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 Indian Institute for Technology Reveal New Findings on Machine Lear ning (Machine Learning Assisted Screening of Mxene With Superior Anchoring Effec t In Al-s Batteries)

    85-85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 Machine Learning are discussed in a new report. According to news reporting originating in Indore , India, by NewsRx journalists, research stated, "Dissolution of polysulfide int ermediates into electrolytes has been a major bottleneck in the development of t he Al-S battery. MXenes can be promising anchoring materials, even though findin g the most suitable candidates from a vast search space in a short span of time is challenging." Financial supporters for this research include University Grants Commission, Ind ia, Science Engineering Research Board (SERB), India, Council of Scientific & Industrial Research (CSIR) - India, University Grants Commission, India. The news reporters obtained a quote from the research from Indian Institute for Technology, "Herein, a combined density functional theory and machine learning ( ML) approach has been implemented to predict suitable M1M2XT2-type MXene materia ls that can optimally anchor the polysulfide intermediates. By employing various ML algorithms, the trained XGBR model is found to exhibit remarkable precision in predicting the anchoring effect of MXenes. 42 promising candidates have been identified to show optimum anchoring across the Al-S intermediates. The F and O terminal groups are found to majorly exhibit the optimum anchoring effect toward the possible polysulfide intermediates." According to the news reporters, the research concluded: "This work provides cru cial insights into the development of next-generation Al-S batteries accelerated by the ML approach, contributing to the advancement of energy storage technolog ies."
      原文链接:
    • NETL
    • NSTL

    New Findings from University of California Davis Update Understanding of Machine Learning (Improving the Precision of Shock Resuscitation By Predicting Fluid Re sponsiveness With Machine Learning and Arterial Blood Pressure Waveform Data)

    86-87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 out of Sacramento, California, by NewsRx editors, research stated, "Fluid bolus therapy (FBT) is fundamental to th e management of circulatory shock in critical care but balancing the benefits an d toxicities of FBT has proven challenging in individual patients. Improved pred ictors of the hemodynamic response to a fluid bolus, commonly referred to as a f luid challenge, are needed to limit non-beneficial fluid administration and to e nable automated clinical decision support and patient-specific precision critica l care management." Financial support for this research came from United States Department of Defens e. Our news journalists obtained a quote from the research from the University of C alifornia Davis, "In this study we retrospectively analyzed data from 394 fluid boluses from 58 pigs subjected to either hemorrhagic or distributive shock. All animals had continuous blood pressure and cardiac output monitored throughout th e study. Using this data, we developed a machine learning (ML) model to predict the hemodynamic response to a fluid challenge using only arterial blood pressure waveform data as the input. A Random Forest binary classifier referred to as th e ML fluid responsiveness algorithm (MLFRA) was trained to detect fluid responsi veness (FR), defined as a>= 15% change in cardiac stroke volume after a fluid challenge. We then compared its performance to pulse pressure variation, a commonly used metric of FR. Model performance was assessed using the area under the receiver operating characteristic curve (AURO C), confusion matrix metrics, and calibration curves plotting predicted probabil ities against observed outcomes. Across multiple train/test splits and feature s election methods designed to assess performance in the setting of small sample s ize conditions typical of large animal experiments, the MLFRA achieved an averag e AUROC, recall (sensitivity), specificity, and precision of 0.82, 0.86, 0.62. a nd 0.76, respectively. In the same datasets, pulse pressure variation had an AUR OC, recall, specificity, and precision of 0.73, 0.91, 0.49, and 0.71, respective ly. The MLFRA was generally well-calibrated across its range of predicted probab ilities and appeared to perform equally well across physiologic conditions. Thes e results suggest that ML, using only inputs from arterial blood pressure monito ring, may substantially improve the accuracy of predicting FR compared to the us e of pulse pressure variation."
      原文链接:
    • NETL
    • NSTL

    Xuzhou Medical University Reports Findings in Robotics (Outcomes of robot-assist ed versus video-assisted mediastinal mass resection during the initial learning curve)

