One of the significant aspects of our digital world is that data are literally everywhere, and it is increasing. On the other hand, the number of cyberattacks aiming to seize this data and use it illegally is increasi...
详细信息
One of the significant aspects of our digital world is that data are literally everywhere, and it is increasing. On the other hand, the number of cyberattacks aiming to seize this data and use it illegally is increasing at an exponential rate, and this is the challenge. Therefore, intrusion detection systems (IDS) have attracted considerable interest from researchers and industries. In this regard, machinelearning (ML) techniques are playing a pivotal role as they put the responsibility of analyzing enormous amounts of data, finding patterns, classifying intrusions, and solving issues on computers instead of humans. This paper implements two separate classification layers of ML-based algorithms with the recently published NF-UQ-NIDS-v2 dataset, preprocessing two volumes of sample records (100 k and 10 million), utilizing MinMaxScaler, LabelEncoder, selecting superlative features by recursive feature elimination, normalizing the data, and optimizing hyper-parameters for classicalalgorithms and neural networks. With a small dataset volume, the results of the classicalalgorithms layer show high detection accuracy rates for support vector (98.26%), decision tree (98.78%), random forest (99.07%), K-nearest neighbors (98.16%), CatBoost (99.04%), and gradient boosting (98.80%). In addition, the layer of neural network algorithms has proven to be a very powerful technology when using deep learning, particularly due to its unique ability to effectively handle enormous amounts of data and detect hidden correlations and patterns;it showed high detection results, which were (98.87%) for long short-term memory and (98.56%) for convolutional neural networks.
Laser-induced breakdown spectroscopy (LIBS) technique is employed for quantitative analysis of aluminum samples by different classicalmachinelearning approaches. A Q-switch Nd:YAG laser at a fundamental harmonic of ...
详细信息
Laser-induced breakdown spectroscopy (LIBS) technique is employed for quantitative analysis of aluminum samples by different classicalmachinelearning approaches. A Q-switch Nd:YAG laser at a fundamental harmonic of 1064 nm is utilized for the creation of LIBS plasma in order to predict constituent concentrations of the aluminum standard alloys. In the current research, concentration prediction is performed by linear approaches of support vector regression (SVR), multiple linear regression (MLR), principal component analysis (PCA) integrated with MLR (PCA-MLR), and SVR (PCA-SVR), as well as nonlinear algorithms of artificial neural network (ANN), kernelized support vector regression (KSVR), and the integration of traditional principal component analysis with KSVR (PCA-KSVR), and ANN (PCA-ANN). Furthermore, dimension reduction is applied to various methodologies by the PCA algorithm in order to improve the quantitative analysis. The results indicated that the combination of PCA with the KSVR algorithm model had the best efficiency in predicting most of the elements among other classical machine learning algorithms.
This paper comprehensively reviews and compares methodologies used to monitor air quality and their impact on human health. With urbanization and industrialization increasing in emerging nations, air pollution levels ...
详细信息
This paper comprehensively reviews and compares methodologies used to monitor air quality and their impact on human health. With urbanization and industrialization increasing in emerging nations, air pollution levels have become a significant threat to human well-being. The study highlights the importance of reducing exposure to air pollution for the improvement of public health. The paper focuses on the comparative analysis of measuring the Air Quality Index (AQI) using deep learningalgorithms like Long Short-Term Memory (LSTM) and classicalmachinelearning models such as Autoregressive Integrated Moving Average (ARIMA), Decision Tree, K-Nearest Neighbour, Extreme Gradient Boosting, Gradient Boosting, Adaptive Boosting, Huber Regressor, and Dummy Regressor for AQI prediction. The performance of these models is evaluated using daily and hourly time series data from 2014 to 2018, with the Root Mean Squared Error (RMSE) used as the performance indicator. The results demonstrate that LSTM outperforms ARIMA, particularly with hourly data. For daily data, ARIMA achieved an RMSE of 97.88, whereas LSTM obtained an RMSE of 143.07. On the other hand, for hourly data, ARIMA yielded an RMSE of 69.65, while LSTM achieved a lower RMSE of 44.6539. These findings highlight the potential of deep learningalgorithms, specifically LSTM, in accurately forecasting air quality.
This study is to construct the autoregressive models for the low-voltage broadband power line communication (PLC) channel noise by two machinelearningalgorithms, namely the least square support vector machine (LS-SV...
详细信息
This study is to construct the autoregressive models for the low-voltage broadband power line communication (PLC) channel noise by two machinelearningalgorithms, namely the least square support vector machine (LS-SVM) and wavelet neural networks. The main work is to compare the two classical machine learning algorithms and also compare them with the traditional Markovian-Gaussian method. To verify their availability and ability to adapt to the time-variant PLC channels, noise measurements for low-voltage PLC channels in indoor and outdoor scenarios are carried out. The accuracy and efficiency of the two models are studied and compared based on a large amount of measurement data. The results show that both of the noise models can simulate and adapt to the time-variant low-voltage broadband PLC channels very well. The LS-SVM model is found to have shorter simulation time and higher accuracy. Moreover, the proposed noise models are also compared with the traditional Markovian-Gaussian model. The results show that both the proposed noise models exhibit higher accuracy and lower complexity, especially that the LS-SVM is more appropriate to be applied as a noise generator in PLC link and network level simulations instead of the current Markovian-Gaussian model.
Twitter is one of the social media platforms that people express themselves freely. Harassment is one consequence of these such platforms, which is hard to obstruct. Text categorization and classification is a task th...
详细信息
ISBN:
(纸本)9781665443371
Twitter is one of the social media platforms that people express themselves freely. Harassment is one consequence of these such platforms, which is hard to obstruct. Text categorization and classification is a task that aims to solve this problem. Several studies applied classicalmachinelearning methods and recent deep neural networks to categorize the text. However, only a few studies have explored graph convolutional neural networks while using classical approaches to categorize harassment Tweets. In this work, we propose using graph convolutional networks (GCN) for tweet categorization. Second, we explore this categorization task using classicalmachinelearning approaches and compare the results with the GCN model. Third, we show the effectiveness of the GCN model on this problem by the other evaluation of the model on fewer sample datasets. In addition, we used different embedding approaches to find the best representation for the dataset in each of the models and represent the best embedding approach to use in this problem.
作者:
Quezada, L. F.Guo-Hua SunShi-Hai DongHuzhou Univ
Res Ctr Quantum Phys Huzhou 313000 Peoples R China UPALM
Inst Politecn Nacl Lab Comp Inteligente Ctr Invest Comp Ciudad De Mexico 07700 Mexico UPALM
Inst Politecn Nacl Lab Informac Cuant Ctr Innovac & Desarrollo Tecnol Comp Ciudad De Mexico 07700 Mexico
In this work a quantum sorting algorithm with adaptable requirements of memory and circuit depth is introduced, and is used to develop a new quantum version of the classicalmachinelearning algorithm known as k-neare...
详细信息
In this work a quantum sorting algorithm with adaptable requirements of memory and circuit depth is introduced, and is used to develop a new quantum version of the classicalmachinelearning algorithm known as k-nearest neighbors (k-NN). Both the efficiency and performance of this new quantum version of the k-NN algorithm are compared to those of the classical k-NN and another quantum version proposed by Schuld et al. Results show that the efficiency of both quantum algorithms is similar to each other and superior to that of the classical algorithm. On the other hand, the performance of the proposed quantum k-NN algorithm is superior to the one proposed by Schuld et al. and similar to that of the classical k-NN.
暂无评论