期刊,Robotics & Machine Learning Daily News 2024年卷Jun.24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

Four-legged, dog-like robot 'sniffs' hazardous gases in inaccessible environment s

1-1页

查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Nightmare material or truly man's best friend? A team of researchers equipped a dog-like quadruped robot with a mechan ized arm that takes air samples from potentially treacherous situations, such as an abandoned building or fire. The robot dog walks samples to a person who scre ens them for potentially hazardous compounds, says the team that published its s tudy in ACS' Analytical Chemistry. While the system needs further refinement, de monstrations show its potential value in dangerous conditions. Testing the air for dangerous chemicals in risky workplaces or after an accident , such as a fire, is an important but very dangerous task for scientists and tec hnicians. To keep humans out of harm's way, Bin Hu and colleagues are developing mobile detection systems for hazardous gases and volatile organic compounds (VO Cs) by building remote-controlled sampling devices like aerial drones and tiny r emotely operated ships. The team's latest entry into this mechanical menagerie i s a dog-like robot with an articulated testing arm mounted on its back. The inde pendently controlled arm is loaded with three needle trap devices (NTDs) that ca n collect air samples at any point during the robot's terrestrial mission.

原文链接:

NETL
NSTL

Research Findings from Universitas Tarumanagara Update Understanding of Artifici al Intelligence [Application of Artificial Intelligence (AI) in Construction Management: A Systematic Literature Review]

1-2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 artificial intell igence are discussed in a new report. According to Intell igence (AI) technology is increasingly being adopted in the construction industr y in the current era. AI can be integrated with digital technologies such as Bui lding Information Modeling (BIM), Internet of Things (IoT), and Smart Vision (SV )." Our news correspondents obtained a quote from the research from Universitas Taru managara: "The integration of AI with digital technology has the potential to en hance efficiency, productivity, accuracy, and safety in construction project. Th is systematic literature review focuses on studying the implementation of AI in construction management, aiming to assess the current role of AI and anticipate future trends in the field. The findings of systematic literature review reveal that AI has been employed in construction projects for tasks such as estimation, resource management, improvement of workplace safety, material selection, struc tural analysis, and more. The advancements in digital technology, including the influence of 5G connectivity, have further augmented the sophistication of AI ap plications in the current era. The systematic literature review also delves into the study of machine learning and deep learning, both of which are pivotal in A I technology for executing predictive tasks, analyses, and automated decision-ma king. Despite the vast potential of AI, this review identifies various challenge s associated with the technology, particularly concerning data security."

原文链接:

NETL
NSTL

University of Wisconsin Madison Researcher Reports on Findings in Machine Learni ng (Improving Subseasonal Soil Moisture and Evaporative Stress Index Forecasts t hrough Machine Learning: The Role of Initial Land State versus Dynamical Model O utput)

2-3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 artificial intell igence are discussed in a new report. According to news reporting from Madison, Wisconsin, by NewsRx journalists, research stated, "The effect of machine learni ng and other enhancements on statistical-dynamical forecasts of soil moisture (0 -10cm and 0-100cm) and a reference evapotranspiration fraction (Evaporative Stre ss Index, ESI) on sub-seasonal time scales (15-28 days) are explored." The news journalists obtained a quote from the research from University of Wisco nsin Madison: "The predictors include the current and past land surface conditio ns, and dynamical model hindcasts from the Sub-seasonal to Seasonal (S2S) Predic tion Project. When the methods are enhanced with machine learning and other impr ovements, the increases in skill are almost exclusively coming from predictors d rawn from observations of current and past land surface states. This suggests th at operational S2S flash drought forecasts should focus on optimizing use of inf ormation on current conditions rather than on integrating dynamically based fore casts, given the current state of knowledge. Nonlinear machine learning methods lead to improved skill over linear methods for soil moisture but not for ESI. Im provements for both soil moisture and ESI are realized by increasing the sample size by including surrounding grid points in training and increasing the number of predictors."

原文链接:

NETL
NSTL

Study Findings from Soldotna Provide New Insights into Robotics (Programming Met hods for Industrial Robotics and Expanding Applications)

3-4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 Soldotna, Alaska, by NewsRx editors, research stated, "Industrial robotics industry is presently experiencin g significant growth and is generally recognized as a crucial element within the industrial sector." The news journalists obtained a quote from the research from Department of Mathe matics: "The technology offered by this system is standardized and well-suited f or a wide range of automated operations. This research investigates the industri al robotics industry and its use of standardized technologies to automate divers e operational procedures. This article explores the two primary tactics used in the process of robotization, with the diverse levels of cooperation seen between human beings and robots. The present study examines the control and programming approaches used in the field of information retrieval, together with the notabl e technological advancements that have arisen within this area. Moreover, it inc orporates the many challenges and limitations faced during the installation of a utomated industrial robot systems."

