As one popular modeling approach for end-to-end speech recognition, attention-based encoder-decoder models are known to suffer the length bias and corresponding beam problem. Different approaches have been applied in ...
详细信息
Dear editor,Although face-sketch synthesis generates a sketch from a given face photo automatically [1], it is an open research problem in computer vision [2–4]. Recently, several deep neural network (DNN)methods for...
详细信息
Dear editor,Although face-sketch synthesis generates a sketch from a given face photo automatically [1], it is an open research problem in computer vision [2–4]. Recently, several deep neural network (DNN)methods for face-sketch synthesis have been proposed with considerable results.
To encourage intra-class compactness and inter-class separability among trainable feature vectors, large-margin softmax methods are developed and widely applied in the face recognition community. The introduction of t...
详细信息
Neural translation models have proven to be effective in capturing sufficient information from a source sentence and generating a high-quality target sentence. However, it is not easy to get the best effect for bidire...
详细信息
A cascaded speech translation model relies on discrete and non-differentiable transcription, which provides a supervision signal from the source side and helps the transformation between source speech and target text....
详细信息
Current pre-trained language models (PLM) are typically trained with static data, ignoring that in real-world scenarios, streaming data of various sources may continuously grow. This requires PLMs to integrate the inf...
详细信息
Flying ad hoc networks (FANETs) have particular importance in various military and civilian applications due to their specific features, including frequent topological changes, the movement of drones in a three-dimens...
详细信息
Prediction models are popular in medical research and practice. By predicting an outcome of interest for specific patients, these models may help inform difficult treatment decisions, and are often hailed as the poste...
详细信息
Nowadays, the use of drones as a fundamental element of smart cities has attracted the attention of many researchers to monitor and control the traffic of vehicles. Because of the high flexibility of multi-drone syste...
详细信息
Nowadays, the use of drones as a fundamental element of smart cities has attracted the attention of many researchers to monitor and control the traffic of vehicles. Because of the high flexibility of multi-drone systems, like flying ad hoc networks (FANETs), they provide various services and improve modern life in smart cities. However, due to the unique features of FANET, especially the high speed of drones and rapid changes in network topology, communication reliability is a serious challenge in this network. Hence, traditional routing protocols, such as optimized link state routing (OLSR) scheme, cannot work well in these networks. In this paper, a smart filtering-based adaptive optimized link state routing (SFA-OLSR) scheme is proposed in FANETs. To increase adaptability to the FANET environment, SFA-OLSR provides a new solution to adjust the hello broadcast period so that each flying node specifies its broadcast period based on a new scale called cosine similarity between real and predicted positions. Furthermore, in SFA-OLSR, each flying node develops a filtering algorithm based on two parameters, namely link lifetime and remaining energy. The purpose of this algorithm is to reduce the size of the single-hop neighboring set of each flying node and minimize the search space when finding multi-point relays (MPRs). This increases the convergence speed of the algorithm. Then, SFA-OLSR exploits the sparrow search algorithm (SSA) to single out the best MPRs. This algorithm introduces a multi-objective function by focusing on three components, including energy, link lifespan, and neighbor degree. Lastly, the simulation process of SFA-OLSR is performed by the NS3 simulator. This process evaluates the performance of the proposed method and three schemes, namely Gangopadhyay et al., P-OLSR, and OLSR-ETX. These evaluations show that SFA-OLSR has a good performance in terms of three scales, namely packet delivery ratio, delay, and throughput, but its overhead is more than
Due to the progress of unmanned aerial vehicles (UAVs), this new technology is widely applied in military and civilian areas. Multi-UAV networks are often known as flying ad hoc networks (FANETs). Due to these applica...
详细信息
Due to the progress of unmanned aerial vehicles (UAVs), this new technology is widely applied in military and civilian areas. Multi-UAV networks are often known as flying ad hoc networks (FANETs). Due to these applications, FANET must ensure communication stability and have high scalability. These goals are achieved by presenting clustering techniques in FANETs. However, the characteristics of these networks, like high-mobility nodes, limited energy, and dynamic topology, have created great challenges in two important processes of clustering protocols, namely cluster construction and the selection of cluster heads. In this paper, an intelligent clustering scheme based on the whale optimization algorithm called ICW is suggested in flying ad hoc networks. Firstly, each UAV specifies its hello interval based on the lifespan of adjacent links to guarantee the adaptability of ICW to FANET. Then, a centralized clustering process is done using a whale optimization algorithm (WOA) to find the best cluster centers on the network. To determine the membership of each UAV in a cluster, ICW employs a new criterion, i.e. closeness ratio, so that each UAV joins a cluster with the best closeness ratio. In addition, the evaluation of each whale is carried out based on a fitness function, consisting of three components, namely the number of isolated clusters, the ratio of inter-cluster distance to intra-cluster distance, and cluster size. Then, a cluster head is selected for each cluster based on a score value. This score is dependent on the weighted sum of four metrics, namely remaining energy, the average link lifespan between each UAV and its neighbors, neighbor degree, and the average distance between each UAV and its neighbors. In the last step, two routing processes, namely intra-cluster routing and inter-cluster routing, are introduced in FANET. Then, the evaluation and implementation of ICW is performed through the NS2 simulator. After completing the simulation process, ICW i
暂无评论