Short-term prediction of ammonia levels in goose houses via combined feature selector and random forest

Ammonia concentration(NH3)is a dominant source of environmental pollution in geese housing and profoundly affects the healthy growth of geese.Accurately forecasting NH3 and analyzing its change trends in geese houses is crucial for the survival of geese.A novel forecasting model was proposed by combining feature selector(CFS)and random forest(RF)to improve the prediction accuracy of NH3 in this study.The developed model integrated two modules.First,combining mutual information(MI)and relief-F,we propose that CFS quantify each feature’s importance values and eliminate the low-relation or unrelated features.Second,a random forest model was built using K-fold cross-validation grid search algorithm(CVGS)to obtain the RF hyperparameters to predict NH_(3).The simulation results show that the prediction accuracy was improved when feature selection after quantification based on the CFS was used.The mean square error(MSE),root mean square error(RMSE),and mean absolute percent error(MAPE)for the proposed model were 0.5072,0.6583,and 2.88%,respectively.The NH_(3) prediction model(CFS-CVGS-RF)based on Combined Feature Selector,cross-validation grid search algorithm(CVGS),and Random Forest(RF)exhibited the best prediction accuracy and generalization performance compared with other parallel forecasting models and is a suitable and useful tool for predicting NH3 in geese houses.The results of the research can provide a reference for the machine learning method to monitor the dynamic changes of ammonia in goose houses.

Clinical features of multiple trauma patients combined with spine and spinal cord injuries

Objective To analyze the clinical features of the multiple trauma patients combined with spine and spinal cord injuries.Methods A retrospective study was performed in143multiple trauma patients combined with spine and spinal

A Fast Image Matching Algorithm Using a Combination of Line Segment Features

The scene matching navigation is a research focus in the field of autonomous navigation,but the real-time performance of image matching algorithm is difficult to meet the needs of real navigation systems.Therefore,this paper proposes a fast image matching algorithm.The algorithm improves the traditional line segment extraction algorithm and combines with the Delaunay triangulation method.By combining the geometric features of points and lines,the image feature redundancy is reduced.Then,the error with confidence criterion is analyzed and the matching process is completed.The simulation results show that the proposed algorithm can still work within 3°rotation and small scale variation.In addition,the matching time is less than 0.5 s when the image size is 256 pixel×256 pixel.The proposed algorithm is suitable for autonomous navigation systems with multiple feature distribution and higher real-time requirements.

Feature combination via importance-inhibition analysis

A new method for combining features via importance-inhibition analysis （IIA） is described to obtain more effective feature combination in learning question classification. Features are combined based on the inhibition among features as well as the importance of individual features. Experimental results on the Chinese questions set show that, the IIA method shows a gradual increase in average and maximum accuracies at all feature combinations, and achieves great improvement over the importance analysis（IA） method on the whole. Moreover, the IIA method achieves the same highest accuracy as the one by the exhaustive method, and further improves the performance of question classification.

Real-Time Brain-Computer Interface System Based on Motor Imagery

Abstract-A brain-computer interface （BCI） real- time system based on motor imagery translates the user＇s motor intention into a real-time control signal for peripheral equipments. A key problem to be solved for practical applications is real-time data collection and processing. In this paper, a real-time BCI system is implemented on computer with electroencephalogram amplifier. In our implementation, the on-line voting method is adopted for feedback control strategy, and the voting results are used to control the cursor horizontal movement. Three subjects take part in the experiment. The results indicate that the best accuracy is 90%.

Feature aggregation for nutrient deficiency identification in chili based on machine learning

Macronutrient deficiency inhibits the growth and development of chili plants.One of the non-destructive methods that plays a role in processing plant image data based on specific characteristics is computer vision.This study uses 5166 image data after augmentation process for six plant health conditions.But the analysis of one feature cannot represent plant health condition.Therefore,a careful combination of features is required.This study combines three types of features with HSV and RGB for color,GLCM and LBP for texture,and Hu moments and centroid distance for shapes.Each feature and its combination are trained and tested using the same MLP architecture.The combination of RGB,GLCM,Hu moments,and Distance of centroid features results the best performance.In addition,this study compares the MLP architecture used with previous studies such as SVM,Random Forest Technique,Naive Bayes,and CNN.CNN produced the best performance,followed by SVM and MLP,with accuracy reaching 97.76%,90.55%and 89.70%,respectively.Although MLP has lower accuracy than CNN,the model for identifying plant health conditions has a reasonably good success rate to be applied in a simple agricultural environment.

An Automatic HFO Detection Method Combining Visual Inspection Features with Multi-Domain Features

As an important promising biomarker,high frequency oscillations(HFOs)can be used to track epileptic activity and localize epileptogenic zones.However,visual marking of HFOs from a large amount of intracranial electroencephalogram(iEEG)data requires a great deal of time and effort from researchers,and is also very dependent on visual features and easily influenced by subjective factors.Therefore,we proposed an automatic epileptic HFO detection method based on visual features and non-intuitive multi-domain features.To eliminate the interference of continuous oscillatory activity in detected sporadic short HFO events,the iEEG signals adjacent to the detected events were set as the neighboring environmental range while the number of oscillations and the peak–valley differences were calculated as the environmental reference features.The proposed method was developed as a MatLab-based HFO detector to automatically detect HFOs in multi-channel,long-distance iEEG signals.The performance of our detector was evaluated on iEEG recordings from epileptic mice and patients with intractable epilepsy.More than 90%of the HFO events detected by this method were confirmed by experts,while the average missed-detection rate was<10%.Compared with recent related research,the proposed method achieved a synchronous improvement of sensitivity and specificity,and a balance between low false-alarm rate and high detection rate.Detection results demonstrated that the proposed method performs well in sensitivity,specificity,and precision.As an auxiliary tool,our detector can greatly improve the efficiency of clinical experts in inspecting HFO events during the diagnosis and treatment of epilepsy.

A Lightweight Improved U-Net with Shallow Features Combination and Its Application to Defect Detection

In order to solve the problems of shallow features loss and high computation cost of U-Net,we propose a lightweight with shallow features combination(IU-Net).IU-Net adds several convolution layers and short links to the skip path to extract more shallow features.At the same time,the original convolution is replaced by the depth-wise separable convolution to reduce the calculation cost and the number of parameters.IU-Net is applied to detecting small metal industrial products defects.It is evaluated on our own SUES-Washer dataset to verify the effectiveness.Experimental results demonstrate that our proposed method outperforms the original U-Net,and it has 1.73%,2.08%and 11.2%improvement in the intersection over union,accuracy,and detection time,respectively,which satisfies the requirements of industrial detection.

Fast TMRM:efficient multi-task recommendation model

An improved multi-task learning recommendation algorithm-fast two-stage multi-task recommendation model boosted feature selection(Fast TMRM) is proposed based on auto-encoders in this paper. Compared to previous work, Fast TMRM improves the convergence speed and accuracy of training. In addition, Fast TMRM builds on previous work to introduce the auto-encoder to encode the important feature combination vector. That is how it can be used for the training of multi-task learning, which helps to improve the training efficiency of the model by nearly 67%. Finally, the nearest neighbor search is used to restore important feature expression.