Recognition Model Training Research Articles

Spoofing attack recognition for GNSS-based train positioning using a BO-LightGBM method.

Trustworthy positioning is critical in the operational control and management of trains. For a train positioning system (TPS) based on a global navigation satellite system (GNSS), a spoofing attack significantly threatens the trustworthiness of positioning. However, the influence and recognition of GNSS spoofing attacks are not considered in the existing research on GNSS-enabled TPS. Spoofing attacks affect the performance of GNSS observations and the positioning results, allowing the development of data-driven spoofing recognition solutions. This study aims to achieve effective spoofing recognition for active security protection in TPS. Different features were designed to reflect the effects of a spoofing attack, including GNSS observation-related indicators and odometer-enabled parameters, and a novel Bayesian optimization-light gradient boosting machine (BO-LightGBM) solution was proposed. In particular, a Bayesian optimization technique was introduced into the LightGBM framework to improve the hyperparameter determination capability for recognition model training. Using a GNSS spoofing test platform with a specific GNSS signal generator and the SimSAFE spoofing test tool, different spoofing attack modes were tested to collect sample datasets for model training and evaluation. The results of model establishment and comparison of the model performance indicators illustrated the advantages of the proposed solution, its adaptability to different spoofing attack situations, and its superiority over state-of-the-art modeling strategies.

A Low-Cost Inertial Measurement Unit Motion Capture System for Operation Posture Collection and Recognition.

In factories, human posture recognition facilitates human-machine collaboration, human risk management, and workflow improvement. Compared to optical sensors, inertial sensors have the advantages of portability and resistance to obstruction, making them suitable for factories. However, existing product-level inertial sensing solutions are generally expensive. This paper proposes a low-cost human motion capture system based on BMI 160, a type of six-axis inertial measurement unit (IMU). Based on WIFI communication, the collected data are processed to obtain the displacement of human joints' rotation angles around XYZ directions and the displacement in XYZ directions, then the human skeleton hierarchical relationship was combined to calculate the real-time human posture. Furthermore, the digital human model was been established on Unity3D to synchronously visualize and present human movements. We simulated assembly operations in a virtual reality environment for human posture data collection and posture recognition experiments. Six inertial sensors were placed on the chest, waist, knee joints, and ankle joints of both legs. There were 16,067 labeled samples obtained for posture recognition model training, and the accumulated displacement and the rotation angle of six joints in the three directions were used as input features. The bi-directional long short-term memory (BiLSTM) model was used to identify seven common operation postures: standing, slightly bending, deep bending, half-squatting, squatting, sitting, and supine, with an average accuracy of 98.24%. According to the experiment result, the proposed method could be used to develop a low-cost and effective solution to human posture recognition for factory operation.

Towards comprehensive understanding of pedestrians for autonomous driving: Efficient multi-task-learning-based pedestrian detection, tracking and attribute recognition

Safe interaction with pedestrians is important for autonomous vehicles in urban environments. Comprehensive understanding of pedestrian behavior is a challenge for autonomous driving, as different pedestrian attributes have different characteristics and there is not yet a dataset providing all attribute labels. In this paper, we design an efficient multi-task model for pedestrian detection, tracking and attribute recognition to fully mine information in multiple tasks and multiple datasets to reduce redundant image processing computation. Multiple training datasets are utilized to take full advantage of the available partially-labeled data. The model consists of two stages. The first stage is to detect and track pedestrians, using only low-resolution images to save computational resources. Accurate pedestrian detection is achieved in the bird's-eye-view (BEV), while pedestrian tracking is implemented on the basis of 3D bounding boxes. The second stage is image-based multi-attribute detection. This stage uses the detection and tracking results and some pre-processed information from the first stage along with high-resolution images. Multi-attributes of the pedestrian are identified, such as pedestrian's pose, age, gender, and motion direction. With a carefully-designed multi-task system that shares necessary feature maps among multiple tasks and reuses computation results, we can solve pedestrian detection, tracking, and multi-attribute recognition problems in an efficient framework. This leads to more accurate decisions and more efficient computations. The innovation of the model is to accomplish a simultaneous detection of multiple pedestrian attributes for autonomous driving, while fully sharing the features in the model to avoid repeated computation, as well as utilizing multiple partially-labeled datasets for the pedestrian detection, tracking and attribute recognition model training.

