Search

Kicks can lead to well control risks during petroleum drilling, and even more serious kicks may lead to serious casualties, which is the biggest threat factor affecting the safety in the process of petroleum drilling. Therefore, how to detect kicks early and efficiently has become a focus practical problem. Traditional machine learning models require a large amount of labeled data, such kicked sample, and it is difficult to label data, which requires a lot of labor and time. To address the above issues, the deep forest is extended to a transfer learning model to improve the generalization ability. In this paper, a transfer learning model is built to detect kicks early. The source domain model adopts the deep forest model. Deep forest is an ensemble learning model with a hierarchical structure similar to deep learning. Each layer contains a variety of random forests. It is an integration of the model in depth and breadth. In the case of a small sample size (20–60 min), kick can be identified 10 min in advance. The deep forest model is established as the source domaining model, and a cascade forest is added at the last layer according to the transfer learning algorithm to form the classification model of this paper. The experimental results show that the kick prediction accuracy of the model is 80.13% by a confusion matrix. In the target domain, the proposed model performs better than other ensemble learning algorithms, and the accuracy is 5% lower than other SOTA transfer learning algorithms. [ABSTRACT FROM AUTHOR]

The dissolution kinetics of Portland cement is a critical factor in controlling the hydration reaction and improving the performance of concrete. Tricalcium silicate (C3S), the primary phase in Portland cement, is known to have complex dissolution mechanisms that involve multiple reactions and changes to particle surfaces. As a result, current analytical models are unable to accurately predict the dissolution kinetics of C3S in various solvents when it is undersaturated with respect to the solvent. This paper employs the deep forest (DF) model to predict the dissolution rate of C3S in the undersaturated solvent. The DF model takes into account several variables, including the measurement method (i.e., reactor connected to inductive coupled plasma spectrometer and flow chamber with vertical scanning interferometry), temperature, and physicochemical properties of solvents. Next, the DF model evaluates the influence of each variable on the dissolution rate of C3S, and this information is used to develop a closed-form analytical model that can predict the dissolution rate of C3S. The coefficients and constant of the analytical model are optimized in two scenarios: generic and alkaline solvents. The results show that both the DF and analytical models are able to produce reliable predictions of the dissolution rate of C3S when it is undersaturated and far from equilibrium. [ABSTRACT FROM AUTHOR]

Machine learning has become an important research field in genetics and molecular biology. Survival analysis using machine learning can provide an important computed-aid clinical research scheme for evaluating tumor treatment options. However, the genomic features are high-dimensional, which limits the prediction performance of the survival learning model. Therefore, in this paper, we propose an improved survival prediction model using a deep forest and self-supervised learning. It uses a deep survival forest to perform adaptive learning of high-dimensional genomic data and ensure robustness. In addition, self-supervised learning, as a semi-supervised learning style, is designed to utilize unlabeled samples to improve model performance. Based on four cancer datasets from The Cancer Genome Atlas (TCGA), the experimental results show that our proposed method outperforms four advanced survival analysis methods in terms of the C-index and brier score. The developed prediction model will help doctors rethink patient characteristics' relevance to survival time and personalize treatment decisions. [ABSTRACT FROM AUTHOR]

Electroencephalography (EEG) records the electrical activity of the brain, which is an important tool for the automatic detection of epileptic seizures. It is certainly a very heavy burden to only recognize EEG epilepsy manually, so the method of computer-assisted treatment is of great importance. This paper presents a seizure detection algorithm based on variational modal decomposition (VMD) and a deep forest (DF) model. Variational modal decomposition is performed on EEG recordings, and the first three variational modal functions (VMFs) are selected to construct the time–frequency distribution of the EEG signals. Then, the log−Euclidean covariance matrix (LECM) is computed to represent the EEG properties and form EEG features. The deep forest model is applied to complete the EEG signal classification, which is a non-neural network deep model with a cascade structure that performs feature learning through the forest. In addition, to improve the classification accuracy, postprocessing techniques are performed to generate the discriminant results by moving average filtering and adaptive collar expansion. The algorithm was evaluated on the Bonn EEG dataset and the Freiburg long−term EEG dataset, and the former achieved a sensitivity and specificity of 99.32% and 99.31%, respectively. The mean sensitivity and specificity of this method for the 21 patients in the Freiburg dataset were 95.2% and 98.56%, respectively, with a false detection rate of 0.36/h. These results demonstrate the superior performance advantage of our algorithm and indicate its great research potential in epilepsy detection. [ABSTRACT FROM AUTHOR]

