Wyniki wyszukiwania - Biblioteka Nauki

Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: green products

Sortuj według:

Ogranicz wyniki do:

Electric power consumption forecasting for industries in Ahmednagar City: a preliminary study

100%

Panchal R. , Kumar B.

tom Vol. 49, No. 4

555--576

This paper reports from the study dealing with the preliminary investigations, concerning forecasting of electric power consumption of some industries from Ahmednagar city. The investigations regarding the potential energy consumption are mainly directed to three energy-related aspects or drives, namely: (i) energy policy, (ii) production of green and non-green products, and (iii) production of FMCG (fast-moving consumer goods) and non- FMCG products. The here proposed methodology is implemented in three phases. The first, initial phase concerns the preparation of the questionnaire that clearly addresses the effects of the aforementioned drives on various industries. The issues mentioned in the questionnaire are closely related to the industries from Ahmednagar city. In the second phase, the prepared questionnaire was distributed to the industries of Ahmednagar city. In the questionnaire, all the questions are made mandatory and subsequently, the industrial authorities are demanded to fill up the precise information as much as possible. The responses from the concerned industries related to power management are then subject to analysis. The analysis is done with the focus on correlation coefficients. Thereby, determining the correlation between different factors helps to arrive a conclusion regarding the dependencies of various factors in the potential power consumption of industries in Ahmednagar city.

Applying Knowledge Distillation to Improve Weed Mapping With Drones

67%

Castellano G. , De Marinis P. , Vessio G.

tom Vol. 35

393--400

Non-invasive remote sensing using UAVs can be used in precision agriculture to observe crops in visible and non-visible spectra. This paper investigates the effectiveness of state-of-the-art knowledge distillation techniques for mapping weeds with drones, an essential component of precision agriculture that employs remote sensing to monitor crops and weeds. The study introduces a lightweight Vision Transformer-based model that achieves optimal weed mapping capabilities while maintaining minimal computation time. The research shows that the student model effectively learns from the teacher model using the WeedMap dataset, achieving accurate results suitable for mobile platforms such as drones, with only 0.5 GMacs compared to 42.5 GMacs of the teacher model. The trained models obtained an F1 score of 0.863 and 0.631 on two data subsets, with a performance improvement of 2 and 7 points, respectively, over the undistilled model. The study results suggest that developing efficient computer vision algorithms on drones can significantly improve agricultural management practices, leading to greater profitability and environmental sustainability.