No abstract

Autonomous driving scenarios face the need for millisecond real-time response, which has led to the study of mobile networks with high speed and ultra-low latency. Software-defined networking (SDN) is recognized as a key technology for next-generation networks because it contains advanced functions such as centralized control, software-based traffic analysis, and forwarding rules for dynamic updates. In this paper, an SDN with flexible architecture is considered and a transport component is proposed. The component based on mesh topology is an example of joint route prediction and forwarding. First, different from existing transport protocols, the component can adopt a software-defined stream access control strategy that includes an extended forwarding mechanism (retransmission) to improve the shortterm response performance. Second, we evaluate the impact of route prediction on transport network performance by using offline training and prediction. The key challenge here is that a suitable model needs to be trained from a limited training sample dataset, which will dynamically update the forwarding rules based on current and historical facts (network data). By introducing a parallel neural network classifier, an intelligent route arrangement is implemented in this work. Experimental results over different traffic patterns verify the advantages of the design. Not only does it enhance the flexibility of SDN, but it also significantly reduces the signaling overhead of the transport network without reducing the network throughput.INDEX TERMS SDN, traffic control, routing, machine learning, prediction.

At present, speech recognition has become a key technology of human-computer interaction, which can be used in semantic recognition and speaker identification and other related applications. This paper focuses on a speaker identification scene and the technical design. Because artificial neural network has the ability to distinguish complex classification boundaries, plenty of work on speech recognition had studied multi-layer perceptual networks to improve the accuracy of classification where back propagation method (BP algorithm) has been used. In the studied scheme, when the test objects (speakers) speak the same isolated word, the identification system can judge who the speaker is by identifying the voice voiceprint of different people. Our design not only considers the recognition based on BP as well as its variant, but also explores the voiceprint recognition based on convolution neural network (CNN). Secondly, the network structure and performance are also compared in detail.

No abstract

We first review the literature on machine behavior which may contain the interaction between machines, and then discuss the methodology and the related case involving collaboration between robots to instantiate the concept with AI empowerment. The navigation case aims to a security application with autonomous control and roadside agent embedded in a mobile edge computing structure. In the studied navigation based on the artificial potential field method, robots need to use position information to calculate the moving direction frequently. In the case of high motion speed as well as GPS positioning error, the path trajectory may show a sharp change of direction. In order to mitigate the trajectory oscillation, this paper proposes a path planning design where training process and motion direction prediction are integrated by using artificial neural network. The auxiliary navigation agent near multiple obstacles can first extract the past movement information of the robot and then determines whether there is a serious path jitter event. Computer simulation analysis shows that the combination of autonomous control and cooperative behavior can effectively reduce the path jitter so as to achieve a fast and safe path planning.