首页期刊导航|Robotics & Machine Learning Daily News
期刊信息/Journal information
Robotics & Machine Learning Daily News
NewsRx
Robotics & Machine Learning Daily News

NewsRx

Robotics & Machine Learning Daily News/Journal Robotics & Machine Learning Daily News
正式出版
收录年代

    Research from Technical University Valencia (TU Valencia) in the Area of Machine Learning Described (Combination of Machine Learning and RGB Sensors to Quantify and Classify Water Turbidity)

    19-20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 out of Technic al University Valencia (TU Valencia) by NewsRx editors, research stated, "Turbid ity is one of the crucial parameters of water quality. Even though many commerci al devices, low-cost sensors, and remote sensing data can efficiently quantify t urbidity, they are not valid tools for the classification it." Funders for this research include European Union Nextgenerationeu; Generalitat V alenciana; Agencia Estatal De Investigacion. Our news correspondents obtained a quote from the research from Technical Univer sity Valencia (TU Valencia): "In this paper, we design, calibrate, and test a no vel optical low-cost sensor for turbidity quantification and classification. The sensor is based on an RGB light source and a light detector. The analyzed sampl es are characterized by turbidity values from 0.02 to 60 NTUs, and have four dif ferent sources. These samples were generated to represent natural turbidity sour ces and leaves in the marine areas close to agricultural lands. The data are gat hered using 64 different combinations of light, generating complex matrix data. Machine learning models are compared to analyze this data, including training, v alidation, and test datasets. Moreover, different alternatives for data preproce ssing and feature selection are assessed. Concerning the quantification of turbi dity, the best results were obtained using averaged data and principal component s analyses in conjunction with exponential gaussian process regression, achievin g an R2 of 0.979."
      原文链接:
    • NETL
    • NSTL

    Center for Genomic Regulation Reports Findings in Leukemia (Integration of trans cription regulation and functional genomic data reveals lncRNA SNHG6's role in h ematopoietic differentiation and leukemia)

    20-21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 - Leukemia is the subject of a report. According to news reporting out of Catalonia, Spain, b y NewsRx editors, research stated, "Long non-coding RNAs (lncRNAs) are pivotal p layers in cellular processes, and their unique cell-type specific expression pat terns render them attractive biomarkers and therapeutic targets. Yet, the functi onal roles of most lncRNAs remain enigmatic." Financial supporters for this research include Israel Science Foundation, Israel Cancer Association. Our news journalists obtained a quote from the research from Center for Genomic Regulation, "To address the need to identify new druggable lncRNAs, we developed a comprehensive approach integrating transcription factor binding data with oth er genetic features to generate a machine learning model, which we have called I NFLAMeR (Identifying Novel Functional LncRNAs with Advanced Machine Learning Res ources). INFLAMeR was trained on high-throughput CRISPR interference (CRISPRi) s creens across seven cell lines, and the algorithm was based on 71 genetic featur es. To validate the predictions, we selected candidate lncRNAs in the human K562 leukemia cell line and determined the impact of their knockdown (KD) on cell pr oliferation and chemotherapeutic drug response. We further performed transcripto mic analysis for candidate genes. Based on these findings, we assessed the lncRN A small nucleolar RNA host gene 6 (SNHG6) for its role in myeloid differentiatio n. Finally, we established a mouse K562 leukemia xenograft model to determine wh ether SNHG6 KD attenuates tumor growth in vivo. The INFLAMeR model successfully reconstituted CRISPRi screening data and predicted functional lncRNAs that were previously overlooked. Intensive cell-based and transcriptomic validation of nea rly fifty genes in K562 revealed cell type-specific functionality for 85% of the predicted lncRNAs. In this respect, our cell-based and transcriptomic ana lyses predicted a role for SNHG6 in hematopoiesis and leukemia. Consistent with its predicted role in hematopoietic differentiation, SNHG6 transcription is regu lated by hematopoiesisassociated transcription factors. SNHG6 KD reduced the pr oliferation of leukemia cells and sensitized them to differentiation. Treatment of K562 leukemic cells with hemin and PMA, respectively, demonstrated that SNHG6 inhibits red blood cell differentiation but strongly promotes megakaryocyte dif ferentiation. Using a xenograft mouse model, we demonstrate that SNHG6 KD attenu ated tumor growth in vivo. Our approach not only improved the identification and characterization of functional lncRNAs through genomic approaches in a cell typ e-specific manner, but also identified new lncRNAs with roles in hematopoiesis a nd leukemia."
      原文链接:
    • NETL
    • NSTL

