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

    University of Sciences and Technology Reports Findings in Neural Computation (Tr ansformer-based deep learning networks for fault detection, classification, and location prediction in transmission lines)

    20-21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 Computation - Neural C omputation is the subject of a report. According to news originating from Bab Ez zouar, Algeria, by NewsRx correspondents, research stated, “Fault detection, cla ssification, and location prediction are crucial for maintaining the stability a nd reliability of modern power systems, reducing economic losses, and enhancing system protection sensitivity. This paper presents a novel Hierarchical Deep Lea rning Approach (HDLA) for accurate and efficient fault diagnosis in transmission lines.” Our news journalists obtained a quote from the research from the University of S ciences and Technology, “HDLA leverages two-stage transformer-based classificati on and regression models to perform Fault Detection (FD), Fault Type Classificat ion (FTC), and Fault Location Prediction (FLP) directly from synchronized raw th ree-phase current and voltage samples. By bypassing the need for feature extract ion, HDLA significantly reduces computational complexity while achieving superio r performance compared to existing deep learning methods. The efficacy of HDLA i s validated on a comprehensive dataset encompassing various fault scenarios with diverse types, locations, resistances, inception angles, and noise levels.”
      原文链接:
    • NETL
    • NSTL

    Fondazione IRCCS Casa Sollievo della Sofferenza Reports Findings in Artificial I ntelligence (Inflammatory bowel disease genomics, transcriptomics, proteomics an d metagenomics meet artificial intelligence)

    21-22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 Artificial Intelligenc e is the subject of a report. According to news reporting originating from San G iovanni Rotondo, Italy, by NewsRx correspondents, research stated, “Various extr insic and intrinsic factors such as drug exposures, antibiotic treatments, smoki ng, lifestyle, genetics, immune responses, and the gut microbiome characterize u lcerative colitis and Crohn’s disease, collectively called inflammatory bowel di sease (IBD). All these factors contribute to the complexity and heterogeneity of the disease etiology and pathogenesis leading to major challenges for the scien tific community in improving management, medical treatments, genetic risk, and e xposome impact.” Our news editors obtained a quote from the research from Fondazione IRCCS Casa S ollievo della Sofferenza, “Understanding the interaction(s) among these factors and their effects on the immune system in IBD patients has prompted advances in multi-omics research, the development of new tools as part of system biology, an d more recently, artificial intelligence (AI) approaches. These innovative appro aches, supported by the availability of big data and large volumes of digital me dical datasets, hold promise in better understanding the natural histories, pred ictors of disease development, severity, complications and treatment outcomes in complex diseases, providing decision support to doctors, and promising to bring us closer to the realization of the ‘precision medicine’ paradigm.”
      原文链接:
    • NETL
    • NSTL

    Study Data from Universidad de Concepcion Provide New Insights into Machine Lear ning (Revisiting historical trends in the Eastern Boundary Upwelling Systems wit h a machine learning method)

