Gender classification from speech using convolutional networks augmented with synthetic spectrograms

Synthetic Bone Marrow Smears Are a Privacy-Preserving Substitute for Developing Accurate Leukemia Classification Models in Hematological Microscopy

This work focuses on automatic gender and age prediction tasks from handwritten documents. This problem is of interest in a variety of fields, such as historical document analysis and forensic investigations. The challenge for automatic gender and age classification can be demonstrated by the relatively low performances of the existing methods. In addition, despite the success of CNN for gender classification, deep neural networks were never applied for age classification. The published works in this area mostly concentrate on English and Arabic languages. In addition to Arabic and English, this work also considers Hebrew, which was much less studied. Following the success of bilinear Convolutional Neural Network (B-CNN) for fine-grained classification, we propose a novel implementation of a B-CNN with ResNet blocks. To our knowledge, this is the first time the bilinear CNN is applied for writer demographics classification. In particular, this is the first attempt to apply a deep neural network for the age classification. We perform experiments on documents from three benchmark datasets written in three different languages and provide a thorough comparison with the results reported in the literature. B-ResNet was top-ranked in all tasks. In particular, B-ResNet outperformed other models on KHATT and QUWI datasets on gender classification.

Crop yield estimation and prediction constitutes a key issue in agricultural management, particularly under the context of demographic pressure and climate change. Currently, the main challenge in estimating crop yields based on remotely sensed data and data-driven methods is how to cope with small datasets and the limited amount of annotated samples. In order to cope with small datasets and the limited amount of annotated samples and improve the accuracy of winter wheat yield estimation in the Guanzhong Plain, PR China, this study proposed a method of combining generative adversarial networks (GANs) and convolutional neural network (CNN) for comprehensive growth monitoring of winter wheat, in which the remotely sensed leaf area index (LAI), vegetation temperature condition index (VTCI) and meteorological data at four growth stages of winter wheat during 2012–2017 were generated as the inputs of multi-layer convolutional neural networks (CNNs), and GAN was employed to artificially increase the number of training samples. Then, a linear regression model between the simulated comprehensive growth monitoring (I) and the measured yields was established to estimate yields of winter wheat in the Guanzhong Plain pixel by pixel. The final results showed when GAN was used to double the size of the training samples, and the simulation values obtained by CNN based on augmented samples using GAN provided a better training (R2 = 0.95, RMSE = 0.05), validation (R2 = 0.54, RMSE = 0.16) and testing (R2 = 0.50, RMSE = 0.14) performance than that just using the original samples. The achieved best pixel-scale yield estimation accuracy of winter wheat (R2 = 0.50, RMSE = 591.46 kg/ha) in the Guanzhong Plain. These results showed that small samples can be enlarged by GAN, thus, more important features for reflecting the growth conditions and yields of winter wheat from the remotely sensed indices and meteorological indices can be extracted, and indicated that CNN accompanied with GAN could contribute a lot to the comprehensive growth monitoring and yield estimation of winter wheat and data augmentation methods are extremely useful for the application of small samples in deep learning.

Generative models have been applied in many fields and can be evaluated with many methods. In the evaluation of generative models, the proper evaluation metric varies with the application field. Therefore, the evaluation of generative adversarial networks is inherently challenging. In this study, conditional deep convolutional generative adversarial networks were applied in mechanical fault diagnosis and then evaluated. We proposed three evaluation metrics of conditional deep convolutional generative adversarial networks: Jensen-Shannon divergence, kernel maximum mean discrepancy, and the 1-nearest neighbor classifier which were used to distinguish generated samples from real samples, test mode collapsing and detect overfitting based on the dataset of Electronic Engineering Laboratory of Case Western Reserve University and the planetary gearbox dataset measured in the laboratory. The Jensen-Shannon divergence could not well distinguish generated samples from real samples. However, the two metrics (maximum mean discrepancy and 1-nearest neighbor classifier) well-distinguished generated samples from real samples, thus verifying the applicability of conditional deep convolutional generative adversarial networks in the field of mechanical diagnosis.

