Filters








1,198 Hits in 5.6 sec

Deep-AIR: A Hybrid CNN-LSTM Framework for Air Quality Modeling in Metropolitan Cities [article]

Yang Han, Qi Zhang, Victor O.K. Li, Jacqueline C.K. Lam
2021 arXiv   pre-print
Our Deep-AIR, a novel hybrid deep learning framework that combines a convolutional neural network with a long short-term memory network, aims to address this gap to provide fine-grained city-wide air pollution  ...  Using Hong Kong and Beijing as case studies, Deep-AIR achieves a higher accuracy than our baseline models.  ...  We would like to acknowledge the Beijing Municipal Environment Monitoring Center and the National Meteorological Information Center, China, for publicizing air quality and meteorological data of Beijing  ... 
arXiv:2103.14587v1 fatcat:ry2zcwif3rdspgyrazqndjeaqy

Air-Quality Prediction Based on the EMD–IPSO–LSTM Combination Model

Yuan Huang, Junhao Yu, Xiaohong Dai, Zheng Huang, Yuanyuan Li
2022 Sustainability  
Second, we built an EMD–IPSO–LSTM air quality prediction model for each IMF component and extracted prediction values.  ...  Third, the results of validation analyses of the algorithm showed that compared with LSTM and EMD–LSTM, the improved model had higher prediction accuracy and improved the model fitting effect, which provided  ...  [29] proposed a comprehensive method of prediction based on LSTM with many environmental datasets.  ... 
doi:10.3390/su14094889 fatcat:mutaidrlsjhn7ghsjxeedhxjju

LSTM-Autoencoder based Anomaly Detection for Indoor Air Quality Time Series Data [article]

Yuanyuan Wei, Julian Jang-Jaccard, Wen Xu, Fariza Sabrina, Seyit Camtepe, Mikael Boulic
2022 arXiv   pre-print
We propose a hybrid deep learning model that combines LSTM with Autoencoder for anomaly detection tasks in IAQ to address this issue.  ...  Anomaly detection for indoor air quality (IAQ) data has become an important area of research as the quality of air is closely related to human health and well-being.  ...  CONCLUSION We proposed an LSTM-Autoencoder based deep-learning technique for detecting anomalies in indoor air quality datasets.  ... 
arXiv:2204.06701v1 fatcat:2nb7pklhffc55cyiqxwr6h7ldq

Event-Driven Source Traffic Prediction in Machine-Type Communications Using LSTM Networks [article]

Thulitha Senevirathna, Bathiya Thennakoon, Tharindu Sankalpa, Chatura Seneviratne, Samad Ali, Nandana Rajatheva
2021 arXiv   pre-print
In this paper, a Long Short-Term Memory (LSTM) based deep learning approach is proposed for event-driven source traffic prediction.  ...  Our model outperforms existing baseline solutions in saving resources and accuracy with a margin of around 9%.  ...  Then, we have proposed an LSTM based deep learning approach for inferring causal relations between the transmission patterns of the MTDs and predicting event-driven traffic.  ... 
arXiv:2101.04365v1 fatcat:edyk224d7bbavbdts5wymwpj6e

Evolving CNN-LSTM Models for Time Series Prediction Using Enhanced Grey Wolf Optimizer

Hailun Xie, Li Zhang, Chee Peng Lim
2020 IEEE Access  
PM2.5 CONCENTRATION PREDICTION 1) DATA SET To further assess model efficiency, we employ the UCI Beijing air quality data set 2 [88] for PM2.5 concentration prediction using the devised evolving CNN-LSTM  ...  The URL of the Beijing air quality data set is: https://archive.ics.uci.edu/ml/datasets/Beijing+Multi-Site+Air-Quality+Data.  ... 
doi:10.1109/access.2020.3021527 fatcat:pv7uhl27ure5zgtpbxd4flj5fe

An LSTM Based Forecasting for Major Stock Sectors Using COVID Sentiment

Ayesha Jabeen, Sitara Afzal, Muazzam Maqsood, Irfan Mehmood, Sadaf Yasmin, Muhammad Tabish Niaz, Yunyoung Nam
2021 Computers Materials & Continua  
The results show that performance improves by using coronavirus event sentiments along with the LSTM prediction model.  ...  We use the Twitter dataset for calculating the coronavirus sentiment with a Long Short-Term Memory (LSTM) model to improve stock prediction.  ...  Deep learning models have been widely used in stock predictions. There are many layers involved in the deep learning structures.  ... 
doi:10.32604/cmc.2021.014598 fatcat:ygamlpugpzfwdiuyu3fasx2pje

Gas Concentration Prediction Based on IWOA-LSTM-CEEMDAN Residual Correction Model

Ningke Xu, Xiangqian Wang, Xiangrui Meng, Haoqian Chang
2022 Sensors  
empirical model decomposition with adaptive noise (CEEMDAN) method.  ...  The IWOA-LSTM-CEEMDAN model also achieves the highest prediction accuracy in multi-step prediction.  ...  Cheng [10] used a deep learning algorithm in combined with a fully connected neural network to construct an LSTM-FC gas concentration prediction model for spatiotemporal sequences using the spatiotemporal  ... 
doi:10.3390/s22124412 fatcat:k6tccl6xgnefbf6vzhcdycc32u

