查看更多>>摘要：Current study results on Machine Learning have been published. According to news reporting originating from Changsha, People’s Republic of China, by NewsRx correspondents, research stated, “Rapid acquisition of rock mechanical parameters and accurate identification of rock drillability are important to guide the safe construction of different scale drilling engineering (wells and boreholes) and high-efficient excavation of rock engineering. A database is established based on 281 sets of drilling parameters and rock mechanical parameters collected from four micro drilling experiments.” Funders for this research include National Natural Science Foundation of China (NSFC), Science and Technology Innovation Program of Hunan Province, China, Fundamental Research Funds for the Central Universities. Our news editors obtained a quote from the research from the School of Resources & Safety Engineering, “The drilling parameters in the database include drilling force (F), torque (T), rotational speed (N), and rate of penetration (Ⅴ), from which the specific energy (SE) and the drillability index (I-d) are calculated. With these parameters as input, fitting regression analysis and machine learning regression are used to predict the uniaxial compressive strength (UCS) of rocks. Furthermore, TOPSIS-RSR method is used to achieve rock drillability classification, and machine learning classification methods are used to perceive and identify drillability. In the prediction and recognition process, the accuracies of different methods are compared to determine the optimal model.”
查看更多>>摘要：Investigators publish new report on Machine Learning. According to news reporting originating in Shanghai, People’s Republic of China, by NewsRx journalists, research stated, “Skin Corrosion/ Irritation (Corr./Irrit.) has long been a health hazard in the Globally Harmonized System (GHS). Several in silico models have been built to predict Skin Corr./Irrit. as an alternative to the increasingly restricted animal testing.” Funders for this research include National Natural Science Foundation of China (NSFC), National Key Research and Development Program of China, National Natural Science Foundation of China (NSFC), Shanghai Frontiers Science Center of Optogenetic Techniques for Cell Metabolism (Shanghai Municipal Education Commission). The news reporters obtained a quote from the research from the East China University of Science and Technology, “However, current studies are limited by data amount/quality and model availability. To address these issues, we compiled a traceable consensus GHS data set comprising 731 Corr., 1283 Irrit., and 1205 negative (Neg.) samples from 6 governmental databases and 2 external data sets. Then, a series of binary classifiers were developed with five machine learning (ML) algorithms and six molecular representations. For 10-fold cross-validation, the best Corr. vs Neg. classifier achieved an Area Under the Receiver Operating Characteristic Curve (AUC) of 97.1%, while the best Irrit. vs Neg. classifier achieved an AUC of 84.7%. Compared with existing in silico tools on external validation, our Attentive FP classifiers showed the highest metrics on Corr. vs Neg. and the second highest accuracy on Irrit. vs Neg. The SHapley Additive exPlanation approach was further applied to figure out important molecular features, and the attention weights were visualized to perform interpretable prediction. Structural alerts associated with Skin Corr./Irrit. were also identified.
查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting originating in London, United Kingdom, by NewsRx journalists, research stated, “Ultrasound-based models exist to support the classification of adnexal masses but are subjective and rely upon ultrasound expertise. We aimed to develop an end-to-end machine learning (ML) model capable of automating the classification of adnexal masses.” The news reporters obtained a quote from the research from Imperial College London, “In this retrospective study, transvaginal ultrasound scan images with linked diagnoses (ultrasound subjective assessment or histology) were extracted and segmented from Imperial College Healthcare, UK (ICH development dataset; n = 577 masses; 1444 images) and Morgagni-Pierantoni Hospital, Italy (MPH external dataset; n = 184 masses; 476 images). A segmentation and classification model was developed using convolutional neural networks and traditional radiomics features. Dice surface coefficient (DICE) was used to measure segmentation performance and area under the ROC curve (AUC), F1-score and recall for classification performance. The ICH and MPH datasets had a median age of 45 (IQR 35-60) and 48 (IQR 38-57) years old and consisted of 23.1% and 31.5% malignant cases, respectively. The best segmentation model achieved a DICE score of 0.85 ? 0.01, 0.88 ? 0.01 and 0.85 ? 0.01 in the ICH training, ICH validation and MPH test sets. The best classification model achieved a recall of 1.00 and F1-score of 0.88 (AUC:0.93), 0.94 (AUC:0.89) and 0.83 (AUC:0.90) in the ICH training, ICH validation and MPH test sets, respectively. We have developed an end-to-end radiomics-based model capable of adnexal mass segmentation and classification, with a comparable predictive performance (AUC 0.90) to the published performance of expert subjective assessment (gold standard), and current risk models.”
