China
Africa
Explore chapters and articles related to this topic
Advanced Agricultural Systems: Identification, Crop Yields and Recommendations Using Image-Processing Techniques and Machine-Learning Algorithms
Published in Sarvesh Tanwar, Sumit Badotra, Ajay Rana, Machine Learning, Blockchain, and Cyber Security in Smart Environments, 2023
Avali Banerjee, Shobhandeb Paul, Soumi Bhattacharya
The decision tree algorithm is one of the most widely used classification algorithms that fall into the category of supervised learning. Decision trees are applied to predict both regression and classification problem statements. They are usually depicted in the form of a tree in two parts or entities, which are known as the decision nodes and leaves. Every leaf node corresponds to a class label and the internal nodes of the tree correspond to the attributes. The leaves depict the decisions or final outcomes, and the nodes form a decision node where the data is split. We can represent any Boolean function on specific attributes using the decision tree. The two main types of decision trees are: classification trees (yes/no type), where the decision variable is categorical; and regression trees (mainly for continuous data types).
Inductive learning – decision trees and random forests
Published in Benny Raphael, Construction and Building Automation, 2023
Decision trees are susceptible to overfitting. In some cases, large number of rules are generated. This happens mainly when the decision boundary cannot accurately be represented as boxes. When the actual decision boundary is a hyperplane (whose equation depends on several variables), the decision tree algorithm tries to divide the data set using the values of individual variables. Hence many rules are generated, and the final data sets contain very few data points. In the worst case, the leaf nodes in the decision tree contain only one data point each. This is equivalent to creating one rule for each data point. Predictions made using only a few data points are likely to be unreliable. This could result in overfitting. While the decision tree predicts correctly when the points in the training data are presented for prediction, it is unable to make predictions when slight variations of these points are presented.
Building Models to Support Augmented Intelligence
Published in Judith Hurwitz, Henry Morris, Candace Sidner, Daniel Kirsch, Augmented Intelligence, 2019
Judith Hurwitz, Henry Morris, Candace Sidner, Daniel Kirsch
An inspectable algorithm allows you to review the results and understand what the model is doing. Decision trees are the only algorithm that enables a user to inspect and gain insights into the results produced by the algorithm. Decision trees have existed since the 1960s and continue to be used. However, they have a major limitation: Decision trees cannot support a large number of features or large data sets. Because of these scalability limitations, it can be difficult to ascertain the patterns that are at the heart of machine learning for large data sets. Despite the fact that inspectability or explainability is instrumental in successfully understanding what models are doing, decision trees serve as only one type of tool in the machine learning predictive toolbox.
A LightGBM-based landslide susceptibility model considering the uncertainty of non-landslide samples
Published in Geomatics, Natural Hazards and Risk, 2023
Deliang Sun, Xiaoqing Wu, Haijia Wen, Qingyu Gu
With the rapid development of artificial intelligence technology, machine learning algorithms have been widely applied in the field of geological disaster warning. Common machine learning algorithms include logistic regression (LR) (Lombardo and Mai 2018), neural network (Zhang et al. 2022), random forest (RF) (Taalab et al. 2018; Wang et al. 2021), support vector machine (SVM) (Wang and Brenning 2021), decision tree (Wu et al. 2020), natural gradient boosting (NGBoost) (Kavzoglu and Teke 2022), and gradient boosting algorithms (Bentéjac et al. 2021; Natekin and Knoll 2013). However, LR may not be effective in addressing issues related to nonlinearity and low accuracy. Neural network often requires tuning a large number of parameters and long learning times. RF and SVM can be computationally expensive due to their algorithm complexity. Decision trees are susceptible to overfitting. The NGBoost and the Gradient Boosting Algorithms have problems, such as large amount of calculation, long training time, and need to pay attention to parameter adjustment. In recent years, XGBoost and LightGBM, which are optimized Gradient Boosting Decision Tree (GBDT), have attracted widespread attention and have been applied by scholars due to their ability to quickly and effectively process large-scale data (Ma et al. 2021; Wang and Wang 2020; Zhang et al. 2023). While compared with XGBoost machine learning algorithm, LightGBM occupies less memory, achieves higher accuracy and runs faster (Zhou et al. 2022; D. Zhang and Gong 2020). Therefore, this article uses the LightGBM model to help improve the accuracy of landslide prediction.
Determining the ambient influences and configuration of optimised environments for emotional wellbeing of older adults
Published in Ergonomics, 2021
Arturo Peralta, Antonio Fernández-Caballero, José Miguel Latorre
The metrics used to evaluate the results of the decision tree classification were as follows:Accuracy: ratio of correctly predicted observations to the total of performed observations.Precision: ratio of correctly predicted positive observations to the total predicted positive observations.Recall: ratio of correctly predicted positive observations to all observations in a specific class.F-Measure: this is the balanced harmonic mean of Recall and Precision, giving both metrics equal weight.
Classification of Customer Reviews Using Machine Learning Algorithms
Published in Applied Artificial Intelligence, 2021
A decision tree is a tree-like graph or model. It is more like an inverted tree because it has its root at the top and it grows downwards. This representation of the data has the advantage compared with other approaches of being meaningful and easy to interpret. Each interior node of tree corresponds to one of the input attributes. The number of edges of a nominal interior node is equal to the number of possible values of the corresponding input attribute. Outgoing edges of numerical attributes are labeled with disjoint ranges. Each leaf node represents a value of the label attribute given the values of the input attributes represented by the path from the root to the leaf. Decision trees in the Simple Cart algorithm are constructed by dividing each decision node into two different branches using various separation criteria (Gulsoy and Kulluk 2019).