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 Central Punjab Researcher Illuminates Research in Agricultural Rob ots (In-Depth Evaluation of Automated Fruit Harvesting in Unstructured Environme nt for Improved Robot Design)

    19-20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 agricul tural robots. According to news reporting out of Lahore, Pakistan, by NewsRx edi tors, research stated, "Using modern machines like robots comes with its set of challenges when encountered with unstructured scenarios like occlusion, shadows, poor illumination, and other environmental factors." Funders for this research include Punjab Higher Education Commission, Punjab, Pa kistan. Our news reporters obtained a quote from the research from University of Central Punjab: "Hence, it is essential to consider these factors while designing harve sting robots. Fruit harvesting robots are modern automatic machines that have th e ability to improve productivity and replace labor for repetitive and laborious harvesting tasks. Therefore, the aim of this paper is to design an improved ora nge-harvesting robot for a real-time unstructured environment of orchards, mainl y focusing on improved efficiency in occlusion and varying illumination. The art icle distinguishes itself with not only an efficient structural design but also the use of an enhanced convolutional neural network, methodologically designed a nd finetuned on a dataset tailored for oranges integrated with position visual servoing control system. Enhanced motion planning uses an improved rapidly explo ring random tree star algorithm that ensures the optimized path for every robot activity. Moreover, the proposed machine design is rigorously tested to validate the performance of the fruit harvesting robot."
      原文链接:
    • NETL
    • NSTL

    Third Affiliated Hospital of Southern Medical University Reports Findings in Mac hine Learning (Analysis and validation of potential ICD-related biomarkers in de velopment of myopia using machine learning)

    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 Machine Learning is th e subject of a report. According to news reporting originating in Guangzhou, Peo ple's Republic of China, by NewsRx journalists, research stated, "We aimed to id entify and verify potential biomarkers in the development of myopia associated w ith immunogenic cell death (ICD). We download high myopia (HM) dataset GSE136701 from Gene Expression Omnibus." The news reporters obtained a quote from the research from the Third Affiliated Hospital of Southern Medical University, "Differentially expressed genes in HM w ere identified to overlapped with ICD-related genes. Least absolute shrinkage an d selection operator were used to select the Hub genes. Furthermore, the correla tion between the hub genes and immune infiltration, immune response activities, and hub genes Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways analysis w as investigated using Spearman's rank correlation. Prediction of the miRNAs upst ream of the Hub genes was based on the TargetScan database. We used guinea pig l ens-induced myopia model's scleral tissues performed quantitative realtime poly merase chain reaction. We identified overlapped with ICD-related genes (LY96, IL 1A, IL33, and AGER) and two genes (LY96 and AGER) as hub genes. Single sample ge ne set enrichment analysis and Spearman's rank correlation revealed that hub gen e expression levels in HM were significantly correlated with the infiltration pe rcentages of CD56dim natural killer cells, macrophages, immature B cells, and th e immune response activities of APC co-stimulation and Kyoto Encyclopedia of Gen es and Genomes pathways, such as terpenoid backbone biosynthesis, aminoacyl-trna biosynthesis, Huntington's disease, oxidative phosphorylation; there were a few additional signaling pathways compared to normal samples. Additionally, several miRNA were predicted as upstream regulators of LY96 and AGER. LY96 was identifi ed as a significantly differentially expressed biomarker in myopia guinea pig's scleral tissues, as verified by qPCR. LY96 was identified and verified as a ICD- related potential myopia biomarker."
      原文链接:
    • NETL
    • NSTL

    Findings from Istanbul Medipol Universitesi Provide New Insights into Machine Le arning (Generating the Flood Susceptibility Map for Istanbul with GIS-Based Mach ine Learning Algorithms)

