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

    VIT-AP University Researchers Update Knowledge of Machine Learning (Node Significance Analysis in Complex Networks Using Machine Learning and Centrality Measures)

    78-79页
    查看更多>>摘要：Investigators discuss new findings in artificial intelligence. According to news reporting originating from Andhra Pradesh, India, by NewsRx correspondents, research stated, “The study addresses the limitations of traditional centrality measures in complex networks, especially in disease-spreading situations, due to their inability to fully grasp the intricate connection between a node’s functional importance and structural attributes.” Financial supporters for this research include National Science And Technology Council, Taiwan; Chang Gung Memorial Hospital, Taoyuan, Taiwan. Our news journalists obtained a quote from the research from VIT-AP University: “To tackle this issue, the research introduces an innovative framework that employs machine learning techniques to evaluate the significance of nodes in transmission scenarios. This framework incorporates various centrality measures like degree, clustering coefficient, Katz, local relative change in average clustering coefficient, average Katz, and average degree (LRACC, LRAK, and LRAD) to create a feature vector for each node. These methods capture diverse topological structures of nodes and incorporate the infection rate, a critical factor in understanding propagation scenarios. To establish accurate labels for node significance, propagation tests are simulated using epidemic models (SIR and Independent Cascade models). Machine learning methods are employed to capture the complex relationship between a node’s true spreadability and infection rate. The performance of the machine learning model is compared to traditional centrality methods in two scenarios.”
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Nanjing Agricultural University Reports Findings in Machine Learning (Machine learning prediction of higher heating value of biochar based on biomass characteristics and pyrolysis conditions)

    78-78页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting originating from Nanjing, People’s Republic of China, by NewsRx correspondents, research stated, “The higher heating value of biochar is an important parameter for the utilization of biomass energy. In this work, extreme gradient boosting regression and artificial neural network were used to predict it based on the characteristics of biomass and pyrolysis conditions.” Our news editors obtained a quote from the research from Nanjing Agricultural University, “Besides, empirical correlations were developed for comparison. Results showed that the extreme gradient boosting regression models showed better performance (R = 0.83-0.94). The shapley additive explanations and partial dependence plot indicated that lignin content and higher heating value of raw material were highly positively correlated with higher heating value of biochar, and found the better conditions such as pyrolysis temperature (>550 ℃), lignin content (>40 wt%) for high-higher heating value biochar preparation. What’s more, a program that predicted higher heating value of biochar was developed through PySimpleGUI library.”
      原文链接:
    • NETL
    • NSTL

    Yantai University Reports Findings in Intelligent Systems (Adaptive Learning Point Cloud and Image Diversity Feature Fusion Network for 3d Object Detection)

    79-80页
    查看更多>>摘要：A new study on Machine Learning - Intelligent Systems is now available. According to news originating from Yantai, People’s Republic of China, by NewsRx correspondents, research stated, “3D object detection is a critical task in the fields of virtual reality and autonomous driving. Given that each sensor has its own strengths and limitations, multi-sensor-based 3D object detection has gained popularity.” Financial support for this research came from National Natural Science Foundation of China (NSFC). Our news journalists obtained a quote from the research from Yantai University, “However, most existing methods extract high-level image semantic features and fuse them with point cloud features, focusing solely on consistent information from both sensors while ignoring their complementary information. In this paper,we present a novel two-stage multi-sensor deep neural network, called the adaptive learning point cloud and image diversity feature fusion network (APIDFF-Net), for 3D object detection. Our approach employs the fine-grained image information to complement the point cloud information by combining low-level image features with high-level point cloud features. Specifically, we design a shallow image feature extraction module to learn fine-grained information from images, instead of relying on deep layer features with coarsegrained information. Furthermore, we design a diversity feature fusion (DFF) module that transforms low-level image features into point-wise image features and explores their complementary features through an attention mechanism, ensuring an effective combination of fine-grained image features and point cloud features.”
      原文链接:
    • NETL
    • NSTL
    • Springer Nature

    Sun Yat-Sen University Reports Findings in Machine Learning (Quantitative identification of the co-exposure effects of e-waste pollutants on human oxidative stress by explainable machine learning)

    80-81页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting originating from Guangzhou, People’s Republic of China, by NewsRx correspondents, research stated, “Global electronic waste (e-waste) generation continues to grow. The various pollutants released during precarious e-waste disposal activities can contribute to human oxidative stress.” Our news editors obtained a quote from the research from Sun Yat-Sen University, “This study encompassed 129 individuals residing near e-waste dismantling sites in China, with elevated urinary concentrations of e-waste-related pollutants including heavy metals, polycyclic aromatic hydrocarbons (PAHs), organophosphorus flame retardants (OPFRs), bisphenols (BPs), and phthalate esters (PAEs). Utilizing an explainable machine learning framework, the study quantified the co-exposure effects of these pollutants, finding that approximately 23% and 18% of the variance in oxidative DNA damage and lipid peroxidation, respectively, was attributable to these substances. Heavy metals emerged as the most critical factor in inducing oxidative stress, followed by PAHs and PAEs for oxidative DNA damage, and BPs, OPFRs, and PAEs for lipid peroxidation. The interactions between different pollutant classes were found to be weak, attributable to their disparate biological pathways. In contrast, the interactions among congeneric pollutants were strong, stemming from their shared pathways and resultant synergistic or additive effects on oxidative stress. An intelligent analysis system for e-waste pollutants was also developed, which enables more efficient processing of large-scale and dynamic datasets in evolving environments.”
      原文链接:
    • NETL
    • NSTL

