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

    Study Findings from Norwegian University of Science and Technology (NTNU) Advance Knowledge in Machine Learning (Transferability of Temperature Evolution of Dissimilar Wire-Arc Additively Manufactured Components by Machine Learning)

    57-58页
    查看更多>>摘要:Fresh data on artificial intelligence are presented in a new report. According to news reporting originating from Trondheim, Norway, by NewsRx correspondents, research stated, “Wire-arc additive manufacturing (WAAM) is a promising industrial production technique.” Our news journalists obtained a quote from the research from Norwegian University of Science and Technology (NTNU): “Without optimization, inherent temperature gradients can cause powerful residual stresses and microstructural defects. There is therefore a need for data-driven methods allowing realtime process optimization for WAAM. This study focuses on machine learning (ML)-based prediction of temperature history for WAAM-produced aluminum bars with different geometries and process parameters, including bar length, number of deposition layers, and heat source movement speed. Finite element (FE) simulations are used to provide training and prediction data. The ML models are based on a simple multilayer perceptron (MLP) and performed well during baseline training and testing, giving a testing mean absolute percentage error (MAPE) of less than 0.7% with an 80/20 train-test split, with low variation in model performance. When using the trained models to predict results from FE simulations with greater length or number of layers, the MAPE increased to an average of 3.22% or less, with greater variability.”

    Investigators from Department of Computer Sciences and Engineering Target Artificial Intelligence (A Study and Comparison of Deep Learning Based Potato Leaf Disease Detection and Classification Techniques Using Explainable Ai)

    58-59页
    查看更多>>摘要:Research findings on Artificial Intelligence are discussed in a new report. According to news reporting from Kolkata, India, by NewsRx journalists, research stated, “The goal of artificial intelligence (AI), a field with a solid scientific foundation, is to enable machines to simulate human intelligence and problem-solving abilities. AI focuses on the study, development, and application of complex algorithms and computational models, with a particular focus on deep learning techniques.” The news correspondents obtained a quote from the research from the Department of Computer Sciences and Engineering, “The application of artificial intelligence to potato leaf disease detection can reduce the restrictions brought on by the artificial selection of spotted disease features and improve the efficiency and speedup. It has also turned into a research hotspot in the agricultural sector. This work consists of four types of potato leaf diseases, such as early-blight disease, septoria disease, late-blight disease, and black-leg disease. It is a challenging task to identify and classify such diseases from the healthy images. As a result, this work uses a set of benchmark deep learning models to identify and categorize these four disease types in potato leaves. Furthermore, compared to existing models, our recommended models provide better accuracy and have visible results. In comparison to other cutting-edge models, the results of the proposed deep ensemble algorithm (CNN, CNN-SVM, and DNN) offers the best accuracy of 99.98%. All the sample images (healthy and unhealthy) are collected from different farms of the West Bengal state and prepare the experimented dataset. The working model has an additional benefit in terms of running time complexity (O(Ei)(1ik) and 17.86 s) and statistical comparison.”

    New Robotics Study Findings Recently Were Reported by Researchers at Southwest Petroleum University (Research On Friction Characteristics of the Support Mechanism of the Drilling Robot Under Axial-torsional Load)

