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 Western Australia Reports Findings in Machine Learning (Exploring genomic feature selection: A comparative analysis of GWAS and machine learning a lgorithms in a large-scale soybean dataset)

    40-40页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New research on Machine Learning is the subject o f a report. According to news reporting from Perth, Australia, by NewsRx journal ists, research stated, “The surge in high-throughput technologies has empowered the acquisition of vast genomic datasets, prompting the search for genetic marke rs and biomarkers relevant to complex traits. However, grappling with the inhere nt complexities of high dimensionality and sparsity within these datasets poses formidable hurdles.” Financial supporters for this research include Australian Research Council, Nati onal Institute of Food and Agriculture.
      原文链接:
    • NETL
    • NSTL

    Researchers from Xiangtan University Describe Findings in Machine Learning (Mach ine Learning-based Fluorescence Sensor Array: Accurate Discrimination, Quantitat ive Assay of Phenothiazine Drugs Via Versatile Dna Probes)

    41-41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 Machine Learning. According to news reporting originating from Xiangtan, People’ s Republic of China, by NewsRx correspondents, research stated, “Phenothiazine d rugs are widely used to treat psychotic diseases in humans. The phenothiazine li gand enables unique interaction between the drugs and DNA double helix.” Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Natural Science Foundation of Hunan Province, Project of Hun an Provincial Department of Edu-cation. Our news editors obtained a quote from the research from Xiangtan University, “W e discovered that it was impossible to select aptamer to selectively bind with p henothiazine drug. In this study, an alternative fluorescence sensor array was f irst developed to accurately discriminate four typical phenothiazine drugs based on machine learning. As the eight sensor elements, versatile DNA probes were de signed based on different oligonucleotides, two unique fluorescence dyes, and di verse buffer solutions. The fingerprint data can offer the fluorescence response patterns against each phenothiazine drug. Linear discriminant analysis (LDA) ca n discriminate single one or mixture samples of phenothiazine drugs with 100% accuracy. Besides, one neural network model showed a good linear relationship be tween predicted and actual concentrations to quantitatively assay specific pheno thiazine drugs.”
      原文链接:
    • NETL
    • NSTL

    University of Southern California Reports Findings in Machine Learning (Explorin g the Global Reaction Coordinate for Retinal Photoisomerization: A Graph Theory- Based Machine Learning Approach)

    42-42页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New research on Machine Learning is the subject o f a report. According to news reporting out of Los Angeles, California, by NewsR x editors, research stated, “Unraveling the reaction pathway of photoinduced rea ctions poses a great challenge owing to its complexity. Recently, graph theory-b ased machine learning combined with nonadiabatic molecular dynamics (NAMD) has b een applied to obtain the global reaction coordinate of the photoisomerization o f azobenzene.” Our news journalists obtained a quote from the research from the University of S outhern California, “However, NAMD simulations are computationally expensive as they require calculating the nonadiabatic coupling vectors at each time step. He re, we showed that ab initio molecular dynamics (AIMD) can be used as an alterna tive to NAMD by choosing an appropriate initial condition for the simulation. We applied our methodology to determine a plausible global reaction coordinate of retinal photoisomerization, which is essential for human vision. On rank-orderin g the internal coordinates, based on the mutual information (MI) between the int ernal coordinates and the HOMO energy, NAMD and AIMD give a similar trend.”
      原文链接:
    • NETL
    • NSTL

    University of Milano Bicocca Reports Findings in Papillary Thyroid Carcinoma (Ma chine learning streamlines the morphometric characterization and multi-class seg mentation of nuclei in different follicular thyroid lesions: everything in a NUT SHELL)

    43-44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 Papillary Thyroid Carc inoma is the subject of a report. According to news reporting from Milan, Italy, by NewsRx journalists, research stated, “The diagnostic assessment of thyroid n odules is hampered by the persistence of uncertainty in borderline cases, and fu rther complicated by the inclusion of non-invasive follicular tumor with papilla ry-like nuclear features (NIFTP) as a less aggressive alternative to papillary t hyroid carcinoma (PTC). In this setting, computational methods might facilitate the diagnostic process by unmasking key nuclear characteristics of NIFTPs.” The news correspondents obtained a quote from the research from the University o f Milano Bicocca, “The main aims of this work were to (1) identify morphometric features of NIFTP and PTC that are interpretable for the human eye, and (2) deve lop a deep learning model for multi-class segmentation as a support tool to redu ce diagnostic variability. Our findings confirmed that nuclei in NIFTP and PTC s hare multiple characteristics, setting them apart from hyperplastic nodules (HP) . The morphometric analysis identified 15 features that can be translated into n uclear alterations readily understandable by pathologists, such as a remarkable inter-nuclear homogeneity for HP in contrast to a major complexity in the chroma tin texture of NIFTP, and to the peculiar pattern of nuclear texture variability of PTC. A few NIFTP cases with available NGS data were also analyzed to initial ly explore the impact of RAS-related mutations on nuclear morphometry. Finally, a pixel-based deep learning model was trained and tested on whole slide images ( WSIs) of NIFTP, PTC, and HP cases. The model, named NUTSHELL (NUclei from Thyroi d tumors Segmentation to Highlight Encapsulated Low-malignant Lesions), successf ully detected and classified the majority of nuclei in all WSIs’ tiles, showing comparable results with already well-established pathology nuclear scores. NUTSH ELL provides an immediate overview of NIFTP areas and can be used to detect micr ofoci of PTC within extensive glandular samples or identify lymph node metastase s.”
      原文链接:
    • NETL
    • NSTL

