Lion is simple and has fewer hyperparameters than AdamW and Adafactor. However, in the trainning process, Lion would cause gradient vanishing or gradient explosion on some deep models. The sign function in Lion optimizer is discontinuous which…
Category: 7. Maths
-
Resource management for multi-drone communications in next-generation NOMA-enabled wireless networks
This work seeks to optimize the ground user UAD association and power allocation to maximize the sum-rate of the NOMA multi-UAD network. It can be observed that the joint optimization problem in (7) subject to (8)–(13) is a mixed-integer,…
Continue Reading
-
A big data driven multilevel deep learning framework for predicting terrorist attacks
Predicting the location of an attack before it occurs can play a vital role in its prevention12. This study proposes a predictive model to identify terrorist attack hotspots. These hotspots are identified at three different scales in terms of…
Continue Reading
-
An optimized elliptic curve digital signature strategy for resource-constrained devices
The proposed methodology is based on the implementation of optimized techniques within the Edwards25519 curve, utilizing (\(\mathcal {E}^e\)) and the windowed ECPM method. This approach incorporates advancements in elliptic curve computations,…
Continue Reading
-
An optimized domain-specific shrimp detection architecture integrating conditional GAN and weighted ensemble learning
Experimental assessment for the Shrimp View dataset is vital to validate its efficacy in training models, ensure real-world applicability by testing model generalizability, and identify potential areas for improvement or refinement in the…
Continue Reading
-
A deep dive into artificial intelligence with enhanced optimization-based security breach detection in internet of health things enabled smart city environment
This paper proposes a novel SADDBN-AMOA technique for smart city-based IoHT networks. The main aim of the SADDBN-AMOA technique is to provide a resilient attack detection method in the IoHT environment of smart cities to mitigate security…
Continue Reading
-
Multiobjective optimization of suspension bridges via coupled modeling and dual population multiobjective particle swarm optimization
Proposal and improvement of the algorithm
NSGA-II has strong search capabilities but is highly dependent on parameters and sensitive to parameter selection. MOPSO converges quickly but tends to become trapped in local optima, failing to find the…
Continue Reading
-
A novel mobiles android application for facilitating wheelchair users access to public buildings in urban environments
This section provides an in-depth overview of our proposed app, WellPathJo. The first subsection offers a general summary of the software tools and programming languages utilized in the development of our system, along with an explanation for the…
Continue Reading
-
Detection of low-altitude infrared small targets for UAVs using a density-based artificial bee colony algorithm
This study first preprocesses infrared images to improve image quality and target visibility. Next, a combination of Butterworth Low-Pass Filter (BLPF), Local Background Subtraction (LBS), and Exponential High-Pass Filter (EHPF) is used to…
Continue Reading
-
Bank data protection and fraud identification based on improved adaptive federated learning and WGAN
In order to effectively protect bank data and complete fraud identification, the study first designed an adaptive bank data protection architecture based on FL and DP. Then, based on improved GAN, integrated models, and other technologies,…
Continue Reading