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

    Data on Robotics and Automation Discussed by Researchers at University of Colorado (Sampling-based Reactive Synthesis for Nondeterministic Hybrid Systems)

    56-57页
    查看更多>>摘要：Investigators publish new report on Robotics - Robotics and Automation. According to news reporting originating from Boulder, Colorado, by NewsRx correspondents, research stated, “This letter introduces a sampling-based strategy synthesis algorithm for nondeterministic hybrid systems with complex continuous dynamics under temporal and reachability constraints. We model the evolution of the hybrid system as a two-player game, where the nondeterminism is an adversarial player whose objective is to prevent achieving temporal and reachability goals.” Financial support for this research came from Strategic University Research Partnership. Our news editors obtained a quote from the research from the University of Colorado, “The aim is to synthesize a winning strategy a reactive (robust) strategy that guarantees the satisfaction of the goals under all possible moves of the adversarial player. Our proposed approach involves growing a (search) game-tree in the hybrid space by combining sampling-based motion planning with a novel bandit-based technique to select and improve on partial strategies. We show that the algorithm is probabilistically complete, i.e., the algorithm will asymptotically almost surely find a winning strategy, if one exists.”
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Investigators at Sichuan Normal University Report Findings in Machine Learning (Active Learning Based Reverse Design of Hydrogen Production From Biomass Fuel)

    57-58页
    查看更多>>摘要：Fresh data on Machine Learning are presented in a new report. According to news reporting originating in Sichuan, People’s Republic of China, by NewsRx journalists, research stated, “Biomass hydrogen production holds substantial promise in addressing critical challenges within the realms of renewable energy and environmental sustainability. Nevertheless, the laborand time-intensive nature of conducting combinatorial experiments and relying on traditional trial-and-error methods significantly constrains the exploration of biomass fuel solutions.” The news reporters obtained a quote from the research from Sichuan Normal University, “This paper introduces a novel framework for the reverse engineering of hydrogen production systems, which seamlessly integrates Bayesian active learning with machine learning models. In Bayesian active learning, 307 biomass fuel samples were expanded to 1354 in order to ensure the accuracy of the model prediction between the seven characteristics of biomass fuel and hydrogen production. Four machine learning algorithms including RF, XGBoost, KNNR, AdaBoost were used to build the prediction model. A stochastic search reverse design approach based on the XGBoost model with the highest coefficient of determination (R2 = 0.91) was innovatively used to realize the ‘reverse design’ from ‘target performance’ to ‘composition and process’. Through reverse design, a two-order-of-magnitude increase in design space is achieved in hundreds of times less time than conventional design time, resulting in a significant improvement in hydrogen production efficiency.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Zhejiang Cancer Hospital Reports Findings in Machine Learning (Serum Protein Fishing for Machine Learning-Boosted Diagnostic Classification of Small Nodules of Lung)

    58-59页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting out of Zhejiang, People’s Republic of China, by NewsRx editors, research stated, “Diagnosis of benign and malignant small nodules of the lung remains an unmet clinical problem which is leading to serious false positive diagnosis and overtreatment. Here, we developed a serum protein fishing-based spectral library (ProteoFish) for data independent acquisition analysis and a machine learning-boosted protein panel for diagnosis of early Non-Small Cell Lung Cancer (NSCLC) and classification of benign and malignant small nodules.” Our news journalists obtained a quote from the research from Zhejiang Cancer Hospital, “We established an extensive NSCLC protein bank consisting of 297 clinical subjects. After testing 5 feature extraction algorithms and six machine learning models, the Lasso algorithm for a 15-key protein panel selection and Random Forest was chosen for diagnostic classification. Our random forest classifier achieved 91.38% accuracy in benign and malignant small nodule diagnosis, which is superior to the existing clinical assays.”
      原文链接:
    • NETL
    • NSTL

    Studies from Indian Institute for Technology in the Area of Machine Learning Reported (Efficient and Reliable Prediction of Dump Slope Stability In Mines Using Machine Learning: an In-depth Feature Importance Analysis)

    59-60页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting originating from Kharagpur, India, by NewsRx correspondents, research stated, “This study rigorously examines the pressing issue of dump slope stability in Indian opencast coal mines, a problem that has led to significant safety incidents and operational hindrances. Employing machine to achieve a scientific goal of predictive accuracy for slope stability under various environmental and operational conditions.” Our news editors obtained a quote from the research from Indian Institute for Technology, “Promising accuracies were attained, notably with RF (0.98), SVM (0.98), and DT (0.97). To address the class imbalance issue, the Synthetic Minority Oversampling Technique (SMOTE) was implemented, resulting in improved model performance. Furthermore, this study introduced a novel feature importance technique to identify critical factors affecting dump slope stability, offering new insights into the mechanisms leading to slope failures.”
      原文链接:
    • NETL
    • NSTL
    • Polska Akad Nauk