原文链接:

NETL
NSTL

Yunnan University Researchers Describe Recent Advances in Sequencing Technology (NmTHC: a hybrid error correction method based on a generative neural machine tr anslation model with transfer learning)

4-5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 sequenc ing technology. According to news reporting from Yunnan University by NewsRx jou rnalists, research stated, "Backgrounds The single-pass long reads generated by third-generation sequencing technology exhibit a higher error rate. However, the circular consensus sequencing (CCS) produces shorter reads." Funders for this research include National Natural Science Foundation of China. The news reporters obtained a quote from the research from Yunnan University: "T hus, it is effective to manage the error rate of long reads algorithmically with the help of the homologous high-precision and low-cost short reads from the Nex t Generation Sequencing (NGS) technology. In this work, a hybrid error correctio n method (NmTHC) based on a generative neural machine translation model is propo sed to automatically capture discrepancies within the aligned regions of long re ads and short reads, as well as the contextual relationships within the long rea ds themselves for error correction. Akin to natural language sequences, the long read can be regarded as a special 'genetic language' and be processed with the idea of generative neural networks. The algorithm builds a sequence-to-sequence( seq2seq) framework with Recurrent Neural Network (RNN) as the core layer. The be fore and post-corrected long reads are regarded as the sentences in the source a nd target language of translation, and the alignment information of long reads w ith short reads is used to create the special corpus for training. The well-trai ned model can be used to predict the corrected long read. NmTHC outperforms the latest mainstream hybrid error correction methods on real-world datasets from tw o mainstream platforms, including PacBio and Nanopore. Our experimental evaluati on results demonstrate that NmTHC can align more bases with the reference genome without any segmenting in the six benchmark datasets, proving that it enhances alignment identity without sacrificing any length advantages of long reads."

原文链接:

NETL
NSTL

University of Texas Austin Researcher Illuminates Research in Artificial Intelli gence (ChatGPT has Aced the Test of Understanding in College Economics: Now What ?)

5-5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 from Austin, Texas, by NewsRx jour nalists, research stated, "The Test of Understanding in College Economics (TUCE) is a standardized test of economics knowledge performed in the United States wh ich primarily targets principles-level understanding." The news editors obtained a quote from the research from University of Texas Aus tin: "We asked ChatGPT to complete the TUCE. ChatGPT ranked in the 91st percenti le for Microeconomics and the 99th percentile for Macroeconomics when compared t o students who take the TUCE exam at the end of their principles course. The res ults show that ChatGPT is capable of providing answers that exceed the mean resp onses of students across all institutions." According to the news editors, the research concluded: "The emergence of artific ial intelligence presents a significant challenge to traditional assessment meth ods in higher education. An important implication of this finding is that educat ors will likely need to redesign their curriculum in at least one of the followi ng three ways: reintroduce proctored, in-person assessments; augment learning wi th chatbots; and/or increase the prevalence of experiential learning projects th at artificial intelligence struggles to replicate well."

原文链接:

NETL
NSTL

New Intelligent Systems Study Findings Recently Were Reported by Researchers at Hunan University (An Improved Fruit Fly Optimization Algorithm With Q-learning f or Solving Distributed Permutation Flow Shop Scheduling Problems)

6-6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 Machine Learn ing - Intelligent Systems. According to news reporting originating from Hunan, P eople's Republic of China, by NewsRx correspondents, research stated, "The distr ibuted permutation flow shop scheduling problem (DPFSP) is one of the hottest is sues in the context of economic globalization. In this paper, a Q-learning enhan ced fruit fly optimization algorithm (QFOA) is proposed to solve the DPFSP with the goal of minimizing the makespan." Funders for this research include National Natural Science Foundation of China ( NSFC), National Natural Science Foundation of China (NSFC), Natural Science Foun dation of Hunan Province, Young Talent of Lifting Engineering for Science and Te chnology in Hunan Province, Outstanding Youth Project of Education Department of Hunan Province, Key Project of Education Department of Hunan Province of china.

