期刊,Robotics & Machine Learning Daily News 2024年卷Oct.4期_国家学术搜索

期刊信息/Journal information

Robotics & Machine Learning Daily News

NewsRx

主办单位：NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News

正式出版

收录年代

Laboratory of Robotics Researchers Have Provided New Study Findings on Robotic S ystems (A reinforcement learning based sliding mode control for passive upper-li mb exoskeleton)

76-77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 robotic systems a re discussed in a new report. According to news reporting originating from Tunis,Tunisia, by NewsRx correspondents, research stated, "Rehabilitation devices su ch as actuated exoskeletons can provide mobility assistance for patients sufferi ng from paralysis or muscle weakness." The news reporters obtained a quote from the research from Laboratory of Robotic s: "In order to improve the well-being of patients, the control design of exoske letons is of paramount importance and highest priority. In this paper, we presen t a sliding reinforcement learning (RL) method control for an upper-limb exoskel eton, enabling it to learn following a desired trajectory in the Cartesian space . The deep deterministic policy gradient (DDPG) using an actor-critic architectu re is employed to continuously adjust the non-singular terminal sliding mode con trol (NSTSMC) control inputs, based on previous experiences. The designed actor network learns the policy and the critic evaluates the quality of the actions ch osen by the actor. The robustness of the proposed approach is studied when the s ystem is subjected to random disturbances. The simulation results demonstrate th at the proposed approach based on the RL method effectively fulfills exoskeleton tracking tasks."

原文链接:

NETL
NSTL

Researchers from Texas A&M University Detail New Studies and Findin gs in the Area of Machine Learning (Precision Polishing of Ablator Capsules Via In Situ Process Monitoring and Machine Learning-based Optimization)

77-78页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Machine Learning are pre sented in a new report. According to news reporting from College Station, Texas, by NewsRx journalists, research stated, "In inertial confinement fusion (ICF) e xperiments seeking output gains of unity and beyond, the quality of the ablator capsule is paramount for minimizing the hydrodynamic mix that quenches the centr al hot spot. Defects in the form of foreign particles or missing mass on the sur face and within the wall of the capsule are primary offenders." Funders for this research include United States Department of Energy (DOE), LLNL laboratory-directed research and development program.

原文链接:

NETL
NSTL

Data from Debark University Broaden Understanding of Artificial Intelligence (Ex plainable artificial intelligence models for predicting pregnancy termination am ong reproductive-aged women in six east African countries: machine learning appr oach)

78-79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 artificial intell igence have been published. According to news reporting from Debark University b y NewsRx journalists, research stated, "Pregnancy termination remains a complex and sensitive issue with approximately 45% of abortions worldwide being unsafe, and 97% of abortions occurring in developing countri es. Unsafe pregnancy terminations have implications for women's reproductive hea lth." The news editors obtained a quote from the research from Debark University: "Thi s research aims to compare black box models in their prediction of pregnancy ter mination among reproductive-aged women and identify factors associated with preg nancy termination using explainable artificial intelligence (XAI) methods. We us ed comprehensive secondary data on reproductive-aged women's demographic and soc ioeconomic data from the Demographic Health Survey (DHS) from six countries in E ast Africa in the analysis. This study implemented five black box ML models, Bag ging classifier, Random Forest, Extreme Gradient Boosting (XGB) Classifier, CatB oost Classifier, and Extra Trees Classifier on a dataset with 338,904 instances and 18 features. Additionally, SHAP, Eli5, and LIME XAI techniques were used to determine features associated with pregnancy termination and Statistical analysi s were employed to understand the distribution of pregnancy termination. The res ults demonstrated that machine learning algorithms were able to predict pregnanc y termination on DHS data with an overall accuracy ranging from 79.4 to 85.6% . The ML classifier random forest achieved the highest result, with an accuracy of 85.6%."

原文链接:

NETL
NSTL

New Findings on Robotics from Zhejiang University Summarized (Real-time Tilapia Fillet Defect Segmentation On Edge Device for Robotic Trimming)

79-79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 out of Zhejiang, People's Republic of China, by N ewsRx editors, research stated, "The implementation of robotic tilapia fillet tr imming instead of manual labor is a pivotal advancement in intelligent fish proc essing, offering substantial superiority in operational efficiency and product q uality. The study presents an improved model called TFDS-YOLOv8n for tilapia fil let defects segmentation." Financial support for this research came from Natural Science Foundation of Zhej iang Province. Our news journalists obtained a quote from the research from Zhejiang University,"The model incorporates Coordinate Attention (CA) into the feature extraction layer, thereby enhancing its ability to capture characteristics at various level s of the input. Additionally, the feature fusion layer is reconstructed as Slim- Neck to reduce the number of parameters without compromising prediction accuracy . Furthermore, the bounding box loss function is modified by MPDIoU to expedite the model convergence. The proposed model was tested employing the dataset colle cted from the practical tilapia processing plant. Ablation experiments demonstra te that TFDS-YOLOv8n achieves a reduction of 0.29 MB in parameters and 1 Gin Flo ating Point Operations (FLOPs) while increasing bbox_mAP and mask_ mAP by 2.8 % and 2.5 %, respectively. Eventually, the model is further accelerated by TensorRT and deployed on the edge device."