    60-61页
    查看更多>>摘要:Investigators publish new report on Robotics. According to news originating from Chengdu, People’s Republic of China, by NewsRx correspondents, research stated, “Because the coiled tubing drilling robot (CTDR) needs to pull the coiled tubing (CT) and provide the weight on bit (WOB), the traction force is an essential parameter for evaluating the performance of the CTDR. The friction performance between the support mechanism of the CTDR and the borehole wall will directly affect the traction force.” Financial supporters for this research include National Natural Science Foundation of China (NSFC), China Postdoctoral Science Foundation, Sichuan Science and Technology Program, Special Funding for Sichuan Postdoctoral Research Project. Our news journalists obtained a quote from the research from Southwest Petroleum University, “At present, there is not a research paper about the mechanical behavior of the interaction between the support mechanism and the borehole wall. On this basis, a model of contact mechanics of the friction block of the support mechanism and the borehole wall was established. The model of contact mechanics integrates the combined factors of the torsional forces and axial forces generated by the drill bit and the CTDR. The friction performance between the friction block of the support mechanism and the borehole wall under different pa-rameters and conditions was investigated. It is found that the size of the rake angle of the tooth has little effect on the damage of the borehole wall only under normal force. And, the rake angle of the tooth is negatively correlated with the equivalent friction coefficient. The embedded depth is positively correlated with the equivalent friction coefficient. When the rake angle of the tooth is greater than 35 degrees, the influence of the embedded depth on the equivalent friction coefficient is weakened. When the embedding depth of the friction block reaches 0.3 mm, the equivalent friction coefficient is greater than 1. When the bevel angle of the tooth is 20 degrees, the friction block performs best. The optimized structural parameters of the friction block are as follows: rake angle of the tooth of 35 degrees, back angle of 60 degrees, spacing of 4 mm, and bevel angle of the tooth of 20 degrees. Further contact experiments were conducted between a single tooth of the friction block and a rock sample. The dif-ferences between the experimental results and the numerical simulation results were analyzed. The correctness of the theoretical model is verified by experiments. This paper reveals the relationship between structural pa-rameters and equivalent friction coefficient.”

    New Findings from Federal University of Rio Grande do Norte Describe Advances in Machine Learning [SHapley Additive exPlanations (SHAP) for Efficient Feature Selection in Rolling Bearing Fault Diagnosis]

    61-62页
    查看更多>>摘要:Investigators publish new report on artificial intelligence. According to news reporting out of Natal, Brazil, by NewsRx editors, research stated, “This study introduces an efficient methodology for addressing fault detection, classification, and severity estimation in rolling element bearings.” Financial supporters for this research include Coordenacao De Aperfeicoamento De Pessoal De Nivel Superior. Our news reporters obtained a quote from the research from Federal University of Rio Grande do Norte: “The methodology is structured into three sequential phases, each dedicated to generating distinct machine-learning-based models for the tasks of fault detection, classification, and severity estimation. To enhance the effectiveness of fault diagnosis, information acquired in one phase is leveraged in the subsequent phase. Additionally, in the pursuit of attaining models that are both compact and efficient, an explainable artificial intelligence (XAI) technique is incorporated to meticulously select optimal features for the machine learning (ML) models. The chosen ML technique for the tasks of fault detection, classification, and severity estimation is the support vector machine (SVM). To validate the approach, the widely recognized Case Western Reserve University benchmark is utilized.”

    Research from University of Belgrade Broadens Understanding of Machine Learning (Differentiable programming in machine learning)

    62-62页
    查看更多>>摘要:Current study results on artificial intelligence have been published. According to news reporting from Belgrade, Serbia, by NewsRx journalists, research stated, “This paper explains automatic differentiation, discussing two primary modes - forward and backward - and their respective implementation methods.” Financial supporters for this research include Ministry of Education, Science And Technological Development of The Republic of Serbia. The news reporters obtained a quote from the research from University of Belgrade: “In the context of issues encountered in machine learning and deep learning, the forward mode is deemed more suitable as it efficiently differentiates functions with numerous inputs compared to outputs. Given Python’s pivotal role in the ML landscape, the paper elaborates on two widely used deep learning libraries-PyTorch and TensorFlow.”