Generative adversarial networks (GANs) have shown striking performances in computer vision applications to augment virtual training samples (VTS). However, the VTS generating by GANs in the context of hyperspectral image classification suffer from structural inconsistency due to the insufficient number of training samples in order to learn high-order features from the discriminator. This work addresses the scarcity of training samples by designing a GAN, in which the performance of discriminator is improved to produce more structurally coherent VTS. In the proposed method, by splitting the discriminator into two parts, GAN undertakes two tasks: the main task is to learn to distinguish between real and fake samples, and the auxiliary task is to learn to distinguish structurally corrupted and real samples. With this setup, GAN will produce real-like VTS with a higher variation than conventional GAN. Furthermore, in order to reduce the computational cost, subspace-based dimension reduction was performed to obtain the dominant features around the training samples to generate meaningful patterns from the original ones to be used in the learning phase. Based on the experimental results on real, and well-known hyperspectral benchmark images, the proposed method improves the performance compared with GANs-related, and conventional data augmentation strategies <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> .

paper, we focus on exploring the relationship between weave patterns and their mechanical properties in woven fiber composites through Machine Learning. Specifically, we explore the interactions between woven architectures and in-plane stiffness properties through Deep Convolutional Neural Network (DCNN) and Generative Adversarial Network (GAN). Our research is important for exploring how woven composite’s pattern is related to its mechanical properties and accelerating woven composite design as well as optimization. We focus on two tasks: (1) Stiffness prediction: Predicting in-plane stiffness properties for given weave patterns. Our DCNN extracts high-level features through several convolutional and fully connected layers to determine the final predictions. (2) Weave pattern prediction: Predicting weave patterns for target stiffness properties, which can be treated as the reverse task of the first one. Due to many-to-one mapping between weave patterns and the composite properties, we utilize a Decoder Neural Network as our baseline model and compare its performance with GAN and Genetic Algorithm. We represent the weave patterns as 2D checkerboard models and use finite element analysis (FEA) to determine in-plane stiffness properties, which serve as input data for our ML framework. We show that: (1) for stiffness prediction, DCNN can predict stiffness values for a given weave pattern with relatively high accuracy (above 93%); (2) for weave pattern prediction, the GAN model gives the best prediction accuracy (above 92%) while Decoder Neural Network has the best time efficiency. HAOTIAN FENG

The understanding of rock characteristic and fluid flow behavior at the near-wellbore region is an important topic. Triaxial experiment setup can help to investigate these properties. In this research, a new triaxial experimental setup has been developed where the higher scale of the parameters such as higher reservoir pressure, and comparatively larger core sample can be used. High permeable synthetic porous samples are prepared to validate the device. The new triaxial experimental setup is validated with water as a base fluid. In the validation test, real samples and synthetic samples are used. First, flow in convergent direction is studied which represents as production at the in-situ condition. Then, the flow in divergent direction is examined that may represent the injection of fluid to enhance the hydrocarbon production. The near-wellbore flow phenomena are studied with real and synthetic samples. The results indicate that using this triaxial setup pressure drop and pressure buildup test can be explained. The new scientific setup is able to reduce the scale-up gap between laboratory data and field data to get actual reservoir flow phenomena.

Brain tumors are formed due to the abnormal growth of the cells that get multiplied and become in uncontrollable perspective. Tumors can damage brain cells by pressing down the skull, which consociate begins in, which negatively affects human health. In advanced stages, a brain tumor is a more dangerous infection that cannot be relieved. Brain tumor detection and early prevention are necessary in today's world. An extreme learning machine (ELM) is a widely adopted algorithm in machine learning. It is proposed to use classification models in brain tumor imaging. This classification is based on the techniques implemented: Convolutional Neural Networks(CNN) and Generative Adversarial Networks(GAN). CNN efficiently solves the convex optimization problem and is faster, requiring less human effort. The algorithmic architecture of GAN uses two neural networks, pocking one against the other. These networks are implemented in various fields to classify brain Tumor images. The present study mainly aims to introduce a new proposed classification system of preschool children brain imaging with Hybrid Convolutional Neural Networks and with the techniques of GAN. The proposed technique is compared with the existing hybrid-CNN and hybrid-GAN techniques. The outcomes are encouraging because the loss is deduced, and the accuracy facet increases. The proposed system achieved a training accuracy of 97.8% and a validation accuracy of 89%. The outcomes of the studies show that ELM in the platform of GAN for preschool children brain imaging classification has achieved higher predictive performance than the traditional classification mechanisms in increasingly complex scenarios. Time elapsed for training brain images samples finds inference value for training samples and time elapsed value increased by 28.9855%. Approximation ratio for cost based on probability, finding Approximation ratio for low probability range is increased by 88.1%. The combination of CNN, GAN and hybrid-CNN, hybrid-GAN, and hybrid CNN + GAN, compared with the proposed hybrid system, increased Detection latency for low range learning rate by 3.31%.

