Video temporal perception characteristics based just noticeable difference model by Yafen1 XING, Haibing YIN, Hongkui WANG, Qionghua LUO

“…The existing temporal domain JND(just noticeable distortion) models are not sufficient to depict the interaction between temporal parameters and HVS characteristics, leading to insufficient accuracy of the spatial-temporal JND model.To solve this problem, feature parameters that can accurately describe the temporal characteristics of the video were explored and extracted, as well as a homogenization method for fusing heterogeneous feature parameters, and the temporal domain JND model based on this was improved.The feature parameters were investigated including foreground and background motion, temporal duration along the motion trajectory, residual fluctuation intensity along motion trajectory and adjacent inter-frame prediction residual, etc., which were used to characterize the temporal characteristics.Probability density functions for these feature parameters in the perception sense according to the HVS(human visual system) characteristics were proposed, and uniformly mapping the heterogeneous feature parameters to the scales of self-information and information entropy to achieve a homogeneous fusion measurement.The coupling method of visual attention and masking was explored from the perspective of energy distribution, and the temporal-domain JND weight model was constructed accordingly.On the basis of the spatial JND threshold, the temporal domain weights was integrated to develop a more accurate spatial-temporal JND model.In order to evaluate the performance of the spatiotemporal JND model, a subjective quality evaluation experiment was conducted.Experimental results justify the effectiveness of the proposed model.…”
Get full text

Semi-supervised gearbox fault diagnosis under variable working conditions based on masked contrastive learning by ZHANG Huiyun, ZUO Fangjun, LI Hang, YU Xi

“…Finally, during the fine-tuning phase, a domain-conditioned feature correction strategy was introduced to generate target domain feature corrections. …”
Get full text

A sleep staging model based on adversarial domain generalized residual attention network by Pengwei Zhang, Sijia Xiang, Kailei Hu, Jialing He, Jingxia Chen

“…The label classifier uses the deep features learned by the feature extractor to perform sleep staging. …”
Get full text

A Fault Diagnosis Model Based on LCD-SVD-ANN-MIV and VPMCD for Rotating Machinery by Songrong Luo, Junsheng Cheng, Kexiang Wei

“…The fault diagnosis process is essentially a class discrimination problem. However, traditional class discrimination methods such as SVM and ANN fail to capitalize the interactions among the feature variables. …”
Get full text

Video temporal perception characteristics based just noticeable difference model by Yafen1 XING, Haibing YIN, Hongkui WANG, Qionghua LUO

“…The existing temporal domain JND(just noticeable distortion) models are not sufficient to depict the interaction between temporal parameters and HVS characteristics, leading to insufficient accuracy of the spatial-temporal JND model.To solve this problem, feature parameters that can accurately describe the temporal characteristics of the video were explored and extracted, as well as a homogenization method for fusing heterogeneous feature parameters, and the temporal domain JND model based on this was improved.The feature parameters were investigated including foreground and background motion, temporal duration along the motion trajectory, residual fluctuation intensity along motion trajectory and adjacent inter-frame prediction residual, etc., which were used to characterize the temporal characteristics.Probability density functions for these feature parameters in the perception sense according to the HVS(human visual system) characteristics were proposed, and uniformly mapping the heterogeneous feature parameters to the scales of self-information and information entropy to achieve a homogeneous fusion measurement.The coupling method of visual attention and masking was explored from the perspective of energy distribution, and the temporal-domain JND weight model was constructed accordingly.On the basis of the spatial JND threshold, the temporal domain weights was integrated to develop a more accurate spatial-temporal JND model.In order to evaluate the performance of the spatiotemporal JND model, a subjective quality evaluation experiment was conducted.Experimental results justify the effectiveness of the proposed model.…”
Get full text

Small Target Detection Algorithm for UAV Aerial Images Based on Improved YOLOv7-tiny by ZHANG Guanghua, LI Congfa, LI Gangying, LU Weidang

