PM2.5 (Particulate Matter) and PM10 are the most common pollutants, and the increasing of concentration in the air will threaten people’s health. The machine learning method has recently been of particular interest to many researchers due to its effectiveness in air quality prediction models. Many solutions employing deep learning-based techniques such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), and hybrid CNN-LSTM models to enhance air quality prediction accuracy have been developed. This paper proposes a hybrid Encoder STM model for predicting the next day to the next five days’ PM2.5 and PM10 concentrations in Hanoi. Additionally, we proposed five extended features to increase the accuracy of prediction. Then other models, namely the LSTM model and the Bidirectional LSTM model, are also considered for PM2.5 and PM10 concentration prediction. Our results show that the proposed approaches outperform other state-of-the-art deep learning-based methods on both Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) due to low error and the small number of features.

A low-energy adaptive clustering hierarchy (LEACH) routing protocol has been proposed specifically for wireless sensor networks (WSNs). However, in LEACH protocol the criteria for clustering and selecting cluster heads (CHs) nodes were not mentioned. In this paper, we propose to improve the LEACH protocol by combining the use of K-means algorithm for clustering and bat algorithm (BA) to select nodes as CHs. The proposed routing algorithm, called BA-LEACH, is superior to other algorithms, namely PSO-LEACH, which using particle swarm optimization (PSO) to improve LEACH. Simulation analysis shows that the BA-LEACH can obviously reduce network energy consumption and optimize the lifetime of WSNs.

In this paper, an efficient direct position determination approach, which is based on the combination model using the Kalman filter, has been proposed. The proposed approach enables accurately estimating the emitter position in various scenarios. Two scenarios have been created to evaluate the performance of the approach in the case exist line of sight (LOS) paths and do not exist a line of sight paths (NLOS) on the way movement of the emitter in the indoor environment. The simulation outcomes show that the proposed approach achieves more accuracy compared to angle-of-arrival (AOA), Direct Position Determination (DPD), and Direct Source Localization (DiSouL) techniques in the same scenario. In particular, when the probability of errors was less than 1m and the environment has not existed with LOS paths, the proposed approach has achieved accuracy is about 60% compared to 1%, 35%, and 45% of AOA, DiSoul, and DPD, respectively.

In Wireless Sensor Networks (WSNs), maximizing the life of the Sensor Nodes (SNs), and energy conservation measures are essential to enhance the performance of the WSNs. A Low-Energy Adaptive Clustering Hierarchy (LEACH) routing protocol has been proposed specifically for WSNs to increase the network lifetime. However, in LEACH protocol the criteria for clustering and selecting Cluster Heads (CHs) nodes were not mentioned. Accordingly, researchers have been focusing on ways to strengthen the LEACH algorithm to make it more efficient. In this paper, we propose to improve the LEACH protocol by combining the use of K-means algorithm for clustering and Slime Mould Algorithm (SMA), a new stochastic optimization to select nodes as CHs. The proposed routing algorithm, called SMA-LEACH, is superior to other algorithms, namely PSO-LEACH, BA-LEACH, which using Particle Swarm Optimization (PSO), Bat Algorithm (BA) to improve LEACH, respectively. Simulation analysis shows that the SMA-LEACH obviously reduces network energy consumption and extends the lifetime of WSNs.