    Studies from Chouaib Doukkali University Further Understanding of Machine Learning (Predictive Performance of Machine Learning Model With Varying Sampling Designs, Sample Sizes, and Spatial Extents)

    63-63页
    查看更多>>摘要:Data detailed on Machine Learning have been presented. According to news reporting originating from El Jadida, Morocco, by NewsRx correspondents, research stated, “Using machine learning and earth observation data to capture real-world variability in spatial predictive map-ping depends on sample size, design, and spatial extent. Nonetheless, there is still ambiguity in answering some basic questions: a) How many samples are necessary for fitting the model? b) Which sampling techniques are suitable for modeling? c) Do results vary with changes in spatial extents? These questions are crucial for spatial modeling projects and require proper investigation.” Our news editors obtained a quote from the research from Chouaib Doukkali University, “In the present study, we evaluated two sampling designs with different sample sizes, considering three nested spatial extents. Specifically, we adopted the conditioned Latin Hypercube Sampling and Simple Random Sampling designs. Based on this, a Random Forest model was used to predict Above-Ground forest Biomass at local, regional, and national spatial extents, comparing different sample sizes (n = 25, 50, 100, 200, 300, and 500). We defined one national extent, five regional extents within the national extent, and a local extent inside each regional extent. Each sampling design and size combination was tested 100 iterations. The results showed that there was no significant difference between the different sampling designs. The accuracy metrics showed marginal differences for 25 and 50 sample sizes, which were then reduced to minimal and provided similar results. However, a deeper analysis of all 100 repetitions exposed a noteworthy pattern: cLHS outperformed the SRS in terms of RMSE and variability. Regarding the sampling size, the R2 values increased with increasing sample size. Nevertheless, beyond a minimum of 300 to 500 samples, the improvement in accuracy became insignificant, emphasizing the diminishing returns with excessively large sample sizes. Moreover, increasing the size of the spatial extent reduced the accuracy of the model, possibly due to the effect of environmental factors or landscape nature.”

    Data on Robotics Reported by Researchers at Nanjing University of Information Science and Technology (NUIST) (Self-sensing Origami-inspired Soft Twisting Actuators and Its Application In Soft Robots)

    64-64页
    查看更多>>摘要:Investigators discuss new findings in Robotics. According to news originating from Nanjing, People’s Republic of China, by NewsRx correspondents, research stated, “The good compliance of soft robots provides a reliable safety environment for human-robot interaction; however, it also creates challenges for adding sensors to soft robots. In this letter, we propose a self-sensing origami-inspired soft twisting actuator.” Financial support for this research came from National Natural Science Foundation of China (NSFC). Our news journalists obtained a quote from the research from the Nanjing University of Information Science and Technology (NUIST), “The actuator is designed based on the structure of origami, enabling the compound motion of twist and contraction. The position sensor made from flexible fabric material is integrated in the soft actuator body. With twisting angle feedback, the self-sensing twisting actuator can not only provide expected motion but also acquire additional environment information based on real-time sensing. This letter discusses the design, fabrication, and experimental validation of proposed self-sensing twisting actuator. Based on the self-sensing twisting actuator, a soft gripper, a soft robotic arm, and a soft hexapod robot, all vacuum-powered, are designed and prototyped to validate their performance.”

    Eindhoven University of Technology Reports Findings in Artificial Intelligence (Artificial intelligence based cardiotocogram assessment during labor)

    65-66页
    查看更多>>摘要:New research on Artificial Intelligence is the subject of a report. According to news originating from Eindhoven, Netherlands, by NewsRx correspondents, research stated, “To assess whether artificial intelligence, inspired by clinical decision-making procedures in delivery rooms, can correctly interpret cardiotocographic tracings and distinguish between normal and pathological events. A method based on artificial intelligence was developed to determine whether a cardiotocogram shows a normal response of the fetal heart rate to uterine activity (UA).” Our news journalists obtained a quote from the research from the Eindhoven University of Technology, “For a given fetus and given the UA and previous FHR, the method predicts a fetal heart rate response, under the assumption that the fetus is still in good condition and based on how that specific fetus has responded so far. We hypothesize that this method, when having only learned from fetuses born in good condition, is incapable of predicting the response of a compromised fetus or an episode of transient fetal distress. The (in)capability of the method to predict the fetal heart rate response would then yield a method that can help to assess fetal condition when the obstetrician is in doubt. Cardiotocographic data of 678 deliveries during labor were selected based on a healthy outcome just after birth. The method was trained on the cardiotocographic data of 548 fetuses of this group to learn their heart rate response. Subsequently it was evaluated on 87 fetuses, by assessing whether the method was able to predict their heart rate responses. The remaining 43 cardiotocograms were segment-by-segment annotated by three experienced gynecologists, indicating normal, suspicious, and pathological segments, while having access to the full recording and neonatal outcome. This future knowledge makes the expert annotations of a quality that is unachievable during live interpretation. The comparison between abnormalities detected by the method (only using past and present input) and the annotated CTG segments by gynecologists (also looking at future input) yields an area under the curve of 0.96 for the distinction between normal and pathological events in majority-voted annotations. The developed method can distinguish between normal and pathological events in near real-time, with a performance close to the agreement between three gynecologists with access to the entire CTG tracing and fetal outcome.”

