A mixing vector based an affine combination of two adaptive filters for sensor array beamforming by Lu, S. T., Sun, J. P., Wang, G. H., Lu, Yilong.

“…When compared to existing methods, the proposed approach exhibits faster convergence rate and higher output signal to interference plus noise ratio (SINR). …”
Get full text
Get full text

A coherent image source method for flat waveguides with locally reacting boundaries by Min, Hequn., Qiu, Xiaojun., Li, Ningrong.

“…By comparisons to the classical wave theory and the existing coherent ray-based methods, it is shown that the proposed method is considerably accurate to predict the sound propagation in flat waveguides with a sound absorbing ceiling and a reflective floor over a broad frequency range and for various source/receiver geometries, even if at large distances from the source compared to the waveguide height while the existing methods are shown to be erroneous.…”
Get full text
Get full text
Get full text

Single frequency sound propagation prediction in flat waveguides with locally reactive impedance boundaries by Chen, Weisong, Qiu, Xiaojun, Min, Hequn

“…Being compared with the classical wave theory and the existing coherent ray-based methods, it is shown that the proposed method provides considerable accuracy and advantages to predict sound propagation in flat waveguides with a sound absorptive ceiling and a reflective floor over a broad frequency range, particularly at large distances from the source where the existing methods are problematic.…”
Get full text
Get full text

Mine yOur owN Anatomy: revisiting medical image segmentation with extremely limited labels by You, C, Dai, W, Liu, F, Min, Y, Dvornek, NC, Li, X, Clifton, DA, Staib, L, Duncan, JS

“…Recent studies on contrastive learning have achieved remarkable performance solely by leveraging few labels in the context of medical image segmentation. Existing methods mainly focus on instance discrimination and invariant mapping (i.e., pulling positive samples closer and negative samples apart in the feature space). …”

Novel reactive power control strategy for mitigating voltage rise in the Malaysian low voltage distribution network with high PV penetration by Alwez, Mustafa Abo, Jasni, Jasronita, Wahab, Raghad, Mohd.Radzi, Mohd Amran, Azis, Norhafiz

“…The technique effectively reduces average voltage, maintains voltage regulation during high sun irradiance and low load demand periods, and surpasses the adaptability of existing methods dependent on PV active injection or network voltage alone. …”
Get full text

A hybrid deep learning model for detecting driver fatigue using electroencephalogram signals by Rafiuddin, Abdubrani, Mahfuzah, Mustafa, Zarith Liyana, Zahari

“…Road accidents caused by driver fatigue are a significant public safety concern, and detecting driver fatigue is crucial for preventing such incidents. Existing methods for detecting driver fatigue are limited in their effectiveness, and there is a need for more accurate and reliable methods. …”
Get full text

Multifidelity Methods for Design of Transition MetalComplexes by Janet, Jon Paul

“…This metric is shown to offer superior performance over existing methods. The application of these methods to virtual design problems is demonstrated with two case studies: 1) identifying spin crossover complexes from a design space of thousands using an evolutionary strategy and 2) probabilistic, multiobjective optimization of redox couples over a 3 million-complex space. …”
Get full text

Identifying Money Laundering Subgraphs on the Blockchain by Song, Kiwhan, Dhraief, Mohamed Ali, Xu, Muhua, Cai, Locke, Chen, Xuhao, Mithal, Arvind, Chen, Jie

Get full text

A study on giant panda recognition based on images of a large proportion of captive pandas by Chen, Peng, Swarup, Pranjal, Matkowski, Wojciech Michal, Kong, Adams Wai Kin, Han, Su, Zhang, Zhihe, Rong, Hou

“…However, it remains a challenging task because the existing methods, such as traditional tracking method, discrimination method based on footprint identification, and molecular biology method, are invasive, inaccurate, expensive, or challenging to perform. …”
Get full text

A narrowband ultrasonic ranging method for multiple moving sensor nodes by Ashhar, Karalikkadan, Md. Noor-A-Rahim, Mohammad Omar Khyam, Soh, Cheong Boon