Public Environment Emotion Prediction Model Using LSTM Network

Qiang Zhang, Tianze Gao, Xueyan Liu, Yun Zheng
2020 Sustainability  
This paper compares the decision performance of LSTM (Long Short-Term Memory) and RNN (Recurrent Neural Network) models on the public environment emotional level through experiments, and uses a variety  ...  It is expected to predict the public environmental sentiment more accurately while predicting the atmospheric environment.  ...  in the international air environment Sustainability 2020, 12, 1665 5 of 16 quality assessment system).  ... 
doi:10.3390/su12041665 fatcat:zwwf4dmwxbg33aq5kezyvlaady

Densely Connected Convolutional Networks with Attention LSTM for Crowd Flows Prediction

Wei Li, Wei Tao, Junyang Qiu, Xin Liu, Xingyu Zhou, Zhisong Pan
2019 IEEE Access  
Some previous works attempted to address this problem using various ways, such as autoregressive integrated moving average, vector auto-regression and some deep learning models.  ...  With the rapid progress of urbanization, predicting citywide crowd flows has become increasingly significant in many fields, such as traffic management and public security.  ...  Measurements for spatiotemporal prediction problems are diversiform, including air quality [35] , weather, taxi order, and bike rent/return.  ... 
doi:10.1109/access.2019.2943890 fatcat:vf2lwb6vczbrlii2wjvjdx5iyy

Event-Driven Source Traffic Prediction in Machine-Type Communications Using LSTM Networks

Thulitha Senevirathna, Bathiya Thennakoon, Tharindu Sankalpa, Chatura Seneviratne, Samad Ali, Nandana Rajatheva
2020 GLOBECOM 2020 - 2020 IEEE Global Communications Conference  
In this paper, a long short-term memory (LSTM) based deep learning approach is proposed for eventdriven source traffic prediction.  ...  Our model outperforms existing baseline solutions in saving resources and accuracy with a margin of around 9%.  ...  Then, we have proposed an LSTM based deep learning approach for inferring causal relations between the transmission patterns of the MTDs and predicting event-driven traffic.  ... 
doi:10.1109/globecom42002.2020.9322417 fatcat:npyrpxsohjhp7kb43ccgtqoqay

A Framework for Predicting Network Security Situation Based on the Improved LSTM

Shixuan Li, Dongmei Zhao, Qingru Li
2020 EAI Endorsed Transactions on Collaborative Computing  
Experiments prove that the framework built with the improved LSTM has better performance to predict network security situation in the near future.  ...  According the needs of this framework, we improve Long Short-Term Memory (LSTM) with Cross-Entropy function, Rectified Linear Unit and appropriate layer stacking.  ...  The authors would like to thank the reviewers for their detailed reviews and constructive comments, which have helped improve the quality of our study.  ... 
doi:10.4108/eai.12-6-2020.165278 fatcat:d6zsgevuhraejdyqjaeqci6yha

Short-Term Rental Forecast of Urban Public Bicycle Based on the HOSVD-LSTM Model in Smart City

Dazhou Li, Chuan Lin, Wei Gao, Zihui Meng, Qi Song
2020 Sensors  
Based on the HOSVD-LSTM prediction model, a prediction model of urban public bicycles based on the hybrid model is proposed by transforming the source data (multiple time series) into a high-order tensor  ...  At the same time, these kernel tenors are directly used to train tensor LSTM models to obtain new kernel tenors.  ...  We built the model based on the deep learning framework TensorFlow.  ... 
doi:10.3390/s20113072 pmid:32485884 pmcid:PMC7309029 fatcat:avkkuxc62jbzdbyxih3uf5id7m

Attention-Based Distributed Deep Learning Model for Air Quality Forecasting

Axel Gedeon Mengara Mengara, Eunyoung Park, Jinho Jang, Younghwan Yoo
2022 Sustainability  
This research focuses on unravelling a new framework for air quality prediction worldwide and features Busan, South Korea as its model city.  ...  The proposed deep learning model has been trained on a distributed framework, referred to data parallelism, to forecast the intensity of particle pollution ( and ).  ...  Training Approach Research lacks evidence towards a deep distributed learning approach for air quality prediction, especially with training time and memory consumption investigations.  ... 
doi:10.3390/su14063269 fatcat:4he3jua6frf55og6kfxzqvtyg4

Deep Learning in Mobile Computing: Architecture, Applications, and Future Challenges

Xiaoxian Yang, Zhiyuan Tan, Zhiling Luo
2021 Mobile Information Systems  
In the paper entitled "Air Quality Prediction Based on a Spatiotemporal Attention Mechanism" by Zou et al., they propose a long short term memory (LSTM) air quality prediction model based on a spatiotemporal  ...  In the paper entitled "Towards Activity Recognition through Multidimensional Mobile Data Fusion with a Smartphone and Deep Learning" by Cao et al., they use an Android smartphone to collect the data of  ... 
doi:10.1155/2021/9874724 fatcat:exsfe42mkrfwxnm6erdwl46h5y

A Deep Learning Approach to the Citywide Traffic Accident Risk Prediction [article]

Honglei Ren, You Song, Jingwen Wang, Yucheng Hu, Jinzhi Lei
2018 arXiv   pre-print
Based on the patterns we found in analysis, we proposed a high accurate deep learning model based on recurrent neural network toward the prediction of traffic accident risk.  ...  The proposed method can be integrated into an intelligent traffic control system toward a more reasonable traffic prediction and command organization.  ...  Other important factors they missed are weather condition, air quality, etc.  ... 
arXiv:1710.09543v2 fatcat:fs4l62shifbvveg6qdf4vomroi
« Previous Showing results 1 — 15 out of 1,198 results