检索结果-内蒙古大学图书馆

Drone-assisted adaptive object detection and privacy-preserving surveillance in smart cities using whale-optimized deep reinforcement learning techniques

学校读者我要写书评

暂无评论

Scientific Reports 2025年第1期15卷 1-20页

作者： Abu-Khadrah, Ahmed Al-Qerem, Ahmad Hassan, Mohammad R. Ali, Ali Mohd Jarrah, Muath Department of Electrical Engineering College of Engineering Technology Al-Balqa Applied University Amman Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa 13132 Jordan Communications and Computer Engineering Department Faculty of Engineering Al-Ahliyya Amman University Amman Jordan School of Computing Skyline University College Sharjah United Arab Emirates

Drone/ unmanned aerial vehicles (UAV) surveillance for object/ human detection is familiar in large gatherings in the modern cities era. Artificial intelligence algorithms and computer-aided processing will handle the images extracted from the surveillance videos to reveal the object. This article proposes a novel object detection technique (ODT) that assimilates whale optimization algorithms and deep reinforcement learning. The optimization algorithm detects spreading image features from the origin to the end of x×y pixels. This feature extraction is performed until the complete image pixels are covered to identify their existence in the least position. The forging behaviour of the whales is implied to identify highly overlapping features for object/ human detection/ classification. If the overlapping features increase, the whale’s movement is updated from the last-known highest pixel position. The reinforcement learning recommends that new whale agents validate the low overlapping features, such that the forging whale agent moves towards the large overlapping feature. Therefore, the highest overlapping feature-based pixel differentiation is pursued using forging and searching whales to identify objects through collated pixels. © The Author(s) 2025.

关键词： DRL Feature overlap Object detection Whale optimization

The Silent Majority: Demystifying Memorization Effect in the Presence of Spurious Correlations

学校读者我要写书评

暂无评论

arXiv 2025年

作者： You, Chenyu Dai, Haocheng Min, Yifei Sekhon, Jasjeet S. Joshi, Sarang Duncan, James S. Department of Electrical & Computer Engineering Yale University New HavenCT United States Scientific Computing and Imaging Institute University of Utah Salt Lake CityUT United States Department of Statistics and Data Science Yale University New HavenCT United States Department of Biomedical Engineering Yale University New HavenCT United States Department of Applied Mathematics & Statistics Stony Brook University Stony BrookNY United States Department of Computer Science Stony Brook University Stony BrookNY United States

Machine learning models often rely on simple spurious features - patterns in training data that correlate with targets but are not causally related to them, like image backgrounds in foreground classification. This reliance typically leads to imbalanced test performance across minority and majority groups. In this work, we take a closer look at the fundamental cause of such imbalanced performance through the lens of memorization, which refers to the ability to predict accurately on atypical examples (minority groups) in the training set but failing in achieving the same accuracy in the testing set. This paper systematically shows the ubiquitous existence of spurious features in a small set of neurons within the network, providing the first-ever evidence that memorization may contribute to imbalanced group performance. Through three experimental sources of converging empirical evidence, we find the property of a small subset of neurons or channels in memorizing minority group information. Inspired by these findings, we articulate the hypothesis: the imbalanced group performance is a byproduct of "noisy" spurious memorization confined to a small set of neurons. To further substantiate this hypothesis, we show that eliminating these unnecessary spurious memorization patterns via a novel framework during training can significantly affect the model performance on minority groups. Our experimental results across various architectures and benchmarks offer new insights on how neural networks encode core and spurious knowledge, laying the groundwork for future research in demystifying robustness to spurious correlation. © 2025, CC BY.

关键词： Neurons

ICGNN: Graph Neural Network Enabled Scalable Beamforming for MISO Interference Channels

学校读者我要写书评

暂无评论

arXiv 2025年

作者： He, Changpeng Lu, Yang Ai, Bo Dobre, Octavia A. Ding, Zhiguo Niyato, Dusit School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China School of Electronics and Information Engineering Beijing Jiaotong University Beijing100044 China Faculty of Engineering and Applied Science Memorial University St. John’sNLA1C 5S7 Canada Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi127788 United Arab Emirates College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

