期刊,Robotics & Machine Learning Daily News 2024年卷Jun.26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

Researchers from Xi'an University of Posts and Telecommunications Describe Findi ngs in Support Vector Machines (Multi-factor Pm2.5 Concentration Optimization Pr ediction Model Based On Decomposition and Integration)

1-2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 Su pport Vector Machines. According to news originating from Shaanxi, People's Repu blic of China, by NewsRx correspondents, research stated, "With the rapid expans ion of increased energy consumption, the issue of air pollution comes to be incr easingly critical. It is essential to achieve accurate PM2.5 concentration predi ction for people's health and lives." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). Our news journalists obtained a quote from the research from the Xi'an Universit y of Posts and Telecommunications, "Therefore, a multi-factor PM2.5 concentratio n optimization prediction model based on circulatory system based optimization ( CSBO), variational mode decomposition (VMD), gated recurrent unit optimized by q uantile regression (QRGRU), mountain gazelle optimizer (MGO) and least square su pport vector machine (LSSVM), named CSBO-VMD-QRGRUMGO-LSSVM, is proposed. Firstl y, RFECV is utilized to discover the optimal feature subset with the strongest r elationship with PM2.5 concentration. Secondly, variational mode decomposition o ptimized by circulatory system based optimization, named CSBO-VMD, is proposed. CSBO-VMD is utilized to decompose PM2.5 concentration adaptively into a restrict ed number of intrinsic mode functions (IMFs). Then, gated recurrent unit optimiz ed by quantile regression, named QRGRU, and least squares support vector machine optimized by mountain gazelle optimizer, named MGO-LSSVM, are proposed. The dec omposed components IMFs and optimal feature subsets are predicted by QRGRU and M GO-LSSVM to generate the integrated prediction results of QRGRU and MGO-LSSVM, r espectively. Finally, the prediction results of QRGRU and MGOLSSVM are assigned weights by the inverse root mean square error blending to obtain the final predi ction results. Considering the geographical location, population density and pol lution risk, PM2.5 concentration in Beijing, Shenyang, Xi'an and Urumqi are pred icted to demonstrate the efficiency and universality of the proposed model."

原文链接:

NETL
NSTL

Research from University of Nevada Provides New Study Findings on Artificial Int elligence (Generative artificial intelligence for distributed learning to enhanc e smart grid communication)

2-2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 from Reno, Nevada, by NewsRx journalists, research stated, "Machine learning models are the backbone of smar t grid optimization, but their effectiveness hinges on access to vast amounts of training data. However, smart grids face critical communication bottlenecks due to the ever-increasing volume of data from distributed sensors." The news correspondents obtained a quote from the research from University of Ne vada: "This paper introduces a novel approach leveraging Generative Artificial I ntelligence (GenAI), specifically a type of pre-trained Foundation Model (FM) ar chitecture suitable for time series data due to its efficiency and privacy-prese rving properties. These GenAI models are distributed to agents, or data holders, empowering them to fine-tune the foundation model with their local datasets. By fine-tuning the foundation model, the updated model can produce synthetic data that mirrors real-world grid conditions. The server aggregates fine-tuned model from all agents and then generates synthetic data which considers all data colle cted in the grid. This synthetic data can be used to train global machine learni ng models for specific tasks like anomaly detection and energy optimization. The n, the trained task models are distributed to agents in the grid to leverage the m."

原文链接:

NETL
NSTL

Recent Findings from University of Brunei Darussalam Has Provided New Informatio n about Machine Learning (Consensus Holistic Virtual Screening for Drug Discover y: a Novel Machine Learning Model Approach)

3-3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 Machine Learning. According to news reporting originating in Gadong, Brunei, by NewsRx journalists, research stated, "In drug discovery, virtual screening is cr ucial for identifying potential hit compounds. This study aims to present a nove l pipeline that employs machine learning models that amalgamates various convent ional screening methods." Financial support for this research came from Council for Research and Advanceme nt in Technology and Science (CREATES) MTIC/CREATES under the Ministry of Transp ort and Infocommunications (MTIC). The news reporters obtained a quote from the research from the University of Bru nei Darussalam, "A diverse array of protein targets was selected, and their corr esponding datasets were subjected to active/decoy distribution analysis prior to scoring using four distinct methods: QSAR, Pharmacophore, docking, and 2D shape similarity, which were ultimately integrated into a single consensus score. The fine-tuned machine learning models were ranked using the novel formula 'w_ new', consensus scores were calculated, and an enrichment study was performed fo r each target. Distinctively, consensus scoring outperformed other methods in sp ecific protein targets such as PPARG and DPP4, achieving AUC values of 0.90 and 0.84, respectively. Remarkably, this approach consistently prioritized compounds with higher experimental PIC50 values compared to all other screening methodolo gies. Moreover, the models demonstrated a range of moderate to high performance in terms of R2 values during external validation."