    87-87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 reporting originating in Jiangsu, People's Repu blic of China, by NewsRx journalists, research stated, "To compare the learning curve of mediastinal mass resection between robot-assisted surgery and thoracosc opic surgery. Retrospective perioperative data were collected from 160 mediastin al mass resection cases." The news reporters obtained a quote from the research from Xuzhou Medical Univer sity, "Data included 80 initial consecutive video-assisted thoracoscopic surgery (VATS) resection cases performed from February 2018 to February 2020 and 80 ini tial consecutive robotic-assisted thoracic surgery (RATS) resection cases perfor med from March 2020 to March 2023. All cases were operated on by a thoracic surg eon. The clinical characteristics and perioperative outcomes of the two groups w ere compared. The operation time in both the RATS group and VATS group was analy zed using the cumulative sum (CUSUM) method. Based on this method, the learning curves of both groups were divided into a learning period and mastery period. Th e VATS group and the RATS group crossed the inflection point in the 27th and 21s t case, respectively. Subsequently, we found that the learning period was longer than the mastery period with statistically significant differences in terms of the operating time, and postoperative hospital stay in the VATS group and the RA TS group." According to the news reporters, the research concluded: "A certain amount of VA TS experience can shorten the learning curve for RATS."
      原文链接:
    • NETL
    • NSTL

    Karolinska Institute Reports Findings in Female Infertility (Prediction of pregn ancy-related complications in women undergoing assisted reproduction, using mach ine learning methods)

    88-89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 Reproductive Medicine - Female Infertility is the subject of a report. According to news reporting ori ginating in Stockholm, Sweden, by NewsRx journalists, research stated, "To use m achine learning methods to develop prediction models of pregnancy complications in women that conceived with Assisted Reproductive Techniques (ART). A nation-wi de register-based cohort study with prospectively collected data. all nulliparou s women who achieved birth within the first three ART treatment cycles between 2 008 and 2016 in Sweden." The news reporters obtained a quote from the research from Karolinska Institute, "Characteristics prior to use of ART, such as demographics and medical history were considered as potential predictors in the development of pre-treatment pred iction models. ART treatment details were further included in post-treatment pre diction models. Potential diagnoses of preeclampsia, placental complications (pr evia, accreta, and abruption), and postpartum hemorrhage were identified using t he international classification of diseases (ICD) recorded in the Swedish Medica l Birth and Patient registers respectively. Multiple prediction model algorithms were performed and compared for each outcome and treatment cycle, including log istic regression, decision tree model, naive Bayes classification, support vecto r machine, random forest, and gradient boosting. The performance of each model w as assessed with C statistic and nested crossvalidation was used to aid model s election and hyperparameter tunning. A total of 14,732 women gave birth after th e first (N=7302), second (N=4688) or third (N=2742) ART cycle, representing birt h rates of 24.1%, 23.8%, and 22.0%. Overa ll prediction performance did not vary much across the different methods used. I n the first cycle, the pre-treatment prediction performance was at best 66% , 66% and 60 % for pre-eclampsia, placental complicat ions and postpartum hemorrhage respectively. Inclusion of posttreatment charact eristics conferred slight improvement (around 1-5%), as did predict ion in later cycles (around 1-5%). The top influential and consiste nt predictors included age, region of residence, infertility diagnosis, and type of embryo transfer (fresh or frozen) in the later (2 and 3) cycles. Body Mass I ndex was a top predictor of preeclampsia, and influential also for placental com plications but not for postpartum hemorrhage. The combined use of demographics, medical history, and ART treatment information was not enough to confidently pre dict serious pregnancy complications in women that conceived with ART."
      原文链接:
    • NETL
    • NSTL

    Studies from University of Surrey Add New Findings in the Area of Artificial Int elligence (Coupling Artificial Intelligence Capability and Strategic Agility for Enhanced Product and Service Creativity)

    89-89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 originating from Guildford, United King dom, by NewsRx correspondents, research stated, "Creativity is key for organizat ions' ability to remain relevant in today's disruptive world. In this paper, we identify new ways in which organizations can use artificial intelligence (AI) mo re effectively for creativity." Our news journalists obtained a quote from the research from the University of S urrey, "Drawing on the resource-based view as a background mechanism, we develop ed and empirically tested a new integrative model. We collected the research dat a via a large survey of managers distributed to 600 organizations in China. Our findings show that coupling AI capability with strategic agility can directly su pport creativity. It also mediates the effects of ambidexterity, customer orient ation and competitor orientation on organizations' creativity and performance wh en developing new products and services. In addition, our findings show that cou pling AI capability and strategic agility can significantly improve firms' new p roduct creativity and new service development performance when there is a high l evel of government institutional support." According to the news editors, the research concluded: "Our findings provide the oretical and practical implications for academics and practitioners interested i n managing AI for organizational creativity." This research has been peer-reviewed.
      原文链接:
    • NETL
    • NSTL

    Reports on Machine Learning Findings from Nankai University Provide New Insights (Reveal the Main Factors and Adsorption Behavior Influencing the Adsorption of Pollutants On Natural Mineral Adsorbents: Based On Machine Learning Modeling and Dft ...)