“…One of the main problems faced by the ultrasonic localization systems is the ranging error due to the Doppler shift. Existing methods for Doppler correction employ a bank of matched filters at the receiver end which is computationally intense and complex. …”
Get full text

An extremum seeking-based approach for Nash equilibrium seeking in N-cluster noncooperative games by Ye, Maojiao, Hu, Guoqiang, Xu, Shengyuan

“…Secondly, the proposed seeking strategy requires each agent to update fewer auxiliary variables compared with the existing methods and hence reduces the communication and computation costs. …”
Get full text

A new framework for automatic detection of motor and mental imagery EEG signals for robust BCI systems by Yu, Xiaojun, Muhammad Zulkifal Aziz, Muhammad Tariq Sadiq, Fan, Zeming, Xiao, Gaoxi

“…Results compared with the other existing methods demonstrated that the highest classification accuracies of 99.82% (data set IV-A), 93.33% (data set IV-b), 91.96% (data set III), and 88.08% (data set V) in subject-specific scenarios, while 82.70% (data set IV-A) in the subject-independent framework are achieved for IEFD with FFNN classifiers collectively. …”
Get full text

Person re-identification via pose-aware multi-semantic learning by Luo, Xiangzhong, Duong, Luan H. K., Liu, Weichen

“…Person re-identification (ReID) remains an open-ended research topic, with its variety of substantial applications such as tracking, searching, etc. Existing methods mostly explore the highest-semantic feature embedding, ignoring the insights hidden among the earlier layers. …”
Get full text

Inferring origin-destination distribution of agent transfer in a complex network using deep gated recurrent units by Saw, Vee-Liem, Vismara, Luca, Suryadi, Yang, Bo, Johansson, Mikael, Chew, Lock Yue

“…By comparing against methods that give exact results, we demonstrate the near-optimal performance of our DNNGRU, which we found to consistently outperform existing methods and alternative neural network architectures, under diverse data generation scenarios.…”
Get full text

VToonify: controllable high-resolution portrait video style transfer by Yang, Shuai, Jiang, Liming, Liu, Ziwei, Loy, Chen Change

“…Extensive experimental results demonstrate the effectiveness of our proposed VToonify framework over existing methods in generating high-quality and temporally-coherent artistic portrait videos with flexible style controls. …”
Get full text

Region embedding with intra and inter-view contrastive learning by Zhang, Liang, Long, Cheng, Cong, Gao

“…While some efforts have been made for solving this problem based on multiple views, existing methods are still insufficient in extracting representations in a view and/or incorporating representations from different views. …”
Get full text

Develop AI based image restoration algorithm for deep tissue imaging in photoacoustic system by Hao, Zeliang

“…The experimental results illustrate that the proposed approach consistently surpasses existing methods in terms of quantitative metrics on both the RWBI dataset and the commonly utilized public GOPRO dataset. …”
Get full text

Deep graph contrastive learning model for drug-drug interaction prediction by Jiang, Zhenyu, Gong, Zhi, Dai, Xiaopeng, Zhang, Hongyan, Ding, Pingjian, Shen, Cong

“…It has become a new challenge to use computational methods to accelerate drug interaction time and reduce its cost-effectiveness. The existing methods often do not fully explore the relationship between the structural information and the functional information of drug molecules, resulting in low prediction accuracy for drug interactions, poor generalization, and other issues. …”
Get full text

Identifying software vulnerabilities via code representation learning by Wu, Bozhi

“…The thesis begins with an empirical study evaluating the effectiveness of existing methods and tools, providing insights into their practical application. …”
Get full text

Respiratory quality indices for automated monitoring of respiration from sensor data by Birrenkott, D

“…The linear regression fusion RQI is used in the development of an RR estimation algorithm, termed RQIFusion, which achieves highly accurate and more complete RR estimates than existing methods. In the Dialysis III data set, implementation of RQIFusion improved RR estimation error by between 1.35 to 2.29 breaths per minute (brpm) to achieve RR estimation errors between 2.18 to 3.46 brpm, depending on the RR estimation algorithm employed. …”