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

    Second Affiliated Hospital of Soochow University Reports Findings in Rectal Cancer (Development and validation of machine learning models and nomograms for predicting the surgical difficulty of laparoscopic resection in rectal cancer)

    48-49页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Oncology - Rectal Canc er is the subject of a report. According tonews reporting originating from Suzh ou, People’s Republic of China, by NewsRx correspondents, researchstated, “The objective of this study is to develop and validate a machine learning (ML) predi ction model forthe assessment of laparoscopic total mesorectal excision (LaTME) surgery difficulty, as well as to identifyindependent risk factors that influe nce surgical difficulty. Establishing a nomogram aims to assist clinicalpractit ioners in formulating more effective surgical plans before the procedure.”Our news editors obtained a quote from the research from the Second Affiliated H ospital of SoochowUniversity, “This study included 186 patients with rectal can cer who underwent LaTME from January2018 to December 2020. They were divided in to a training cohort (n = 131) versus a validation cohort (n= 55). The difficul ty of LaTME was defined based on Escal’s et al. scoring criteria with modificati ons.We utilized Lasso regression to screen the preoperative clinical characteri stic variables and intraoperativeinformation most relevant to surgical difficul ty for the development and validation of four ML models:logistic regression (LR ), support vector machine (SVM), random forest (RF), and decision tree (DT).The performance of the model was assessed based on the area under the receiver oper ating characteristiccurve(AUC), sensitivity, specificity, and accuracy. Logisti c regression-based column-line plots were createdto visualize the predictive mo del. Consistency statistics (C-statistic) and calibration curves were usedto di scriminate and calibrate the nomogram, respectively. In the validation cohort, a ll four ML modelsdemonstrate good performance: SVM AUC = 0.987, RF AUC = 0.953, LR AUC = 0.950, and DT AUC= 0.904. To enhance visual evaluation, a logistic re gression-based nomogram has been established.Predictive factors included in the nomogram are body mass index (BMI), distance between the tumor tothe dentate l ine 10 cm, radiodensity of visceral adipose tissue (VAT), area of subcutaneous a dipose tissue(SAT), tumor diameter >3 cm, and comorbid hypertension.”
      原文链接:
    • NETL
    • NSTL

    New Robotics Study Findings Reported from National University of Defense Technology (Digital Battle: A Three-Layer Distributed Simulation Architecture for Heter ogeneous Robot System Collaboration)

    49-50页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New study results on robotics have bee n published. According to news reporting fromChangsha, People’s Republic of Chi na, by NewsRx journalists, research stated, “In this paper, we proposea three-l ayer distributed simulation network architecture, which consists of a distribute d virtual simulationnetwork, a perception and control subnetwork, and a coopera tive communication service network.”Our news correspondents obtained a quote from the research from National Univers ity of DefenseTechnology: “The simulation architecture runs on a distributed pl atform, which can provide unique virtualscenarios and multiple simulation servi ces for the verification of basic perception, control, and planningalgorithms o f a single-robot system and can verify the distributed collaboration algorithms of heterogeneousmultirobot systems. Further, we design simulation experimental scenarios for classic heterogeneous roboticsystems such as unmanned aerial vehi cles (UAVs) and unmanned ground vehicles (UGVs).”
      原文链接:
    • NETL
    • NSTL

    Swiss Tropical and Public Health Institute Reports Findings in Machine Learning (Modelling Europe-wide fine resolution daily ambient temperature for 2003-2020 using machine learning)

    50-51页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Machine Learning is th e subject of a report. According to newsreporting originating from Allschwil, S witzerland, by NewsRx correspondents, research stated, “To improveour understan ding of the health impacts of high and low temperatures, epidemiological studies requirespatiotemporally resolved ambient temperature (Ta) surfaces. Exposure a ssessment over various Europeancities for multi-cohort studies requires high re solution and harmonized exposures over larger spatiotemporalextents.”Our news editors obtained a quote from the research from Swiss Tropical and Publ ic Health Institute,“Our aim was to develop daily mean, minimum and maximum amb ient temperature surfaces with a 1x 1 km resolution for Europe for the 2003-202 0 period. We used a two-stage random forest modellingapproach. Random forest wa s used to (1) impute missing satellite derived Land Surface Temperature(LST) us ing vegetation and weather variables and to (2) use the gap-filled LST together with land useand meteorological variables to model spatial and temporal variati on in Ta measured at weather stations.To assess performance, we validated these models using random and block validation. In addition toglobal performance, an d to assess model stability, we reported model performance at a higher granularity (local). Globally, our models explained on average more than 81 % and 93 % of the variability in theblock validation sets for LST a nd Ta respectively. Average RMSE was 1.3, 1.9 and 1.7 ℃ for mean,min and max a mbient temperature respectively, indicating a generally good performance. For Ta models,local performance was stable across most of the spatiotemporal extent, but showed lower performance inareas with low observation density. Overall, mod el stability and performance were lower when using blockvalidation compared to random validation.”
      原文链接:
    • NETL
    • NSTL