VGNet: A Lightweight Intelligent Learning Method for Corn Diseases Recognition

The automatic recognition of crop diseases based on visual perception algorithms is one of the important research directions in the current prevention and control of crop diseases. However, there are two issues to be addressed in corn disease identification: (1) A lack of multicategory corn disease image datasets that can be used for disease recognition model training. (2) The existing methods for identifying corn diseases have difficulty satisfying the dual requirements of disease recognition speed and accuracy in actual corn planting scenarios. Therefore, a corn diseases recognition system based on pretrained VGG16 is investigated and devised, termed as VGNet, which consists of batch normalization (BN), global average pooling (GAP) and L2 normalization. The performance of the proposed method is improved by using transfer learning for the task of corn disease classification. Experiment results show that the Adam optimizer is more suitable for crop disease recognition than the stochastic gradient descent (SGD) algorithm. When the learning rate is 0.001, the model performance reaches a highest accuracy of 98.3% and a lowest loss of 0.035. After data augmentation, the precision of nine corn diseases is between 98.1% and 100%, and the recall value ranges from 98.6% to 100%. What is more, the designed lightweight VGNet only occupies 79.5 MB of space, and the testing time for 230 images is 75.21 s, which demonstrates better transferability and accuracy in crop disease image recognition.

Automatic generation of artificial images of leukocytes and leukemic cells using generative adversarial networks (syntheticcellgan)

Background and objectives: Visual analysis of cell morphology has an important role in the diagnosis of hematological diseases. Morphological cell recognition is a challenge that requires experience and in-depth review by clinical pathologists. Within the new trend of introducing computer-aided diagnostic tools in laboratory medicine, models based on deep learning are being developed for the automatic identification of different types of cells in peripheral blood. In general, well-annotated large image sets are needed to train the models to reach a desired classification performance. This is especially relevant when it comes to discerning between cell images in which morphological differences are subtle and when it comes to low prevalent diseases with the consequent difficulty in collecting cell images. The objective of this work is to develop, train and validate SyntheticCellGAN (SCG), a new system for the automatic generation of artificial images of white blood cells, maintaining morphological characteristics very close to real cells found in practice in clinical laboratories. Methods: SCG is designed with two sequential generative adversarial networks. First, a Wasserstein structure is used to transform random noise vectors into low resolution images of basic mononuclear cells. Second, the concept of image-to-image translation is used to build specific models that transform the basic images into high-resolution final images with the realistic morphology of each cell type target: 1) the five groups of normal leukocytes (lymphocytes, monocytes, eosinophils, neutrophils and basophils); 2) atypical promyelocytes and hairy cells, which are two relevant cell types of complex morphology with low abundance in blood smears. Results: The images of the SCG system are evaluated with four experimental tests. In the first test we evaluated the generated images with quantitative metrics for GANs. In the second test, morphological verification of the artificial images is performed by expert clinical pathologists with 100% accuracy. In the third test, two classifiers based on convolutional neural networks (CNN) previously trained with images of real cells are used. Two sets of artificial images of the SCG system are classified with an accuracy of 95.36% and 94%, respectively. In the fourth test, three CNN classifiers are trained with artificial images of the SCG system. Real cells are identified with an accuracy ranging from 87.7% to 100%. Conclusions: The SCG system has proven effective in creating images of all normal leukocytes and two low-prevalence cell classes associated with diseases such as acute promyelocyte leukemia and hairy cell leukemia. Once trained, the system requires low computational cost and can help augment high-quality image datasets to improve automatic recognition model training for clinical laboratory practice.

Research on Fruit Recognition and Positioning Based on you only look once version4 (YOLOv4)

The recognition and spatial coordinate positioning is an important part of picking equipment of fruits. This paper introduced a method of target detection and pixel learning positioning of fruits based on the Darknet depth framework YOLOv4. We utilized GPU training in Ubuntu 19.10, and used 2000 images of various fruits as the training set for recognition model training, and performed and verified tests in the GPU environment. The results showed that the accuracy of fruit recognition is above 94%, the detection time of a single image is 12.3ms, and the detection rate of the video is 17f/s. The actual test showed that the system has good stability, real-time performance, and correctness of picking objects.

