This article adopts three artificial intelligence techniques, Gaussian Process Regression（GPR）, Least Square Support Vector Machine（LSSVM） and Extreme Learning Machine（ELM）, for prediction of rock depth（d） at ...This article adopts three artificial intelligence techniques, Gaussian Process Regression（GPR）, Least Square Support Vector Machine（LSSVM） and Extreme Learning Machine（ELM）, for prediction of rock depth（d） at any point in Chennai. GPR, ELM and LSSVM have been used as regression techniques.Latitude and longitude are also adopted as inputs of the GPR, ELM and LSSVM models. The performance of the ELM, GPR and LSSVM models has been compared. The developed ELM, GPR and LSSVM models produce spatial variability of rock depth and offer robust models for the prediction of rock depth.展开更多
Aimed at uncertainties and model's impreciseness, nonlinearity and time-variability of depth control system in autonomous underwater vehicle (AUV), a depth predictive control method was put forward based on rough ...Aimed at uncertainties and model's impreciseness, nonlinearity and time-variability of depth control system in autonomous underwater vehicle (AUV), a depth predictive control method was put forward based on rough set (RS) and least squares support vector machine (LSSVM). By using RS theory, the monitor data attribute of AUV was reduced to eliminate the redundant information and to improve efficiency. Then, LSSVM model was trained by using the reduced rules, and its parameters were optimized by using chaos theory for the higher accurate control. Taken an AUV typed NPS Phoenix as an example, its depth step response, horizontal rudder and pitch change were simulated. The simulation results show that the method improves the model's accuracy and has better real-time response, fault-tolerant ability, reliability and strong anti-interfere capability.展开更多
针对正常基因和异常基因在样本中的占比差异较大、变异断点位置难以准确确定的问题,提出了一种基于OCSVM(one-class support vector machine)的多策略融合拷贝数变异检测算法。算法融合读对深度、分裂读段和双端映射三种策略,建立多信...针对正常基因和异常基因在样本中的占比差异较大、变异断点位置难以准确确定的问题,提出了一种基于OCSVM(one-class support vector machine)的多策略融合拷贝数变异检测算法。算法融合读对深度、分裂读段和双端映射三种策略,建立多信号通道,并使用OCSVM模型解决正常基因和异常基因占比差异较大的影响以提高算法的拷贝数变异检测性能;对串联重复区域、穿插重复区域和缺失区域进行了分析探索,利用分裂读段信号实现变异点位置的精确定位,并确定变异类型。在240个模拟数据集和4个真实数据集上进行测试,并与其它几种算法进行比较。实验结果表明,该算法可以显著提高拷贝数变异检测的灵敏度、精度、F1评分以及重叠密度评分,同时减小了检测结果的边界偏差。展开更多
文摘This article adopts three artificial intelligence techniques, Gaussian Process Regression（GPR）, Least Square Support Vector Machine（LSSVM） and Extreme Learning Machine（ELM）, for prediction of rock depth（d） at any point in Chennai. GPR, ELM and LSSVM have been used as regression techniques.Latitude and longitude are also adopted as inputs of the GPR, ELM and LSSVM models. The performance of the ELM, GPR and LSSVM models has been compared. The developed ELM, GPR and LSSVM models produce spatial variability of rock depth and offer robust models for the prediction of rock depth.
文摘Aimed at uncertainties and model's impreciseness, nonlinearity and time-variability of depth control system in autonomous underwater vehicle (AUV), a depth predictive control method was put forward based on rough set (RS) and least squares support vector machine (LSSVM). By using RS theory, the monitor data attribute of AUV was reduced to eliminate the redundant information and to improve efficiency. Then, LSSVM model was trained by using the reduced rules, and its parameters were optimized by using chaos theory for the higher accurate control. Taken an AUV typed NPS Phoenix as an example, its depth step response, horizontal rudder and pitch change were simulated. The simulation results show that the method improves the model's accuracy and has better real-time response, fault-tolerant ability, reliability and strong anti-interfere capability.
文摘针对正常基因和异常基因在样本中的占比差异较大、变异断点位置难以准确确定的问题,提出了一种基于OCSVM(one-class support vector machine)的多策略融合拷贝数变异检测算法。算法融合读对深度、分裂读段和双端映射三种策略,建立多信号通道,并使用OCSVM模型解决正常基因和异常基因占比差异较大的影响以提高算法的拷贝数变异检测性能;对串联重复区域、穿插重复区域和缺失区域进行了分析探索,利用分裂读段信号实现变异点位置的精确定位,并确定变异类型。在240个模拟数据集和4个真实数据集上进行测试,并与其它几种算法进行比较。实验结果表明,该算法可以显著提高拷贝数变异检测的灵敏度、精度、F1评分以及重叠密度评分,同时减小了检测结果的边界偏差。