    First Affiliated Hospital of Guangxi Medical University Reports Findings in Diab etic Kidney Disease (Identification and validation of immune and cuproptosis - r elated genes for diabetic nephropathy by WGCNA and machine learning)

    22-23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 Kidney Diseases and Co nditions - Diabetic Kidney Disease is the subject of a report. According to news reporting originating from Nanning, People's Republic of China, by NewsRx corre spondents, research stated, "As the leading cause of chronic kidney disease, dia betic kidney disease (DKD) is an enormous burden for all healthcare systems arou nd the world. However, its early diagnosis has no effective methods." Our news editors obtained a quote from the research from the First Affiliated Ho spital of Guangxi Medical University, "First, gene expression data in GEO databa se were extracted, and the differential genes of diabetic tubulopathy were obtai ned. Immune-related genesets were generated by WGCNA and immune cell infiltratio n analyses. Then, differentially expressed immune-related cuproptosis genes (DEI CGs) were derived by the intersection of differential genes and genes related to cuproptosis and immune. To investigate the functions of DEICGs, volcano plots a nd GO term enrichment analysis was performed. Machine learning and protein-prote in interaction (PPI) network analysis helped to finally screen out hub genes. Th e diagnostic efficacy of them was evaluated by GSEA analysis, receiver operating characteristic (ROC) curve, single-cell RNA sequencing and the Nephroseq websit e. The expression of hub genes at the animal level by STZ -induced and db/db DKD mouse models was further verified. Finally, three hub genes, including, and th at were up-regulated in both the test set GSE30122 and the validation set GSE305 29, were screened. The areas under the curve (AUCs) of ROC curves of hub genes w ere 0.911, 0.935 and 0.922, respectively, and 0.946 when taking as a whole. Corr elation analysis showed that the expression level of three hub genes demonstrate d their negative relationship with GFR, while those of displayed a positive corr elation with the level of serum creatinine. GSEA was enriched in inflammatory an d immune-related pathways. Single-nucleus RNA sequencing indicated the main dist ribution of in podocyte and mesangial cells, the high expression of in leukocyte s and the main localization of in the loop of Henle. In mouse models, all three hub genes were increased in both STZ-induced and db/db DKD models."
      原文链接:
    • NETL
    • NSTL

    Northeast Agricultural University Researchers Target Machine Learning (Multimoda l deep fusion model based on Transformer and multi-layer residuals for assessing the competitiveness of weeds in farmland ecosystems)

    23-24页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in artificial intelligence. According to news reporting out of Harbin, People's Rep ublic of China, by NewsRx editors, research stated, "Weed competitiveness monito ring is crucial for field management at specific locations. Recent research in t he fusion of multimodal data from unmanned aerial vehicles (UAVs) has propelled this advancement." Financial supporters for this research include National Natural Science Foundati on of China. The news journalists obtained a quote from the research from Northeast Agricultu ral University: "However, these studies merely stack extracted features equivale ntly, neglecting the full utilization of fused information. This study utilizes hyperspectral and LiDAR data collected by UAVs to proposes a multimodal deep fus ion model (MulDFNet) using Transformer and multi-layer residuals. It utilizes a comprehensive competitive index (CCI-A) based on multidimensional phenotypes of maize to assess the competitiveness of weeds in farmland ecosystems. To validate the effectiveness of this model, a series of ablation studies were conducted in volving different modalities data, with/without the Transformer Encoder (TE) mod ules, and different fusion modules (shallow residual fusion module, deep feature fusion module). Additionally, a comparison was made with early/late stacking fu sion models, traditional machine learning models, and deep learning models from relevant studies. The results indicate that the multimodal deep fusion model uti lizing HSI, VI, and CHM data achieved a predictive effect of R2 = 0.903 (RMSE = 0.078). Notably, the best performance was observed during the five-leaf stage. T he combination of shallow and deep fusion modules demonstrated better predictive performance compared to a single fusion module. The positive impact of the TE m odule on model performance is evident, as its multi-head attention mechanism aid s in better capturing the relationships and importance between feature maps and competition indices, thereby enhancing the model's predictive capability."
      原文链接:
    • NETL
    • NSTL

