期刊,Robotics & Machine Learning Daily News 2024年卷Sep.30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

Like humans, artificial minds can learn by thinking

1-2页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Some of the greatest discoveries don't come merely from observations but from thinking. Einstein developed theories ab out relativity through thought experiments, and Galileo derived insights about g ravity through mental simulations. A review published September 18 in the journa l Trends in Cognitive Sciences shows that this process of thinking is not exclus ive to humans. Artificial intelligence, too, is capable of self-correction and a rriving at new conclusions through "learning by thinking." "There are some recent demonstrations of what looks like learning by thinking in AI, particularly in large language models," says author Tania Lombrozo, a profe ssor of psychology and co-director of the Natural and Artificial Minds initiativ e at Princeton University. "Sometimes ChatGPT will correct itself without being explicitly told. That's similar to what happens when people are engaged in learn ing by thinking."

原文链接:

NETL
NSTL

Miguel Hernandez University Reports Findings in Machine Learning (A calculator f or musculoskeletal injuries prediction in surgeons: a machine learning approach)

2-3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 Alicante, Spai n, by NewsRx journalists, research stated, "Surgical specialists experience sign ificant musculoskeletal strain as a consequence of their profession, a domain wi thin the healthcare system often recognized for the pronounced impact of such is sues. The aim of this study is to calculate the risk of presenting musculoskelet al injuries in surgeons after surgical practice." The news reporters obtained a quote from the research from Miguel Hernandez Univ ersity, "Crosssectional study carried out using an online form (12/2021-03/2022 ) aimed at members of the Spanish Association of Surgeons. Demographic variables on physical and professional activity were recorded, as well as musculoskeletal pain (MSP) associated with surgical activity. Univariate and multivariate analy sis were conducted to identify risk factors associated with the development of M SP based on personalized surgical activity. To achieve this, a risk algorithm wa s computed and an online machine learning calculator was created to predict them . Physiotherapeutic recommendations were generated to address and Alleviate each MSP. A total of 651 surgeons (112 trainees, 539 specialists). 90.6% reported MSP related to surgical practice, 60% needed any therapeu tic measure and 11.7% required a medical leave. In the long term, MSP was most common in the cervical and lumbar regions (52.4, 58.5% , respectively). StatisticAlly significant risk factors (OR CI 95%) were for trunk pain, long interventions without breaks (3.02, 1.65-5.54). Obesi ty, indicated by BMI, to lumbar pain (4.36, 1.84-12.1), while an inappropriate l aparoscopic screen location was associated with cervical and trunk pain (1.95, 1 .28-2.98 and 2.16, 1.37-3.44, respectively). A predictive model and an online ca lculator were developed to assess MSP risk. Furthermore, a need for enhanced erg onomics training was identified by 89.6% of surgeons. The prevalen ce of MSP among surgeons is a prevalent but often overlooked health concern."

原文链接:

NETL
NSTL

Studies from University of Quebec Trois-Rivieres Provide New Data on Machine Lea rning (Assessing the potential responses of ten important fisheries species to a changing climate with machine learning and observational data across the provin ce ...)

3-3页

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 artific ial intelligence. According to news reporting out of Quebec, Canada, by NewsRx e ditors, research stated, "Models are needed to predict changes in game fish abun dances with respect to climatic factors undergoing change, but such models are o ften limited by data availability and the capacity of statistical methods to fit chAllenging ecological datasets." Our news journalists obtained a quote from the research from University of Quebe c Trois-Rivieres: "We use current methods in machine learning to describe the re sponses of ten fish species to climatic factors across Quebec. We assembled a ne w province-wide, synthetic dataset of fish catches spanning almost 50 years and 6000 sites. Extreme Gradient Boosting (XGBoost) models revealed that climatic fa ctors are more important predictors of trends in game fish catches than nuisance factors (sampling gear, time), lending support to collating other heterogeneous datasets for analyses. Mean annual temperature and precipitation were the most important drivers of species catches."

原文链接:

NETL
NSTL

Wuxi Institute of Technology Reports Findings in Machine Learning (Co-firing cha racteristic prediction of solid waste and coal for supercritical CO2 power cycle based on CFD simulation and machine learning algorithm)