    90-90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 Machine Learning have been presented. According to news reporting originating in Tianjin, People's Re public of China, by NewsRx journalists, research stated, "Montmorillonite, as a natural mineral adsorption material that has high research value in water pollut ion treatment. However, the adsorption capacity varies depending on the type of pollutant and the properties of the montmorillonite material, and the factors co ntrolling adsorption are not yet clear." Financial support for this research came from Tianjin science and technology sup port key projects. The news reporters obtained a quote from the research from Nankai University, "H erein, we investigated the adsorption behavior of pollutants on montmorillonite materials using density functional theory (DFT) calculations and machine learnin g modeling. Furthermore, it explores the main factors influencing their adsorpti on. The machine learning results indicate that the gradient boosting decision tr ee (GBDT) model exhibits a better fit to the experimental data compared to the o ther five machine learning models (R2 = 0.79). The higher pH levels and larger r elative molecular mass of pollutants have a positive impact on montmorillonite a dsorption. However, an increase in the proportion of oxygen atoms in the adsorbe nt material and longer hydrothermal preparation time show a trend of initially p ositive and then negative effects on the predicted results. The influence of pH on the adsorption capacity of montmorillonite adsorbents was further analyzed us ing density functional theory (DFT). Density functional theory (DFT) studies rev eal that montmorillonite primarily removes protonated sulfamethoxazole (SMZ) thr ough hydrogen bonding (N-H...O) interactions, accompanied by van der waals (O-O) and ionic bond (C-O...Al) forces under different pH conditions. The partial den sity of states (PDOS) reveals that the LUMO orbital of montmorillonite has a hig her electron accepting ability than the HOMO orbital of SMZ (p orbital peak is g reater than the S orbital) in the actual electron transfer process."
      原文链接:
    • NETL
    • NSTL

    Guy's and St Thomas' NHS Foundation Trust Reports Findings in Endometriosis (Rob otic assisted en-bloc removal of kidney, ureter and bladder wall for endometrios is)

    91-92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 Uterine Diseases and C onditions - Endometriosis is the subject of a report. According to news reportin g originating in London, United Kingdom, by NewsRx journalists, research stated, "To highlight a case where a nephroureterectomy and partial bladder cystectomy needed to be done due to endometriosis DESIGN: A video article demonstrating a c ase study and the surgical management SETTING: Ureteral endometriosis is a compl ex form of endometriosis. If left untreated, the ureter can become significantly compressed leading to hydroureter, hydronephrosis and complete loss of kidney f unction." The news reporters obtained a quote from the research from Guy's and St Thomas' NHS Foundation Trust, "This is a case of a 29-year-old patient with pelvic pain and cyclical rectal bleeding. Further investigation showed significant left hydr onephrosis and almost complete loss of left kidney function (8% on renogram). MRI revealed endometriosis involving the posterior bladder wall and distal left ureter, a large full-thickness sigmoid nodule and a large left endom etrioma. The patient underwent a robotic-assisted left nephroureterectomy, parti al cystectomy (bladder), excision of pelvic endometriosis and sigmoid resection. This procedure was performed jointly with the gynaecologist, urologist and colo rectal surgeon and the SOSURE technique was employed. The specimen (left kidney, whole length of ureter and bladder wall around ureteric orifice) was removed en -bloc through a small 3cm extension of the umbilical incision. As the distance b etween the sigmoid nodule and the anal verge was 35cm, which was above the limit of the transanal circular stapler, a limited resection was performed over a dis coid excision. The patient made a good recovery post-operatively. Ureteral endom etriosis is an indolent and aggressive condition which can lead to silent kidney loss. It is essential that hydronephrosis and hydroureter is ruled out in cases with deep endometriosis."
      原文链接:
    • NETL
    • NSTL

    University Medical Center Utrecht Reports Findings in Pancreatic Neoplasms (DNA methylation profiling enables accurate classification of non-ductal primary panc reatic neoplasms)

