The Neural Networks (NN) model which is incorporated in the control system design has been studied, and the results show better performance than the mathematical model approach. However, some studies consider that onl...
详细信息
This paper presents a novel algorithm for reachability analysis of nonlinear discrete-time systems. The proposed method combines constrained zonotopes (CZs) with polyhedral relaxations of factorable representations of...
详细信息
ISBN:
(数字)9798350316339
ISBN:
(纸本)9798350316346
This paper presents a novel algorithm for reachability analysis of nonlinear discrete-time systems. The proposed method combines constrained zonotopes (CZs) with polyhedral relaxations of factorable representations of nonlinear functions to propagate CZs through nonlinear functions, which is normally done using conservative linearization techniques. The new propagation method provides better approximations than those resulting from linearization procedures, leading to significant improvements in the computation of reachable sets in comparison to other CZ methods from the literature. Numerical examples highlight the advantages of the proposed algorithm.
The implementation of Gated Recurrent Neural Networks (GRU) to generate background music (BGM) combines deep learning technology with music that is used for the visual content of a commercial or educational. Indeed, t...
The implementation of Gated Recurrent Neural Networks (GRU) to generate background music (BGM) combines deep learning technology with music that is used for the visual content of a commercial or educational. Indeed, this BGM is necessary to enhance the intended message expressed to the other audience. This work aimed to provide the model network of GRU which is based on RNN to generate multi-label genres of music by using the open source of GTZAN to evaluate the new BGM. Our GRU networks can solve the vanishing gradient problem by utilizing both the reset gate and the update gate on the network. In the results, we achieved a new BGM that synchronized with the human mood which made more variety of sounds.
A meta-optic platform for accelerating object classification is demonstrated. End-to-end design is used to co-optimize the optical and digital systems resulting in high-speed classifiers that are demonstrated for hand...
详细信息
In this paper, we propose a novel approach to locate and detect moving pedestrians in a video. Our proposed method first locates the region of interest (ROI) using a background subtraction algorithm based on guided fi...
详细信息
Quantum illumination (QI) provides entanglement-enabled target-detection enhancement, despite operating in an entanglement-breaking environment. Existing experimental studies of QI have utilized a Bayesian approach, a...
详细信息
Cortical visual prostheses are designed to treat blindness by restoring visual perceptions through artificial electrical stimulation of the primary visual cortex (V1). Intracortical microelectrodes produce the smalles...
Cortical visual prostheses are designed to treat blindness by restoring visual perceptions through artificial electrical stimulation of the primary visual cortex (V1). Intracortical microelectrodes produce the smallest visual percepts and thus higher resolution vision - like a higher density of pixels on a monitor. However, intracortical microelectrodes must maintain a minimum spacing to preserve tissue integrity. One solution to increase the density of percepts is to implant and stimulate multiple visual areas, such as V1 and V2, although the properties of microstimulation in V2 remain largely unexplored. We provide a direct comparison of V1 and V2 microstimulation in two common marmoset monkeys. We find similarities in response trends between V1 and V2 but differences in threshold, neural activity duration, and spread of activity at the threshold current. This has implications for using multi-area stimulation to increase the resolution of cortical visual prostheses.
In this paper, a method using deep reinforcement learning is proposed to deal with the 3D online bin packing problem. The packing objects are not limited to several specific or fixed cuboid objects, but are composed o...
In this paper, a method using deep reinforcement learning is proposed to deal with the 3D online bin packing problem. The packing objects are not limited to several specific or fixed cuboid objects, but are composed of more than a thousand objects and randomly generated cuboids, which make the trained policy network can handle novel unknown objects. In addition, the posture of the object in the box can be any angle, not limited to horizontal and vertical. In the proposed method, four voxel maps are used as inputs, and a Soft Actor-Critic (SAC) algorithm is used to train a policy network. On the other hand, in order to deal with various objects with irregular shapes, a packing task simulator with physics engine enable the policy network to learn the state of falling and stacking objects. In terms of training environment of deep reinforcement learning, the proposed method can be applied to boxes of different sizes because of the scalable image information. Moreover, a reward function and a training strategy with gradually increasing difficulty are proposed to effectively improve the learning of policy network. In terms of experimental results, the results on a random object bin packing task in a simulator illustrate the effectiveness of the proposed method.
The placement of distributed generation (DG) units in power systems is an efficient way for energy loss reduction, especially when the penetration of DG in modern systems is growing due to their impacts on environment...
详细信息
The placement of distributed generation (DG) units in power systems is an efficient way for energy loss reduction, especially when the penetration of DG in modern systems is growing due to their impacts on environmental sustainability. On the other hand, load variations and methods of electricity consumption affect energy losses amount. Therefore, power demand variations have an essential role in the determination of energy loss amount and optimal generation of DG. However, considering the variability of load level in the DG allocation problem increases the burden and computational time, and neglecting it causes the energy losses to be calculated inaccurately. Therefore, this paper aims to evaluate the effect of load patterns on renewable DG allocation plans in order to find out the importance of considering load variations in energy loss minimization via DG placement. The analysis has been conducted on 7-, 12-, 16-, 28-, 30-, 33-, 59-, 69-, 70-, 84-, and 119-bus distribution systems by a classic optimization tool named AMPL.
As the complexity of tasks addressed through reinforcement learning (RL) increases, the definition of reward functions also has become highly complicated. We introduce an RL method aimed at simplifying the reward-shap...
详细信息
暂无评论