    21-22页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on artificial intelligence is the su bject of a new report. According to news originating from the Istanbul Medipol U niversitesi by NewsRx editors, the research stated, "The main objective of the c urrent study is to generate a flood hazard map by using the machine learning alg orithms hybridized with the geographic information systems (GIS). In this regard , the province of Istanbul, which is the metropolitan city of Turkey, was select ed as the focal region within the scope of the study." Our news journalists obtained a quote from the research from Istanbul Medipol Un iversitesi: "The class imbalance was tackled through the commonly used random un der sampling (RUS) technique in order to create a fair comparison datum line. It is worth mentioning that this is the first time this approach has been used for flood hazard mapping studies in Turkey. Random forest (RF), stochastic gradient boosting (SGB), and XGBoost algorithms were used. The best predictive performan ce was obtained with the XGBoost algorithm, followed by SGB and RF, respectively . The RF and SGB models showed a 90.67% success rate in determinin g the inundation points, while the XGBoost model outperformed its counterparts w ith a 92.00% success rate in determining the inundation points. In this research, the importance levels of the flood triggering variables were fur ther investigated in order to enliven the comprehensibility of the obtained resu lts."
      原文链接:
    • NETL
    • NSTL

    First Affiliated Hospital of Hunan Normal University Reports Findings in Cholang iocarcinoma (Machine learning developed an intratumor heterogeneity signature fo r predicting prognosis and immunotherapy benefits in cholangiocarcinoma)

    22-23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 Oncology - Cholangioca rcinoma is the subject of a report. According to news reporting out of Hunan, Pe ople's Republic of China, by NewsRx editors, research stated, "Cholangiocarcinom a is a kind of epithelial cell malignancy with high mortality. Intratumor hetero geneity (ITH) is involved in tumor progression, aggressiveness, treatment resist ance, and disease recurrence." Our news journalists obtained a quote from the research from the First Affiliate d Hospital of Hunan Normal University, "Integrative machine learning procedure i ncluding 10 methods (random survival forest, elastic network, Lasso, Ridge, step wise Cox, CoxBoost, partial least squares regression for Cox, supervised princip al components, generalized boosted regression modeling, and survival support vec tor machine) was performed to construct an ITH-related signature (IRS) for chola ngiocarcinoma. Single cell analysis was performed to clarify the communication b etween immune cell subtypes. Cellular experiment was used to verify the biologic al function of hub gene. The optimal prognostic IRS developed by Lasso method se rved as an independent risk factor and had a stable and powerful performance in predicting the overall survival rate in cholangiocarcinoma, with the AUC of 2-, 3-, and 4-year ROC curve being 0.955, 0.950 and 1.000 in TCGA cohort. low IRS sc ore indicated with a lower tumor immune dysfunction and exclusion score, lower t umor microsatellite instability, lower immune escape score, lower MATH score, an d higher mutation burden score in cholangiocarcinoma. Single cell analysis revea led a strong communication between fibroblasts, microphage and epithelial cells by specific ligand-receptor pairs, including COL4A1-(ITGAV+ITGB8) and COL1A2-(IT GAV+ITGB8). Down-regulation of BET1L inhibited the proliferation, migration and invasion as well as promoted apoptosis of cholangiocarcinoma cell. Integrative m achine learning analysis was performed to construct a novel IRS in cholangiocarc inoma."
      原文链接:
    • NETL
    • NSTL

    Reports from Cairo University Add New Data to Findings in Artificial Intelligenc e (Artificial Intelligence Powered Metaverse: Analysis, Challenges and Future Pe rspectives)

    23-24页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Artificial In telligence have been published. According to news reporting originating from Giz a, Egypt, by NewsRx correspondents, research stated, "The Metaverse, a virtual r eality (VR) space where users can interact with each other and digital objects, is rapidly becoming a reality. As this new world evolves, Artificial Intelligenc e (AI) is playing an increasingly important role in shaping its development." Financial support for this research came from Cairo University. Our news editors obtained a quote from the research from Cairo University, "Inte grating AI with emerging technologies in the Metaverse creates new possibilities for immersive experiences that were previously impossible. This paper explores how AI is integrated with technologies such as the Internet of Things, blockchai n, Natural Language Processing, virtual reality, Augmented Reality, Mixed Realit y, and Extended Reality. One potential benefit of using AI in the Metaverse is t he ability to create personalized experiences for individual users, based on the ir behavior and preferences. Another potential benefit of using AI in the Metave rse is the ability to automate repetitive tasks, freeing up time and resources f or more complex and creative endeavors. However, there are also challenges assoc iated with using AI in the Metaverse, such as ensuring user privacy and addressi ng issues of bias and discrimination. By examining the potential benefits and ch allenges of using AI in the Metaverse, including ethical considerations, we can better prepare for this exciting new era of VR."
      原文链接:
    • NETL
    • NSTL

