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

    Studies from University of Basque Country in the Area of Machine Learning Descri bed (Ranking Building Design and Operation Parameters for Residential Heating De mand Forecasting With Machine Learning)

    105-106页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on Machine Learning is now available. According to news reporting originating in Bilbao, Spain, by NewsRx journalists, research stated, “The European Union’s Energy Performance in Buildi ngs Directive has made significant strides in enhancing building energy efficien cy since its inception in 2002. However, approximately 75% of EU b uildings still fall short of energy-efficient standards.” Funders for this research include La Caixa Foundation, PIF scholarship, Universi ty of the Basque Country, European Commission Joint Research Centre, University of the Basque Country (UPV/EHU).
      原文链接:
    • NETL
    • NSTL

    New Artificial Intelligence Study Results from Yale University School of Medicin e Described (Artificial Intelligence-aided Steatosis Assessment In Donor Livers According To the Banff Consensus Recommendations)

    106-107页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Research findings on Artificial Intelligence are discussed in a new report. According to news reporting out of New Haven, Connect icut, by NewsRx editors, research stated, “Severe macrovesicular steatosis in do nor livers is associated with primary graft dysfunction. The Banff Working Group on Liver Allograft Pathology has proposed recommendations for steatosis assessm ent of donor liver biopsy specimens with a consensus for defining ‘large droplet fat’ (LDF) and a 3-step algorithmic approach.” Our news journalists obtained a quote from the research from the Yale University School of Medicine, “We retrieved slides and initial pathology reports from pot ential liver donor biopsy specimens from 2010 to 2021. Following the Banff appro ach, we reevaluated LDF steatosis and employed a computer-assisted manual quanti fication protocol and artificial intelligence (AI) model for analysis. In a tota l of 113 slides from 88 donors, no to mild (<33% ) macrovesicular steatosis was reported in 88.5% (100/113) of slid es; 8.8% (10/113) was reported as at least moderate steatosis (> = 33%) initially. Subsequent pathology evaluation, following the Ba nff recommendation, revealed that all slides had LDF below 33%, a f inding confirmed through computer-assisted manual quantification and an AI model . Correlation coefficients between pathologist and computer-assisted manual quan tification, between computer-assisted manual quantification and the AI model, an d between the AI model and pathologist were 0.94, 0.88, and 0.81, respectively ( P <.0001 for all). The 3-step approach proposed by the Ban ff Working Group on Liver Allograft Pathology may be followed when evaluating st eatosis in donor livers.”
      原文链接:
    • NETL
    • NSTL

    Studies from Catholic University of Korea Describe New Findings in Machine Learn ing (Enhancing Patient Flow in Emergency Departments: A Machine Learning and Sim ulation-Based Resource Scheduling Approach)

    107-107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 new report. According to news reporting from Seoul, South Korea, by NewsRx journalists, research stated, “The efficient scheduling of reso urces within emergency departments (EDs) is crucial to minimizing patient length of stay (LoS) times and maximizing the utilization of limited resources.” Financial supporters for this research include National Research Foundation of K orea. Our news journalists obtained a quote from the research from Catholic University of Korea: “Reducing patient wait times can enhance the operation of emergency d epartments and improve patient satisfaction and the quality of medical care. Thi s study develops a simulation model using Discrete Event Simulation (DES) method ology, examining six resource scheduling policies that consider different combin ations of general and senior physicians. By leveraging six scheduling policies a nd machine learning techniques, this model dynamically identifies the most effec tive scheduling policy, based on a comprehensive dataset of ED visits in South K orea.”
      原文链接:
    • NETL
    • NSTL

    Researcher from Tallinn University of Technology Describes Findings in Robotics (Condition Monitoring of a Cartesian Robot with a Mechanically Damaged Gear to C reate a Fuzzy Logic Control and Diagnosis Algorithm)

    108-108页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Investigators publish new report on robotics. Acc ording to news reporting from Tallinn, Estonia, by NewsRx journalists, research stated, “The detection of faults during an operational process constitutes a cru cial objective within the framework of developing a control system to monitor th e structure of industrial mechanisms.” Our news reporters obtained a quote from the research from Tallinn University of Technology: “Even minor faults can give rise to significant consequences that r equire swift resolution. This research investigates the impact of overtension in the tooth belt transmission and heating of the screw transmission worm on the v ibration signals in a robotic system. Utilizing FFT techniques, distinct frequen cy characteristics associated with different faults were identified. Overtension in the tooth belt transmission caused localized oscillations, addressed by adju sting the acceleration and deceleration speeds. Heating of the screw transmissio n worm led to widespread disturbances affecting servo stress and positioning acc uracy. A fuzzy logic algorithm based on spectral analysis was proposed for adapt ive control, considering the vibration’s frequency and amplitude.”
      原文链接:
    • NETL
    • NSTL

    Researchers from Tsinghua University Report Recent Findings in Machine Learning (On the Privacy Effect of Data Enhancement Via the Lens of Memorization)

    109-110页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on Machine Learning are pre sented in a new report. According to news reporting out of Beijing, People’s Rep ublic of China, by NewsRx editors, research stated, “Machine learning poses seve re privacy concerns as it has been shown that the learned models can reveal sens itive information about their training data. Many works have investigated the ef fect of widely adopted data augmentation and adversarial training techniques, te rmed data enhancement in the paper, on the privacy leakage of machine learning m odels.” Financial support for this research came from National Natural Science Foundatio n of China (NSFC).
      原文链接:
    • NETL
    • NSTL

