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

    Researcher at New York University (NYU) Zeroes in on Machine Learning (Physics-I nformed Machine Learning for Calibrating Macroscopic Traffic Flow Models)

    30-30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 ar tificial intelligence. According to news reporting originating from New York Uni versity (NYU) by NewsRx correspondents, research stated, “Well-calibrated traffi c flow models are fundamental to understanding traffic phenomena and designing c ontrol strategies.” The news reporters obtained a quote from the research from New York University ( NYU): “Traditional calibration has been developed based on optimization methods. In this paper, we propose a novel physicsinformed, learning-based calibration approach that achieves performances comparable to and even better than those of optimization-based methods. To this end, we combine the classical deep autoencod er, an unsupervised machine learning model consisting of one encoder and one dec oder, with traffic flow models. Our approach informs the decoder of the physical traffic flow models and thus induces the encoder to yield reasonable traffic pa rameters given flow and speed measurements. We also introduce the denoising auto encoder into our method so that it can handle not only with normal data but also corrupted data with missing values. We verified our approach with a case study of Interstate 210 Eastbound in California.”
      原文链接:
    • NETL
    • NSTL

    German Sport University Cologne Reports Findings in Machine Learning (Composite activity type and stride-specific energy expenditure estimation model for thigh- worn accelerometry)

    31-32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 from Cologne, Ger many, by NewsRx correspondents, research stated, “Accurately measuring energy ex penditure during physical activity outside of the laboratory is challenging, esp ecially on a large scale. Thigh-worn accelerometers have gained popularity due t o the possibility to accurately detect physical activity types.” Financial support for this research came from Deutsche Sporthochschule Koln (DSH S).
      原文链接:
    • NETL
    • NSTL

    Researcher at University of Utah Reports Research in Robotics (Proximal Joint Co mpliance as a Passive Method for Ground Reaction Force Redirection During Legged Locomotion)

    31-31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 robotics have been pr esented. According to news reporting from the University of Utah by NewsRx journ alists, research stated, “Ground reaction forces (GRFs) are a critical component of legged locomotion, and controlling their direction leads to more stable, eff icient, and robust performance.” Our news correspondents obtained a quote from the research from University of Ut ah: “The novelty of this work is to studying passive proximal joint (hips/should ers) compliance for the purpose of redirecting the GRF passively. Previous works have redirected the GRF actively or studied passive proximal joint compliance f or purposes such as swing phase efficiency, but passive methods of stance-phase GRF redirection are under-developed. This paper analyzes the relationship betwee n hip compliance and the GRF direction analytically and with simulations of a tr otting quadruped. The results show increased GRF redirection, on average, with i ncreased joint stiffness, for a range of cases. An example method of utilizing t his relationship to improve locomotion performance is presented by simulating on line compliance adaptation. By adapting the compliance parameter during locomoti on, the cost of locomotion was reduced toward the known minimum within the param eter space explored.”
      原文链接:
    • NETL
    • NSTL

    Data on Robotics Published by a Researcher at University of Salento (An Innovati ve Vision-Guided Feeding System for Robotic Picking of Different-Shaped Industri al Components Randomly Arranged)

    32-33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 out of Lecce, Italy, by NewsRx editors, rese arch stated, “Within an industrial plant, the handling of randomly arranged obje cts is becoming increasingly popular.” The news correspondents obtained a quote from the research from University of Sa lento: “The technology industry has introduced ever more powerful devices to the market, but they are often unable to meet the demands of the industry in terms of processing times. Using a multi-component feeder, which facilitates the autom atic picking of objects arranged in bulk, is the ideal element to speed up the i dentification of objects by the vision system. The innovative designed feeder el iminates the dead time of the vision system since the feeder has two working sur faces, thus making the viewing time hidden in relation to the total handling cyc le time. In addition, the step feeder integrated into the feeder structure allow s for control over the number of objects that fall onto the work surface, optimi zing the material flow. The feeder was designed to palletize aluminum hinge fins but can also handle other products with different shapes and sizes.”
      原文链接:
    • NETL
    • NSTL