“…Second, to strengthen the feature extraction capability for multi-scale targets and improve the detection of small targets, a small-target detection layer is designed, leading to a tiny-target detection head that increases the model receptive field and better addresses the scale variance problem caused by drastic target size changes. …”
Get full text

Integrated neural network framework for multi-object detection and recognition using UAV imagery by Mohammed Alshehri, Tingting Xue, Tingting Xue, Ghulam Mujtaba, Yahya AlQahtani, Nouf Abdullah Almujally, Ahmad Jalal, Ahmad Jalal, Hui Liu, Hui Liu, Hui Liu

“…Combining several advanced models ensures that the system works smoothly even when dealing with problems like people being covered up and varying sizes.…”
Get full text

Smart contract vulnerability detection method based on Bi-modal cross-attention mechanism by CHEN Jinfu, HU Xinyi, CAI Saihua, MIN Xirun

“…Residual connections were introduced to effectively preserve and transmit original feature information, mitigating the vanishing gradient problem in deep network training. …”
Get full text

基于EEMD与奇异熵增量谱的齿轮故障特征提取 by 杨望灿, 张培林, 吴定海, 陈彦龙

“…A method of feature extraction for gear fault based on Ensemble empirical mode decomposition（EEMD）and incremental spectrum of singularity entropy is put forward for the non-stationary and non-linear characteristics of gear vibration signal.Firstly,the gear vibration signal is decomposed into several smooth intrinsic mode functions（IMFs）by EEMD.The method of EEMD could take advantage of dyadic scale decomposition characteristics of the normal distribution white noise to suppress the problem of mode confusion in EMD.Because of the interference of background noise and residual assisted white noise,the gear fault feature is not extracted exactly from IMF.The method of singular value decomposition is used to remove the noise and reconstruct the IMF.The reconstruction order is determined according to the incremental spectrum of singularity entropy.Therefore the gear fault feature frequency could be extracted exactly.Results of simulation analysis and the gear fault test indicated that this method is accurate and effective for gear fault feature extraction.…”
Get full text

Foreign object detection on coal conveyor belt enhanced by attention mechanism by ZHANG Yang, CHENG Zhiyu, CHEN Yunjiang, ZHANG Jiannan, YUAN Wensheng, ZHANG Hui

“…A unique combination of convolution and pooling operations was used by the CPCA attention mechanism to perform global average pooling and maximum pooling on the input feature map, multi-dimensional feature information was deeply mined, and then attention weights for each channel and spatial position were accurately generated through nonlinear transformation, guiding the model to focus on the key feature areas of foreign objects and enhance feature extraction capabilities. …”
Get full text

Bio inspired optimization techniques for disease detection in deep learning systems by A. Ashwini, Vanajaroselin Chirchi, S. Balasubramaniam, Mohd Asif Shah

“…Abstract Numerous contemporary computer-aided disease detection methodologies predominantly depend on feature engineering techniques; yet, they possess several drawbacks, including the presence of redundant features and excessive time consumption. …”
Get full text

SDFA-Net: Synergistic Dynamic Fusion Architecture With Deformable Attention for UAV Small Target Detection by Yunsong Qi, Hengwei Cao

“…Second, the dynamic attention interaction mechanism (attention) is used to replace the traditional Attention-based Intrascale Feature Interaction (AIFI) module, which effectively alleviates the computational complexity problem and strengthens the feature interaction efficiency. …”
Get full text

EER-DETR: An Improved Method for Detecting Defects on the Surface of Solar Panels Based on RT-DETR by Jiajun Dun, Hai Yang, Shixin Yuan, Ying Tang

