FPGA-based implementation of classification techniques: A survey

Recently, a number of classification techniques have been introduced. However, processing large dataset in a reasonable time has become a major challenge. This made classification task more complex and expensive in calculation. Thus, the need for solutions to overcome these constraints such as field programmable gate arrays (FPGAs). In this paper, we give an overview of the various classification techniques. Then, we present the existing FPGA based implementation of these classification methods. After that, we investigate the confronted challenges and the optimizations strategies. Finally, we highlight the hardware accelerator architectures and tools for hardware design suggested to improve the FPGA implementation of classification methods.     

BE-ACGAN: Photo-realistic residual bit-depth enhancement by advanced conditional GAN

Since more demands for high quality visualization have been raised in various fields, monitors with higher bit-depth (HBD) become popular in recent years. However, most digital images are at low bit-depth (LBD) and usually of low visual quality with annoying false contours when displayed on HBD monitors directly. To reconstruct visually pleasant HBD images, many bit-depth enhancement (BE) algorithms have been proposed from various aspects, but the recovered HBD images are usually unsatisfactory with conspicuous false contours or over-blurred textures. Inspired by discriminative learning, we propose a residual BE algorithm based on advanced conditional generative adversarial network (BE-ACGAN), in which the discriminator adversarially helps assess image quality and train the generator to achieve more photo-realistic recovery performance. Besides, since it is hard to distinguish between the reconstructed and real HBD images with similar structures, the discriminator takes residual images as input and further takes LBD images as conditions to achieve more reliable performance. In addition, we present a novel loss function to deal with the difficulty of unstable adversarial training. The proposed algorithm outperforms the state-of-the-art methods on large-scale benchmark datasets. Source codes are available at https://github.com/TJUMMG/BE- ACGAN/.     

Input-to-state learning of recurrent neural networks with delay and disturbance

This article deals with the issue of input-to-state stabilization for recurrent neural networks with delay and external disturbance. The goal is to design a suitable weight-learning law to make the considered network input-to-state stable with a predefined -gain. Based on the solution of linear matrix inequalities, two schemes for the desired learning law are presented via using decay-rate-dependent and decay-rate-independent Lyapunov functionals, respectively. It is shown that, in the absence of external disturbance, the proposed learning law also guarantees the exponential stability of the network. To illustrate the applicability of the present weight-learning law, two numerical examples with simulations are given.     

Machine Learning-Based Two-Stage Data Selection Scheme for Long-Term Influenza Forecasting

One popular strategy to reduce the enormous number of illnesses and deaths from a seasonal influenza pandemic is to obtain the influenza vaccine on time. Usually, vaccine production preparation must be done at least six months in advance, and accurate long-term influenza forecasting is essential for this. Although diverse machine learning models have been proposed for influenza forecasting, they focus on short-term forecasting, and their performance is too dependent on input variables. For a country’s long-term influenza forecasting, typical surveillance data are known to be more effective than diverse external data on the Internet. We propose a two-stage data selection scheme for worldwide surveillance data to construct a long-term forecasting model for influenza in the target country. In the first stage, using a simple forecasting model based on the country’s surveillance data, we measured the change in performance by adding surveillance data from other countries, shifted by up to 52 weeks. In the second stage, for each set of surveillance data sorted by accuracy, we incrementally added data as input if the data have a positive effect on the performance of the forecasting model in the first stage. Using the selected surveillance data, we trained a new long-term forecasting model for influenza and perform influenza forecasting for the target country. We conducted extensive experiments using six machine learning models for the three target countries to verify the effectiveness of the proposed method. We report some of the results.     

Image-Based Lifelogging: User Emotion Perspective

Lifelog is a digital record of an individual’s daily life. It collects, records, and archives a large amount of unstructured data; therefore, techniques are required to organize and summarize those data for easy retrieval. Lifelogging has been utilized for diverse applications including healthcare, self-tracking, and entertainment, among others. With regard to the image-based lifelogging, even though most users prefer to present photos with facial expressions that allow us to infer their emotions, there have been few studies on lifelogging techniques that focus upon users’ emotions. In this paper, we develop a system that extracts users’ own photos from their smartphones and configures their lifelogs with a focus on their emotions. We design an emotion classifier based on convolutional neural networks (CNN) to predict the users’ emotions. To train the model, we create a new dataset by collecting facial images from the CelebFaces Attributes (CelebA) dataset and labeling their facial emotion expressions, and by integrating parts of the Radboud Faces Database (RaFD). Our dataset consists of 4,715 high-resolution images. We propose Representative Emotional Data Extraction Scheme (REDES) to select representative photos based on inferring users’ emotions from their facial expressions. In addition, we develop a system that allows users to easily configure diaries for a special day and summaize their lifelogs. Our experimental results show that our method is able to effectively incorporate emotions into lifelog, allowing an enriched experience.     

Prediction of rockhead using a hybrid N-XGBoost machine learning framework

The spatial information of rockhead is crucial for the design and construction of tunneling or underground excavation. Although the conventional site investigation methods (i.e. borehole drilling) could provide local engineering geological information, the accurate prediction of the rockhead position with limited borehole data is still challenging due to its spatial variation and great uncertainties involved. With the development of computer science, machine learning (ML) has been proved to be a promising way to avoid subjective judgments by human beings and to establish complex relationships with mega data automatically. However, few studies have been reported on the adoption of ML models for the prediction of the rockhead position. In this paper, we proposed a robust probabilistic ML model for predicting the rockhead distribution using the spatial geographic information. The framework of the natural gradient boosting (NGBoost) algorithm combined with the extreme gradient boosting (XGBoost) is used as the basic learner. The XGBoost model was also compared with some other ML models such as the gradient boosting regression tree (GBRT), the light gradient boosting machine (LightGBM), the multivariate linear regression (MLR), the artificial neural network (ANN), and the support vector machine (SVM). The results demonstrate that the XGBoost algorithm, the core algorithm of the probabilistic N-XGBoost model, outperformed the other conventional ML models with a coefficient of determination (R²) of 0.89 and a root mean squared error (RMSE) of 5.8 m for the prediction of rockhead position based on limited borehole data. The probabilistic N-XGBoost model not only achieved a higher prediction accuracy, but also provided a predictive estimation of the uncertainty. Thus, the proposed N-XGBoost probabilistic model has the potential to be used as a reliable and effective ML algorithm for the prediction of rockhead position in rock and geotechnical engineering.     

Actuator fault estimation based on generalized learning observer for quasi-linear parameter varying systems

This article presents a generalized learning observer (GLO) design for the simultaneous estimation of states and actuator faults for polytopic quasi-linear parameter varying systems. The proposed approach is based on the use of a GLO, which generalized the existing results on the proportional-integral observers. Conditions of existence and stability of the observer are given through the stability analysis in the sense of Lyapunov. Its design is obtained in terms of a set of linear matrix inequalities. The performance of the proposed method is evaluated by simulation in a one-link-flexible joint robot system.