This paper investigates the graph neural network (GNN)-enabled beamforming design for interference channels. We propose a model termed interference channel GNN (ICGNN) to solve a quality-of-service constrained energy efficiency maximization problem. The ICGNN is two-stage, where the direction and power parts of beamforming vectors are learned separately but trained jointly via unsupervised learning. By formulating the dimensionality of features independent of the transceiver pairs, the ICGNN is scalable with the number of transceiver pairs. Besides, to improve the performance of the ICGNN, the hybrid maximum ratio transmission and zero-forcing scheme reduces the output ports, the feature enhancement module unifies the two types of links into one type, the subgraph representation enhances the message passing efficiency, and the multi-head attention and residual connection facilitate the feature extracting. Furthermore, we present the over-the-air distributed implementation of the ICGNN. Ablation studies validate the effectiveness of key components in the ICGNN. Numerical results also demonstrate the capability of ICGNN in achieving near-optimal performance with an average inference time less than 0.1 ms. The scalability of ICGNN for unseen problem sizes is evaluated and enhanced by transfer learning with limited fine-tuning cost. The results of the centralized and distributed implementations of ICGNN are illustrated. © 2025, CC BY.

关键词： Graph neural networks

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicular Twin Networks

学校读者我要写书评

暂无评论

Lightweight Authenticated Task Offloading in 6G-Cloud Vehicu...

IEEE Conference on Wireless Communications and Networking

作者： Sarah Al–Shareeda Fusun Ozguner Keith Redmill Trung Q. Duong Berk Canberk Electrical and Computer Engineering Department Center for Automotive Research (CAR) The Ohio State University USA BTS Group Turkey Department of AI and Data Engineering Istanbul Technical University Turkey School of Electronics Electrical Engineering and Computer Science Queen's University Belfast UK Faculty of Engineering and Applied Science Memorial University of Newfoundland St. John's NL Canada School of Computing Engineering and The Built Environment Edinburgh Napier University UK

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

Task offloading management in 6G vehicular net-works is crucial for maintaining network efficiency, particularly as vehicles generate substantial data. Integrating secure communication through authentication introduces additional computational and communication overhead, significantly impacting offloading efficiency and latency. This paper presents a unified framework incorporating lightweight Identity-Based Cryptographic (IBC) authentication into task offloading within cloud-based 6G Vehicular Twin Networks (VTNs). Utilizing Proximal Policy Optimization (PPO) in Deep Reinforcement Learning (DRL), our approach optimizes authenticated offloading decisions to minimize latency and enhance resource allocation. Performance evaluation under varying network sizes, task sizes, and data rates reveals that IBC authentication can reduce offloading efficiency by up to 50 % due to the added overhead. Besides, increasing network size and task size can further reduce offloading efficiency by up to 91.7%. As a countermeasure, increasing the transmission data rate can improve the offloading performance by as much as 63%, even in the presence of authentication overhead. The code for the simulations and experiments detailed in this paper is available on GitHub for further reference and reproducibility [1].

关键词： 6G mobile communication Performance evaluation Identity-based encryption Authentication Deep reinforcement learning Reproducibility of results Resource management Cryptography Optimization Software development management

Kilometer-Scale E3SM Land Model Simulation over North America

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Wang, Dali Wang, Chen Cao, Qinglei Schwartz, Peter Yuan, Fengming Krishna, Jayesh Wu, Danqing Ricciuto, Danial Thornton, Peter Kao, Shih-Chieh Thornton, Michele Mohror, Kathryn Environmental Sciences Division Oak Ridge National Laboratory Oak RidgeTN37831 United States Center for Applied Scientific Computing Lawrence Livermore National Laboratory LivermoreCA United States Department of Computer Science Saint Louis University Saint LouisMO United States Mathematics and Computer Sciences Argonne National Laboratory ArgonneIL United States

The development of a kilometer-scale E3SM Land Model (km-scale ELM) is an integral part of the E3SM project, which seeks to advance energy-related Earth system science research with state-of-the-art modeling and simulation capabilities on exascale computing systems. Through the utilization of high-fidelity data products, such as atmospheric forcing and soil properties, the km-scale ELM plays a critical role in accurately modeling geographical characteristics and extreme weather occurrences. The model is vital for enhancing our comprehension and prediction of climate patterns, as well as their effects on ecosystems and human activities. This study showcases the first set of full-capability, km-scale ELM simulations over various computational domains, including simulations encompassing 21.6 million land gridcells, reflecting approximately 21.5 million square kilometers of North America at a 1 km × 1 km resolution. We present the largest km-scale ELM simulation using up to 100,800 CPU cores across 2,400 nodes. This continental-scale simulation is 300 times larger than any previous studies, and the computational resources used are about 400 times larger than those used in prior efforts. Both strong and weak scaling tests have been conducted, revealing exceptional performance efficiency and resource utilization. The km-scale ELM uses the common E3SM modeling infrastructure and a general data toolkit known as KiloCraft. Consequently, it can be readily adapted for both fully-coupled E3SM simulations and data-driven simulations over specific areas, ranging from a single gridcell to the entire North America. © 2025, CC BY.