    22-23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 artific ial intelligence. According to news originating from Concepcion, Chile, by NewsR x correspondents, research stated, “Eastern boundary upwelling systems (EBUS) ho st very productive marine ecosystems that provide services to many surrounding c ountries. The impact of global warming on their functioning is debated due to li mited long-term observations, climate model uncertainties, and significant natur al variability.” Funders for this research include Agencia Nacional De Investigacion Y Desarrollo . Our news journalists obtained a quote from the research from Universidad de Conc epcion: “This study utilizes the usefulness of a machine learning technique to d ocument long-term variability in upwelling systems from 1993 to 2019, focusing o n high-frequency synoptic upwelling events. Because the latter are modulated by the general atmospheric and oceanic circulation, it is hypothesized that changes in their statistics can reflect fluctuations and provide insights into the long -term variability of EBUS. A two-step approach using Self-Organizing Maps (SOM) and Hierarchical Agglomerative Clustering (HAC) algorithms was employed. These a lgorithms were applied to sets of upwelling events to characterize signatures in sealevel pressure, meridional wind, shortwave radiation, sea-surface temperatu re (SST), and Ekman pumping based on dominant spatial patterns. Results indicate d that the dominant spatial pattern, accounting for 56%-75% of total variance, representing the seasonal pattern, due to the marked seasonal ity in along-shore wind activity. Findings showed that, except for the Canary-Ib erian region, upwelling events have become longer in spring and more intense in summer. Southern Hemisphere systems (Humboldt and Benguela) had a higher occurre nce of upwelling events in summer (up to 0.022 Events/km²) compared to spring (<0.016 Events/km²), contrasting with Northern Hemisphere systems (<0.012 Events/km²). Furthermore, longterm changes in dominant spatial patterns w ere examined by dividing the time period in approximately two equally periods, t o compare past changes (1993-2006) with relatively new changes (2007-2019), reve aling shifts in key variables. These included poleward shifts in subtropical hig h-pressure systems (SHPS), increased upwelling-favorable winds, and SST drops to wards higher latitudes. The Humboldt Current System (HumCS) exhibited a distinct ive spring-to-summer pattern, with mid-latitude meridional wind weakening and co ncurrent SST decreases.”
      原文链接:
    • NETL
    • NSTL

    University of Potsdam Reports Findings in Machine Learning (Machine learning of metabolite-protein interactions from model-derived metabolic phenotypes)

    23-24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 originating from Potsdam, Germany, by N ewsRx correspondents, research stated, “Unraveling metaboliteprotein interactio ns is key to identifying the mechanisms by which metabolism affects the function of other cellular layers. Despite extensive experimental and computational effo rts to identify the regulatory roles of metabolites in interaction with proteins , it remains challenging to achieve a genome-scale coverage of these interaction s.” Financial supporters for this research include European Union’s Horizon 2020, Kl aus Tschira Boost Fund. Our news journalists obtained a quote from the research from the University of P otsdam, “Here, we leverage established gold standards for metabolite-protein int eractions to train supervised classifiers using features derived from genome-sca le metabolic models and matched data on protein abundance and reaction fluxes to distinguish interacting from non-interacting pairs. Through a comprehensive com parative study, we explore the impact of different features and assess the effec t of gold standards for noninteracting pairs on the performance of the classifi ers. Using data sets from and , we demonstrate that the features constructed by integrating fluxomic and proteomic data with metabolic phenotypes predicted from genome-scale metabolic models can be effectively used to train classifiers, acc urately predicting metabolite-protein interactions in the context of metabolism. Our results reveal that the high performance of classifiers trained on these fe atures is unaffected by the method used to generate gold standards for non-inter acting pairs.”
      原文链接:
    • NETL
    • NSTL

    Gansu Agricultural University Researcher Publishes New Study Findings on Machine Learning (A Comparative Analysis of Remote Sensing Estimation of Aboveground Bi omass in Boreal Forests Using Machine Learning Modeling and Environmental Data)

    24-24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 artificial intell igence are discussed in a new report. According to news reporting originating fr om Lanzhou, People’s Republic of China, by NewsRx correspondents, research state d, “It is crucial to have precise and current maps of aboveground biomass (AGB) in boreal forests to accurately track global carbon levels and develop effective plans for addressing climate change.” Financial supporters for this research include Nature Science Foundation of Gans u Province. Our news reporters obtained a quote from the research from Gansu Agricultural Un iversity: “Remote sensing as a cost-effective tool offers the potential to updat e AGB maps for boreal forests in real time. This study evaluates different machi ne learning algorithms, namely Light Gradient Boosting Machine (LightGBM), Extre me Gradient Boosting (XGBoost), Random Forest (RF), and Support Vector Regressio n (SVR), for predicting AGB in boreal forests. Conducted in the Qilian Mountains , northwest China, the study integrated field measurements, space-borne LiDAR, o ptical remote sensing, and environmental data to develop a training dataset. Amo ng 34 variables, 22 were selected for AGB estimation modeling. Our findings reve aled that the LightGBM AGB model had the highest level of accuracy (R2 = 0.84, R MSE = 15.32 Mg/ha), outperforming the XGBoost, RF, and SVR AGB models. Notably, the LightGBM AGB model effectively addressed issues of underestimation and overe stimation.”
      原文链接:
    • NETL
    • NSTL

