Nonlinear Intelligent Inversion Method and Practice for In-situ Stress in Stratified Rock Masses with Deep Valley

Rock Mechanics and Rock Engineering, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 19, 2024

Язык: Английский

---

Inchworm Search Algorithm: A Memory-Saving Nature-Inspired Metaheuristic Algorithm for Real-World Online Optimization Problems

Опубликована: Янв. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Язык: Английский

---

A novel similarity algorithm for triangular cloud models based on exponential closeness and cloud drop variance

Complex & Intelligent Systems, Год журнала: 2024, Номер 10(4), С. 5171 - 5194

Опубликована: Апрель 20, 2024

Abstract Cloud model similarity algorithm is an important part of cloud modelling theory. Most the existing algorithms suffer from poor discriminability, classification, unstable results, and low time efficiency. In this paper, a new proposed that considers triangular distance shape. First, according to $${{D}}_{\text{T}}$$ D T formula, exponential closeness measure defined, with which models characterized. Then, shape calculated variance drops. Finally, two similarities are synthesized define for determining formula based on (DD T STCM). stability, efficiency theoretical interpretability taken as evaluation indices. Equipment security system capability experiment, differentiation simulation experiment series classification accuracy set up verify effectiveness in terms four above aspects. The experimental results show DD STCM has good excellent effects. series, average reaches 91.78%, at least 2.78% higher than those other seven commonly used algorithms. CPU running also extremely high, group training always order milliseconds, effectively reduces cost. case study conducted analyse risk assessment problem China’s island microgrid industry, line human cognition have value engineering applications. Graphical abstract

Язык: Английский

---

Intelligent device recognition of internet of things based on machine learning

Intelligent Systems with Applications, Год журнала: 2024, Номер 22, С. 200368 - 200368

Опубликована: Апрель 12, 2024

With the rapid popularization and application of Internet Things technology, smart devices have become an indispensable part people's daily lives. Therefore, it is crucial to accurately identify these as their numbers continue grow. The research aimed introduce a lightweight method for identifying based on network flow characteristics scheduling algorithms. This can improve device identification accuracy while maintaining high efficiency. constructed comprehensive optimization algorithm selection framework achieve performance in different scenarios. took into account many factors, including traffic characteristics, requirements, system efficiency, ensure flexible adaptation scenarios optimize overall performance. Research results showed that proposed had 96.8 % at 1-minute intervals, which increased 99.7 10-minute reached 99.9 both 30-minute 60-minute intervals. In 100 experiments, improved by average 1.5 compared with baseline. fingerprint recognition, long short-term memory exceeded 90 %, area under curve 0.99. Most over 95 recall rate remained around effectiveness study was further verified. not only efficiency but also provided powerful solutions field security. provides useful guidance practical applications related fields.

Язык: Английский

---

Optimization of End Milling Parameters Using African Vulture Optimization Algorithm

Lecture notes in networks and systems, Год журнала: 2024, Номер unknown, С. 310 - 320

Опубликована: Янв. 1, 2024

Язык: Английский

---