Path recommendation is an essential application in people’s daily life. However, drivers’ experience hidden in their driving history and their personal preferences are less considered in path planning. In this paper...
详细信息
ISBN:
(纸本)9781665442084
Path recommendation is an essential application in people’s daily life. However, drivers’ experience hidden in their driving history and their personal preferences are less considered in path planning. In this paper we propose a dynamic time-constrained path recommendation method, utilizing the historical GPS trajectory information and user preferences. First, based on graph entropy, critical intersections are extracted from trajectory information to simplify the road network structure. Then the time-dependent mostly chosen path (TDMCP) is obtained by trajectories processing to determine the time-varying paths between critical intersections. Thus the original complex road network is abstracted as a search subnet. Finally we propose an improved dynamic A* search (IDAS) on the search sub-net to find the candidate paths satisfying the time-constraints, and further allow users to set personal preferences to select the final optimal path. The proposed method is validated on the real-world data set, and the result shows that the proposed method surpasses the competing ones especially on long distance path recommendation.
With the expansion of network scale, traditional routing strategies in Software-Defined Networking (SDN) have difficulty adapting to fast traffic variability. The large flow in the network occupies 80% of the network ...
详细信息
With the expansion of network scale, traditional routing strategies in Software-Defined Networking (SDN) have difficulty adapting to fast traffic variability. The large flow in the network occupies 80% of the network traffic. An unreasonable schedule of the large flow will lead to the emergence of bottleneck links and reduce the network performance. To solve the above problems, this paper proposes a different routing method, called Routing Strategy for SDN Large Flow Based on Deep Reinforcement Learning (RSDRL). Considering the links in the network that can carry large flow are limited, RSDRL can schedule large flow firstly and generate routing strategies adaptively. At the same time, in order to avoid the occurrence of congestion, RSDRL quantifies the degree of congestion in the network to implement routing. Experiments show that the proposed model has better Quality of service (QoS) performance under the test traffic, realizing a reasonable schedule of traffic.
Evolutionary multitasking algorithms use information exchange among individuals in a population to solve multiple optimization problems simultaneously. Negative transfer is a critical factor that affects the performan...
详细信息
Traffic matrix is the main research object of traffic prediction in software-defined networking. Accurate and timely traffic matrix prediction plays an important role in avoiding network congestion. While various meth...
详细信息
Traffic matrix is the main research object of traffic prediction in software-defined networking. Accurate and timely traffic matrix prediction plays an important role in avoiding network congestion. While various methods have been proposed in previous studies to solve the SDN traffic prediction problem, few of them consider both inter- and intra-flow features. In this paper, we propose a dual-stage attention based Traffic Prediction method for the SDN traffic matrix prediction task. First, our method uses temporal pattern attention as the inter-flow attention mechanism before the encoding stage to realize adaptive feature extraction. Then, temporal attention is introduced as the intra-flow attention mechanism before the decoding stage to capture long-term temporal dependencies. Finally, we use the autoregressive module to handle the highly dynamic SDN traffic volume. Experimental results show that our proposed SDN traffic prediction method can capture more traffic features and improve the SDN traffic matrix prediction performance to some extent.
Nowadays, large numbers of smart sensors(e.g., road-side cameras) which communicate with nearby base stations could launch distributed denial of services(DDoS) attack storms in intelligent transportation systems. DDoS...
详细信息
Nowadays, large numbers of smart sensors(e.g., road-side cameras) which communicate with nearby base stations could launch distributed denial of services(DDoS) attack storms in intelligent transportation systems. DDoS attacks disable the services provided by base stations. Thus in this paper, considering the uneven communication traffic flows and privacy preserving, we give a hidden Markov model-based prediction model by utilizing the multi-step characteristic of DDoS with a federated learning framework to predict whether DDoS attacks will happen on base stations in the future. However, in the federated learning,we need to consider the problem of poisoning attacks due to malicious participants. The poisoning attacks will lead to the intelligent transportation systems paralysis without security protection. Traditional poisoning attacks mainly apply to the classification model with labeled data. In this paper, we propose a reinforcement learning-based poisoning method specifically for poisoning the prediction model with unlabeled data. Besides, previous related defense strategies rely on validation datasets with labeled data in the server. However, it is unrealistic since the local training datasets are not uploaded to the server due to privacy preserving, and our datasets are also unlabeled. Furthermore, we give a validation dataset-free defense strategy based on Dempster–Shafer(D–S) evidence theory avoiding anomaly aggregation to obtain a robust global model for precise DDoS prediction. In our experiments, we simulate 3000 points in combination with DARPA2000 dataset to carry out evaluations. The results indicate that our poisoning method can successfully poison the global prediction model with unlabeled data in a short time. Meanwhile, we compare our proposed defense algorithm with three popularly used defense algorithms. The results show that our defense method has a high accuracy rate of excluding poisoners and can obtain a high attack prediction probability.