LDGAN: A Synthetic Aperture Radar Image Generation Method for Automatic Target Recognition

Under the framework of a supervised learning-based automatic target recognition (ATR) approach, recognition performance is primarily dependent on the amount of training samples. However, shortage in training samples is a consistent issue for ATR. In this article, we propose a new image to image generation method, called label-directed generative adversarial networks (LDGANs), which will provide labeled samples to be used for recognition model training. We define an entirely new loss function for the LDGAN, which utilizes the Wasserstein distance to replace the original distance measurement of the conventional generative adversarial networks (GANs), thus efficiently avoiding the collapse mode problem. The label information is also added to the loss function of the LDGAN to avoid generating a large number of unlabeled target images. More importantly, the proposed method also makes corresponding changes to the network architecture regarding the new GANs. At the same time, the detailed algorithm about the LDGAN is also introduced in this article to deal with the issue that characteristically GANs are not easy to train. Based on comparisons with other directed generation methods, the experimental results show comparative results of several types of generated images in statistical features, gradient features, classic features of synthetic aperture radar (SAR) targets and the independence from the real image. While demonstrating that the images generated by the LDGAN produced better results using the assumptions of independent and identical distribution, the experiment also explores the performance of the generated image in the ATR. A comparison of these experimental results demonstrates a better way to use the generated image for ATR. The experimental results also prove that the proposed method does have the ability to supplement information for ATR when the training sample information is insufficient.

Rapid Diagnosis of Normal and Abnormal Conditions in Solid-State Fermentation of Bioethanol Using Fourier Transform Near-Infrared Spectroscopy

Rapid diagnosis of normal and abnormal fermentation conditions in solid-state fermentation (SSF) of bioethanol is crucial to process and quality controls. The Fourier transform near-infrared (FT-NIR) spectroscopy analysis technique combined with pattern recognition methods was employed to monitor fermentation conditions (i.e., normal and abnormal) in this study. To achieve optimum performance in identification of fermentation conditions, linear discriminant analysis (LDA), K-nearest neighbors (KNN), and support vector machine (SVM) classifications were employed to construct the recognition models. The optimization of arithmetical parameters and number of principal components (PCs) were implemented simultaneously using leave-one-out cross-validation (LOOCV) during the recognition model training phase. The results of this study revealed that the SVM model presented better performance compared to the other two models, and the best SVM recognition model was finally established by use of four PCs. The SVM mode...

Seismic classification-based method for recognizing epicenter-neighboring orbits

From the point of view of the Fourth Paradigm, this paper attempts to find a recognizing method based on DEMETER (Detection of Electro-Magnetic Emissions Transmitted from Earthquake Regions) satellite data for epicenter-neighboring orbits during strong shocks. Detection points or small regions are used as research objects in numerous studies on seismic activities recognition. Due to the infrequency of strong shocks, the number of non-seismic data is far larger than the abnormal one, which results in the underfitting during the training of recognition model. Additionally, data located along the edge of seismic regions can hardly be classified into abnormal dataset or non-seismic one. A sloppy classification can badly reduce the accuracy of model. Hence, it is desired to put forward a more suitable approach to make better use of original data. In this paper, a seismic classification-based method for recognizing epicenter-neighboring orbit is proposed to address these problems. Unlike the existing approaches, our method regards the satellite orbits as the analyzing objects, which avoids the underfitting performance caused by the unbalanced data distribution. Moreover, error correcting output coding (ECOC) strategy is utilized to transform the recognizing problem into a series of binary classifications. By means of safe semi-supervised support vector machines (S4VMs) with kernel combination, the unlabeled orbits help obtain a better classification performance. Finally, three groups of comprehensive experiments are applied to validate the effectiveness of the method.

Signal conditioned minimum error rate training for continuous speech recognition

Hierarchical signal bias removal (HSBR) signal conditioning (26) uses a codebook (28) constructed from the set of recognition models (34). HSBR signal conditioning and recognition model training may be based on the same set of recognition model parameters and provides a reduction in recognition errors.