期刊,Robotics & Machine Learning Daily News 2024年卷Jun.26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

Shenyang Sport University Reports Findings in Compression Fractures (Effects of robot-assisted percutaneous kyphoplasty on osteoporotic vertebral compression fr actures: a systematic review and meta-analysis)

11-11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 Compression Fractures is the subject of a report. According to news originating from Shenyang, People' s Republic of China, by NewsRx correspondents, research stated, "This study syst emically reviewed the effects of robot-assisted percutaneous kyphoplasty (R-PKP) on the clinical outcomes and complications of patients with osteoporotic verteb ral compression fracture (OVCF). The articles published from the establishment o f the database to 19 April 2024 were searched in PubMed, The Cochrane Library, W eb of Science, Embase, Scopus, China National Knowledge Infrastructure (CNKI), a nd Chinese biomedical literature service system (SinoMed)." Our news journalists obtained a quote from the research from Shenyang Sport Univ ersity, "Metaanalysis was employed to evaluate the status of pain relief and co mplications between the control and R-PKP groups. Standardized mean difference ( SMD) or mean difference (MD), risk ratios (RR), and 95% confidence interval (CI) were selected for analysis, and a common or random effect model w as adopted to merge the data. Eight studies involving 773 patients with OCVFs we re included. R-PKP could effectively Cobb's angles (MD = -1.00, 95% CI -1.68 to -0.33, P = 0.0034), and decrease the occurrence of cement leakage (R R = 0.36, 95% CI 0.21 to 0.60, P<0.0001). Ho wever, there was no significant effect on the results of visual analog scale (MD = -0.09, 95% CI -0.20 to 0.02, P = 0.1145), fluoroscopic frequenc y (SMD = 5.31, 95% CI -7.24 to 17.86, P = 0.4072), and operation t ime (MD = -0.72, 95% CI -7.47 to 6.03, P = 0.8342). R-PKP could si gnificantly correct vertebral angle and reduce cement leakage."

原文链接:

NETL
NSTL

Data on Machine Learning Discussed by Researchers at University of Science and T echnology of China (Size dependent lithium-ion conductivity of solid electrolyte s in machine learning molecular dynamics simulations)

12-12页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New study results on artificial intelligence have been published. According to news reporting originating from Anhui, People's Re public of China, by NewsRx correspondents, research stated, "Solidstate electro lytes are key ingredients in next-generation devices for energy storage and rele ase." Funders for this research include National Natural Science Foundation of China; Chinese Academy of Sciences. The news correspondents obtained a quote from the research from University of Sc ience and Technology of China: "Machine learning molecular dynamics (MLMD) has s hown great promise in studying the diffusivity of mobile ions in solid-state ele ctrolytes, with much higher efficiency than conventional ab initio molecular dyn amics (AIMD). In this work, we combine an efficient embedded atom neural network (EANN) approach and an uncertainty-driven active learning algorithm that optima lly selects data points from high-temperature AIMD trajectories to construct ML potentials for solid-state electrolytes and validate this strategy in a benchmar k system, Li3YCl6, for which several controversy theoretical results exist. Thro ugh systematic MLMD simulations, we find that a typically used small supercell i n AIMD simulations fails to predict the supersonic transition at a critical temp erature, leading to a significant overestimation of the Li+ conductivity in Li3Y Cl6 at room temperature. Fortunately, thanks to the scalability of the EANN pote ntial, extended MLMD simulations in a sufficiently large cell does yield a notab le change of temperature-dependence in conductivity at 420 K and a much lower ro om-temperature conductivity in excellent with experiment. Interestingly, our res ults are all based on a semi-local PBE density functional, which was argued unab le to predict the superionic transition. We analyze possible reasons of the seem ingly inconsistent MLMD results reported in literature with different ML potenti als."

原文链接:

NETL
NSTL

Data on Robotics Reported by Researchers at York University (Visual Control for Robotic 3d Printing On a Moving Platform)

