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 Machine Learning Reported by Researchers at University of Hawaii Manoa (Improving the Prediction of Wildfire Susceptibility On Hawai'i Island, Hawai'i, Using Explainable Hybrid Machine Learning Models)

    65-66页
    查看更多>>摘要：Research findings on Machine Learning are discussed in a new report. According to news reporting originating from Honolulu, Hawaii, by NewsRx correspondents, research stated, “This study presents a comparative analysis of four Machine Learning (ML) models used to map wildfire susceptibility on HawaiModified Letter Turned Commai Island, HawaiModified Letter Turned Commai. Extreme Gradient Boosting (XGBoost) combined with three meta-heuristic algorithms - Whale Optimization (WOA), Black Widow Optimization (BWO), and Butterfly Optimization (BOA) - were employed to map areas susceptible to wildfire.” Financial support for this research came from Hawaii-Emergency Management Agency (HI-EMA) grant. Our news editors obtained a quote from the research from the University of Hawaii Manoa, “To generate a wildfire inventory, 1408 wildfire points were identified within the study area from 2004 to 2022. The four ML models (XGBoost, WOA-XGBoost, BWOXGBoost, and BOA-XGBoost) were run using 14 wildfire-conditioning factors categorized into four main groups: topographical, meteorological, vegetation, and anthropogenic. Six performance metrics - sensitivity, specificity, positive predictive values, negative predictive values, the Area Under the receiver operating characteristic Curve (AUC), and the average precision (AP) of Precision-Recall Curves (PRCs) - were used to compare the predictive performance of the ML models. The SHapley Additive exPlanations (SHAP) framework was also used to interpret the importance values of the 14 influential variables for the modeling of wildfire on HawaiModified Letter Turned Commai Island using the four models. The results of the wildfire modeling indicated that all four models performed well, with the BWOXGBoost model exhibiting a slightly higher prediction performance (AUC = 0.9269), followed by WOAXGBoost (AUC = 0.9253), BOA-XGBoost (AUC = 0.9232), and XGBoost (AUC = 0.9164). SHAP analysis revealed that the distance from a road, annual temperature, and elevation were the most influential factors.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Data on Endometriosis Reported by Gianmarco D'Ancona and Colleagues (Combined Robotic Transanal Transection Single-stapled Technique in Ultralow Rectal Endometriosis Involvement Associated with Parametrial and Vaginal Infiltration)

    66-67页
    查看更多>>摘要：New research on Uterine Diseases and Conditions - Endometriosis is the subject of a report. According to news reporting originating from Bordeaux, France, by NewsRx correspondents, research stated, “To describe a combined robotic and transanal technique used to treat ultralow rectal endometriosis in a 36-year-old patient with multiple pelvic compartments, which was responsible for infertility, dyspareunia, left sciatic pain, and severe dyschezia. Surgical video article.” Our news editors obtained a quote from the research, “The achievement of a perfect bowel anastomosis in patients with low rectal endometriosis could be challenging owing to technical and anatomic limitations [1]. By allowing a right angle rectotomy with a single-stapled anastomosis, the transanal transection single- stapled technique overcomes these technical difficulties ensuring a good-quality anastomosis with an easier correction of postoperative anastomotic leakage when it occurs [2,3]. The surgery starts by splitting the nodule in 3 components according to different anatomic structures involved (parametrium, vagina, and rectum). Parametrial and vaginal fragments are excised as previously described (Supplemental Videos 1) [4]. The rectal involvement is approached following several steps: isolation and cut of inferior mesenteric vessels (inferior mesenteric artery and inferior mesenteric vein) and left colic artery to obtain a proper colon mobilization; transanal rectotomy immediately below the lower limit of the nodule; extraction of the specimen through the anus (Supplemental Videos 2); proximal bowel segment transection 1 cm above the upper limit of the nodule; introduction of circular stapler anvil into the sigmoid colon; placement of 2 purse string to secure the anvil and at distal rectal cuff, respectively; connection of the anvil to the shoulder of circular stapler; stapler closing and firing with coloanal anastomosis formation; stapled line reinforcement by stitching; and integrity anastomosis test (Supplemental Videos 3). No preventive diverting stoma was performed in accordance with our policy [5].”
      原文链接:
    • NETL
    • NSTL

    Research Data from De La Salle University Update Understanding of Computational Intelligence (Enhancing Fault Detection and Classification in Grid-Tied Solar Energy Systems Using Radial Basis Function and Fuzzy Logic-Controlled Data Switch)

