查看更多>>摘要：Researchers detail new data in Machine Learning. According to news reporting from Beijing, People's Republic of China, by NewsRx journalists, research stated, "Radiomics refers to the high-throughput extraction of quantitative features from medical images, and is widely used to construct machine learning models for the prediction of clinical outcomes, while feature engineering is the most important work in radiomics. However, current feature engineering methods fail to fully and effectively utilize the heterogeneity of features when dealing with different kinds of radiomics features." Financial support for this research came from National Natural Science Foundation of China (NSFC). The news correspondents obtained a quote from the research from Beihang University, "In this work, latent representation learning is first presented as a novel feature engineering approach to reconstruct a set of latent space features from original shape, intensity and texture features. This proposed method projects features into a subspace called latent space, in which the latent space features are obtained by minimizing a unique hybrid loss function including a clustering-like loss and a reconstruction loss. The former one ensures the separability among each class while the latter one narrows the gap between the original features and latent space features. Experiments were performed on a multi-center non-small cell lung cancer (NSCLC) subtype classification dataset from 8 international open databases. Results showed that compared with four traditional feature engineering methods (baseline, PCA, Lasso and L2,1-norm minimization), latent representation learning could significantly improve the classification performance of various machine learning classifiers on the independent test set (all p＜0.001). Further on two additional test sets, latent representation learning also showed a significant improvement in generalization performance."
查看更多>>摘要：2024 FEB 22 (NewsRx) – By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News – New research on Robotics is the subject of a report. According to news reporting originating in Zhejiang, People's Republic of China, by NewsRx journalists, research stated, "Synthesizing the best material globally is challenging; it needs to know what and how much the best ingredient composition should be for satisfying multiple figures of merit simultaneously. Traditional one-variable-at-a-time methods are inefficient; the design-build-test-learn (DBTL) method could achieve the optimal composition from only a handful of ingredients." The news reporters obtained a quote from the research from Zhejiang Laboratory, "A vast design space needs to be explored to discover the possible global optimal composition for on-demand materials synthesis. This research developed a hypothesis-guided DBTL (H-DBTL) method combined with robots to expand the dimensions of the search space, thereby achieving a better global optimal performance. First, this study engineered the search space with knowledge-aware chemical descriptors and customized multiobjective functions to fulfill on-demand research objectives. To verify this concept, this novel method was used to optimize colorimetric ammonia sensors across a vast design space of as high as 19 variables, achieving two remarkable optimization goals within 1 week: first, a sensing array was developed for ammonia quantification of a wide dynamic range, from 0.5 to 500 ppm; second, a new state-of-the-art detection limit of 50 ppb was reached."
查看更多>>摘要：New research on Oncology - Liver Cancer is the subject of a report. According to news reporting from Beijing, People's Republic of China, by NewsRx journalists, research stated, "To develop and validate a radiomics machine learning (Rad-ML) model based on preoperative MRI to predict extrahepatic metastasis (EHM) in hepatocellular carcinoma (HCC) patients receiving transarterial chemoembolization (TACE) treatment. A total of 355 HCC patients who received multiple TACE procedures were split at random into a training set and a test set at a 7:3 ratio." The news correspondents obtained a quote from the research from Cancer Hospital, "Radiomic features were calculated from tumor and peritumor in arterial phase and portal venous phase, and were identified using intraclass correlation coefficient, maximal relevance and minimum redundancy, and least absolute shrinkage and selection operator techniques. Cox regression analysis was employed to determine the clinical model. The best-performing algorithm among eight machine learning methods was used to construct the Rad-ML model. A nomogram combining clinical and Rad-ML parameters was used to develop a combined model. Model performance was evaluated using C-index, decision curve analysis, calibration plot, and survival analysis. In clinical model, elevated neutrophil to lymphocyte ratio and alpha-fetoprotein were associated with faster EHM. The XGBoost-based Rad-ML model demonstrated the best predictive performance for EHM. When compared to the clinical model, both the Rad-ML model and the combination model performed better (C-indexes of 0.61, 0.85, and 0.86 in the training set, and 0.62, 0.82, and 0.83 in the test set, respectively). However, the combined model's and the Rad-ML model's prediction performance did not differ significantly. The most influential feature was peritumoral waveletHLL_firstorder_Minimum in AP, which exhibited an inverse relationship with EHM risk."
