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 from University of Carlos III Madrid Provide New Insights into Support Vector Machines (Cost-sensitive Probabilistic Predictions for Support Vector Mac hines)

    60-61页
    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 Support Vector Machines is now available. According to news reporting from Madrid, Spain, by NewsRx jou rnalists, research stated, "Support vector machines (SVMs) are widely used and c onstitute one of the best examined and used machine learning models for two-clas s classification. Classification in SVM is based on a score procedure, yielding a deterministic classification rule, which can be transformed into a probabilist ic rule (as implemented in off -the-shelf SVM libraries), but is not probabilist ic in nature." Funders for this research include EC H2020 MSCA RISE NeEDS Project, Projects EC H2020 MSCA RISE NeEDS Project - MCIN/AEI, European Union "NextGenerationEU"/PRTR , Junta de Andalucia, Universidad de Cadiz, Spanish Government, EU ERD Funds.
      原文链接:
    • NETL
    • NSTL

    Researcher at Southern University of Science and Technology (SUSTech) Has Publis hed New Data on Robotics (Proprioceptive learning with soft polyhedral networks)

    61-62页
    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 originating from Guangdong, People's Republic of China, by NewsRx correspondents, research stated, "Proprioception is the "sixth sense" that detects limb postures with motor neurons." Funders for this research include National Natural Science Foundation of China; The Science, Technology, And Innovation Commission of Shenzhen Municipality; Gua ngdong Provincial Key Laboratory of Human-augmentation And Rehabilitation Roboti cs in Universities. The news journalists obtained a quote from the research from Southern University of Science and Technology (SUSTech): "It requires a natural integration between the musculoskeletal systems and sensory receptors, which is challenging among m odern robots that aim for lightweight, adaptive, and sensitive designs at low co sts in mechanical design and algorithmic computation. Here, we present the Soft Polyhedral Network with an embedded vision for physical interactions, capable of adaptive kinesthesia and viscoelastic proprioception by learning kinetic featur es. This design enables passive adaptations to omnidirectional interactions, vi sually captured by a miniature high-speed motion-tracking system embedded inside for proprioceptive learning. The results show that the soft network can infer r eal-time 6D forces and torques with accuracies of 0.25/0.24/0.35 N and 0.025/0.0 34/0.006 Nm in dynamic interactions. We also incorporate viscoelasticity in prop rioception during static adaptation by adding a creep and relaxation modifier to refine the predicted results."
      原文链接:
    • NETL
    • NSTL

    Researchers at Beihang University Release New Data on Machine Learning (Advancin g C5+ Hydrocarbons Fuels Production: an Interpretable Machine Learning Framework for Co-catalyzed Syngas Conversion)

    62-63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 in Beijing, People's R epublic of China, by NewsRx journalists, research stated, "Thermocatalytic conve rsion of the renewable syngas into long chain hydrocarbons fuels was an attracti ve energy production technology, for combating climate change, energy crisis, an d wastes disposal. However, this thermochemical process was very complicated, an d target product also highly depended on the feedstock information, catalyst pro perties, and process condition." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). The news reporters obtained a quote from the research from Beihang University, " At present, it was still challenging to fully understand and optimize this proce ss. To address this gap, we developed a machine learning framework to model Fisc her-Tropsch synthesis process of syngas towards C5+ hydrocarbons fuels from expe rimental descriptors. A database of Cobalt-based catalyst with 406 datapoints wa s compiled from literature and subjected to data mining. Accurate ensemble-tree models (R-2 > 0.82) were developed to predict the CO con version and C5+ hydrocarbons fuels selectivity from 12 descriptors, where the si gnificance of dispersion, pressure, temperature, and metal content was revealed. Casual analysis revealed that C5+ hydrocarbons fuels selectivity was positively correlated with lower temperature (<481 K) and higher disp ersion (>7.72 %). Besides, some interesting findings were also observed, for example, smaller cobalt size, and lower pore s ize (<9.27 wt%) and cobalt loading (<22 wt%) were positively related to C(5+ )hydrocarbons fuels selecti vity. The framework was purely data-driven, interpretable, and highlighted the a bility of this method to unearth relationships of target variables and descripto rs in thermocatalytic conversion of syngas, by isolating effects of individual d esign parameters in a manner that would be difficult to achieve experimentally."
      原文链接:
    • NETL
    • NSTL

    New Findings from Tianjin University Update Understanding of Robotics (Voicemap: Autonomous Mapping of Microphone Array for Voice Localization)