    New Machine Learning Study Findings Have Been Reported by Researchers at Wuhan U niversity (Ionic Liquid Binary Mixtures: Machine Learning-assisted Modeling, Sol vent Tailoring, Process Design, and Optimization)

    24-25页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Fresh data on Machine Learning are pre sented in a new report. According to news reporting out of Hubei, People's Repub lic of China, by NewsRx editors, research stated, "This work conducts a comprehe nsive modeling study on the viscosity, density, heat capacity, and surface tensi on of ionic liquid (IL)-IL binary mixtures by combining the group contribution ( GC) method with three machine learning algorithms: artificial neural network, XG Boost, and LightGBM. A large number of experimental data from reliable open sour ces is exhaustively collected to train, validate, and test the proposed ML-based GC models." Funders for this research include National Natural Science Foundation of China ( NSFC), University of Delaware, Technical University of Denmark. Our news journalists obtained a quote from the research from Wuhan University, " Furthermore, the Shapley Additive Explanations technique is employed to quantify the influential factors behind all the studied properties. Finally, these ML-ba sed GC models are sequentially integrated into computer-aided mixed solvent desi gn, process design, and optimization through an industrial case study of recover ing hydrogen from raw coke oven gas."
      原文链接:
    • NETL
    • NSTL

    Research on Artificial Intelligence Described by a Researcher at Hongik Universi ty [Overcoming Uncertainty in Novel Technologies: The Role of Venture Capital Syndication Networks in Artificial Intelligence (AI) Startup In vestments in Korea and ...]

    25-25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 ar tificial intelligence. According to news reporting out of Seoul, South Korea, by NewsRx editors, research stated, "This paper investigates how historical interfirm syndication networks influence venture capitalists' (VCs) propensity to inv est in startups pursuing novel, uncertain technologies, with a focus on artifici al intelligence (AI)." Financial supporters for this research include Waseda University; 2023 Hongik Un iversity Innovation Support Program Fund. Our news editors obtained a quote from the research from Hongik University: "We theorize that VCs' positional attributes within cumulative syndication networks determine their access to external expertise and intelligence that aid AI invest ment decisions amidst informational opacity. Specifically, reachability to prior AI investors provides referrals and insights transmitted across short network p aths to reduce ambiguity. Additionally, VC brokerage between disconnected indust ry clusters furnishes expansive, non-redundant information that is pivotal for d iscovering and assessing AI opportunities. Through hypotheses grounded in social network theory, we posit network-based mechanisms that equip VCs to navigate un certainty when engaging with ambiguous innovations like AI. We test our framewor k, utilizing comprehensive historical records of global venture capital investme nts. Analyzing the location information of VC firms in this database, we uncover ed a history of 14,751 investments made by Korean and Japanese firms."
      原文链接:
    • NETL
    • NSTL

    Islamic Azad University Researcher Has Provided New Data on Machine Learning (Qu antitative forecasting of bed sediment load in river engineering: an investigati on into machine learning methodologies for complex phenomena)

    26-26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 Islamic Azad University by Ne wsRx journalists, research stated, "The intricate calculation of bed sediment lo ad (BSL), which is influenced by hydraulic, hydrological, and sedimentary factor s, is vital for informed decision-making in water resource management." The news editors obtained a quote from the research from Islamic Azad University : "Machine learning models, which are gaining popularity due to their accessibil ity and ability to reveal complex relationships, play a significant role in tack ling these challenges. The efficacy of gene expression programming (GEP) models, support vector machines (SVMs), multi-layer perceptron (MLP), and multivariate adaptive regression splines (MARS) has been assessed through measured data of nu mber 540 obtained from six rivers, namely Oak Creek, Nahal Yatir, Sagehen Creek, Elbow River, Jacoby River, and Goodwin Creek from 1954 to 1992. The assessment of model performance has been conducted utilizing root mean square error (RMSE), R2, Nash-Sutcliffe coefficient (NSE), and developed discrepancy ratio (DDR) as indices. Following data normalization within the range of 0-1, the data models u nderwent training and testing processes with a partition ratio of 80% for training and 20% for testing."
      原文链接:
    • NETL
    • NSTL

    Zhejiang Normal University Reports Findings in Machine Learning (POPs identifica tion using simple low-code machine learning)

