Data Visualization and Knowledge Engineering by Unknown

Data Visualization and Knowledge Engineering by Unknown

Author:Unknown
Language: eng
Format: epub
ISBN: 9783030257972
Publisher: Springer International Publishing


2.Remove redundant, irrelevant or noisy data.

3.Improve data quality.

4.Increase the accuracy of resulting model.

5.Feature set reduction.

6.Improve the performance to gain predictive accuracy.

7.Gain knowledge about the process.

The objective of feature selection and feature extraction concerns the dimension reduction to improve analysis of data. The important aspect becomes relevant on considering real world datasets having hundreds or thousands of features. The author concluded to first perform the reduction without changing them whereas feature extraction reduces dimensionality. It emphasised to create other features that was more significant by computing transformation of the unique features [12].

Convolutional neural network (CNN) is a type of deep learning neural network (NN) for image recognition and classification. The link has valued weights that are finely tuned in the training process that results in a trained network. The neural network has layers connected by artificial neurons. Each layer categorizes a set of simple patterns of the input. A standard CNN have 5–25 layers that ends with an output layer [13]. A large database of good quality images with strong and distinctive features is taken for good classification results. The CNN model on classification accuracy removes the need of a Graphics Processing Unit (GPU) for training despite the advantage of shortening the training time and the transfer learning exceeds full training [14].

Automated behaviour-based malware detection using machine learning techniques is a thoughtful and fruitful method. It has generated behaviour reports on an emulated (sandbox) environment and the malware will be identified automatically. Different classifiers namely k-Nearest Neighbours (kNN), Naïve Bayes, J48 Decision Tree, Support Vector Machine (SVM), and Multilayer Perceptron Neural Network (MLP) were used. The experimental results achieved by J48 decision tree with a recall of 95.9%, a false positive rate of 2.4%, a precision of 97.3%, and an accuracy of 96.8% concluded that the use of machine learning techniques detects malware quite efficiently and effectively [15].

Researchers [16] have proposed a data-driven methodology consisting of CI methods to compare and forecast AQ parameters. The PCA and ANNs methods were chosen for the CI tasks. Implementation of a novel hybrid method for selecting the input variables of the ANN-MLP models were considered. To improve the accuracy of the forecasting model a nonlinear algorithm such as the ANN-MLP, the multi-fold training and validation scheme were adopted for air pollution.

The four algorithms of supervised learning, were compared for calculating correctness rate of waste generation. For successfully forecasting the future trends in MSW generation deep learning and machine learning models provide promising tools that may allow decision makers for planning MSW management purposes. They concluded that ANFIS, kNN, and SVM models results best prediction performance. In addition, results suggest that ANFIS model produced more accurate forecasts than kNN and SVM. Hence kNN modelling is applied for waste generation forecasting [17].

Reference [18] revealed the importance of laying a sustainable foundation for advanced technologies in intelligent buildings based on green Architecture and Integrated Project delivery. They concluded that it should be done before Nanotechnology, Building Information Modelling and Lean Construction along with Artificial Intelligence to achieve intelligent buildings and concern global warming.



Download



Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.