Online Feature Transformation Learning for Cross-Domain Object Category Recognition

Online Unsupervised Domain Adaptation via Reducing Inter- and Intra-Domain Discrepancies

Unsupervised domain adaptation (UDA) transfers knowledge from a labeled source domain to an unlabeled target domain on cross-domain object recognition by reducing a distribution discrepancy between the source and target domains (interdomain discrepancy). Prevailing methods on UDA were presented based on the premise that target data are collected in advance. However, in online scenarios, the target data often arrive in a streamed manner, such as visual image recognition in daily monitoring, which means that there is a distribution discrepancy between incoming target data and collected target data (intradomain discrepancy). Consequently, most existing methods need to re-adapt the incoming data and retrain a new model on online data. This paradigm is difficult to meet the real-time requirements of online tasks. In this study, we propose an online UDA framework via jointly reducing interdomain and intradomain discrepancies on cross-domain object recognition where target data arrive in a streamed manner. Specifically, the proposed framework comprises two phases: classifier training and online recognition phases. In the former, we propose training a classifier on a shared subspace where there is a lower interdomain discrepancy between the two domains. In the latter, a low-rank subspace alignment method is introduced to adapt incoming data to the shared subspace by reducing the intradomain discrepancy. Finally, online recognition results can be obtained by the trained classifier. Extensive experiments on DA benchmarks and real-world datasets are employed to evaluate the performance of the proposed framework in online scenarios. The experimental results show the superiority of the proposed framework in online recognition tasks.

Lane Position Detection Based on Long Short-Term Memory (LSTM)

Accurate detection of lane lines is of great significance for improving vehicle driving safety. In our previous research, by improving the horizontal and vertical density of the detection grid in the YOLO v3 (You Only Look Once, the 3th version) model, the obtained lane line (LL) algorithm, YOLO v3 (S × 2S), has high accuracy. However, like the traditional LL detection algorithms, they do not use spatial information and have low detection accuracy under occlusion, deformation, worn, poor lighting, and other non-ideal environmental conditions. After studying the spatial information between LLs and learning the distribution law of LLs, an LL prediction model based on long short-term memory (LSTM) and recursive neural network (RcNN) was established; the method can predict the future LL position by using historical LL position information. Moreover, by combining the LL information predicted with YOLO v3 (S × 2S) detection results using Dempster Shafer (D-S) evidence theory, the LL detection accuracy can be improved effectively, and the uncertainty of this system be reduced correspondingly. The results show that the accuracy of LL detection can be significantly improved in rainy, snowy weather, and obstacle scenes.

Online Nash-optimization tracking control of multi-motor driven load system with simplified RL scheme

Although the optimal tracking control problem (OTCP) has been addressed recently, only the single-input system is considered in the recent literature. In this paper, the OTCP of unknown multi-motor driven load systems (MMDLS) is addressed based on a simplified reinforcement learning (RL) structure, where all the motor inputs with different dynamics will be obtained as a Nash equilibrium. Thus, the performance indexes associated with each input can be optimized as an outcome of a Nash equilibrium. Firstly, we use an identifier to reconstruct MMDLS dynamics, such that the accurate model required in the general control design is avoided. We use the identified dynamics to drive Nash-optimization inputs, which include the steady-state controls and the RL-based controls. The steady-state controls are designed with the identified system model. The RL-based controls are designed using the optimization method with the simplified RL-based critic NN schemes. We use the simplified RL structures to approximate the cost function of each motor input in the optimal control design. The NN weights of both the identified algorithm and simplified RL-based structure are approximated by using a novel adaptation algorithm, where the learning gains can be optimized adaptively. The weight convergences and the Nash-optimization MMDLS stability are all proved. Finally, numerical MMDLS simulations are implemented to show the correctness and the improved performance of the proposed methods.

