U-Net-Based Deep Learning Hybrid Model: Research and Evaluation for Precise Prediction of Spinal Bone Density on Abdominal Radiographs by Lixiao Zhou, Thongphi Nguyen, Sunghoon Choi, Jonghun Yoon

“…The U-Net model is employed for image preprocessing to reduce background noise and enhance bone tissue features, followed by analysis with the artificial neural network model to predict bone mineral density through nonlinear regression. …”
Get full text

DDA-MSLD: A Multi-Feature Speech Lie Detection Algorithm Based on a Dual-Stream Deep Architecture by Pengfei Guo, Shucheng Huang, Mingxing Li

“…It can perform in-depth sequence pattern analysis on manually extracted static prosodic features and nonlinear dynamic features, obtaining high-order dynamic features related to lies. …”
Get full text

Systematic Approach for Malware Detection in IoT Devices: Enhancing Security and Performance by Vasudeva Pai, B. H. Karthik Pai, G. S. Sudhiksha, Vandya Kamath, K. Varsha, S. Manjunatha

“…Using the IoT23 dataset, which contains a wide range of network traffic patterns from various IoT devices and malware families, the research explores and evaluates multiple machine learning techniques. …”
Get full text

A Novel Lightweight Framework for Non-Contact Broiler Face Identification in Intensive Farming by Bin Gao, Yongmin Guo, Pengshen Zheng, Kaisi Yang, Changxi Chen

Get full text

A Brain Network Analysis-Based Double Way Deep Neural Network for Emotion Recognition by Weixin Niu, Chao Ma, Xinlin Sun, Mengyu Li, Zhongke Gao

“…In the second way of the model, we feed the emotional EEG signals directly into another deep neural network block to extract temporal features. At the end of the two ways, the features are concatenated for classification. …”
Get full text

Improved Hierarchical Convolutional Features for Robust Visual Object Tracking by Jinping Sun

“…First, the objective function is designed by lasso regression modeling, and a sparse, time-series low-rank filter is learned to increase the interpretability of the model. Second, the features of the last layer and the second pool layer of the convolutional neural network are extracted to realize the target position prediction from coarse to fine. …”
Get full text

Spectrogram Features-Based Automatic Speaker Identification For Smart Services by Rashid Jahangir, Mohammed Alreshoodi, Fawaz Khaled Alarfaj

“…This study investigates ASI based on features derived from spectrogram images through a convolution neural network (CNN) with rectangular-shaped kernels. …”
Get full text

Deception detection based on micro-expression and feature selection methods by Shusen Yuan, Zilong Shao, Zhongjun Ma, Ting Cao, Hongbo Xing, Yong Liu, Yewen Cao

Get full text

Explainable Feature-Injected Diffusion Model for Medical Image Translation by Jung Su Ahn, Ki Hoon Kwak, Young-Rae Cho

“…Experimental results demonstrate that EIDM outperforms latest Generative Adversarial Networks (GANs) and diffusion models, generating realistic MR images that preserve anatomical integrity, as evidenced by enhanced scores across evaluation metrics. …”
Get full text

Influences on policy-formulation, decision-making, organisation and management for maternal, newborn and child health in Bangladesh, Ethiopia, Malawi and Uganda: The roles and legi... by Kohenour Akter, Yusra Ribhi Shawar, Anene Tesfa, Callie Daniels Howell, Gloria Seruwagi, Agnes Kyamulabi, Albert Dube, Geremew Gonfa, Kasonde Mwaba, QCN Evaluation Group, Mary Kinney, Mike English, Jeremy Shiffman, Nehla Djellouli, Tim Colbourn

Get full text

Complementarity-Oriented Feature Fusion for Face-Phone Trajectory Matching by Changfeng Cao, Wenchuan Zhang, Hua Yang, Dan Ruan

“…Specifically, a Cycle Heterogeneous Trajectory Translation Network (CCTTN) is proposed to realize a TFE (Trajectory Feature Extractor) which captures the latent transforming relationships between the face and phone modalities. …”
Get full text

Multi-Feature Facial Complexion Classification Algorithms Based on CNN by Xiyuan Cao, Delong Zhang, Chunyang Jin, Zhidong Zhang, Chenyang Xue

“…Precisely categorizing facial complexions poses a significant challenge due to the subtle distinctions in facial features. Three multi-feature facial complexion classification algorithms leveraging convolutional neural networks (CNNs) are proposed. …”
Get full text

Data Fusion of Electronic Nose and Multispectral Imaging for Meat Spoilage Detection Using Machine Learning Techniques by Vassilis S. Kodogiannis, Abeer Alshejari

Get full text

Circle of Willis variations and features in an American Midwestern cadaver population by Swathi Sridhar, Farida Mehrhoff, Dominic Maiuro, Chloe Maye, Cameron Smith, Phil Sheridan, Robert Hillard

Get full text

AI-driven diagnosis and health management of autonomous electric vehicle powertrains: An empirical data-driven approach by Hicham El hadraoui, Adila El maghraoui, Oussama Laayati, Erroumayssae Sabani, Mourad Zegrari, Ahmed Chebak

“…Among the models, the optimized neural network combined with CA-selected features achieved the most consistent diagnostic performance, supported by low root mean square error and balanced evaluation metrics. …”
Get full text

A network traffic classification method based on random forest and improved convolutional neural network by Bensheng YUN, Xiaoya GAN, Yaguan QIAN

“…In order to improve the efficiency and reduce the complexity of network traffic classification model, a classification method based on random forest and improved convolutional neural network was proposed.Firstly, the random forest was used to evaluate the importance of each feature of network traffic, and the feature was selected according to the importance ranking.Secondly, AdamW optimizer and triangular cyclic learning rate were adopted to optimize the convolutional neural network classification model.Then, the model was built on Spark cluster to realize the parallelization of model training.Adopting triangular cyclic learning rate with constant cycle amplitude, the experimental results of selecting 1 024, 400, 256 and 100 most important features as input show that the model accuracy is improved to 97.68%, 95.84%, 95.03% and 94.22%, respectively.The 256 most important features were selected and the experimental results based on adopting different learning rates show that the learning rate with half the cycle amplitude works best, the accuracy of the model is improved to 95.25%, and training time of the model is reduced by nearly half.…”
Get full text

Temporal evolution of anchor tracks on a silty seafloor (Eckernförde Bay/Baltic Sea) by Inken Schulze, Mischa Schönke, Peter Feldens, Svenja Papenmeier

“…The data reveal a dense network of anchor tracks, characterized by elongated furrows flanked by mounds to both sides and extensive abrasion zones caused by the anchor chains. …”
Get full text

Visible feature engineering to detect fraud in black and red peppers by Mohammad Hossein Nargesi, Kamran Kheiralipour

“…The efficient features were classified using artificial neural networks and support vector machine methods. …”
Get full text

Kronecker convolutional feature pyramid for fault diagnosis in rolling bearings by Sadia Batool, Abbas Ali Abid, Muhammad Asif, Sagheer Abbas, Khan Muhammad Adnan, Asghar Ali Shah, Taher M. Ghazal

Get full text

Decom-UNet3+: A Retinal Vessel Segmentation Method Optimized With Decomposed Convolutions by Qun Li, Juntao Zhang, Licheng Hua, Songyin Fu, Chenjie Gu

Get full text