查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on Robotics - Robotics and Automation are presented in a new report. According to news reporting out of Syd ney, Australia, by NewsRx editors, research stated, “Recently, heatmap-oriented approaches have demonstrated their state-of-the-art performance in pedestrian tr ajectory prediction by exploiting scene information from input images before run ning the encoder. To align the image and trajectory information, existing method s centre the scene images to agents’ last observed locations or convert trajecto ry sequences into images.” Our news journalists obtained a quote from the research from the University of N ew South Wales, “Such alignment processes cause repetitive executions of the sce ne encoder for each pedestrian in an input image while there are often many pede strians in an image, thus leading to significant memory consumption. In this let ter, we address this problem by fully decoupling scene and trajectory feature ex tractions so that the scene information is only encoded once for an input image regardless of the number of pedestrians in the image. To do this, we directly ex tract temporal information from trajectories in a global pixel coordinate system . Then, we propose a transformer-based heatmap decoder to model the complex inte raction between high-level trajectory and image features via trajectory self-att ention, trajectory-to-image cross-attention and image-to-trajectory cross-attent ion layers. We also introduce scene counterfactual learning to alleviate the ove r-focusing on the trajectory features and knowledge transfer from Segment Anythi ng Model to simplify the training.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Researchers detail new data in Robotic s - Robotics and Automation. According to news reporting originating in Bonn, Ge rmany, by NewsRx journalists, research stated, “Basically all multi-sensor syste ms must calibrate their sensors to exploit their full potential for state estima tion such as mapping and localization. In this letter, we investigate the proble m of extrinsic and intrinsic calibration of perception systems.” Financial supporters for this research include German Research Foundation (DFG), European Union’s Horizon Europe Research and Innovation Programme, Federal Mini stry of Education & Research (BMBF).
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 originating from Shenzhen, People’s Rep ublic of China, by NewsRx correspondents, research stated, “Heterostructures for med by transition metal dichalcogenides (TMDs) and two-dimensional layered halid e perovskites (2D-LHPs) have attracted significant attention due to their unique optoelectronic properties. However, theoretical studies face challenges due to the large number of atoms and the need for lattice matching.” Our news journalists obtained a quote from the research from the Southern Univer sity of Science and Technology (SUSTech), “With the discovery of more 2D-LHPs, t here is an urgent need for methods to rapidly predict and screen TMDs/2D-LHPs he terostructures. This study employs first-principles calculations to perform high -throughput computations on 602 TMDs/2D-LHPs heterostructures. Results show that different combinations exhibit diverse band alignments, with MoS and WS more li kely to form type- II heterostructures with 2D-LHPs. The highest photoelectric co nversion efficiency of type-II structures reaches 23.26%, demonstra ting potential applications in solar cells. Notably, some MoS/2D-LHPs form type- S structures, showing promise in photocatalysis. Furthermore, we found that TMDs can significantly affect the conformation of organic molecules in 2D-LHPs, thus modulating the electronic properties of the heterostructures. To overcome compu tational cost limitations, we constructed a crystal graph convolutional neural n etwork model based on the calculated data to predict the electronic properties o f TMDs/2D-LHPs heterostructures.”
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – Investigators publish new report on robotics. Acc ording to news reporting out of Russian University of Transport by NewsRx editor s, research stated, “Machine learning and artificial intelligence, capable of ma king decisions on their own, have become indispensable tools for optimizing ware house operations. The use of lifting equipment on a mobile platform on mechanica l wheels in warehouses has a high degree of practical implementation, since the platform in question can move in any direction without U-turns.” The news correspondents obtained a quote from the research from Russian Universi ty of Transport: “Kinematic studies of the movement of the robotic arm on the pl atform under consideration make it possible to opti-mize its movement and behavi or in conditions of movement in a confined space with movable and fixed obstacle s, which, from the standpoint of creating a mathematical model of platform contr ol, are input parameters that determine the operating conditions of the platform . The methodology for conducting experimental studies and their analysis allow y ou to optimize the management and behavior of the platform in practice. The plat form movement algorithm is developed taking into account its features and is des igned to select the optimal route and navigation accuracy under changing space c onditions (moving and stationary objects). In order to verify and evaluate the e ffectiveness of the localization and path planning algorithm in order to improve the control system of the mobile platform on mecanum wheels, modeling and simul ation of the presented model were carried out, which made it possible to assess the kinematic parameters of the platform to achieve better results. The kinemati c analysis made it possible to carry out a qualitative and quantitative assessme nt of the features of the movement of the platform behavior in space with variou s input data. Modeling and simulation of the path localization and planning algo rithm made it possible to test its effectiveness in various operating conditions .”
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 artificial intelligence is now available. According to news originating from Bern University Hospital b y NewsRx correspondents, research stated, “The study aimed to evaluate the impac t of AI assistance on pulmonary nodule detection rates among radiology residents and senior radiologists, along with assessing the effectiveness of two differen t commercialy available AI software systems in improving detection rates and Lun gRADS classification in chest CT.” The news editors obtained a quote from the research from Bern University Hospita l: “The study cohort included 198 participants with 221 pulmonary nodules. Resid ents’ mean detection rate increased significantly from 64 to 77% w ith AI assist, while seniors’ detection rate remained largely unchanged (85% vs. 86%). Residents showed significant improvement in segmental nod ule localization with AI assistance, seniors did not. Software 2 slightly outper formed software 1 in increasing detection rates (67-77% vs. 80-86% ), but neither significantly affected LungRADS classification.”
