-
3781
RSWD-YOLO: A Walnut Detection Method Based on UAV Remote Sensing Images
Published 2025-04-01“…Through model deployment and testing on small edge devices, we demonstrate the feasibility of our proposed method. The detection algorithm achieves 86.1% mean Average Precision on the walnut dataset while maintaining operational functionality on small edge devices. …”
Get full text
Article -
3782
Intelligent deep learning for human activity recognition in individuals with disabilities using sensor based IoT and edge cloud continuum
Published 2025-08-01“…For feature subset selection, the enhanced honey badger algorithm (EHBA) model is used to effectively reduce dimensionality while retaining critical activity-related features. …”
Get full text
Article -
3783
Ship-DETR: A Transformer-Based Model for EfficientShip Detection in Complex Maritime Environments
Published 2025-01-01“…To address these issues, we propose an effective ship detection algorithm—Ship Detection Transformer (Ship-DETR). …”
Get full text
Article -
3784
Enhanced Vector Quantization for Embedded Machine Learning: A Post-Training Approach With Incremental Clustering
Published 2025-01-01“…While VQ is a technique that reduces model size by grouping similar parameters, incremental clustering, implemented via the AutoCloud K-Fixed algorithm, preserves accuracy during compression. …”
Get full text
Article -
3785
DQN-Based Shaped Reward Function Mold for UAV Emergency Communication
Published 2024-11-01“…The experimental outcomes underscore the prowess of our methodology in effectively curtailing training time while augmenting convergence rates. In summary, our work underscores the potential of leveraging sophisticated virtual environments and refined reinforcement learning techniques to optimize UAVs deployment in emergency communication contexts.…”
Get full text
Article -
3786
Semantic RF Waveform Adaptation in Flying Ad Hoc Networks via Hybrid Knowledge Bases and Deep Reinforcement Learning
Published 2025-01-01“…We propose a framework that jointly optimizes modulation order and cyclic prefix length while considering the semantic importance of transmitted data. …”
Get full text
Article -
3787
Collaborative Relay Beamforming Based on Minimum Power for M2M Devices in Multicell Systems
Published 2013-12-01“…The main contribution of this paper is that we propose an iterative algorithm to jointly optimize the BS and relay beamforming weights with minimizing the BS and relay power under the receive SINR constraints in the perfect channel state information (CSI). …”
Get full text
Article -
3788
Day-Ahead Scheduling of IES Containing Solar Thermal Power Generation Based on CNN-MI-BILSTM Considering Source-Load Uncertainty
Published 2025-04-01“…By integrating the EH–photothermal storage module, the model achieves efficient coupled power generation and thermal storage operation, aiming to optimize economic targets while enhancing the grid’s peak-shaving and valley-filling capabilities and utilization of renewable energy. …”
Get full text
Article -
3789
Edge Computing-Aided Dynamic Wireless Charging and Trip Planning of UAVs
Published 2025-01-01“…Additionally, a dynamic arrival management algorithm is introduced to minimize UAV wait times to enhance operational efficiency. …”
Get full text
Article -
3790
Fast and Efficient Drone Path Planning Using Riemannian Manifold in Indoor Environment
Published 2024-09-01“…This paper introduces an innovative dual-path planning algorithm rooted in a topological three-dimensional Riemannian manifold (T3DRM) to optimize drone navigation in complex environments. …”
Get full text
Article -
3791
Enhanced Spectral Efficiency in RIS-Assisted MIMO Systems Through Joint Precoding and RIS Configuration
Published 2025-01-01“…Water-filling is used for power allocation across channel eigenmodes, while manifold optimization ensures efficient phase shift updates under unit-modulus constraints. …”
Get full text
Article -
3792
Relay-Assisted Wireless Sensor Networks Using KNN-DBSCAN Static Clustering
Published 2025-01-01“…To address this challenge, we propose KDL, a novel hybrid clustering algorithm that combines K-Nearest Neighbor (KNN) and Density-Based Spatial Clustering (DBSCAN) to optimize energy efficiency in WSNs. …”
Get full text
Article -
3793
A Comparative Study of Image Processing Techniques for Javanese Ancient Manuscripts Enhancement
Published 2025-01-01“…Digital preservation to preserve information in ancient manuscripts is often not optimal because of the object’s condition, which has degraded over time. …”
Get full text
Article -
3794
AI-enhanced fire detection and suppression system for autonomous ships
Published 2024-01-01“…In this paper, we introduce an innovative AFDSS that integrates RGB, infrared (IR), and ultraviolet (UV) sensors to reduce false alarms and employ a reinforcement learning algorithm to optimize water spray under sea conditions. …”
Get full text
Article -
3795
Evolution of Computer-Aided Process Planning for Hybrid Additive/Subtractive Process
Published 2020-01-01“…Additionally, the genetic algorithm has been employed to obtain the best path with minimum inspection time. …”
Get full text
Article -
3796
Image-Based Classification of Freshwater Fish Species to Support Feed Recommendation Using Random Forest
Published 2025-08-01“…Notably, catfish, barb, and tilapia classes achieved perfect classification, while pomfret and gourami showed room for improvement due to overlapping visual features. …”
Get full text
Article -
3797
Low power IoT device communication through hybrid AES-RSA encryption in MRA mode
Published 2025-04-01“…The enhanced RSA algorithm replaces the traditional dual-prime system with a triple-prime system, increasing the number of primes while reducing the bit length of each prime. …”
Get full text
Article -
3798
Global trends in machine learning applications for single-cell transcriptomics research
Published 2025-08-01“…Research hotspots concentrated on random forest (RF) and deep learning models, showing transition from algorithm development to clinical applications (e.g., tumor immune microenvironment analysis). …”
Get full text
Article -
3799
Interpretable prediction model for hand-foot-and-mouth disease incidence based on improved LSTM and XGBoost
Published 2025-07-01“…To further enhance the LSTM performance, the GWO is employed to adaptively optimize the key parameters of the LSTM. Thirdly, to fully leverage the advantages of XGBoost in handling nonlinear relationships and high-dimensional data while overcoming its complexities in parameter tuning and slower convergence, the GA is used to optimize the parameters of XGBoost. …”
Get full text
Article -
3800
Continuous Train Positioning Using Visible Light Communication Assisted with Zero Velocity Update
Published 2024-11-01“…A zero-velocity detection condition is adopted to determine whether the train is stationary, and the results of dynamic train positioning are further optimized using the Unscented Kalman Filter (UKF) algorithm. …”
Get full text
Article