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

    Department of ICU Reports Findings in Machine Learning (Suboptimal capability of individual machine learning algorithms in modeling small-scale imbalanced clini cal data of local hospital)

    64-65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 Shaanxi, People's Repub lic of China, by NewsRx correspondents, research stated, "In recent years, artif icial intelligence (AI) has shown promising applications in various scientific d omains, including biochemical analysis research. However, the effectiveness of A I in modeling small-scale, imbalanced datasets remains an open question in such fields." Our news editors obtained a quote from the research from the Department of ICU, "This study explores the capabilities of eight basic AI algorithms, including ri dge regression, logistic regression, random forest regression, and others, in mo deling a small, imbalanced clinical dataset (total n = 387, class 0 = 27, class 1 = 360) related to the records of the biochemical blood tests from the patients with multiple wasp stings (MWS). Through rigorous evaluation using k-fold cross -validation and comprehensive scoring, we found that none of the models could ef fectively model the data. Even after fine-tuning the hyperparameters of the best -performing models, the results remained below acceptable thresholds. The study highlights the challenges of applying AI to small-scale datasets with imbalanced groups in biochemical or clinical research and emphasizes the need for novel al gorithms tailored to small-scale data."
      原文链接:
    • NETL
    • NSTL

    New Findings from Indian Institute for Technology in the Area of Robotics Report ed (Physically Plausible 3d Human-scene Reconstruction From Monocular Rgb Image Using an Adversarial Learning Approach)

    65-66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 report. According to news reporting from Maharashtra, India, by NewsRx jo urnalists, research stated, "Holistic 3D human-scene reconstruction is a crucial and emerging research area in robot perception. A key challenge in holistic 3D human-scene reconstruction is to generate a physically plausible 3D scene from a single monocular RGB image." Financial supporters for this research include Australian Research Council, US A ir Force Research Laboratory, Defense Advanced Research Projects Agency (DARPA). The news correspondents obtained a quote from the research from Indian Institute for Technology, "The existing research mainly proposes optimization-based appro aches for reconstructing the scene from a sequence of RGB frames with explicitly defined physical laws and constraints between different scene elements (humans and objects). However, it is hard to explicitly define and model every physical law in every scenario. This letter proposes using an implicit feature representa tion of the scene elements to distinguish a physically plausible alignment of hu mans and objects from an implausible one. We propose using a graph-based holisti c representation with an encoded physical representation of the scene to analyze the human-object and object-object interactions within the scene. Using this gr aphical representation, we adversarially train our model to learn the feasible a lignments of the scene elements from the training data itself without explicitly defining the laws and constraints between them. Unlike the existing inferencet ime optimization-based approaches, we use this adversarially trained model to pr oduce a per-frame 3D reconstruction of the scene that abides by the physical law s and constraints. Our learning-based method achieves comparable 3D reconstructi on quality to existing optimization-based holistic humanscene reconstruction me thods and does not need inference time optimization."
      原文链接:
    • NETL
    • NSTL

    Bengbu Medical University Reports Findings in Diabetic Nephropathy (Integrated m achine learning and deep learning for predicting diabetic nephropathy model cons truction, validation, and interpretability)

    66-67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 Kidney Diseases and Co nditions - Diabetic Nephropathy is the subject of a report. According to news re porting from Bengbu, People's Republic of China, by NewsRx journalists, research stated, "To construct a risk prediction model for assisted diagnosis of Diabeti c Nephropathy (DN) using machine learning algorithms, and to validate it interna lly and externally. Firstly, the data was cleaned and enhanced, and was divided into training and test sets according to the 7:3 ratio." The news correspondents obtained a quote from the research from Bengbu Medical U niversity, "Then, the metrics related to DN were filtered by difference analysis , Least Absolute Shrinkage and Selection Operator (LASSO), Recursive Feature Eli mination (RFE), and Max-relevance and Min-redundancy (MRMR) algorithms. Ten mach ine learning models were constructed based on the key variables. The best model was filtered by Receiver Operating Characteristic (ROC), Precision-Recall (PR), Accuracy, Matthews Correlation Coefficient (MCC), and Kappa, and was internally and externally validated. Based on the best model, an online platform had been c onstructed. 15 key variables were selected, and among the 10 machine learning mo dels, the Random Forest model achieved the best predictive performance. In the t est set, the area under the ROC curve was 0.912, and in two external validation cohorts, the area under the ROC curve was 0.828 and 0.863, indicating excellent predictive and generalization abilities."
      原文链接:
    • NETL
    • NSTL