    Reports on Robotics from California Institute of Technology (Caltech) Provide Ne w Insights (Multimodal Soft Robotic Actuation and Locomotion)

    24-25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 from Pasadena, California, by Ne wsRx correspondents, research stated, "Diverse and adaptable modes of complex mo tion observed at different scales in living creatures are challenging to reprodu ce in robotic systems. Achieving dexterous movement in conventional robots can b e difficult due to the many limitations of applying rigid materials." Financial supporters for this research include National Science Foundation (NSF) , Alfred P. Sloan Foundation, Heritage Medical Research Institute. Our news editors obtained a quote from the research from the California Institut e of Technology (Caltech), "Robots based on soft materials are inherently deform able, compliant, adaptable, and adjustable, making soft robotics conducive to cr eating machines with complicated actuation and motion gaits. This review examine s the mechanisms and modalities of actuation deformation in materials that respo nd to various stimuli. Then, strategies based on composite materials are conside red to build toward actuators that combine multiple actuation modes for sophisti cated movements. Examples across literature illustrate the development of soft a ctuators as free-moving, entirely soft-bodied robots with multiple locomotion ga its via careful manipulation of external stimuli. The review further highlights how the application of soft functional materials into robots with rigid componen ts further enhances their locomotive abilities. Finally, taking advantage of the shape-morphing properties of soft materials, reconfigurable soft robots have sh own the capacity for adaptive gaits that enable transition across environments w ith different locomotive modes for optimal efficiency. Overall, soft materials e nable varied multimodal motion in actuators and robots, positioning soft robotic s to make real-world applications for intricate and challenging tasks. Soft robo ts are a promising direction to create machines capable of complex motion observ ed in living creatures. Designing soft actuators that perform a combination of m ultiple actuation modalities allows them to perform intricate tasks."
      原文链接:
    • NETL
    • NSTL

    Researchers' from Norwegian University of Science and Technology (NTNU) Report D etails of New Studies and Findings in the Area of Machine Learning (SODRet: Inst ance retrieval using salient object detection for self-service shopping)

    25-25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 reporting from Norwegian University of Scien ce and Technology (NTNU) by NewsRx journalists, research stated, "Selfservice s hopping technologies have become commonplace in modern society. Although various innovative solutions have been adopted, there is still a gap in providing effic ient services to consumers." The news correspondents obtained a quote from the research from Norwegian Univer sity of Science and Technology (NTNU): "Recent developments in mobile applicatio n technologies and internet-of-things devices promote information and knowledge dissemination by integrating innovative services to meet users' needs. We argue that object retrieval applications can be used to provide effective online or se lf-service shopping. Therefore, to fill this technological void, this study aims to propose an object retrieval system using a fusion-based salient object detec tion (SOD) method. The SOD has attracted significant attention, and recently man y heuristic computational models have been developed for object detection. It ha s been widely used in object detection and retrieval applications. This work pro poses an instance retrieval system based on the SOD to find the objects from the commodity datasets. A prediction about the object's position is made using the saliency detection system through a saliency model, and the proposed SODbased r etrieval (SODRet) framework uses saliency maps for retrieving the searched items ."
      原文链接:
    • NETL
    • NSTL

    New Findings from University of Minnesota in the Area of Robotics Described (Kin et: Unsupervised Forward Models for Robotic Pushing Manipulation)

    26-26页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Current study results on Robotics have been published. According to news originating from Minneapolis, Minnesota, by N ewsRx correspondents, research stated, "Centric representation is an essential a bstraction for forward prediction. Most existing forward models learn this repre sentation through extensive supervision (e.g., object class and bounding box) al though such ground-truth information is not readily accessible in reality." Financial supporters for this research include Sony Research Award Program, Nati onal Science Foundation (NSF). Our news journalists obtained a quote from the research from the University of M innesota, "To address this, we introduce KINet (Keypoint Interaction Network)-an end-to-end unsupervised framework to reason about object interactions based on a keypoint representation. Using visual observations, our model learns to associ ate objects with keypoint coordinates and discovers a graph representation of th e system as a set of keypoint embed dings and their relations. It then learns an action-conditioned forward model using contrastive estimation to predict future keypoint states. By learning to perform physical reasoning in the keypoint spac e, our model automatically generalizes to scenarios with a different number of o bjects, novel backgrounds, and unseen object geometries."
      原文链接:
    • NETL
    • NSTL

