Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

A Hybrid Machine Learning Model for Forest Wildfire Detection Using Sounds

Damaševičius Robertas, Qurthobi Ahmad, Maskeliunas Rytis

Annals of Computer Science and Information Systems

2024

Vol. 39

99--106

Forest wildfires pose a significant threat to ecosystems, human settlements, and the global environment. Early detection is crucial for effective mitigation and response. Traditional methods, such as satellite imagery and smoke detectors, have limitations in real-time response and coverage. This paper introduces a novel approach to forest wildfire detection by harnessing the unique sound signatures associated with wildfires. Our proposed model combines the strengths of deep learning techniques with heuristic optimization algorithms. The deep learning component focuses on recognizing the intricate patterns in the sound data, while the heuristic optimization ensures the model's adaptability and efficiency in diverse forest environments. After preprocessing and feature extraction, a deep neural network was trained to recognize wildfire-specific sound patterns. The heuristic optimization, based on a Particle Sworm Optimization (PSO) algorithm, was then integrated to fine-tune the model parameters, ensuring optimal performance. Preliminary results indicate that our hybrid model outperforms traditional methods and existing machine learning models in terms of accuracy, sensitivity, and specificity. The model demonstrates robustness against ambient forest noise, ensuring fewer false alarms. This research not only contributes to the field of environmental monitoring through sound recognition but also showcases the potential of hybrid machine learning models to address complex real-world challenges. Future work will focus on deploying this model in real-time monitoring systems and further refining its capabilities through continuous learning.

Energy-efficient walking over irregular terrain: a case of hexapod robot

Luneckas Mindaugas, Luneckas Tomas, Udris Dainius, Plonis Darius, Maskeliunas Rytis, Damasevicius Robertas

Metrology and Measurement Systems

2019

Vol. 26, nr 4

645--660

Adaptive locomotion over difficult or irregular terrain is considered as a superiority feature of walking robots over wheeled or tracked machines. However, safe foot positioning, body posture and stability, correct leg trajectory, and efficient path planning are a necessity for legged robots to overcome a variety of possible terrains and obstacles. Without these properties, any walking machine becomes useless. Energy consumption is one of the major problems for robots with a large number of Degrees of Freedom (DoF). When considering a path plan or movement parameters such as speed, step length or step height, it is important to choose the most suitable variables to sustain long battery life and to reach the objective or complete the task successfully. We change the settings of a hexapod robot leg trajectory for overcoming small terrain irregularities by optimizing consumed energy and leg trajectory during each leg transfer. The trajectory settings are implemented as a part of hexapod robot simulation model and tested through series of experiments with various terrains of differing complexity and obstacles of various sizes. Our results show that the proposed energy-efficient trajectory transformation is an effective method for minimizing energy consumption and improving overall performance of a walking robot.