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

    University of Queensland Details Findings in Machine Learning (Evasion Attack an d Defense On Machine Learning Models In Cyberphysical Systems: a Survey)

    20-21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 is now available. According to news originating from Brisbane, Australia, by NewsRx co rrespondents, research stated, "Cyber-physical systems (CPS) are increasingly re lying on machine learning (ML) techniques to reduce labor costs and improve effi ciency. However, the adoption of ML also exposes CPS to potential adversarial ML attacks witnessed in the literature." Our news journalists obtained a quote from the research from the University of Q ueensland, "Specifically, the increased Internet connectivity in CPS has resulte d in a surge in the volume of data generation and communication frequency among devices, thereby expanding the attack surface and attack opportunities for ML ad versaries. Among various adversarial ML attacks, evasion attacks are one of the most well-known ones. Therefore, this survey focuses on summarizing the latest r esearch on evasion attack and defense techniques, to understand state-of-the-art ML model security in CPS. To assess the attack effectiveness, this survey propo ses an attack taxonomy by introducing quantitative measures such as per-turbation level and the number of modified features. Similarly, a defense taxonomy is int roduced based on four perspectives demonstrating the defensive techniques from m odels' inputs to their outputs."
      原文链接:
    • NETL
    • NSTL

    New Robotics Study Findings Have Been Reported from Xiamen University (Visualize d Sensing-integrated Multi-responsive Soft Actuator for On-demand Robotic Manipu lation)

    21-22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 Xiamen, People's Republic of China, by NewsRx correspondents, research stated, "Research on smallscale soft robots has emerged in recent years, and various soft actuators have been develo ped to implement various actions. Nevertheless, realizing self-sensing alongside environmental sensing capabilities remains a challenge, largely due to the cons traints imposed by compact dimensions and the limited load-bearing capacity intr insic to these robots." Financial support for this research came from Xiamen Science Foundation.
      原文链接:
    • NETL
    • NSTL

    Findings from University of Maryland Provides New Data on Machine Learning (A Ma chine Learning Interatomic Potential for High Entropy Alloys)

    22-23页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Data detailed on Machine Learning have been prese nted. According to news reporting originating in College Park, Maryland, by News Rx journalists, research stated, "High entropy alloys (HEAs) possess a vast comp ositional space, providing exciting prospects for tailoring material properties yet also presenting challenges in their rational design. Efficiently achieving a well -designed HEA often necessitates the aid of atomistic simulations, which r ely on the availability of high -quality interatomic potentials." Financial support for this research came from Oracle. The news reporters obtained a quote from the research from the University of Mar yland, "However, such potentials for most HEA systems are missing due to the com plex interatomic interaction. To fundamentally resolve the challenge of the rati onal design of HEAs, we propose a strategy to build a machine learning (ML) inte ratomic potential for HEAs and demonstrate this strategy using CrFeCoNiPd as a m odel material. The fully trained ML model can achieve remarkable prediction prec ision (>0.92 R 2 ) for atomic forces, comparable to the ab initio molecular dynamics (AIMD) simulations. To further validate the accurac y of the ML model, we implement the ML potential for CrFeCoNiPd in parallel mole cular dynamics (MD) code. The MD simulations can predict the lattice constant (1 % error) and stacking fault energy (10 % error) of CrFeCoNiPd HEAs with high accuracy compared to experimental results. Through sys tematic MD simulations, for the first time, we reveal the atomicscale deformatio n mechanisms associated with the stacking fault formation and dislocation crosss lips in CrFeCoNiPd HEAs under uniaxial compression, which are consistent with ex perimental observations. This study can help elucidate the underlying deformatio n mechanisms that govern the exceptional performance of CrFeCoNiPd HEAs."
      原文链接:
    • NETL
    • NSTL

    New Study Findings from Newcastle University Illuminate Research in Machine Lear ning (Spatial Downscaling of Satellite-Based Soil Moisture Products Using Machin e Learning Techniques: A Review)

    23-24页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New study results on artificial intelligence have been published. According to news reporting out of Callaghan, Australia, by New sRx editors, research stated, "Soil moisture (SM) is a key variable driving hydr ologic, climatic, and ecological processes." Financial supporters for this research include Cooperative Research Centre For H igh Performance Soils. The news editors obtained a quote from the research from Newcastle University: " Although it is highly variable, both spatially and temporally, there is limited data availability to inform about SM conditions at adequate spatial and temporal scales over large regions. Satellite SM retrievals, especially L-band microwave remote sensing, has emerged as a feasible solution to offer spatially continuou s global-scale SM information. However, the coarse spatial resolution of these L -band microwave SM retrievals poses uncertainties in many regional- and local-sc ale SM applications which require a high amount of spatial details. Numerous stu dies have been conducted to develop downscaling algorithms to enhance the spatia l resolution of coarse-resolution satellite-derived SM datasets. Machine Learnin g (ML)-based downscaling models have gained prominence recently due to their abi lity to capture non-linear, complex relationships between SM and its driving fac tors, such as vegetation, surface temperature, topography, and climatic conditio ns. This review paper presents a comprehensive review of the ML-based approaches used in SM downscaling."
      原文链接:
    • NETL
    • NSTL

