Remote sensing semantic segmentation based on multimodal feature alignment and fusion by B. Chang, T. Balz

“…The overarching algorithmic framework is analogous to that of the Unet model. First, the data in different modalities is aggregated and the image size is reduced through the use of multi-level downsampling modules based on the Haar wavelet transform. …”
Get full text

Breath Detection from a Microphone Using Machine Learning by Tomasz Sankowski, Piotr Sulewski, Jan Walczak, Aleksandra Bruska

“…The dataset comprised approximately 1,000 recordings of inhalations, exhalations, and silences between breaths, collected using four different microphones and recorded by three different individuals. …”
Get full text

Unveiling the Efficacy of AI-based Algorithms in Phishing Attack Detection by Tajamul Shahzad, Kashif Aman

“…The increased usage of the Internet has resulted in the emergence of a different kind of theft referred to as cybercrime. …”
Get full text

Dual-Domain deep prior guided sparse-view CT reconstruction with multi-scale fusion attention by Jia Wu, Jinzhao Lin, Xiaoming Jiang, Wei Zheng, Lisha Zhong, Yu Pang, Hongying Meng, Zhangyong Li

“…First, we establish a residual regularization strategy that applies constraints on the difference between the prior image and target image, effectively integrating deep learning-based priors with model-based optimization. …”
Get full text

A New and Tested Ionospheric TEC Prediction Method Based on SegED-ConvLSTM by Yuanhang Liu, Yingkui Gong, Hao Zhang, Ziyue Hu, Guang Yang, Hong Yuan

“…We also examined the effect of using different numbers of space weather feature values in these models. …”
Get full text

Research on Abnormal Ship Brightness Temperature Detection Based on Infrared Image Edge-Enhanced Segmentation Network by Xiaobin Hong, Guanqiao Chen, Yuanming Chen, Ruimou Cai

“…Statistical analysis reveals that the proportion of ship temperature differences predicted by the XGBoost model exceeding 2 is less than 0.020%. …”
Get full text

OcularAge: A Comparative Study of Iris and Periocular Images for Pediatric Age Estimation by Naveenkumar G. Venkataswamy, Poorna Ravi, Stephanie Schuckers, Masudul H. Imtiaz

“…We utilized a longitudinal dataset comprising more than 21,000 near-infrared (NIR) images, collected from 288 pediatric subjects over eight years using two different imaging sensors. A multi-task deep learning framework was employed to jointly perform age prediction and age-group classification, enabling a systematic exploration of how different convolutional neural network (CNN) architectures, particularly those adapted for non-square ocular inputs, capture the complex variability inherent in pediatric eye images. …”
Get full text

Particle swarm optimization with YOLOv8 for improved detection performance of tomato plants by Sarah M. Ayyad, Nada M. Sallam, Samah A. Gamel, Zainab H. Ali

“…Within the past few years, applying deep learning in detecting and classifying tomatoes into different classes has gained popularity. This study aims to build a new framework for the efficient automated harvesting of tomato plants based on deep learning. …”
Get full text

Electric Vehicle Charging Demand Prediction Model Based on Spatiotemporal Attention Mechanism by Yang Chen, Zeyang Tang, Yibo Cui, Wei Rao, Yiwen Li

“…The experimental results indicate that the proposed model has a more powerful comprehensive ability to capture spatiotemporal relationships and improve accuracy and stability in different prediction steps.…”
Get full text

A single flow detection enabled method for DDoS attacks in IoT based on traffic feature reconstruction and mapping by Lixia XIE, Bingdi YUAN, Hongyu YANG, Ze HU, Xiang CHENG, Liang ZHANG