    Findings from Jagiellonian University Provide New Insights into Machine Learning (Hypercolor: a Hypernetwork Approach for Synthesizing Autocolored 3-d Models for Game Scenes Population)

    60-60页
    查看更多>>摘要：Researchers detail new data in Machine Learning. According to news reporting originating from Krakow, Poland, by NewsRx correspondents, research stated, “Designing a 3-D game scene is a tedious task that often requires a substantial amount of work. Typically, this task involves the synthesis and coloring of 3-D models within the scene.” Financial support for this research came from Priority Research Area Digiworld. Our news editors obtained a quote from the research from Jagiellonian University, “To lessen this workload, we can apply machine learning to automate some aspects of the game scene development. Earlier research has already tackled automated generation of the game scene background with machine learning. However, model autocoloring remains an underexplored problem. The automatic coloring of a 3-D model is a challenging task, especially when dealing with the digital representation of a colorful, multipart object. In such a case, we have to ‘understand’ the object’s composition and coloring scheme of each part. Moreover, existing single-stage methods have their caveats. We address these limitations by proposing a two-stage training approach to synthesize autocolored 3-D models. In the first stage, we obtain a 3-D point cloud representing a 3-D object, while in the second stage, we assign colors to points within such a cloud. Next, we generate a 3-D mesh in which the surfaces are colored based on the interpolation of colored points representing vertices of a given mesh triangle.”
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Study Results from Shanghai Jiao Tong University Provide New Insights into Robotics (Vacuum-driven Parallel Continuum Robots With Self-sensing Origami Linkages)

    61-61页
    查看更多>>摘要：Investigators publish new report on Robotics. According to news reporting from Shanghai, People’s Republic of China, by NewsRx journalists, research stated, “Parallel continuum robots (PCRs) based on soft actuators have been recently proposed to take advantage of both, soft robots in flexible, diverse actuation, parallel robots in stable, and precise motion. Although various designs have been exhibited, most of them suffer from positioning inaccuracy, especially under uncertain payloads, due to the lack of strong actuation and effective integrated sensing methods.” Financial support for this research came from National Natural Science Foundation of China (NSFC). The news correspondents obtained a quote from the research from Shanghai Jiao Tong University, “Here, we introduce a vacuum-driven PCR that can simultaneously perform multimode motion, high positioning accuracy, and high load-carrying capacity, on the basis of the mechanical feature of origami. With a soft-rigid hybrid 3-D printing method, the origami linkages of the PCR can be constructed at one time. This forms soft but less stretchable pneumatic chambers that can generate strong actuation based on origami folding. The vacuum-driven linkages exploit the contraction-twisting coupled folding characteristic of the Kresling origami pattern. The length of each linkage can be determined by recording the twisting angles. Theoretical models for both the self-sensing linkage and the PCR with three individually actuated linkages, as well as a closed-loop feedback control strategy, have been presented for the motion control of the PCR. The experimental results of a PCR prototype demonstrate its multimode motion, including contraction/extension, omnidirectional bending, and circular swing. The combination of the design and fabrication methods, the sensing strategy, and the feedback control enables the prototype to perform high positioning accuracy with various trajectories, even under a 2-kg payload.”
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Recent Research from Tsinghua University Highlight Findings in Robotics and Automation (Poses As Queries: End-to-end Imageto-lidar Map Localization With Transformers)

    62-62页
    查看更多>>摘要：Investigators publish new report on Robotics Robotics and Automation. According to news reporting originating from Beijing, People’s Republic of China, by NewsRx correspondents, research stated, “High-precision vehicle localization with commercial setups is a crucial technique for high-level autonomous driving tasks. As a newly emerged approach, monocular localization in LiDAR map achieves promising balance between cost and accuracy, but estimating pose by finding correspondences between such cross-modal sensor data is challenging, thereby damaging the localization accuracy.” Financial support for this research came from National Natural Science Foundation of China (NSFC). Our news editors obtained a quote from the research from Tsinghua University, “In this letter, we address the problem by proposing a novel Transformer-based neural network to register 2D images into 3D LiDAR map in an end-to-end manner. We first implicitly represent poses as high-dimensional feature vectors called pose queries and gradually optimize poses by interacting with the retrieved relevant information from cross-modal features using attention mechanism in a proposed POse Estimator Transformer (POET) module. Moreover, we apply a multiple hypotheses aggregation method that estimates the final poses by performing parallel optimization on multiple randomly initialized pose queries to reduce the network uncertainty.”
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Research Reports on Computational Intelligence from Kyushu Institute of Technology Provide New Insights (Layer Configurations of BERT for Multitask Learning and Data Augmentation)