原文链接:

NETL
NSTL

New Findings from Bern University Hospital in the Area of Machine Learning Repor ted (Machine Learning Applications In Precision Medicine: Overcoming Challenges and Unlocking Potential)

80-80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 have been presented. According to news reporting originating in Bern, Switzerland, b y NewsRx journalists, research stated, "Precision medicine, utilizing genomic an d phenotypic data, aims to tailor treatments for individual patients. However, s uccessful implementation into clinical practice is challenging." Financial supporters for this research include Swiss National Science Foundation (SNSF), Swiss National Science Foundation (SNSF), Research Council of Finland. The news reporters obtained a quote from the research from Bern University Hospi tal, "Machine learning (ML) algorithms have demonstrated incredible capabilities in handling probabilities, managing diverse datasets, and are increasingly appl ied in precision medicine research. The key ML applications include classificati on for diagnosis, patient stratification, prognosis, and treatment monitoring. M L offers solutions for automated structural elucidation, in silico library const ruction, and efficient processing of mass spectrometry raw data. Integration of ML with genome-scale metabolic models (GEMs) provides mechanistic insights into genotype-phenotype relationships. In this manuscript, we examine the impact of M L in various facets of precision medicine, from diagnostics and patient phenotyp ing to personalized treatment strategies."

原文链接:

NETL
NSTL

New Robotics and Automation Study Findings Have Been Reported by Investigators a t Chinese Academy of Sciences (Modeling and Analysis of Oblique-chamber and Symm etric Oblique-chamber Pneu-net Soft Actuators)

81-81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-Robotics an d Automation is the subject of a report. According to news reporting originating in Hefei, People's Republic of China, by NewsRx journalists, research stated, " Oblique-chamber pneu-net soft actuators (OC-PNSAs) exhibit helical deformation u pon inflation. The symmetric oblique-chamber pneu-net soft actuator (SOC-PNSA) c onsists of two symmetric OC-PNSAs." Financial supporters for this research include National Key R&D Pro gram of China, Special Key Project of Technological Innovation and Application D evelopment in Chongqing. The news reporters obtained a quote from the research from the Chinese Academy o f Sciences, "By adjusting the pressures in the two chambers, the deformation sha pe can be controlled, enabling it to grasp objects of varying shapes. In this le tter, we first establish a deformation model for OC-PNSAs. We demonstrate that t he OC-PNSA bends around the inclined wall upon inflation, thereby revealing the mechanism of its helical deformation. Furthermore, we demonstrate that the helic al bending angle of the OC-PNSA is equal to the bending angle of the PNSA with t he same dimensions. Therefore, the existing PNSA bending model can be applied to OC-PNSAs. Additionally, considering the coupling effects of the symmetric obliq ue chambers, we develop a deformation model for SOC-PNSAs based on the OC-PNSA m odel and the principle of equivalent effects. Both experiments and simulations v alidate the theoretical model's accuracy in predicting actuator deformation."

原文链接:

NETL
NSTL

Study Data from Guangdong University of Technology Update Knowledge of Computati onal Intelligence (A Novel Hypercomplex Graph Convolution Refining Mechanism)

82-82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 Machine Learning-Computational Intelligence. According to news reporting originating from Guangzhou, People's Republic of China, by NewsRx correspondents, research s tated, "Hypercomplex graph convolutions with higher hypercomplex dimensions can extract more complex features in graphs and features with varying levels of comp lexity are suited for different situation. However, existing hypercomplex graph neural networks have a constraint that they can only carry out hypercomplex grap h convolutions in a predetermined and unchangeable dimension." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Science and Technology Development Fund of Macau SAR, Guangd ong Basic and Applied Basic Research Foundation, Key Areas Research and Developm ent Program of Guangzhou, Guangdong Provincial Key Laboratory of Cyber-Physical System. Our news editors obtained a quote from the research from the Guangdong University of Technology, "To address this limitation, this paper presents a solution to overcome this limitation by introducing the FFT-based Adaptive Fourier hypercomp lex graph convolution filtering mechanism (FAF mechanism), which can adaptively select hypercomplex graph convolutions with the most appropriate dimensions for different situations by projecting the outputs from all candidate hypercomplex g raph convolutions to the frequency domain and selecting the one with the highest energy via the FFT-based Adaptive Fourier Decomposition. Meanwhile, we apply th e FAF mechanism to our proposed hypercomplex high-order interaction graph neural network (HHG-Net), which performs high-order interaction and strengthens intera ction features through quantum graph hierarchical attention module and feature i nteraction gated graph convolution. During convolution filtering, the FAF mechan ism projects the outputs from different candidate hypercomplex graph convolution s to the frequency domain, extracts their energy, and selects the convolution th at outputs the largest energy. After that, the model with selected hypercomplex graph convolutions is trained again. Our method outperforms many benchmarks, inc luding the model with hypercomplex graph convolutions selected by DARTS, in node classification, graph classification, and text classification."