“…To address the slow response time of existing detection modules to Internet of things (IoT) distributed denial of service (DDoS) attacks, their low feature differentiation, and poor detection performance, a single flow detection enabled method based on traffic feature reconstruction and mapping (SFDTFRM) was proposed.Firstly, SFDTFRM employed a queue to store previously arrived flow based on the first in, first out rule.Secondly, to address the issue of similarity between normal communication traffic of IoT devices and DDoS attack traffic, a multidimensional reconstruction neural network model more lightweight compared to the baseline model and a function mapping method were proposed.The modified model loss function was utilized to reconstruct the quantitative feature matrix of the queue according to the corresponding index, and transformed into a mapping feature matrix through the function mapping method, enhancing the differences between different types of traffic, including normal communication traffic of IoT devices and DDoS attack traffic.Finally, the frequency information was extracted using a text convolutional network and information entropy calculation and the machine learning classifier was employed for DDoS attack traffic detection.The experimental results on two benchmark datasets show that SFDTFRM can effectively detect different DDoS attacks, and the average metrics value of SFDTFRM is a maximum of 12.01% higher than other existing methods.…”
Get full text

SiamAHG: adaptive hierarchical graph attention for lightweight siamese tracking by Na Li, Yaofu Fan, Xuhao Chen, Xinyu Liu, Jinglu He

“…AFMRM refines feature maps of different stages and strengthens the model expression by combining multiple convolutional kernels dynamically based upon diverse attentions. …”
Get full text

Generalizable deep learning models for predicting laboratory earthquakes by Chonglang Wang, Kaiwen Xia, Wei Yao, Chris Marone

“…Here, we show a fine-tuned convolutional neural network (CNN) model effectively transfer across different conditions. …”
Get full text

Thyroid nodule classification in ultrasound imaging using deep transfer learning by Yan Xu, Mingmin Xu, Zhe Geng, Jie Liu, Bin Meng

“…Following model fusion, the AUC improved to 0.783 (95% CI: 0.724–0.841). The difference in performance between the fusion model and the traditional machine learning model was statistically significant (p = 0.036). …”
Get full text

A Tank Experiment of the Autonomous Detection of Seabed-Contacting Segments for Submarine Pipelaying Operations by Bo Wang, Jie Wang, Chen Zheng, Ye Li, Jian Cao, Yueming Li

“…The results show that our modules can improve the performance of different neural network models for seabed-contacting segment detection. …”
Get full text

Prediction of foreign currency exchange rates using an attention-based long short-term memory network by Shahram Ghahremani, Uyen Trang Nguyen

“…We conducted comprehensive experiments to evaluate and compare the performance of ALFA against several models used in previous work and against state-of-the-art deep learning models such as temporal convolutional networks (TCN) and Transformer. Experimental results show that ALFA outperforms the baseline models in most cases, across different currency pairs and feature sets, thanks to its attention mechanism that filters out irrelevant or redundant data to focus on important features. …”
Get full text

An automated deep learning model for liver tumor and skin lesion segmentation by R. V. Manjunath, N. Yashaswini Gowda, Manjunath Lakkannavar

“…Abstract Artificial Intelligence plays a vital role in automatically identifying different diseases from a given set of medical images. …”
Get full text

Learning Feature Fusion in Deep Learning-Based Object Detector by Ehtesham Hassan, Yasser Khalil, Imtiaz Ahmad

“…Deep features characterize different regions of interest in a testing image with a rich set of statistical features. …”
Get full text

SMS Spam Detection System Based on Deep Learning Architectures for Turkish and English Messages by Hakan Can Altunay, Zafer Albayrak

“…Short Message Service (SMS) still continues its existence despite the emergence of different messaging services. It plays a part in our lives as a communication service. …”
Get full text

Pipeline and Rotating Pump Condition Monitoring Based on Sound Vibration Feature-Level Fusion by Yu Wan, Shaochen Lin, Yan Gao

“…To overcome this issue, a pipeline and rotating pump condition monitoring method is proposed by extracting and fusing sound and vibration features in different ways. Firstly, a hand-crafted feature set is established from two aspects of sound and vibration. …”
Get full text

Load magnitude and location estimation on additively manufactured circular structures using deep learning by Romaine Byfield, Ibrahim Tansel

“…Two 3D printed stainless steel rocket nozzle type structures with two different sizes and a C shaped tube section were used. …”
Get full text