13-13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 Robotics are disc ussed in a new report. According to news reporting from Toronto, Canada, by News Rx journalists, research stated, "In recent years, there has been significant pr ogress in developing specialized 3D printing techniques that cater to various de manding applications. However, the current state of this technology is challenge d when it comes to complex in situ printing scenarios, which require a controlle d printing platform." Financial support for this research came from Natural Sciences and Engineering R esearch Council of Canada (NSERC). The news correspondents obtained a quote from the research from York University, "The lack of a stable printing platform is a fundamental limitation of its use in in situ applications. To address this issue, we present a novel platform-inde pendent 3D fabrication process that enables printing on platforms with non-coope rative movement. The process overcomes the challenge of high-speed tracking, mot ion compensation, and real-time printing by developing a closed-loop visual feed back-controlled robotic printing process. The proposed process incorporates a ma rker-based visual detection and tracking controller setup, which is discussed in detail. The algorithm consists of two loops running asynchronously: a high-spee d inner control loop and an outer measurement loop. This setup enables precise a nd accurate tracking of the printing platform, compensating for any disturbances during the printing process. Our experimental results demonstrate the successfu l printing of simple linear geometries, even with low-disturbing platform veloci ties. Moreover, the tracking controllers' ability to handle measurement occlusio n is validated, showing the proposed process's robustness and effectiveness."

原文链接:

NETL
NSTL

Hospital for Special Surgery Reports Findings in Robotics (Levelspecific Compar ison of 3D Navigated and Robotic Arm-Guided Screw Placement: An Accuracy Assessm ent of 1210 Pedicle Screws in Lumbar Surgery)

14-15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 reporting from New York City, New York, by News Rx journalists, research stated, "Robotic spine surgery, utilizing 3D imaging an d robotic arms, has been shown to improve the accuracy of pedicle screw placemen t compared to conventional methods, although its superiority remains under debat e. There are few studies evaluating the accuracy of 3D navigated versus robotic- guided screw placement across lumbar levels, addressing anatomical challenges to refine surgical strategies and patient safety." The news correspondents obtained a quote from the research from Hospital for Spe cial Surgery, "This study aims to investigate the pedicle screw placement accura cy between 3D navigation and robotic arm-guided systems across distinct lumbar l evels. A retrospective review of a prospectively collected registry SAMPLE: Pati ents undergoing fusion surgery with pedicle screw placement in the prone positio n, using either via 3D image navigation only or robotic arm guidance MEASURES: R adiographical screw accuracy was assessed by the postoperative computed tomograp hy (CT) according to the Gertzbein- Robbins classification, particularly focused on accuracy at different lumbar levels. Accuracy of screw placement in the 3D na vigation (Nav group) and robotic arm guidance (Robo group) was compared using Ch i-squared test/Fisher's exact test with effect size measured by Cramer's V, both overall and at each specific lumbosacral spinal level. A total of 321 patients were included (Nav, 157; Robo, 189) and evaluated 1210 screws (Nav, 651; Robo 55 9). The Robo group demonstrated significantly higher overall accuracy (98.6 vs. 93.9%; P<0.001, V=0.25). This difference of no breach screw rate was signified the most at the L3 level (No breach screw: Robo 91.3 vs. 57.8%, P<0.001, V=0.35) followed by L4 (89.6 vs. 64.7%, P<0.001, V=0.28), and L5 ( 92.0 vs. 74.5%, P<0.001, V=0.22). However, scr ew accuracy at S1 was not significant between the groups (81.1 vs. 72.0% , V=0.10). This study highlights the enhanced accuracy of robotic arm-guided sys tems compared to 3D navigation for pedicle screw placement in lumbar fusion surg eries, especially at the L3, L4, and L5 levels."

原文链接:

NETL
NSTL

Findings from National Institute of Technology Raipur in the Area of Parkinson's Disease Described (An Ensemble Technique To Predict Parkinson's Disease Using M achine Learning Algorithms)

15-16页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Neurodegenerative Diseases and Co nditions-Parkinson's Disease is the subject of a report. According to news rep orting originating from Chhattisgarh, India, by NewsRx correspondents, research stated, "Parkinson's Disease (PD) is a progressive neurodegenerative disorder af fecting motor and non-motor symptoms. Its symptoms develop slowly, making early identification difficult." Our news editors obtained a quote from the research from the National Institute of Technology Raipur, "Machine learning has a significant potential to predict P arkinson's disease on features hidden in voice data. This work aimed to identify the most relevant features from a high-dimensional dataset, which helps accurat ely classify Parkinson's Disease with less computation time. Three individual da tasets with various medical features based on voice have been analyzed in this w ork. An Ensemble Feature Selection Algorithm (EFSA) technique based on filter, w rapper, and embedding algorithms that pick highly relevant features for identify ing Parkinson's Disease is proposed, and the same has been validated on three di fferent datasets based on voice. These techniques can shorten training time to i mprove model accuracy and minimize overfitting. We utilized different ML models such as K-Nearest Neighbors (KNN), Random Forest, Decision Tree, Support Vector Machine (SVM), Bagging Classifier, Multi-Layer Perceptron (MLP) Classifier, and Gradient Boosting. Each of these models was fine-tuned to ensure optimal perform ance within our specific context. Moreover, in addition to these established cla ssifiers, we proposed an ensemble classifier is found on a high optimal majority of the votes. Dataset-I achieves classification accuracy with 97.6 % , F1-score 97.9 %, precision with 98 % and recall wit h 98 %. Dataset-II achieves classification accuracy 90.2 % , F1-score 90.2 %, precision 90.2 %, and recall 90.5 % . Dataset-III achieves 83.3 % accuracy, F1-score 83.3 % , precision 83.5 % and recall 83.3 %. These results h ave been taken using 13 out of 23, 45 out of 754, and 17 out of 46 features from respective datasets."

