关键词： Left-sided colon cancer   Right-sided colon cancer   Machine learning   Mutations   Gene expression  

摘要： BackgroundIn recent years, the differences between left-sided colon cancer (LCC) and right-sided colon cancer (RCC) have received increasing attention due to the clinicopathological variation between them. However, some of these differences have remained unclear and conflicting results have been *** The Cancer Genome Atlas (TCGA), we obtained RNA sequencing data and gene mutation data on 323 and 283 colon cancer patients, respectively. Differential analysis was firstly done on gene expression data and mutation data between LCC and RCC, separately. Machine learning (ML) methods were then used to select key genes or mutations as features to construct models to classify LCC and RCC patients. Finally, we conducted correlation analysis to identify the correlations between differentially expressed genes (DEGs) and mutations using logistic regression (LR) *** found distinct gene mutation and expression patterns between LCC and RCC patients and further selected the 30 most important mutations and 17 most important gene expression features using ML methods. The classification models created using these features classified LCC and RCC patients with high accuracy (areas under the curve (AUC) of 0.8 and 0.96 for mutation and gene expression data, respectively). The expression of PRAC1 and BRAF V600E mutation (rs113488022) were the most important feature for each model. Correlations of mutations and gene expression data were also identified using LR models. Among them, rs113488022 was found to have significance relevance to the expression of four genes, and thus should be focused on in further *** the basis of ML methods, we found some key molecular differences between LCC and RCC, which could differentiate these two groups of patients with high accuracy. These differences might be key factors behind the variation in clinical features between LCC and RCC and thus help to improve treatment, such as determining the appropriate therapy

关键词： Machine learning   force fields   molecular dynamics   ab initiomolecular dynamics   instant modelling  

摘要： Ab initiomolecular dynamics (AIMD) has become a popular simulation technique but long simulation times are often hampered due to its high computational effort. Alternatively, classical molecular dynamics (MD) based on force fields may be used, which, however, has certain shortcomings compared to AIMD. In order to alleviate that situation, a trajectory-based machine learning (TrajML) approach is introduced for the construction of force fields by learning from AIMD trajectories. Only nuclear trajectories are required, which can be obtained by other methods beyond AIMD as well. We developed an easy-to-use MD machine learning package (TrajML MD) for instant modelling of the force field and system-focussed prediction of molecular configurations for MD trajectories. It consumes similar computational resources as classical MD but can simulate complex systems with a higher accuracy due to the targeted learning on the system of interest.

关键词： Machine learning   Association rule mining   Non-redundancy   Context-aware computing   Decision making   Personalization   Mobile data analytics   Rule-based system   Intelligent services  

摘要： This paper formulates the problem of a rule-based machine learning method to discover the behavioral rules of individual smartphone users to provide context-aware intelligent services. Smartphones nowadays are considered as one of the most important Internet-of-Things (IoT) devices for providing various context-aware personalized services. These devices can record individuals' contextual data - for example, temporal, spatial, or social contexts, and their daily behavioral activity records. Association rule mining (ARM) is the most popular rule-based machine learning method for discovering rules for a particular constraint preference utilizing a given dataset However, it generates numerous uninteresting contextual associations which lead to generate huge number of redundant rules that become useless in making context-aware decisions. This redundant generation makes not only the rule-set unnecessarily large but also makes the context-aware decision making process more complex and ineffective. To minimize these issues, in this paper, we propose a rule-based machine learning method "ABC-RuleMiner" that effectively identifies the redundancy in associations, and discovers a set of non-redundant behavioral rules (IF-THEN) for individual users by taking into account the precedence of relevant contexts. Our experiments on individuals' contextual smartphone datasets show that this rule discovery approach is more effective while comparing with traditional rule-based methods.

关键词： Activity recognition   Wearable sensors   Fabric sensors   Women safety   Decision tree   Classifier   SVM classifier  

摘要： Purpose The paper aims to develop a novel method for the classification of different physical activities of a human being, using fabric sensors. This method focuses mainly on classifying the physical activity between normal action and violent attack on a victim and verifies its validity. Design/methodology/approach The system is realized as a protective jacket that can be worn by the subject. Stretch sensors, pressure sensors and a 9 degree of freedom accelerometer are strategically woven on the jacket. The jacket has an internal bus system made of conductive fabric that connects the sensors to the Flora chip, which acts as the data acquisition unit for the data generated. Different activities such as still, standing up, walking, twist-jump-turn, dancing and violent action are performed. The jacket in this study is worn by a healthy subject. The main phases which describe the activity recognition method undertaken in this study are the placement of sensors, pre-processing of data and deploying machine learning models for classification. Findings The effectiveness of the method was validated in a controlled environment. Certain challenges are also faced in building the experimental setup for the collection of data from the hardware. The most tedious challenge is to collect the data without noise and error, created by voltage fluctuations when stretched. The results show that the support vector machine classifier can classify different activities and is able to differentiate normal action and violent attacks with an accuracy of 98.8%, which is superior to other methods and algorithms. Practical implications This study leads to an understanding of human physical movement under violent activity. The results show that data compared with normal physical motion, which includes even a form of dance is quite different from the data collected during violent physical motion. This jacket construction with woven sensors can capture every dimension of the physical motion adding f

关键词： Intensive care unit   Sepsis   Prediction model   Machine learning   In-hospital mortality  