    New Agricultural Robots Study Findings Recently Were Published by a Researcher a t University of Tsukuba (3D Camera and Single- Point Laser Sensor Integration for Apple Localization in Spindle- Type Orchard Systems)

    24-25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 agricultural robots. According to news reporting from Tsukuba, Japan, by NewsRx journalists, research stated, "Accurate localization of apples is the key factor that determines a successful harvesting cycle in the automation of apple harves ting for unmanned operations. In this regard, accurate depth sensing or position al information of apples is required for harvesting apples based on robotic syst ems, which is challenging in outdoor environments because of uneven light variat ions when using 3D cameras for the localization of apples." The news reporters obtained a quote from the research from University of Tsukuba : "Therefore, this research attempted to overcome the effect of light variations for the 3D cameras during outdoor apple harvesting operations. Thus, integrated single-point laser sensors for the localization of apples using a state-of-the- art model, the EfficientDet object detection algorithm with an mAP@0.5 of 0.775 were used in this study. In the experiments, a RealSense D455f RGB-D camera was integrated with a single-point laser ranging sensor utilized to obtain precise a pple localization coordinates for implementation in a harvesting robot. The sing le-point laser range sensor was attached to two servo motors capable of moving t he center position of the detected apples based on the detection ID generated by the DeepSORT (online real-time tracking) algorithm. The experiments were conduc ted under indoor and outdoor conditions in a spindletype apple orchard artifici al architecture by mounting the combined sensor system behind a four-wheel tract or. The localization coordinates were compared between the RGB-D camera depth va lues and the combined sensor system under different light conditions."
      原文链接:
    • NETL
    • NSTL

    Study Results from Universidad Carlos III de Madrid Provide New Insights into Ro botics (Creating Expressive Social Robots That Convey Symbolic and Spontaneous C ommunication)

    25-26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 robotics is the subjec t of a new report. According to news originating from Madrid, Spain, by NewsRx c orrespondents, research stated, "Robots are becoming an increasingly important p art of our society and have started to be used in tasks that require communicati ng with humans." Funders for this research include Ministerio De Ciencia, Innovacion Y Universida des; Agencia Estatal De Investigacion. Our news journalists obtained a quote from the research from Universidad Carlos III de Madrid: "Communication can be decoupled in two dimensions: symbolic (info rmation aimed to achieve a particular goal) and spontaneous (displaying the spea ker's emotional and motivational state) communication. Thus, to enhance human-ro bot interactions, the expressions that are used have to convey both dimensions. This paper presents a method for modelling a robot's expressiveness as a combina tion of these two dimensions, where each of them can be generated independently. This is the first contribution of our work. The second contribution is the deve lopment of an expressiveness architecture that uses predefined multimodal expres sions to convey the symbolic dimension and integrates a series of modulation str ategies for conveying the robot's mood and emotions."
      原文链接:
    • NETL
    • NSTL

    Argonne National Laboratory Researcher Provides Details of New Studies and Findi ngs in the Area of Machine Learning (Simulationtrained machine learning models for Lorentz transmission electron microscopy)

    26-27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 originating from Lemont, Illinois, by NewsRx correspondents, research stated, "Understanding the collective behavi or of complex spin textures, such as lattices of magnetic skyrmions, is of funda mental importance for exploring and controlling the emergent ordering of these s pin textures and inducing phase transitions." Funders for this research include Basic Energy Sciences. Our news correspondents obtained a quote from the research from Argonne National Laboratory: "It is also critical to understand the skyrmion-skyrmion interactio ns for applications such as magnetic skyrmionenabled reservoir or neuromorphic computing. Magnetic skyrmion lattices can be studied using in situ Lorentz trans mission electron microscopy (LTEM), but quantitative and statistically robust an alysis of the skyrmion lattices from LTEM images can be difficult. In this work, we show that a convolutional neural network, trained on simulated data, can be applied to perform segmentation of spin textures and to extract quantitative dat a, such as spin texture size and location, from experimental LTEM images, which cannot be obtained manually. This includes quantitative information about skyrmi on size, position, and shape, which can, in turn, be used to calculate skyrmion- skyrmion interactions and lattice ordering. We apply this approach to segmenting images of Neel skyrmion lattices so that we can accurately identify skyrmion si ze and deformation in both dense and sparse lattices."
      原文链接:
    • NETL
    • NSTL

    Shandong Jianzhu University Researcher Updates Knowledge of Machine Learning (A Comparative Analysis of Machine Learning Algorithms in Predicting the Performanc e of a Combined Radiant Floor and Fan Coil Cooling System)