    Study Findings on Machine Learning Detailed by Researchers at Vellore Institute of Technology (Brake fault diagnosis using a voting ensemble of machine learning classifiers)

    33-34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 artificial intelligence. According to news reporting out of Chennai, India, by N ewsRx editors, research stated, “Brake fault diagnosis is a crucial aspect of en hancing driving safety, as various faults such as air in brake fluid, brake oil spill, reservoir leak, mechanical fade and distinct types of brake pad wear can compromise vehicle safety. This study presents a method for timely fault detecti on by analyzing vibration signals.” The news reporters obtained a quote from the research from Vellore Institute of Technology: “Vibration signals for normal and faulty conditions were captured us ing a hydraulic brake test setup equipped with a piezoelectric transducer and da ta acquisition system. Feature extraction was performed using an autoregressive moving average (ARMA) model. The performance of five different classifiers name ly, random forest (RF), Naive Bayes (NB), instance-based k-nearest neighbours (I Bk), logistic model trees (LMT) and J48 decision tree was evaluated. The LMT cla ssifier achieved the highest accuracy at 95.00 % followed by IBk, RF, J48 and NB with accuracies of 92.00 %, 90.00 %, 90 .00 % and 87.00 %. To further improve the diagnosis a ccuracy, a voting-based ensemble approach was employed by combining two, three, four and five classifiers with the application of five different voting strategi es. The results obtained showcase that a combination of three classifiers LMT, I Bk and NB utilizing the majority voting rule yielded an enhanced classification accuracy of 98.00 % highlighting the effectiveness of this ensembl e method in brake fault diagnosis.”
      原文链接:
    • NETL
    • NSTL

    Researchers from South China Agricultural University Detail New Studies and Find ings in the Area of Support Vector Machines (A Newly Early Warning Model for Ana erobic Digestion Systems: Based On an Improved Sparrow Search Algorithm Combined ...)

    34-35页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Research findings on Support Vector Machines are discussed in a new report. According to news reporting from Guangzhou, People’s Republic of China, by NewsRx journalists, research stated, “Anaerobic digestion as an important means of organic waste treatment will play a key role in the rea lization of ecological civilization and the goal of double carbon. However, the instability of the system due to the high sensitivity to operating conditions re stricts the economy and sustainability of the current commercial biogas projects in China.” Funders for this research include National Key Research & Developm ent Program of China, Guangdong Key Construction Discipline Research Capacity En hance-ment Project.
      原文链接:
    • NETL
    • NSTL

    Investigators from University of Naples Federico II Report New Data on Artificia l Intelligence (Evaluating Explainable Artificial Intelligence Tools for Hard Di sk Drive Predictive Maintenance)

    35-36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 Artificial Intelligence. According to news reporting originating from Naples, It aly, by NewsRx correspondents, research stated, “In the last years, one of the m ain challenges in Industry 4.0 concerns maintenance operations optimization, whi ch has been widely dealt with several predictive maintenance frameworks aiming t o jointly reduce maintenance costs and downtime intervals. Nevertheless, the mos t recent and effective frameworks mainly rely on deep learning models, but their internal representations (black box) are too complex for human understanding ma king difficult explain their predictions.” Our news editors obtained a quote from the research from the University of Naple s Federico II, “This issue can be challenged by using eXplainable artificial int elligence (XAI) methodologies, the aim of which is to explain the decisions of d ata-driven AI models, characterizing the strengths and weaknesses of the decisio n-making process by making results more understandable by humans. In this paper, we focus on explanation of the predictions made by a recurrent neural networks based model, which requires a treedimensional dataset because it exploits spati al and temporal features for estimating remaining useful life (RUL) of hard disk drives (HDDs). In particular, we have analyzed in depth as explanations about R UL prediction provided by different XAI tools, compared using different metrics and showing the generated dashboards, can be really useful for supporting predic tive maintenance task by means of both global and local explanations. For this a im, we have realized an explanation framework able to investigate local interpre table model-agnostic explanations (LIME) and SHapley Additive exPlanations (SHAP ) tools w.r.t. to the Backblaze Dataset and a long short-term memory (LSTM) pred iction model.”
      原文链接:
    • NETL
    • NSTL

