Research and Optimization of White Blood Cell Classification Methods Based on Deep Learning and Fourier Ptychographic Microscopy by Mingjing Li, Junshuai Wang, Shu Fang, Le Yang, Xinyang Liu, Haijiao Yun, Xiaoli Wang, Qingyu Du, Ziqing Han

“…The proposed method introduces four key innovations to enhance detection accuracy and model efficiency: (1) A novel Conv2Former (Convolutional Transformer) backbone was designed to combine the local pattern extraction capability of convolutional neural networks (CNNs) with the global contextual reasoning of transformers, thereby improving the expressiveness of feature representation. (2) The CARAFE (Content-Aware ReAssembly of Features) upsampling operator was adopted to replace conventional interpolation methods, thereby enhancing the spatial resolution and semantic richness of feature maps. (3) An Efficient Multi-scale Attention (EMA) module was introduced to refine multi-scale feature fusion, enabling the model to better focus on spatially relevant features critical for WBC classification. (4) Soft-NMS (Soft Non-Maximum Suppression) was used instead of traditional NMS to better preserve true positives in densely packed or overlapping cell scenarios, thereby reducing false positives and false negatives. …”
Get full text

Adversarial Attacks Defense Method Based on Multiple Filtering and Image Rotation by Feng Li, Xuehui Du, Liu Zhang

“…An image filtering method is often used to evaluate the robustness of adversarial examples. However, filtering induces the loss of valuable features that reduce the classification accuracy and weakens the adversarial perturbation. …”
Get full text

Cyclone vulnerability assessment of the central coast of Bangladesh: A comprehensive study utilizing FAHP and geospatial techniques. by Md Abdullah Salman, Mahmudul Hasan Rakib, Shacin Chandra Saha, Md Emdadul Haque, Md Sabbir Hossen

“…This research develops a comprehensive tropical cyclone mapping strategy utilizing the Fuzzy Analytical Hierarchy Process (FAHP) and geospatial techniques to analyze the vulnerability distribution in the central coastal regions of Bangladesh. Eighteen spatial features, categorized into physical, social, and mitigation capacity criteria, were assessed to evaluate vulnerability. …”
Get full text

Adaptive fusion of multi-cultural visual elements using deep learning in cross-cultural visual communication design by HuPei Wang

“…We address the challenge of creating culturally appropriate digital interfaces by developing a comprehensive framework that combines convolutional neural networks, attention mechanisms, and generative adversarial networks to analyze, extract, and adaptively fuse cultural features from diverse visual communication design elements. …”
Get full text

TWO PERSPECTIVES ON ONE COMPETITION: SLOVENIAN COVERAGE OF ARTISTIC GYMNASTICS AT THE 2008 SUMMER OLYMPICS by Simon Ličen, Andrew C. Billings

“… Televised sports images are complemented by the speech of network-employed announcers who dramatize the narrative and interpret the on-screen events. …”
Get full text

A Novel Deep Learning Model for Human Skeleton Estimation Using FMCW Radar by Parma Hadi Rantelinggi, Xintong Shi, Mondher Bouazizi, Tomoaki Ohtsuki

“…To address this challenge, we propose a novel deep learning framework integrating convolutional neural networks (CNNs), multi-head transformers, and Bi-LSTM networks to enhance spatiotemporal feature representations. …”
Get full text

Research review on intelligent object detection technology for coal mines based on deep learning by Fan ZHANG, Jiarong ZHANG, Haixing CHENG

“…An analysis and comparison of object detection networks based on CNN and Transformer were also conducted. …”
Get full text

Discrimination of Rock Fracture and Blast Events Based on Signal Complexity and Machine Learning by Zilong Zhou, Ruishan Cheng, Xin Cai, Dan Ma, Chong Jiang

“…First, the permutation entropy values of signals at different scale factors are calculated to reflect complexity of signals and constructed into a feature vector set. Secondly, based on the feature vector set, back-propagation neural network (BPNN) as a means of machine learning is applied to establish a discriminator for rock fracture and blast events. …”
Get full text

Mathematical Model for Constructing a Map of the Location of Areas that Make Up the Background Environment for Optical-Electronic Systems by А. V. Siarheyenka, A. Y. Liplianin, А. V. Khizhniak

“…Adequacy assessment was carried out using an artificial neural network developed by the authors, which evaluates the similarity of two images using a normalized similarity index ranging from 0.0 to 1.0, and its k-fold cross-validation. …”
Get full text

Enhancing biodiversity monitoring with CNN: Invasive plant species detection by Konatham Mukunda Sri, marrapu Jayasree, Gopinath M.