4-4页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Machine Learning is the subject o f a report. According to news originating from Wuxi, People's Republic of China, by NewsRx correspondents, research stated, "The co-firing technology of combust ible solid waste (CSW) and coal in the supercritical CO (S-CO) circulating fluid ized bed (CFB) can effectively deal with domestic waste, promote social and envi ronmental benefits, improve the coal conversion rate, and reduce pollutant emiss ion. This study focuses on the co-firing characteristics of CSW and coal under S -CO power cycle, and simulations are conducted by employing Multiphase Particle- in-cell (MP-PIC) method integrated with the comprehensive chemical reaction mode ls in a 300 MW S-CO CFB boiler." Our news journalists obtained a quote from the research from the Wuxi Institute of Technology, "Effects of operating parameters including fuel mixture proportio n and first stage stoichiometry on the gas emission characteristics are further analyzed. Based on training and testing database based on the simulation results , a novel Improved Whale Optimization Algorithm and Bi-dictionary Long Short-Ter m Memory (IWOABiLSTM) algorithm model is established to predict CFB temperature , NOx emission concentration, and SO emission concentration, respectively. CO and SO decrease with the coal mass ratio of the fuel mixture increasing, while NOx increases. With the increase of first stage stoichiometry, CO increases, NOx de clines, and the change of SO is not obvious."

原文链接:

NETL
NSTL

Reports on Intelligent Systems from Guangdong Polytechnical Normal University Pr ovide New Insights (Multi-order Hypergraph Convolutional Networks Integrated Wit h Self-supervised Learning)

5-5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 - Int elligent Systems is the subject of a report. According to news originating from Guangzhou, People's Republic of China, by NewsRx correspondents, research stated , "Hypergraphs, as a powerful representation of information, effectively and nat urAlly depict complex and non-pair-wise relationships in the real world. Hypergr aph representation learning is useful for exploring complex relationships implic it in hypergraphs." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Guangdong Provincial Key Laboratory Project of Intellectual Property and Big Data, Special Projects for Key Fields in Higher Education of Gu angdong, China, National Natural Science Foundation of Guangdong Province, Key Field R&D Plan Project of Guanzhou, Youth Innovation Project of the Department of Education of Guangdong Province, China.

原文链接:

NETL
NSTL

Carol Davila University of Medicine and Pharmacy Reports Findings in Biomarkers (Development and validation of cardiometabolic risk predictive models based on L DL oxidation and candidate geromarkers from the MARK-AGE data)

6-6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 Diagnostics and Screen ing - Biomarkers is the subject of a report. According to news reporting from Bu charest, Romania, by NewsRx journalists, research stated, "The predictive value of the susceptibility to oxidation of LDL particles (LDLox) in cardiometabolic r isk assessment is incompletely understood. The main objective of the current stu dy was to assess its relationship with other relevant biomarkers and cardiometab olic risk factors from MARK-AGE data." The news correspondents obtained a quote from the research from the Carol Davila University of Medicine and Pharmacy, "A cross-sectional observational study was carried out on 1089 subjects (528 men and 561 women), aged 40-75 years old, ran domly recruited age- and sex-stratified individuals from the general population. A correlation analysis exploring the relationships between LDLox and relevant b iomarkers was undertaken, as well as the development and validation of several m achine learning algorithms, for estimating the risk of the combined status of hi gh blood pressure and obesity for the MARK-AGE subjects. The machine learning mo dels yielded Area Under the Receiver Operating Characteristic Curve Score rangin g 0.783-0.839 for the internal validation, while the external validation resulte d in an Under the Receiver Operating Characteristic Curve Score between 0.648-0. 787, with the variables based on LDLox reaching significant importance within th e obtained predictions. The current study offers novel insights regarding the co mbined effects of LDL oxidation and other ageing markers on cardiometabolic risk ."

原文链接:

NETL
NSTL

Abdullah Gul University Reports Findings in Colon Cancer (CCPred: Global and pop ulation-specific colorectal cancer prediction and metagenomic biomarker identifi cation at different molecular levels using machine learning techniques)

7-7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 Oncology - Colon Cance r is the subject of a report. According to news originating from Kayseri, Turkey , by NewsRx correspondents, research stated, "Colorectal cancer (CRC) ranks as the third most common cancer globAlly and the second leading cause of cancer-rela ted deaths. Recent research highlights the pivotal role of the gut microbiota in CRC development and progression." Our news journalists obtained a quote from the research from Abdullah Gul Univer sity, "Understanding the complex interplay between disease development and metag enomic data is essential for CRC diagnosis and treatment. Current computational models employ machine learning to identify metagenomic biomarkers associated wit h CRC, yet there is a need to improve their accuracy through a holistic biologic al knowledge perspective. This study aims to evaluate CRC-associated metagenomic data at species, enzymes, and pathway levels via conducting global and populati on-specific analyses. These analyses utilize relative abundance values from huma n gut microbiome sequencing data and robust classification models are built for disease prediction and biomarker identification. For global CRC prediction and b iomarker identification, the features that are identified by SelectKBest (SKB), Information Gain (IG), and Extreme Gradient Boosting (XGBoost) methods are combi ned. Population-based analysis includes within-population, leaveone- dataset-out (LODO) and cross-population approaches. Four classification algorithms are empl oyed for CRC classification. Random Forest achieved an AUC of 0.83 for species d ata, 0.78 for enzyme data and 0.76 for pathway data globAlly. On the global scal e, potential taxonomic biomarkers include ruthenibacterium lactatiformanas; enzy me biomarkers include RNA 2' 3' cyclic 3' phosphodiesterase; and pathway biomark ers include pyruvate fermentation to acetone pathway. This study underscores the potential of machine learning models trained on metagenomic data for improved d isease prediction and biomarker discovery."