关键词： Digital elevation model

Multi-Layer Perceptron Regression Model for Material Characterization in the Microwave Frequency Range with Cross-Dataset Validation

学校读者我要写书评

暂无评论

Multi-Layer Perceptron Regression Model for Material Charact...

International Youth Conference on Radio Electronics, Electrical and Power Engineering (REEPE)

作者： Hanima Kannan C H Deepa Gupta Parul Mathur Dhanesh G Kurup Tilesh Sanjay Chaudhari Priyanka Mathur Department of Electronics and Communication Engineering RF and Wireless Systems Laboratory Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru India Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India Department of Chemical Engineering Creative and Advanced Research Based on Nanomaterials Laboratory Indian Institute of Technology Hyderabad School of Engineering and Applied Science Bennett University Greater Noida U.P. India

ISBN: (数字)9798331531836

ISBN: (纸本)9798331531843

This paper presents a Multi-Layer Perceptron (MLP) based regression model for characterizing materials at micrwave frequency range. A mathematical model and experimental setup of the Open-Ended Coaxial Probe (OECP) sensor interacting with the material under test (MUT) generate a cross-dataset to validate the MLP regression model, utilizing the frequency-dependent complex dielectric constant for material characterization. This paper utilizes the frequency-dependent response of the OECP sensor (scattering parameters) as input features for the MLP model, while the complex dielectric constant of the MUT serves as the output feature. The optimized MLP model has an $R^{2}$ of 99.991% and MSE of $6.65 \times 10^{-5}$ , with predictions closely aligning with literature values for standard loads such as distilled water, acetone, and ethanol, obtained using a commercially available dielectric assessment software kit. This cost-effective model enables precise dielectric property estimation, with future work extending to unknown materials, mixtures, and electrolyte solutions.

关键词： Power engineering Dielectric constant Predictive models Mathematical models Software Scattering parameters Probes Permittivity Standards Load modeling

FedDA-TSformer: Federated Domain Adaptation with Vision TimeSformer for Left Ventricle Segmentation on Gated Myocardial Perfusion SPECT Image

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Yehong Zhao, Chen Dhakal, Rochak Zhao, Min Hung, Guang-Uei Jiang, Zhixin Zhou, Weihua Department of Computer Science Kennesaw State University MariettaGA United States Department of Applied Computing Michigan Technological University HoughtonMI United States Department of Nuclear Medicine Xiangya Hospital Central South University Changsha China Department of Nuclear Medicine Chang Bing Show Chwan Memorial Hospital Changhua Taiwan Nanjing China Center for Biocomputing and Digital Health Institute of Computing and Cyber-systems Health Research Institute Michigan Technological University HoughtonMI United States

Background and Purpose: Functional assessment of the left ventricle using gated myocardial perfusion (MPS) single-photon emission computed tomography relies on the precise extraction of the left ventricular contours while simultaneously ensuring the security of patient data. Methods: In this paper, we introduce the integration of Federated Domain Adaptation with TimeSformer, named "FedDA-TSformer" for left ventricle segmentation using MPS. FedDA-TSformer captures spatial and temporal features in gated MPS images, leveraging spatial attention, temporal attention, and federated learning for improved domain adaptation while ensuring patient data security. In detail, we employed Divide-Space-Time-Attention mechanism to extract spatio-temporal correlations from the multi-centered MPS datasets, ensuring that predictions are spatio-temporally consistent. To achieve domain adaptation, we align the model output on MPS from three different centers using local maximum mean discrepancy (LMMD) loss. This approach effectively addresses the dual requirements of federated learning and domain adaptation, enhancing the model's performance during training with multi-site datasets while ensuring the protection of data from different hospitals. Results: Our FedDA-TSformer was trained and evaluated using MPS datasets collected from three hospitals, comprising a total of 150 subjects. Each subject's cardiac cycle was divided into eight gates. The model achieved Dice Similarity Coefficients (DSC) of 0.842 and 0.907 for left ventricular (LV) endocardium and epicardium segmentation, respectively. Conclusion: Our proposed FedDA-TSformer model addresses the challenge of multi-center generalization, ensures patient data privacy protection, and demonstrates effectiveness in left ventricular (LV) segmentation. © 2025, CC BY.