    67-67页
    查看更多>>摘要：New research on computational intelligence is the subject of a new report. According to news originating from Manila, Philippines, by NewsRx correspondents, research stated, “This study integrates fuzzy logic-controlled data switching and the radial basis function neural network (RBFNN) for fault detection and classification in grid-tied solar energy systems.” Financial supporters for this research include De La Salle Manila; Bulacan State University. Our news reporters obtained a quote from the research from De La Salle University: “The fuzzy logic controller filters out invalid sensor data through a data switch, ensuring that the fault detection and classification system receives reliable input. Training data were prepared through data normalization using the z-score function and principal component analysis, thereby reducing data complexity and standardizing the inputs. The resulting RBFNN model exhibited a low mean squared error with a value of 7.67×10~(-4) ,indicating its ability to classify faults based on the actual system scenarios.”
      原文链接:
    • NETL
    • NSTL
    • Fuji Technology Press Ltd

    Findings on Robotics Reported by Investigators at Beihang University (Knowledge Graph and Function Block Based Digital Twin Modeling for Robotic Machining of Large-scale Components)

    68-68页
    查看更多>>摘要：Investigators publish new report on Robotics. According to news reporting from Beijing, People's Republic of China, by NewsRx journalists, research stated, “Robotic machining is a potential method for machining large-scale components (LSCs) due to its low cost and high flexibility. However, the low stiffness of robots and complex machining process of LSCs result in a lack of alignment between the physical process and digital models, making it difficult to realize the robotic machining of LSCs.” Funders for this research include National Natural Science Foundation of China (NSFC), National Key Research and Development Program of China. The news correspondents obtained a quote from the research from Beihang University, “The recent Digital Twin (DT) concept shows potential in terms of representing and modeling physical processes. Therefore, this study proposes a robotic machining DT for LSCs. However, the current DT is not capable of knowledge representation, multi-source data integration, optimization algorithm implementation, and real-time control. To address these issues, Knowledge Graph (KG) and Function Block (FB) are employed in the proposed robotic machining DT. Here, robotic machining related information, such as the machining parameters and errors, is represented in the virtual space by building the KG, whereas the FBs are responsible for integrating and applying the algorithms for process execution and optimization based on real-world events. Moreover, a novel adaptive process adjustment strategy is proposed to improve the efficiency of the process execution. Finally, a prototype system of the robotic machining DT is developed and validated by an experiment on robotic milling of the assembly interface for an LSC.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Recent Findings from University of the Chinese Academy of Sciences Has Provided New Information about Robotics (Sketch Rl: Interactive Sketch Generation for Long-horizon Tasks Via Vision-based Skill Predictor)

    69-69页
    查看更多>>摘要：Investigators discuss new findings in Robotics. According to news originating from Beijing, People's Republic of China, by NewsRx correspondents, research stated, “For autonomous robots, it is desirable to learn coordination of primitive skills that can effectively solve long-horizon tasks and perform novel ones. Recent advances in hierarchical policy learning have shown that decomposing complex tasks into sequences of primitive skills which are called sketches can enable robots to perform directed exploration in challenging manipulation tasks.” Financial support for this research came from National Key Research and Development Plan of China. Our news journalists obtained a quote from the research from the University of the Chinese Academy of Sciences, “However, they usually fall short in sequencing skills in a new task without retraining as the task sketches are almost hard-coded or learned by deep reinforcement learning. To improve exploration efficiency for long-horizon tasks, we propose Sketch RL, a hierarchical framework that combines supervised learning with reinforcement learning interactively generates the task sketch, and utilizes it as the curriculum to guide low-level skill learning. Furthermore, to allow for multitask decomposition and generalizing few- shot to new tasks, our method exploits a Vision-based Skill Predictor (VSP) to capture shared subtask structure.
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Data on Robotics Discussed by Researchers at Harbin Institute of Technology (Pose Estimation of an Aerial Construction Robot Based On Motion and Dynamic Constraints)

    70-70页
    查看更多>>摘要：New research on Robotics is the subject of a report. According to news reporting originating from Shenzhen, People's Republic of China, by NewsRx correspondents, research stated, “High accuracy pose estimation with high data rate of an aerial construction robot is the prerequisite for aerial construction robot control. A dynamic and motion constrained robust extended Kalman filter is developed for robot localization in aerial construction environment which is characterized by radio signal occlusion and few visual features.” Financial supporters for this research include Shenzhen-Hong Kong Science and Technology Innovation Cooperation Zone, InnoHK of the Government of the Hong Kong Special Administrative Region via the Hong Kong Centre for Logistics Robotics, Hong Kong SAR Government, CUHK T Stone Robotics Institute, Zanecon Co., Ltd…
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Study Results from Shanghai Jiao Tong University Update Understanding of Machine Learning (An Interpretable Machine Learning Model for Trajectory Prediction Based On Nonlinear Dynamics Mechanism Constraints: Applications for Hvs)