原文链接:

NETL
NSTL

New Machine Learning Study Findings Have Been Reported by Investigators at China University of Mining and Technology Beijing (Classifying Iron Ore With Water or Dust Adhesion Combining Differential Feature and Random Forest Using Hyperspect ral ...)

83-84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 Beijing, People's Republic of China, by NewsRx correspondents, research stated, "Hyperspectral im aging (HSI), a promising technique integrating imaging and spectroscopy, can hel p sort iron ores with different total iron (TFe) contents. However, the adhesion of dust (caused by crushing) or water can affect the sorting process." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Fundamental Research Funds for the Central Universities. Our news editors obtained a quote from the research from the China University of Mining and Technology Beijing, "Currently, the mechanisms underlying this influ ence and methods to conveniently mitigate it remain unclear, hindering the pract ical application of HSI-based sorting. This study aimed to investigate this issu e. For the experimental materials, 300 ore samples (particle size: 20-40 mm) wit h different TFe contents were prepared. Subsequently, three sample conditions we re prepared (‘No dust, no water', ‘With dust, no water' and ‘No dust, with water ') through washing and drying measures, and their hyperspectral images were acqu ired (953-2517 nm). Finally, the TFe content of each ore sample was measured. Af ter preprocessing, the effects of water and dust on the spectra and sorting proc ess were initially analyzed. Subsequently, a new spectral differential feature c onsidering dust and water (DFDW) was proposed to mitigate this influence. Then, using the spectral and calculated proportion features as input, different grades of iron ore were classified into four classes using a machine learning classifi er. For validation, models using several different input features and machine le arning classifiers were tested for classification accuracy (the ratio of correct ly predicted instances to the total number of predictions). On ‘No dust, no wate r', ‘With dust, no water' and ‘No dust, with water' data, the model DFDW-random forest (RF) achieved accuracies of 87.7 %, 85.0 %, and 85.3 %, respectively, which was optimal."

原文链接:

NETL
NSTL

Researchers from University of Michigan Report on Findings in Robotics (Effect o f Human Emotional Responses On Human-robot Team Pty In Construction)

84-84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 Ann Arbor, Michigan, by NewsR x journalists, research stated, "Human-robot collaboration (HRC) is expected to improve construction productivity by integrating robotic capabilities with human expertise. However, the effects of HRC on human emotions are unclear despite th eir critical impacts on human performance during HRC." Financial support for this research came from National Science Foundation (NSF). The news reporters obtained a quote from the research from the University of Mic higan, "This paper examined the inter-relationship between robots' parameters, l ike movement speed, and emotional responses, during HRC for a construction task. Eighteen participants were observed as they experience various conditions of ro bots' parameters during a bricklaying task with an arm-type collaborative robot in a laboratory setting. Their brainwaves (i.e., electroencephalogram (EEG) sign als) were monitored using an EEG headset to identify emotional responses. Result s showed significant emotional variations due to robots' parameters, which could affect the estimated productivity of human-robot teams."

原文链接:

NETL
NSTL

Reports on Computational Intelligence Findings from Anhui Normal University Prov ide New Insights (Density Peaks Clustering Based On Label Propagation and K-mutu al-nearest Neighbors)

85-85页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Machine Learning-Computational Intelligence is the subject of a report. According to news reporting originating in Anhui, People's Republic of China, by NewsRx journalists, research stated, " The density peaks clustering algorithm is one of the density-based clustering al gorithms. This algorithm has several advantages, including not requiring a prese t number of clusters, requiring fewer parameters, and being able to achieve clus tering of any shape." Funders for this research include National Natural Science Foundation of China ( NSFC), Natural Science Foundation of Anhui Province, Natural Science Research Pr oject for Universities in Anhui Province.

原文链接:

NETL
NSTL