Radiomics extracts and mines large number of medical imaging features quantifying tumor phenotypic characteristics. Highly accurate and reliable machine-learning approaches can drive the success of radiomic applications in clinical care. In this radiomic study, fourteen feature selection methods and twelve classification methods were examined in terms of their performance and stability for predicting overall survival. A total of 440 radiomic features were extracted from pre-treatment computed tomography (CT) images of 464 lung cancer patients. To ensure the unbiased evaluation of different machine-learning methods, publicly available implementations along with reported parameter configurations were used. Furthermore, we used two independent radiomic cohorts for training (n = 310 patients) and validation (n = 154 patients). We identified that Wilcoxon test based feature selection method WLCX (stability = 0.84 ± 0.05, AUC = 0.65 ± 0.02) and a classification method random forest RF (RSD = 3.52%, AUC = 0.66 ± 0.03) had highest prognostic performance with high stability against data perturbation. Our variability analysis indicated that the choice of classification method is the most dominant source of performance variation (34.21% of total variance). Identification of optimal machine-learning methods for radiomic applications is a crucial step towards stable and clinically relevant radiomic biomarkers, providing a non-invasive way of quantifying and monitoring tumor-phenotypic characteristics in clinical practice.
Matthias Rupp, Matthias Rupp, Alexandre Tkatchenko
et al.
We introduce a machine learning model to predict atomization energies of a diverse set of organic molecules, based on nuclear charges and atomic positions only. The problem of solving the molecular Schrödinger equation is mapped onto a nonlinear statistical regression problem of reduced complexity. Regression models are trained on and compared to atomization energies computed with hybrid density-functional theory. Cross validation over more than seven thousand organic molecules yields a mean absolute error of ∼10 kcal/mol. Applicability is demonstrated for the prediction of molecular atomization potential energy curves.
Ioannis Tsochantaridis, Thomas Hofmann, T. Joachims
et al.
Learning general functional dependencies is one of the main goals in machine learning. Recent progress in kernel-based methods has focused on designing flexible and powerful input representations. This paper addresses the complementary issue of problems involving complex outputs such as multiple dependent output variables and structured output spaces. We propose to generalize multiclass Support Vector Machine learning in a formulation that involves features extracted jointly from inputs and outputs. The resulting optimization problem is solved efficiently by a cutting plane algorithm that exploits the sparseness and structural decomposition of the problem. We demonstrate the versatility and effectiveness of our method on problems ranging from supervised grammar learning and named-entity recognition, to taxonomic text classification and sequence alignment.
Abstract Risk prediction plays an important role in clinical cardiology research. Traditionally, most risk models have been based on regression models. While useful and robust, these statistical methods are limited to using a small number of predictors which operate in the same way on everyone, and uniformly throughout their range. The purpose of this review is to illustrate the use of machine-learning methods for development of risk prediction models. Typically presented as black box approaches, most machine-learning methods are aimed at solving particular challenges that arise in data analysis that are not well addressed by typical regression approaches. To illustrate these challenges, as well as how different methods can address them, we consider trying to predicting mortality after diagnosis of acute myocardial infarction. We use data derived from our institution's electronic health record and abstract data on 13 regularly measured laboratory markers. We walk through different challenges that arise in modelling these data and then introduce different machine-learning approaches. Finally, we discuss general issues in the application of machine-learning methods including tuning parameters, loss functions, variable importance, and missing data. Overall, this review serves as an introduction for those working on risk modelling to approach the diffuse field of machine learning.
The emerging field of quantum machine learning has the potential to substantially aid in the problems and scope of artificial intelligence. This is only enhanced by recent successes in the field of classical machine learning. In this work we propose an approach for the systematic treatment of machine learning, from the perspective of quantum information. Our approach is general and covers all three main branches of machine learning: supervised, unsupervised, and reinforcement learning. While quantum improvements in supervised and unsupervised learning have been reported, reinforcement learning has received much less attention. Within our approach, we tackle the problem of quantum enhancements in reinforcement learning as well, and propose a systematic scheme for providing improvements. As an example, we show that quadratic improvements in learning efficiency, and exponential improvements in performance over limited time periods, can be obtained for a broad class of learning problems.
In bioinformatics, the classification of gene-disease associations is crucial. It directly affects whether we can untangle the genetic roots of various disease as well as if we will find some justifiable therapy for these cured diseases.Using XBNet to construct genetic algorithms for higher accuracy and speeds of gene-disease classification--this is the method developed in the book.Consisting of gene expression profiles for six diseases--Alzheimer's, Asthma, Cancer, Diabetes, Fabry and Down syndrome--our research has applied a comprehensive pre-processing technique to this data set from Kaggle. This has included such things as eliminating stop-words and punctuation marks and tokenization. Using the terms of Frequency (TF) and of Term Frequency-Inverse Document Frequency (TF-IDF method) for features extraction, our text data on genes are transformed into numerical axes fit for input to machine learning models.
