Machine-Learning-Based Classification Approaches toward Recognizing Slope Stability Failure

Moayedi, Hossein; Bui, Dieu Tien; Kalantar, Bahareh; Foong, Loke Kok

doi:10.3390/app9214638

Cited by 33 publications

(14 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Having the features of the portfolio is significant since the classifications are done (for more, refer to [34]) based on these characteristics. In this section, we take into account having a portfolio of loans linking three features as follows [35]:…”

Section: Lending Portfolio and Featuresmentioning

confidence: 99%

Classifying a Lending Portfolio of Loans with Dynamic Updates via a Machine Learning Technique

2020

View full text Add to dashboard Cite

Bankruptcy prediction has been broadly investigated using financial ratios methodologies. One involved factor is the quality of the portfolio of loans which is given. Hence, having a model to classify/predict position of each loan candidate based on several features is important. In this work, an application of machine learning approach in mathematical finance and banking is discussed. It is shown how we can classify some lending portfolios of banks under several features such as rating categories and various maturities. Dynamic updates of the portfolio are also given along with the top probabilities showing how the financial data of this type can be classified. The discussions and results reveal that a good algorithm for doing such a classification on large economic data of such type is the k-nearest neighbors (KNN) with k=1 along with parallelization even over the support vector machine, random forest, and artificial neural network techniques to save as much as possible on computational time.

show abstract

Section: Lending Portfolio and Featuresmentioning

confidence: 99%

Classifying a Lending Portfolio of Loans with Dynamic Updates via a Machine Learning Technique

2020

View full text Add to dashboard Cite

show abstract

“…In the experiments, the Jaccard similarity threshold was 20% and 𝑤 1 , 𝑤 2 , and 𝑤 3 were For comparison, well-known classification algorithms in the literature were used. These algorithms are Naive Bayes-NB (Rish, 2001), Support Vector Machine-SVM (Yue et al, 2003), Decision Tree-DT (Kotsiantis, 2013) and IBk (Moayedi et al, 2019). A total of 20 independent experiments were carried out.…”

Section: Methodsmentioning

confidence: 99%

A new plant intelligence-based method for sentiment analysis: Chaotic sunflower optimization

Yildirim¹,

Yıldırım²,

Alataş³

2021

Computer Science

View full text Add to dashboard Cite

Various social networking applications provide people with many opportunities such as expressing, commenting, disseminating and transmitting their opinions within certain limits. The emotions and ideas that people express in their messages make sense of thousands of articles and opinions published instantly. Trying to make sense of emotional data, generating meaningful information from these data, analyzing these data, and making predictions and inferences on these data is a new important study field. In this study, sentiment analysis is considered an optimization problem in order to achieve high performance. For this purpose, sunflower optimization, which is one of the new and successful plant intelligence-based algorithms, has been modelled as a sentiment analyzer for the first time. A chaotic sunflower optimization algorithm was used by combining sunflower optimization and chaos theory in order to make effective sentiment analysis. In order for the proposed method to effectively solve the sentiment analysis problem, a suitable representation form and fitness function have been proposed. The proposed method treats the data as a search space and searches for a solution for analysis by detecting emotion in this search space. An up-to-date data set including customer feedback and satisfaction information was used in the study. Results based on accuracy, precision, and recall metrics show that plant intelligence-based metaheuristic algorithms can provide high performance.

show abstract

“…(a) From the available dataset, randomly draw a new training set (bootstrap sample) with replacement; (b) Grow a tree using the bootstrap sample by iteratively splitting the nodes until no further splits are possible or the user-defined stopping criterion is reached. In order to split the nodes at the most informative feature, we use an objective function to maximize the information gain at each split, which is defined as [23]:…”

Section: Feature Selection Using Random Forest Regression Methodsmentioning

confidence: 99%

A Data-Driven Approach to Trip Generation Modeling for Urban Residents and Non-local Travelers

Yang

Ding

et al. 2020

Sustainability

View full text Add to dashboard Cite

Trip generation modeling is essential in transportation planning activities. Previous modeling methods that depend on traditional data collection methods are inefficient and expensive. This paper proposed a novel data-driven trip generation modeling method for urban residents and non-local travelers utilizing location-based social network (LBSN) data and cellular phone data and conducted a case study in Nanjing, China. First, the point of interest (POI) data of the LBSN were classified into various categories by the service type, then, four features of each category including the number of users, number of POIs, number of check-ins, and number of photos were aggregated by traffic analysis zones to be used as explanatory variables for the trip generation models. We used a random tree regression method to select the most important features as the model inputs, and the trip models were established based on the ordinary least square model. Then, an exploratory approach was used to test the performance of each combination of the variables with various test methods to identify the best model for residents’ and travelers’ trip generation functions. The results suggest land use compositions have significant impact on trip generations, and the trip generation patterns are different between urban residents and non-local travelers.

show abstract

Machine-Learning-Based Classification Approaches toward Recognizing Slope Stability Failure

Cited by 33 publications

References 59 publications

Classifying a Lending Portfolio of Loans with Dynamic Updates via a Machine Learning Technique

Classifying a Lending Portfolio of Loans with Dynamic Updates via a Machine Learning Technique

A new plant intelligence-based method for sentiment analysis: Chaotic sunflower optimization

A Data-Driven Approach to Trip Generation Modeling for Urban Residents and Non-local Travelers

Contact Info

Product

Resources

About