查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-The National Center for Supercomputing Applications was recently awarded $4.9 million of supplemental fun ding from the U.S. National Science Foundation (NSF) for Delta and an additional $4.9 million for DeltaAI to expand the potential capabilities of t he soon-to-launch system by nearly 50 percent. NCSA originally received nearly $25 million from NSF in 2023 to dep loy and operate DeltaAI, an advanced computing and data resource that will be a companion system to Delta. DeltaAI will triple NCSA's AI-focused computing capac ity and greatly expand the capacity available within the NSF-funded advanced com puting ecosystem. "DeltaAI will provide powerful capabilities for simulation and data science, wit h a strong emphasis on support for AI, which is in growing demand across many fi elds of science and engineering, said NCSA Director Bill Gropp during the DeltaA I announcement. "This project seeks to expand the use of AI methods in research by providing easier access, training offerings and other support to promote a wi der demographic of researchers. These project goals align with our greater missi on at NCSA and the NSF effort to democratize high-performance computing."
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 originating from Florence, Ital y, by NewsRx correspondents, research stated, "The increasing frequency and inte nsity of extreme weather events are accelerating the mechanisms of surface degra dation of heritage buildings, and it is therefore appropriate to find automatic techniques to reduce the time and cost of monitoring and to support their planne d conservation." Funders for this research include Spoke 7; European Union-next Generation Eu. The news reporters obtained a quote from the research from University of Florenc e: "A fully automated approach is presented here for the segmentation and classi fication of the architectural elements that make up one of the facades of Palazz o Pitti. The aim of this analysis is to provide tools for a more detailed assess ment of the risk of detachment of parts of the pietraforte sandstone elements. M achine learning techniques were applied for the segmentation and classification of information from a DEM obtained via a photogrammetric drone survey. An unsupe rvised geometry-based classification of the segmented objects was performed usin g K-means for identifying the most vulnerable elements according to their shapes ."
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 - Pattern Recognition and Artificial Intelligence. According to n ews reporting originating from Wuhan, People's Republic of China, by NewsRx corr espondents, research stated, "As the demand for recognizing irregular text in na tural scenes increases, people are increasingly realizing the value of such appl ications, such as license plate recognition systems, image search, handwriting r ecognition, and autonomous driving, which are profoundly changing our lives in t he field of text recognition. Recent studies have shown that the recognition of curved text and perspective text has become an important challenge in the field of text recognition, and the correction of curved text is a key step to achieve accurate recognition."
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New study results on artificial intell igence have been published. According to news reporting originating from the Chi nese Academy of Medical Sciences by NewsRx correspondents, research stated, "Thi s study aimed to develop a higher performance nomogram based on explainable mach ine learning methods, and to predict the risk of death of stroke patients within 30 days based on clinical characteristics on the first day of intensive care un its (ICU) admission. Data relating to stroke patients were extracted from the Me dical Information Marketplace of the Intensive Care (MIMIC) IV and III database. " Funders for this research include Beijing Natural Science Foundation; The Cams I nnovation Fund For Medical Sciences; The Program of Chinese Academy of Medical S ciences. Our news journalists obtained a quote from the research from Chinese Academy of Medical Sciences: "The LightGBM machine learning approach together with Shapely additive explanations (termed as explain machine learning, EML) was used to sele ct clinical features and define cut-off points for the selected features. These selected features and cut-off points were then evaluated using the Cox proportio nal hazards regression model and Kaplan-Meier survival curves. Finally, logistic regression-based nomograms for predicting 30-day mortality of stroke patients w ere constructed using original variables and variables dichotomized by cut-off p oints, respectively. The performance of two nomograms were evaluated in overall and individual dimension. A total of 2982 stroke patients and 64 clinical featur es were included, and the 30-day mortality rate was 23.6% in the M IMIC-IV datasets. 10 variables (‘sofa (sepsis-related organ failure assessment)' , ‘minimum glucose', ‘maximum sodium', ‘age', ‘mean spo2 (blood oxygen saturatio n)', ‘maximum temperature', ‘maximum heart rate', ‘minimum bun (blood urea nitro gen)', ‘minimum wbc (white blood cells)' and ‘charlson comorbidity index') and r espective cut-off points were defined from the EML. In the Cox proportional haza rds regression model (Cox regression) and Kaplan-Meier survival curves, after gr ouping stroke patients according to the cut-off point of each variable, patients belonging to the high-risk subgroup were associated with higher 30-day mortalit y than those in the low-risk subgroup. The evaluation of nomograms found that th e EML-based nomogram not only outperformed the conventional nomogram in NIR (net reclassification index), brier score and clinical net benefits in overall dimen sion, but also significant improved in individual dimension especially for low ‘ maximum temperature' patients."