The rotor is an essential actuator of quadrotor UAV, and is prone to failure due to high speed rotation and environmental disturbances. It is difficult to diagnose rotor faults and identify the fault localization simultaneously. In this paper, we propose a fault diagnosis and localization scheme based on the Extended State Observer (ESO) and Deep Forest (DF). This scheme can accurately complete the fault diagnosis and localization for the quadrotor UAV actuator without knowing the fault size by combining the model-based and the data-driven methods. First, we obtain the angular acceleration residual signal of the quadrotor UAV by using ESO. The residual signal is the difference between the observed state of ESO and the true fault state. Then, we design the residual feature analysis method by considering the position distribution of the quadrotor UAV actuator. This method can embed the actuator fault localization information into the fault data by simultaneously considering pitch and roll of the quadrotor UAV. Finally, we complete the fault diagnosis and localization of the quadrotor UAV actuator by processing the fault data by using DF. This scheme has the advantages of straightforward observer modeling, strong generalization ability, adaptability to small sample data, and few hyperparameters. Our simulation results indicate that the accuracy of the proposed scheme reaches more than 99% for the unknown size of the quadrotor UAV actuator fault. [ABSTRACT FROM AUTHOR]

The frequent accidents caused by the main fan motor in coal mines have exposed the safety hazards of rolling bearings. When a rolling bearing fails, its symmetry is broken, resulting in a rapid decline in its safety performance and posing a great threat to the main fan. Therefore, accurate rolling bearing fault diagnoses are the key to ensuring the safe and durable operation of main fans. Thus, in this paper, we propose a new fault diagnosis method of rolling bearing based on wavelet packet analysis and deep forest algorithm. Firstly, experiments were conducted under different health states to guarantee the diversity of data relating to the rolling bearing's main fan and then to ensure the accuracy of the fault diagnosis under different health states. On the basis of the collected vibration signal data, we conducted the wavelet packet analysis method to extract the characteristics of the vibration signal and obtained a feature vector that characterizes the health of the bearing. After that, the extracted feature vector was used as the feature vector of the deep forest algorithm to train the deep forest diagnosis model and determine the location and fault type of the bearing fault. Finally, the proposed method in this paper was validated with real-time monitoring data of a main ventilation fan and compared with other diagnostic algorithms, which not only verified the diagnostic capability of deep forest in handling small samples, but also verified the diagnostic capability of the fault diagnosis model. In summary, the proposed fault diagnosis approach is promising in real coal mine main fans. [ABSTRACT FROM AUTHOR]

The occurrence of rockburst can cause significant disasters in underground rock engineering. It is crucial to predict and prevent rockburst in deep tunnels and mines. In this paper, the deficiencies of ensemble learning algorithms in rockburst prediction were investigated. Aiming at these shortages, a novel machine learning model, deep forest, was proposed to predict rockburst risk. The deep forest combines the characteristics of deep learning and ensemble models, which can solve complex problems. To develop the deep forest model for rockburst prediction, 329 real rockburst cases were collected to build a comprehensive database for intelligent analysis. Bayesian optimization was proposed to tune the hyperparameters of the deep forest. As a result, the deep forest model achieved 100% training accuracy and 92.4% testing accuracy, and it has more outstanding capability to forecast rockburst disasters compared to other widely used models (i.e., random forest, boosting tree models, neural network, support vector machine, etc.). The results of sensitivity analysis revealed the impact of variables on rockburst levels and the applicability of deep forest with a few input parameters. Eventually, real cases of rockburst in two gold mines, China, were used for validation purposes while the needed data sets were prepared by field observations and laboratory tests. The promoting results of the developed model during the validation phase confirm that it can be used with a high level of accuracy by practicing engineers for predicting rockburst occurrences. [ABSTRACT FROM AUTHOR]

