Enhancing Session-Based Recommendations with Popularity-Aware Graph Neural Networks

Wawage, Pawan; Deshpande, Yogesh

doi:10.56578/ataiml010104

Cited by 10 publications

(9 citation statements)

References 18 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thereby, feature clustering algorithms can be used effectively for feature-matching techniques. Many clustering algorithms have been used recently for speaker recognition, including Vector Quantization (VQ), K-means Clustering, Support Vector Machine (SVM) [29], Neural Network (NN) [30,31], Hidden Markov Modeling (HMM), and Dynamic Time Warping (DTW) [32]. In this paper, the VQ and K-means tactics have been used to identify the clusters.…”

Section: Mfcc Features Clusteringmentioning

confidence: 99%

Accurate Reader Identification for the Arabic Holy Quran Recitations Based on an Enhanced VQ Algorithm

Al‐Jarrah¹,

Ahmad²,

Jarrah³

et al. 2022

RIA

View full text Add to dashboard Cite

The Speaker identification process is not a new trend; however, for the Arabic Holy Quran recitation, there are still quite improvements that can make this process more accurate and reliable. This paper collected the input data from 14 native Arabic reciters, consisting of “Surah Al-Kawthar” speech signals from the Holy Quran. Moreover, this paper discusses the accuracy rates for 8 and 16 features. Indeed, a modified Vector Quantization (VQ) technique will be presented, in addition to realistically matching the centroids of the various codebooks and measuring systems’ effectiveness. Note that the VQ technique will be utilized to generate the codebooks by clustering these features into a finite number of centroids. The proposed system’s software was built and executed using MATLAB®. The proposed system’s total accuracy rate was 97.92% and 98.51% for 8 and 16 centroids codebooks, respectively. However, this study discussed two validation tactics to ensure that the outcomes are reliable and can be reproduced. Hence, the K-mean clustering algorithm has been used to validate the obtained results and discuss the outcomes of this study. Finally, it has been found that the improved VQ method gives a better result than the K-means method.

show abstract

Section: Mfcc Features Clusteringmentioning

confidence: 99%

Accurate Reader Identification for the Arabic Holy Quran Recitations Based on an Enhanced VQ Algorithm

Al‐Jarrah¹,

Ahmad²,

Jarrah³

et al. 2022

RIA

View full text Add to dashboard Cite

show abstract

“…The proposed system provides a good balance between the sum rate performance and hardware complexity of the system using a partially connected sub-array structure. Recently deep learning based algorithms are efficiently used for many signal processing applications and has given tremendous improvement in the results [31,32]. In future the performance of hybrid beamforming can be enhanced using deep learning techniques.…”

Section: Discussionmentioning

confidence: 99%

An Effective Kalman Based Hybrid Beamforming for Millimeter Wave Massive MIMO System by Using 2D Overlapped Partially Connected Sub-Array Structure

Londhe¹,

Hendre²

2022

View full text Add to dashboard Cite

In 5G mobile communication networks, millimeter-wave (mmWave) technology plays a key role. To deal with the problem of path loss that happens in the mmWave band, competent beamforming employing a large antenna array is required. Fully digital beamforming approaches currently require separate radio frequency chains (RF chains) for each antenna, which adds to the computational complexity and hardware expense. In a multi-user environment, fully digital beamforming suffers from a larger antenna array layout, whereas analog beamforming solutions are prone to numerous performance concerns. Hybrid beamforming, on the other hand, offers a promising solution for multi-user mmWave communication. This work proposes a two-dimensional overlapping partially connected (2D-OPC) sub-array structure to reduce the antenna structure's hardware complexity and cost. The suggested technique comprises several sub-arrays that are overlapped in 2D space in the form of a Uniform Planar Array (UPA). The suggested scheme's performance is assessed using Kalman-based hybrid beamforming, which exhibits a considerable increase in spectral efficiency when compared to existing hybrid beamforming techniques. The suggested technique, which uses Kalman based hybrid beamforming and 2D-OPC provides 3.14% and 4.96% improvement over the MMSE hybrid beamforming and ZF pre-coding technique respectively.

show abstract

“…Better use of increasing audio, text, video and other information to assist human production and life has been a concern of scholars at home and abroad [1][2][3][4][5][6][7]. With the development of in-depth learning technology and people's demand for intelligent security, human-computer interaction, shopping mall guidance and other technologies, computer vision technology for pedestrian identity recognition shows great application value [8][9][10][11][12][13]. Influenced by various problems in the actual surveillance shooting scene, the appearance difference, obscured field of view, poor lighting conditions, unclear images or incomplete shooting and other problems limit the rapid application of pedestrian identification technology, which still requires in-depth research [14][15][16][17][18][19][20][21].…”

Section: Introductionmentioning

confidence: 99%

Pedestrian Identification Method Based on Multi-Scale Feature Learning in Surveillance Video Images

Li¹,

Pang²,

An³

et al. 2022

View full text Add to dashboard Cite

With the development of deep learning technology and people's demand for intelligent security, human-computer interaction, shopping guide and other technologies, computer vision technology for pedestrian identification shows great application value. In this paper, pedestrian identification method based on multi-scale feature learning in surveillance video images is studied. Firstly, the deep residual network ResNet and densely connected convolutional network DenseNet are introduced as baseline networks. A model is constructed based on hybrid hourglass network module, enhanced weighted feature pyramid fusion network module and post-processing module. The loss function is designed, which is unified with other traditional models, and the optimization objective of the loss function is respectively corresponding to three parts, namely, the prediction error of corresponding center point, the prediction error of offset and the prediction error of bounding box size. The experimental results verify the effectiveness of the proposed model.

show abstract

Enhancing Session-Based Recommendations with Popularity-Aware Graph Neural Networks

Cited by 10 publications

References 18 publications

Accurate Reader Identification for the Arabic Holy Quran Recitations Based on an Enhanced VQ Algorithm

Accurate Reader Identification for the Arabic Holy Quran Recitations Based on an Enhanced VQ Algorithm

An Effective Kalman Based Hybrid Beamforming for Millimeter Wave Massive MIMO System by Using 2D Overlapped Partially Connected Sub-Array Structure

Pedestrian Identification Method Based on Multi-Scale Feature Learning in Surveillance Video Images

Contact Info

Product

Resources

About