In recent years, advances in image restoration have prominently featured Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs).Specifically, in seismic image denoising, the DnCNN model, rooted in CNN, employs residual learning combined with batch normalization for a streamlined approach to denoising.Alternatively, SRGAN, leveraging GAN and super-resolution techniques, trains its generative model using a perceptual loss function, accentuating perceptual disparities between generated and authentic images to boost visual quality.Recognizing the importance of preserving salient seismic data, the Constrained-DnCNN model has been introduced, refining seismic data interpretation.Additionally, the CR-SRGAN model, targeting super-resolution of artifacts and color restoration, deviates from conventional training datasets acquired via high-resolution image interpolation and downsampling.Upon comparative analysis, the DCGAN, amalgamating features of CNN and GAN, stands out for harnessing CNN's robust feature extraction.This bolsters the model's capacity to adeptly fit real data distributions.DCGAN's potential spans aspects like multimodal fusion, model interpretability, trustworthiness, and image restoration quality, marking it a promising research avenue.

In the present report we evaluate the possible utility of the Generative Adversarial Networks (GANs) in mapping the chemical structural space for molecular property profiles, with the goal of subsequently yielding synthetic (artificial) samples for ligand-based molecular modeling. Two case studies are considered: BACE-1 (β-Secretase 1) and DENV (Dengue Virus) inhibitory activities, with the former focused on data populating and the latter on data balancing tasks. We train GANs using subsamples extracted from datasets for each bioactivity endpoint, and apply the trained networks in generating synthetic examples from the respective bioactivity chemical spaces. Original and synthetic samples are pooled together and employed to build BACE-1 and DENV inhibitory activity classifiers and their performance evaluated over tenfold external validation sets. In both case studies, the obtained classifiers demonstrate satisfactory predictivity with the former yielding accuracy (ACC) and Mathew's correlation coefficient (MCC) values of 0.80 and 0.59, while the latter produces balanced accuracy(BACC) and MCC values of 0.81 and 0.70, respectively. Moreover, the statistics of these classifiers are compared with those of other models in the literature demonstrating comparable to better performance. These results suggest that GANs may be useful in mapping the chemical space for molecular property profiles of interest, and thus allow for the extraction of synthetic examples for computational modeling.

The speech emotion recognition based on the deep networks on small samples is often a very challenging problem in natural language processing. The massive parameters of a deep network are much difficult to be trained reliably on small-quantity speech samples. Aiming at this problem, we propose a new method through the systematical cooperation of Generative Adversarial Network (GAN) and Long Short Term Memory (LSTM). In this method, it utilizes the adversarial training of GAN’s generator and discriminator on speech spectrogram images to implement sufficient sample augmentation. A six-layer convolution neural network (CNN), followed in series by a two-layer LSTM, is designed to extract features from speech spectrograms. For accelerating the training of networks, the parameters of discriminator are transferred to our feature extractor. By the sample augmentation, a well-trained feature extraction network and an efficient classifier could be achieved. The tests and comparisons on two publicly available datasets, i.e., EMO-DB and IEMOCAP, show that our new method is effective, and it is often superior to some state-of-the-art methods.

Prior work by a subset of authors led to a development of optical camera platform, which has a capability of distinguishing between human and animal movement in an outdoor environment. Once the image is classified as a human, an idea of providing additional information and insights led to the exploration of gender (men vs women) and direction (left to right vs right to left) classifications. The proposed method classifies the human gender, based on the full body image oriented in a side view manner. An additional feature is to classify the direction of the movement. In the current paper, the Convolutional Neural Networks (CNNs) are used to distinguish between men and women gender classes and to identify the direction of the movement. Furthermore, different aspects of CNN are visualized (for example, attention heat maps, t-Distributed Stochastic Neighbor Embedding plot, etc.) to provide useful insights corresponding to classifications and misclassifications. Additionally, different CNN architectures were tried to figure out the best possible choice. The classification accuracies for gender (men vs women) and direction classification (left to right vs right to left) on the test data are close to 93.3% and 94%, respectively.