Prognostics and health management (PHM) with failure prognosis and maintenance decision-making as the core is an advanced technology to improve the safety, reliability, and operational economy of engineering systems. However, studies of failure prognosis and maintenance decision-making have been conducted separately over the past years. Key challenges remain open when the joint problem is considered. The aim of this paper is to develop an integrated strategy for dynamic predictive maintenance scheduling (DPMS) based on a deep auto-encoder and deep forest-assisted failure prognosis method. The proposed DPMS method involves a complete process from performing failure prognosis to making maintenance decisions. The first step is to extract representative features reflecting system degradation from raw sensor data by using a deep auto-encoder. Then, the features are fed into the deep forest to compute the failure probabilities in moving time horizons. Finally, an optimal maintenance-related decision is made through quickly evaluating the costs of different decisions with the failure probabilities. Verification was accomplished using NASA's open datasets of aircraft engines, and the experimental results show that the proposed DPMS method outperforms several state-of-the-art methods, which can benefit precise maintenance decisions and reduce maintenance costs. [ABSTRACT FROM AUTHOR]

Background: the credit scoring model is an effective tool for banks and other financial institutions to distinguish potential default borrowers. The credit scoring model represented by machine learning methods such as deep learning performs well in terms of the accuracy of default discrimination, but the model itself also has many shortcomings such as many hyperparameters and large dependence on big data. There is still a lot of room to improve its interpretability and robustness. Methods: the deep forest or multi-Grained Cascade Forest (gcForest) is a decision tree depth model based on the random forest algorithm. Using multidimensional scanning and cascading processing, gcForest can effectively identify and process high-dimensional feature information. At the same time, gcForest has fewer hyperparameters and has strong robustness. So, this paper constructs a two-stage hybrid default discrimination model based on multiple feature selection methods and gcForest algorithm, and at the same time, it optimizes the parameters for the lowest type II error as the first principle, and the highest AUC and accuracy as the second and third principles. GcForest can not only reflect the advantages of traditional statistical models in terms of interpretability and robustness but also take into account the advantages of deep learning models in terms of accuracy. Results: the validity of the hybrid default discrimination model is verified by three real open credit data sets of Australian, Japanese, and German in the UCI database. Conclusions: the performance of the gcForest is better than the current popular single classifiers such as ANN, and the common ensemble classifiers such as LightGBM, and CNNs in type II error, AUC, and accuracy. Besides, in comparison with other similar research results, the robustness and effectiveness of this model are further verified. [ABSTRACT FROM AUTHOR]

Target detection on the sea-surface has always been a high-profile problem, and the detection of weak targets is one of the most difficult problems and the key issue under this problem. Traditional techniques, such as imaging, cannot effectively detect these types of targets, so researchers choose to start by mining the characteristics of the received echoes and other aspects for target detection. This paper proposes a false alarm rate (FAR) controllable deep forest model based on six-dimensional feature space for efficient and accurate detection of weak targets on the sea-surface. This is the first attempt at the deep forest model in this field. The validity of the model was verified on IPIX data, and the detection probability was compared with other proposed methods. Under the same FAR condition, the average detection accuracy rate of the proposed method could reach over 99.19%, which is 9.96% better than the results of the current most advanced method (K-NN FAR-controlled Detector). Experimental results show that multi-feature fusion and the use of a suitable detection framework have a positive effect on the detection of weak targets on the sea-surface. [ABSTRACT FROM AUTHOR]

Conventional classification algorithms have shown great success in balanced hyperspectral data classification. However, the imbalanced class distribution is a fundamental problem of hyperspectral data, and it is regarded as one of the great challenges in classification tasks. To solve this problem, a non-ANN based deep learning, namely SMOTE-Based Weighted Deep Rotation Forest (SMOTE-WDRoF) is proposed in this paper. First, the neighboring pixels of instances are introduced as the spatial information and balanced datasets are created by using the SMOTE algorithm. Second, these datasets are fed into the WDRoF model that consists of the rotation forest and the multi-level cascaded random forests. Specifically, the rotation forest is used to generate rotation feature vectors, which are input into the subsequent cascade forest. Furthermore, the output probability of each level and the original data are stacked as the dataset of the next level. And the sample weights are automatically adjusted according to the dynamic weight function constructed by the classification results of each level. Compared with the traditional deep learning approaches, the proposed method consumes much less training time. The experimental results on four public hyperspectral data demonstrate that the proposed method can get better performance than support vector machine, random forest, rotation forest, SMOTE combined rotation forest, convolutional neural network, and rotation-based deep forest in multiclass imbalance learning. [ABSTRACT FROM AUTHOR]