    63-64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 originating in Tianjin, People's Republic of China, by NewsRx journalists, research stated, "Voice command systems have been widely deployed on many smart devices for remote control. To further enrich the intelligence of these smart devices, the location of sound plays an important r ole in context-aware acoustic services." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). The news reporters obtained a quote from the research from Tianjin University, " Despite initial steps made toward reliable voice localization, the state-of-the- arts rely on prior knowledge of device location, device orientation and an indoo r electronic map. To mitigate this additional cost, this article presents VoiceM ap, an autonomous mapping system of acoustic devices for voice localization. The insight behind VoiceMap is to explore the cooperation of sweeping robots and vo ice devices. Specifically, the sweeping robot is responsible for exploring the e lectronic map of the environment, while the microphone array is responsible for localizing the sweeping robot, so that we can establish the positional relations hip between them. The core challenges are how to accurately locate the continuou sly moving robot, and how to synchronize the coordinate systems of the sweeping robot and the voice devices. To this end, we first design an inertial-based supe r-resolution method to estimate the angle of arrival (AoA) with respect to the r obot. Then, we develop an effective coordinate synchronization mechanism, so tha t VoiceMap can automatically locate the voice devices on the electronic map gene rated by the robot. Finally, we implement a prototype system using commercial de vices, and conduct comprehensive experiments to verify the proposed system."
      原文链接:
    • NETL
    • NSTL

    New Robotic Systems Research Has Been Reported by a Researcher at Northwestern P olytechnical University (A heuristic autonomous exploration method based on envi ronmental information gain during quadrotor flight)

    64-65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 robotic systems h ave been published. According to news originating from Northwestern Polytechnica l University by NewsRx correspondents, research stated, "Autonomous exploration is a widely studied fundamental application in the field of quadrotor, which req uires them to automatically explore unknown space to obtain complete information about the environment." Our news correspondents obtained a quote from the research from Northwestern Pol ytechnical University: "The frontier-based method, one of the representative wor ks on autonomous exploration, drives autonomous determination by the definition of frontier information so that complete information about the environment is av ailable to the quadrotor. However, existing frontier-based methods are able to a ccomplish the task but still suffer from inefficient exploration, and how to imp rove the efficiency of autonomous exploration is the focus of research nowadays. Slow frontier generation affecting real-time viewpoint determination and insuff icient determination methods affecting the quality of viewpoints are typical of these problems. Therefore, to overcome the aforementioned problems, this article proposes a two-level viewpoint determination method for frontier-based autonomo us exploration. First, a sampling-based frontier detection method is presented f or faster frontier generation, improving the immediacy of environmental represen tation compared to traditional traversal-based methods. Second, the access to en vironmental information during flight is considered for the first time, and an i nnovative heuristic evaluation function is designed to decide on high-quality vi ewpoint as the next local navigation target in each exploration iteration."
      原文链接:
    • NETL
    • NSTL

    Studies from Shanghai Jiao Tong University Yield New Data on Robotics (A Microsc opic Vision-based Robotic System for Floating Electrode Assembly)

    65-66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. According to news reporting originating from Shanghai, People's Republic of C hina, by NewsRx correspondents, research stated, "The implantation of multichann el, miniaturized, flexible neuroelectrodes for high-quality brain signal acquisi tion is of great importance for brain science research and brain-computer interf acing (BCI). However, slender and thin flexible neuroelectrodes usually require a tungsten probe as the shuttle to assist in penetrating the pia mater for impla ntation." Financial support for this research came from Shanghai Municipal Science and Tec hnology Major Project. Our news editors obtained a quote from the research from Shanghai Jiao Tong Univ ersity, "The process in which the tungsten probe passes through the engaging hol e on the tip of the electrode and is tightly bonded is called electrode assembly , which is challenging due to the small-scale and fragile microstructures. The c onventional manual assembly is error-prone and time-consuming with low yields. I t has a high risk of electrode damage, requiring extensive training, very stable hand- eye coordination, and a high level of manual dexterity of the operator. T he development of a robot-controlled microassembly system is essential for neuro science research and clinical deployment. This article presents a universal auto mated microscopic vision-guided robotic system for brain electrode assembly. A r obot system with learning-based detection combined with visual servoing is devel oped for 3-D object and pose estimation, and a robot with submicron displacement accuracy achieves the precise control of the probe. In addition, a new end-to-e nd deep learning network is designed for microfeature detection, and a palpation -based motion strategy is proposed to enable motion control with missing depth i nformation in the microenvironment."
      原文链接:
    • NETL
    • NSTL

    Researchers from Maynooth University Report Findings in Engineering (A Kernel-ba sed Approximate Dynamic Programming Approach: Theory and Application)

    66-66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 En gineering. According to news originating from Kildare, Ireland, by NewsRx corres pondents, research stated, "This article proposes a novel kernel -based Dynamic Programming (DP) approximation method to tackle the typical curse of dimensional ity of stochastic DP problems over the finite time horizon. Such a method utiliz es kernel functions in combination with Support Vector Machine (SVM) regression to determine an approximate cost function for the entire state space of the unde rlying Markov Decision Process (MDP), by leveraging cost function computed for s elected representative states." Our news journalists obtained a quote from the research from Maynooth University , "Kernel functions are used to define the so-called kernel matrix, while the pa rameter vector of the given kernel -based cost function approximation is compute d by moving backwards in time from the terminal condition and by applying SVM re gression. This way, the difficulty of selecting a proper set of features is also tackled. The proposed method is then extended to the infinite time horizon case ."
      原文链接:
    • NETL
    • NSTL