Thanks to the availability of large-scale data, deep Convolutional Neural Networks (CNNs) have witnessed success in various applications of computer vision. However, the performance of CNNs on Synthetic Aperture Radar (SAR) image classification is unsatisfactory due to the lack of well-labeled SAR data, as well as the differences in imaging mechanisms between SAR images and optical images. Therefore, this paper addresses the problem of SAR image classification by employing the Generative Adversarial Network (GAN) to produce more labeled SAR data. We propose special GANs for generating SAR images to be used in the training process. First, we incorporate the quadratic operation into the GAN, extending the convolution to make the discriminator better represent the SAR data; second, the statistical characteristics of SAR images are integrated into the GAN to make its value function more reasonable; finally, two types of parallel connected GANs are designed, one of which we call PWGAN, combining the Deep Convolutional GAN (DCGAN) and Wasserstein GAN with Gradient Penalty (WGAN-GP) together in the structure, and the other, which we call CNN-PGAN, applying a pre-trained CNN as a discriminator to the parallel GAN. Both PWGAN and CNN-PGAN consist of a number of discriminators and generators according to the number of target categories. Experimental results on the TerraSAR-X single polarization dataset demonstrate the effectiveness of the proposed method.

Text sentiment analysis is one of the most important tasks in the field of public opinion monitoring, service evaluation and satisfaction analysis under network environments. Compared with the traditional Natural Language Processing analysis tools, convolution neural networks can automatically learn useful features from sentences and improve the performance of the affective analysis model. However, the original convolution neural network model ignores sentence structure information which is very important for text sentiment analysis. In this paper, we add piece-wise pooling to the convolution neural network, which allows the model to obtain the sentence structure. And the main features of different sentences are extracted to analyze the emotional tendencies of the text. At the same time, the user’s feedback involves many different fields, and there is less labeled data. In order to alleviate the sparsity of the data, this paper also uses the generative adversarial network to make common feature extractions, so that the model can obtain the common features associated with emotions in different fields, and improves the model’s Generalization ability with less training data. Experiments on different datasets demonstrate the effectiveness of this method.

From real–time tumor classification to operative outcome prediction, applications of machine learning to neurosurgery are powerful. However, the translation of many of these applications are restricted by the lack of “big data” in neurosurgery. Important restrictions in patient privacy and sharing of imaging data reduce the diversity of the datasets used to train resulting models and therefore limit generalizability. Synthetic learning is a recent development in machine learning that generates synthetic data from real data and uses the synthetic data to train downstream models while preserving patient privacy. Such an approach has yet to be successfully demonstrated in the spine surgery domain. Spine radiographs were collected from the VinDR–SpineXR dataset, with 1470 labeled as abnormal and 2303 labeled as normal. A conditional generative adversarial network (GAN) was trained on the radiographs to generate a spine radiograph and normal/abnormal label. A modified conditional GAN (SpineGAN) was trained on the same task. A convolutional neural network (CNN) was trained using the real data to label abnormal radiographs. A CNN was trained to label abnormal radiographs using synthetic images from the GAN and in a separate experiment from SpineGAN. Using the real radiographs, an AUC of 0.856 was achieved in abnormality classification. Training on synthetic data generated by the standard GAN (AUC of 0.814) and synthetic data generated by our SpineGAN (AUC of 0.830) resulted in similar classifier performance. SpineGAN generated images with higher FID and lower precision scores, but with higher recall and increased performance when used for synthetic learning. The successful application of synthetic learning was demonstrated in the spine surgery domain for the classification of spine radiographs as abnormal or normal. A modified domain–relevant GAN is introduced for the generation of spine images, evidencing the importance of domain–relevant generation techniques in synthetic learning. Synthetic learning can allow neurosurgery to use larger and more diverse patient imaging sets to train more generalizable algorithms with greater patient privacy.