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 out of Islamabad, Pa kistan, by NewsRx editors, research stated, "Intrusion Detection Systems (IDSs) play a crucial role in safeguarding network infrastructures from cyber threats a nd ensuring the integrity of highly sensitive data. Conventional IDS technologie s, although successful in achieving high levels of accuracy, frequently encounte r substantial model bias." Funders for this research include Princess Nourah Bint Abdulrahman University. The news journalists obtained a quote from the research from Iqra University: "T his bias is primarily caused by imbalances in the data and the lack of relevance of certain features. This study aims to tackle these challenges by proposing an advanced machine learning (ML) based IDS that minimizes misclassification error s and corrects model bias. As a result, the predictive accuracy and generalizabi lity of the IDS are significantly improved. The proposed system employs advanced feature selection techniques, such as Recursive Feature Elimination (RFE), sequ ential feature selection (SFS), and statistical feature selection, to refine the input feature set and minimize the impact of non-predictive attributes. In addi tion, this work incorporates data resampling methods such as Synthetic Minority Oversampling Technique and Edited Nearest Neighbor (SMOTE_ENN), Ada ptive Synthetic Sampling (ADASYN), and Synthetic Minority Oversampling Technique -Tomek Links (SMOTE_Tomek) to address class imbalance and improve t he accuracy of the model. The experimental results indicate that our proposed mo del, especially when utilizing the random forest (RF) algorithm, surpasses exist ing models regarding accuracy, precision, recall, and F Score across different d ata resampling methods."
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 reporting out of Singapore, Sing apore, by NewsRx editors, research stated, "The clinical management of type 2 di abetes mellitus (T2DM) presents a significant challenge due to the constantly ev olving clinical practice guidelines and growing array of drug classes available. Evidence suggests that artificial intelligence (AI)-enabled clinical decision s upport systems (CDSSs) have proven to be effective in assisting clinicians with informed decision-making." Our news journalists obtained a quote from the research from the Duke-National U niversity of Singapore Medical School, "Despite the merits of AI-driven CDSSs, a significant research gap exists concerning the early-stage implementation and a doption of AI-enabled CDSSs in T2DM management. This study aimed to explore the perspectives of clinicians on the use and impact of the AI-enabled Prescription Advisory (APA) tool, developed using a multi-institution diabetes registry and i mplemented in specialist endocrinology clinics, and the challenges to its adopti on and application. We conducted focus group discussions using a semistructured interview guide with purposively selected endocrinologists from a tertiary hospi tal. The focus group discussions were audio-recorded and transcribed verbatim. D ata were thematically analyzed. A total of 13 clinicians participated in 4 focus group discussions. Our findings suggest that the APA tool offered several usefu l features to assist clinicians in effectively managing T2DM. Specifically, clin icians viewed the AI-generated medication alterations as a good knowledge resour ce in supporting the clinician's decision-making on drug modifications at the po int of care, particularly for patients with comorbidities. The complication risk prediction was seen as positively impacting patient care by facilitating early doctorpatient communication and initiating prompt clinical responses. However, the interpretability of the risk scores, concerns about overreliance and automat ion bias, and issues surrounding accountability and liability hindered the adopt ion of the APA tool in clinical practice."