    Korea University Researchers Describe Research in Robotics (Selective-collective scalable locomotion control of helical magnetic swimmers within confined channe ls using global magnetic fields)

    67-67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 robotics have been published. According to news reporting from Sejong, South Korea, by NewsRx journalists, research stated, "Achieving selective-individual and collective co ntrol over multiple magnetic microrobots remains a formidable challenge." Funders for this research include National Research Foundation of Korea. Our news editors obtained a quote from the research from Korea University: "Exis ting techniques for controlling identical magnetic swimmers are often limited to two-dimensional, small working spaces, while heterogeneous swimmers can only be controlled in small numbers without the option for collective control. In this study, we present a purely magnetic control methodology for the selective-scalab le locomotion of helical magnetic swimmers within confined channels. By employin g a unique gradient field distribution, referred to as the "selection field," al ong with space-uniform rotating fields, we establish a "selection volume" that a llows swimmers within it to fully rotate, while those outside remain stationary. We explore various conditions of the selection volume to analyze the locomotion dynamics of the swimmers in relation to the position of the selection volume. E xperimental results demonstrate the selective-scalable locomotion of identical r obots, ranging from one to an arbitrary number (N) of robots, as well as their s electiveindividual manipulation for multitasking applications. Furthermore, com patibility of the proposed method with different magnetic torque-driven robots i s exemplified through the selective control of rolling robots." According to the news editors, the research concluded: "Moreover, three-dimensio nal selective-scalable control is also demonstrated for four swimmers in a quasi -three-dimensional channel, as well as for two swimmers within a true three-dime nsional channel."
      原文链接:
    • NETL
    • NSTL

    Capital Medical University Reports Findings in Non-Alcoholic Fatty Liver Disease (Establishment of a machine learning predictive model for non-alcoholic fatty l iver disease: A longitudinal cohort study)

    67-68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 Liver Diseases and Con ditions - Non-Alcoholic Fatty Liver Disease is the subject of a report. Accordin g to news reporting from Beijing, People's Republic of China, by NewsRx journali sts, research stated, "Non-alcoholic fatty liver disease (NAFLD) is a common chr onic liver disease, which lacks effective drug treatments. This study aimed to c onstruct an eXtreme Gradient Boosting (XGBoost) prediction model to identify or evaluate potential NAFLD patients." The news correspondents obtained a quote from the research from Capital Medical University, "We conducted a longitudinal study of 22,140 individuals from the Be ijing Health Management Cohort. Variable filtering was performed using the least absolute shrinkage and selection operator. Random Over Sampling Examples was us ed to address imbalanced data. Next, the XGBoost model and the other three machi ne learning (ML) models were built using balanced data. Finally, the variable im portance of the XGBoost model was ranked. Among four ML algorithms, we got that the XGBoost model outperformed the other models with the following results: accu racy of 0.835, sensitivity of 0.835, specificity of 0.834, Youden index of 0.669 , precision of 0.831, recall of 0.835, F-1 score of 0.833, and an area under the curve of 0.914. The top five variables with the greatest impact on the onset of NAFLD were aspartate aminotransferase, cardiometabolic index, body mass index, alanine aminotransferase, and triglyceride-glucose index. The predictive model b ased on the XGBoost algorithm enables early prediction of the onset of NAFLD."
      原文链接:
    • NETL
    • NSTL

    Recent Findings in Robotics Described by Researchers from Leibniz University Han nover (The Voraus-ad Dataset for Anomaly Detection In Robot Applications)

    68-69页
    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 originating in Hannover, Germany, by NewsRx jour nalists, research stated, "During the operation of industrial robots, unusual ev ents may endanger the safety of humans and the quality of production. When colle cting data to detect such cases, it is not ensured that data from all potentiall y occurring errors is included as unforeseeable events may happen over time." Financial support for this research came from Federal Ministry of Education & Research (BMBF). The news reporters obtained a quote from the research from Leibniz University Ha nnover, "Therefore, anomaly detection (AD) delivers a practical solution, using only normal data to learn to detect unusual events. We introduce a dataset that allows training and benchmarking of anomaly detection methods for robotic applic ations based on machine data which will be made publicly available to the resear ch community. As a typical robot task the dataset includes a pick-and-place appl ication which involves movement, actions of the end effector, and interactions w ith the objects of the environment. Since several of the contained anomalies are not task-specific but general, evaluations on our dataset are transferable to o ther robotics applications as well. In addition, we present multivariate time-se ries flow (MVT-Flow) as a new baseline method for anomaly detection: It relies o n deep-learning-based density estimation with normalizing flows, tailored to the data domain by taking its structure into account for the architecture."
      原文链接:
    • NETL
    • NSTL