    Reports from Singapore University of Technology and Design Highlight Recent Research in Artificial Intelligence (The innovation paradox: concept space expansion with diminishing originality and the promise of creative artificial intelligence)

    51-51页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on ar tificial intelligence. According to news reportingfrom Singapore University of Technology and Design by NewsRx journalists, research stated, “Innovation,typic ally spurred by reusing, recombining and synthesizing existing concepts, is expe cted to result in anexponential growth of the concept space over time.”Our news journalists obtained a quote from the research from Singapore Universit y of Technologyand Design: “However, our statistical analysis of TechNet, which is a comprehensive technology semanticnetwork encompassing over 4 million conc epts derived from patent texts, reveals a linear rather thanexponential expansi on of the overall technological concept space. Moreover, there is a notable decl inein the originality of newly created concepts. These trends can be attributed to the constraints of humancognitive abilities to innovate beyond an ever-grow ing space of prior art, among other factors.”
      原文链接:
    • NETL
    • NSTL

    New Machine Learning Findings Reported from Tianjin University (Exploring the Learning Difficulty of Data: Theory and Measure)

    51-52页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ma chine Learning. According to news reportingoriginating in Tianjin, People’s Rep ublic of China, by NewsRx journalists, research stated, “Easy/hardsample’ is a popular parlance in machine learning. Learning difficulty of samples refers to h ow easy/harda sample is during a learning procedure.”Funders for this research include National Natural Science Foundation of China ( NSFC), TJF.The news reporters obtained a quote from the research from Tianjin University, “ An increasing needof measuring learning difficulty demonstrates its importance in machine learning (e.g., difficulty-basedweighting learning strategies). Prev ious literature has proposed a number of learning difficulty measures.However, no comprehensive investigation for learning difficulty is available to date, res ulting in that nearlyall existing measures are heuristically defined without a rigorous theoretical foundation. This study attemptsto conduct a pilot theoreti cal study for learning difficulty of samples. First, influential factors forlea rning difficulty are summarized. Under various situations conducted by summarize d influential factors,correlations between learning difficulty and two vital cr iteria of machine learning, namely, generalizationerror and model complexity, a re revealed. Second, a theoretical definition of learning difficulty is proposedon the basis of these two criteria. A practical measure of learning difficulty is proposed under thedirection of the theoretical definition by importing the b ias-variance trade-off theory. Subsequently, therationality of theoretical defi nition and the practical measure are demonstrated, respectively, by analysisof several classical weighting methods and abundant experiments realized under all situations conductedby summarized influential factors. The mentioned weighting methods can be reasonably explained underthe proposed theoretical definition an dconcerned propositions.”
      原文链接:
    • NETL
    • NSTL

    Hongqi Hospital Affiliated to Mudanjiang Medical University Reports Findings in Vascular Dementia (Machine learning based on the EEG and structural MRI can predict different stages of vascular cognitive impairment)

