Ensemble

摘要： Machine learning algorithms have been deployed in numerous optimization,prediction and classification problems.This has endeared them for application in fields such as computer networks and medical diagnosis.Although these machine learning algorithms achieve convincing results in these fields,they face numerous challenges when deployed on imbalanced dataset.Consequently,these algorithms are often biased towards majority class,hence unable to generalize the learning process.In addition,they are unable to effectively deal with high-dimensional datasets.Moreover,the utilization of conventional feature selection techniques from a dataset based on attribute significance render them ineffective for majority of the diagnosis applications.In this paper,feature selection is executed using the more effective Neighbour Components Analysis(NCA).During the classification process,an ensemble classifier comprising of K-Nearest Neighbours(KNN),Naive Bayes(NB),Decision Tree(DT)and Support Vector Machine(SVM)is built,trained and tested.Finally,cross validation is carried out to evaluate the developed ensemble model.The results shows that the proposed classifier has the best performance in terms of precision,recall,F-measure and classification accuracy.

摘要： In recent years, there has been increasing demand for high-resolution seasonal climate forecasts at sufficient lead times to allow response planning from users in agriculture, hydrology, disaster risk management, and health, among others. This paper examines the forecasting skill of the North American Multi-model Ensemble (NMME) over Ethiopia during the June to September (JJAS) season. The NMME, one of the multi-model seasonal forecasting systems, regularly generates monthly seasonal rainfall forecasts over the globe with 0.5 - 11.5 months lead time. The skill and predictability of seasonal rainfall are assessed using 28 years of hindcast data from the NMME models. The forecast skill is quantified using canonical correlation analysis (CCA) and root mean square error. The results show that the NMME models capture the JJAS seasonal rainfall over central, northern, and northeastern parts of Ethiopia while exhibiting weak or limited skill across western and southwestern Ethiopia. The performance of each model in predicting the JJAS seasonal rainfall is variable, showing greater skill in predicting dry conditions. Overall, the performance of the multi-model ensemble was not consistently better than any single ensemble member. The correlation of observed and predicted seasonal rainfall for the better performing models—GFDL-CM2p5-FLOR-A06, CMC2-CanCM4, GFDL-CM2p5-FLOR-B01 and NASA-GMAO-062012—is 0.68, 0.58, 0.52, and 0.5, respectively. The COLA-RSMAS-CCSM4, CMC1- CanCM3 and NCEP-CFSv2 models exhibit less skill, with correlations less than 0.4. In general, the NMME offers promising skill to predict seasonal rainfall over Ethiopia during the June-September (JJAS) season, motivating further work to assess its performance at longer lead times.

摘要： Awide range of camera apps and online video conferencing services support the feature of changing the background in real-time for aesthetic,privacy,and security reasons.Numerous studies show that theDeep-Learning(DL)is a suitable option for human segmentation,and the ensemble of multiple DL-based segmentation models can improve the segmentation result.However,these approaches are not as effective when directly applied to the image segmentation in a video.This paper proposes an Adaptive N-Frames Ensemble(AFE)approach for high-movement human segmentation in a video using an ensemble of multiple DL models.In contrast to an ensemble,which executes multiple DL models simultaneously for every single video frame,the proposed AFE approach executes only a single DL model upon a current video frame.It combines the segmentation outputs of previous frames for the final segmentation output when the frame difference is less than a particular threshold.Our method employs the idea of the N-Frames Ensemble(NFE)method,which uses the ensemble of the image segmentation of a current video frame and previous video frames.However,NFE is not suitable for the segmentation of fast-moving objects in a video nor a video with low frame rates.The proposed AFE approach addresses the limitations of the NFE method.Our experiment uses three human segmentation models,namely Fully Convolutional Network(FCN),DeepLabv3,and Mediapipe.We evaluated our approach using 1711 videos of the TikTok50f dataset with a single-person view.The TikTok50f dataset is a reconstructed version of the publicly available TikTok dataset by cropping,resizing and dividing it into videos having 50 frames each.This paper compares the proposed AFE with single models and the Two-Models Ensemble,as well as the NFE models.The experiment results show that the proposed AFE is suitable for low-movement as well as high-movement human segmentation in a video.