    92-93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 Digestive System Disea ses and Conditions - Pancreatic Neoplasms is the subject of a report. According to news reporting originating in Utrecht, Netherlands, by NewsRx journalists, re search stated, "Cytological and histopathological diagnosis of non-ductal pancre atic neoplasms can be challenging in daily clinical practice while it is crucial for therapy and prognosis. The cancer methylome is successfully used as a diagn ostic tool in other cancer entities." The news reporters obtained a quote from the research from University Medical Ce nter Utrecht, "Here, we investigate if methylation profiling can improve the dia gnostic work-up of pancreatic neoplasms. DNA methylation data were obtained for 301 primary tumors spanning six primary pancreatic neoplasms and 20 normal pancr eas controls. Neural Network, Random Forest, and XGBoost machine learning models were trained to distinguish between tumor types. Methylation data of 29 non-pan creatic neoplasms (n = 3708) were used to develop an algorithm capable of detect ing neoplasms of non-pancreatic origin. After benchmarking three state-of-the-ar t machine learning models, the Random Forest model emerged as the best classifie r with 96.9% accuracy. All classifications received a probability score reflecting the confidence of the prediction. Increasing the score threshol d, improved the Random Forest classifier performance up to 100% wi th 87% of samples with scores surpassing the cutoff. Using a logis tic regression model, detection of non-pancreatic neoplasms achieved an area und er the curve (AUC) of > 0.99. Analysis of biopsy specime ns showed concordant classification with their paired resection sample. Pancreat ic neoplasms can be classified with high accuracy based on DNA methylation signa tures. Additionally, non-pancreatic neoplasms are identified with near perfect p recision."
      原文链接:
    • NETL
    • NSTL

    Research Data from Istanbul Technical University Update Understanding of Robotic s (A process-based framework for adaptable modules in robotic clay 3D printing)

    92-92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 is now availab le. According to news reporting originating from Istanbul, Turkey, by NewsRx cor respondents, research stated, "Robotic Clay Printing (RCP) offers opportunities in sustainable architectural applications." Funders for this research include Bilimsel Arastirma Projeleri Birimi, I stanbul Teknik Universitesi. The news correspondents obtained a quote from the research from Istanbul Technic al University: "This paper presents a framework to integrate locally sourced ear th-based materials with robotic fabrication techniques while enhancing designer' s control over the process. The methodology involves two key steps: first, refin ing critical 3DP (3DP) control parameters to develop an informed toolpath algori thm. This algorithm grants designers' direct control over factors like layer hei ght and extrusion speed, enabling customization and ensuring structural integrit y." According to the news reporters, the research concluded: "Second, the framework is applied to design and RCP of an interlocking modular wall component system. E valuation encompasses the impact of 3DP control parameters, informed toolpath pl anning, RCP performance, and assembly possibilities." For more information on this research see: A process-based framework for adaptab le modules in robotic clay 3D printing. International Journal of Architectural Computing, 2024. The publisher for International Journal of Architectural Computing is SA GE Publications.
      原文链接:
    • NETL
    • NSTL

    Investigators at University of Wisconsin Detail Findings in Machine Learning (Le veraging Computer Vision-based Pose Estimation Technique In Dairy Cows for Objec tive Mobility Analysis and Scoring System)

    94-95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 Machine Learn ing have been published. According to news reporting originating from Madison, W isconsin, by NewsRx correspondents, research stated, "This study investigated th e feasibility of utilizing a computer vision-based pose estimation technique for quantitative mobility analysis in dairy cows, specifically focusing on commonly used variables in visual mobility scoring. Additionally, the study determined t he potential of a machine learning classification algorithm to predict mobility scores based on data obtained from the aforementioned pose estimation technique. " Financial support for this research came from Grants-in-Aid for Scientific Resea rch (KAKENHI). Our news editors obtained a quote from the research from the University of Wisco nsin, "A dataset comprising 204 individual cows' video clips was collected, with each video clip recorded from a sideview perspective during walking. The cows were scored using a 4-level mobility scoring system: Score 0 (good mobility: 64 cows), Score 1 (imperfect mobility: 65 cows), Score 2 (impaired mobility: 57 cow s), and Score 3 (severely impaired mobility: 18 cows). The video clips were anal yzed using a software for cattle pose estimation, capable of detecting 25 keypoi nts and generating time-series XY-coordinates of those keypoints. Based on the d ata, a total of 17 mobility variables were calculated, such as head bob, stride length, stride duration, walking speed, back angle, and range of motion in leg j oints. The measurements of these variables closely align with previously reporte d and comparable data derived from precise sensing technologies (e.g., walkway p ressure mapping systems) and labor-intensive techniques (e.g., attaching markers to cows and manually annotating on sequential images). The relationships betwee n these measurements and the mobility scores were also consistent with the findi ngs reported before. To account for the limited number of cows classified as Sco re3, the cows classified as Score 2 and Score 3 were merged into a single class, and a classification model for the 3-level mobility score (Score 0, 1, and 2 + 3) was developed using a random forest algorithm. The model's performance was ev aluated using a repeated holdout data split method. In this process, the dataset was randomly divided into an 80 % training set and a 20 % test set, and this was replicated ten times to ensure a robust assessment of the model's predictive ability. The overall 3-class classification performance of t he model resulted in a weighted kappa coefficient of 0.69 and area under the cur ve of the receiver operating characteristic curve of 0.86."
      原文链接:
    • NETL
    • NSTL