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

    Researchers from HeNan Polytechnic University Report on Findings in Support Vect or Machines (Ensemble Learning With Support Vector Machines Algorithm for Surfac e Roughness Prediction In Longitudinal Vibratory Ultrasound-assisted Grinding)

    86-86页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-Current study results on Support Vector Machines have been published. According to news reporting originating from Jiaozuo, Peopl e's Republic of China, by NewsRx correspondents, research stated, "It is critica l to have an accurate prediction of surface roughness (Sa) in order to improve g rinding productivity, reduce costs, and minimize the period of time required for trials and testing. Although many prediction methods have been developed, fewer studies have been conducted on the prediction of surface roughness in longitudi nal ultrasonic vibration-assisted grinding (LUVAG)." Our news editors obtained a quote from the research from HeNan Polytechnic Unive rsity, "In this paper, a surface roughness prediction model algorithm based on e nsemble learning of support vector machines (ELSVM) is proposed that can be used for surface roughness prediction of LUVAG alumina ceramics. This paper first de tails the development of the ELSVM surface roughness prediction model, which con sists of four modules: the prepossessing module, the multi-algorithm regression module, the support vector machine algorithm (SVM) module, and the ensemble modu le. In addition, ELSVM was compared with four other machine learning methods bas ed on experimental results for surface roughness prediction modeling. The error of ELSVM model was reduced by 6.3%, 7.9%, 8.9% , and 7.5%, respectively, compared to the individual prediction mod els such as I-AISPSO, I-AIS, SPSO, and KBaNN."
      原文链接:
    • NETL
    • NSTL

    Studies from Brunel University London Update Current Data on Machine Learning (A Comparative Analysis of Advanced Machine Learning Techniques for River Streamfl ow Time-Series Forecasting)

    87-87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 originating from Uxbridge, United King dom, by NewsRx correspondents, research stated, "This study examines the contrib ution of rainfall data (RF) in improving the streamflow-forecasting accuracy of advanced machine learning (ML) models in the Syr Darya River Basin." Financial supporters for this research include Horizon Europe. The news editors obtained a quote from the research from Brunel University Londo n: "Different sets of scenarios included rainfall data from different weather st ations located in various geographical locations with respect to the flow monito ring station. Long short-term memory (LSTM)-based models were used to examine th e contribution of rainfall data on streamflow-forecasting performance by investi gating five scenarios whereby RF data from different weather stations were incor porated depending on their geographical positions. Specifically, the All-RF scen ario included all rainfall data collected at 11 stations; Upstream-RF (Up-RF) an d Downstream-RF (Down-RF) included only the rainfall data measured upstream and downstream of the streamflow-measuring station; Pearson-RF (P-RF) only included the rainfall data exhibiting the highest level of correlation with the streamflo w data, and the Flow-only (FO) scenario included streamflow data. The evaluation metrics used to quantitively assess the performance of the models included the RMSE, MAE, and the coefficient of determination, R2. Both ML models performed be st in the FO scenario, which shows that the diversity of input features (hydrolo gical and meteorological data) did not improve the predictive accuracy regardles s of the positions of the weather stations."
      原文链接:
    • NETL
    • NSTL

    Researchers from North China Electric Power University Detail New Studies and Fi ndings in the Area of Machine Learning (Learnable Bilevel Optimization Method fo r Electrical Capacitance Tomography)

    88-88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 Ma chine Learning. According to news reporting from Beijing, People's Republic of C hina, by NewsRx journalists, research stated, "The positive role of electrical c apacitance tomography technology depends on high -precision tomographic images. Despite its success, one of the main barriers is the low -quality tomogram." Financial support for this research came from National Key Research and Develop- ment Program of China. The news correspondents obtained a quote from the research from North China Elec tric Power University, "A new learnable bilevel optimization imaging method is p roposed to address this problem in this study, in which the image prior and mode l parameters can be learned from the collected datasets. The upper level optimiz ation problem learns the regularization parameter under the constraint of the lo wer level optimization problem that implements image reconstruction. A new lower level optimization problem with the introduced machine learning prior is built, which leverages the prior knowledge from collected datasets, imaging targets an d imaging mechanisms. The machine learning prior is learned through extreme lear ning machine, and the training is reformulated into a fractional optimization pr oblem with the physical mechanisms of imaging as a constraint. A new optimizer i s proposed to solve the learnable bilevel optimization imaging problem. The effe ctiveness has been demonstrated by the reconstruction of higher precision images and better noise immunity in comparison with advanced imaging techniques."
      原文链接:
    • NETL
    • NSTL

    Recent Research from Tsinghua University Highlight Findings in Robotics (3-d Den se Reconstruction of Vision-based Tactile Sensor With Coded Markers)