    52-53页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Cerebrovascular Diseas es and Conditions - Vascular Dementia isthe subject of a report. According to n ews reporting originating from Mudanjiang, People’s Republicof China, by NewsRx correspondents, research stated, “Vascular cognitive impairment (VCI) is a majo rcause of cognitive impairment in the elderly and a co-factor in the developmen t and progression of most neurodegenerative diseases. With the continuing develo pment of neuroimaging, multiple markers can becombined to provide richer biolog ical information, but little is known about their diagnostic value in VCI.”Our news editors obtained a quote from the research from Hongqi Hospital Affilia ted to MudanjiangMedical University, “A total of 83 subjects participated in ou r study, including 32 patients with vascularcognitive impairment with no dement ia (VCIND), 21 patients with vascular dementia (VD), and 30normal controls (NC) . We utilized resting-state quantitative electroencephalography (qEEG) power spectra, structural magnetic resonance imaging (sMRI) for feature screening, and co mbined them with supportvector machines to predict VCI patients at different di sease stages. The classification performance of sMRIoutperformed qEEG when dist inguishing VD from NC (AUC of 0.90 vs. 0,82), and sMRI also outperformedqEEG wh en distinguishing VD from VCIND (AUC of 0.8 vs. 0,0.64), but both underperformed whendistinguishing VCIND from NC (AUC of 0.58 vs. 0.56). In contrast, the join t model based on qEEG andsMRI features showed relatively good classification ac curacy (AUC of 0.72) to discriminate VCIND fromNC, higher than that of either q EEG or sMRI alone. Patients at varying stages of VCI exhibit diverselevels of b rain structure and neurophysiological abnormalities. EEG serves as an affordable and convenientdiagnostic means to differentiate between different VCI stages.”
      原文链接:
    • NETL
    • NSTL

    Data on Machine Learning Discussed by a Researcher at Mugla Sitki Kocman University (Decoding Functional Brain Data for Emotion Recognition: A Machine Learning Approach)

    53-54页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Data detailed on artificial intelligen ce have been presented. According to newsreporting originating from Mugla, Turk ey, by NewsRx correspondents, research stated, “The identification of emotions i s an open research area and has a potential leading role in the improvement of s ocio-emotionalskills such as empathy, sensitivity, and emotion recognition in h umans.”The news editors obtained a quote from the research from Mugla Sitki Kocman Univ ersity: “Thecurrent study aimed to use Event Related Potential (ERP) components (N100, N200, P200, P300, earlyLate Positive Potential (LPP), middle LPP, and l ate LPP) of EEG data for the classification of emotionalstates (positive, negat ive, neutral). EEG data were collected from 62 healthy individuals over 18 electrodes. An emotional paradigm with pictures from the International Affective Pict ure System (IAPS) wasused to record the EEG data. A linear Support Vector Machi ne (C=0.1) was used to classify emotions, anda forward feature selection approa ch was used to eliminate irrelevant features. The early LPP component,which was the most discriminative among all ERP components, had the highest classificatio n accuracy(70.16%) for identifying negative and neutral stimuli. T he classification of negative versus neutral stimulihad the best accuracy (79.8 4%) when all ERP components were used as a combined feature set, fo llowedby positive versus negative stimuli (75.00%) and positive ve rsus neutral stimuli (68.55%).”
      原文链接:
    • NETL
    • NSTL

    Comillas Pontifical University Reports Findings in Chronic Disease (Machine Learning-Based Prediction of Changes in the Clinical Condition of Patients With Complex Chronic Diseases: 2-Phase Pilot Prospective Single-Center Observational Study)