“…This research work explores the use of Convolutional Neural Networks (CNNs) to identify invasive species from images. …”
Get full text

iDILI-MT: identifying drug-induced liver injury compounds with a multi-head Transformer by Wanrong Zheng, Fobao Lai

“…We present iDILI-MT (identifying drug-induced liver injury compounds with a multi-head Transformer), a self-contained computational framework that integrates a feed-forward network for sequential feature extraction, a multi-head Transformer encoder for contextual representation learning, and a squeeze-and-excitation attention module for channel-wise feature recalibration. …”
Get full text

Automated detection of epicardial adipose tissue in cardiac CT using ensemble machine learning for improved diagnosis by Jasmine S, Marichamy P

“…An ensemble machine learning model combining Support Vector Machine (SVM) and Artificial Neural Network (ANN) is developed for segmentation. The model’s performance was evaluated using accuracy, precision, recall, Dice score, and classification time. …”
Get full text

YOLO-BS: a traffic sign detection algorithm based on YOLOv8 by Hong Zhang, Mingyin Liang, Yufeng Wang

“…A small object detection layer was incorporated into the YOLOv8 framework to enrich feature extraction. Additionally, a bidirectional feature pyramid network (BiFPN) was integrated into the detection framework to enhance the handling of multi-scale objects and improve the performance in detecting small objects. …”
Get full text

Challenges in Imputation of ICU Time-Series Data: A Comparison of Classical and Machine Learning Approaches by Favio Salinas, Marvin Agristean, Sobhan Moazemi, Steven Kessler, Bastian Dewitz, Hug Aubin, Artur Lichtenberg, Falko Schmid

“…Advanced imputation techniques, such as Bidirectional Recurrent Imputation for Time Series (BRITS), Self-Attention-based Imputation for Time Series (SAITS), and Multi-directional Recurrent Neural Network (M-RNN), show strong performance but are influenced by dataset characteristics like missing patterns and feature distributions. …”
Get full text

A Novel Fuzzy Kernel Extreme Learning Machine Algorithm in Classification Problems by Asli Kaya Karakutuk, Ozer Ozdemir

“…On the original dataset, the proposed method was compared with an extreme learning machine and wavelet neural network, and it was found that the method has remarkable efficiency compared to the other two methods.…”
Get full text

Simplified Deep Learning for Accessible Fruit Quality Assessment in Small Agricultural Operations by Víctor Zárate, Danilo Cáceres Hernández

“…Two approaches were compared: training a convolutional neural network (CNN) from scratch and fine-tuning a pre-trained MobileNetV2 model through transfer learning. …”
Get full text

MRI based early Temporal Lobe Epilepsy detection using DGWO based optimized HAETN and Fuzzy-AAL Segmentation Framework (FASF). by Hasim Khan, Ahmed Ibrahim Alutaibi, Ghanshyam G Tejani, Sunil Kumar Sharma, Ahmad Raza Khan, Fuzail Ahmad, Seyed Jalaleddin Mousavirad

“…To overcome these difficulties, a new Hybrid Attention-Enhanced Transformer Network (HAETN) is introduced for early TLE diagnosis. …”
Get full text

Deep learning model for gastrointestinal polyp segmentation by Zitong Wang, Zeyi Wang, Pengyu Sun

“…Our method employs an encoder-decoder structure with a pre-trained ConvNeXt model as the encoder to learn multi-scale feature representations. The feature maps are passed through a ConvNeXt Block and then through a decoder network consisting of three decoder blocks. …”
Get full text

BRAIN TUMOR DIAGNOSIS BASED ON MEDICAL IMAGES USING VISION TRANSFORMER by Masuma Mammadova, Fargana Abdullayeva

“…The proposed models are tested on the Brain Tumor MRI database containing 7023 histological images open for scientific research and evaluated based on various metrics. Comparative analysis of the evaluation results determines a model that identifies all images containing pathological changes with higher accuracy.…”
Get full text

DRSegNet: A cutting-edge approach to Diabetic Retinopathy segmentation and classification using parameter-aware Nature-Inspired optimization. by Sundreen Asad Kamal, Youtian Du, Majdi Khalid, Majed Farrash, Sahraoui Dhelim

“…This study proposes a novel approach to the identification of DR employing methods such as synthetic data generation, K- Means Clustering-Based Binary Grey Wolf Optimizer (KCBGWO), and Fully Convolutional Encoder-Decoder Networks (FCEDN). This is achieved using Generative Adversarial Networks (GANs) to generate high-quality synthetic data and transfer learning for accurate feature extraction and classification, integrating these with Extreme Learning Machines (ELM). …”
Get full text