关键词： Single photon emission computed tomography

Trade-offs between machine learning and deep learning for mental illness detection on social media

学校读者我要写书评

暂无评论

Scientific Reports 2025年第1期15卷 1-14页

作者： Ding, Zhanyi Wang, Zhongyan Zhang, Yeyubei Cao, Yuchen Liu, Yunchong Shen, Xiaorui Tian, Yexin Dai, Jianglai Center for Data Science New York University NY United States School of Engineering and Applied Science University of Pennsylvania Philadelphia United States Department of EECS University of California Berkeley Berkeley United States Khoury College of Computer Science Northeastern University Boston United States College of Computing Georgia Institute of Technology Atlanta United States

Social media platforms provide valuable insights into mental health trends by capturing user-generated discussions on conditions such as depression, anxiety, and suicidal ideation. Machine learning (ML) and deep learning (DL) models have been increasingly applied to classify mental health conditions from textual data, but selecting the most effective model involves trade-offs in accuracy, interpretability, and computational efficiency. This study evaluates multiple ML models, including logistic regression, random forest, and LightGBM, alongside DL architectures such as ALBERT and Gated Recurrent Units (GRUs), for both binary and multi-class classification of mental health conditions. Our findings indicate that ML and DL models achieve comparable classification performance on medium-sized datasets, with ML models offering greater interpretability through variable importance scores, while DL models are more robust to complex linguistic patterns. Additionally, ML models require explicit feature engineering, whereas DL models learn hierarchical representations directly from text. Logistic regression provides the advantage of capturing both positive and negative associations between features and mental health conditions, whereas tree-based models prioritize decision-making power through split-based feature selection. This study offers empirical insights into the advantages and limitations of different modeling approaches and provides recommendations for selecting appropriate methods based on dataset size, interpretability needs, and computational constraints. © The Author(s) 2025.

关键词： Deep learning Feature importance Machine learning Mental health detection Model interpretability Natural language processing Social media

Early detection of Alzheimer’s disease progression stages using hybrid of CNN and transformer encoder models

学校读者我要写书评

暂无评论

Scientific Reports 2025年第1期15卷 1-22页

作者： Almalki, Hassan Khadidos, Alaa O. Alhebaishi, Nawaf Senan, Ebrahim Mohammed Department of Information Technology College of Technology for Communications and Information Technical and Vocational training Corporation Riyadh Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Center of Research Excellence in Artificial Intelligence and Data Science King Abdulaziz University Jeddah Saudi Arabia Department of Computer Science College of Applied Sciences Hajjah University Hajjah Yemen Department of Artificial Intelligence Faculty of Computer Science and Information Technology Al-Razi University Sana’a Yemen

Alzheimer’s disease (AD) is a neurodegenerative disorder that affects memory and cognitive functions. Manual diagnosis is prone to human error, often leading to misdiagnosis or delayed detection. MRI techniques help visualize the fine tissues of the brain cells, indicating the stage of disease progression. Artificial intelligence techniques analyze MRI with high accuracy and extract subtle features that are difficult to diagnose manually. In this study, a modern methodology was designed that combines the power of CNN models (ResNet101 and GoogLeNet) to extract local deep features and the power of Vision Transformer (ViT) models to extract global features and find relationships between image spots. First, the MRI images of the Open Access Imaging Studies Series (OASIS) dataset were improved by two filters: the adaptive median filter (AMF) and Laplacian filter. The ResNet101 and GoogLeNet models were modified to suit the feature extraction task and reduce computational cost. The ViT architecture was modified to reduce the computational cost while increasing the number of attention vertices to further discover global features and relationships between image patches. The enhanced images were fed into the proposed ViT-CNN methodology. The enhanced images were fed to the modified ResNet101 and GoogLeNet models to extract the deep feature maps with high accuracy. Deep feature maps were fed into the modified ViT model. The deep feature maps were partitioned into 32 feature maps using ResNet101 and 16 feature maps using GoogLeNet, both with a size of 64 features. The feature maps were encoded to recognize the spatial arrangement of the patch and preserve the relationship between patches, helping the self-attention layers distinguish between patches based on their positions. They were fed to the transformer encoder, which consisted of six blocks and multiple vertices to focus on different patterns or regions simultaneously. Finally, the MLP classification layers classify each

关键词： Alzheimer’s disease CNN-ViT GoogLeNet Hybrid Models ResNet101 Vision transformer