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 - Computational Intelligence. According to news reporting origina ting in Wuhan, People’s Republic of China, by NewsRx journalists, research state d, “A long-standing problem remains with the heterogeneous clients in Federated Learning (FL), who often have diverse gains and requirements for the trained mod el, while their contributions are hard to evaluate due to the privacy-preserving training. Existing works mainly rely on single-dimension metric to calculate cl ients’ contributions as aggregation weights, which however may damage the social fairness, thus discouraging the cooperation willingness of worse-off clients an d causing the revenue instability.” Financial support for this research came from National Natural Science Foundatio n of China (NSFC).
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Cardiovascular Disease s and Conditions - Thrombosis is the subject of a report. According to news repo rting from Hunan, People’s Republic of China, by NewsRx journalists, research st ated, “Central venous access devices (CVADs) are integral to cancer treatment. H owever, catheter-related thrombosis (CRT) poses a considerable risk to patient s afety.” The news correspondents obtained a quote from the research from Central South Un iversity, “It interrupts treatment; delays therapy; prolongs hospitalisation; an d increases the physical, psychological and financial burden of patients. Our st udy aims to construct and validate a predictive model for CRT risk in patients w ith cancer. It offers the possibility to identify independent risk factors for C RT and prevent CRT in patients with cancer. We prospectively followed patients w ith cancer and CVAD at Xiangya Hospital of Central South University from January 2021 to December 2022 until catheter removal. Patients with CRT who met the cri teria were taken as the case group. Two patients with cancer but without CRT dia gnosed in the same month that a patient with cancer and CRT was diagnosed were s elected by using a random number table to form a control group. Data from patien ts with CVAD placement in Qinghai University Affiliated Hospital and Hainan Prov incial People’s Hospital (January 2023 to June 2023) were used for the external validation of the optimal model. The incidence rate of CRT in patients with canc er was 5.02% (539/10 736). Amongst different malignant tumour type s, head and neck (9.66%), haematological (6.97%) and r espiratory (6.58%) tumours had the highest risks. Amongst catheter types, haemodialysis (13.91%), central venous (8.39%) and peripherally inserted central (4.68%) catheters were associated with the highest risks. A total of 500 patients with CRT and 1000 without CRT p articipated in model construction and were randomly assigned to the training (n = 1050) or testing (n = 450) groups. We identified 11 independent risk factors, including age, catheterisation method, catheter valve, catheter material, infect ion, insertion history, D-dimer concentration, operation history, anaemia, diabe tes and targeted drugs. The logistic regression model had the best discriminativ e ability amongst the three models. It had an area under the curve (AUC) of 0.86 8 (0.846-0.890) for the training group. The external validation AUC was 0.708 (0 .618-0.797). The calibration curve of the nomogram model was consistent with the ideal curve. Moreover, the Hosmer-Lemeshow test showed a good fit (P > 0.05) and high net benefit value for the clinical decision curve. The nomogram model constructed in this study can predict the risk of CRT in patients with can cer.”
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 in Genoa, Italy, by NewsRx journalis ts, research stated, “This work introduces a novel parallel elastic actuation pr inciple designed to provide torque compensation for legged robots. Unlike existi ng solutions, the proposed concept leverages a nitrogen N$_ {2}$ gas spring combined with a cam roll er module to generate a highly customizable torque compensation profile for the target leg joint.” Financial support for this research came from European Union’s Horizon Europe Fr amework Programme.
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 originating in Tianjin , People’s Republic of China, by NewsRx journalists, research stated, “Artificia l intelligence is already widely utilized in gastroenterology. This study aims t o comprehensively evaluate the research hotspots and development trends within t he field of AI in gastroenterology by employing bibliometric techniques to scrut inize geographical distribution, authorship, affiliated institutions, keyword us age, references, and other pertinent data contained within relevant publications .” Financial support for this research came from National Key Research and Developm ent Program of China.
查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Coronavirus - COVID-19 is the subject of a report. According to news reporting originating from Zhejia ng, People’s Republic of China, by NewsRx correspondents, research stated, “This cross-sectional study investigates the factors that contribute to academic resi lience among nursing students during COVID-19 pandemic. A cross-sectional study. ” Our news editors obtained a quote from the research from Taizhou Central Hospita l (Taizhou University Hospital), “A survey was conducted in a general hospital b etween November and December 2022. The Nursing Student Academic Resilience Inven tory (NSARI) model was used to assess the academic resilience of 96 nursing stud ents. The Boruta method was then used to identify the core factors influencing o verall academic resilience, and rough set analysis was used to analyse the behav ioural patterns associated with these factors. Attributes were categorised into three importance levels. Three statistically significant attributes were identif ied (‘I earn my patient’s trust by making suitable communication,’ ‘I receive su pport from my instructors,’ and ‘I try to endure academic hardship’) based on co mparison with shadow attributes. The rough set analysis showed nine main behavio ural patterns. Random forest, support vector machines, and backpropagation artif icial neural networks were used to test the performance of the model, with accur acies ranging from 73.0% to 76.9%.”
NETL
NSTL