期刊,Robotics & Machine Learning Daily News 2024年卷Jun.19期_国家学术搜索

期刊信息/Journal information

Robotics & Machine Learning Daily News

NewsRx

主办单位：NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News

正式出版

收录年代

Data on Major Depressive Disorder Reported by Bo Lin and Colleagues (Graph convo lutional network with attention mechanism improve major depressive depression di agnosis based on plasma biomarkers and neuroimaging data)

105-106页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Major Depressive Disorder is the subject of a report. According to news reporting from Hangzhou, People's Republi c of China, by NewsRx journalists, research stated, "The absence of clinically-v alidated biomarkers or objective protocols hinders effective major depressive di sorder (MDD) diagnosis. Compared to healthy control (HC), MDD exhibits anomalies in plasma protein levels and neuroimaging presentations." The news correspondents obtained a quote from the research, "Despite extensive m achine learning studies in psychiatric diagnosis, a reliable tool integrating mu lti-modality data is still lacking. In this study, blood samples from 100 MDD an d 100 HC were analyzed, along with MRI images from 46 MDD and 49 HC. Here, we de vised a novel algorithm, integrating graph neural networks and attention modules , for MDD diagnosis based on inflammatory cytokines, neurotrophic factors, and O rexin A levels in the blood samples. Model performance was assessed via accuracy and F1 value in 3-fold cross-validation, comparing with 9 traditional algorithm s. We then applied our algorithm to a dataset containing both the aforementioned protein quantifications and neuroimages, evaluating if integrating neuroimages into the model improves performance. Compared to HC, MDD showed significant alte rations in plasma protein levels and gray matter volume revealed by MRI. Our new algorithm exhibited superior performance, achieving an F1 value and accuracy of 0.9436 and 94.08 %, respectively. Integration of neuroimaging data enhanced our novel algorithm's performance, resulting in an improved F1 value a nd accuracy, reaching 0.9543 and 95.06 %. This single-center study with a small sample size requires future evaluations on a larger test set for im proved reliability."

原文链接:

NETL
NSTL

New Findings from Federal University Rio Grande do Sul in the Area of Machine Le arning Described (Allok: a Machine Learning Approach for Efficient Graph Executi on On Cpu-gpu Clusters)

106-107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 from Port o Alegre, Brazil, by NewsRx correspondents, research stated, "The unprecedented increase in interconnected data has driven the development of efficient graph an alytics for extensive data analysis, resulting in improvements across various do mains. Prior work has focused on optimizing graph execution for both CPUs and GP Us while overlooking the scalability of graph applications and the selection of an ideal architecture." Financial support for this research came from Conselho Nacional de Desenvolvimen to Cientfico e Tecnolgico. Our news editors obtained a quote from the research from Federal University Rio Grande do Sul, "Thus, we propose Allok, a flexible graph processing framework th at aids in selecting the optimal processing architecture (CPU or GPU) for a batc h of graph applications while also optimizing number of threads on CPUs. Allok r elies solely on high-level graph features to make decisions without the need for further application execution."

原文链接:

NETL
NSTL

Findings from Zhejiang University Provides New Data about Artificial Intelligenc e (Resistance To Artificial Intelligence In Health Care: Literature Review, Conc eptual Framework, and Research Agenda)

107-108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 Artificial In telligence have been published. According to news reporting originating from Zhe jiang, People's Republic of China, by NewsRx correspondents, research stated, "R esistance has historically been considered a salient obstacle to the implementat ion of information systems, including healthcare information technology. However , artificial intelligence in health care (AIH) reshapes the relationships among technologies, physicians, and patients, and the nature of resistance has thus be en transformed." Funders for this research include National Natural Science Foundation of China ( NSFC), Ministry of Science and Technology (STI 2030 Major Projects), Joint PhD P rogrammes (PolyU-ZJU) Leading. Our news editors obtained a quote from the research from Zhejiang University, "T o gain a comprehensive understanding of this phenomenon, this study systematical ly examines resistance to AIH across health care providers and recipients by rev iewing 94 articles. Combining innovation resistance theory and the sociotechnica l perspective, we develop an overarching framework to synthesize research and pr ovide agendas for future research."