原文链接:

NETL
NSTL

Reports from AMOLF Highlight Recent Findings in Robotics (Robust Phototaxis By H arnessing Implicit Communication In Modular Soft Robotic Systems)

4-4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 originating from Amsterdam, Netherlands, by N ewsRx correspondents, research stated, "In robotics, achieving adaptivity in com plex environments is challenging. Traditional robotic systems use stiff material s and computationally expensive centralized controllers, while nature often favo rs soft materials and embodied intelligence." Funders for this research include Horizon 2020, European Union (EU), Netherlands Organization for Scientific Research (NWO). Our news journalists obtained a quote from the research from AMOLF, "Inspired by nature's distributed intelligence, this study explores a decentralized approach for robust behavior in soft robotic systems without knowledge of their shape or environment. It is demonstrated that only a few basic rules implemented in iden tical modules that shape the soft robotic system can enable whole-body phototaxi s, navigating on a surface toward a light source, without explicit communication between modules or prior system knowledge. The results reveal the method's effe ctiveness in generating robust and adaptive behavior in dynamic and challenging environments. Moreover, the approach's simplicity makes it possible to illustrat e and understand the underlying mechanism of the observed behavior, paying parti cular attention to the geometry of the assembled system and the effect of learni ng parameters. Consequently, the findings offer insights into the development of adaptive, autonomous robotic systems with minimal computational power, paving t he way for robust and useful behavior in soft and microscale robots, as well as robotic matter, that operate in real-world environments. How soft modular system s can achieve robust phototactic behavior without centralized control and explic it intermodule communication, but only by leveraging basic local rules is explor ed."

原文链接:

NETL
NSTL

NSW Health Pathology Reports Findings in Clinical Chemistry and Laboratory Medic ine (Multivariate anomaly detection models enhance identification of errors in r outine clinical chemistry testing)

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 Health and Medicine-Clinical Chemistry and Laboratory Medicine is the subject of a report. According to news reporting from Liverpool, Australia, by NewsRx editors, the research st ated, "Conventional autoverification rules evaluate analytes independently, pote ntially missing unusual patterns of results indicative of errors such as serum c ontamination by collection tube additives. This study assessed whether multivari ate anomaly detection algorithms could enhance the detection of such errors." The news correspondents obtained a quote from the research from NSW Health Patho logy, "Multivariate Gaussian, k-nearest neighbours (KNN) distance, and one-class support vector machine (SVM) anomaly detection models, along with conventional limit checks, were developed using a training dataset of 127,451 electrolyte, ur ea, and creatinine (EUC) results, with a 5 % flagging rate targete d for all approaches. The models were compared with limit checks for their abili ty to detect atypical EUC results from samples spiked with additives from collec tion tubes: EDTA, fluoride, sodium citrate, or acid citrate dextrose (n=200 per contaminant). The study additionally assessed the ability of the models to ident ify 127,449 single-analyte errors, a potential weakness of multivariate models. The KNN distance and SVM models outperformed limit checks for detecting all cont aminants (p-values <0.05). The multivariate Gaussian model did not surpass limit checks for detecting EDTA contamination but was superior f or detecting the other additives. All models surpassed limit checks for identify ing single-analyte errors, with the KNN distance model demonstrating the highest overall sensitivity. Multivariate anomaly detection models, particularly the KN N distance model, were superior to the conventional approach for detecting serum contamination and single-analyte errors."

原文链接:

NETL
NSTL

Findings from Huazhong University of Science and Technology in the Area of Robot ics Reported (A Bionic Localization Memristive Circuit Based On Spatial Cognitiv e Mechanisms of Hippocampus and Entorhinal Cortex)

6-6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 from Wuhan, People's Republic of Ch ina, by NewsRx journalists, research stated, "In this article, a bionic localiza tion memristive circuit is proposed, which mainly consists of head direction cel l module, grid cell module, place cell module and decoding module. This work mod ifies the two-dimensional Continuous Attractor Network (CAN) model of grid cells into two one-dimensional models in X and Y directions." Financial support for this research came from National Natural Science Foundatio n of China (NSFC). The news correspondents obtained a quote from the research from the Huazhong Uni versity of Science and Technology, "The head direction cell module utilizes memr istors to integrate angular velocity and represents the real orientation of an a gent. The grid cell module uses memristors to sense linear velocity and orientat ion signals, which are both self-motion cues, and encodes the position in space by firing in a periodic mode. The place cell module receives the grid cell modul e's output and fires in a specific position. The decoding module decodes the ang le or place information and transfers the neuron state to a 'one-hot' code. This proposed circuit completes the localizing task in space and realizes in-memory computing due to the use of memristors, which can shorten the execution time. Th e functions mentioned above are implemented in LTSPICE. The simulation results s how that the proposed circuit can realize path integration and localization. Mor eover, it is shown that the proposed circuit has good robustness and low area ov erhead."

