, i.e. whether specificity in choosing a predictor leads to significantly bett er performance."
      原文链接:
    • NETL
    • NSTL

    Studies from China Agricultural University Yield New Data on Robotics (Detection Method for the Cucumber Robotic Grasping Pose In Clutter Scenarios Via Instance Segmentation)

    59-60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 Beijing, People's Republic of China, by NewsRx correspondents, research stated, "The application of robotic gr asping for agricultural products pushes automation in agriculture-related indust ries. Cucumber, a common vegetable in greenhouses and supermarkets, often needs to be grasped from a cluttered scene." Financial support for this research came from Beijing Innovation Consortium of A griculture Research System. Our news journalists obtained a quote from the research from China Agricultural University, "In order to realize efficient grasping in cluttered scenes, a fully automatic cucumber recognition, grasping, and palletizing robot system was cons tructed in this paper. The system adopted Yolact++ deep learning network to segm ent cucumber instances. An early fusion method of F-RGBD was proposed, which inc reases the algorithm's discriminative ability for these appearance-similar cucum bers at different depths, and at different occlusion degrees. The results of the comparative experiment of the F-RGBD dataset and the common RGB dataset on Yola ct++ prove the positive effect of the F-RGBD fusion method. Its segmentation mas ks have higher quality, are more continuous, and are less false positive for pri oritizinggrasping prediction. Based on the segmentation result, a 4D grab line prediction method was proposed for cucumber grasping. And the cucumber detection experiment in cluttered scenarios is carried out in the real world."
      原文链接:
    • NETL
    • NSTL