查看更多>>摘要：New research on Oncology - Cervical Cancer is the subject of a report. According to news reporting originating from Toronto, Canada, by NewsRx correspondents, research stated, “A randomized non-inferiority trial showed worse survival in women with early-stage cervical cancer treated with radical hysterectomy by minimally invasive approach compared to laparotomy; the impact of surgical approach on survival following radical trachelectomy is unknown. To examine oncologic outcomes in women with early-stage cervical cancer who underwent robotic or vaginal radical trachelectomy at Canadian cancer centers with the highest volumes of radical trachelectomy procedures.” Our news editors obtained a quote from the research from the University of Toronto, “Retrospective multi-centre cohort analysis which includes patients who had surgery between 2006 and 2019. Women with International FIGO 2009 stage IA-IB cervical cancer who underwent radical trachelectomy and lymph node assessment were grouped by surgical approach (vaginal versus robotic surgery). A total of 197 patients were included from 4 regional referral centres. 56 women underwent robotic radical trachelectomy and 141 underwent vaginal radical trachelectomy. All patients had lymph node assessment by a minimally invasive technique. Median age was 32 years, median tumor size was 12 mm, and median depth of invasion was 5 mm. Recurrence-free survival was 97% in both groups at a median follow-up of 57 months. On multivariable analysis, after adjusting for previously chosen confounders (high risk pathologic criteria, tumor size, and LVSI) there was no statistically significant difference in PFS between the 2 groups (HR 2.1, 95%CI 0.3-7.1, p = 0.5). Tumor size larger than 2 cm (HR 9.4, 95%CI 2.8-26, p = 0.003) was the only variable predictive of recurrence. Survival outcomes were excellent in both cohorts of patients undergoing robotic vs. vaginal radical trachelectomy.”
查看更多>>摘要：Current study results on Machine Learning have been published. According to news originating from Ciudad de Mexico, Mexico, by NewsRx correspondents, research stated, “We present a methodology leveraging machine learning models to generate interatomic potentials for crystalline materials. This approach is rooted in the material’s crystallography in question.” Financial supporters for this research include LAREC Laboratory of the Institute of Physics, UNAM, LAREC Laboratory of the Institute of Physics, UNAM, Mexico. Our news journalists obtained a quote from the research from the National Autonomous University of Mexico (UNAM), “Specifically, we tap into the occupied Wyckoff sites, extracting the defining features that encapsulate the atomic local order in the material. Our choice for the target variable is the formation energy per atom, derived from the total energy of the structure’s representative cell. Our machine learning model’s architecture depends on the occupied Wyckoff sites. The diversity of these occupied sites conditions the layering scheme within the model. Atoms occupying a particular Wyckoff site were modeled with the architecture and learning parameters linked to the respective layer. To illustrate our method, we developed an interatomic potential for atomic interactions in alpha-alumina. For training purposes, we generated the samples through quantum mechanical computations. The evaluation of the learned interatomic potential involved conducting molecular dynamics calculations on a 2 x 2 x 2 supercell, yielding formation energies per atom deviating by less than 1.0 meV from the quantum mechanics results. The methodology described here paves the way for further innovations, potentially ushering in the creation of interatomic potentials that can be utilized for more than one material.”
查看更多>>摘要：New research on artificial intelligence is the subject of a new report. According to news reporting out of Kozani, Greece, by NewsRx editors, research stated, “Remote sensing stands out as one of the most widely used operations in the field. In this research area, UAVs offer full coverage of large cultivation areas in a few minutes and provide orthomosaic images with valuable information based on multispectral cameras.” Funders for this research include European Union’s Horizon Europe Research And Innovation Programme. The news journalists obtained a quote from the research from University of Western Macedonia: “Especially for orchards, it is helpful to isolate each tree and then calculate the preferred vegetation indices separately. Thus, tree detection and crown extraction is another important research area in the domain of Smart Farming. In this paper, we propose an innovative tree detection method based on machine learning, designed to isolate each individual tree in an orchard. First, we evaluate the effectiveness of Detectron2 and YOLOv8 object detection algorithms in identifying individual trees and generating corresponding masks. Both algorithms yield satisfactory results in cherry tree detection, with the best F1-Score up to 94.85%. In the second stage, we apply a method based on OTSU thresholding to improve the provided masks and precisely cover the crowns of the detected trees.”