12-h abstinence-induced functional connectivity density changes and craving in young smokers: a resting-state study

Studying the neural correlates of craving to smoke is of great importance to improve treatment outcomes in smoking addiction. According to previous studies, the critical roles of striatum and frontal brain regions had been revealed in addiction. However, few studies focused on the hub of brain regions in the 12 h abstinence induced craving in young smokers. Thirty-one young male smokers were enrolled in the present study. A within-subject experiment design was carried out to compare functional connectivity density between 12-h smoking abstinence and smoking satiety conditions during resting state in young adult smokers by using functional connectivity density mapping (FCDM). Then, the functional connectivity density changes during smoking abstinence versus satiety were further used to examine correlations with abstinence-induced changes in subjective craving. We found young adult smokers in abstinence state (vs satiety) had higher local functional connectivity density (lFCD) and global functional connectivity density (gFCD) in brain regions including striatal subregions (i.e., bilateral caudate and putamen), frontal regions (i.e., anterior cingulate cortex (ACC) and orbital frontal cortex (OFC)) and bilateral insula. We also found higher lFCD during smoking abstinence (vs satiety) in bilateral thalamus. Additionally, the lFCD changes of the left ACC, bilateral caudate and right OFC were positively correlated with the changes in craving induced by abstinence (i.e., abstinence minus satiety) in young adult smokers. The present findings improve the understanding of the effects of acute smoking abstinence on the hubs of brain gray matter in the abstinence-induces craving and may contribute new insights into the neural mechanism of abstinence-induced craving in young smokers in smoking addiction.

A Fast Learning Method for Accurate and Robust Lane Detection Using Two-Stage Feature Extraction with YOLO v3

To improve the accuracy of lane detection in complex scenarios, an adaptive lane feature learning algorithm which can automatically learn the features of a lane in various scenarios is proposed. First, a two-stage learning network based on the YOLO v3 (You Only Look Once, v3) is constructed. The structural parameters of the YOLO v3 algorithm are modified to make it more suitable for lane detection. To improve the training efficiency, a method for automatic generation of the lane label images in a simple scenario, which provides label data for the training of the first-stage network, is proposed. Then, an adaptive edge detection algorithm based on the Canny operator is used to relocate the lane detected by the first-stage model. Furthermore, the unrecognized lanes are shielded to avoid interference in subsequent model training. Then, the images processed by the above method are used as label data for the training of the second-stage model. The experiment was carried out on the KITTI and Caltech datasets, and the results showed that the accuracy and speed of the second-stage model reached a high level.

Distributed zero-sum differential game for multi-agent systems in strict-feedback form with input saturation and output constraint

This paper investigates the distributed differential game tracking problem for nonlinear multi-agent systems with output constraint under a fixed directed graph. Each follower can be taken as strict-feedback structure with uncertain nonlinearities and input saturation. Firstly, by utilizing the command filtered backstepping technique, the distributed tracking control problem of multi-agent systems in strict-feedback form can be transformed into an equivalent distributed differential game problem of tracking error dynamics in affine form by designing a distributed feedforward tracking controller, in which neural networks (NNs) and the auxiliary system are introduced to deal with the unknown nonlinearities and input saturation, respectively. Especially, a novel barrier Lyapunov function (BLF) is firstly introduced to tackle with the output constraint. Subsequently, by using adaptive dynamic programming (ADP) technique, the distributed zero-sum differential game strategy is derived, in which a critic network is constructed to approximate the cooperative cost function online with a novel updating law. Therefore, the whole distributed control scheme not only guarantees the closed-loop signals to be cooperatively uniformly ultimately bounded (CUUB), but also ensures the cooperative cost function to be minimized. Meanwhile, the output constraint and input saturation are not violated. Finally, simulation results demonstrate the effectiveness of the proposed method.

Simulation of knock probability in an internal combustion engine

In spark-ignition internal combustion engines, fluctuations of the in-cylinder pressure trace and the tendency of combustion knock are usually different from one cycle to another. These cycle-to-cycle variations are affected by the initial state at ignition time and the subsequent burning. The occurrence of the phenomena is unpredictable, and their stochastic nature offers challenges in the optimization of engine control strategies. In this paper, a simulator providing a series of cycle-to-cycle varied in-cylinder pressures is introduced. The Wiebe function and Livengood-Wu integration are used to describe the determinacy of combustion. Various means, including the Markov chain, are introduced to express the stochastic quantities during combustion. In addition, the combustion of a given knock probability is simulated.