    54-55页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Disease Attributes - C hronic Disease is the subject of a report.According to news reporting originati ng in Madrid, Spain, by NewsRx journalists, research stated, “Functionalimpairm ent is one of the most decisive prognostic factors in patients with complex chro nic diseases.A more significant functional impairment indicates that the diseas e is progressing, which requires implementingdiagnostic and therapeutic actions that stop the exacerbation of the disease.”The news reporters obtained a quote from the research from Comillas Pontifical U niversity, “This studyaimed to predict alterations in the clinical condition of patients with complex chronic diseases by predictingthe Barthel Index (BI), to assess their clinical and functional status using an artificial intelligence mo deland data collected through an internet of things mobility device. A 2-phase pilot prospective single-centerobservational study was designed. During both ph ases, patients were recruited, and a wearable activitytracker was allocated to gather physical activity data. Patients were categorized into class A (BI 20;to tal dependence), class B (20 <BI 60; severe dependence), an d class C (BI >60; moderate or mild dependence, or indep endent). Data preprocessing and machine learning techniques were used to analyzemobility data. A decision tree was used to achieve a robust and interpretable m odel. To assess the qualityof the predictions, several metrics including the me an absolute error, median absolute error, and rootmean squared error were consi dered. Statistical analysis was performed using SPSS and Python for themachine learning modeling. Overall, 90 patients with complex chronic diseases were inclu ded: 50 duringphase 1 (class A: n=10; class B: n=20; and class C: n=20) and 40 during phase 2 (class B: n=20 andclass C: n=20). Most patients (n=85, 94% ) had a caregiver. The mean value of the BI was 58.31 (SD24.5). Concerning mobi lity aids, 60% (n=52) of patients required no aids, whereas the ot hers requiredwalkers (n=18, 20%), wheelchairs (n=15, 17% ), canes (n=4, 7%), and crutches (n=1, 1%). Regardingclinical complexity, 85% (n=76) met patient with polypathology cri teria with a mean of 2.7 (SD 1.25)categories, 69% (n=61) met the frailty criteria, and 21% (n=19) met the patients with complex chr onicdiseases criteria. The most characteristic symptoms were dyspnea (n=73, 82% ), chronic pain (n=63, 70%), asthenia (n=62, 68%), and anxiety (n=41, 46%). Polypharmacy was presented in 87% (n=78) ofpatients. The most important variables for predicting the BI were iden tified as the maximum step countduring evening and morning periods and the abse nce of a mobility device. The model exhibited consistencyin the median predicti on error with a median absolute error close to 5 in the training, validation, an dproduction-like test sets. The model accuracy for identifying the BI class was 91%, 88%, and 90% in thetraining, vali dation, and test sets, respectively.”
      原文链接:
    • NETL
    • NSTL

    Northwestern Polytechnical University Reports Findings in Robotics (Approximate optimal and safe coordination of nonlinear secondorder multirobot systems with model uncertainties)

    55-56页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Robotics is the subjec t of a report. According to news reporting fromShaanxi, People’s Republic of Ch ina, by NewsRx journalists, research stated, “This paper investigatesthe approx imate optimal coordination for nonlinear uncertain second-order multi-robot syst ems withguaranteed safety (collision avoidance) Through constructing novel loca l error signals, the collision-freecontrol objective is formulated into an coor dination optimization problem for nominal multi-robot systems.Based on approxim ate dynamic programming technique, the optimal value functions and control polic iesare learned by simplified critic-only neural networks (NNs).”The news correspondents obtained a quote from the research from Northwestern Pol ytechnical University,“Then, the approximated optimal controllers are redesigne d using adaptive law to handle the effectsof robots’ uncertain dynamics. It is shown that the NN weights estimation errors are uniformly ultimatelybounded und er proper conditions, and safe coordination of multiple robots can be achieved r egardless ofmodel uncertainties.”
      原文链接:
    • NETL
    • NSTL

    Adelaide Institute of Higher Education Reports Findings in Artificial Intelligence [eXplainable Artificial Intelligence (XAI) for improving organisational regility]

    56-57页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Artificial Intelligenc e is the subject of a report. According to newsreporting out of Adelaide, Austr alia, by NewsRx editors, research stated, “Since the pandemic started,organisat ions have been actively seeking ways to improve their organisational agility and resilience (regility)and turn to Artificial Intelligence (AI) to gain a deeper understanding and further enhance their agility andregility. Organisations are turning to AI as a critical enabler to achieve these goals.”Our news journalists obtained a quote from the research from the Adelaide Instit ute of Higher Education,“AI empowers organisations by analysing large data sets quickly and accurately, enabling fasterdecision-making and building agility an d resilience. This strategic use of AI gives businesses a competitiveadvantage and allows them to adapt to rapidly changing environments. Failure to prioritise agility andresponsiveness can result in increased costs, missed opportunities, competition and reputational damage,and ultimately, loss of customers, revenue , profitability, and market share. Prioritising can be achieved byutilising eXp lainable Artificial Intelligence (XAI) techniques, illuminating how AI models ma ke decisionsand making them transparent, interpretable, and understandable. Bas ed on previous research on using AIto predict organisational agility, this stud y focuses on integrating XAI techniques, such as Shapley AdditiveExplanations ( SHAP), in organisational agility and resilience. By identifying the importance o f different features that affect organisational agility prediction, this study a ims to demystify the decision-makingprocesses of the prediction model using XAI . This is essential for the ethical deployment of AI, fosteringtrust and transp arency in these systems.”
      原文链接:
    • NETL
    • NSTL