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

    Reports Summarize Machine Learning Findings from North China Electric Power University (Machine Learning Insights In Predicting Heavy Metals Interaction With Biochar)

    85-86页
    查看更多>>摘要：Current study results on Machine Learning have been published. According to news originating from Beijing, People’s Republic of China, by NewsRx correspondents, research stated, “The use of machine learning (ML) in the field of predicting heavy metals interaction with biochar is a promising field of research, mainly because of the growing understanding of how removal efficiency is affected by characteristic variables, reaction conditions and biochar properties. The practical application in biochar still faces large challenges, such as difficulties in data collection, inadequate algorithm development, and insufficient information.” Financial support for this research came from National Natural Science Foundation of China (NSFC). Our news journalists obtained a quote from the research from North China Electric Power University, “However, the quantity, quality, and representation of data have a large impact on the accuracy, efficiency, and generalizability of machine learning tasks. From this perspective, the present data descriptors, the efficiency of machine learning-aided property and performance prediction, the interpretation of underlying mechanisms and complicated relationships, and some potential ways to augment the data are discussed regarding the interactions of heavy metals with biochar. Finally, future perspectives and challenges are discussed, and an enhanced model performance is proposed to reinforce the feasibility of a particular perspective.”
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Studies from Department of Research and Development Provide New Data on Escherichia coli (Classification of Water By Bacterial Presence Using Chemometrics Associated With Excitation-emission Matrix Fluorescence Spectroscopy)

    87-88页
    查看更多>>摘要：Investigators publish new report on Gram-Negative Bacteria - Escherichia coli. According to news reporting originating from Serra, Brazil, by NewsRx correspondents, research stated, “Bacterial presence in water is an important indicator of water quality and, when found in high concentrations, may risk human health. The detection of total coliforms, thermotolerant coliforms, and Escherichia coli (E. coli) in water through standard methods involves time-consuming and expensive laboratory tests, which may not always provide timely and accurate results.” Funders for this research include FAPES (Fundacao de Amparo a Pesquisa e Inovacao do Espirito Santo), Coordenacao de Aperfeicoamento de Pessoal de Nivel Superior (CAPES), Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPQ). Our news editors obtained a quote from the research from the Department of Research and Development, “An alternative approach is excitation-emission matrix fluorescence spectroscopy (EEMFS), which offers fast detection of bacteria in water by analyzing fluorescent compounds. Chemometrics methods can be used to process EEMF spectrum, extract the relevant information, and differentiate water samples based on the presence of bacteria using classification models. In this study, various classification algorithms were applied to EEMFS datasets, including k-nearest neighbors (k-NN), partial least squares discriminant analysis (PLS-DA), multiway-PLS (NPLS-DA), principal component analysis with discriminant analysis (PCA-DA), support vector machines (SVM), and random forest (RF). Models were developed after the unfold multiway and parallel factor analysis (PARAFAC) to classify groundwater, freshwater, saltwater, and treated water samples according to the presence of E. coli, thermotolerant coliforms, and total coliforms. Among these models, PLS-DA, SVM, and RF demonstrated superior performance in discriminating the samples in most cases. In the test sets, the accuracy of the best models for total coliforms varied from 85.2% to 100% for groundwater, 71.4% to 98.2% for freshwater, 64.6% to 81.3% for treated water, and 65.8% to 71.1% for saltwater. Accuracy for E. coli and thermotolerant coliforms ranged from 89.3% to 100% in groundwater and from 64.7% to 87.5% for treated water.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Reports from University of Colorado Denver Add New Data to Findings in Machine Learning (Inverse Design of Multi-material Gyroid Structures Made By Additive Manufacturing)

    88-89页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting out of Denver, Colorado, by NewsRx editors, research stated, “Additively manufactured gyroid structures have great potential in lightweight structure design, energy absorption, heat transfer, and biomedical applications. The optimization and design of the relative density of gyroid structures have been studied for a decade but mainly focusing on a single material phase.” Financial support for this research came from College of Engineering, Design and Computing, University of Colorado Denver. Our news journalists obtained a quote from the research from the University of Colorado Denver, “Multi-material Additive Manufacturing brought out the material complexity in structures, which extended the design parameter for gyroid structures from relative density to material distribution. In this research, a data-driven inverse design model was developed for multi-material gyroid structures using machine learning. The structures were fabricated by the material extrusion process with a combination of PLA and TPU materials. The mechanical properties of these structures were studied by compression tests and polynomial interpolations. It was found that the interpolation method can accurately indicate the relationship between relative density, material ratio, and mechanical properties. The interpolation functions were used to randomly generate the training data for machine learning. A well-trained neural network model was developed to find the inverse relationship between the mechanical properties and the design parameters. It is used in the design process to determine the relative density and PLA/TPU ratio by the elastic modulus, energy absorption, and peak stress. Subsequent validation experiments verified the efficacy of the proposed design model, demonstrating its ability to accurately predict the desired properties using the machine learning framework.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Researchers from Academy of Sciences of the Czech Republic Report New Studies and Findings in the Area of Robotics (Long Term Follow-up Coverage of Gaia Photometric Alert Sources By Ondrejov Robotic Telescopes)