原文链接:

NETL
NSTL

Duzce University Researcher Describes Research in Machine Learning (An Efficient Approach for Automatic Fault Classification Based on Data Balance and One-Dimen sional Deep Learning)

7-7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 from Duzce, Turkey, by NewsRx jour nalists, research stated, "Predictive maintenance (PdM) is implemented to effici ently manage maintenance schedules of machinery and equipment in manufacturing b y predicting potential faults with advanced technologies such as sensors, data a nalysis, and machine learning algorithms. This paper introduces a study of diffe rent methodologies for automatically classifying the failures in PdM data." The news journalists obtained a quote from the research from Duzce University: " We first present the performance evaluation of fault classification performed by shallow machine learning (SML) methods such as Decision Trees, Support Vector M achines, k-Nearest Neighbors, and one-dimensional deep learning (DL) techniques like 1D-LeNet, 1D-AlexNet, and 1D-VGG16. Then, we apply normalization, which is a scaling technique in which features are shifted and rescaled in the dataset. W e reapply classification algorithms to the normalized dataset and present the pe rformance tables in comparison with the first results we obtained. Moreover, in contrast to existing studies in the literature, we generate balanced dataset gro ups by randomly selecting normal data and all faulty data for all fault types fr om the original dataset. The dataset groups are generated with 100 different rep etitions, recording performance scores for each one and presenting the maximum s cores. All methods utilized in the study are similarly employed on these groups. "

原文链接:

NETL
NSTL

Study Findings from Central South University of Forestry and Technology Provide New Insights into Machine Learning (Estimating the Vertical Distribution of Biom ass in Subtropical Tree Species Using an Integrated Random Forest and Least Squa res ...)

8-8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 out of Changsha, Peo ple's Republic of China, by NewsRx editors, research stated, "Accurate quantific ation of forest biomass (FB) is the key to assessing the carbon budget of terres trial ecosystems." Financial supporters for this research include Natural Science Foundation of Hun an Province; Key Project of Hunan Education Department; Scientific Research Proj ect of Hunan Education Department; Key Discipline of The State Forestry Administ ration; "double First-class" Cultivating Subject of Hunan Province. The news journalists obtained a quote from the research from Central South Unive rsity of Forestry and Technology: "Using remote sensing to apply inversion techn iques to the estimation of FBs has recently become a research trend. However, th e limitations of vertical scale analysis methods and the nonlinear distribution of forest biomass stratification have led to significant uncertainties in FB est imation. In this study, the biomass characteristics of forest vertical stratific ation were considered, and based on the integration of random forest and least s quares (RF-LS) models, the FB prediction potential improved. The results indicat ed that compared with traditional biomass estimation methods, the overall R2 of FB retrieval increased by 12.01%, and the root mean square error (R MSE) decreased by 7.50 Mg·hm-2. The RF-LS model we established exhibited better performance in FB inversion and simulation assessments. The indicators of forest canopy height, soil organic matter content, and red-edge chlorophyll vegetation index had greater impacts on FB estimation."

原文链接:

NETL
NSTL

Central South University Reports Findings in Endometriosis (Unraveling the signi ficance of AGPAT4 for the pathogenesis of endometriosis via a multi-omics approa ch)

9-9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 Uterine Diseases and C onditions - Endometriosis is the subject of a report. According to news reportin g out of Changsha, People's Republic of China, by NewsRx editors, research state d, "Endometriosis is characterized by the ectopic proliferation of endometrial c ells, posing considerable diagnostic and therapeutic challenges. Our study inves tigates AGPAT4's involvement in endometriosis pathogenesis, aiming to unveil new therapeutic targets." Financial support for this research came from Natural Science Foundation of Huna n Province. Our news journalists obtained a quote from the research from Central South Unive rsity, "Our investigation by analyzing eQTL data from GWAS for preliminary scree ning. Subsequently, within the GEO dataset, we utilized four machine learning al gorithms to precisely identify risk-associated genes. Gene validity was confirme d through five Mendelian Randomization methods. AGPAT4 expression was measured b y Single-Cell Analysis, ELISA and immunohistochemistry. We investigated AGPAT4's effect on endometrial stromal cells using RNA interference, assessing cell prol iferation, invasion, and migration with CCK8, wound-healing, and transwell assay s. Protein expression was analyzed by western blot, and AGPAT4 interactions were explored using AutoDock. Our investigation identified 11 genes associated with endometriosis risk, with AGPAT4 and COMT emerging as pivotal biomarkers through machine learning analysis. AGPAT4 exhibited significant upregulation in both ect opic tissues and serum samples from patients with endometriosis. Reduced express ion of AGPAT4 was observed to detrimentally impact the proliferation, invasion, and migration capabilities of endometrial stromal cells, concomitant with dimini shed expression of key signaling molecules such as Wnt3a, b-Catenin, MMP-9, and SNAI2."

原文链接:

NETL
NSTL