原文链接:

NETL
NSTL

New Machine Learning Findings from CEA Described (Application of Machine Learnin g To Micado Passive and Active Neutron Measurement System for the Characterizati on of Radioactive Waste Drums)

16-17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 Ma chine Learning. According to news originating from St. Paul les Durance, France, by NewsRx correspondents, research stated, "A passive and active neutron measur ement system has been developed within the Measurement and Instrumentation for C leaning and Decommissioning Operation (MICADO) H2020 project to estimate the nuc lear material mass inside legacy waste drums of low and intermediate radioactivi ty levels. Monte-Carlo simulations were performed to design a transportable neut ron system allowing both passive neutron coincidence counting and active interro gation with the differential die-away technique (DDT)." Financial support for this research came from Horizon 2020. Our news journalists obtained a quote from the research from CEA, "However, the calibration coefficients (CCs) representing the signal of interest (due to nucle ar material) in these two measurement modes may vary by a large amount depending on the properties of the matrix of the nuclear waste drum. Therefore, this arti cle investigates matrix effects based on 104 Monte-Carlo calculations with diffe rent waste drums, based on Taguchi experimental design with a range of densities , material compositions, filling levels, and nuclear material masses. A matrix c orrection method is studied using machine learning algorithms. The matrix effect on the neutron signal is deduced from the signal of internal neutron monitors l ocated inside the measurement cavity and from a transmission measurement with an AmBe neutron source. Those quantities can be assessed experimentally and are us ed as explanatory variables for the definition of a predictive model of the simu lated CC, either in passive or in active mode. A multilinear regression model of the CC based on ordinary least square (OLS) is built and compared to the random forest (RF) machine-learning algorithm and to the multilayer perceptron (MLP) a rtificial neural network. In passive neutron coincidence counting, the residual error of the regression is lower for the MLP and RF than for OLS. The agreement between the predicted CCs of four mockup drums used as test is better than 17% and 3%, respectively, with the MLP and RF methods, while three pred ictions are out of the 95 % confidence level range with OLS. In act ive neutron interrogation, similar conclusions are drawn. The prediction of the CC for the four mockup drums is better than 12%, 35%, and 72% for the respective MLP, RF, and OLS methods."

原文链接:

NETL
NSTL

Chinese Academy of Sciences Reports Findings in Machine Learning (Predicting the onset of overweight in Chinese high school students: a machine-learning approac h in a one-year prospective cohort study)

17-18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 Machine Learning is th e subject of a report. According to news reporting out of Hefei, People's Republ ic of China, by NewsRx editors, research stated, "This study aimed to develop an d evaluate machine-learning models for predicting the onset of overweight in ado lescents aged 14-17, utilizing easily collectible personal information. This stu dy was a one-year prospective cohort study." Our news journalists obtained a quote from the research from the Chinese Academy of Sciences, "Baseline data were collected through anthropometric measurements and questionnaires, and the incidence of overweight was calculated one year late r via anthropometric measurements. Predictive factors were selected through univ ariate analysis. Six machine-learning models were developed for predicting the o nset of overweight. The SHapley Additive exPlanations (SHAP) was used for global and local interpretation of the models. Out of 1,241 adolescents, 204 (16.4% ) were identified as overweight after one year. Nineteen features were associate d with the overweight incidence in univariable analysis. Participants were rando mly divided into a training group and a testing group in a 7:3 ratio. The Light Gradient Boosting Machine (LGBM) algorithm achieved outperformed other models, a chieving the following metrics: Accuracy (0.956), Recall (0.812), Specificity (0 .983), F1-score (0.855), AUC (0.961). Importance ranking revealed that the top 1 1 minimal feature set can maintain the stability of model performance. The onset of overweight in adolescents was accurately predicted using easily collectible personal information. The LGBM-based model exhibited superior performance. Overs ampling technique notably improved model performance."