查看更多>>摘要：Current study results on Machine Learning have been published. According to news reporting from Newark, New Jersey, by NewsRx journalists, research stated, “Project bundling is a strategy that combines several infrastructure projects into a single contract to improve the overall performance of projects. While previous research efforts have been conducted on certain aspects of project bundling, no research particularly focused on studying the opportunities and challenges of project bundling and the associated patterns between them.” Funders for this research include US Department of Transportation, Office of the Assistant Secretary for Research and Technology (OST-R), Center for Advanced Infrastructure and Transportation (CAIT) Region 2 UTC Consortium Led by Rutgers, The State University of New Jersey. The news correspondents obtained a quote from the research from the New Jersey Institute of Technology, “To this end, this paper addresses this knowledge gap. Based on data from 30 case studies that implemented project bundling strategies in the US, various opportunities and challenges were extracted. In addition, spectral clustering was implemented to cluster the identified opportunities and challenges based on the strength of their interconnectivities. Also, association rules mining analysis was conducted to determine key patterns. The results identified a total of 27 opportunities and 27 challenges for project bundling. Furthermore, the most critical associations between the opportunities and challenges were determined within each of the obtained clusters. The outcomes also reflected that while many opportunities and challenges could individually affect the performance of bundled projects, other opportunities and challenges could also result due to a combination of factors that might not be perceived to be critical on the individual level but rather become critical when combined with other factors.”
查看更多>>摘要：New research on Artificial Intelligence is the subject of a report. According to news reporting originating from Leicestershire, United Kingdom, by NewsRx correspondents, research stated, “This study proposes a bi-level framework for real-time crash risk forecasting (RTCF) for signalised intersections, leveraging the temporal dependency among crash risks of contiguous time slices. At the first level of RTCF, a non-stationary generalised extreme value (GEV) model is developed to estimate the rear-end crash risk in real time (i.e., at a signal cycle level).” Financial support for this research came from QUT Postgraduate Research Scholarship. Our news editors obtained a quote from the research from Loughborough University, “Artificial intelligence techniques, like YOLO and DeepSort were used to extract traffic conflicts and time-varying covariates from traffic movement videos at three signalised intersections in Queensland, Australia. The estimated crash frequency from the non-stationary GEV model is compared against the historical crashes for the study locations (serving as ground truth), and the results indicate a close match between the estimated and observed crashes. Notably, the estimated mean crashes lie within the confidence intervals of observed crashes, further demonstrating the accuracy of the extreme value model. At the second level of RTCF, the estimated signal cycle crash risk is fed to a recurrent neural network to predict the crash risk of the subsequent signal cycles. Results reveal that the model can reasonably estimate crash risk for the next 20-25 min.”
查看更多>>摘要：Data detailed on Robotics have been presented. According to news reporting originating from Jinan, People’s Republic of China, by NewsRx correspondents, research stated, “Skill generalization across different tasks is currently a challenging task for robots. As for recent works based on robot learning, substantial environmental interaction costs or abundant expert data are usually needed, thus causing great harm to the robot or the operating object.” Financial supporters for this research include Guangdong Key Research and Development Program, National Natural Science Foundation of China (NSFC), National Natural Science Foundation of China (NSFC). Our news editors obtained a quote from the research from Shandong University, “In this article, featureselected adaptation transfer is proposed, aiming at accelerating the network learning process, and reducing the harm caused by the interaction process. Based on the domain adaptation, the source domain data with small maximum mean discrepancy to the target domain are extracted to pretrain the target domain policy. By extracting the shared features of the source domain and the target domain, the knowledge transfer between old task and new task is realized. Moreover, the data, more favorable to the target domain, are selected to update the network and further improve the stability of network training.”
查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting originating from Shenzhen, People’s Republic of China, by NewsRx correspondents, research stated, “Machine learning potentials (MLPs) have attracted significant attention in computational chemistry and materials science due to their high accuracy and computational efficiency. The proper selection of atomic structures is crucial for developing reliable MLPs.” Financial supporters for this research include National Natural Science Foundation of China, National Key R&D Program of China, Shenzhen Fundamental Research Funding, Shenzhen Key Laboratory of Micro/Nano-Porous Functional Materials, National Science Foundation. Our news editors obtained a quote from the research from the Southern University of Science and Technology (SUSTech), “Insufficient or redundant atomic structures can impede the training process and potentially result in a poor quality MLP. Here, we propose a local-environment-guided screening algorithm for efficient dataset selection in MLP development. The algorithm utilizes a local environment bank to store unique local environments of atoms. The dissimilarity between a particular local environment and those stored in the bank is evaluated using the Euclidean distance. A new structure is selected only if its local environment is significantly different from those already present in the bank. Consequently, the bank is then updated with all the new local environments found in the selected structure. To demonstrate the effectiveness of our algorithm, we applied it to select structures for a Ge system and a Pd13H2 particle system. The algorithm reduced the training data size by around 80% for both without compromising the performance of the MLP models. We verified that the results were independent of the selection and ordering of the initial structures. We also compared the performance of our method with the farthest point sampling algorithm, and the results show that our algorithm is superior in both robustness and computational efficiency.”
NETL
NSTL
Journal Of Central South Univ
Amer Chemical Soc
Mdpi
Asce-Amer Soc Civil Engineers
IEEE