    27-28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 Jinhua, People 's Republic of China, by NewsRx journalists, research stated, "Effectively ident ifying persistent organic pollutants (POPs) with extensive organic chemical data sets poses a formidable challenge but is of utmost importance. Leveraging machin e learning techniques can enhance this process, but previous models often demand ed advanced programming skills and high-end computing resources." The news reporters obtained a quote from the research from Zhejiang Normal Unive rsity, "In this study, we harnessed the simplicity of PyCaret, a Python-based pa ckage, to construct machine-learning models for POP screening based on 2D molecu lar descriptors. We compared the performance of these models against a deep conv olutional neural network (DCNN) model. Utilising minimal Python code, we generat ed several models that exhibited superior or comparable performance to the DCNN. The most outstanding performer, the Light Gradient Boosting Machine (LGBM), ach ieved an accuracy of 96.20 %, an AUC of 97.70 %, and a n F1 score of 82.58 %. This model outshone the DCNN model. Furtherm ore, it excelled in identifying POPs within the REACH PBT and compiled industria l chemical lists. Our findings highlight the accessibility and simplicity of PyC aret, requiring only a few lines of code, rendering it suitable for non-computin g professionals in environmental sciences. The ability of low code machine learn ing tools (e.g."
      原文链接:
    • NETL
    • NSTL

    Researchers from University of Illinois Describe Findings in Robotics and Automa tion (Trackdlo: Tracking Deformable Linear Objects Under Occlusion With Motion C oherence)

    27-27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 - Ro botics and Automation have been published. According to news reporting originati ng from Urbana, Illinois, by NewsRx correspondents, research stated, "The TrackD LO algorithm estimates the shape of a Deformable Linear Object (DLO) under occlu sion from a sequence of RGB-D images. TrackDLO is vision-only and runs in real-t ime." Financial supporters for this research include Illinois Space Grant Consortium U ndergraduate Research Opportunity Program, NASA Space Technology Graduate Resear ch Opportunity. Our news editors obtained a quote from the research from the University of Illin ois, "It requires no external state information from physics modeling, simulatio n, visual markers, or contact as input. The algorithm improves on previous appro aches by addressing three common scenarios which cause tracking failure: tip occ lusion, mid-section occlusion, and self-occlusion. This is achieved through the application of Motion Coherence Theory to impute the spatial velocity of occlude d nodes, the use of the topological geodesic distance to track self-occluding DL Os, and the introduction of a non-Gaussian kernel that only penalizes lower-orde r spatial displacement derivatives to reflect DLO physics. Improved real-time DL O tracking under mid-section occlusion, tip occlusion,and self-occlusion is demo nstrated experimentally." According to the news editors, the research concluded: "The source code and demo nstration data are publicly released."
      原文链接:
    • NETL
    • NSTL

    New Robotics Data Have Been Reported by Investigators at Shri Ramdeobaba College of Engineering & Management (Cgpcrobot: Pole Climbing Robot With Controlled Gripper Mechanism)

    28-29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 Robotic s. According to news reporting out of Nagpur, India, by NewsRx editors, research stated, "This paper presents the design and implementation of a lightweight Pol e Climbing Robot (PCR) featuring a controlled gripper mechanism. The robot boast s dimensions of 200x150x500\documentclass[12pt]{minimal} \usep ackage{amsmath} \usepackage{ wasysym} \usepackage{amsfonts} \ usepackage{amssymb} \usepackage{ amsbsy} \usepackage {mathrsfs} \ usepackage{upgreek} \setlength{ \oddsidemargin}{-69pt} \ begin{document}$$200 \ times 150 \times 500$$\ end{document} and demonstrates exceptional versatility by adeptly ascending cylindrical and rectangular poles within the diameter range of 40-130 mm." Our news journalists obtained a quote from the research from the Shri Ramdeobaba College of Engineering & Management, "The specially engineered gr ipper accommodates a broad spectrum of pole cross-sections, including those with irregular shapes. Operating at an average speed of 100 cm/min, the robot weighs approximately 1.1 Kg and exhibits lifting capacities of 0.36 Kg on steel poles and 0.6 Kg on wooden poles. The practical applications of this robot are evident in scenarios necessitating swift climbing maneuvers. Notably, the robot's movem ents are wirelessly controllable via mobile devices." According to the news editors, the research concluded: "The paramount objective of this research is to mitigate the risks associated with manual pole climbing a ctivities, particularly in professions such as electrical maintenance where work ers, including electricians, face inherent dangers while ascending utility poles to ensure consistent electricity supply to connected households or, in the case of agricultural contexts, climbing trees like coconut trees."
      原文链接:
    • NETL
    • NSTL