查看更多>>摘要：Fresh data on Machine Learning - Support Vector Machines are presented in a new report. According to news reporting out of Qingdao, People's Republic of China, by NewsRx editors, research stated, "The intelligent recognition and monitoring of sand particles in annular multiphase flow are of paramount importance for the safe production of high-yield gas wells. In this study, an experiment based on a uniaxial vibration method was initially designed to collect collision response signals between sand particles and the pipe wall." Financial supporters for this research include National Natural Science Foundation of China (NSFC), National Natural Science Foundation of China (NSFC), Natural Science Foundation of Shandong Province, Natural Science Basic Research Program of Shaanxi. Our news journalists obtained a quote from the research from the China University of Petroleum (East China), "Utilizing wavelet packet analysis, the identification and classification of sand-carrying signals in the liquid film and gas core regions were first achieved. The results indicate that the excitation frequency range for sand-carrying signals impacting the pipe wall in the liquid film region was 19.2-38.4 kHz, while in the gas core region, it was 38.4-51.2 kHz. Finally, convolutional neural network (CNN) models, support vector machine (SVM) models, and CNN-SVM models were constructed to characterize and identify sand particles in annular multiphase flow. The results show that the CNN-SVM model improved the accuracy of sand-carrying data recognition by 2.0% compared to CNN and by 5.6% compared to SVM for gas core region data, and by 1.8% compared to CNN and by 8.6% compared to SVM for liquid film region data."
查看更多>>摘要：Data detailed on artificial intelligence have been presented. According to news origi- nating from Abu Dhabi, United Arab Emirates, by NewsRx correspondents, research stated, "This state-of- the-art review comprehensively examines the landscape of Distributed Denial of Service (DDoS) anomaly detection in Software Defined Networks (SDNs) through the lens of advanced Machine Learning (ML) and Deep Learning (DL) techniques. The application domain of this work is focused on addressing the inherent security vulnerabilities of SDN environments and developing an automated system for detecting and mitigating network attacks." Funders for this research include United Arab Emirates University Under Research Start-up Proposal. Our news correspondents obtained a quote from the research from United Arab Emirates University: "The problem focused on in this review is the need for effective defensive mechanisms and detection methodologies to address these vulnerabilities. Conventional network measurement methodologies are limited in the context of SDNs, and the proposed ML and DL techniques aim to overcome these limitations by providing more accurate and efficient detection and mitigation of DDoS attacks. The objective of this work is to provide a comprehensive review of related works in the field of SDN anomaly detection recent advances, categorized into two groups via ML and DL techniques. The proposed systems utilize a variety of techniques, including Supervised Learning (SL), Unsupervised Learning (UL) Ensemble Learning (EL) and DL solutions, to process IP flows, profile network traffic, and identify attacks. The output comprises the mitigation policies learned by ML/DL techniques, and the proposed systems act as sophisticated gatekeepers, applying automated mitigation policies to curtail the extent of damage resulting from these attacks. The results obtained from the evaluation metrics, including accuracy, precision, and recall, confirm the marked effectiveness of the proposed systems in detecting and mitigating various types of attacks, including Distributed Denial of Service (DDoS) attacks. The proposed systems' foundational contributions are manifest in their efficacy for both DDoS attack detection and defense within the SDN environment."
查看更多>>摘要：Investigators discuss new findings in Robotics. According to news reporting originating in Zhejiang, People's Republic of China, by NewsRx journalists, research stated, "Almost all forms of soft crawling robots and animals rely on frictional anisotropy to achieve terrestrial locomotion. However, the electroadhesion force of actuators is limited to the materials, roughness of various terrain, and patterning high- and low- friction materials on the ventral side of the robot can only enable the robot to crawl along a single direction." Financial supporters for this research include National Natural Science Foundation of China (NSFC), Natural Science Foundation of Zhejiang Province, Fundamental Research Funds for the Central Universities. The news reporters obtained a quote from the research from Zhejiang University, "This paper presents a novel pneumatic foot that can regulate the friction between itself and the crawling surface to achieve frictional anisotropy in two opposite directions. The design scheme, working mechanism and analytical model based on the energy method of the pneumatic foot are described. The accuracy of the analytical model is verified by numerical simulation and experimental study. A soft crawling robot, including its locomotion mode and control system, is designed. Crawling experiments on various terrain and payload experiments are conducted to prove the feasibility of the pneumatic foot. The pneumatic foot can enable the robot to crawl on various terrain at a maximum speed of 0.128 BL/s. When the payloads are 4.29 times of the robot's weight, the crawling speed is still relatively high (0.108 BL/s)."
查看更多>>摘要：Investigators publish new report on Machine Learning. According to news originating from Perak, Malaysia, by NewsRx correspondents, research stated, "This study presents an innovative and compact monopole antenna with dual-band frequency reconfigurability for LoRa applications. It operates within the 915 MHz and 868 MHz frequencies, aligning with the designated bands for use in America, Asia and Europe." Financial support for this research came from Universiti Teknologi PETRONAS, Malaysia, YUTP-PRG (Yayasan Universiti Teknologi PETRONAS-Prototype Research Grant). Our news journalists obtained a quote from the research from the University of Technology, "No existing compact reconfigurable antenna with these features for LoRa applications within ISM bands below 1 GHz is known. Employing an economical FR-4 substrate in its design, the antenna attains a compact size of 40 x 42 mm(2) (0.12 lambda(0) x 0.12 lambda(0)), where lambda(0) denotes the wavelength in free space corresponding to 868 MHz. A single RF PIN diode enables seamless switching between 868 MHz and 915 MHz bands. simulation, and optimization employed CST MWS ® software. Supervised regression Machine Learning (ML) models predicted resonance frequencies, with Gaussian Process Regression emerging as optimal, achieving R-squared and variance scores of 92.87% and 93.77%, respectively. A maximum gain of 2 dBi at 915 MHz and 70% efficiency, boasting good radiation patterns and matching was demonstrated by the antenna. Experimental validation in a football field at Universiti Teknologi PETRONAS, Malaysia, assessed the proposed antenna's performance on a LoRa transceiver system based on LoRa SX1276. The Received Signal Strength Indicator (RSSI) of the proposed antenna consistently exceeded the conventional commercially available monopole antenna by an average of -12 dBm at every point up to 300 m, showcasing enhanced signal reception."