原文链接:

NETL
NSTL

Research Findings from School of Art Update Understanding of Intelligent Systems (Classical music recommendation algorithm on art market audience expansion unde r deep learning)

108-109页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Investigators publish new report on intelligent s ystems. According to news reporting originating from Chongqing, People's Republi c of China, by NewsRx correspondents, research stated, "The purpose of the study is to help users know about their favorite music and expand art market audience s." The news correspondents obtained a quote from the research from School of Art: " First, the personalized recommendation data of classical music are obtained base d on the deep learning recommendation algorithm technology, artificial intellige nce, and music playback software of users. Second, a systematic experiment is co nducted on the improved recommendation algorithm, and a classical music dataset is established and used for model training and user testing. Then, the network m odel of the classical music recommendation algorithm is constructed through the typical convolutional neural network model, and the optimal parameters suitable for the model are found."

原文链接:

NETL
NSTL

Studies from University of Science and Technology Beijing in the Area of Machine Learning Described (Crack Pattern Identification In Cementitious Materials Base d On Acoustic Emission and Machine Learning)

109-110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 Machine Learning is th e subject of a report. According to news originating from Beijing, People's Repu blic of China, by NewsRx correspondents, research stated, "The cracking patterns in cementitious materials before failure are closely related to acoustic emissi on (AE) monitoring signals. Traditional rise angle -average frequency analysis m ethods rely on empirical judgment for boundary line determination, lacking effec tive automated recognition methods to distinguish between tensile, shear, and mi xed crack types."

原文链接:

NETL
NSTL

Recent Studies from University Grenoble Alpes Add New Data to Robotics (Planning Socially Expressive Mobile Robot Trajectories)

110-110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 robotics have been published. According to news reporting out of Grenoble, France, by NewsRx editors, research stated, "Many mobile robotics applications require robots to n avigate around humans who may interpret the robot's motion in terms of social at titudes and intentions." The news reporters obtained a quote from the research from University Grenoble A lpes: "It is essential to understand which aspects of the robot's motion are rel ated to such perceptions so that we may design appropriate navigation algorithms . Current works in social navigation tend to strive towards a single ideal style of motion defined with respect to concepts such as comfort, naturalness, or leg ibility. These algorithms cannot be configured to alter trajectory features to c ontrol the social interpretations made by humans. In this work, we firstly prese nt logistic regression models based on perception experiments linking human perc eptions to a corpus of linear velocity profiles, establishing that various traje ctory features impact human social perception of the robot. Secondly, we formula te a trajectory planning problem in the form of a constrained optimization, usin g novel constraints that can be selectively applied to shape the trajectory such that it generates the desired social perception."

原文链接:

NETL
NSTL

University of Naples Federico II Reports Findings in Robotics [The role of RObotic surgery in EMergency setting (ROEM): protocol for a multicen tre, observational, prospective international study on the use of robotic platfo rm in emergency ...]

111-112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 Naples, Italy, by News Rx journalists, research stated, "Robotic surgery has gained widespread acceptan ce in elective interventions, yet its role in emergency procedures remains under explored. While the 2021 WSES position paper discussed limited studies on the ap plication of robotics in emergency general surgery, it recommended strict patien t selection, adequate training, and improved platform accessibility." The news reporters obtained a quote from the research from the University of Nap les Federico II, "This prospective study aims to define the role of robotic surg ery in emergency settings, evaluating intraoperative and postoperative outcomes and assessing its feasibility and safety. The ROEM study is an observational, pr ospective, multicentre, international analysis of clinically stable adult patien ts undergoing robotic surgery for emergency treatment of acute pathologies inclu ding diverticulitis, cholecystitis, and obstructed hernias. Data collection incl udes patient demographics and intervention details. Furthermore, data relating t o the operating theatre team and the surgical instruments used will be collected in order to conduct a cost analysis. The study plans to enrol at least 500 pati ents from 50 participating centres, with each centre having a local lead and col laborators. All data will be collected and stored online through a secure server running the Research Electronic Data Capture (REDCap) web application. Ethical considerations and data governance will be paramount, requiring local ethical co mmittee approvals from participating centres. Current literature and expert cons ensus suggest the feasibility of robotic surgery in emergencies with proper supp ort. However, challenges include staff training, scheduling conflicts with elect ive surgeries, and increased costs. The ROEM study seeks to contribute valuable data on the safety, feasibility, and costeffectiveness of robotic surgery in em ergency settings, focusing on specific pathologies. Previous studies on cholecys titis, abdominal hernias, and diverticulitis provide insights into the benefits and challenges of robotic approaches."