原文链接:

NETL
NSTL

Researchers from East China Normal University Detail Findings in Machine Learnin g (Dpsur: Accelerating Differentially Private Stochastic Gradient Descent Using Selective Update and Release)

18-19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 from Shanghai, People's Republic o f China, by NewsRx journalists, research stated, "Machine learning models are kn own to memorize private data to reduce their training loss, which can be inadver tently exploited by privacy attacks such as model inversion and membership infer ence. To protect against these attacks, differential privacy (DP) has become the de facto standard for privacy-preserving machine learning, particularly those p opular training algorithms using stochastic gradient descent, such as DPSGD." Funders for this research include Natural Science Foundation of Shanghai, Nation al Natural Science Foundation of China (NSFC), National Natural Science Foundati on of China (NSFC), Hong Kong Research Grants Council, CAAI-Huawei MindSpore Ope n Fund. The news correspondents obtained a quote from the research from East China Norma l University, "Nonetheless, DPSGD still suffers from severe utility loss due to its slow convergence. This is partially caused by the random sampling, which bri ngs bias and variance to the gradient, and partially by the Gaussian noise, whic h leads to fluctuation of gradient updates. Our key idea to address these issues is to apply selective updates to the model training, while discarding those use less or even harmful updates. Motivated by this, this paper proposes DPSUR, a Di fferentially Private training framework based on Selective Updates and Release, where the gradient from each iteration is evaluated based on a validation test, and only those updates leading to convergence are applied to the model. As such, DPSUR ensures the training in the right direction and thus can achieve faster c onvergence than DPSGD. The main challenges lie in two aspects-privacy concerns arising from gradient evaluation, and gradient selection strategy for model upd ate. To address the challenges, DPSUR introduces a clipping strategy for update randomization and a threshold mechanism for gradient selection."

原文链接:

NETL
NSTL

Gannan Normal University Reports Findings in Machine Learning (A deep learning m odel for DNA enhancer prediction based on nucleotide position aware feature enco ding)

19-19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 Machine Learning is th e subject of a report. According to news reporting originating in Jiangxi, Peopl e's Republic of China, by NewsRx journalists, research stated, "Enhancers, genom ic DNA elements, regulate neighboring gene expression crucial for biological pro cesses like cell differentiation and stress response. However, current machine l earning methods for predicting DNA enhancers often underutilize hidden features in gene sequences, limiting model accuracy." The news reporters obtained a quote from the research from Gannan Normal Univers ity, "Hence, this article proposes the PDCNN model, a deep learning-based enhanc er prediction method. PDCNN extracts statistical nucleotide representations from gene sequences, discerning positional distribution information of nucleotides i n modifier-like DNA sequences. With a convolutional neural network structure, PD CNN employs dual convolutional and fully connected layers. The cross-entropy los s function iteratively updates using a gradient descent algorithm, enhancing pre diction accuracy. Model parameters are fine-tuned to select optimal combinations for training, achieving over 95% accuracy. Comparative analysis w ith traditional methods and existing models demonstrates PDCNN's robust feature extraction capability."

原文链接:

NETL
NSTL

Hebei University of Technology Reports Findings in Machine Learning (Machine Lea rning Assisted Electronic/Ionic Skin Recognition of Thermal Stimuli and Mechanic al Deformation for Soft Robots)

20-20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 Machine Learning is th e subject of a report. According to news reporting from Tianjin, People's Republ ic of China, by NewsRx journalists, research stated, "Soft robots have the advan tage of adaptability and flexibility in various scenarios and tasks due to their inherent flexibility and mouldability, which makes them highly promising for re al-world applications. The development of electronic skin (E-skin) perception sy stems is crucial for the advancement of soft robots." Financial support for this research came from Natural Science Foundation of Chon gqing Municipality. The news correspondents obtained a quote from the research from the Hebei Univer sity of Technology, "However, achieving both exteroceptive and proprioceptive ca pabilities in E-skins, particularly in terms of decoupling and classifying sensi ng signals, remains a challenge. This study presents an E-skin with mixed electr onic and ionic conductivity that can simultaneously achieve exteroceptive and pr oprioceptive, based on the resistance response of conductive hydrogels. It is in tegrated with soft robots to enable state perception, with the sensed signals fu rther decoded using the machine learning model of decision trees and random fore st algorithms. The results demonstrate that the newly developed hydrogel sensing system can accurately predict attitude changes in soft robots when subjected to varying degrees of pressing, hot pressing, bending, twisting, and stretching."

原文链接:

NETL
NSTL