The information extraction of polarimetric synthetic aperture radar (PolSAR) images typically requires a great number of training samples; however, the training samples from historical images are less reusable due to the distribution differences. Consequently, there is a significant manual cost to collecting training samples when processing new images. In this paper, to address this problem, we propose a novel active transfer learning method, which combines active learning and the deep forest model to perform transfer learning. The main idea of the proposed method is to gradually improve the performance of the model in target domain tasks with the increase of the levels of the cascade structure. More specifically, in the growing stage, a new active learning strategy is used to iteratively add the most informative target domain samples to the training set, and the augmented features generated by the representation learning capability of the deep forest model are used to improve the cross-domain representational capabilities of the feature space. In the filtering stage, an effective stopping criterion is used to adaptively control the complexity of the model, and two filtering strategies are used to accelerate the convergence of the model. We conducted experiments using three sets of PolSAR images, and the results were compared with those of four existing transfer learning algorithms. Overall, the experimental results fully demonstrated the effectiveness and robustness of the proposed method. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) has become one of the most important means of information acquisition in today's society and shows great potential in many fields. Target identification and classification of SAR images are also the focus of research. With the vigorous development of deep learning, many researchers apply this method to SAR target classification to obtain a more automatic process and more accurate results. In this paper, a novel deep forest model constructed by multi-grained cascade forest (gcForest), which is different from the traditional neural network (NN) model, is employed to classify ten types of SAR targets in the moving and stationary target acquisition and recognition (MSTAR) dataset. Considering that the targets of input images may be off-center and of different sizes in practical applications, two improved models based on varying weights by image features have been put forward, and both obtain better results. A series of experiments have been conducted to optimize model parameters, and final results with the MSTAR dataset illustrate that the two improved models are both superior to the original gcForest model. This is the first attempt to classify SAR targets using the non-NN model. [ABSTRACT FROM AUTHOR]

The quality of a machined surface plays a critical role in assembly performance, especially for precise matching parts, and therefore it is necessary to develop a surface quality monitoring system in the machining process. In this paper, an indirect surface quality monitoring approach is proposed with a wireless sensory tool holder. First, experimentation is conducted to collect the machining process signals from the tool holder. Then, the time domain, frequency domain and time–frequency domain features are extracted, and the deep forest algorithm is adopted to identify the surface quality, which is evaluated through the surface average parameter. Finally, the results of the experiment and the comparisons with other approaches demonstrate the effectiveness of the proposed method, which could be applied to ensure the surface quality, improve the machining efficiency and reduce the rejection rate of the machining process. [ABSTRACT FROM AUTHOR]

The paper presents a flexible system for extracting features and creating training and test examples for solving the all-words sense disambiguation (WSD) task. The system allows integrating word and sense embeddings as part of an example description. The system possesses two unique features distinguishing it from all similar WSD systems—the ability to construct a special compressed representation for word embeddings and the ability to construct training and test sets of examples with different data granularity. The first feature allows generation of data sets with quite small dimensionality, which can be used for training highly accurate classifiers of different types. The second feature allows generating sets of examples that can be used for training classifiers specialized in disambiguating a concrete word, words belonging to the same part-of-speech (POS) category or all open class words. Intensive experimentation has shown that classifiers trained on examples created by the system outperform the standard baselines for measuring the behaviour of all-words WSD classifiers. [ABSTRACT FROM AUTHOR]

Distributed Denial of Service (DDoS) has developed multiple variants, one of which is Distributed Reflective Denial of Service (DRDoS). With the increasing number of Internet of Things (IoT) devices, the threat of DRDoS attack is growing, and the damage of a DRDoS attack is more destructive than other types. The existing DDoS detection methods cannot be generalized in DRDoS early detection, which leads to heavy load or degradation of service when deployed at the final point. In this paper, we propose a DRDoS detection and defense method based on deep forest model (DDDF), and then we integrate differentiated service into defense model to filter out DRDoS attack flow. Firstly, from the statistics perspective on different stages of DRDoS attack flow in the big data environment, we extract a host-based DRDoS threat index (HDTI) from the network flows. Secondly, using the HDTI feature we build a DRDoS detection and defense model based on the deep forest, which consists of 1 extreme gradient boost (XGBoost) forest estimator, 2 random forest estimators, and 2 extra random forest estimators in each layer. Lastly, the differentiated service procedure applies the detection result from DDDF to drop the traffic identified in different stages and different detection points. Theoretical analysis and experiments show that the method we proposed can effectively identify DRDoS attack with higher detection rate and a lower false alarm rate, the defense model also shows distinguishing ability to effectively eliminate the DRDoS attack flows, and dramatically mitigate the damage of a DRDoS attack. [ABSTRACT FROM AUTHOR]