Embedded Files
Forest observatory: This involves collection of data on forest ecosystems, including environmental conditions, forest structure, biodiversity, and other relevant information. Smart applications can be integrated into the forest observatory to enhance the accuracy and efficiency of data collection and analysis. Some examples of smart applications for a forest observatory include using sensors, remote sensing, machine learning, and geospatial data to monitor forest health, detect and predict forest fires, protect forests from deforestation and other human activities, monitor wildlife populations, and optimize forest management practices. By using smart applications, a forest observatory can provide valuable insights into the health and well-being of forest ecosystems, helping to inform management decisions and support conservation efforts.
Some smart applications for a forest observatory could include:
Forest monitoring: using sensors to collect data on tree growth, health, and other environmental conditions such as temperature and humidity.
Forest fire detection: using remote sensing and machine learning algorithms to detect and predict forest fires in real-time, allowing for early intervention.
Forest conservation: using geospatial data and AI to monitor and protect forests from deforestation, illegal logging, and other human activities that can harm ecosystems.
Wildlife monitoring: using cameras and other sensors to monitor wildlife populations and track their movements in and around the forest.
Forest management: using data-driven insights to optimize forest management practices, such as identifying areas for reforestation, sustainable harvesting, and reducing the impact of human activities on forest ecosystems.
Deep Learning For Resource Constraint Edge Devices : A Solution For Forest Sound Classification
· D. Ranmal, P. Ranasinghe, T. Paranayapa, D. Meedeniya, C. Perera, "ESC-NAS: Environment Sound Classification Using Hardware-Aware Neural Architecture Search for the Edge", Sensors vol. 24, no. 12, p. 3749, 2024. DOI: https://doi.org/10.3390/s24123749 (pdf) · P. Ranasinghe, T. Paranayapa, D. Ranmal and D. Meedeniya, "Hardware-aware Neural Architecture Search for Sound Classification in Constrained Environments," 2024 International Research Conference on Smart Computing and Systems Engineering (SCSE), Colombo, Sri Lanka, 2024, pp. 1-6, doi: https://doi.org/10.1109/SCSE61872.2024.10550556. (pdf) · T. Paranayapa, P. Ranasinghe, D. Ranmal, D. Meedeniya, C. Perera. A Comparative Study of Preprocessing and Model Compression Techniques in Deep Learning for Forest Sound Classification. Sensors, vol. 24, no. 4:1149, 2024. Doi: https://doi.org/10.3390/s24041149
Awards:
Best Students Research Project of the Year award and
Merit award in the Tertiary Student category, at the NBQSA 2025,
NBQSA, provides recognition to outstanding achievements of individuals and organizations in Sri Lanka who have developed high quality ICT products; provides a window to gain International Recognition of Local ICT products; improves the quality of products & Services to meet International Standards and Identifies young talent and provide them an opportunity to develop their skills in ICT. The competition has been conducted by the Sri Lankan section of the BCS The Chartered Institute for IT. The projects were evaluated with presentations for novelty and creativity. The award ceremony was held on 10th October 2025, in Colombo, Sri Lanka.
Page updated
Google Sites
Report abuse