    Data on Artificial Intelligence Reported by Vaitheeswaran Kulothungan and Collea gues (Topic modeling and social network analysis approach to explore diabetes di scourse on Twitter in India)

    67-68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 Machine Learning - Art ificial Intelligence is the subject of a report. According to news reporting ori ginating from Bengaluru, India, by NewsRx correspondents, research stated, "The utilization of social media presents a promising avenue for the prevention and m anagement of diabetes. To effectively cater to the diabetes-related knowledge, s upport, and intervention needs of the community, it is imperative to attain a de eper understanding of the extent and content of discussions pertaining to this h ealth issue." Our news editors obtained a quote from the research, "This study aims to assess and compare various topic modeling techniques to determine the most effective mo del for identifying the core themes in diabetes-related tweets, the sources resp onsible for disseminating this information, the reach of these themes, and the i nfluential individuals within the Twitter community in India. Twitter messages f rom India, dated between 7 November 2022 and 28 February 2023, were collected us ing the Twitter API. The unsupervised machine learning topic models, namely, Lat ent Dirichlet Allocation (LDA), non-negative matrix factorization (NMF), BERTopi c, and Top2Vec, were compared, and the best-performing model was used to identif y common diabetes-related topics. Influential users were identified through soci al network analysis. The NMF model outperformed the LDA model, whereas BERTopic performed better than Top2Vec. Diabetes-related conversations revolved around ei ght topics, namely, promotion, management, drug and personal story, consequences , risk factors and research, raising awareness and providing support, diet, and opinion and lifestyle changes. The influential nodes identified were mainly heal th professionals and healthcare organizations. The study identified important to pics of discussion along with health professionals and healthcare organizations involved in sharing diabetes-related information with the public."
      原文链接:
    • NETL
    • NSTL

    Findings from Vellore Institute of Technology in the Area of Machine Learning Re ported (Dynamic Machine Learning-based Heuristic Energy Optimization Approach On Multicore Architecture)

    68-69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 Machine Learn ing have been published. According to news reporting from Tamil Nadu, India, by NewsRx journalists, research stated, "In the present era, energy is progressivel y turning into the major limitation in designing multicore chips. However, power and performance are the primary segments of energy, which are contrarily correl ated in multicore architectures." The news correspondents obtained a quote from the research from the Vellore Inst itute of Technology, "This research primarily focused on optimizing energy level of multicore chips using parallel workloads by utilizing either power or execut ion advancement based on machine learning computation on dynamic programming. To do as such, the novel dynamic machine learning-based heuristic energy optimizat ion (DML-HEO) algorithm has been designed and developed in this research on appl ication-specific controllers to optimize energy-level on multicore architecture. Here DML-HEO is implemented on the controller to maximize the execution inside a fixed power spending plan or to limit the expended capacity to accomplish a si milar pattern execution. The controller is additionally scalable as it does not bring about critical overhead due to the increase in quantity of cores. The stra tegy has been assessed utilizing controllers on a full-framework test system at lab-scale analysis."
      原文链接:
    • NETL
    • NSTL

    Data on Machine Learning Described by Researchers at Madhav Institute of Science & Technology (Machine Learning Model for Healthcare Investments P redicting the Length of Stay In a Hospital & Mortality Rate)