    University of Adelaide Reports Findings in Artificial Intelligence (Relationship between anterior occlusion, arch dimension, and mandibular movement during spee ch articulation: A three-dimensional analysis)

    44-45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 originating from Adelaide, Austr alia, by NewsRx correspondents, research stated, “Studies correlating occlusal m orphology from 3-dimensional intraoral scans with both soft and hard tissue dyna mic landmark tracking within the same participant population are lacking. The pu rpose of this clinical study was to use 3-dimensional intraoral scanning, comput er-aided design, electrognathography, and artificial intelligence to investigate the relationships between anterior occlusion and arch parameters with hard and soft tissue displacements during speech production.” Our news journalists obtained a quote from the research from the University of A delaide, “An artificial intelligence (AI) driven software program and electrogna thography was used to record the phonetic activities in 62 participants for soft tissue (ST) and hard tissue (HT) displacement. Soft tissue displacement was qua ntified by the mean difference between subnasale and soft tissue pogonion peaks during phonetic expressions, and hard tissue displacement was directly measured with an electrognathograph. Intercanine and intermolar distances, arch perimeter s, and horizontal and vertical overlap were measured from the intraoral scan dat a. ST and HT displacements were successfully estimated for fricative (ST=7.16 ±4 .51 mm, HT=11.86 ±4.02 mm), sibilant (ST=5.11 ±3.49 mm, HT=8.24 ±3.31 mm), lingu odental (ST=5.72 ±4.46 mm, HT=10.01 ±3.16 mm), and bilabial (ST=5.56 ±4.64 mm, H T=11.69 ±4.28 mm) phonetics. Vertical overlap correlated positively with hard ti ssue movement during all speech expressions except bilabial phonetics (r=.30 to. 41, P<.05). Maxillary and mandibular arch perimeters showed negative correlations with soft tissue displacement during linguodental and bil abial speech (r=-.25 to -.41, P<.05) but were significantly correlated with hard tissue movement during all speech assessments (r=-.28 to - .44, P<.05). Maxillary intermolar distances negatively corr elated with hard tissue phonetic expressions (r=- .24 to -.30, P<.05). Participant age positively correlated with soft tissue displacement during all speech patterns (r=.28 to.33, P<.05) and with weight i ncrease (r=.27, P=.033), and hard tissue displacement (r=.25, P=.048) during max imum mouth opening significantly correlated with linguodental phonetics.”
      原文链接:
    • NETL
    • NSTL

    Second People’s Hospital Reports Findings in Arthroplasty (Enhancing total knee arthroplasty outcomes: the role of individualized femoral sagittal alignment in robotic-assisted surgery - A randomized controlled trial)

    45-46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 Surgery - Arthroplasty is the subject of a report. According to news reporting from Chongqing, People’ s Republic of China, by NewsRx journalists, research stated, “Optimal sagittal a lignment of the femoral prosthesis is critical to the success of total knee arth roplasty (TKA). While robotic-assisted TKA can improve alignment accuracy, the e fficacy of default femoral alignment versus individualized alignment remains und er scrutiny.” The news correspondents obtained a quote from the research from Second People’s Hospital, “This study aimed to compare the differences in prosthetic alignment, anatomical restoration, and clinical outcomes between individualized femoral sag ittal alignment and default sagittal alignment in robotic-assisted TKA. In a pro spective randomised controlled trial, 113 patients (120 knees) underwent robotic -assisted TKA were divided into two groups: 61 with individualized femoral flexi on (individualized alignment group) and 59 with default 3-5° flexion (default al ignment group). The individualized alignment was based on the distal femoral sag ittal anteverted angle (DFSAA), defined as the angle between the mechanical and distal anatomical axes of the femur. The radiographic and clinical outcomes were compared. Despite similar postoperative femoral flexion angles between groups ( P = 0.748), the individualized alignment group exhibited significantly lower inc idences of femoral prosthesis extension and higher rates of optimal 0-3° prosthe sis flexion (9.8% vs. 27.1%, P = 0.014,78.7% vs. 55.9%, p = 0.008, respectively). The individualized alignment g roup also demonstrated more favourable changes in sagittal anatomy, with higher maintenance of postoperative anterior femoral offset within 1 mm (54.1% vs. 33.9%, P = 0.026) and posterior condylar offset within 1 mm and 2 mm (44.3% vs. 25.4%, p = 0.031,73.8% vs. 50.8%, p = 0.010, respectively). Although slight improvement in the Hospital for Special Surgery Knee Score (HSS) at three months was observed (P = 0.045), it did not reach a minimal clinically important difference.”
      原文链接:
    • NETL
    • NSTL