    Research Conducted at Tsinghua University Has Provided New Information about Rob otics and Automation (Heterogeneous Embodied Multi-agent Collaboration)

    109-109页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A new study on Robotics - Robotics and Automation is now available. According to news reporting originating from Beiji ng, People’s Republic of China, by NewsRx correspondents, research stated, “Mult i-agent embodied tasks have been studied in indoor visual environments, but most of the existing research focuses on homogeneous multi-agent tasks. Heterogeneou s multi-agent tasks are common in realworld scenarios, and the collaboration st rategy among heterogeneous agents with different capabilities is a challenging a nd important problem to be solved.” Financial support for this research came from National Natural Science Foundatio n of China (NSFC).
      原文链接:
    • NETL
    • NSTL

    Shanghai Jiao Tong University Reports Findings in Neural Computation (Sparse Gen eralized Canonical Correlation Analysis: Distributed Alternating Iteration-Based Approach)

    110-111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 reporting out of Shangh ai, People’s Republic of China, by NewsRx editors, research stated, “Sparse cano nical correlation analysis (CCA) is a useful statistical tool to detect latent i nformation with sparse structures. However, sparse CCA, where the sparsity could be considered as a Laplace prior on the canonical variates, works only for two data sets, that is, there are only two views or two distinct objects.” Our news journalists obtained a quote from the research from Shanghai Jiao Tong University, “To overcome this limitation, we propose a sparse generalized canoni cal correlation analysis (GCCA), which could detect the latent relations of mult iview data with sparse structures. Specifically, we convert the GCCA into a line ar system of equations and impose $\ell _ 1$ minimization penalty to pursue sparsity. This results in a nonc onvex problem on the Stiefel manifold. Based on consensus optimization, a distri buted alternating iteration approach is developed, and consistency is investigat ed elaborately under mild conditions.”
      原文链接:
    • NETL
    • NSTL

    Study Results from Purdue University Provide New Insights into Machine Learning (Investigating Machine Learning’s Capacity To Enhance the Prediction of Career C hoices)

    111-112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 West Lafayette, Indiana, by N ewsRx correspondents, research stated, “Vocational interest measurement has long played a significant role in work contexts, particularly in helping individuals make career choices. A recent meta-analysis indicated that interest inventories have substantial validity for predicting career choices.” Our news journalists obtained a quote from the research from Purdue University, “However, traditional approaches to interest inventory scoring (e.g., profile ma tching) typically capture broad, or average relations between vocational interes ts and occupations in the population, yet may not be accurate in capturing the s pecific relations in a given sample. Machine learning (ML) approaches provide a potential way forward as they can effectively take into account complexities in the relation between interests and career choices. Thus, this study aims to enha nce the accuracy of interest inventory-based career choice prediction through th e application of ML. Using a large sample (N = 81,267) of employed and unemploye d participants,we compared the prediction accuracy of a traditional interest pr ofile method (profile matching) to a new machine-learning augmented method in pr edicting occupational membership (for employed participants) and vocational aspi rations (for unemployed participants). Results suggest that, compared to the tra ditional profile method, the machine-learning augmented method resulted in highe r overall accuracy for predicting both types of career choices. The machine-lear ning augmented method was especially predictive of job categories with high base rates, yet underpredicted job categories with low base rates.”
      原文链接:
    • NETL
    • NSTL

    'Suction device and apparatus' in Patent Application Approval Process (USPTO 202 40157583)

    112-115页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A patent application by the inventors Fofonoff, Timothy (Cambridge, MA, US); Lee, Vivian (Somerville, MA, US); Payton, Nicholas (Somerville, MA, US), filed on October 3, 2023, was made available onl ine on May 16, 2024, according to news reporting originating from Washington, D. C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background informa tion supplied by the inventors: “Logistic operations such as those in warehouse environments often include robotic devices to gather items from a first location (e.g., a container) and place the items at a second location (e.g., on a convey or belt). Accordingly, these operations require the robotic device to first gras p the item. Existing robotic devices often include a suction device that generat es a suction force to “grasp” the item. “Existing picking devices are typically designed for a narrow range of items and those with similar features. For example, a picking device may have a suction d evice shaped to grasp boxes of a particular size. Similarly, a picking device ma y be configured to only grasp items that have a particular shape, weight, materi al, surface, etc. This limits a picking device’s utility, as it can only grasp i tems with certain characteristics.
      原文链接:
    • NETL
    • NSTL

    'Machine Learning Systems And Methods' in Patent Application Approval Process (U SPTO 20240161003)

    115-119页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – A patent application by the inventors AlMutairi, Mohammed Hazza (Dammam, SA); Alexander, Anton (Columbia, MD, US), fil ed on May 12, 2023, was made available online on May 16, 2024, according to news reporting originating from Washington, D.C., by NewsRx correspondents. This patent application has not been assigned to a company or institution. The following quote was obtained by the news editors from the background informa tion supplied by the inventors: “Artificial intelligence (AI) can enable compute rs to perform increasingly complicated tasks,such as tasks related to cognitive functions typically associated with humans. Several approaches to AI are preval ent, including machine learning (ML) techniques. In ML, a computer may be progra mmed to parse data, learn from the data, and make predictions from real-world in puts. With ML, a computer may be trained using data to perform a task, rather th an explicitly programmed with a particular algorithm for performing the task. On e ML approach, referred to as artificial neural networks, was inspired by the in terconnections of neurons in a biological brain.
      原文链接:
    • NETL
    • NSTL