Search

Summary: One of the best methods for estimating the softmax layer in neural network language models is the noise‐contrastive estimation (NCE) method. However, this method is not proper for word embedding applications compared with some other robust methods such as the negative sampling (NEG) method. The NEG method implements the pointwise mutual information (PMI) relation between the word‐context space in the neural network, and the NCE method implements conditional probability. Both the NCE and NEG methods use dot‐product‐based mapping to map words and contexts vector to the probabilities. This article presents the parametric objective function, which uses the mapping function as the parameter. Also, we obtained a parametric relation between word‐context space according to the mapping parameter. Using the parametric objective function, we identify conditions for a mapping that make it a proper selection for both softmax estimation and word embedding. The article also presents two specific mapping functions with the required conditions, and we compared their performance with that of the dot‐product mapping function. The performance of the new mapping functions is also reported over common word embedding and language models' benchmarks. [ABSTRACT FROM AUTHOR]

In this paper, distributed heterogeneous wireless networks are studied and a spectrum access scheme that fairly allocates channels among users based on their request levels is investigated. To be closer to what happens in practice, users' request levels to have different priorities are also considered, i.e. some packets are more important for the user to be transmitted than the others. Due to the distributed nature of the problem and since users are not able to coordinate with each other before transmission, a scheme based on reinforcement learning is proposed in which the network state is estimated based on the previous successful transmissions of packets in the network. The reinforcement learning method's adaptive nature lets our method work in heterogeneous settings where there exist users with other medium access control protocols. The performance of the proposed scheme is evaluated in different network settings, and it is shown that it tries to implement a fair spectrum access policy (considering the packets' priorities) while maximising the total throughput of the network. [ABSTRACT FROM AUTHOR]

The first step of secure communication is authenticating users and detecting malicious ones. In recent years, some promising schemes have been proposed using wireless medium network's features, in particular, channel state information (CSI) as a means of authentication. These schemes mainly compare the user's previous CSI with the new received CSI to determine if the user is what it is claiming to be. Despite high accuracy, these approaches lack the stability in authentication when the users rotate in their positions. It is due to the significant change in CSI when a user rotates, which misleads the authenticator when it compares the new CSI with the previous ones. Our approach presents a way of extracting features from raw CSI measurements, which are stable with respect to rotation. We employ a deep neural network to extract these features. We also present a scenario in which users can be efficiently authenticated while they are at specific locations in an environment (even if they rotate) and will be rejected if they change their location. In addition, experimental results are presented to show the performance of the proposed scheme. [ABSTRACT FROM AUTHOR]

For gathering data in a crowdsensing network, we need to support the connectivity of a massive number of low power devices. In this paper, a new multiple access technique is proposed for such networks with a large number of devices/sensors/users where we have taken advantage of the fact that these devices usually do not become active at the same time, which we refer to as sparse activation property. In this scheme, each device uses a specific spreading code which is changing at symbol level. Symbol‐level change of the spreading code and the random nature of user activation are the two building blocks that provide opportunistic low interference between data transmitted by devices, which are activated in a specific time slot. We also discuss how the proposed scheme can be used in grant free schemes which eliminate the need for heavy signaling before data transmission. The performance of the proposed scheme has been evaluated in different scenarios, and the block error rates are compared with a few other multiple access schemes. [ABSTRACT FROM AUTHOR]