Combining Trend-Based Loss with Neural Network for Air Quality Forecasting in Internet of Things

Abstract

Internet of Things (IoT) is a network that connects things in a special union. It embeds a physical entity through an intelligent perception system to obtain information about the component at any time. It connects various objects. IoT has the ability of information transmission, information perception, and information processing. The air quality forecasting has always been an urgent problem, which affects people's quality of life seriously. So far, many air quality prediction algorithms have been proposed, which can be mainly classified into two categories. One is regression-based prediction, the other is deep learning-based prediction. Regression-based prediction is aimed to make use of the classical regression algorithm and the various supervised meteorological characteristics to regress the meteorological value. Deep learning methods usually use convolutional neural networks (CNN) or recurrent neural networks (RNN) to predict the meteorological value. As an excellent feature extractor, CNN has achieved good performance in many scenes. In the same way, as an efficient network for orderly data processing, RNN has also achieved good results. However, few or none of the above methods can meet the current accuracy requirements on prediction. Moreover, there is no way to pay attention to the trend monitoring of air quality data. For the sake of accurate results, this paper proposes a novel predicted-trend-based loss function (PTB), which is used to replace the loss function in RNN. At the same time, the trend of change and the predicted value are constrained to obtain more accurate prediction results of PM 2.5 . In addition, this paper extends the model scenario to the prediction of the whole existing training data features. All the data on the next day of the model is mixed labels, which effectively realizes the prediction of all features. The experiments show that the loss function proposed in this paper is effective.

Deep Learning Applied to Computational Mechanics: A Comprehensive Review, State of the Art, and the Classics

“…Other applications of deep learning include a real-time maskless-face detector using deep residual networks [356], topology optimization with embedded physical law and physical constraints [357], prediction of stress-strain relations in granular materials from triaxial test results [358], surrogate model for flight-load analysis [359], classification of domestic refuse in medical institutions based on transfer learning and convolutional neural network [360], convolutional neural network for arrhythmia diagnosis [361], e-commerce dynamic pricing by deep reinforcement learning [362], network intrusion detection [363], road pavement distress detection for smart maintenance [364], traffic flow statistics [365], multi-view gait recognition using deep CNN and channel attention mechanism [366], mortality risk assessment of ICU patients [367], stereo matching method based on space-aware network model to reduce the limitation of GPU RAM [368], air quality forecasting in Internet of Things [369], analysis of cardiac disease abnormal ECG signals [370], detection of mechanical parts (nuts, bolts, gaskets, etc.) by machine vision [371], asphalt road crack detection [372], steel commondity selection using bidirectional encoder representations from transformers (BERT) [373], short-term traffic flow prediction using LSTM-XGBoost combination model [374], emotion analysis based on multi-channel CNN in social networks [375].…”

A New Hybrid Ensemble Deep Learning Model for Train Axle Temperature Short Term Forecasting

“…As a description of the datasets, Table 2 lists the maximum, minimum, and average values of the three datasets. According to the literature survey [14,52,53] of prediction models, the proportion of training set and testing set can be 5:1 to 7:1. In the paper, each series includes 600 samples, in which the training set has 500 samples for the predictor and the testing set includes 100 samples to test the accuracy of the models.…”

Research on Automatic Cargo Recognition in Smart City Environment

“…At present, many excellent scholars have achieved some good research results, including [1][2][3][4] for the research on the Internet of Vehicles, and their research can improve the efficiency and safety of urban traffic. [5,6] Applying deep learning technology to air quality prediction can take measures to solve air problems in advance, which is of great significance to the construction of smart cities. [7] e application of deep learning technology to the problem of sentiment analysis can sense the emotions and psychology of college students in advance, which has become a research hotspot in the fields of psychology, health medicine, and computer science, and has high practical application value.…”