原文链接:

NETL
NSTL

University of Dundee Reports Findings in Machine Learning (Electroconvulsive the rapy response and remission in moderate to severe depressive illness: a decade o f national Scottish data)

8-8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 out of Dundee, United Kingdom , by NewsRx editors, research stated, "Despite strong evidence of efficacy of el ectroconvulsive therapy (ECT) in the treatment of depression, no sensitive and s pecific predictors of ECT response have been identified. Previous meta-analyses have suggested some pre-treatment associations with response at a population lev el." Our news journalists obtained a quote from the research from the University of D undee, "Using 10 years (2009-2018) of routinely collected Scottish data of peopl e with moderate to severe depression ( = 2074) receiving ECT we tested two hypot heses: (a) that there were significant group-level associations between post-ECT clinical outcomes and pre-ECT clinical variables and (b) that it was possible t o develop a method for predicting illness remission for individual patients usin g machine learning. Data were analysed on a group level using descriptive statis tics and association analyses as well as using individual patient prediction wit h machine learning methodologies, including cross-validation. ECT is highly effe ctive for moderate to severe depression, with a response rate of 73% and remission rate of 51%. ECT response is associated with older ag e, psychotic symptoms, necessity for urgent intervention, severe distress, psych omotor retardation, previous good response, lack of medication resistance, and c onsent status. Remission has the same associations except for necessity for urge nt intervention and, in addition, history of recurrent depression and low suicid e risk. It is possible to predict remission with ECT with an accuracy of 61% . Pre-ECT clinical variables are associated with both response and remission and can help predict individual response to ECT."

原文链接:

NETL
NSTL

Findings in Artificial Intelligence Reported from University of Ha'il (SIFT: Sif ting file types-application of explainable artificial intelligence in cyber fore nsics)

9-9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 artificial intelligen ce have been presented. According to news reporting out of the University of Ha' il by NewsRx editors, research stated, "Artificial Intelligence (AI) is being ap plied to improve the efficiency of software systems used in various domains, esp eciAlly in the health and forensic sciences. Explainable AI (XAI) is one of the fields of AI that interprets and explains the methods used in AI." The news reporters obtained a quote from the research from University of Ha'il: "One of the techniques used in XAI to provide such interpretations is by computi ng the relevance of the input features to the output of an AI model. File fragme nt classification is one of the vital issues of file carving in Cyber Forensics (CF) and becomes chAllenging when the filesystem metadata is missing. Other majo r chAllenges it faces are: proliferation of file formats, file embeddings, autom ation, We leverage and utilize interpretations provided by XAI to optimize the c lassification of file fragments and propose a novel sifting approach, named SIFT (Sifting File Types). SIFT employs TF-IDF to assign weight to a byte (feature), which is used to select features from a file fragment. Threshold-based LIME and SHAP (the two XAI techniques) feature relevance values are computed for the sel ected features to optimize file fragment classification. To improve multinomial classification, a Multilayer Perceptron model is developed and optimized with fi ve hidden layers, each layer with $$i\times n$$ i x n neurons, where i = the layer number a nd n = the total number of classes in the dataset."

原文链接:

NETL
NSTL

New Computational Intelligence Findings from Hunan Normal University Discussed ( Two Znn-based Unified Smc Schemes for Finite/fixed/preassigned-time Synchronizat ion of Chaotic Systems)

9-10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 Machine Learning - Comp utational Intelligence is now available.According to news reporting originating from Changsha, People's Republic of China, by NewsRx correspondents, research s tated, "Sliding mode control (SMC) is widely recognized as an effective control scheme for the synchronization of chaotic systems (CSs). However, numerous exist ing SMC schemes for chaos synchronization assume a noise-free environment and de pend on multiple parameters." Funders for this research include Natural Science Foundation of Hunan Province, National Natural Science Foundation of China (NSFC), Postgraduate Scientific Res earch Innovation Project of Hunan Province, Scientific Research Project of Hunan Provincial Department of Education.

原文链接:

NETL
NSTL