    Findings from Prince of Songkla University Provide New Insights into Machine Learning (Electrocardiogram Analysis for Kratom Users Utilizing Deep Residual Learning Network and Machine Learning)

    66-67页
    查看更多>>摘要:Current study results on Machine Learning have been published. According to news reporting from Hat Yai, Thailand, by NewsRx journalists, research stated, “Kratom (Mitragyna speciosa Korth) is a common tropical plant found in Southeast Asia. Its leaves possess medicinal properties and are used to treat various ailments.” Financial support for this research came from Center for Addiction Studies (CADS) and the Thai Health Promotion Foundation. The news correspondents obtained a quote from the research from the Prince of Songkla University, “However, the effects of kratom extract in terms of biological domains are still concerning. Although considerable studies have been conducted on the effects of kratom usage over the last few years, no study using in silico analysis of kratom users’ electrocardiogram (ECG) has been reported to date. This study aims to examine the long-term effects of kratom consumption using the ECG signals and deep learning (DL) network and machine learning techniques. Raw ECG signals were used as input for training and detecting abnormalities, and a deep residual learning network (DRLN) model was implemented to develop a feature extractor from single-lead datasets; the extracted features were used to train conventional machine learning classifiers. The confounding ECG abnormality factors, namely, age, sex, smoking, alcohol consumption, and exercise, were analyzed for association using the chi-square test. The main results of our study showed that kratom usage is not associated with ECG abnormalities. However, the ECG signal was affected more by gender than by the other factors; it exhibited the highest sensitivity and specificity (score = 0.63).”

    University Hospital Arnau de Vilanova Reports Findings in Glioblastomas (Glioblastoma Pseudoprogression Discrimination Using Multiparametric Magnetic Resonance Imaging, Principal Component Analysis, and Supervised and Unsupervised Machine ...)

    67-67页
    查看更多>>摘要:New research on Oncology - Glioblastomas is the subject of a report. According to news reporting originating in Lleida, Spain, by NewsRx journalists, research stated, “One of the most frequent phenomena in the follow-up of glioblastoma is pseudoprogression, present in up to half of cases. The clinical usefulness of discriminating this phenomenon through magnetic resonance imaging and nuclear medicine has not yet been standardized; in this study, we used machine learning on multiparametric magnetic resonance imaging to explore discriminators of this phenomenon.” The news reporters obtained a quote from the research from University Hospital Arnau de Vilanova, “For the study, 30 patients diagnosed with IDH wild-type glioblastoma operated on at both study centers in 2011-2020 were selected; 15 patients corresponded to early tumor progression and 15 patients to pseudoprogression. Using unsupervised learning, the number of clusters and tumor segmentation was recorded using gap-stat and k-means method, adjusting to voxel adjacency. In a second phase, a class prediction was carried out with a multinomial logistic regression supervised learning method; the outcome variables were the percentage of assignment, class overrepresentation, and degree of voxel adjacency. Unsupervised learning of the tumor in its diagnosis shows up to 14 well-differentiated tumor areas. In the supervised learning phase, there is a higher percentage of assigned classes (P <0.01), less overrepresentation of classes (P <0.01), and greater adjacency (55% vs. 33%) in cases of true tumor progression compared with pseudoprogression.”