Detection of mare parturition through balanced multi-scale feature fusion based on improved Libra RCNN. by Buyu Wang, Weijun Duan, Jian Zhao, Dongyi Bai

“…The model achieved a mean average precision of 86.26% in scenarios of imbalanced positive and negative samples of mare parturition data, subtle parturition feature differences, and multi-scale data distribution, with a detection speed of 15.06 images per second and an average recall rate of 98.17%. …”
Get full text

PhishingGNN: Phishing Email Detection Using Graph Attention Networks and Transformer-Based Feature Extraction by Mejdl Safran, Abdulbaset Musleh

Get full text

Comprehensive Feature-Driven PCOS Predictor: A Reinforcement Learning-Based Binary Equilibrium Optimization Approach by S. Reka, T. Suriya Praba, Krishna Kumar Manchala, Anna Venkateswarlu

“…However, finding an efficient solution is still difficult due to noise and redundant information which may degrade the model performance. In this article, a hybrid filter-wrapper approach is proposed to identify the optimal attributes. …”
Get full text

MSU-Net: A Synthesized U-Net for Exploiting Multi-Scale Features in OCT Image Segmentation by Dejie Chen, Xiangping Chen, Hao Gu, Su Zhao, Hao Jiang

“…The proposed framework enhances performance through two innovations: 1) replacement of standard encoder blocks with a multi-branch module combining heterogeneous convolutions to achieve multi-scale receptive field diversification; 2) redesign of skip connections through a pyramid fusion module with spatial attention for adaptive multi-level feature weighting. …”
Get full text

High-Resolution Mapping of Topsoil Sand Content in Planosol Regions Using Temporal and Spectral Feature Optimization by Jiaying Meng, Nanchen Chu, Chong Luo, Huanjun Liu, Xue Li

“…Finally, the prediction accuracy was further improved to R² = 0.79 and RMSE = 1.05% by multi-temporal-multi-feature fusion modeling. The spatial distribution map of sand content generated by the optimized model shows that areas with high sand content are primarily located in the northern and central regions of Shuguang Farm. …”
Get full text

TCL: Time-Dependent Clustering Loss for Optimizing Post-Training Feature Map Quantization for Partitioned DNNs by Oscar Artur Bernd Berg, Eiraj Saqib, Axel Jantsch, Irida Shallari, Silvia Krug, Isaac Sanchez Leal, Mattias O'Nils

“…The proposed framework offers a scalable solution for deploying high-performance AI models on IoT devices, extending the feasibility of real-time inference in resource-constrained environments.…”
Get full text

DFDA-AD: An Approach with Dual Feature Extraction Architecture and Dual Attention Mechanism for Image Anomaly Detection by Babak Masoudi

“…The evaluation of the model's performance was done on the MVTec AD data set, and the results of the evaluations for anomaly detection and localization were satisfactory compared to several other approaches that have been recently proposed.…”
Get full text

Advancing frontline early pancreatic cancer detection using within-class feature extraction in FTIR spectroscopy by Zheng Tang, Edward Duckworth, Benjamin Mora, Bilal Al - Sarireh, Matthew Mortimer, Debdulal Roy

Get full text

Self-Supervised ECG Anomaly Detection Based on Time-Frequency Specific Waveform Mask Feature Fusion by Chongrui Tian, Fengbin Zhang

“…Specifically, the proposed method incorporates an auto-encoder module, a time-frequency mask module, and a contrastive learning module to extract masked time-frequency domain features of ECG signals. The model then reconstructs the signal using time-frequency feature fusion and employs contrastive learning to structure the feature space, ensuring abnormal distributions are effectively learned. …”
Get full text

Identification of candidates with hepatocellular carcinoma to receive TACE combined with MWA by assessing tumor burden and radiologic features by Chao An, Lujun Shen, Qifeng Chen, Yiquan Jiang, Chen Li, He Ren, Peihong Wu, Xi Liu

“…Moreover, the TBR score provided greater net benefit across the range of reasonable threshold probabilities than other models. Based on cutoff values of 32 and 74 centiles of the TBR score, the cohort was divided into low-, middle-, and high-risk strata, which provide consistent performance in survival discrimination across different patient subgroups. …”
Get full text

Melanoma Skin Cancer Recognition with a Convolutional Neural Network and Feature Dimensions Reduction with Aquila Optimizer by Jalaleddin Mohamed, Necmi Serkan Tezel, Javad Rahebi, Raheleh Ghadami

“…<b>Methods:</b> The proposed method utilized CNNs to extract features from melanoma images, while the AO was employed to reduce feature dimensionality, enhancing the performance of the model. …”
Get full text