摘要： The paper reports three new ensembles of supervised learning predictors for managing medical insurance costs.The open dataset is used for data analysis methods development.The usage of artificial intelligence in the management of financial risks will facilitate economic wear time and money and protect patients’health.Machine learning is associated withmany expectations,but its quality is determined by choosing a good algorithm and the proper steps to plan,develop,and implement the model.The paper aims to develop three new ensembles for individual insurance costs prediction to provide high prediction accuracy.Pierson coefficient and Boruta algorithm are used for feature selection.The boosting,stacking,and bagging ensembles are built.A comparison with existing machine learning algorithms is given.Boosting modes based on regression tree and stochastic gradient descent is built.Bagged CART and Random Forest algorithms are proposed.The boosting and stacking ensembles shown better accuracy than bagging.The tuning parameters for boosting do not allow to decrease the RMSE too.So,bagging shows its weakness in generalizing the prediction.The stacking is developed using K Nearest Neighbors(KNN),Support Vector Machine(SVM),Regression Tree,Linear Regression,Stochastic Gradient Boosting.The random forest(RF)algorithm is used to combine the predictions.One hundred trees are built forRF.RootMean Square Error(RMSE)has lifted the to 3173.213 in comparison with other predictors.The quality of the developed ensemble for RootMean Squared Error metric is 1.47 better than for the best weak predictor(SVR).

摘要： The data from event cameras not only portray contours of moving objects but also contain motion information inherently.Herein,motion information can be used in event-based and frame-based object trackers to ease the challenges of occluded objects and data association,respectively.In the event-based tracker,events within a short interval are accumulated.Within the interval,the histogram of local time measurements(or‘motion histogram’)is proposed as the feature to describe the target and candidate regions.Then the mean-shift tracking approach is used by shifting the tracker towards similarity maximisation on motion histograms between target and candidate regions.As for the frame-based tracker,given the assumption that a single object moves at a constant velocity on the image plane,the distribution of local timestamps is modelled,followed by which object-level velocities are obtained from parameter estimation.We then build a Kalman-based ensemble,in which object-level velocities are deemed as an additional measurement on top of object detection results.Experiments have been conducted to measure the performance of proposed trackers based on our self-collected data.Thanks to the assistance from motion information,the event-based tracker successfully differentiates partially overlapped objects with distinct motion profiles;The inter-frame tracker avoids data association failure on fast-moving objects and leads to fast convergence on object velocity estimation.

摘要： Generally,the risks associated with malicious threats are increasing for the Internet of Things(IoT)and its related applications due to dependency on the Internet and the minimal resource availability of IoT devices.Thus,anomaly-based intrusion detection models for IoT networks are vital.Distinct detection methodologies need to be developed for the Industrial Internet of Things(IIoT)network as threat detection is a significant expectation of stakeholders.Machine learning approaches are considered to be evolving techniques that learn with experience,and such approaches have resulted in superior performance in various applications,such as pattern recognition,outlier analysis,and speech recognition.Traditional techniques and tools are not adequate to secure IIoT networks due to the use of various protocols in industrial systems and restricted possibilities of upgradation.In this paper,the objective is to develop a two-phase anomaly detection model to enhance the reliability of an IIoT network.In the first phase,SVM and Naïve Bayes,are integrated using an ensemble blending technique.K-fold cross-validation is performed while training the data with different training and testing ratios to obtain optimized training and test sets.Ensemble blending uses a random forest technique to predict class labels.An Artificial Neural Network(ANN)classifier that uses the Adam optimizer to achieve better accuracy is also used for prediction.In the second phase,both the ANN and random forest results are fed to the model’s classification unit,and the highest accuracy value is considered the final result.The proposed model is tested on standard IoT attack datasets,such as WUSTL_IIOT-2018,N_BaIoT,and Bot_IoT.The highest accuracy obtained is 99%.A comparative analysis of the proposed model using state-of-the-art ensemble techniques is performed to demonstrate the superiority of the results.The results also demonstrate that the proposed model outperforms traditional techniques and thus improves the reliability of an IIoT network.

摘要： Feature selection is essential for prioritising important attributes in data to improve prediction quality in machine learning algorithms.As different selection techniques identify different feature sets,relying on a single method may result in risky decisions.The authors propose an ensemble approach using union and quorum combination techniques with five primary individual selection methods which are analysis of variance,variance threshold,sequential backward search,recursive feature elimination,and least absolute selection and shrinkage operator.The proposed method reduces features in three rounds:(i)discard redundant features using pairwise correlation,(ii)individual methods select their own feature sets independently,and(iii)equalise individual feature sets.The equalised individual feature sets are combined using union and quorum techniques.Both the combined and individual sets are tested for network anomaly detection using random forest,decision tree,K-nearest neighbours,Gaussian Naive Bayes,and logistic regression classifiers.The experimental results on the UNSW-NB15 data set show that random forest with union and quorum feature sets yields 99 and 99.02% f1_score with minimum 6 and 12 features,respectively.The results on the NSL-KDD data set show that random forest with union and quorum gets 99.34 and 99.21% f1_score with a minimum of 28 and 18 features.