    Data on Mental Health Diseases and Conditions Reported by Md Emran Hasan and Col leagues (Suicidal behaviors among high school graduates with preexisting mental health problems: a machine learning and GIS-based study)

    25-25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 Mental Health Diseases and Conditions is the subject of a report. According to news reporting originat ing in Dhaka, Bangladesh, by NewsRx journalists, research stated, “Suicidal beha vior among adolescents with mental health disorders, such as depression and anxi ety, is a critical issue. This study explores the prevalence and predictors of p ast-year suicidal behaviors among Bangladeshi high school graduates, employing b oth traditional statistical and machine learning methods.” The news reporters obtained a quote from the research, “To investigate the preva lence and predictors of past-year suicidal behaviors among high school graduates with mental health disorders, evaluate the effectiveness of various machine lea rning models in predicting these behaviors, and identify geographical disparitie s. A cross-sectional survey was conducted with 1,242 high school graduates (54.1 % female) in June 2023, collecting data on sociodemographic charac teristics, mental health status, sleep patterns, and digital addiction. Statisti cal analyses were performed using SPSS, while machine learning and GIS analyses were conducted with Python and ArcMap 10.8, respectively. Among the participants , 29.9% reported suicidal ideation, 15.3% had suicid e plans, and 5.4% attempted suicide in the past year. Significant predictors included rural residence, sleep duration, comorbid depression and anx iety, and digital addiction. Machine learning analyses revealed that permanent r esidence was the most significant predictor of suicidal behavior, while digital addiction had the least impact. Among the models used, the CatBoost model achiev ed the highest accuracy (69.42% for ideation, 87.05% for planning, and 94.77% for attempts) and demonstrated superior p redictive performance. Geographical analysis showed higher rates of suicidal beh aviors in specific districts, though overall disparities were not statistically significant. Enhancing mental health services in rural areas, addressing sleep i ssues, and implementing digital health and community awareness programs are cruc ial for reducing suicidal behavior.”
      原文链接:
    • NETL
    • NSTL

    Hamburg University of Technology Reports Findings in Robotics (Human-exoskeleton interaction portrait)

    26-26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 originating from Hamburg, Germany, by NewsRx co rrespondents, research stated, “Human-robot physical interaction contains crucia l information for optimizing user experience, enhancing robot performance, and o bjectively assessing user adaptation. This study introduces a new method to eval uate human-robot interaction and co-adaptation in lower limb exoskeletons by ana lyzing muscle activity and interaction torque as a two-dimensional random variab le.” Funders for this research include New Frontiers in Research Fund - Exploration, Canadian Foundation for Innovation (CFI) - JELF, Ontario Research Foundation, Na tural Sciences and Engineering Research Council of Canada.
      原文链接:
    • NETL
    • NSTL

    Weifang People’s Hospital Reports Findings in Collagen Diseases and Conditions ( The diagnostic value and associated molecular mechanism study for fibroblast-rel ated mitochondrial genes on keloid)

