Search

Long-Term Evolution (LTE) was brought in to fulfill the Quality of Service (QoS) demands and needs of users. Existing buffering technique do not have QoS factors and does not support live feed streaming. There are various solutions for problems in the downlink packet scheduling, but there is still room to have a higher QoS to provide greater satisfaction to users. A better user experience requires real-time applications to have minimal amount of delay. Thus, three novel schemes, that regards real-time applications, are proposed and developed. The performances of our proposed algorithms are compared with the latest two-level scheduling algorithm, Frame Level Scheduler and Maximum Throughput (FLS-MT). Our proposed frameworks, 1) FLS and Enhanced Exponential with MT (FE2M) downlink scheduler, 2) FE2M and Exaggerated Earliest Dateline First (E2DF) with MT as weight and best effort packets using the basic MT rule (FE2E2M_I), and 3) FE2M and E2DF with MT as weight and best effort packets using the Proportional Fairness (PF) rule (FE2E2M_II), have exploited innovative approaches based on packet delay at the lower level. The upper level of the scheduling algorithm remains as it is based on discrete-time linear control. A comparative study of recent existing scheduling strategies implemented in LTE are presented. Based on extensive experimental tests, the results generated clearly show that the simulation results of our proposed lower-level scheduling frameworks, FE2M, FE2E2M_I, and FE2E2M_II, outperform the existing two-level scheduling algorithm in terms of throughput, delay, spectral efficiency, and packet loss rate for real-time multimedia applications. [ABSTRACT FROM AUTHOR]

ABSTRACT In this work, a dynamic handwritten signature verification system based on hybrid discrete wavelet transform and discrete Fourier transform is presented. Wavelet transform is adopted to analyze the signature information in a multi-resolution representation while retaining its local information by decomposing the signature into different sub-bands. Fourier transform is performed to extract the feature descriptor of the decomposed sub-bands. A dissimilarity score of the extracted features between the test signature and reference data is computed using Euclidean distance and enveloped Euclidean distance. Apart from that, several score level fusion mechanisms have been investigated to combine decisive information to boost up the system performance. The k-nearest neighbor and support vector machine are applied in order to fuse multiple features. The resulting score value is then normalized and compared with a threshold value in order to decide whether a given signature is genuine or forgery. Experiments are conducted on a released version of benchmark SVC2004 database. Two datasets (Task 1 and Task 2), which have different types of signature information, are used to evaluate the proposed system, and promising verification results are achieved. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Background: In recent years, human activity recognition (HAR) has been an active research topic due to its widespread application in various fields such as healthcare, sports, patient monitoring, etc. HAR approaches can be categorised as handcrafted feature methods (HCF) and deep learning methods (DL). HCF involves complex data pre-processing and manual feature extraction in which the models may be exposed to high bias and crucial implicit pattern loss. Hence, DL approaches are introduced due to their exceptional recognition performance. Convolutional Neural Network (CNN) extracts spatial features while preserving localisation. However, it hardly captures temporal features. Recurrent Neural Network (RNN) learns temporal features, but it is susceptible to gradient vanishing and suffers from short-term memory problems. Unlike RNN, Long-Short Term Memory network has a relatively longer-term dependency. However, it consumes higher computation and memory because it computes and stores partial results at each level. Methods: This work proposes a novel multiscale temporal convolutional network (MSTCN) based on the Inception model with a temporal convolutional architecture. Unlike HCF methods, MSTCN requires minimal pre-processing and no manual feature engineering. Further, multiple separable convolutions with different-sized kernels are used in MSTCN for multiscale feature extraction. Dilations are applied to each separable convolution to enlarge the receptive fields without increasing the model parameters. Moreover, residual connections are utilised to prevent information loss and gradient vanishing. These features enable MSTCN to possess a longer effective history while maintaining a relatively low in-network computation. Results: The performance of MSTCN is evaluated on UCI and WISDM datasets using subject independent protocol with no overlapping subjects between the training and testing sets. MSTCN achieves F1 scores of 0.9752 on UCI and 0.9470 on WISDM. Conclusion: The proposed MSTCN dominates the other state-of-the-art methods by acquiring high recognition accuracies without requiring any manual feature engineering., Competing Interests: No competing interests were disclosed., (Copyright: © 2021 Raja Sekaran S et al.)