    People’s Hospital of Longhua Reports Findings in Stroke (Advanced Machine Learni ng Models for Predicting Post-Thrombolysis Hemorrhagic Transformation in Acute I schemic Stroke Patients: A Systematic Review and Meta-Analysis)

    36-37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 Cerebrovascular Diseas es and Conditions - Stroke is the subject of a report. According to news reporti ng originating from Shenzhen, People’s Republic of China, by NewsRx corresponden ts, research stated, “Thrombolytic therapy is essential for acute ischemic strok e (AIS) management but poses a risk of hemorrhagic transformation (HT), necessit ating accurate prediction to optimize patient care. A comprehensive search was c onducted across PubMed, Web of Science, Scopus, Embase, and Google Scholar, cove ring studies from inception until July 10, 2024.” Our news editors obtained a quote from the research from the People’s Hospital o f Longhua, “Studies were included if they used machine learning (ML) or deep lea rning algorithms to predict HT in AIS patients treated with thrombolysis. Exclus ion criteria included studies involving endovascular treatments and those not ev aluating model effectiveness. Data extraction and quality assessment were perfor med following PRISMA guidelines and using the Transparent Reporting of a Multiva riable Prediction Model for Individual Prognosis or Diagnosis (TRIPOD) and Predi ction Model Risk of Bias Assessment Tool (PROBAST) tools. Out of 1943 identified records, 12 studies were included in the final analysis, encompassing 18 007 AI S patients who received thrombolytic therapy. The ML models demonstrated high pr edictive performance, with pooled area under the curve (AUC) values ranging from 0.79 to 0.95. Specifically, XGBoost models achieved AUCs of up to 0.953 and Art ificial Neural Network (ANN) models reached up to 0.942. Sensitivity and specifi city varied significantly, with the highest sensitivity at 0.90 and specificity at 0.99. Significant predictors of HT included age, glucose levels, NIH Stroke S cale (NIHSS) score, systolic and diastolic blood pressure, and radiomic features . Despite these promising results, methodological disparities and limited extern al validation highlighted the need for standardized reporting and further rigoro us testing. ML techniques, especially XGBoost and ANN, show great promise in pre dicting HT following thrombolysis in AIS patients, enhancing risk stratification and clinical decision-making.”
      原文链接:
    • NETL
    • NSTL

    University of Padova Reports Findings in Machine Learning (Preventing illegal se afood trade using machine-learning assisted microbiome analysis)

    37-38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 Legnaro, Italy, by New sRx editors, research stated, “Seafood is increasingly traded worldwide, but its supply chain is particularly prone to frauds. To increase consumer confidence, prevent illegal trade, and provide independent validation for eco-labelling, acc urate tools for seafood traceability are needed.” Financial support for this research came from Universita degli Studi di Padova.
      原文链接:
    • NETL
    • NSTL

    Investigators from Xi’an Jiaotong University Have Reported New Data on Nanoparti cles (A Hybrid Machine Learning-cfd Method for the Innovative Analysis of Al2o3 Nanoparticle Deposition In Shelland- tubes Heat Exchangers)

    38-39页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Current study results on Nanotechnology - Nanopar ticles have been published. According to news reporting originating in Xi’an, Pe ople’s Republic of China, by NewsRx journalists, research stated, “This study ex amines the intricate dynamics surrounding the deposition of Al2O3 nanoparticles within a heat exchanger, with the aim of optimizing heat transfer efficiency and gaining insights into gas dynamics. A comprehensive investigation of various pa rameters is conducted, including nanoparticle diameter ranging from 10 to 100 nm , heat flux variations from 500 to 3000 W/m2, Reynolds numbers spanning from 308 to 1540, and mass fractions ranging from 0.5 to 8 %. The methodolo gy integrates machine learning algorithms with Eulerian and Lagrange methods, le veraging Python programming to deepen the understanding of complex deposition pr ocesses.”
      原文链接:
    • NETL
    • NSTL