    27-28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 Connective Tissue Dise ases and Conditions - Collagen Diseases and Conditions is the subject of a repor t. According to news reporting from Shandong, People’s Republic of China, by New sRx journalists, research stated, “This study aims to reveal the mechanism of fi broblastrelated mitochondrial genes on keloid formation and explore promising s ignature genes for keloid diagnosis. The distribution of fibroblasts between the keloid sample and control sample based on three keloid datasets, followed by th e differentially expressed genes (DEGs) investigation and associated enrichment analysis.” The news correspondents obtained a quote from the research from Weifang People’s Hospital, “Then, hub genes were explored based on DEGs, mitochondrial genes fro m an online database, as well as fibroblastrelated genes that were revealed by WCGNA. Subsequently, signature genes were screened through machine learning, and their diagnostic value was validated by nomogram. Moreover, the targeted drugs and related transcriptional regulation of these genes were analyzed. Finally, th e verification analysis was performed on signature genes using qPCR analysis. A total of totally 329 DEGs were revealed based on three datasets, followed by enr ichment analysis. WGCNA revealed a total of 258 fibroblast-related genes, which were primarily assembled in functions like muscle tissue development. By using m achine learning, we screened four signature genes (ACSF2, ALDH1B1, OCIAD2, and S IRT4) based on eight hub genes (fibroblast-related mitochondrial genes). Nomogra m and validation analyses confirmed the well-diagnostic performance of these fou r genes in keloid. Immune infiltration and drug correlation analyses showed that SIRT4 was significantly associated with immune cell type 2 T helper cells and m olecular drug cyclosporin. All these findings provided new perspectives for the clinical diagnosis and therapy of keloid.”
      原文链接:
    • NETL
    • NSTL

    University of Utah Researcher Updates Current Data on Robotics (Magnetically-Act uated Endoluminal Soft Robot With Electroactive Polymer Actuation for Enhanced G ait Performance)

    28-28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 new report. According to news originating from the University of Utah by NewsRx correspondents, research stated, “Endoluminal devices are indispensable i n medical procedures in the natural lumina of the body, such as the circulatory system and gastrointestinal tract.” Financial supporters for this research include Division of Emerging Frontiers in Research And Innovation; Office of International Science And Engineering. Our news reporters obtained a quote from the research from University of Utah: “ In current clinical practice, there is a need for increased control and capabili ties of endoluminal devices with less discomfort and risk to the patient. This p aper describes the detailed modeling and experimental validation of a magneto-el ectroactive endoluminal soft (MEESo) robot concept that combines magnetic and el ectroactive polymer (EAP) actuation to improve the utility of the device. The pr oposed capsule-like device comprises two permanent magnets with alternating pola rity connected by a soft, low-power ionic polymer-metal composite (IPMC) EAP bod y. A detailed model of the MEESo robot is developed to explore quantitatively th e effects of dual magneto-electroactive actuation on the robot’s performance. It is shown that the robot’s gait is enhanced, during the magnetically-driven gait cycle, with IPMC body deformation. The concept is further validated by creating a physical prototype MEESo robot.”
      原文链接:
    • NETL
    • NSTL

    Recent Findings from Al-Iraqia University Highlight Research in Machine Learning (Machine Learning Versus Deep Learning for Contact Detection in Human-Robot Col laboration)

    29-30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 artificial intelligen ce have been presented. According to news originating from Baghdad, Iraq, by New sRx correspondents, research stated, “Due to the rapid progression of Human-Robo t Collaboration (HRC), ensuring safe interactions between humans and robots, con tact detecting systems must be dependable and efficient.” Our news reporters obtained a quote from the research from Al-Iraqia University: “In this research, various models are tested using a contact detection dataset that includes non-contact motions, intentional interactions, and accidental coll isions among others. K-Nearest Neighbors (KNN), Bagging, and Long Short-Term Mem ory (LSTM) networks are evaluated on their ability to classify different types o f contacts. According to the findings of the experiment, it is clear that KNN an d Bagging are reasonably accurate, but LSTM has surpassed both by achieving high er accuracy levels besides being better at handling temporal dependencies which are inherent in sensor data collected from dynamic human-robot interactions. The results have shown that when it comes to such kind of contact detection dataset s, long short-term memory (LSTM) and other deep learning models are superior to other methods. These results show that HRC systems can be made safer and more ef fective by using more sophisticated neural networks.”
      原文链接:
    • NETL
    • NSTL