GIS-based spatial prediction of recreational trail susceptibility in protected area of Sikkim Himalaya using logistic regression, decision tree and random forest model

Sahani, Nemai; Ghosh, Tirthankar

doi:10.1016/j.ecoinf.2021.101352

Cited by 38 publications

(16 citation statements)

References 99 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Gini index outperforms well in terms of various metrics when compared to entropy. The next metric accuracy was evaluated [24]. The accuracy was computed for training data and test data.…”

Section: Resultsmentioning

confidence: 99%

Feature based analysis of endometriosis using machine learning

Visalaxi

SudalaiMuthu²,

Ramalingam³

2023

IJEECS

View full text Add to dashboard Cite

<span lang="EN-US">Machine learning is a cutting-edge technology used for predicting and diagnosing various diseases. Various machine learning algorithm facilitates the prediction. The decision tree belongs to learning algorithm that performs both classification and prediction. The decision tree constructs the tree-like to evaluate the best features. The decision tree performs well in the prediction of various diseases. Endometriosis is a recurrence disease that creates an emotional impact in women. Endometriosis is a lump-like structure that appears at several locations in reproductive organs of women. The diagnosis of endometriosis was predicted through scanning procedures and laparoscopic procedures. The symptoms identified from laparoscopic surgery were used as the features for predicting the severity of endometriosis. The symptoms include mass-like structure, tissue size, variation in tissue colour, and blockages in fallopian tubes. The decision tree analyze the features of endometriosis by using two criteria such as entropy and Gini index. The entropy and Gini index construct the tree by identifying the size of tissue as major influencing attributes. The Gini index outperforms well with training accuracy of 84.08% and test accuracy of 84.85.</span>

show abstract

“…Gini index outperforms well in terms of various metrics when compared to entropy. The next metric accuracy was evaluated [24]. The accuracy was computed for training data and test data.…”

Section: Resultsmentioning

confidence: 99%

Feature based analysis of endometriosis using machine learning

Visalaxi

SudalaiMuthu²,

Ramalingam³

2023

IJEECS

View full text Add to dashboard Cite

show abstract

“…This approach is used to measure the prediction model's accuracy, consistency, and efficiency. Kappa values range from 1 to +1, a number that trends to +1 indicates that the model is more accurate [6].…”

Section: Discussionmentioning

confidence: 99%

Predictive modelling of mercury pollution in Indonesian ASGM areas and evaluation of the main factors using machine learning algorithm

Nuryanty

Riani

Abidin

et al. 2022

IOP Conf. Ser.: Earth Environ. Sci.

View full text Add to dashboard Cite

Artisanal Small-scales Gold Mining (ASGM) which are using mercury as a gold solvent is still exposed in Indonesia recently. The purpose of this study was to predict the level of environmental pollution due to the presence of mercury in ASGM areas in several cities in Indonesia. This study used data mining techniques based on samples of mercury concentration data in groundwater, river water, sediment, soil, plants, biota (fish), and ambient air collected from 2018 to 2021 at ASGM areas that are still actively operated. The prediction model was using the Naïve Bayes algorithm which showed an accuracy of 99.1% and a Kappa value of 0.815 which illustrated that the level of agreement of the model is very strong. The study result describe the mercury content of each environmental media compared to the national quality standard showed that the areas with the highest levels of pollution were Lebak-Banten, while the areas with moderate and low levels of pollution were Simpenan-Sukabumi and Cineam-Tasikmalaya. A prediction model through visualization can provide an overview of the main factor causing high pollution in certain ASGM areas, namely the non-optimal process of transferring gold processing technology without mercury and the lack of awareness of the dangers of mercury. These factors can be used as evidence for preparing “Regional Action Plans for Mercury Reduction and Elimination”.

show abstract

“…Therefore, this study uses the method of multicollinearity diagnosis to make judgments (Mihreteab et al, 2020). Commonly used diagnostic indicators of multivariate collinearity mainly include variance in ation factor (VIF) and tolerance (TOL) (Sahani and Ghosh, 2021). These two indicators have a reciprocal relationship.…”

Section: Rationality Of Indicatorsmentioning

confidence: 99%

Dynamic evaluation and prediction of the ecological environment quality of the urban agglomeration on the northern slope of Tianshan Mountains

Yibo

Ziyuan

Simayi

et al. 2022

Environ Sci Pollut Res

View full text Add to dashboard Cite

In order to timely understand the dynamic changes of the ecological environment quality and future development laws of the urban agglomeration on the northern slope of the Tianshan Mountains, combined with the actual situation of the urban agglomeration, 11 indicators are selected from the three aspects of natural ecology, social ecology, and economic ecology. Based on RS and GIS technology methods, Principal component analysis, coe cient of variation and analytic hierarchy process are used to reduce the dimensions of the indicators, and the ecological environmental quality (EQI) from 2000 to 2018 is dynamically evaluated, and the CA-Markov model is introduced to simulate the development status in 2026 predict.The main results are as follows: the overall ecological environment of the area shows a gradually improving distribution change from southwest to northeast; the proportion of ecological environment classi cation shows a gradually decreasing change pattern; the spatial differentiation of ecological environment quality shows a signi cant spatial positive correlation; from the in uencing factors It can be seen that natural ecological factors occupy a major position; the prediction accuracy veri cation shows that the CA-Markov model is suitable for the prediction of the ecological environment quality in the region and has high accuracy; the comprehensive regional ecological environment quality indexes are 5.7392, 6.1856 and 6.4366, respectively, and the forecast in 2026 The value is predicted to be 6.6285, indicating that the overall ecological environment quality of the region has been improved and developed well. The research reveals the law of dynamic changes and future development of the ecological environment quality in the region, which can be used as a theoretical reference for the formulation of ecological environmental protection measures in the region.

show abstract

GIS-based spatial prediction of recreational trail susceptibility in protected area of Sikkim Himalaya using logistic regression, decision tree and random forest model

Cited by 38 publications

References 99 publications

Feature based analysis of endometriosis using machine learning

Feature based analysis of endometriosis using machine learning

Predictive modelling of mercury pollution in Indonesian ASGM areas and evaluation of the main factors using machine learning algorithm

Dynamic evaluation and prediction of the ecological environment quality of the urban agglomeration on the northern slope of Tianshan Mountains

Contact Info

Product

Resources

About