Weakly Supervised Semantic Segmentation of Remote Sensing Images Using Siamese Affinity Network by Zheng Chen, Yuheng Lian, Jing Bai, Jingsen Zhang, Zhu Xiao, Biao Hou

“…To address the issues of inaccurate and incomplete seed areas and unreliable pseudo masks in WSSS, we propose a novel WSSS method for remote sensing images based on the Siamese Affinity Network (SAN) and the Segment Anything Model (SAM). First, we design a seed enhancement module for semantic affinity, which strengthens contextual relevance in the feature map by enforcing a unified constraint principle of cross-pixel similarity, thereby capturing semantically similar regions within the image. …”
Get full text

Deep learning and transfer learning for device-free human activity recognition: A survey by Jianfei Yang, Yuecong Xu, Haozhi Cao, Han Zou, Lihua Xie

“…Traditional machine learning has made significant progress by heuristic hand-crafted features and statistical models, but it suffers from the limitation of manual feature design. …”
Get full text

Improved MobileVit deep learning algorithm based on thermal images to identify the water state in cotton by Kaijun Jin, Jihong Zhang, Ningning Liu, Miao Li, Zhanli Ma, Zhenhua Wang, Jinzhu Zhang, Feihu Yin

“…These enhancements aim to improve model performance while maintaining its compact size. …”
Get full text

Global and regional perspectives on optimizing thermo-responsive dynamic windows for energy-efficient buildings by Yuan Gao, Jacob C. Jonsson, D. Charlie Curcija, Simon Vidanovic, Tianzhen Hong

“…World heatmap results, derived from well-trained artificial neural network models, reveal that thermo-responsive windows are especially useful in climates where buildings demand both heating and cooling energy, whereas thermo-responsive windows with optimal transition temperatures show no dynamic features in most of low-latitude tropical regions. …”
Get full text

MVCG-SPS: A Multi-View Contrastive Graph Neural Network for Smart Ponzi Scheme Detection by Xiaofang Jiang, Wei-Tek Tsai

“…Our approach incorporates three key innovations: (1) Meta-Path-Based View Construction, which constructs multiple views of the data using meta-paths to capture different semantic relationships; (2) Reinforcement-Learning-Driven Multi-View Aggregation, which adaptively combines features from multiple views by optimizing aggregation weights through reinforcement learning; and (3) Multi-Scale Contrastive Learning, which aligns embeddings both within and across views to enhance representation robustness and improve anomaly detection performance. …”
Get full text

Machine learning driven dashboard for chronic myeloid leukemia prediction using protein sequences. by Waqar Ahmad, Abdul Raheem Shahzad, Muhammad Awais Amin, Waqas Haider Bangyal, Tahani Jaser Alahmadi, Saddam Hussain Khan

“…We also take into consideration the identification and handling of outliers, as well as the validation of feature selection using the Pearson Correlation Coefficient (PCA). …”
Get full text

A City-scale and Harmonized Dataset for Global Electric Vehicle Charging Demand Analysis by Zihan Guo, Linlin You, Rui Zhu, Yan Zhang, Chau Yuen

Get full text

Joint neural denoising and consolidation for portable handheld laser scan by T. Zhang, S. Filin

“…Mobile and handheld laser scanners document scenes in an economical manner, but the data they acquire are often noisy, of low resolution, unevenly distributed, and feature voids within the scanned scene. These characteristics challenge such applications as feature extraction and 3D modeling when processing the raw pointset. …”
Get full text

Uncertainty Avoider Defuzzification of General Type-2 Multi-Layer Fuzzy Membership Functions for Image Segmentation by Sirwan Mohammad Kekshar, Sadegh Abdollah Aminifar

“…To demonstrate the effectiveness of the proposed multilayer approach, it has been applied to image segmentation, a critical aspect of image processing often hindered by challenges like noise, low contrast, and blurred features. The proposed multilayer type-2 fuzzy method based on the uncertainty avoider method has shown very good performance in image segmentation, especially in the case of high-noise images, compared to type one Fuzzy C-Means (FCM) and type-2 FCM methods as well as hybrid methods presented recently in the literature.…”
Get full text

Inverse link prediction with graph convolutional networks for knowledge-preserving sparsification in cheminformatics by Elnaz Bangian Tabrizi, Mehrdad Jalali, Mahboobeh Houshmand