摘要： Background Early and accurate identification of sepsis patients with high risk of in-hospital death can help physicians in intensive care units (ICUs) make optimal clinical decisions. This study aimed to develop machine learning-based tools to predict the risk of hospital death of patients with sepsis in ICUs. Methods The source database used for model development and validation is the medical information mart for intensive care (MIMIC) III. We identified adult sepsis patients using the new sepsis definition Sepsis-3. A total of 86 predictor variables consisting of demographics, laboratory tests and comorbidities were used. We employed the least absolute shrinkage and selection operator (LASSO), random forest (RF), gradient boosting machine (GBM) and the traditional logistic regression (LR) method to develop prediction models. In addition, the prediction performance of the four developed models was evaluated and compared with that of an existent scoring tool - simplified acute physiology score (SAPS) II - using five different performance measures: the area under the receiver operating characteristic curve (AUROC), Brier score, sensitivity, specificity and calibration plot. Results The records of 16,688 sepsis patients in MIMIC III were used for model training and test. Amongst them, 2949 (17.7%) patients had in-hospital death. The average AUROCs of the LASSO, RF, GBM, LR and SAPS II models were 0.829, 0.829, 0.845, 0.833 and 0.77, respectively. The Brier scores of the LASSO, RF, GBM, LR and SAPS II models were 0.108, 0.109, 0.104, 0.107 and 0.146, respectively. The calibration plots showed that the GBM, LASSO and LR models had good calibration;the RF model underestimated high-risk patients;and SAPS II had the poorest calibration. Conclusion The machine learning-based models developed in this study had good prediction performance. Amongst them, the GBM model showed the best performance in predicting the risk of in-hospital death. It has the potential to assist physic

关键词： 机器学习   流体机械   优化设计   流动计算   流动控制   深度学习  

摘要： 随着机器学习方法的不断发展,形成了各类算法,已有学者将其应用于流体机械的流动计算、流动控制以及优化设计。以深度学习为代表的机器学习方法具有强大的归纳学习能力,能够自主进行特征学习,不仅可以直接利用实验和数值模拟数据,从中挖掘出潜在的流场信息,更可以在优化设计过程中实现自适应的设计参数探索,以实现快速、鲁棒、全局且高效的优化,因此可以作为一种全新的流体机械优化设计方法。本文概述了流体机械气动优化的现状、机器学习方法的研究现状、机器学习在流动计算、流动控制以及流体机械优化设计中的应用现状,并指出了深度学习在流体机械优化设计上的应用前景。

关键词： 二维材料   第一性原理   机器学习   带隙  

摘要： 利用密度泛函理论与机器学习相结合的方法,对二维金属化合物的带隙进行研究,得到比传统理论计算成本更低且更有效的带隙预测方法.以广义梯度近似(general gradient approximation,GGA)-Perdew-Burke-Ernzerhof(PBE)(GGA-PBE)和G0W0的带隙计算结果为参考,考察了化学通式为MX2的二维材料数据集.利用套索回归,即最小绝对值收敛和选择算子(least absolute shrinkage and selection operator,LASSO)、支持向量回归(support vector regression,SVR)和梯度树提升回归(gradient boosting regression,GBR)等机器学习方法建立带隙的预测模型.测试结果表明,对于大多数二维材料,基于线性核函数的SVR与LASSO模型的预测性能相对较好,训练模型的平均绝对误差为0.34 eV,测试集误差为0.5 eV.这说明对于二维材料带隙采取的特征参数集具有一定的完备性和合理性,对新材料带隙的初步预测有一定的参考价值.

关键词： methods: data analysis   Sun: coronal mass ejections (CMEs)   Techniques: image processing  

摘要： The detection of Coronal Mass Ejections (CMEs) is an important prerequisite for establishing a CME event database and realizing the prediction of CME interplanetary propagation. The Lyman-alpha Solar Telescope (LST) aboard the ASO-S (Advanced Space-based Solar Observatory) satellite will be equipped with a white-light coronagraph. The images with CME detected will be contributed to various space weather prediction centers in China for CME early warning. The Visual Geometry Group (VGG) 16 convolutional neural network method is applied by us to automatically and effectively classify coronagraph images. Firstly, based on the image of the white light coronagraph of Large Angle and Spectrometric Coronagraph Experiment (LASCO) C2, we labeled the images according to whether a CME is observed. Then, the data set was used for training the VGG model. We find that the accuracy of the model in the test set classification reaches 92.5%. Next, according to the obtained classification results and combined with the space-time continuity rules, we corrected the mislabeling of images, and derived our final CME image sequences. Compared with the manual CME catalog of Coordinated Data Analysis Workshops (CDAW), the classified CME image sequences can include CME data more completely, and have higher detection sensitivity for weak CME structures. © 2020

关键词： X射线相衬显微CT   肝癌   特征提取   机器学习  

摘要： 肝癌是我国恶性肿瘤发病率和死亡率较高的癌症之一,传统医学影像设备因成像机制导致成像分辨率不足,对肝癌的检查和诊断具有较大的影响。基于同步辐射的X射线相衬显微CT成像具有极高的灵敏度和分辨率,结合机器学习方法建立肝癌分类模型,为肝癌辅助诊断提供参考。收集弥漫型和溃疡型肝肿瘤X射线相衬图像各500幅,归一化和中值滤波后提取灰度直方图、灰度共生矩阵、灰度-梯度共生矩阵和灰度差分统计等灰度及纹理特征,并组合成融合特征,采用十折交叉验证法进行机器学习方法的训练和分类。使用支持向量机、随机森林和神经网络等3种分类算法对肝癌图像进行分类,灰度共生矩阵特征和神经网络分类算法下分类准确率最高,达到99.5%,取得较好的分类效果,有望帮助医生准确完成肝肿瘤类型的鉴别。