    89-90页
    查看更多>>摘要：A new study on Robotics is now available. According to news reporting from Ondrejov, Czech Republic, by NewsRx journalists, research stated, “The robotic telescopes at the Ondrejov Observatory are providing long-term optical multi-color coverage for selected 25 Gaia alert triggers located in the northern sky hemisphere. I will present and briefly discuss examples of selected results, mostly unpublished, obtained with these devices.” Funders for this research include Horizon 2020, Netherlands Enterprise Agency (RVO). The news correspondents obtained a quote from the research from the Academy of Sciences of the Czech Republic, “In addition to that, I will present and discuss the potential of large historical photographic plate archives located around the globe as sources of both photometric as well as spectroscopic data. They allow us to perform the long-term study of photometric and spectroscopic evolution for astrophysical sources in general and for Gaia alert sources in particular.” According to the news reporters, the research concluded: “Some of these databases were digitized and on-line access is provided.”
      原文链接:
    • NETL
    • NSTL
    • Slovak Academy Sciences Astronomical Inst

    Findings from South China University of Technology in the Area of Robotics Described (One-shot Sim-to-real Transfer Policy for Robotic Assembly Via Reinforcement Learning With Visual Demonstration)

    90-91页
    查看更多>>摘要：Research findings on Robotics are discussed in a new report. According to news originating from Guangzhou, People’s Republic of China, by NewsRx correspondents, research stated, “Reinforcement learning (RL) has been successfully applied to a wealth of robot manipulation tasks and continuous control problems. However, it is still limited to industrial applications and suffers from three major challenges: sample inefficiency, real data collection, and the gap between simulator and reality.” Financial supporters for this research include National Natural Science Foundation of China (NSFC), Guangdong Basic and Applied Basic Research Foundation, Industrial Key Technologies R&D Program of Foshan.
      原文链接:
    • NETL
    • NSTL
    • Cambridge Univ Press

    ImpriMed Inc. Researchers Update Current Data on Machine Learning (Multimodal machine learning models identify chemotherapy drugs with prospective clinical efficacy in dogs with relapsed B-cell lymphoma)

    90-90页
    查看更多>>摘要：Investigators publish new report on artificial intelligence. According to news originating from Mountain View, California, by NewsRx correspondents, research stated, “Dogs with B-cell lymphoma typically respond well to first-line CHOP-based chemotherapy, but there is no standard of care for relapsed patients.” The news editors obtained a quote from the research from ImpriMed Inc.: “To help veterinary oncologists select effective drugs for dogs with lymphoid malignancies such as B-cell lymphoma, we have developed multimodal machine learning models that integrate data from multiple tumor profiling modalities and predict the likelihood of a positive clinical response for 10 commonly used chemotherapy drugs. Here we report on clinical outcomes that occurred after oncologists received a prediction report generated by our models.”
      原文链接:
    • NETL
    • NSTL
    • Frontiers Media Sa

    Data on Machine Learning Discussed by Researchers at Qingdao University of Technology (Quantification of the Concrete Freezethaw Environment Across the Qinghai-tibet Plateau Based On Machine Learning Algorithms)

    91-92页
    查看更多>>摘要：Data detailed on Machine Learning have been presented. According to news reporting out of Qingdao, People’s Republic of China, by NewsRx editors, research stated, “The reasonable quantification of the concrete freezing environment on the Qinghai-Tibet Plateau (QTP) is the primary issue in frost resistant concrete design, which is one of the challenges that the QTP engineering managers should take into account. In this paper, we propose a more realistic method to calculate the number of concrete freeze-thaw cycles (NFTCs) on the QTP.” Funders for this research include Natural Science Foundation of Shandong Province, Key Research and Development Project in Shandong Province, Project for excellent youth foundation of the innovation teacher team, Shandong. Our news journalists obtained a quote from the research from the Qingdao University of Technology, “The calculated results show that the NFTCs increase as the altitude of the meteorological station increases with the average NFTCs being 208.7. Four machine learning methods, i.e., the random forest (RF) model, generalized boosting method (GBM), generalized linear model (GLM), and generalized additive model (GAM), are used to fit the NFTCs. The root mean square error (RMSE) values of the RF, GBM, GLM, and GAM are 32.3, 4.3, 247.9, and 161.3, respectively. The R2 values of the RF, GBM, GLM, and GAM are 0.93, 0.99, 0.48, and 0.66, respectively. The GBM method performs the best compared to the other three methods, which was shown by the results of RMSE and R2 values. The quantitative results from the GBM method indicate that the lowest, medium, and highest NFTC values are distributed in the northern, central, and southern parts of the QTP, respectively. The annual NFTCs in the QTP region are mainly concentrated at 160 and above, and the average NFTCs is 200 across the QTP.”
      原文链接:
    • NETL
    • NSTL
    • Science Press