    89-89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 Robotics is now availab le. According to news reporting from Beijing, People's Republic of China, by New sRx journalists, research stated, "Perceiving accurate 3-D object shape is an es sential and challenging task for robotic manipulation, which is commonly based o n vision systems. However, vision perception suffers from several limitations, e specially in manipulation tasks where objects are often occluded by the robotic hand." Financial support for this research came from National Science and Technology Ma jor Project of the Ministry of Science and Technology of China. The news correspondents obtained a quote from the research from Tsinghua Univers ity, "Alternatively, tactile perception attracts a lot of attention. Due to the low resolution, the density and efficiency of existing tactile-based 3-D reconst ructions are limited. In order to solve the above problems, this article describ es a vision-based tactile sensor with coded markers. By combining the neighborho od structure coding method and U-net-based decoding algorithm, the sensor can re construct high-density 3-D object shapes efficiently."
      原文链接:
    • NETL
    • NSTL

    Reports from Florida International University Add New Data to Findings in Artifi cial Intelligence [Music Teachers' Labeling Accuracy and Qual ity Ratings of Lesson Plans By Artificial Intelligence (Ai) and Humans]

    90-90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 originating in Miami, Flori da, by NewsRx editors, the research stated, "This study explored the potential o f artificial intelligence (ChatGPT) to generate lesson plans for music classes t hat were indistinguishable from music lesson plans created by humans, with curre nt music teachers as assessors. Fifty-six assessors made a total of 410 ratings across eight lesson plans, assigning a quality score to each lesson plan and lab eling if they believed each lesson plan was created by a human or generated by A I." The news reporters obtained a quote from the research from Florida International University, "Despite the human-made lesson plans being rated higher in quality as a group (p <.01, d = 0.44), assessors were unable to ac curately label if a lesson plan was created by a human or generated by AI (55% accurate overall). Labeling accuracy was positively predicted by quality scores on human-made lesson plans and previous personal use of AI, while accuracy was n egatively predicted by quality scores on AI-generated lesson plans and perceptio n of how useful AI will be in the future. Open-ended responses from 42 teachers suggested assessors used three factors when making evaluations: specific details , evidence of classroom knowledge, and wording."
      原文链接:
    • NETL
    • NSTL

    Study Data from Beijing Information Science and Technology University Update Und erstanding of Robotics (Accurate Kinematic Calibration of a Six-dof Serial Robot By Using Hybrid Models With Reduced Dimension and Minimized Linearization Error s)

    91-92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 Robotics are presented i n a new report. According to news reporting from Beijing, People's Republic of C hina, by NewsRx journalists, research stated, "PurposeIn typical model-based cal ibration, linearization errors are derived inevitably, and non-negligible negati ve impact will be induced on the identification results if the rotational kinema tic errors are not small enough or the lengths of links are too long, which is c ommon in the industrial cases. Thus, an accurate two-step kinematic calibration method minimizing the linearization errors is presented for a six-DoF serial rob ot to improve the calibration negative impact of linearization on identification accuracy is minimized by rem oving the responsible linearized kinematic errors from the complete kinematic er ror model." Funders for this research include National Natural Science Foundation of China ( NSFC), National Natural Science Foundation of China (NSFC).
      原文链接:
    • NETL
    • NSTL

    Tongji University Reports Findings in Sepsis (Machine learning reveals ferroptos is features and a novel ferroptosis classifier in patients with sepsis)

    92-93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 originating from Shanghai, People's Republic of China, by NewsRx correspondents, research stated, "Sepsis is an organ malfunction disease that may become fatal and is commonly a ccompanied by severe complications such as multiorgan dysfunction. Patients who are already hospitalized have a high risk of death due to sepsis." Our news journalists obtained a quote from the research from Tongji University, "Even though early diagnosis is very important, the technology and clinical appr oaches that are now available are inadequate. Hence, there is an immediate neces sity to investigate biological markers that are sensitive, specific, and reliabl e for the prompt detection of sepsis to reduce mortality and improve patient pro gnosis. Mounting research data indicate that ferroptosis contributes to the occu rrence, development, and prevention of sepsis. However, the specific regulatory mechanism of ferroptosis remains to be elucidated. This research evaluated the e xpression profiles of ferroptosis-related genes (FRGs) and the diagnostic signif icance of the ferroptosis-related classifiers in sepsis. We collected three peri pheral blood data sets from septic patients, integrated the clinical examination data and mRNA expression profile of these patients, and identified 13 FRGs in s epsis through a co-expression network and differential analysis. Then, an optima l classifier tool for sepsis was constructed by integrating a variety of machine learning algorithms. Two key genes, ATG16L1 and SRC, were shown to be shared be tween the algorithms, and thus were identified as the FRG signature of classifie r. The tool exhibited satisfactory diagnostic efficiency in the training data se t (AUC = 0.711) and two external verification data sets (AUC = 0.961; AUC = 0.91 3). In the rat cecal ligation puncture sepsis model, in vivo experiments verifie d the involvement of ATG16L1 and SRC in the early sepsis process."
      原文链接:
    • NETL
    • NSTL

