关键词： 质谱   蛋白质组学   生物标志物   机器学习   特征选择   深度学习  

摘要： 随着质谱技术的进步以及生物信息学与统计学算法的发展,以疾病研究为主要目的之一的人类蛋白质组计划正快速推进。蛋白质生物标志物在疾病早期诊断和临床治疗等方面有着非常重要的意义,其发现策略和方法的研究已成为一个重要的热点领域。特征选择与机器学习对于解决蛋白质组数据'高维度'及'稀疏性'问题有较好的效果,因而逐渐被广泛地应用于发现蛋白质生物标志物的研究中。文中主要阐述蛋白质生物标志物的发现策略以及其中特征选择与机器学习方法的原理、应用实例和适用范围,并讨论深度学习方法在本领域的应用前景及局限性,以期为相关研究提供参考。

关键词： 森林火灾   受灾面积   机器学习   支持向量机模型  

摘要： 森林火灾在对人类生存与生活带来极大危害的同时还对生态环境造成难以挽回的破坏,而快速检测正是预测森林火灾的一个有效途径。利用来自葡萄牙东北部的Montesinho国家公园采集测试的真实数据,使用支持向量机对于森林火灾进行预测。研究结果能够准确预测规模较小且发生频繁的火灾的受灾面积。

关键词： 分类方法   协作优化   计算机科学家   材料科学家   钢材   机器学习技术   质量控制程序   机器学习方法  

摘要： 利用机器学习技术,德国萨尔大学的计算机科学家和材料科学家开发出一种分类方法,据报道,该方法比传统的质量控制程序更加准确和客观。首先,材料研究人员需要帮助计算机科学家了解材料的内部结构是如何与其性能相关的。同样,计算机科学家向材料研究人员展示了机器学习方法如何能够比材料科学家手动进行的任何图像分析产生更准确的结果。

关键词： 机器学习方法   室内定位   室内导航   贝叶斯方法  

摘要： 移动节点的准确定位对于无人机的环境感知、路径规划及控制系统的开发至关重要。对决策树、SVM和贝叶斯等三种机器学习方法在使用锚节点的室内空间进行定位准确率对比研究,最终选择了具有高泛化准确率的贝叶斯方法作为定位方法。结合改进后的A*算法在室内空间对无人机进行自动路径规划,并借助激光传感器感知环境中未知障碍,不断更新室内地图并指导无人机进行避障,无人机导航实验验证了机器学习方法用于室内空间定位的可行性。

关键词： Association (Psychology)   Machine Learning   Toxicity  

关键词： 地震预测   前驱波   异常波   直观预测  

摘要： 本文所研究的是一种基于超低频的振动测量传感器系统,专门捕捉地震前驱波的记录装置。将此装置布设在陕西子午、甘肃兰州、四川成都、河南洛阳四个站点,选取了近一年的连续数据记录,对所记录的海量信号数据进行分析,单纯利用出现异常信号与地震发生之间的对应关系得到预测地震的准确率。

关键词： Phase field model   Quasi phase equilibrium   Multicomponent   Machine learning  

摘要： The phase field model for multicomponent alloys are usually coupled with the thermodynamic database. But it will take much time to solve the quasi phase equilibrium equations. In order to reduce such time and keep the enough accuracy, we develop a new model to predict the quasi phase equilibrium based on the machine learning method. As an example, the quasi phase equilibrium during the isothermal solidification of Al-Cu-Mg alloy is studied in detail. A neural network model with 3 inputs, 4 outputs and a hidden layer of 150 nodes is constructed. The "training data" are prepared by solving the quasi phase equilibrium equations with least square method. The neural network model is trained by different amount of data set, which can fully cover the ranges of all the variables. The accuracy and performance of the neural network model are discussed in detail. Its high accuracy and fast speed demonstrated that this will be a convenient method to acquire the quasi phase equilibrium data in phase field model for multicomponent alloys.

关键词： Single channel   EEG   machine learning   major depressive disorder   MDD prescreening  

摘要： Many studies developed the machine learning method for discriminating Major Depressive Disorder (MDD) and normal control based on multi-channel electroencephalogram (EEG) data, less concerned about using single channel EEG collected from forehead scalp to discriminate the MDD. The EEG dataset is collected by the Fp1 and Fp2 electrode of a 32-channel EEG system. The result demonstrates that the classification performance based on the EEG of Fp1 location exceeds the performance based on the EEG of Fp2 location, and shows that single-channel EEG analysis can provide discrimination of MDD at the level of multi-channel EEG analysis. Furthermore, a portable EEG device collecting the signal from Fp1 location is used to collect the second dataset. The Classification and Regression Tree combining genetic algorithm (GA) achieves the highest accuracy of 86.67% based on leave-one-participant-out cross validation, which shows that the single-channel EEG-based machine learning method is promising to support MDD prescreening application.

关键词： machine learning   rare disease diagnosis   phenotype score   variant prioritization   ACMG/AMP guideline  

摘要： Purpose: Despite the successful progress next-generation sequencing technologies has achieved in diagnosing the genetic cause of rare Mendelian diseases, the current diagnostic rate is still far from satisfactory because of heterogeneity, imprecision, and noise in disease phenotype descriptions and insufficient utilization of expert knowledge in clinical genetics. To overcome these difficulties, we present a novel method called Xrare for the prioritization of causative gene variants in rare disease diagnosis. Methods: We propose a new phenotype similarity scoring method called Emission-Reception Information Content (ERIC), which is highly tolerant of noise and imprecision in clinical phenotypes. We utilize medical genetic domain knowledge by designing genetic features implementing American College of Medical Genetics and Genomics (ACMG) guidelines. Results: ERIC score ranked consistently higher for disease genes than other phenotypic similarity scores in the presence of imprecise and noisy phenotypes. Extensive simulations and real clinical data demonstrated that Xrare outperforms existing alternative methods by 10-40% at various genetic diagnosis scenarios. Conclusion: The Xrare model is learned from a large database of clinical variants, and derives its strength from the tight integration of medical genetics features and phenotypic features similarity scores. Xrare provides the clinical community with a robust and powerful tool for variant prioritization.