Classification of Receiving Electricity Subsidy Assistance in Blang Panyang Village Using the K-NN (K-Nearest Neighbor) Method DOI Creative Commons
Miftahul Jannah,

Cut Syahira Salsabila,

Nur Faiza

et al.

Deleted Journal, Journal Year: 2024, Volume and Issue: 1(1), P. 1 - 1

Published: Jan. 1, 2024

The electricity subsidy program is one of the poverty reduction programs by providing assistance funds to poor and disadvantaged households paid Government Indonesia PT PLN (Persero). government implements a targeted policy, must be truly enjoyed poor. purpose this research test K-Nearest Neighbors algorithm in predicting receipt assistance. In dataset beneficiaries used study, there are 45 records or tuples with four attributes (house condition, income, occupation number amperes). prediction new data categories done using manual calculation stage Euclidean Distance from three different K values. results show that K=15, K=30 K=45 (46) has an "Ineligible" category accuracy rate 100%. Then K=45, (D46) "Viable" 66.6%.

Language: Английский

Enhanced rainfall-runoff modeling with hybrid machine learning and NRCS: bridging AI and hydrology DOI

Nawbahar Faraj Mustafa

Modeling Earth Systems and Environment, Journal Year: 2025, Volume and Issue: 11(4)

Published: April 24, 2025

Language: Английский

Citations

0
Improving multi-model ensemble streamflow forecasts by combining lumped, distributed and deep learning hydrological models DOI
William F. Armstrong, Richard Arsenault, Jean‐Luc Martel

et al.

Hydrological Sciences Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 25, 2025

Language: Английский

Citations

0
A multiscale attribution framework for separating the effects of cascade and individual reservoirs on runoff DOI

Yongsheng Jie,

Hui Qin,

Benjun Jia

et al.

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 933, P. 172784 - 172784

Published: April 26, 2024

Language: Английский

Citations

3
Climate Change and Viticulture in Italy: Historical Trends and Future Scenarios DOI Creative Commons
Vittorio Alba, Alessandra Russi,

Angelo Raffaele Caputo

et al.

Atmosphere, Journal Year: 2024, Volume and Issue: 15(8), P. 885 - 885

Published: July 25, 2024

(1) Background: The aim of this work was to characterize climatic evolution and change based on multicriteria classification through the dynamics bioclimatic indices in viticulture across Italy its regional administrative boundaries, focusing latitudes elevations. (2) Methods: This study analyzes climate influences Italian with reference historical information (1991–2021) future scenarios (until 2080) primarily SSP2-4.5 SSP5-8.5 scenarios, taking into account 13 GCMs. (3) Results: have all shown a significant trend period, an increase temperature decrease precipitation, reflecting their effects entire territory respect HI, up 44° N for CI, 46° DI, regardless altitude. highlighted shift towards warmer classes two temperature-based (HI CI) both SSPs, especially altitudes 900 m a.s.l. DI-based DI remained relatively stable over time, although values will become increasingly negative near future. (4) Conclusions: is warming, south coastal regions. By 2080, more areas be “very hot” “warm nights”. Drought also impact viticulture. These findings spotlight need adaptive strategies hold satisfactory productivity under changing conditions.

Language: Английский

Citations

3
Climate Change Impacts on Viticulture in Italy: Insights from Historical and Future Scenarios Across Administrative Areas, Latitudes, and Elevations DOI Open Access
Vittorio Alba, Alessandra Russi,

Angelo Raffaele Caputo

et al.

Published: June 24, 2024

(1) Background: The aim of the work was to characterize climatic evolution and change based on Multi Criteria Classification through dynamics bioclimatic indices in viticulture across Italy its regional administrative boundaries, focusing latitudes elevations. (2) Methods: impact climate analysed spatialized with reference historical data from 1991 2021 Future Scenarios up 2080 assumed by SSP2-4.5 SSP5-8.5, taking into account 13 GCMs. (3) Results: have all shown a significant trend period, an increase temperature decrease precipitation, reflecting their effects entire Italian territory respect HI, 44°N for CI 46°N DI, regardless altitude. highlighted shift towards warmer classes two temperature-based (HI CI) both SSPs, especially altitudes 900 m a.s.l.. DI-based classification DI remained relatively stable over time, although values will become increasingly negative near future. (4) Conclusions: is warming, south coastal regions. By 2080, more areas be “Very Hot” “Warm Nights.” Drought also viticulture. importance higher mitigating justifies continuing relocation vineyards as medium-term solution alternative targeted cultivation methods that must adopted short-term safeguard suitability area quality

Language: Английский

Citations

1
Addressing K-Nn Limitations Through Boosted Multi-Algorithm Nearest Neighbour Ensembles DOI

Appel R.D.,

Priyanga K.K

Published: Aug. 8, 2024

Language: Английский

Citations

0
Classification of Receiving Electricity Subsidy Assistance in Blang Panyang Village Using the K-NN (K-Nearest Neighbor) Method DOI Creative Commons
Miftahul Jannah,

Cut Syahira Salsabila,

Nur Faiza

et al.

Deleted Journal, Journal Year: 2024, Volume and Issue: 1(1), P. 1 - 1

Published: Jan. 1, 2024

The electricity subsidy program is one of the poverty reduction programs by providing assistance funds to poor and disadvantaged households paid Government Indonesia PT PLN (Persero). government implements a targeted policy, must be truly enjoyed poor. purpose this research test K-Nearest Neighbors algorithm in predicting receipt assistance. In dataset beneficiaries used study, there are 45 records or tuples with four attributes (house condition, income, occupation number amperes). prediction new data categories done using manual calculation stage Euclidean Distance from three different K values. results show that K=15, K=30 K=45 (46) has an "Ineligible" category accuracy rate 100%. Then K=45, (D46) "Viable" 66.6%.

Language: Английский

Citations

0