摘要： 为了设计实现基于HIS系统的脑电图预约系统,替代以往效率低下的预约方式,文章分析原有脑电图预约流程,基于Ensemble平台,结合Caché Server Page与HIS UI完成前端界面的构建,使用JavaScript完成前端界面逻辑与和后端进行数据交互的功能,通过Caché ObjectScript处理后端数据逻辑,最后使用Caché数据库自带的Global存储结构完成数据存储。通过基于HIS系统开发,将脑电图预约系统嵌入HIS系统,替代以往脑电图预约方式。对于脑电图医务人员来说,脑电图预约系统的预约效率更高,数据存储更加安全,预约记录查询更加方便,减少患者排队预约脑电图的时间。

摘要： Classification of skin lesions is a complex identification challenge.Due to the wide variety of skin lesions,doctors need to spend a lot of time and effort to judge the lesion image which zoomed through the dermatoscopy.The diagnosis which the algorithm of identifying pathological images assists doctors gets more and more attention.With the development of deep learning,the field of image recognition has made long-term progress.The effect of recognizing images through convolutional neural network models is better than traditional image recognition technology.In this work,we try to classify seven kinds of lesion images by various models and methods of deep learning,common models of convolutional neural network in the field of image classification include ResNet,DenseNet and SENet,etc.We use a fine-tuning model with a multi-layer perceptron,by training the skin lesion model,in the validation set and test set we use data expansion based on multiple cropping,and use five models’ensemble as the final results.The experimental results show that the program has good results in improving the sensitivity of skin lesion diagnosis.

摘要： 本发明涉及一种支持混合模型融合的Model Ensemble方法，两个模型的输出均包括实例框和类别分布，分别对两个实例框和两个类别分布进行加权融合，对加权融合后的输出去重获得唯一的模型融合输出。当两个模型中有一个分类模型时，将该分类模型的输出改造成检测模型输出，用“检测模型的实例框+分类模型的类别分布”来构造一个虚拟的检测模型输出。本方法不限于分类模型融合，可以融合不同AI模型。

摘要： 本发明涉及一种支持混合模型融合的Model Ensemble方法，两个模型的输出均包括实例框和类别分布，分别对两个实例框和两个类别分布进行加权融合，对加权融合后的输出去重获得唯一的模型融合输出。当两个模型中有一个分类模型时，将该分类模型的输出改造成检测模型输出，用“检测模型的实例框+分类模型的类别分布”来构造一个虚拟的检测模型输出。本方法不限于分类模型融合，可以融合不同AI模型。

摘要： 本发明公开一种联合U‑Net和Temporal Ensembling的信号初至拾取方法及装置，所述方法包括：获取原始微地震信号数据并进行预处理，得到微地震信号数据集；根据微地震信号数据集的部分数据制作有标签数据集；对数据集进行数据扩增，添加随机噪声并投入U‑Net网络进行训练；对U‑Net网络添加丢弃正则化防止训练过拟合，计算交叉熵损失和均方差损失的加权损失；根据所述加权损失结合Temporal Ensembling模型进行半监督训练；获取待测信号，根据所述联合U‑Net和Temporal Ensembling的微地震有效信号检测模型进行有效信号初至拾取。本发明可以对少量微地震信号扩容，集成预测有效信号，大大提高初至拾取效率。

摘要： 本申请提出了基于Ensemble学习模型的电量异常检测方法，包括对获取到的部分用电数据进行数据整合和用户分类；基于异常审核规则对处理后的用电数据进行特征提取；构建Ensemble学习模型，将特征提取后的数据划分为n组训练集和1个测试集，将训练集导入以ELM为基模型的Ensemble学习模型中进行训练，得到n组分类检测模型；将测试集投入训练好的模型中进行测试，得到n种输出结果；对检测结果进行多数投票决策是否存在电量异常。通过结合用户类别和电量异常审核规则来进行特征抽取，可以把源数据具有强烈的时间序列特点变成具有无序列特点，使得在后面的电量异常检测分类算法的选择上更加具有普适性。同时用多数投票法对多模型预测结果进行投票，提高了异常数据检测率。