原文链接:

NETL
NSTL

Amsterdam University Medical Center Reports Findings in Liver Resection (Healthc are cost expenditure for robotic versus laparoscopic liver resection: a bottom-u p economic evaluation)

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 Surgery-Liver Resect ion is the subject of a report. According to news reporting originating from Ams terdam, Netherlands, by NewsRx correspondents, research stated, "Minimally invas ive liver surgery (MILS) is increasingly performed via the robot-assisted approa ch but may be associated with increased costs. This study is a post-hoc comparis on of healthcare cost expenditure for robotic liver resection (RLR) and laparosc opic liver resection (LLR) in a high-volume center." Our news editors obtained a quote from the research from Amsterdam University Me dical Center, "In-hospital and 30-day postoperative healthcare costs were calcul ated per patient in a retrospective series (October 2015-December 2022). Overall , 298 patients were included (143 RLR and 155 LLR). Benefits of RLR were lower c onversion rate (2.8% vs 12.3%, p = 0.002), shorter op erating time (167 min vs 198 min, p = 0.044), and less blood loss (50 mL vs 200 mL, p<0.001). Total per-procedure costs of RLR (€0260) an d LLR (€931) were not significantly different (mean difference €29 [95% bootstrapped confidence interval (BCI) €1179-€120] ). Lower costs with RLR due to shorter surgical and operating room time were off set by higher disposable instrumentation costs resulting in comparable intraoper ative costs (€559 vs €247, mean difference €12 [95% BCI €25-€48]). Postoperative costs were similar for RLR (€ 701) and LLR (€684), mean difference €7 [95% BCI €1357-€727]. When also considering purchase and mainten ance costs, RLR resulted in higher total per-procedure costs."

原文链接:

NETL
NSTL

Guizhou University Reports Findings in Sepsis (Unraveling the genetic and molecu lar landscape of sepsis and acute kidney injury: A comprehensive GWAS and machin e learning approach)

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 Blood Diseases and Con ditions-Sepsis is the subject of a report. According to news reporting origina ting from Guiyang, People's Republic of China, by NewsRx correspondents, researc h stated, "This study aimed to explore the underlying mechanisms of sepsis and a cute kidney injury (AKI), including sepsis-associated AKI (SA-AKI), a frequent c omplication in critically ill sepsis patients. GWAS data was analyzed for geneti c association between AKI and sepsis." Our news editors obtained a quote from the research from Guizhou University, "Th en, we systematically applied three distinct machine learning algorithms (LASSO, SVM-RFE, RF) to rigorously identify and validate signature genes of SA-AKI, ass essing their diagnostic and prognostic value through ROC curves and survival ana lysis. The study also examined the functional and immunological aspects of these genes, potential drug targets, and ceRNA networks. A mouse model of sepsis was created to test the reliability of these signature genes. LDSC confirmed a posit ive genetic correlation between AKI and sepsis, although no significant shared l oci were found. Bidirectional MR analysis indicated mutual increased risks of AK I and sepsis. Then, 311 key genes common to sepsis and AKI were identified, with 42 significantly linked to sepsis prognosis. Six genes, selected through LASSO, SVM-RFE, and RF algorithms, showed excellent predictive performance for sepsis, AKI, and SA-AKI. The models demonstrated near-perfect AUCs in both training and testing datasets, and a perfect AUC in a sepsis mouse model. Significant differ ences in immune cells, immune-related pathways, HLA, and checkpoint genes were f ound between high- and low-risk groups. The study identified 62 potential drug t reatments for sepsis and AKI and constructed a ceRNA network. The identified sig nature genes hold potential clinical applications, including prognostic evaluati on and targeted therapeutic strategies for sepsis and AKI."

原文链接:

NETL
NSTL

New Findings from Eotvos Lorand University Describe Advances in Machine Learning (Investigating Traditional Machine Learning Models and the Utility of Audio Fea tures for Lightweight Swarming Prediction In Beehives)

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 Machine Learning is th e subject of a report. According to news reporting originating from Budapest, Hu ngary, by NewsRx correspondents, research stated, "Remote monitoring of the stat us of beehives is essential for efficient beekeeping, leading to less workload o n the beekeeper and, because of not opening the hives too frequently, to less st ress for the colonies. Sound analysis, utilizing machine learning models of vari ous paradigms, is a common feature of so-called smart hives." Financial support for this research came from Ministry of Innovation and Technol ogy of Hungary from the National Research, Development and Innovation Fund.

原文链接:

NETL
NSTL

New Findings from Nanjing University of Science and Technology in the Area of Ma chine Learning Described (Localization of Coordinated Cyber-Physical Attacks in Power Grids Using Moving Target Defense and Machine Learning)

10-10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 originating from Nanjing, Pe ople's Republic of China, by NewsRx correspondents, research stated, "Coordinate d cyber-physical attacks (CCPAs) are dangerously stealthy and have considerable destructive effects against power grids." The news correspondents obtained a quote from the research from Nanjing Universi ty of Science and Technology: "The problem of stealthy CCPA (SCCPA) localization , specifically identifying disconnected lines in attack, is a nonlinear multi-cl assification problem. To the best of our knowledge, only one paper has studied t he problem; nevertheless, the total number of classifications is not appropriate . In the paper, we propose several methods to solve the problem of SCCPA localiz ation. Firstly, considering the practical constraints and abiding by one of our previous studies, we elaborately determine the total number of classifications a nd design an approach for generating training and testing datasets. Secondly, we develop two algorithms to solve multiple classifications via the support vector machine (SVM) and random forest (RF), respectively."

原文链接:

NETL
NSTL