Hierarchical text classification (HTC) is essential for various real applications. However, HTC models are challenging to develop because they often require processing a large volume of documents and labels with hierarchical taxonomy. Recent HTC models based on deep learning have attempted to incorporate hierarchy information into a model structure. Consequently, these models are challenging to implement when the model parameters increase for a large-scale hierarchy because the model structure depends on the hierarchy size. To solve this problem, we formulate HTC as a sub-hierarchy sequence generation to incorporate hierarchy information into a target label sequence instead of the model structure. Subsequently, we propose the Hierarchy DECoder (HiDEC), which decodes a text sequence into a sub-hierarchy sequence using recursive hierarchy decoding, classifying all parents at the same level into children at once. In addition, HiDEC is trained to use hierarchical path information from a root to each leaf in a sub-hierarchy composed of the labels of a target document via an attention mechanism and hierarchy-aware masking. HiDEC achieved state-of-the-art performance with significantly fewer model parameters than existing models on benchmark datasets, such as RCV1-v2, NYT, and EURLEX57K.

In this paper, two dimensional (2D) target location is estimated in the passive coherent location (PCL) system in noisy and cluttered environment. Compared to the conventional filter based target estimation schemes that require a prior information of target dynamics, the proposed target estimation scheme does not require that information and can track a target with various movements, such as maneuvering or non-maneuvering target, using a grid point (GP)-based estimation method. Bistatic range sum (BRS) measurements from all receivers are combined and processed for target estimation, but some of them are reflected by clutters rather than a target, degrading estimation accuracy. To tackle this problem, the proposed scheme first eliminates â€false†clutter-reflected BRS measurements by taking multiple time measurements into account. Then, a successive GP update scheme is applied for the remaining sets of BRS measurement, and candidate target locations are determined as a result. In the last step, a soft decision method is applied to determine the target location from the candidates. Simulation results show that our proposed target estimation scheme can track a target with various movements, especially highly-maneuvering target, despite the lack of prior knowledge of target dynamics.

Passive Coherent Location (PCL) system is a field of radar systems that exploits non-cooperative illuminator of opportunity to detect and track a target. Due to bistatic configuration of PCL system, the locations of transmitter and receiver with respect to a target are important to target estimation accuracy. In this paper, we propose a receiver selection algorithm that utilizes the Position Dilution of Precision (PDOP) to estimate a single target location. Previous works utilize the PDOP to select the optimal receiver, but require comparison of all possible combinations of transmitter and receiver, limiting real-time target estimation. On the other hands, our proposed receiver selection algorithm lowers the computational complexity based on the optimal receiver configuration derived from the PDOP. Once receivers are selected, Extended Kalman Filter (EKF) is used to correct the estimation errors. Simulation results demonstrate that performance of the proposed algorithm is comparable with that of the exhaustive search that provides optimal receiver selection.

This paper studies a secure communication over multiple-input multiple-output multi-antenna eavesdropper (MIMOME) channels which consist of legitimate parities, namely a transmitter and receiver, equipped with multi-antennas and a passive eavesdropper with multi-antennas. For securing the communication between the legitimate parties, we consider an artificial noise (AN) scheme in which the legitimate transmitter sends its secret messages and AN signal together. Meanwhile, it is assumed that the legitimate receiver has a full-duplex capability which enables it to capture the secret message from the transmitter and simultaneously generate a jamming signal to strengthen security. While there have been studies on similar setups, most of them focus on the design of the jamming signal with the assumption of full channel-state information (CSI) and/or system parameter optimization based on numerical evaluations. On the contrary, in this work, we instead introduce a tight lower bound on an achievable ergodic secrecy rate as a versatile analytic tool and derive a closed-form expressions for the bound. To confirm the analytic results, we carry out numerical evaluations of the ergodic secrecy rate which are compared with the proposed lower bound.

We present a secret key agreement (SKA) protocol for a multi-user time-division duplex system where a base-station (BS) with a large antenna array (LAA) shares secret keys with users in the presence of non-colluding eavesdroppers. In the system, when the BS transmits random sequences to legitimate users for sharing common randomness, the eavesdroppers can attempt the pilot contamination attack (PCA) in which each of eavesdroppers transmits its target user's training sequence in hopes of acquiring possible information leak by steering beam towards the eavesdropper. We show that there exists a crucial complementary relation between the received signal strengths at the eavesdropper and its target user. This relation tells us that the eavesdropper inevitably leaves a trace that enables us to devise a way of measuring the amount of information leakage to the eavesdropper even if PCA parameters are unknown. To this end, we derive an estimator for the channel gain from the BS to the eavesdropper and propose a rate-adaptation scheme for adjusting the length of secret key under the PCA. Extensive analysis and evaluations are carried out under various setups, which show that the proposed scheme adequately takes advantage of the LAA to establish the secret keys under the PCA.

We consider secret key agreement (SKA) over time division duplex for a multi-user wireless system, in which a base station (BS) equipped with a large antenna array remotely generates different secret keys for multiple users in the system. The BS can have the SKA over downlink broadcast channels with precoding based on uplink training from the multiple users. In this case, unfortunately, an eavesdropper can effectively perform a pilot contamination attack (PCA) by transmitting a targeted user's training sequence for the purpose to steer beam direction toward the eavesdropper. As the beam direction becomes under the eavesdroppers control, this PCA can result in information leakage from the BS to the targeted user. In order to fend off this PCA, we derive PCA detectors based on generalized likelihood ratio test and propose a countermeasure. For the performance analysis, we consider the outage probability and show that it decreases exponentially with the number of antennas at the BS, which cannot be achieved by the conventional SKA.