原文链接:

NETL
NSTL

First Hospital of Shanxi Medical University Reports Findings in Machine Learning (Machine learning methods for adult OSAHS risk prediction)

112-113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 Machine Learning is th e subject of a report. According to news reporting originating in Taiyuan, Peopl e's Republic of China, by NewsRx journalists, research stated, "Obstructive slee p apnea hypopnea syndrome (OSAHS) is a common disease that can cause multiple or gan damage in the whole body. Our aim was to use machine learning (ML) to build an independent polysomnography (PSG) model to analyze risk factors and predict O SAHS." The news reporters obtained a quote from the research from the First Hospital of Shanxi Medical University, "Clinical data of 2064 snoring patients who underwen t physical examination in the Health Management Center of the First Affiliated H ospital of Shanxi Medical University from July 2018 to July 2023 were retrospect ively collected, involving 24 characteristic variables. Then they were randomly divided into training group and verification group according to the ratio of 7:3 . By analyzing the importance of these features, it was concluded that LDL-C, Cr , common carotid artery plaque, A1c and BMI made major contributions to OSAHS. M oreover, five kinds of machine learning algorithm models such as logistic regres sion, support vector machine, Boosting, Random Forest and MLP were further estab lished, and cross validation was used to adjust the model hyperparameters to det ermine the final prediction model. We compared the accuracy, Precision, Recall r ate, F1-score and AUC indexes of the model, and finally obtained that MLP was th e optimal model with an accuracy of 85.80%, Precision of 0.89, Reca ll of 0.75, F1-score of 0.82, and AUC of 0.938. We established the risk predicti on model of OSAHS using ML method, and proved that the MLP model performed best among the five ML models."

原文链接:

NETL
NSTL

New Robotics Study Findings Have Been Reported from Shanghai University (Motion Performance Study of 2upr-1rps/2r Hybrid Robot Based On Kinematics, Dynamics, an d Stiffness Modeling)

113-113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 Robotics have been pr esented. According to news reporting from Shanghai, People's Republic of China, by NewsRx journalists, research stated, "The unique structural characteristics o f hybrid robots, such as few degrees-of-freedom (DOF) and redundant constraints, lead to a series of challenges in the establishment of theoretical models. Howe ver, these theoretical models are indispensable parts of motion control." The news correspondents obtained a quote from the research from Shanghai Univers ity, "Therefore, this paper focuses on establishing the kinematics, dynamics, an d stiffness models for an Exechon-like hybrid robot, which are then used for err or compensation and velocity planning to improve the robot's motion performance. First, the kinematic model is derived through intermediate parameters and the k inematics equivalent chains. By analyzing the parasitic motion due to few DOF, t he redundant equations in the model are eliminated to obtain the solution of inv erse kinematics. Second, based on the beam element, the optimal equivalent confi guration of the moving platform which connects the parallel part and serial part is determined, and then an entire equivalent structure of the robot is formed. It helps establish the stiffness model by using the matrix structure analysis me thod. Next, the dynamic model is established by combining the Newton-Euler metho d with co-deformation theory to solve the underdetermined dynamic equations caus ed by redundant constraints. Finally, the compensation method is designed based on the stiffness model and kinematic model to improve the end positioning accura cy of the robot; the velocity planning algorithm is designed based on the dynami c model and kinematic model to enhance the smoothness of the robot motion."

原文链接:

NETL
NSTL

New Findings on Robotics Described by Investigators at Zhejiang University (Desi gn of Soft Microjoint To Improve Robotic Cell Micromanipulation Flexibility)

114-114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 Ro botics. According to news reporting originating from Hangzhou, People's Republic of China, by NewsRx correspondents, research stated, "Dexterity micromanipulati on is a significant topic in the field of robotics. Herein, a novel robotic rota ting microjoint controlled by an exogenous magnetic field based on magnetic prog rammable soft materials, which brings more dexterity to the micromanipulation ta sk is proposed." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Funding of Central Government Guiding Local Science and Tech nology Development.

原文链接:

NETL
NSTL