Software Defect Prediction Based on Effective Fusion of Multiple Features by Chaozheng Zhang, Junhua Wu

“…Traditional software defect prediction models typically rely on a single feature or perform simple aggregation of multiple features during training. …”
Get full text

Background-Supported Global Feature Response Image Classification Network by JIANG Wentao, LI Weida, ZHANG Shengchong

“…The lack of background information support in current image classification methods leads to the limited classification accuracy of the model. Aiming at this problem, a background-supported global feature response image classification network (BGRNet) is proposed. …”
Get full text

Reflective Distributed Denial of Service Detection: A Novel Model Utilizing Binary Particle Swarm Optimization—Simulated Annealing for Feature Selection and Gray Wolf Optimization-... by Daoqi Han, Honghui Li, Xueliang Fu

“…The BPSO-SA algorithm enhances the global search capability of Particle Swarm Optimization (PSO) using the SA mechanism and effectively screens out the optimal feature subset; the GWO algorithm optimizes the hyperparameters of LightGBM by simulating the group hunting behavior of gray wolves to enhance the detection performance of the model. …”
Get full text

Internet traffic classification method based on behavior feature learning by Zhen LIU, Ruoyu WANG

“…The connection graph based internet traffic classification method can reflect the connectivity behavior between hosts.Thus，it has high stability.But the heuristic rules summarized for traffic classification are generally incomplete，and they difficultly obtain high classification accuracy.Host communication behavior model and BOF method was researched，and a set of host connection related behavior features （HCBF）was extracted from the multiple flows with the same ｛destination IP，destination port and transport protocol｝.To evaluate the performance of HCBF，it was compared with the existing feature set on the respect of basic classification performance and classification stability.The experiments were carried out on the traffic collected in the traditional and mobile networks.Results show that HCBF out performs existing feature sets.…”
Get full text

A Feature Integration Network for Multi-Channel Speech Enhancement by Xiao Zeng, Xue Zhang, Mingjiang Wang

“…We conducted an ablation study to assess the contribution of each module, with each showing a significant impact on performance. Additionally, our model was trained on the SPA-DNS dataset using a circular microphone array and the Libri-wham dataset with a linear microphone array, achieving competitive results compared to state-of-the-art models.…”
Get full text

An Efficient Group Convolution and Feature Fusion Method for Weed Detection by Chaowen Chen, Ying Zang, Jinkang Jiao, Daoqing Yan, Zhuorong Fan, Zijian Cui, Minghua Zhang

“…Leveraging GCAA-Fusion and PAFPN, we developed an Adaptive Feature Fusion (AFF) feature pyramid structure that amplifies the model’s feature extraction capabilities. …”
Get full text

FEATURES AND PROSPECTS FOR USE OF WIND-POWERED DRIVE ON AGRICULTURAL AIRPLANE by V. P. Asovsky, A. S. Kuzmenko

“…Software package to comprehensively assess wind-powered drive conditions and performance indicators is generated and tested taking into account experimental data, as well as airplane performance and flight modes. …”
Get full text

Feature Transformation-Based Few-Shot Class-Incremental Learning by Xubo Zhang, Yang Luo

“…In the process of few-shot class-incremental learning, the limited number of samples for newly introduced classes makes it difficult to adequately adapt model parameters, resulting in poor feature representations for these classes. …”
Get full text

Adaptive Track Association Method Based on Automatic Feature Extraction by Zhaoyue Zhang, Guanting Dong, Chenghao Huang

“…Fuzzy mathematical techniques are subsequently applied to extract discriminative features from both definite association and nonassociation sets, followed by training a support vector machine (SVM) model. …”
Get full text

Intrusion Detection System Framework for SDN-Based IoT Networks Using Deep Learning Approaches With XAI-Based Feature Selection Techniques and Domain-Constrained Features by Manlaibaatar Tserenkhuu, Md Delwar Hossain, Yuzo Taenaka, Youki Kadobayashi

“…Randomly selecting hyperparameters and using datasets with irrelevant features can negatively affect model performance and computational complexity. …”
Get full text

GFADE: generalized feature adaptation and discrimination enhancement for deepfake detection by ZhiYong Tian, Junkai Yi

Get full text

Predicting total healthcare demand using machine learning: separate and combined analysis of predisposing, enabling, and need factors by Fatih Orhan, Mehmet Nurullah Kurutkan

“…The models were evaluated for accuracy and generalization ability using performance metrics such as recall, precision, F1 score, and ROC AUC. …”
Get full text

DAGAN-Based Gait Features Augmentation for Ankle Instability Detection by Xin Liu, Yao Zhang, Yuwei Jiao, Bin Zheng, Qinwei Guo, Yuanyuan Yu, Aziguli Wulamu

“…This study shows that Attention-DualGAN generates synthetic gait features with high correlation to real data, and the performance of the detection model in the diagnosis of ankle ligament injury can be improved by adding appropriate synthetic data.…”
Get full text

Optimal forwarding policy in opportunistic based on social features of nodes by Zhi-fei WANG, Pei-teng SHI, Su DENG, Hong-bin HUANG, Ya-hui WU

“…A forwarding model of opportunistic network was established based on social features of node and by introducing the Pontryagin’s maximal principle,the optimal policy was got,which obeyed the threshold form.Let h denotes the stop time,when t＆lt;h,nodes forward the messages with the maximum probability,when t＆gt;h,the node stops sending messages.Experiments show that the optimal strategy is better than optimal static policy.Further analysis show that the bigger the average number of friends of node is,the smaller the stopping time is,the better the performance is.…”
Get full text

A Multiscale Chaotic Feature Extraction Method for Speaker Recognition by Jiang Lin, Yi Yumei, Zhang Maosheng, Chen Defeng, Wang Chao, Wang Tonghan

“…Finally, we use a GMM-UBM model to develop a speaker recognition system. Our experimental results verified its good performance. …”
Get full text

Frobenius deep feature fusion architecture to detect diabetic retinopathy by C. Priyadharsini, Y. Asnath Victy Phamila

“…Methods This work proposes a multi-model architecture by combining the features extracted from convolutional neural networks using novel Frobenius norm-based feature fusion with an ensemble of machine learning classifiers to perform the classification of binary and multi-class stages of Diabetic Retinopathy. …”
Get full text

A Systematic Review of Intelligent Systems and Analytic Applications in Credit Card Fraud Detection by Ercan Oztemel, Muhammed Isik

Get full text

UAV Signal Modulation Recognition Algorithm Based on Joint Features by Yang Zheng, Zhihai Zhuo

“…To address the limitations of existing algorithms that overly rely on single features, resulting in low recognition rates and excessive model complexity, this paper proposes a drone signal modulation recognition algorithm based on joint features. …”
Get full text

Research on Small-Target Detection of Flax Pests and Diseases in Natural Environment by Integrating Similarity-Aware Activation Module and Bidirectional Feature Pyramid Network Mod... by Manxi Zhong, Yue Li, Yuhong Gao

“…Secondly, in terms of model architecture, a Bidirectional Feature Pyramid Network (BiFPN) module is introduced to replace the original feature extraction network. …”
Get full text

GLIHamba: global–local context image harmonization based on Mamba by Jinsheng SUN, Jiao PAN, Yu GUO, Chao YAO

“…However, the Mamba model cannot maintain spatial local dependencies between adjacent features and thus lacks local consistency. …”
Get full text