Exploration of Intelligent Teaching Methods for Ideological and Political Education in Colleges and Universities under the Background of “Mass Entrepreneurship and Innovation” by Kaiqiang An

“…AI does not provide information resources, technology, and thinking opportunities for the innovation of ideological and political education in colleges and universities. …”
Get full text

Heart Sound Classification Based on Multi-Scale Feature Fusion and Channel Attention Module by Mingzhe Li, Zhaoming He, Hao Wang

Get full text

An Expert System for Leukocyte Classification using Probabilistic Deep Feature Optimization via Distribution Estimation by Awais Muhammad, Akram Tallha, Alasiry Areej, Marzougui Mehrez, Park Jongwoon, Chang Byoungchol

Get full text

Multi-modality deep learning for pulse prediction in homogeneous nonlinear systems via parametric conversion by Hao Zhang, Linshan Sun, Jack Hirschman, Sergio Carbajo

“…In this Letter, we introduce FusionNet, a multi-modality deep learning framework designed to predict and analyze output pulses in high-power rare-earth-doped laser systems driving parametric conversion in homogeneous guided nonlinear media. …”
Get full text

A Novel Software Simulator Model Based on Active Hybrid Architecture by Amr AbdElHamid, Peng Zong

Get full text

Appearance consistency and motion coherence learning for internal video inpainting by Ruixin Liu, Yuesheng Zhu, GuiBo Luo

“…In ACMC‐Net, a transformer‐based appearance network is developed to capture global context information within the video frame for representing appearance consistency accurately. …”
Get full text

Facial recognition and analysis: A machine learning-based pathway to corporate mental health management by Zicheng Zhang, Tianshu Zhang, Jie Yang

Get full text

Cross-dataset person re-identification method based on multi-pool fusion and background elimination network by Yanfeng LI, Bin ZHANG, Jia SUN, Houjin CHEN, Jinlei ZHU

“…The existing cross-dataset person re-identification methods were generally aimed at reducing the difference of data distribution between two datasets,which ignored the influence of background information on recognition performance.In order to solve this problem,a cross-dataset person re-ID method based on multi-pool fusion and background elimination network was proposed.To describe both global and local features and implement multiple fine-grained representations,a multi-pool fusion network was constructed.To supervise the network to extract useful foreground features,a feature-level supervised background elimination network was constructed.The final network loss function was defined as a multi-task loss,which combined both person classification loss and feature activation loss.Three person re-ID benchmarks were employed to evaluate the proposed method.Using MSMT17 as the training set,the cross-dataset mAP for Market-1501 was 35.53%,which was 9.24% higher than ResNet50.Using MSMT17 as the training set,the cross-dataset mAP for DukeMTMC-reID was 41.45%,which was 10.72% higher than ResNet50.Compared with existing methods,the proposed method shows better cross-dataset person re-ID performance.…”
Get full text

PUBLIC AWARENESS OF DEPOSIT INSURANCE AND INVESTOR COMPENSATION SCHEMES IN BULGARIA by Irina Kazandzhieva, Elena Ralinska

“…The results of the survey provide information that the efforts of the regulators and financial safety net schemes should be directed to increasing the awareness of depositors and investors in Bulgaria about the benefits and limitations of both schemes. …”
Get full text

Breast cancer classification using breast ultrasound images with a hybrid of transfer learning and Bayesian-optimized fast learning network by Emmanuel Ahishakiye, Fredrick Kanobe

Get full text

Classifying forensically important flies using deep learning to support pathologists and rescue teams during forensic investigations. by Anna Katharina Gohe, Marius Johann Kottek, Ricardo Buettner, Pascal Penava

“…In this study, two models were evaluated using transfer learning with MobileNetV3-Large and VGG19. Both models achieved a very high accuracy of 99.39% and 99.79%. …”
Get full text

Virtual Reality Video Image Classification Based on Texture Features by Guofang Qin, Guoliang Qin

“…Finally, based on DenseNet, an improved shallow layer dense convolutional neural network (L-DenseNet) is proposed, which can compress network parameters and improve the feature extraction ability of the network. …”
Get full text

Advancing semantic segmentation: Enhanced UNet algorithm with attention mechanism and deformable convolution. by Effat Sahragard, Hassan Farsi, Sajad Mohamadzadeh

“…Our approach utilizes an enhanced UNet architecture that leverages an improved ResNet50 backbone. We replace the last layer of ResNet50 with deformable convolution to enhance feature representation. …”
Get full text

Sea Breeze-Driven Variations in Planetary Boundary Layer Height over Barrow: Insights from Meteorological and Lidar Observations by Hui Li, Wei Gong, Boming Liu, Yingying Ma, Shikuan Jin, Weiyan Wang, Ruonan Fan, Shuailong Jiang, Yujie Wang, Zhe Tong

Get full text

Generative priors-constraint accelerated iterative reconstruction for extremely sparse photoacoustic tomography boosted by mean-reverting diffusion model: Towards 8 projections by Teng Lian, Yichen Lv, Kangjun Guo, Zilong Li, Jiahong Li, Guijun Wang, Jiabin Lin, Yiyang Cao, Qiegen Liu, Xianlin Song

“…., mean state), a mean-reverting diffusion model is trained to learn prior information of the data distribution. Then the learned prior information is employed to generate a high-quality image from the sparse image by iteratively sampling the noisy state. …”
Get full text

Feasibility Analysis of an Immersive Network Laboratory as a Support Tool for Teaching Practices by Erberson Evangelista Vieira, Francisco Petrônio de A. Medeiros

“… Background: Information and Communication Technologies play a fundamental role in education, bringing real-world content closer to students and expanding learning opportunities. …”
Get full text

Diffused Multi-scale Generative Adversarial Network for low-dose PET images reconstruction by Xiang Yu, Daoyan Hu, Qiong Yao, Yu Fu, Yan Zhong, Jing Wang, Mei Tian, Hong Zhang

“…Methods The proposed method includes two modules: the diffusion generator and the u-net discriminator. The goal of the first module is to get different information from different levels, enhancing the generalization ability of the generator to the image and improving the stability of the training. …”
Get full text

INTER-POPULATION COMPARISONS AND THE IMPORTANCE IN INFECTIOUS DISEASES OF THE IRF7, TBK1, IFNAR1, IFNAR2 AND TLR3 GENE VARIANTS IN TURKISH INDIVIDUALS by Aslı Karacan, Güven Toksoy, Zehra Oya Uyguner, Birsen Karaman, Seher Başaran, Ayşe Evrim Bayrak

“…However, there is no information about variants of these genes in the Turkish population. …”
Get full text

AI-Assisted Detection and Localization of Spinal Metastatic Lesions by Edgars Edelmers, Artūrs Ņikuļins, Klinta Luīze Sprūdža, Patrīcija Stapulone, Niks Saimons Pūce, Elizabete Skrebele, Everita Elīna Siņicina, Viktorija Cīrule, Ance Kazuša, Katrina Boločko

Get full text

Emotion-Aware Embedding Fusion in Large Language Models (Flan-T5, Llama 2, DeepSeek-R1, and ChatGPT 4) for Intelligent Response Generation by Abdur Rasool, Muhammad Irfan Shahzad, Hafsa Aslam, Vincent Chan, Muhammad Ali Arshad

“…Our approach combines multiple emotion lexicons, including NRC Emotion Lexicon, VADER, WordNet, and SentiWordNet, with state-of-the-art LLMs such as Flan-T5, Llama 2, DeepSeek-R1, and ChatGPT 4. …”
Get full text