Abstract The volatility of renewable energy generation impacts the safe and stable operation of power systems. Moreover, load uncertainty complicates renewable energy consumption. Therefore, accurately extracting load patterns using artificial intelligence (AI) technology is crucial. Load classification is an effective way to master load behaviour. However, issues in the collected load data, such as data class imbalance, significantly affect the accuracy of traditional load classification. To address this problem, this study proposes a novel classification method based on data augmentation and few‐shot learning, significantly enhancing the training efficiency of algorithm recognition. This addresses the challenge of real‐data recognition in power systems. First, time‐series load data are converted into images based on the Gramian angular field method to extract time‐series data features using a convolutional neural network. Subsequently, the data are augmented based on variational autoencoder generative adversarial network to generate samples with distributions similar to those of the original data. Finally, the augmented few‐shot data are classified using the embedding and relation modules of the relation network. A comparison of the experimental results reveals that the proposed method effectively improves power load classification accuracy, even with insufficient data.
Crafts are products with both functional and aesthetic properties. Through emotional design, we can enhance not only the functionality of craft products but also their aesthetic appeal. This study focuses on ceramic teapots as a case study, selecting 20 samples from top-selling Chinese and Japanese ceramic teapots on JD.com. Employing machine learning methods, this study explores the relationship between the design features of ceramic teapots and the emotional preferences of young consumers. A classification model was developed, and new teapots were designed for validation. The main findings are as follows: 1) The shape of the teapot lid, spout, handle, and body, as well as the color, decoration, and usability of the teapot, significantly influence young people’s emotional preferences. 2) Model evaluation revealed that the accuracies of the binary and ternary classification models established through random forest reached 91.0% and 81.3%, respectively. 3) The proportion of newly designed teapots that aligned with young people’s emotional preferences reached 91.1% (binary classification) and 64.5% (ternary classification), which are higher than those for the original 20 teapots. In conclusion, this study demonstrates that the relationship between the perceived image and design features of top-selling Chinese and Japanese ceramic teapots can effectively guide the design of ceramic teapot forms and successfully convey the intended image. The established model can be used to evaluate the emotional quality of newly designed teapots, providing data-driven support for designers to create ceramic teapots that resonate with market preferences.
With the explosion of information, the amount of text data has increased significantly, making text categorization a central area of research in natural language processing (NLP). Traditional machine learning methods are effective, but deep learning models excel in processing semantic information. Models such as CNN, RNN, LSTM, and GRU have emerged as powerful tools for text classification. Pre-trained models such as BERT and GPT have further advanced text categorization techniques. Contrastive learning has become a key research focus aimed at improving classification performance by learning the similarities and differences between samples using models. However, existing contrastive learning methods have notable shortcomings, primarily concerning insufficient data utilization. This study focuses on data enhancement techniques to expand the text data through symbol insertion, affirmative auxiliary verbs, double negation, and punctuation repetition, aiming to improve the generalization and robustness of the pre-trained model. Two data enhancement strategies, affirmative enhancement and negative transformation, are introduced to deepen the data’s meaning and increase the volume of training data. To address the introduction of false data, an instance weighting method is employed to penalize false negative samples, while complementary models generate sample weights to mitigate the impact of sampling bias. Finally, the effectiveness of the proposed method is demonstrated through several experiments.
Muhammad Afaq Hussain, Zhanlong Chen, Biswajeet Pradhan
et al.
Study region: The National Highways 85 and 50, key routes of the China–Pakistan Economic Corridor (CPEC) in Balochistan, Pakistan. Study focus: Flooding is a natural disaster that is becoming increasingly frequent and severe. The National Highways 85 and 50 are vulnerable, necessitating accurate flood susceptibility mapping (FSM). Current machine learning (ML) models for FSM often suffer from low efficiency and overfitting. This study introduces an innovative hybrid FSM approach using four heterogeneous ensemble learning (HEL) techniques combined with three ML models: Random Forest (RF), Support Vector Machine (SVM), and Light Gradient Boosting Machine (LGBM). The proposed method was tested using satellite data from Sentinel-1, Sentinel-2, and Landsat-8, analyzing 1371 flood locations and 12 contributing variables. RF, variable importance factors (VIF), and information gain ratio (IGR) were applied to assess multicollinearity. The dataset was split (70:30) for model training and testing, with HEL-based models achieving superior performance over single ML models. New hydrological insights for the region: The stacking model yielded the highest AUROC (0.98), Kappa (0.82), accuracy (0.927), precision (0.963), Matthew’s correlation coefficient (0.820), and F1-score (0.950). HEL-based models proved more stable and resistant to overfitting. IGR analysis identified slope and distance from streams as key factors in FSM. The resulting flood-prone maps provide insights for disaster management adaptation strategies, demonstrating the broader applicability of the developed approach to enhance FSM accuracy and reliability.