Kinship recognition is becoming an important path in the evolution of biometric recognition research. Over the past decade, notable progress has been achieved in this emerging field attracting more researchers to expl...
详细信息
ISBN:
(数字)9798350309584
ISBN:
(纸本)9798350309591
Kinship recognition is becoming an important path in the evolution of biometric recognition research. Over the past decade, notable progress has been achieved in this emerging field attracting more researchers to exploit new methods for its branches. The most common use case is facial kinship recognition with its two variants: verification and identification. In this paper, we propose a novel kinship verification network based on a self-calibrated attention model and residual blocks to expand the fields-of-view through the attention stack for producing more discriminative features. In addition, we extend our work to build a kinship identification network based on joint learning of self-calibrated verification ensembles. Experimental results on benchmark datasets are demonstrated to show the effectiveness of our proposed scheme when compared to state-of-the-art solutions on the kinship identification track.
Drug-drug interactions (DDIs) can significantly impact treatment outcomes by causing adverse effects or reducing therapeutic efficacy. Whereas many DDIs are already known, there are numerous hidden interactions. There...
详细信息
This work presents a novel non-destructive methodology to screen out devices with lower short circuit withstand time (SCWT) in commercial 4 {H}-{SiC} power metal-oxide semiconductor field effect transistors (MOSFETs) ...
详细信息
The paper presents the results of the study of the process of porous materials impregnation from the point of view of percolation theory. Diffusion front, diffusion front shell, percolation cluster are determined usin...
详细信息
Ambiguity is gaining attention in self-tracking research as a means to go beyond the mere quantification of body signals. Recent research has suggested that ambiguity can be used even to enable social connection media...
详细信息
A multi-objective Scheduling approach for large-scale microservice Critical Notification system applications (SCN-DRL) based on Deep Reinforcement Learning is presented. This paper addresses optimization for three obj...
详细信息
Stroke and amyotrophic lateral sclerosis manifest symptoms that affect facial motion in patients. Tracking these movements and assessing the severity of the impairment can be achieved with facial alignment technology ...
详细信息
Class imbalance, which negatively affects classification model performance, is a common problem with machine learning. Various oversampling methods have been developed as potential solutions to compensate for imbalanc...
详细信息
Alzheimer's disease (AD) poses a significant challenge to global health, affecting over 50 million individuals worldwide with no current cure. Early identification and treatment are vital to mitigate its impact on...
详细信息
The integration of Satellite-Terrestrial Networks (ISTN) necessitates advanced security measures, particularly Intrusion Detection systems (IDSs). This study introduces hybrid sequential intrusion detection models for...
详细信息
ISBN:
(数字)9798350378511
ISBN:
(纸本)9798350378528
The integration of Satellite-Terrestrial Networks (ISTN) necessitates advanced security measures, particularly Intrusion Detection systems (IDSs). This study introduces hybrid sequential intrusion detection models for ISTNs, combining Deep Learning (DL) and Machine Learning (ML) techniques. The models employ both anomaly-based and signature-based detection to enhance accuracy, utilizing methods such as Extra Trees (ET), Decision Trees (DT), Random Forest (RF), XGBoost (XGB), and Gated Recurrent Units (GRU). These models are chosen for their superior performance and are used sequentially to improve IDSs effectiveness. RF-based Sequential Feature Selection (RF-SFS) is also utilized to reduce dataset dimensionality, which in turn decreases the computational costs for each model. Evaluations using UNSW-NB15 and STIN datasets-representing terrestrial and satellite traffic, respectively-demonstrate the models' superiority over traditional IDSs. The XGB-ET model achieved 99.99% accuracy in anomaly detection, while the XGB-GRU model attained 89% accuracy in signature-based detection on the UNSW-NB15 dataset. On the STIN dataset, the ET-DT-GRU model reached 96.47% accuracy in signature-based detection. Additionally, RF-SFS reduced execution times, with training and testing speedups up to 2.8x.
暂无评论