    Mahidol University Reports Findings in Machine Learning (Development and interna l validation of machine-learning models for predicting survival in patients who underwent surgery for spinal metastases)

    93-93页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Machine Learning is the subject o f a report. According to news reporting originating from Bangkok, Thailand, by N ewsRx correspondents, research stated, "A retrospective study. This study aimed to develop machine-learning algorithms for predicting survival in patients who u nderwent surgery for spinal metastasis." Our news editors obtained a quote from the research from Mahidol University, "Th is study develops machine-learning models to predict postoperative survival in s pinal metastasis patients, filling the gaps of traditional prognostic systems. U tilizing data from 389 patients, the study highlights XGBoost and CatBoost algor ithms effectiveness for 90, 180, and 365-day survival predictions, with preopera tive serum albumin as a key predictor. These models offer a promising approach f or enhancing clinical decisionmaking and personalized patient care. A registry of patients who underwent surgery (instrumentation, decompression, or fusion) fo r spinal metastases between 2004 and 2018 was used. The outcome measure was surv ival at postoperative days 90, 180, and 365. Preoperative variables were used to develop machinelearning algorithms to predict survival chance in each period. The performance of the algorithms was measured using the area under the receiver operating characteristic curve (AUC). A total of 389 patients were identified, with 90-, 180-, and 365-day mortality rates of 18%, 41% , and 45% postoperatively, respectively. The XGBoost algorithm sho wed the best performance for predicting 180-day and 365-day survival (AUCs of 0. 744 and 0.693, respectively). The CatBoost algorithm demonstrated the best perfo rmance for predicting 90-day survival (AUC of 0.758). Serum albumin had the high est positive correlation with survival after surgery."
      原文链接:
    • NETL
    • NSTL

    Saveetha School of Engineering Researcher Provides New Data on Support Vector Ma chines (Testing the auto-regressive integrated moving average approach vs the su pport vector machines-based model for materials forecasting to reduce inventory)

    94-94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 . According to news originating from Tamil Nadu, India, by NewsRx editors, the r esearch stated, "Poor planning and scheduling increase buying, storage, and obso lescence expenses. Material shortages increase labor, machine optimum time, etc. " Funders for this research include King Saud University. Our news correspondents obtained a quote from the research from Saveetha School of Engineering: "Industrial raw materials, semi-finished items, spares, and cons umables have distinct consumption patterns, reorder points, purchase lead times, quantity limits, discounts, etc. To save money, machine learning predicts deman d and prepares materials. This study employs ARIMA or Support Vector Machine (SV M) machine learning-based forecasting approaches to forecast materials for less inventory. Feature engineering eliminates seasonality, time series, and external demand and ignores data irregularities, missing figures, and disparities. This approach needs to adapt traits to factors, separate test and training data, and consider many future models to represent the best forecasts. Forecast reliabilit y and consistency were examined for each model. Inventory management systems wer e evaluated for computational complexity and installation ease and found impleme ntation issues. Both models' input data and resilience were examined using sensi tivity analysis. Accurate prediction SVM and ARIMA predict material demand diffe rently. Meaningful statistics show the optimal model."
      原文链接:
    • NETL
    • NSTL

    Study Data from National University of Technology Update Knowledge of Robotics ( Indoor Scene Classification through Dual-Stream Deep Learning: A Framework for I mproved Scene Understanding in Robotics)

    95-95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 robotics is now availab le. According to news reporting originating from Islamabad, Pakistan, by NewsRx correspondents, research stated, "Indoor scene classification plays a pivotal ro le in enabling social robots to seamlessly adapt to their environments, facilita ting effective navigation and interaction within diverse indoor scenes. By accur ately characterizing indoor scenes, robots can autonomously tailor their behavio rs, making informed decisions to accomplish specific tasks." Our news editors obtained a quote from the research from National University of Technology: "Traditional methods relying on manually crafted features encounter difficulties when characterizing complex indoor scenes. On the other hand, deep learning models address the shortcomings of traditional methods by autonomously learning hierarchical features from raw images. Despite the success of deep lear ning models, existing models still struggle to effectively characterize complex indoor scenes. This is because there is high degree of intra-class variability a nd inter-class similarity within indoor environments. To address this problem, w e propose a dual-stream framework that harnesses both global contextual informat ion and local features for enhanced recognition. The global stream captures high -level features and relationships across the scene. The local stream employs a f ully convolutional network to extract fine-grained local information.
      原文链接:
    • NETL
    • NSTL