“…In response to the shortcomings of existing detection methods in identifying tiny defects and model efficiency, this study innovatively constructed the EER-DETR detection framework: firstly, a feature reconstruction module WDBB with a differentiable branch structure was introduced to significantly enhance the feature retention ability for fine cracks and other small targets; secondly, an adaptive feature pyramid network EHFPN was innovatively designed, which achieved efficient integration of multi-level features through a dynamic weight allocation mechanism, reducing the model complexity by 9.7% while maintaining detection accuracy, solving the industry problem of “precision—efficiency imbalance” in traditional feature pyramid networks; finally, an enhanced upsampling component was introduced to effectively address the problem of detail loss that occurs in traditional methods during image resolution enhancement. …”
Get full text

An Improved Pose Estimation Method Based on Projection Vector With Noise Error Uncertainty by Jiashan Cui, Changwan Min, Xiangyun Bai, Jiarui Cui

“…Aiming at the problem of anomalous and non-independent distribution of the image errors in the feature-based visual pose estimation, a method of monocular visual pose estimation based on the uncertainty of noise error established by projection vector is proposed. …”
Get full text

Ship Classification with High Resolution TerraSAR-X Imagery Based on Analytic Hierarchy Process by Zhi Zhao, Kefeng Ji, Xiangwei Xing, Wenting Chen, Huanxin Zou

“…The main idea is to apply AHP on both feature selection and classification decision. On one hand, the AHP based feature selection constructs a selection decision problem based on several feature evaluation measures (e.g., discriminability, stability, and information measure) and provides objective criteria to make comprehensive decisions for their combinations quantitatively. …”
Get full text

Deep learning-based prediction of multi-level just noticeable distortion by Haifeng XU, Hongkui WANG, Haibing YIN, Chuqiao CHEN

“…Visual just noticeable distortion (JND) directly reflects the sensitivity of the human visual system to visual signal noise, and is widely used in image and video processing.Aiming at the multilevel prediction problem of video JND threshold, it was transformed into the prediction problem of satisfied user ratio (SUR) curve, and a feature fusion-based SUR curve prediction model was proposed.The model was mainly divided into key frame extraction module, feature extraction and fusion module, and SUR score regression module.In the key frame extraction module, according to the visual perception mechanism, the spatial-temporal domain perception complexity was proposed and used as the video key frame judgment index.In the feature extraction and fusion module, a multi-scale dense residual network was proposed based on dense residual block (RDB) to realize image feature extraction and multi-scale fusion.The experimental results show that the proposed SUR curve prediction model is overall better than the existing models in terms of JND prediction accuracy and reduces the time cost by 8.1% on average in terms of operational efficiency.Meanwhile, the model can also be used to predict other layers of JND thresholds, which can be directly applied to video multilevel perceptual coding optimization.…”
Get full text

Content of the Right to Defence of Persons Affected by Domestic Violence by M. V. Naumenko

“…It is noted that universality is a qualitative feature of the legal category of the right to defence ion. …”
Get full text

AMCL: supervised contrastive learning with hard sample mining for multi-functional therapeutic peptide prediction by Jiwei Fang, Henghui Fan, Jintao Zhao, Jianping Zhao, Junfeng Xia

“…The field faces challenges such as long-tail distribution problems, data sparsity, and complex label co-occurrence patterns due to peptides’ multi-functional nature. …”
Get full text

SASDL and RBATQ: Sparse Autoencoder With Swarm Based Deep Learning and Reinforcement Based Q-Learning for EEG Classification by Sunil Kumar Prabhakar, Seong-Whan Lee

“…<italic>Methods</italic>: The main advantage of using deep learning when compared to other machine learning algorithms is that it has the capability to accomplish feature engineering on its own. Swarm intelligence is also a highly useful technique to solve a wide range of real-world, complex, and non-linear problems. …”
Get full text

Mathematical Assessment of Results of Investigation of the BCL-2 and Caspase-3 Protein Expression under the Influence of nanobiocomposites of Silver on natural and Synthetic Matrix... by M. A. Novikov, E. A. Titov, V. A. Vokina, L. M. Sosedova

Get full text