PM 2.5 Concentration Prediction By Data Mining Method

The global air pollution is constantly increasing and causing negative effects on human health such as respiratory, cardiovascular diseases and cancers. Recently, pollution in Hanoi has become increasingly worse, especially when PM2.5 concentration is always at high level. Thus, PM2.5 prediction is of more urgency to issue early forecasts. Depending on air data including meteorological indicators and air pollution indicators collected in Hanoi, we have proposed a new characteristic extraction method that gave better results when uing the same algorithm compared to those of old methods. XGBoost algorithm was applied to predict the concentration of PM2.5 and the test showed that the accuracy of this algorithm is higher than that of other data mining algorithms while the training time is significantly lower.

Recognition of Psychological Characteristics of Students’ Behavior Based on Improved Machine Learning

Contemporary classroom teaching requires the combination of students’ classroom behavior and their psychological activities and appropriately changes the teaching mode according to students’ psychological characteristics. This paper analyzes the traditional characteristic recognition algorithm, and after improving its deficiencies, an improved characteristic extraction algorithm is proposed, based on the actual situation of classroom learning. This new algorithm can effectively improve the students’ psychological feature prediction; with the support of this algorithm, a comprehensive analysis model with classroom behavior recognition and psychological feature recognition is constructed; also, the functional structure of the system is built up. Through experimental research, the model proposed in this paper is analyzed, and the experimental data has approved that the systemic model could play an important role in classroom teaching.

Investigation of Biometric Identification Technology Based on biological Fingerprints and Facial Features

Biometric identification is largely dependent on feature extraction technology. As feature extraction techniques are increasingly mature, scholars have gradually turned their attention to the relevant problems between biometric characteristics. This paper reviews the characteristic extraction method of face and fingerprint analyzes the feature classification extraction method based on empirical knowledge and the depth learning-based computer logic sampling extraction method and compares existing solutions from the angle of image processing. Based on feature extraction, it will have prospected in the future biometric identification model of progress.

Fault Characteristic Extraction by Fractional Lower-Order Bispectrum Methods

The generated signals generally contain a large amount of background noise when the mechanical bearing fails, and the fault signals present nonlinear and non-Gaussian feature, which have heavy tail and belong to α -stable distribution ( 1 < α < 2 ); even the background noises are also α -stable distribution process. Then it is difficult to obtain reliable conclusion by using the traditional bispectral analysis method under α -stable distribution environment. Two improved bispectrum methods are proposed based on fractional lower-order covariation in this paper, including fractional low-order direct bispectrum (FLODB) method, fractional low-order indirect bispectrum (FLOIDB) method. In order to decrease the estimate variance and increase the bispectral flatness, the fractional lower-order autoregression (FLOAR) model bispectrum and fractional lower-order autoregressive moving average (FLOARMA) model bispectrum methods are presented, and their calculation steps are summarized. We compare the improved bispectrum methods with the conventional methods employing second-order statistics in Gaussian and S α S distribution environments; the simulation results show that the improved bispectrum methods have performance advantages compared to the traditional methods. Finally, we use the improved methods to estimate the bispectrum of the normal and outer race fault signal; the result indicates that they are feasible and effective for fault diagnosis.

Scattering Characteristic Extraction and Recovery for Multiple Targets Based on Time Frequency Analysis

The multi-target scattering field consists of the scattering fields of each target, but it is difficult to know the scattering characteristics of the specific target from the total scattering field. However, the scattering characteristics of single target embedded in the total scattered field have important research significance for target recognition and detection. In this paper, a method is proposed to extract and recover each target’s scattering characteristics from the total scattering field of multiple targets. The theoretical basis of the method is that the scattering echoes corresponding to different targets reach the receiver at different time. We acquire the total scattering field at first. Then, we perform the signal processing with time-frequency analysis to obtain the arrival time of different scattering echoes. According to the time slot difference, the time domain signal of each target can be extracted to recover its scattering field. Several examples validate the proposed method.

Small Moving Target Recognition in Star Image with TRM

Recognition of small moving targets in space has become one of the frontier scientific researches in recent decade. Most of them focus on detection and recognition in star image with sidereal stare mode. However, in this research field, few researches are about detection and recognition in star image with track rate mode. In this paper, a novel approach is proposed to recognize the moving target in single frame by machine learning method based on elliptical characteristic extraction of star points. The technical path about recognition of moving target in space is redesigned instead of traditional processing approaches. Elliptical characteristics of each star point can be successfully extracted from single image. Machine learning can achieve the classification goal in order to make sure that all moving targets can be extracted. The experiments show that our proposed approach can have better performance in star images with different qualities.

An HADOOP File Systems Based Data Analysis of Flood Prediction

One of the most well-known uses of Artificial Intelligence which has noticed an enormous development within the digital era is actually Machine Learning Techniques in which the method scientific studies and also increases the overall performance of its via progressive learning with no explicit programming. It is popular within many programs certainly one of them becoming a weather condition prediction. Image distinction, as well as feature extraction, are regarded as to become essentially the most popularly pre-owned techniques finished utilizing machine mastering procedure. With this proposed method, a hybrid model is developed for predicting rainfall by using feature extraction methods that have been proposed by us. The unit was created in such a manner it fetches a sequence of pictures originating from a data source as well as different info regarding earlier rainfalls wearing a particular region. The pictures are actually pre-processed as well as additional segmented for option extraction. The segmented pictures are then categorized via the Random Forest algorithm in which the sequence of pictures is actually validated frame by frame. The effectiveness of the suggested design is actually evaluated and it is kept in a sent out HADOOP File Systems (HDFS) for faster retrieval of information. It’s found that this suggested model provides greater results. The functionality of this unit tends to be more precise because the unit has an iterative method for characteristic extraction inside classifying pictures. The suggested item is actually incorporated by using an aware process to be able to attain a warning or an alert to the individuals in a space properly prior to a flood really hits.