    Studies from University of Illinois Urbana-Champaign Describe New Findings in Robotics (Ad Hoc Mesh Network Localization Using Ultra-Wideband for Mobile Robotics)

    92-93页
    查看更多>>摘要：Investigators discuss new findings in robotics. According to news originating from Urbana, Illinois, by NewsRx editors, the research stated, “This article explores the implementation of high-accuracy GPS-denied ad hoc localization.” Our news editors obtained a quote from the research from University of Illinois Urbana-Champaign: “Little research exists on ad hoc ultra-wideband-enabled localization systems with mobile and stationary nodes. This work aims to demonstrate the localization of bicycle-modeled robots in a non-static environment through a mesh network of mobile, stationary robots, and ultra-wideband sensors. The non-static environment adds a layer of complexity when actors can enter and exit the node’s field of view. The method starts with an initial localization step where each unmanned ground vehicle (UGV) uses the surrounding, available anchors to derive an initial local or, if possible, global position estimate. The initial localization uses a simplified implementation of the iterative multi-iteration ad hoc localization system (AHLos). This estimate was refined using an unscented Kalman filter (UKF) following a constant turn rate and velocity magnitude model (CTRV).”
      原文链接:
    • NETL
    • NSTL
    • Mdpi

    First Affiliated Hospital of Dalian Medical University Reports Findings in Artificial Intelligence (Artificial intelligence technology improves the accuracy of preoperative planning in primary total hip arthroplasty)

    93-94页
    查看更多>>摘要：New research on Artificial Intelligence is the subject of a report. According to news reporting out of Dalian, People’s Republic of China, by NewsRx editors, research stated, “Successful total hip arthroplasty relies on accurate preoperative planning. However, the conventional preoperative planning, a two-dimensional method using X-ray template, has shown poor reliability of predicting component size.” Our news journalists obtained a quote from the research from the First Affiliated Hospital of Dalian Medical University, “To our knowledge, artificial intelligence technology assisted three-dimensional preoperative planning is promising to improve the accuracy of preoperative planning but there is a dearth of clinical evidence. Therefore, in this study we compared the prediction accuracy of these two maneuvers. We conducted a prospective study consisting of 117 consecutive patients who underwent a primary cementless total hip arthroplasty to compare the prediction accuracy of these two methods. The twodimensional and artificial intelligence assisted three-dimensional planning results of the same patient were compared with the definitive implant size respectively. The prediction accuracy of artificial intelligence assisted three-dimensional planning for cup and the stem sizes were 66.67% (78/117) and 65.81% (77/117), two-dimensional planning was 30.77% (36/117) and 37.61% (44/117) (p ＜0.05). There were poor prediction results of two-dimensional planning in patients with hip dysplasia (p = 0.004, OR = 7.143) and excessive femoral anteversion (p = 0.012, OR = 1.052), meanwhile the failure risk of stem side twodimensional planning increased as patients got older (p = 0.003, OR = 1.118). The accuracy of artificial intelligence assisted three-dimensional planning cannot be affected by above factors. We confirmed that artificial intelligence assisted three-dimensional preoperative planning showed higher accuracy and stability than two-dimensional preoperative planning in primary cementless total hip arthroplasty.”
      原文链接:
    • NETL
    • NSTL

    Data from Portland State University Advance Knowledge in Machine Learning (Identification of Solder Joint Failure Modes Using Machine Learning)

    94-95页
    查看更多>>摘要：Investigators publish new report on Machine Learning. According to news originating from Portland, Oregon, by NewsRx correspondents, research stated, “The reliability of solder joints is one of the most critical factors that determine the lifecycle of electronic devices, and the identification of solder joint failure modes is necessary to enhance the performance and durability of electronic devices. In this study, solder joint failure modes were identified using the fine-tuned visual geometry group 19 (VGG 19) pretrained model.” Financial support for this research came from Ministry of Trade, Industry, and Energy (MOTIE) in South Korea, through the Fostering Global Talents for Innovative Growth Program supervised by the Korea Institute for Advancement of Technology (KIAT). Our news journalists obtained a quote from the research from Portland State University, “Raw images (57 images) were augmented into 428 images by sectioning to classify the solder joint failure mode into two classes (good or not-good mode) for the binary classification model, and 265 not-good data points obtained from the binary classification were employed as input to classify solder joint failure mode into six classes (failure modes 1-6) for the multiclass classification model. The binary and multiclass classification models were trained and validated, achieving 99% accuracy. The binary model classified shadows and small voids as defects, identifying the failure mode as ‘not-good.’ The multiclass model occasionally misclassified the failure modes due to the multiple modes or difficulty in classification. The trained binary and multiclass classification models were further verified using 102 and 64 third-party experimental data points, respectively, confirming 100% accuracy.”
      原文链接:
    • NETL
    • NSTL
    • IEEE