Beyond Granularity: Enhancing Continuous Sign Language Recognition with Granularity-Aware Feature Fusion and Attention Optimization by Yao Du, Taiying Peng, Xiaohui Hu

“…In addition, applying a vanilla Transformer to sequence modeling in cSLR exhibits weak performance because specific video frames could interfere with the attention mechanism. …”
Get full text

Hearing vocals to recognize schizophrenia: speech discriminant analysis with fusion of emotions and features based on deep learning by Jie Huang, Yanli Zhao, Zhanxiao Tian, Wei Qu, Xia Du, Jie Zhang, Meng Zhang, Yunlong Tan, Zhiren Wang, Shuping Tan

“…In this study, a discriminative model of schizophrenic speech based on deep learning is developed, which combines different emotional stimuli and features. …”
Get full text

Prediction of clinical stages of cervical cancer via machine learning integrated with clinical features and ultrasound-based radiomics by Maochun Zhang, Qing Zhang, Xueying Wang, Xiaoli Peng, Jiao Chen, Hanfeng Yang

“…Abstract To investigate the prediction of a model constructed by combining machine learning (ML) with clinical features and ultrasound radiomics in the clinical staging of cervical cancer. …”
Get full text

Machine and Deep Learning-Based Seizure Prediction: A Scoping Review on the Use of Temporal and Spectral Features by Yousif A. Saadoon, Mohamad Khalil, Dalia Battikh

“…Emphasizing convolutional neural networks (CNNs) and other deep architectures, we explore the role of time-domain and frequency-domain features, such as wavelet transforms, short-time Fourier transforms, and spectrogram representations, in improving model performance. …”
Get full text

Transferring enhanced material knowledge via image quality enhancement and feature distillation for pavement condition identification by Zejiu Wu, Yuxing Zou, Boyang Liu, Zhijie Li, Donghong Ji, Hongbin Zhang

“…The IQEFD model first leverages ConvNeXt as its backbone to extract high-quality basic features. …”
Get full text

Validation of predictors of successful weaning from mechanical circulatory support and histological features in lymphocytic fulminant myocarditis by Masatoshi Minamisawa, Soichiro Ebisawa, Hirohiko Motoki, Koichiro Kuwahara, Kazuhiro Kimura, Sho Suzuki, Takeshi Uehara, Nami Teraoka, Kii Ito, Ken Nishikawa, Yukari Okuma, Koji Yoshie, Tatsuichiro Seto, Hiroshi Imamura

Get full text

Causality-Driven Feature Selection for Calibrating Low-Cost Airborne Particulate Sensors Using Machine Learning by Vinu Sooriyaarachchi, David J. Lary, Lakitha O. H. Wijeratne, John Waczak

“…We evaluated the predictive performance and generalizability of these causally optimized models, observing improvements in both while reducing the number of input features, thus adhering to the Occam’s razor principle. …”
Get full text

YOLO-v4 Small Object Detection Algorithm Fused With L-α by ZHANG Ning, YU Ming, REN Honge, AO Rui, ZHAO Long

“… The detection ability for small object is still need to be improved urgently in spite of the rapidly developing object detection technology based on deep learning at present.Compared with large objects, small object detection tasks hold drawbacks of low resolution and feature loss which leads to that many general algorithms cannot be directly applied to small object detection.The feature pyramid fusion can effectively combine the features of deep and shallow layers to enhance the performance.To solve the problem most models existing ignoring the imbalance of information during the feature fusion between adjacent layers, it is proposed to integrate the idea of fusion factor into the PANet of YOLOv4, use the fusion factor L-αto control the amount of information transmitted from the deep layer to the shallow, so as to effectively improve the efficiency of information fusion and enhance the ability of YOLO-v4 for small objects detection.With the addition of L-αin YOLO- V4 model, the experiment results show that the APtiny50and APsmall50on the TinyPerson are improved by 2.14% and 1.85% respectively, while the AP and APS on the MS COCO are separately increased by 1.4% and 2.7%.It is proved that this improved method is effective for small object detection with the evidence of better result than other small object detection algorithms.…”
Get full text

Diagnosis of Malignant Endometrial Lesions from Ultrasound Radiomics Features and Clinical Variables Using Machine Learning Methods by Shanshan Li, Jiali Wang, Li Zhou, Hui Wang, Xiangyu Wang, Jian Hu, Qingxiu Ai

“…And Random Forest model algorithms have demonstrated excellent performance in identifying benign and malignant changes in endometrial tissue. …”
Get full text