Search

Weakly supervised semantic segmentation with only image-level labels is an essential application since it reduces the considerable human effort to fully annotate image. Most state-of-the-art methods take into account discriminative regions or prior knowledge (called seeds) by applying the recent Classification Activation Maps (CAM) methods. As seeds used in the CAM methods could be considered as segmentation knowledge, increasing seeds will naturally improve the performance of the CAM methods. We treat such task as a seed exploration with clustering learning, which is different from the current methods in which region mining or seeds learning are performed in an end-to-end learning manner. In this paper, we propose a progressive framework containing autoencoders to explore numerous and accurate seeds to further improve the performance of CAM methods. Our explored seeds can replace the initial seeds, and thus, they can be integrated with current weakly supervised semantic segmentation methods for performance improvement. We show experimentally that our provided seeds lead to better model training. As a result, we obtain performance improvement from corresponding counterparts to reach 68.1 and 69.2% mIoU on PASCAL VOC 2012 validation and test dataset, respectively. [ABSTRACT FROM AUTHOR]

Electronic throttle valves are electromechanical systems which regulate the air flow inside gasoline engines. The objective of electronic throttle valve control is to ensure fast and accurate reference tracking of the valve plate angle. This control demands are hard to accomplish since the plant is burdened with strong nonlinear effects and parameters uncertainty. In this paper, a genetic algorithm-based adaptive fuzzy sliding mode controller (AFSMC) is proposed for an electronic throttle considering actuator nonlinearities. In the AFSMC approach, fuzzy logic system is applied to approximate the plant model and the actuator model, the sliding mode controller makes full use of the plant model to guarantee robust control even in the presence of parameters uncertainty, and genetic algorithm is developed to search the optimal control gains values of the AFSMC. The performance of the AFSMC is verified by computer simulation and experiment. [ABSTRACT FROM AUTHOR]

Recently, the application of the maintenance transmission line robot has been very popular in the power industry. However, difficulties in the control of maintenance transmission line robot exist due to multiple nonlinearities, plant parameter variations and external disturbances. This paper investigates the possibility of using neural network as a promising self-learning control alternative for the control problem of inspection and deicing transmission line robot. We first discuss the mechanical structure, as well as dynamic model of a deicing robot. And then, a neural network-based self-learning control strategy consists of a fuzzy neural network controller and an ELM-based single-layer-feedback neural networks identifier are proposed for this deicing transmission line robot. Both the structure and the learning algorithm of the control system are presented. The proposed controller is verified by computer simulations and experiments. [ABSTRACT FROM AUTHOR]

Artificial neural network training algorithms aim to optimize the network parameters regarding the pre-defined cost function. Gradient-based artificial neural network training algorithms support iterative learning and have gained immense popularity for training different artificial neural networks end-to-end. However, training through gradient methods is time-consuming. Another family of training algorithms is based on the Moore–Penrose inverse, which is much faster than many other gradient methods. Nevertheless, most of those algorithms are non-iterative and thus do not support mini-batch learning in nature. This work extends two non-iterative Moore–Penrose inverse-based training algorithms to enable online sequential learning: a single-hidden-layer autoencoder training algorithm and a sub-network-based classifier training algorithm. We further present an approach that uses the proposed autoencoder for self-supervised dimension reduction and then uses the proposed classifier for supervised classification. The experimental results show that the proposed approach achieves satisfactory classification accuracy on many benchmark datasets with extremely low time consumption (up to 50 times faster than the support vector machine on CIFAR 10 dataset). [ABSTRACT FROM AUTHOR]

Experimental results on five public gene expression profile datasets verify that the proposed algorithm outperforms other methods in terms of diversity, distribution stability, and quality of generated samples. The fifth paper by I Tingyu Ye i et al. on "Artificial bee colony algorithm with an adaptive search manner and dimension perturbation" proposes a modified artificial bee colony (ABC) algorithm with an adaptive search manner and dimension perturbation (ASDABC). The tenth paper by I Fei Han i et al. on "Gene-CWGAN: A Data Enhancement Method for Gene Expression Profile Based on Improved CWGAN-GP" tackles the problem of high dimension and small sample size of gene expression profile data classification. [Extracted from the article]

How to ensemble the high representative ability for discriminating the target from its background and high adaptive ability to fast appearance changes, while keeping the real-time performance simultaneously is still an open topic in the field of object tracking, especially in the complex urban traffic scenes. To address this issue, motivated by that existing excellent trackers may have their advantages in tackling different kinds of tracking difficulties respectively, we propose a new real-time stage-wise object tracking method that allows different trackers to complement each other and combines their respective advantages. A tracker selection agent is trained to learn the policy of switching to the most appropriate candidate tracker according to the current tracking environment. To capture the dynamics of tracking environment effectively, we consider the tracker selection problem as a Partially Observable Markov Decision Process problem. A lightweight deep neural network with the recurrent unit is designed for learning the optimal policy accurately and rapidly. We also elaborately collected Traffic Scenes Object Tracking Annotated Dataset (TS-OTAD) for demonstrating the effectiveness of our method. Experimental results conducted on TS-OTAD and OTB-100 demonstrate that our method has superior performance than any of the candidate tracker and has a good trade-off between accuracy and efficiency compared with other state-of-the-art methods. Besides, our stage-wise tracking framework is not limited to any specific tracker, and any excellent tracker can be used as the candidate, which provides a new way for boosting object tracking accuracy and efficiency. [ABSTRACT FROM AUTHOR]

The electronic throttle control (ETC) for a gasoline engine is a typical nonlinear plant because of its nonlinear spring and model-parameter changes caused by external environmental variables. In this paper, a fuzzy proportional-integral-derivative (PID) control strategy is proposed in order to improve the responsiveness of ETC. In the fuzzy-PID scheme, the input variables are the error signal and its derivative, and the output variable is PID gains expressed in terms of fuzzy rules. In this manner, the fuzzy-PID controller has more flexibility and capability than conventional ones. A novel technique to tune the fuzzy rules of fuzzy-PID controller is proposed using a harmony search algorithm, which can search the optimal PID gains for the plant. Simulation and experiment results have shown the effective performance of the proposed controller. [ABSTRACT FROM AUTHOR]