    69-70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 Machine Learn ing have been published. According to news originating from Madhya Pradesh, Indi a, by NewsRx correspondents, research stated, "The demand for healthcare workers and infrastructure from an alarmingly growing patient population may contribute to the increased Length of Stay (LOS) in Hospital and Mortality rate. The short age of doctors, nurses, and hospital beds may be blamed for this increase." Our news journalists obtained a quote from the research from the Madhav Institut e of Science & Technology, "As Constant patient monitoring is esse ntial and the better hospital management and administration are necessary, there fore this research aimed foremost, to develop a machine learning model to predic t long-term outcomes like Length of Stay (LOS), mortality rate of a patient admi tted into the hospital. We used Machine Learning (ML) in the National Hospital C are Research Database (NHCRD) to create minimum feature-based predictive modelin g with adequate performance. Unlike other approaches, ours requires the patient' s profile, tests reports at the time of admission and treatment history to accur ately predict outcomes like the length of stay and mortality rate, making our te chnique novel with 98% accuracy, 98% precision, 95% AUROC Score, 94% F1 Score, 0.97 Recall, 0.95 Train Accuracy, and 0 .90 Test Accuracy with the Support Vector Machine Algorithm. The ratio of traini ng data to testing data was divided in the ratio 8:2 then the Machine Learning m ethods were applied. Descriptive statistical graphs, feature significance, preci sion-recall curve, accuracy plots, and Area Under the Curve (AUC), Accuracy, Pre cision, Recall, F1-Score, Mean Squared Error, Mean Absolute Error and Root Mean Squared Error were used to evaluate different machine learning methods like Rand om Forests (RF), Logistic Regression (LR), Gradient Boosting (GB), Decision Tree (DT), Naive Bayes (NB), Artificial Neural Network (ANN), and Ensemble Learning Techniques (EL), etc. Adopting the proposed framework, which considers the imbal anced dataset for classification-based methods based on electronic healthcare re cords, may allow us to apply Machine Learning to forecast patient length of stay and mortality rate in the hospital's clinical information system."
      原文链接:
    • NETL
    • NSTL

    New Findings on Machine Learning from Sichuan University Summarized (Decoding Pf as Contamination Via Raman Spectroscopy: a Combined Dft and Machine Learning Inv estigation)

    70-71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 Machine Learning have been presented. According to news reporting out of Chengdu, People's Republic o f China, by NewsRx editors, research stated, "In this study, density function th eory (DFT) is employed to compute Raman spectra of 40 important Per-fluoroalkyl substances (PFASs) as listed in Draft Method 1633 by U.S. Environmental Protecti on Agent. A systematic comparison of their spectral features is conducted, and R aman peaks and vibrational modes are identified." Funders for this research include National Natural Science Foundation of China ( NSFC), United States Department of Agriculture (USDA). Our news journalists obtained a quote from the research from Sichuan University, "The Raman spectral regions for the main chemical bonds (such as C-C, CF2 & CF3, O-H) and main functional groups (such as-COOH,-SO3H,-C2H4SO3H, and -SO2NH2) are identified and compared. The impacts of branching location in isomer, molec ular chain length, and functional groups on the Raman spectra are analyzed. Part icularly, the isomers of PFOA alter the peak locations slightly in wavenumber re gions of 200 - 800 and 1000 - 1400 cm-1, while for PFOS, spectral features in th e 230 - 360, 470 - 680, and 1030 - 1290 cm-1 regions exhibit significant differe nce. The carbon chain length can significantly increase the number of Raman peak s, while different functional groups give significantly different peak locations . To facilitate differentiation, a spectral database is constructed by introduci ng controlled noise into the DFT-computed Raman spectra. Subsequently, two chemo metric techniques, principal component analysis (PCA) and t-distributed stochast ic neighbor embedding (t-SNE), are applied to effectively distinguish among thes e spectra, both for 40 PFAS compounds and the isomers."
      原文链接:
    • NETL
    • NSTL

    Data on Machine Learning Reported by Andrea Valsecchi and Colleagues (Informatio n fusion for infant age estimation from deciduous teeth using machine learning)