    71-71页
    查看更多>>摘要：Current study results on Machine Learning have been published. According to news reporting originating in Shanghai, People's Republic of China, by NewsRx journalists, research stated, “It is challenging for hypersonic vehicles (HVs) with strong nonlinear dynamics characteristics to achieve high-precision trajectory prediction. The un-interpretability of current prediction models and the difficulty in on-orbit data acquisition, high transmission costs and low data integrity bring huge obstacles to the accuracy and reliability of online prediction results.” Financial supporters for this research include Chinese-German Center for Research Promotion, National Natural Science Foundation of China (NSFC), Young Elite Scientists Sponsorship Program by China Association for Science and Technology.
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    University of Cadiz Reports Findings in Machine Learning (Machine learning-based approaches to Vis-NIR data for the automated characterization of petroleum wax blends)

    72-72页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting out of Cadiz, Spain, by NewsRx editors, research stated, “Petroleum waxes are products derived from lubricating oils with a wide spectrum of industrial and consumer applications that depend on their composition. In addition, the intended applications of this product are also subject to the practice of blending petroleum waxes with different chemical characteristics (e.g., paraffin waxes and microwaxes) to achieve the appropriate physicochemical properties.” Our news journalists obtained a quote from the research from the University of Cadiz, “This study in- troduces a novel method based on visible and near-infrared spectroscopy (Vis-NIR) combined with machine learning (ML) for the characterization of blends of the two types of commonly marketed petroleum waxes (paraffin waxes and microwaxes). With spectroscopic data, Partial Least Squared Regression (PLSR), Support Vector Regression (SVR), and Random Forest (RF) Regression-based regression ML models have been developed, obtaining satisfactory results for the characterization of the percentage of blending in petroleum waxes. Moreover, strategies using wrapper variable selection methods like the Boruta algorithm and Genetic Algorithm (GA) have been implemented to assess if fewer predictors enhance model performance. Particularly, the application of wrapper variable selection methods, specifically the Boruta algorithm, has led to an improvement in the performance of the models obtained. Results obtained by the Boruta-PLS model showed the best performance with an RMSE of 2.972 and an R of 0.9925 for the test set and an RMSE of 1.814 and an R of 0.9977 for the external validation set. Additionally, this model allowed for establishing the relative importance of the variables in the characterization of the waxes mixture, pointing out that the hydrocarbon content ratio is critical in the determination of this value.”
      原文链接:
    • NETL
    • NSTL

    King's College London Reports Findings in Robotics (Semiautonomous Robotic Manipulator for Minimally Invasive Aortic Valve Replacement)

    73-73页
    查看更多>>摘要：New research on Robotics is the subject of a report. According to news originating from London, United Kingdom, by NewsRx correspondents, research stated, “Aortic valve surgery is the preferred procedure for replacing a damaged valve with an artificial one. The ValveTech robotic platform comprises a flexible articulated manipulator and surgical interface supporting the effective delivery of an artificial valve by teleoperation and endoscopic vision.” Our news journalists obtained a quote from the research from King's College London, “This article presents our recent work on force-perceptive, safe, semiautonomous navigation of the ValveTech platform prior to valve implantation. First, we present a force observer that transfers forces from the manipulator body and tip to a haptic interface. Second, we demonstrate how hybrid forward/inverse mechanics, together with endoscopic visual servoing, lead to autonomous valve positioning. Benchtop experiments and an artificial phantom quantify the performance of the developed robot controller and navigator. Valves can be autonomously delivered with a 2.0±0.5 mm position error and a minimal misalignment of 3.4±0.9°. The hybrid force/shape observer (FSO) algorithm was able to predict distributed external forces on the articulated manipulator body with an average error of 0.09 N. FSO can also estimate loads on the tip with an average accuracy of 3.3%.”
      原文链接:
    • NETL
    • NSTL

    Researchers from Southern University of Science and Technology (SUSTech) Provide Details of New Studies and Findings in the Area of Machine Learning (Selective Discrimination of Vocs Gases At Ppb-level Using Mos Gas Sensor In Temperature-pulsed…)

    74-74页
    查看更多>>摘要：Fresh data on Machine Learning are presented in a new report. According to news re- porting originating from Shenzhen, People's Republic of China, by NewsRx correspondents, research stated, “Due to the complicated gas-sensing process on the surface of metal oxide semiconductors (MOS), it is hard to accurately characterize the transient changes of MOS gas sensor. This paper introduces a modified Hill equation to quantitatively analyze the instantaneous resistance of MOS gas sensors operating in temperature-pulsed operation mode, to extract the gas-sensing dynamic features and key parameters for the selective identification of various volatile organic compounds (VOCs) gases (such as ethanol, formaldehyde, toluene and acetone) by machine learning algorithms.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier