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

    New Computational Intelligence Findings Has Been Reported by Investigators at China University of Mining and Technology Beijing (Self-supervised Adaptive Illumination Estimation for Low-light Image Enhancement)

    9-10页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - A new study on Machine Learning - Comp utational Intelligence is now available.According to news reporting out of Beij ing, People’s Republic of China, by NewsRx editors, researchstated, “In low-lig ht image enhancement tasks, global structure and local texture details have diff erenteffects on illumination estimation. However, most existing works fail to e ffectively explore the intrinsicassociation within them.”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 China Universit y of Mining andTechnology Beijing, “To effectively balance the structure-preser ving and texture-smoothing for illuminationmaps, this paper introduces a new il lumination smoothing loss and proposes a self-supervised adaptiveillumination e stimation network (AIE-Net). The illumination smoothing loss achieves a balance betweenstructure-preserving and texture-smoothing mainly through L2 norm, trunc ated Huber, and Gaussiankernel function with color affinity. To construct AIE-N et, we introduce a local-global adaptive modulation(LGAM) module in deep featur e extraction. The module allows local and global features to be adaptivelyfused in a spatially varying manner by predicting scaling and adding factors. Finally , we separately estimatethe illumination maps for the input image and its inver ted image, and then achieve exposure correctionwith multi-exposure fusion.”
      原文链接:
    • NETL
    • NSTL

    Zhejiang Chinese Medical University Reports Findings in Stroke (How robot-assist ed gait training affects gait ability, balance and kinematic parameters afterst roke: a systematic review and metaanalysis)

    10-11页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Cerebrovascular Diseas es and Conditions - Stroke is the subject ofa report. According to news reporti ng originating in Zhejiang, People’s Republic of China, by NewsRxjournalists, r esearch stated, “Gait ability is often cited by stroke survivors. Robot-assisted gait training(RAGT) can help stroke patients with lower limb motor impairment regain motor coordination.”10The news reporters obtained a quote from the research from Zhejiang Chinese Medi cal University,“PubMed, Cochrane Library, Embase were systematically searched u ntil September 2023, to identify randomizedcontrolled trials presenting: stroke survivors as participants; RAGT as intervention; conventionalrehabilitation as a comparator; gait assessment, through scales or quantitative parameters, as ou tcomemeasures. Twenty-seven publications involving 1167 patients met the inclus ion criteria. Meta-analysisshowed no significant differences in speed, cadence, spatial symmetry, and changes in joint mobility anglesbetween the RAGT group a nd the control group. In addition, RAGT was associated with changes inaffected side step length (SMD=0.02, 95% CI: 0.01, 0.03; P<0.0001), temporal symmetry (SMD=-0.38,95% CI: -0.6, -0.16; P=0.00 06], Six-Minute Walk Test (SMD=25.14, 95% CI: 1 0.19, 40.09; P=0.0010]and Functional Ambulation Categories ( SMD=0.32, 95% CI: 0.01, 0.63; P=0.04). According to thePEDro scal e, 19 (70.4%) studies were of high quality and eight were of modera te quality (29.6%).Taken together, the review synthesis showed tha t RAGT might have a potential role in the recovery ofwalking dysfunction after stroke. However, its superiority over conventional rehabilitation requires furth erresearch.”
      原文链接:
    • NETL
    • NSTL

    New Machine Learning Data Have Been Reported by Researchers at Pontifical Univer sity (A Machine Learning Approach for Enhancing Permittivity Mixing Rules of Binary Liquids With a Gaussian Modification and a New Interaction Factor Estimation)

    11-12页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Current study results on Machine Learn ing have been published. According to newsreporting originating from Madrid, Sp ain, by NewsRx correspondents, research stated, “The microstructureand solvatio n mechanics of binary liquids are key for predicting mixture permittivity. Howev er, sincetraditional mixing rules do not consider this complexity, they must be modified to address the mixturecharacteristics through an interaction factor ( k(int)).”Our news editors obtained a quote from the research from Pontifical University, “This paper evaluatesthis parameter for several mixing rules, applying Support Vector Regressor models trained with glycerinwaterreflective signals acquired with a Dielectric Resonator sensor. The regression error of these modelsindicat es both the optimal interaction factor and the mixing rule that fits the most wi th experimentalpermittivity values. Kraszewski and Hashin-Shtrikman mixing rule s achieved the best performance withan RMSE of around 1. In addition, this pape r suggests that the interaction factor can be estimatedthrough the molar volume and the dielectric contrast between liquids (k(int) = 2.67) without acquiring experimental data. Moreover, after analyzing the physical limitations of a linear modification formula, thispaper proposes an alternative based on a Gaussian fu nction that avoids unrealistic volume fractions.”
      原文链接:
    • NETL
    • NSTL

    New Robotics Findings from University of California San Diego (UCSD) Described (Material Scrunching Enables Working Channels In Miniaturized Vine-inspired Robots)

    12-13页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Researchers detail new data in Robotic s. According to news reporting originating fromLa Jolla, California, by NewsRx correspondents, research stated, “A new subclass of soft robot, known astip-ext ending or ‘vine’ robots, consists of long inflatable devices that move through t he environment byextending from the tip. A key requirement for many application s of these robots is a working channel-ahollow tube through the core of the rob ot for passing tools, sensors, fluids, etc.”Financial support for this research came from National Science Foundation (NSF).Our news editors obtained a quote from the research from the University of Calif ornia San Diego(UCSD), “While working channels have been proposed in a few vine robots, it remains an open challengeto create miniaturized vine robots (diamet er <1 cm) with working channels that enable continuous access through the core. In this article, we analyze the growth models of current vi ne robot designs and showthat the working channel greatly increases required pr essure to grow at small scales due to internal friction.Based on this insight, we propose the concept of storing scrunched material at the tip of the vine robotto circumvent this frictional force. We validate our models and demonstrate th is concept via prototypesdown to diameter of 2.3 mm.”
      原文链接:
    • NETL
    • NSTL

    University of Craiova Researcher Provides Details of New Studies and Findings in the Area of Artificial Intelligence (Autonomous fetal morphology scan: deep learning + clustering merger - the second pair of eyes behind the doctor)

    13-14页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Research findings on artificial intell igence are discussed in a new report. According tonews reporting from the Unive rsity of Craiova by NewsRx journalists, research stated, “The main cause offeta l death, of infant morbidity or mortality during childhood years is attributed t o congenital anomalies.They can be detected through a fetal morphology scan.”Financial supporters for this research include Ministerul Cercetarii, Inovarii S i Digitalizarii.Our news correspondents obtained a quote from the research from University of Cr aiova: “An experiencedsonographer (with more than 2000 performed scans) has the detection rate of congenital anomaliesaround 52%. The rates go do wn in the case of a junior sonographer, that has the detection rate of 32.5% . One viable solution to improve these performances is to use Artificial Intelli gence. The first step in afetal morphology scan is represented by the different iation process between the view planes of the fetus,followed by a segmentation of the internal organs in each view plane. This study presents an Artificial Intelligence empowered decision support system that can label anatomical organs usi ng a merger betweendeep learning and clustering techniques, followed by an orga n segmentation with YOLO8. Our frameworkwas tested on a fetal morphology image dataset that regards the fetal abdomen. The experimental resultsshow that the s ystem can correctly label the view plane and the corresponding organs on real-timeultrasound movies.”
      原文链接:
    • NETL
    • NSTL

    Studies from Southwest University of Science and Technology Yield New Informatio n about Robotics (Adaptive Time-delay Attitude Control of Jumping Robots Based On Voltage Control Model)

    14-15页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on Ro botics. According to news originating fromMianyang, People’s Republic of China, by NewsRx editors, the research stated, “This letter presents anadaptive contr ol framework for the attitude control of jumping robot with time-delay estimatio n(TDE). Forhandling the uncertainties and unknown coupling of motors, voltage-b ased motor control was presented.”Financial support for this research came from National Key Research and Developm ent Program ofChina.Our news journalists obtained a quote from the research from the Southwest Unive rsity of Scienceand Technology, “Compared to the current-based control model, t he voltage-based control model ismore computationally simple and realistic. The proposed adaptive law was designed to compensate theerror produced by TDE, wit hout considering the threshold value of control parameters. By the stabilityana lysis, the control framework was verified by the semi-globally uniformly ultimat ely bounded stability.Experiment results have been discussed and the effectiven ess of the adaptive control framework have beendemonstrated.”
      原文链接:
    • NETL
    • NSTL

    Research from Chung-Ang University Yields New Findings on Machine Learning (Mult imodal machine learning for predicting heat transfer characteristics in micro-pin finheat sinks)

    15-16页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators publish new report on ar tificial intelligence. According to news reportingout of Seoul, South Korea, by NewsRx editors, research stated, “As three-dimensional integrated circuit(3D-I C) chip technology advances, thermal management has become increasingly importan t because ofincreasing heat flux from thermal stacking. Micro-pin fin-embedded cooling has emerged as a promisingsolution for 3D-ICs, offering better thermal and hydraulic performance than conventional microchannelheat sinks.”The news editors obtained a quote from the research from Chung-Ang University: “ It is also easy tointegrate into existing 3D-IC structures, such as through-sil icon vias between stacks. The utilization oftwo-phase flow in micro-pin fins fu rther enhances temperature uniformity and improves the heat transfercoefficient by leveraging latent heat. Nevertheless, predicting thermal performance in micr o-pin fin heatsinks under boiling conditions remains challenging owing to intri cate geometric shapes and diverse operatingconditions. The present lack of corr elation or theoretical models poses a significant obstacle. To addressthis prob lem, our study employed a Multimodal machine-learning (ML) approach, combining i magedata capturing boiling patterns of two-phase flow and information about geo metric shape and operatingconditions, to predict heat transfer characteristics in micro-pin fin heat sinks. We utilized experimentaldata comprising 155 types of boiling heat transfer data with the dielectric fluid FC-72 in two micro-fin shapes directly etched on Si. Four ML algorithms (XGBoost, LightGBM, Multilayer p erceptron (MLP), andMultimodal ML) were employed to predict thermal performance . The correlation coefficient analysis beforelearning revealed the influence of each type of measurement data on the heater surface temperature duringtwo-phas e flow. Prediction accuracy was measured using mean absolute percent error (MAPE ), and theresults were compared in terms of maximum and average temperature dep ending on the characteristicsof each ML algorithm. Overall, the Multimodal appr oach demonstrated superior capability in predictingtemperature distributions wi th spatial details, surpassing conventional decision-tree algorithms and MLPin performance.”
      原文链接:
    • NETL
    • NSTL

    Findings from Shanghai Jiao Tong University Update Knowledge of Robotics (Error Constrained-formation Path-following Method With Disturbance Elimination for Multisnake Robots)

    16-17页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - Investigators discuss new findings in Robotics. According to news reporting originatingfrom Shanghai, People’s Republ ic of China, by NewsRx correspondents, research stated, “This articlereports a novel path-following method based on error constraints to fulfill formation cont rol with theanti-disturbance for multisnake robots. A synchronized line-of-sigh t guidance rule and a high-coupleddynamic frequency compensator are designed to revise the movement speed of each robot, ensuring positionconsistency among fo rmation members.”Funders for this research include National Science Fund for Distinguished Young Scholars, NationalNatural Science Foundation of China (NSFC), Shanghai Municipa l Science and Technology Major Project,China Postdoctoral Science Foundation.Our news editors obtained a quote from the research from Shanghai Jiao Tong Univ ersity, “Theequivalent principle of the barrier function restricts the state er rors within a set range, eliminating thesingularity of virtual variables and en hancing the steady-state performance of path following. Moreover,this article p redicts the model uncertainty and external disturbances to precompensate for the joint offsetand torque input of the robot. The method further improves the con vergence rates and robustness ofthe following errors. Barrier Lyapunov theory p roves the uniform ultimate boundedness of the proposedmethod.”
      原文链接:
    • NETL
    • NSTL