查看更多>>摘要：New research on Machine Learning is the subject of a report. According to news reporting originating from Dortmund, Germany, by NewsRx correspondents, research stated, "Ideally, health services and interventions to improve dental health should be tailored to local target populations. But this is not the standard." Our news editors obtained a quote from the research from Data Science Center, "Little is known about risk clusters in dental health care and their evaluation based on small-scale, spatial data, particularly among under-represented groups in health surveys. Our study aims to investigate the incidence rates of major oral diseases among privately insured and self-paying individuals in Germany, explore the spatial clustering of these diseases, and evaluate the influence of social determinants on oral disease risk clusters using advanced data analysis techniques, i.e. machine learning. A retrospective cohort study was performed to calculate the age- and sex-standardized incidence rate of oral diseases in a study population of privately insured and self-pay patients in Germany who received dental treatment between 2016 and 2021. This was based on anonymized claims data from BFS health finance, Bertelsmann, Dortmund, Germany. The disease history of individuals was recorded and aggregated at the ZIP code 5 level (n = 8871). Statistically significant, spatially compact clusters and relative risks (RR) of incidence rates were identified. By linking disease and socioeconomic databases on the ZIP-5 level, local risk models for each disease were estimated based on spatial-neighborhood variables using different machine learning models. We found that dental diseases were spatially clustered among privately insured and self-payer patients in Germany. Incidence rates within clusters were significantly elevated compared to incidence rates outside clusters. The relative risks (RR) for a new dental disease in primary risk clusters were min = 1.3 (irreversible pulpitis; 95%-CI = 1.3-1.3) and max = 2.7 (periodontitis; 95%-CI = 2.6-2.8), depending on the disease. Despite some similarity in the importance of variables from machine learning models across different clusters, each cluster is unique and must be treated as such when addressing oral public health threats. Our study analyzed the incidence of major oral diseases in Germany and employed spatial methods to identify and characterize high-risk clusters for targeted interventions. We found that private claims data, combined with a network-based, data-driven approach, can effectively pinpoint areas and factors relevant to oral healthcare, including socioeconomic determinants like income and occupational status."
查看更多>>摘要：Fresh data on robotics are presented in a new report. According to news reporting out of Madrid, Spain, by NewsRx editors, research stated, "This paper introduces a novel method that enables robots to identify objects based on user gaze, tracked via eye-tracking glasses." Financial supporters for this research include Companion-cm, Inteligencia Artificial Y Modelos Cogni- tivos Para La Interaccion Simetrica Humano-robot En El Ambito De La Robotica Asistencial; Proyectos Sinergicos De I+D La Comunidad De Madrid. Our news correspondents obtained a quote from the research from University of Carlos III: "This is achieved without prior knowledge of the objects' categories or their locations and without external markers. The method integrates a two-part system: a category-agnostic object shape and pose estimator using superquadrics and Siamese networks. The superquadrics-based component estimates the shapes and poses of all objects, while the Siamese network matches the object targeted by the user's gaze with the robot's viewpoint. Both components are effectively designed to function in scenarios with partial occlusions. A key feature of the system is the user's ability to move freely around the scenario, allowing dynamic object selection via gaze from any position. The system is capable of handling significant viewpoint differences between the user and the robot and adapts easily to new objects."
查看更多>>摘要：Investigators publish new report on Machine Learning. According to news originating from Tianjin, People's Republic of China, by NewsRx correspondents, research stated, "Narrow-gap laser welding is a novel joining process for thick-walled applications. However, it is challenging to obtain accurate root weld penetration as a crucial parameter for evaluating welding quality due to the limited spatial position." Funders for this research include National Natural Science Foundation of China (NSFC), Natural Science Foundation of Tianjin. Our news journalists obtained a quote from the research from Tianjin University, "The images of the front-side weld pool are one of the most effective signals for reflecting the root weld penetration. Hence, this paper proposes using a high dynamic range (HDR) camera to capture the weld pool morphology under narrow-gap laser welding. The characteristics of weld pool under different root weld penetration states are obtained and analyzed through orthogonal experiments. Furthermore, the root weld penetration states prediction model is constructed based on a backpropagation (BP) neural network."
NETL
NSTL
IEEE
Elsevier
Springer Nature
Mdpi