    Second Affiliated Hospital of Anhui Medical University Reports Findings in Heart Attack (Machine learning prediction of no reflow in patients with ST-segment el evation myocardial infarction undergoing primary percutaneous coronary intervent ion)

    46-47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 Heart Disorders and Di seases - Heart Attack is the subject of a report. According to news reporting or iginating from Hefei, People’s Republic of China, by NewsRx correspondents, rese arch stated, “No-reflow (NRF) phenomenon is a significant challenge in patients with ST-segment elevation myocardial infarction (STEMI) undergoing primary percu taneous coronary intervention (pPCI). Accurate prediction of NRF may help improv e clinical outcomes of patients.”
      原文链接:
    • NETL
    • NSTL

    New Artificial Intelligence Research from Inha University Discussed (Optimal Ele ctrical Vehicle Charging Planning and Routing Using Real-Time Trained Energy Pre diction With Physics-Based Powertrain Model)

    47-48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 artificial intelligence are presented in a new report. According to news reporting from Incheon, South K orea, by NewsRx journalists, research stated, “Electric vehicles (EVs) are risin g in popularity due to technological developments and the nation’s decarbonizati on efforts, which are enticing drivers to move away from gasoline-dependent tran sportation. However, a major challenge in EV charging is optimal day-ahead charg ing planning under time-varying conditions, such as fluctuating charging prices and traffic conditions.” Financial supporters for this research include Korea Institute of Energy Technol ogy Evaluation And Planning; National Research Foundation of Korea.
      原文链接:
    • NETL
    • NSTL

    Data on Machine Learning Reported by Alexia Pelloux and Colleagues (Machine lear ning-based q-RASAR predictions of the bioconcentration factor of organic molecul es estimated following the organisation for economic co-operation and developmen t ...)

    48-49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 Lund, Sweden, by NewsRx journalists, research stated, “In this study, we utilized an innovative quantita tive read-across (RA) structure-activity relationship (q-RASAR) approach to pred ict the bioconcentration factor (BCF) values of a diverse range of organic compo unds, based on a dataset of 575 compounds tested using Organisation for Economic Co-operation and Development Test Guideline 305 for bioaccumulation in fish. In itially, we constructed the q-RASAR model using the partial least squares regres sion method, yielding promising statistical results for the training set (R =0.7 1, Q=0.68, mean absolute error [MAE]=0.54) .” The news correspondents obtained a quote from the research, “The model was furth er validated using the test set (Q=0.77, Q=0.75, MAE=0.51). Subsequently, we exp lored the q-RASAR method using other regression-based supervised machine-learnin g algorithms, demonstrating favourable results for the training and test sets. A ll models exhibited R and Q values exceeding 0.7, Q values greater than 0.6, and low MAE values, indicating high model quality and predictive capability for new , unidentified chemical substances.”
      原文链接:
    • NETL
    • NSTL

    University of Oslo Researcher Publishes New Data on Machine Learning (Comparativ e Study of Machine Learning Methods for State of Health Estimation of Maritime B attery Systems)

    49-49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 Oslo, Norway, by NewsRx correspondents, research stated, “This paper tests tw o data-driven approaches for predicting the state of health (SOH) of lithium-ion -batteries (LIBs) for the purpose of monitoring maritime battery systems.” The news correspondents obtained a quote from the research from University of Os lo: “First, nonsequential approaches are investigated and various models are te sted: ridge, lasso, support vector regression, and gradient boosted trees. Binni ng is proposed for feature engineering for these types of models to capture the temporal structure in the data. Such binning creates histograms for the accumula ted time the LIB has been within various voltage, temperature, and current range s. Further binning to combine these histograms into 2D or 3D histograms is explo red in order to capture relationships between voltage, temperature, and current. Second, a sequential approach is explored where different deep learning archite ctures are tried out: long short-term memory, transformer, and temporal convolut ional network. Finally, the various models and the two approaches are compared i n terms of their SOH prediction ability.”
      原文链接:
    • NETL
    • NSTL