    First Affiliated Hospital of Nanjing Medical University Reports Findings in Cath eterization (Modified robot-assisted nephroureterectomy with ureteral catheteriz ation for radical resection of the distal ureter: Procedures and short-term outcomes)

    17-18页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - New research on Catheterization is the subject of a report. According to news reportingout of Nanjing, People’s Repub lic of China, by NewsRx editors, research stated, “To describe a bladdercuff ex cision method modified with ureteral catheterization to better visualize the ure teral orifice duringrobot-assisted nephroureterectomy (RANU). We retrospectivel y analyzed 66 patients with upper urinarytract urothelial carcinoma of the rena l pelvis and/or upper-mid ureter treated between January 2020 andJanuary 2023.”Our news journalists obtained a quote from the research from the First Affiliate d Hospital of NanjingMedical University, “Among them, 32 patients (group A) und erwent RANU supported by ureteralcatheterization, and the remaining patients (g roup B) received routine transperitoneal RANU. Postoperativecystoscopy was perf ormed routinely to compare the rates of residual ureteral orifice between the tw ogroups. Surgeries were completed uneventfully in all 66 patients, without bloo d transfusion or conversionto open procedures. The operative time, estimated bl ood loss, and postoperative length of hospital staywere similar between both gr oups. However, the mean time required for BCE in group A was shorter thanthat i n group B (9.5 min vs. 16.0 min, p = 0.006). Cystoscopy at postoperative three m onths showedno ipsilateral ureteral orifice in group A, but residual ureteral o rifice was found in 23.5% of patients ingroup B. During a short f ollow-up period of 16 months, no patients in group A experienced bladder tumorr ecurrence. However, two patients (5.9%) in group B developed bladde r tumor recurrence, with oneexperiencing local tumor recurrence at the level of the ureteral stump.”
      原文链接:
    • NETL
    • NSTL

    Research from Shandong University of Science and Technology Provides New Study Findings on Robotics (Automatic Hand-Eye Calibration Method of Welding Robot Based on Linear Structured Light)

    18-19页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews - Investigators publish new report on robotics. Acc ording to news reporting out of Shandong,People’s Republic of China, by NewsRx editors, research stated, “Aiming at solving the problems suchas long calibrati on time, low precision, and complex operation in hand-eye calibration of welding robot,an automatic hand-eye calibration algorithm based on linear structured l ight was proposed to solve thecalibration matrix X by using AX=ZB calibration equation.”Funders for this research include Shandong Province Higher Educational Science A nd TechnologyProgram; Natural Science Foundation of Shandong Province; Tai’an C ity Science And Technology DevelopmentProgram.Our news journalists obtained a quote from the research from Shandong University of Science andTechnology: “Firstly, a square calibration plate is customized t o effectively constrain the structured light.The a-shape algorithm was adopted to extract the contour of the 3D point cloud model of the calibrationplate. Sec ondly, an improved random sampling consistency algorithm which could determine t he optimaliterative number was proposed to fit the contour point cloud, the con tour point cloud model fitted wasobtained. Finally, the 3D coordinates of the t arget points were determined with the linear structuredlight to complete the ha nd-eye calibration. In order to prevent the calibration plate from deviating fro mthe acquisition range of the vision sensor during the calibration process, the distance between the linearstructural light and the inner circle in the calibr ation plate was set to limit the motion range of the robot.In order to eliminat e the error transfer of the robot body, an optimal solution of the rotation matr ix Rand the translation vector t of the calibration data was calculated with the singular value decomposition(S VD) and the least square rigid transpose method.”
      原文链接:
    • NETL
    • NSTL