Considering at the issue that the performance of the traditional beamforming algorithm will decrease sharply when the disturbance occurs at the disturbed position and the steering vector mismatch occurs, a new robust ...
详细信息
Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existin...
ISBN:
(纸本)9781713871088
Collab.rative Metric Learning (CML) has recently emerged as a popular method in recommendation systems (RS), closing the gap between metric learning and Collab.rative Filtering. Following the convention of RS, existing methods exploit unique user representation in their model design. This paper focuses on a challenging scenario where a user has multiple categories of interests. Under this setting, we argue that the unique user representation might induce preference bias, especially when the item category distribution is imbalanced. To address this issue, we propose a novel method called Diversity-Promoting Collab.rative Metric Learning (DPCML), with the hope of considering the commonly ignored minority interest of the user. The key idea behind DPCML is to include a multiple set of representations for each user in the system. Based on this embedding paradigm, user preference toward an item is aggregated from different embeddings by taking the minimum item-user distance among the user embedding set. Furthermore, we observe that the diversity of the embeddings for the same user also plays an essential role in the model. To this end, we propose a Diversity control Regularization Scheme (DCRS) to accommodate the multi-vector representation strategy better. Theoretically, we show that DPCML could generalize well to unseen test data by tackling the challenge of the annoying operation that comes from the minimum value. Experiments over a range of benchmark datasets speak to the efficacy of DPCML.
The advancement of millimeter-wave communicationtechnology heralds new sensing capabilities. By leveraging channel multipath parameter estimates, we can harness simultaneous localization and mapping (SLAM) for precis...
详细信息
ISBN:
(数字)9798350362244
ISBN:
(纸本)9798350362251
The advancement of millimeter-wave communicationtechnology heralds new sensing capabilities. By leveraging channel multipath parameter estimates, we can harness simultaneous localization and mapping (SLAM) for precise user equipment (UE) localization and radio map construction in 6 G communication systems. Particularly in multi-UE scenarios, SLAM empowers base stations to amalgamate the local radio maps of various UEs efficiently. This study introduces a novel Bayesian framework specifically designed for multi-UE SLAM, complemented by a tailored factor graph. We also unveil a two-stage multi-UE SLAM algorithm. Our simulation results reveal that this algorithm substantially enhances radio map construction accuracy by $\mathbf{4 8. 5 \%}$ and UE localization accuracy by $13.5 \%$, outperforming single-UE cases. Moreover, the algorithm demonstrates remarkable adaptability to environmental changes, showcasing its potential for long-term evolution in dynamic settings.
A novel CaLaNbWO8 (CLNWO) ceramic was prepared using traditional solid-state methods. The CLNWO ceramics that were sintered at 1440°C displayed noteworthy dielectric properties, with Εr = 11.18, Q×f = 32,99...
详细信息
Aiming at the problem that Distributed Optical Fiber Acoustic Sensing (DAS) system will misjudge external intrusion signals, an intrusion signal discrimination method based on MFCC-Energy entropy feature and FTO-SVM i...
详细信息
In order to optimize the orthogonal design of MIMO radar waveform, an improved algorithm based on niche genetic algorithm is proposed. The algorithm is able to eliminate individuals with similar structures in the popu...
详细信息
Traditional multicast routing methods have some problems in constructing a multicast tree, such as limited access to network stateinformation, poor adaptability to dynamic and complex changes in the network, and infl...
详细信息
In this paper, the radar clutter reconstruction model based on singularity power spectrum (SPS) and instantaneous singularity exponent (ISE) is proposed. The proposed ISE-SPS model consists of power measure channel an...
详细信息
ISBN:
(数字)9781728168968
ISBN:
(纸本)9781728168975
In this paper, the radar clutter reconstruction model based on singularity power spectrum (SPS) and instantaneous singularity exponent (ISE) is proposed. The proposed ISE-SPS model consists of power measure channel and dimension measure channel. The multi-scale wavelet coefficients are estimated based on the coupling of the two channels to reconstruct the radar sea clutter. Experiment based on the Ice Multi-parameter Imaging X-Band (IPIX) indicates that the proposed model behaves better than the N-partitioned random multiplicative model (NRMM), with about 32% increment in terms of correlation coefficient and normalized MSE of MFS and SPS.
Broadcast is an important link in mobile ad hoc wireless networks (MANETs). In order to improve broadcast coverage, reduce forwarding probability and broadcast collision, a dynamic space-covered broadcast algorithm ba...
详细信息
Smart vocational education is the specific application of new information technologies such as the Intemet of Things, cloud computing, mobile Internet and artificial intelligence technology in the field of education. ...
详细信息
暂无评论