    71-72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 Machine Learning is th e subject of a report. According to news reporting originating from Ponferrada, Spain, by NewsRx correspondents, research stated, "Over the past few years, seve ral methods have been proposed to improve the accuracy of age estimation in infa nts with a focus on dental development as a reliable marker. However, traditiona l approaches have limitations in efficiently combining information from differen t teeth and features." Financial support for this research came from Universidad de Granada. Our news editors obtained a quote from the research, "In order to address these challenges, this article presents a study on age estimation in infants with Mach ine Learning (ML) techniques, using deciduous teeth. The involved dataset compri ses 114 infant skeletons from the Granada osteological collection of identified infants, aged between 5 months of gestation and 3 years of age. The samples cons ist of features such as the maximum length and mineralization and alveolar stage s of teeth. For the purpose of designing a method capable of combining all the i nformation available from each individual, a Multilayer Perceptron model is prop osed, one of the most popular artificial neural networks. This model has been va lidated using the leave-one-out experimental validation protocol. Through differ ent groups of experiments, the study examines the informativeness of the aforeme ntioned features, individually and in combination. The results indicate that the fusion of different variables allows for more accurate age estimates (RMSE = 66 days) than when variables are analyzed separately (RMSE = 101 days). Additional ly, the study demonstrates the benefits of involving multiple teeth, which signi ficantly reduces the RMSE compared to a single tooth." According to the news editors, the research concluded: "This article underlines the clear advantages of ML-based methods, emphasizing their potential to improve the accuracy and robustness when estimating the age of infants."
      原文链接:
    • NETL
    • NSTL

    New Machine Learning Study Findings Have Been Reported by Researchers at Univers ity of Milan (On the Robustness of Random Forest Against Untargeted Data Poisoni ng: an Ensemble-based Approach)

    72-73页
    查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Research findings on Machine Learning are discussed in a new report. According to news reporting from Milan, Italy, by NewsRx journalists, research stated, "Machine learning is becoming ubiquitous. From finance to medicine, machine learning models are boosting decision-making p rocesses and even outperforming humans in some tasks." Financial support for this research came from Technology Innovation Institute. The news correspondents obtained a quote from the research from the University o f Milan, "This huge progress in terms of prediction quality does not however fin d a counterpart in the security of such models and corresponding predictions, wh ere perturbations of fractions of the training set (poisoning) can seriously und ermine the model accuracy. Research on poisoning attacks and defenses received i ncreasing attention in the last decade, leading to several promising solutions a iming to increase the robustness of machine learning. Among them, ensemble-based defenses, where different models are trained on portions of the training set an d their predictions are then aggregated, provide strong theoretical guarantees a t the price of a linear overhead. Surprisingly, ensemble-based defenses, which d o not pose any restrictions on the base model, have not been applied to increase the robustness of random forest. The work in this paper aims to fill in this ga p by designing and implementing a novel hash-based ensemble approach that protec ts random forest against untargeted, random poisoning attacks. An extensive expe rimental evaluation measures the performance of our approach against a variety o f attacks, as well as its sustainability in terms of resource consumption and pe rformance, and compares it with a traditional monolithic model based on random f orest."
      原文链接:
    • NETL
    • NSTL

    Findings from University of Zagreb Provide New Insights into Robotics (Control o f Robot Motion in Radial Mass Density Field)

    73-73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 originating from the University of Zagreb by N ewsRx correspondents, research stated, "T In this article, a new approach to con trol of robot motion in the radial mass density field is presented." Our news editors obtained a quote from the research from University of Zagreb: " This field is between the maximal and the minimal radial mass density values. Be tween these two limited values, one can use n points (n = 1, 2,. . . nmax) that can be included in the related algorithm for control of the robot motion. The nu mber of the points nstep can be calculated by using the relation nstep = nmax / nvar , where nvar is the control parameter. The radial mass density is maximal a t the minimal gravitational radius and minimal at the maximal gravitational radi us." According to the news editors, the research concluded: "This is valid for Planck scale and for the scales that are less or higher of that one. Using the ratio o f Planck mass and Planck radius it is generated the energy conservation constant k = 0.99993392118."
      原文链接:
    • NETL
    • NSTL