    63-63页
    查看更多>>摘要：Investigators discuss new findings in computational intelligence. According to news reporting from Fukuoka, Japan, by NewsRx journalists, research stated, “Multitask learning (MTL) and data augmentation are becoming increasingly popular in natural language processing (NLP). These techniques are particularly useful when data are scarce.” The news editors obtained a quote from the research from Kyushu Institute of Technology: “In MTL, knowledge learned from one task is applied to another. To address data scarcity, data augmentation facilitates by providing additional synthetic data during model training. In NLP, the bidirectional encoder representations from transformers (BERT) model is the default candidate for various tasks. MTL and data augmentation using BERT have yielded promising results. However, a detailed study regarding the effect of using MTL in different layers of BERT and the benefit of data augmentation in these configurations has not been conducted. In this study, we investigate the use of MTL and data augmentation from generative models, specifically for category classification, sentiment classification, and aspect-opinion sequence-labeling using BERT. The layers of BERT are categorized into top, middle, and bottom layers, which are frozen, shared, or unshared.”
      原文链接:
    • NETL
    • NSTL
    • Fuji Technology Press Ltd

    Research from Northeastern University in the Area of Machine Learning Published (Preliminary Research on Outdoor Thermal Comfort Evaluation in Severe Cold Regions by Machine Learning)

    64-64页
    查看更多>>摘要：Current study results on artificial intelligence have been published. According to news reporting from Shenyang, People’s Republic of China, by NewsRx journalists, research stated, “The thermal comfort evaluation of the urban environment arouses widespread concern among scholars, and research in this field is mostly based on thermal comfort evaluation indexes such as PMV, PET, SET, UTCI, etc.” Our news journalists obtained a quote from the research from Northeastern University: “These thermal comfort index evaluation models are complex in the calculation process and poor in operability, which makes it difficult for people who lack a relevant knowledge background to understand, calculate, and apply them. The purpose of this study is to provide a simple, efficient, and easy-to-operate outdoor thermal comfort evaluation model for severe cold areas in China using a machine learning method. In this study, the physical environment parameters are obtained by field measurement, and individual information is obtained by a field questionnaire survey. The applicability of four machine learning models in outdoor thermal comfort evaluation is studied. A total of 320 questionnaires are collected. The results show that the correlation coefficients between predicted values and voting values of the extreme gradient lifting model, gradient lifting model, random forest model, and neural network model are 0.9313, 0.7148, 0.9115, and 0.5325, respectively.”
      原文链接:
    • NETL
    • NSTL
    • Mdpi

    Study Findings from Egypt-Japan University of Science and Technology Provide New Insights into Machine Learning (Classification and Detection of Natural Disasters Using Machine Learning and Deep Learning Techniques: a Review)

    65-65页
    查看更多>>摘要：Investigators discuss new findings in Machine Learning. According to news reporting originating from Alexandria, Egypt, by NewsRx correspondents, research stated, “For efficient disaster management, it is essential to identify and categorize natural disasters. The classical approaches and current technological advancements for identifying, categorizing, and reducing the harmful effects of natural catastrophes are discussed in this review article.” Funders for this research include Science, Technology, and Innovation Funding Authority, JICA. Our news editors obtained a quote from the research from the Egypt-Japan University of Science and Technology, “They include human observation and reporting, satellite images, seismology, radar, infrared imagery, and sonar. The article explores natural disasters’ challenges and harmful effects and their mitigation measures. The article explains the benefits and drawbacks of published approaches and emphasizes how they may be used to identify many kinds of natural catastrophes, including earthquakes, floods, wildfires, and hurricanes. Discussions on current technological advancements, including machine and deep learning applications, that can potentially increase the precision and efficiency of natural disaster detection and classification are presented. Overall, the review article emphasizes the significance of continuing research and improving current techniques to increase communities’ and countries’ resilience and preparedness for natural disasters.”
      原文链接:
    • NETL
    • NSTL
    • Springer Nature