“…Validated on MOF similarity graphs, the sparsified graphs maintain structural integrity and support robust performance across both graph-based (GCN, GraphRAGE) and non-graph-based (Gradient Boosting Trees, Logistic Regression, Naïve Bayes, Deep Neural Networks) machine learning models for tasks such as pore limiting diameter prediction. …”
Get full text

The impact of artificial intelligence on behavioral intentions to use mobile banking in the post-COVID-19 era by Johannes Schrank, Johannes Schrank

“…The study extends the Unified Theory of Acceptance and Use of Technology (UTAUT) framework by incorporating two key characteristics of AI, i.e. perceived intelligence and perceived anthropomorphism.MethodsIt uses the UTAUT as a theoretical framework, and extends it by integrating core features of AI. Data has been collected from 412 respondents in Thailand, and structural equation modeling has been employed for the data analysis.ResultsThe findings reveal significant positive effects of performance expectancy, effort expectancy, social influence, facilitating conditions, trust, perceived privacy, perceived intelligence and anthropomorphism of AI on users’ behavioral intentions to use mobile banking. …”
Get full text

Audio Deepfake Detection Using Deep Learning by Ousama A. Shaaban, Remzi Yildirim

“…These operations are followed by residual connections, which enhance the network's performance. The self‐attention modules are trained in a layered way alongside these fundamental layers to detect multi‐headed attention within audio frames. …”
Get full text

Edge-aware joint neural denoising and normal estimation for mobile and handheld laser point clouds by T. Zhang, S. Filin

“…Performance analysis demonstrates that over 93% of points deviate by ≤ 1 cm – double the percentage achieved by state-of-the-art denoising networks.…”
Get full text

Implementation of Adaptive Short Time Fourier Transform and Sigmoid based Kernel Support Vector Machine for Radar Signal Identification by AHMAD Ashraf Adam, MUHAMMAD Farouk Isah

“…At -5dB and above, the performance of 100% classification accuracy for all higher SNR values is achieved. …”
Get full text

Real-Time Run-Off-Road Risk Prediction Based on Deep Learning Sequence Forecasting Approach by Yunteng Chen, Lijun Wei, Qiong Bao, Huansong Zhang

“…This study extracted 660 near-roadside lane-changing samples from the high-D natural driving dataset. The performance of sequence and status prediction for ROR risk was compared across five mainstream deep learning models: LSTM, CNN, LSTM-CNN, CNN-LSTM-MA, and Transformer. …”
Get full text

Predicting the Behavior of Road Users in Rural Areas for Self-Driving Cars by S. A. Ivanov, B. Rasheed

“…The presented analysis described the basic features of the prediction module in the rural road domain, showed a comparison of popular models, and discussed its applicability to new conditions. …”
Get full text

Study on real-time warning system of blind path for the visually impaired based on improved deep residual shrinkage network by Zhezhou Yu, Fuwang Wang

“…DB-DRSN replaces the convolutional hidden layer in the original residual shrinkage module with dense blocks and integrates dense connections to optimize the use of both shallow and deep features. The results show that the system achieves an accuracy of 96.72% in recognizing the difficulties faced by the visually impaired, significantly outperforming traditional models. …”
Get full text

A high-throughput ResNet CNN approach for automated grapevine leaf hair quantification by Nagarjun Malagol, Tanuj Rao, Anna Werner, Reinhard Töpfer, Ludger Hausmann

“…This approach achieved an overall model prediction accuracy of 95.41%. As final validation, 10,120 input images from a segregating F1 biparental population were used to evaluate the algorithm performance. …”
Get full text

Dynamic Response and Stress Evolution of RPC Slabs Protected by a Three-Layered Energy-Dissipating System Based on the SPH-FEM Coupled Method by Dongmin Deng, Hanqing Zhong, Shuisheng Chen, Zhixiang Yu

“…A three-dimensional Smoothed Particle Hydrodynamics–Finite Element Method (SPH-FEM) coupled numerical model is developed in LS-DYNA (Livermore Software Technology Corporation, Livermore, CA, USA, version R13.1.1), with its validity rigorously verified. …”
Get full text

GC-Like LDPC Code Construction and its NN-Aided Decoder Implementation by Yu-Lun Hsu, Li-Wei Liu, Yen-Chin Liao, Hsie-Chia Chang

“…Not only eliminating the second minimum value in the check node update process for reducing hardware complexity, our approach featuring a fast-convergent shuffled scheduling method proposed to enhance convergence speed can also maintain similar decoding performance as compared to the traditional normalized min-sum algorithm. …”
Get full text