Source location is an interesting topic in the field of swarm ***-source location is a vital branch of *** with a single-source location problem,the main difficulty for the multi-source location lies in that the numbe...
详细信息
Source location is an interesting topic in the field of swarm ***-source location is a vital branch of *** with a single-source location problem,the main difficulty for the multi-source location lies in that the number and distribution of sources are *** Swarm Optimizer(PSO) has been widely adopted for the single-source location ***,its performance deteriorates greatly when it faces multiple sources because it is designed to find the single global best solution,not multiple *** handle such a challenge,a virtual source mechanism is proposed to help PSO overcome this *** key idea of the virtual source mechanism is to divide the search area into multiple cells,each of which has a virtual *** virtual source leads the swarm to cover each cell such that particles can cover all cells in a search space before they *** results demonstrate that the virtual source mechanism-based PSO effectively locates multiple sources.
Extreme Multi-label text Classification ( XMC) is a task of recalling the most relevant labels for each given text from an extremely large-scale label set. It is emphasized that XMC is a more complex classification ta...
详细信息
ISBN:
(纸本)9781665480468
Extreme Multi-label text Classification ( XMC) is a task of recalling the most relevant labels for each given text from an extremely large-scale label set. It is emphasized that XMC is a more complex classification task because there are two main problems: large space of labels and the labels in XMC tasks tend to be correlated. Existing methods attempt to model label correlations by viewing the XMC task as a sequence generation problem however they still suffer from (1) using the slow serial decoding strategy where labels are predicted one-by-one. (2) needing to compare a mass of label ordering strategies in the decoding stage to achieve satisfied accuracy. In this work, we propose LAbel Mask-Predicted Transformer (LAMPT) to address the both issues, which is a novel non-autoregressive generation model that (1) enriches the input raw text representation with the additional label features by fully exploiting the label dependencies, (2) allows for efficient parallel decoding thanks to its non-autoregressive decoding formulation and mask-prediced training strategy. Experimental results demonstrate that single model performance is substantially enhanced by LAMPT. On a Wiki dataset with thirty-one thousand labels, LAMPT-XLNet accuracy has gained 1.6% relative improvement on P@3 over the LightXML-XLNet. Also, the P@1 of ensemble LAMPT is 90.00%, a significant i mprovement over the state-of-the-art ensemble LightXML (transformer-based) and AttentionXML (LSTM-based), which achieve 89.45% and 87.47%, respectively.
In this response letter, we focus on addressing Yu Hang Yang's comments so that the correctness and validity of the proposed auxiliary-differential-equation-based (ADE) Crank-Nicolson finite-difference time-domain...
详细信息
In this paper, the problem of remote state estimation is investigated for a class of complex networks with noisy wireless communication channels. The employment of the binary encoding scheme allows for the description...
详细信息
In this paper,the finite time cluster consensus(FnTCC) of fractional-order multi-agent systems(FOMAS)with directed topology is *** fractional-order system is converted into an integer-order system by defining a neighb...
详细信息
In this paper,the finite time cluster consensus(FnTCC) of fractional-order multi-agent systems(FOMAS)with directed topology is *** fractional-order system is converted into an integer-order system by defining a neighborhood-based error variable,and suitable control rules are designed for the obtained first-order multi-agent *** to the exponential finite-time stability theorem,suitable Lyapunov functions are ***,the settling time function is *** simulation results prove the feasibility and validity of our theory.
暂无评论