    Researchers from Daegu Gyeongbuk Institute of Science and Technology (DGIST) Report on Findings in Machine Learning (Machine learning-based high-frequency neuronal spike reconstruction from low-frequency and low-sampling-rate recordings)

    81-82页
    查看更多>>摘要：New study results on artificial intelligence have been published. According to news reporting out of the Daegu Gyeongbuk Institute of Science and Technology (DGIST) by NewsRx editors, research stated, “Recording neuronal activity using multiple electrodes has been widely used to understand the functional mechanisms of the brain.” The news reporters obtained a quote from the research from Daegu Gyeongbuk Institute of Science and Technology (DGIST): “Increasing the number of electrodes allows us to decode more variety of functionalities. However, handling massive amounts of multichannel electrophysiological data is still challenging due to the limited hardware resources and unavoidable thermal tissue damage. Here, we present machine learning (ML)-based reconstruction of high-frequency neuronal spikes from subsampled low-frequency band signals. Inspired by the equivalence between high-frequency restoration and super-resolution in image processing, we applied a transformer ML model to neuronal data recorded from both in vitro cultures and in vivo male mouse brains. Even with the x8 downsampled datasets, our trained model reasonably estimated high-frequency information of spiking activity, including spike timing, waveform, and network connectivity.”
      原文链接:
    • NETL
    • NSTL

    Investigators from Beijing University of Technology Target Robotics (A Novel Robotic System Enabling Multiple Bilateral Upper Limb Rehabilitation Training Via an Admittance Controller and Force Field)

    82-83页
    查看更多>>摘要：A new study on Robotics is now available. According to news reporting originating from Beijing, People’s Republic of China, by NewsRx correspondents, research stated, “Patients with hemiplegia are usually restricted to performing general bilateral activities of daily life (gbADLs). Bilateral training has been verified to contribute to the rehabilitation of physical functions.” Funders for this research include Beijing Postdoctoral Science Foundation, China, Beijing Natural Science Foundation, National Natural Science Foundation of China (NSFC). Our news editors obtained a quote from the research from the Beijing University of Technology, “Although robotic systems are gradually being employed in the field of rehabilitation, few studies have performed simulations with regards to gbADLs for training. Therefore, a novel end-effector bilateral rehabilitation robotic system (EBReRS) for the upper limb is developed in this article for the task rendering of gbADLs, in which the gbADL-corresponding workspace is obtained via modularly designed bilateral parallelogram mechanisms. In addition, the interaction rendering of multiple bimanual modes (uncoupled, trans-soft-coupled, trans-semi-coupled, and rotation-coupled) is achieved by implementing the admittance model, the inner force field between robotic end-effectors, and the outer force field distributed around. Experiments of the proposed four rehabilitation training modes were carried out on the healthy subject, with the results showing a feasible method of the EBReRS in the simulation of multiple bimanual coordinated rehabilitation training tasks.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Researcher from Stanford University Provides Details of New Studies and Findings in the Area of Artificial Intelligence (Audio-Based Emotion Recognition Using Self-Supervised Learning on an Engineered Feature Space)

    83-84页
    查看更多>>摘要：Research findings on artificial intelligence are discussed in a new report. According to news originating from Stanford, California, by NewsRx correspondents, research stated, “Emotion recognition models using audio input data can enable the development of interactive systems with applications in mental healthcare, marketing, gaming, and social media analysis. While the field of affective computing using audio data is rich, a major barrier to achieve consistently high-performance models is the paucity of available training labels.” Financial supporters for this research include National Institutes of Health. Our news correspondents obtained a quote from the research from Stanford University: “Self-supervised learning (SSL) is a family of methods which can learn despite a scarcity of supervised labels by predicting properties of the data itself. To understand the utility of self-supervised learning for audio-based emotion recognition, we have applied self-supervised learning pre-training to the classification of emotions from the CMU Multimodal Opinion Sentiment and Emotion Intensity (CMU- MOSEI)’s acoustic data. Unlike prior papers that have experimented with raw acoustic data, our technique has been applied to encoded acoustic data with 74 parameters of distinctive audio features at discrete timesteps. Our model is first pre-trained to uncover the randomly masked timestamps of the acoustic data. The pre-trained model is then finetuned using a small sample of annotated data. The performance of the final model is then evaluated via overall mean absolute error (MAE), mean absolute error (MAE) per emotion, overall four-class accuracy, and four-class accuracy per emotion. These metrics are compared against a baseline deep learning model with an identical backbone architecture. We find that self-supervised learning consistently improves the performance of the model across all metrics, especially when the number of annotated data points in the fine-tuning step is small.”
      原文链接:
    • NETL
    • NSTL
    • Mdpi