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 from London, United Kingdom, by NewsR x journalists, research stated, "Touch offers important non-verbal possibilities for socioaffective communication. Yet most digital communications lack capabili ties regarding exchanging affective tactile messages (tactile emoticons)." Financial supporters for this research include European Research Council, HORIZO N EUROPE European Research Council, University College London, University Colleg e London, University College London. The news correspondents obtained a quote from the research from University Colle ge London (UCL), "Additionally, previous studies on tactile emoticons have not c apitalised on knowledge about the affective effects of certain mechanoreceptors in the human skin, e.g., the C-Tactile (CT) system. Here, we examined whether ge ntle manual stroking delivered in velocities known to optimally activate the CT system (defined as ‘tactile emoticons'), during lab-simulated social media commu nications could convey increased feelings of social support and other prosocial intentions compared to (1) either stroking touch at CT sub-optimal velocities, o r (2) standard visual emoticons. Participants (N = 36) felt more social intent w ith CToptimal compared to sub-optimal velocities, or visual emoticons. In a sec ond, preregistered study (N = 52), we investigated whether combining visual emot icons with tactile emoticons, this time delivered at CT-optimal velocities by a soft robotic device, could enhance the perception of prosocial intentions and af fect participants' physiological measures (e.g., skin conductance rate) in compa rison to visual emoticons alone. Visuotactile emoticons conveyed more social int ent overall and in anxious participants affected physiological measures more tha n visual emoticons."
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 out of Rio de Janeiro, Braz il, by NewsRx editors, research stated, "The Machine learning widespread adoptio n has inadvertently led to the amplification of societal biases and discriminati on, with many consequential decisions now influenced by data -driven systems. In this scenario, fair machine learning techniques has become a frontier for AI re searchers and practitioners." Our news journalists obtained a quote from the research from Federal University Rio de Janeiro, "Addressing fairness is intricate; one cannot solely rely on the data used to train models or the metrics that assess them, as this data is ofte n the primary source of bias - akin to noisy data. This paper delves into the co nvergence of these two research domains, highlighting the similarities and diffe rences between fairness and noise in machine learning. We introduce the Fair Tra nsition Loss, a novel method for fair classification inspired by label noise rob ustness techniques. Traditional loss functions tend to ignore distributions of s ensitive features and their impact on outcomes. Our approach uses transition mat rices to adjust predicted label probabilities based on this ignored data."
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 originating from Moscow, Russia, by Ne wsRx correspondents, research stated, "Solar filaments are well-known tracers of polarity inversion lines that separate two opposite magnetic polarities on the solar photosphere. Because observations of filaments began long before the syste matic observations of solar magnetic fields, historical filament catalogs can fa cilitate the reconstruction of magnetic polarity maps at times when direct magne tic observations were not yet available." Financial support for this research came from Russian Science Foundation (RSF).
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 originating from West Bengal , India, by NewsRx correspondents, research stated, "The current study aims to q uantify the relationship between hydrological richness in river and riparian wet land habitats and fragmentation analysis. Eight relevant parameters, such as the frequency of water presence, hydroperiod, and proximity to the river, have bee n incorporated into four models-two statistical models (Shannon entropy and Logi stic Regression) and two machine learning models (artificial neural network and random forest)-in order to investigate wetland hydrological richness." Our news editors obtained a quote from the research from the Department of Geogr aphy, "The models are evaluated using statistical techniques such as ROC curves, and field-based validation is also performed. The information about the best-pe rforming models (random forest for machine learning and logistic regression for statistical models) is valuable for understanding the predictive capabilities of the models applied. RF model identified 168.43 km2, 110.91 km2, 70.13 km2, and 39.15 km2 areas as having very rich and rich water richness zones in 1990, 2000, 2010, and 2020, respectively. The percentage of poor and very poor areas has ra pidly increased from 29.7% in 1990 to 55.35% in 2020 . Additionally, the relationship between wetland fragmentation and hydrological richness is assessed. Wetland fragmentation and shrinking core areas due to anth ropogenic intrusion significantly impact the hydrological richness of wetlands. This study will provide important insights into the changing state of wetlands o ver time, especially concerning the impact of anthropogenic activities on hydrol ogical richness."
NETL
NSTL