    Researchers from University of Naples Federico II Report Recent Findings in Mach ine Learning (* * Trichoderma* * Biocontrol Performances against Baby-Lettuce Fu sarium Wilt Surveyed by Hyperspectral Imaging-Based Machine Learning and Infrare d ...)

    27-27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 out of Portici, Italy, by New sRx editors, research stated, "* * Fusarium oxysporum* * f. sp. * * lactucae* * is one of the most aggressive baby-lettuce soilborne pathogens." Funders for this research include Italian Ministry For Agriculture, Food Soverei gnty And Forestry. Our news editors obtained a quote from the research from University of Naples Fe derico II: "The application of * * Trichoderma* * spp. as biocontrol agents can minimize fungicide treatments and their effective targeted use can be enhanced b y support of digital technologies. In this work, two * * Trichoderma harzianum* * strains achieved 40-50% inhibition of pathogen radial growth in vitro. Their effectiveness in vivo was surveyed by assessing disease incidence a nd severity and acquiring hyperspectral and thermal features of the canopies bei ng treated. Infected plants showed a reduced light absorption in the green and n ear-red regions over time, reflecting the disease progression. In contrast, * * Trichoderma* * -treated plant reflectance signatures, even in the presence of th e pathogen, converged towards the healthy control values. Seventeen vegetation i ndices were selected to follow disease progression. The thermographic data were informative in the middle-late stages of disease (15 days post-infection) when s ymptoms were already visible."
      原文链接:
    • NETL
    • NSTL

    Hohai University Reports Findings in Machine Learning [Uncert ainty-based saltwater intrusion prediction using integrated Bayesian machine lea rning modeling (IBMLM) in a deep aquifer]

    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 Machine Learning is th e subject of a report. According to news reporting from Nanjing, People's Republ ic of China, by NewsRx journalists, research stated, "Data-driven machine learni ng approaches are promising to substitute physically based groundwater numerical models and capture input-output relationships for reducing computational burden . But the performance and reliability are strongly influenced by different sourc es of uncertainty." The news correspondents obtained a quote from the research from Hohai University , "Conventional researches generally rely on a stand-alone machine learning surr ogate approach and fail to account for errors in model outputs resulting from st ructural deficiencies. To overcome this issue, this study proposes a flexible in tegrated Bayesian machine learning modeling (IBMLM) method to explicitly quantif y uncertainties originating from structures and parameters of machine learning s urrogate models. An Expectation-Maximization (EM) algorithm is combined with Bay esian model averaging (BMA) to find out maximum likelihood and construct posteri or predictive distribution. Three machine learning approaches representing diffe rent model complexity are incorporated in the framework, including artificial ne ural network (ANN), support vector machine (SVM) and random forest (RF). The pro posed IBMLM method is demonstrated in a field-scale real-world ‘1500-foot' sand aquifer, Baton Rouge, USA, where overexploitation caused serious saltwater intru sion (SWI) issues. This study adds to the understanding of how chloride concentr ation transport responds to multi-dimensional extraction-injection remediation s trategies in a sophisticated saltwater intrusion model. Results show that most I BMLM exhibit r values above 0.98 and NSE values above 0.93, both slightly higher than individual machine learning, confirming that the IBMLM is well established to provide better model predictions than individual machine learning models, wh ile maintaining the advantage of high computing efficiency. The IBMLM is found u seful to predict saltwater intrusion without running the physically based numeri cal simulation model. We conclude that an explicit consideration of machine lear ning model structure uncertainty along with parameters improves accuracy and rel iability of predictions, and also corrects uncertainty bounds."
      原文链接:
    • NETL
    • NSTL