    Faculty of Technology Researchers Discuss Research in Robotics (Comparative Analysis of Reinforcement Learning Algorithms for Bipedal Robot Locomotion)

    84-84页
    查看更多>>摘要：Researchers detail new data in robotics. According to news reporting out of the Faculty of Technology by NewsRx editors, research stated, “In this research, an optimization methodology was introduced for improving bipedal robot locomotion controlled by reinforcement learning (RL) algorithms.” The news journalists obtained a quote from the research from Faculty of Technology: “Specifically, the study focused on optimizing the Proximal Policy Optimization (PPO), Advantage Actor-Critic (A2C), Soft Actor-Critic (SAC), and Twin Delayed Deep Deterministic Policy Gradients (TD3) algorithms. The optimization process utilized the Tree-structured Parzen Estimator (TPE), a Bayesian optimization technique. All RL algorithms were applied to the same environment, which was created within the OpenAI GYM framework and known as the bipedal walker. The optimization involved the fine-tuning of key hyperparameters, including learning rate, discount factor, generalized advantage estimation, entropy coefficient, and Polyak update parameters. The study comprehensively analyzed the impact of these hyperparameters on the performance of RL algorithms. The results of the optimization efforts were promising, as the fine-tuned RL algorithms demonstrated significant improvements in performance.”
      原文链接:
    • NETL
    • NSTL
    • IEEE

    Study Data from Norwegian University of Science and Technology (NTNU) Update Knowledge of Machine Learning (Electricity Demand Forecasting With Hybrid Classical Statistical and Machine Learning Algorithms: Case Study of Ukraine)

    85-85页
    查看更多>>摘要：Data detailed on Machine Learning have been presented. According to news reporting originating in Trondheim, Norway, by NewsRx journalists, research stated, “This article presents a novel hybrid approach using classic statistics and machine learning to forecast the national demand of electricity. As investment and operation of future energy systems require long-term electricity demand forecasts with hourly resolution, our mathematical model fills a gap in energy forecasting.” Financial support for this research came from Joachim Herz Foundation. The news reporters obtained a quote from the research from the Norwegian University of Science and Technology (NTNU), “The proposed methodology was constructed using hourly data from Ukraine’s electricity consumption ranging from 2013 to 2020. To this end, we analysed the underlying structure of the hourly, daily and yearly time series of electricity consumption. The long-term yearly trend is evaluated using macroeconomic regression analysis. The mid-term model integrates temperature and calendar regressors to describe the underlying structure, and combines ARIMA and LSTM ‘black-box’pattern-based approaches to describe the error term. The short-term model captures the hourly seasonality through calendar regressors and multiple ARMA models for the residual. Results show that the best forecasting model is composed by combining multiple regression models and a LSTM hybrid model for residual prediction. Our hybrid model is very effective at forecasting long-term electricity consumption on an hourly resolution.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier

    Studies from Clarkson University Yield New Information about Machine Learning (Organic Catalysts for Hydrogen Production From Noodle Wastewater: Machine Learning and Deep Learning-based Analysis)

    86-87页
    查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting out of Potsdam, New York, by NewsRx editors, research stated, “Hydrogen production from the electrolysis of wastewater is an environmentally friendly and highly efficient process. The performance of this process for instant noodle wastewater is strongly influenced by covering the PVC sheet with different arrangements of antioxidant-containing protein (ACAP) as an organic catalyst.” Financial support for this research came from Ministry of Education in Saudi Arabia. Our news journalists obtained a quote from the research from Clarkson University, “However, analyzing this process through traditional models and experimental studies takes time, money, and effort. In the present research, several machine learning-based models, including the recurrent neural network (RNN), the least absolute shrinkage and selection operator (LASSO), the extreme gradient boosting (XGBoost), the linear regression (LR), and the light gradient-boosting machine (LightGBM) were developed to accurately predict hydrogen production performance from the electrolysis of noodle wastewater. Several materials have been studied in this research, such as Car, Car-Tur, Tur-Car, Tur, Car-Ver-Tur, and Car-Tof-Ver in the 12-V and 24-V states. For each material created, the LASSO regression and the linear regression formula include 12 formulas (six formulas for each state) for hydrogen production. The R-Squared values range between 0.989 and 0.997 for the six formulas by the polynomial form and by the XGBoost and the lightGBM making the six models for the hydrogen production, and the R-Squared values for all models are 0.999 by linear form for the hydrogen production in the 24-V state. For the hydrogen productions in the 12-V state, the values of the R-Squared range between 0.995 and 0.998 by the polynomial form. Using the lightGBM and the XGBoost, six models are made in linear form, and all of those models’ R-Squared values are 0.999.”
      原文链接:
    • NETL
    • NSTL
    • Elsevier