    27-28页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Researchers detail new data in artificial intelli gence. According to news reporting originating from Jinan, People's Republic of China, by NewsRx correspondents, research stated, "Machine learning algorithms h ave proven to be practical in a wide range of applications. Many studies have be en conducted on the operational energy consumption and thermal comfort of radian t floor systems." Funders for this research include Natural Science Foundation of Shandong Provinc e. The news journalists obtained a quote from the research from Shandong Jianzhu Un iversity: "This paper conducts a case study in a self-designed experimental setu p that combines radiant floor and fan coil cooling (RFCFC) and develops a data m onitoring system as a source of historical operational data. Seven machine learn ing algorithms (extreme learning machine (ELM), convolutional neural network (CN N), genetic algorithm-back propagation (GA-BP), radial basis function (RBF), ran dom forest (RF), support vector machine (SVM), and long short-term memory (LSTM) ) were employed to predict the behavior of the RFCFC system. Corresponding predi ction models were then developed to evaluate operative temperature (Top) and ene rgy consumption (Eh). The performance of the model was evaluated using five erro r metrics. The obtained results showed that the RF model had very high performan ce in predicting Top and Eh, with high correlation coefficients (> 0.9915) and low error metrics. Compared with other models, it also demonstrated high accuracy in Eh prediction, yielding maximum reductions of 68.1, 82.4, and 4 3.2 % in the mean absolute percentage error (MAPE), mean squared er ror (MSE), and mean absolute error (MAE), respectively. A sensitivity ranking al gorithm analysis was also conducted."
      原文链接:
    • NETL
    • NSTL

    Copenhagen University Hospital Reports Findings in Liver Surgery (Efficacy and s afety of robotic liver surgery for the elderly: A propensity-score matched analy sis of short-term outcomes with open liver surgery at a single center in Denmark )

    28-29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 Surger y is the subject of a report. According to news reporting from Copenhagen, Denma rk, by NewsRx journalists, research stated, "The incidence of liver tumors requi ring surgical treatment continues to increase in elderly patients. This study co mpared the short-term results of robotic liver surgery (RLS) versus open liver s urgery (OLS) for liver tumors in elderly patients." The news correspondents obtained a quote from the research from Copenhagen Unive rsity Hospital, "A prospective database including all patients undergoing liver surgery at Copenhagen University Hospital between July 2019 and July 2022 was ma naged retrospectively. Short-term surgical outcomes of the two main cohorts (OLS and RLS) and subgroups were compared using propensity score matching (PSM) in e lderly patients (age 70 years) with liver tumors. A total of 42 matched patients from each group were investigated: the RLS group had significantly larger tumor diameters, less blood loss (821.2 vs. 155.2 mL, p<.001), and shorter hospital stays (6.6 vs. 3.4 days, p<.001). Ove rall morbidity was comparable, while operative times were longer in the RLS grou p. The advantages observed with the robotic approach were replicated in the subg roup of minor liver resections. In patients 70 years, RLS for liver tumors resul ts in significantly less blood loss and shorter hospital stays than OLS."
      原文链接:
    • NETL
    • NSTL

    Cardiff Metropolitan University Reports Findings in Mental Health Diseases and C onditions (Mental health analysis of international students using machine learni ng techniques)

    29-30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 Mental Health Diseases and Conditions is the subject of a report. According to news reporting originat ing in Cardiff, United Kingdom, by NewsRx journalists, research stated, "Interna tional students' mental health has become an increasing concern in recent years, as more students leave their country for better education. They experience a wi de range of challenges while studying abroad that have an impact on their psycho logical well-being." The news reporters obtained a quote from the research from Cardiff Metropolitan University, "These challenges can include language obstacles, cultural differenc es, homesickness, financial issues and other elements that could severely impact the mental health of international students. Given the limited research on the demographic, cultural, and psychosocial variables that influence international s tudents' mental health, and the scarcity of studies on the use of machine learni ng algorithms in this area, this study aimed to analyse data to understand the d emographic, cultural factors, and psychosocial factors that impact mental health of international students. Additionally, this paper aimed to build a machine le arning-based model for predicting depression among international students in the United Kingdom. This study utilized both primary data gathered through an onlin e survey questionnaire targeted at international students and secondary data was sourced from the ‘A Dataset of Students' Mental Health and Help-Seeking Behavio rs in a Multicultural Environment,' focusing exclusively on international studen t data within this dataset. We conducted data analysis on the primary data and c onstructed models using the secondary data for predicting depression among inter national students. The secondary dataset is divided into training (70% ) and testing (30%) sets for analysis, employing four machine learn ing models: Logistic Regression, Decision Tree, Random Forest, and K Nearest Nei ghbor. To assess each algorithm's performance, we considered metrics such as Acc uracy, Sensitivity, Specificity, Precision and AU-ROC curve. This study identifi es significant demographic variables (e.g., loan status, gender, age, marital st atus) and psychosocial factors (financial difficulties, academic stress, homesic kness, loneliness) contributing to international students' mental health."
      原文链接:
    • NETL
    • NSTL