Filters








50 Hits in 4.8 sec

A Deep Belief Network Based Model for Urban Haze Prediction

2018 Tehnički Vjesnik  
In order to improve the accuracy of urban haze prediction, a novel deep belief network (DBN)-based model was proposed.  ...  Compared with the traditional prediction algorithms, the CC is improved by 18 % on average, while the MAE is reduced by 15.7 μg/m 3 .  ...  Based on the above discussion, this study aims to establish a deep belief network (DBN) based model for urban haze prediction by using deep learning (DL) theory to accurately predict the tendency of haze  ... 
doi:10.17559/tv-20180204162632 fatcat:56fhjgtqrnh3dai5qmaur5wezm

Wine Quality Prediction Using Machine Learning

Vrusha P. Sangodkar
2021 International Journal for Research in Applied Science and Engineering Technology  
Keywords: Data Extraction, PCA, SVM,BP neural network, Randomforest  ...  feature selection and then accuracy is find using SVM, backpropagation neural network and Random forest algorithm to find which model fits best and gives greater accuracy.  ...  network and random forest .The results are predicted based on this.  ... 
doi:10.22214/ijraset.2021.37629 fatcat:g7dio4uqqfcafitam45kmewkae

Data-Driven Temporal-Spatial Model for the Prediction of AQI in Nanjing

Xuan Zhao, Meichen Song, Anqi Liu, Yiming Wang, Tong Wang, Jinde Cao
2020 Journal of Artificial Intelligence and Soft Computing Research  
The temporal dimension model is presented at first based on the enhanced k-Nearest Neighbor (KNN) algorithm to predict the AQI values among monitoring stations, the acceptability of the results achieves  ...  Meanwhile, in order to forecast the evolution of air quality in the spatial dimension, the method is utilized with the help of Back Propagation neural network (BP), which considers geographical distance  ...  ., Artificial neural network: The simplicity and generality of the BP algorithm can lead to a bright prospect, so the BP algorithm with hidden layers is chosen in this paper.  ... 
doi:10.2478/jaiscr-2020-0017 fatcat:3isuvpna6veffmzzwtpggrcc7m

Soft Computing Applications in Air Quality Modeling: Past, Present, and Future

Muhammad Muhitur Rahman, Md Shafiullah, Syed Masiur Rahman, Abu Nasser Khondaker, Abduljamiu Amao, Md. Hasan Zahir
2020 Sustainability  
It was observed that many advanced, reliable, and self-organized soft computing models like functional network, genetic programming, type-2 fuzzy logic, genetic fuzzy, genetic neuro-fuzzy, and case-based  ...  Among the many soft computing techniques in AQM, this article reviews and discusses artificial neural network (ANN), support vector machine (SVM), evolutionary ANN and SVM, the fuzzy logic model, neuro-fuzzy  ...  neural networks (BP-NN) ( Table 2) .  ... 
doi:10.3390/su12104045 fatcat:laoiyhzeejgy7k63lzhxmko4nu

Day-Ahead PM2.5 Concentration Forecasting Using WT-VMD Based Decomposition Method and Back Propagation Neural Network Improved by Differential Evolution

Deyun Wang, Yanling Liu, Hongyuan Luo, Chenqiang Yue, Sheng Cheng
2017 International Journal of Environmental Research and Public Health  
Therefore, this paper proposes a novel hybrid model based on WT-VMD decomposition method and BP neural network optimized by DE algorithm for one day ahead PM 2.5 concentration forecasting.  ...  Wang et al. [32] proposed a hybrid model based on two-layer decomposition method and BP neural network optimized by firefly algorithm for multi-step electricity price forecasting, and the experimental  ...  Step 5: Train and test the BP neural network based on the training and testing samples.  ... 
doi:10.3390/ijerph14070764 pmid:28704955 pmcid:PMC5551202 fatcat:xgddksykhjctxlj75ki5b372ge

Air Quality Prediction in Smart Cities Using Machine Learning Technologies based on Sensor Data: A Review

Ditsuhi Iskandaryan, Francisco Ramos, Sergio Trilles
2020 Applied Sciences  
This paper covers the revision of the studies related to air pollution prediction using machine learning algorithms based on sensor data in the context of smart cities.  ...  After thorough reviewing those papers, the main features were extracted, which served as a base to link and compare them to each other.  ...  Vector Machine DBN Deep Belief Network DBN-H DBN-based urban haze prediction DNN Deep Neural Network ACC Accuracy NO x Nitrogen oxide FFANN-BP FeedForward Neural Network based on Back Propagation  ... 
doi:10.3390/app10072401 fatcat:b3weeysblfhgdazm6adej253nm

Front Matter: Volume 10605

Yueguang Lv, Jianzhong Su, Wei Gong, Jian Yang, Weimin Bao, Weibiao Chen, Zelin Shi, Jindong Fei, Shensheng Han, Weiqi Jin
2018 LIDAR Imaging Detection and Target Recognition 2017  
using a Base 36 numbering system employing both numerals and letters.  ...  A unique citation identifier (CID) number is assigned to each article at the time of publication.  ...  10605 2S AOD furnace splash soft-sensor in the smelting process based on improved BP neural network [10605-140] 10605 2T Research on optimization method of deep neural network [10605-141] 10605  ... 
doi:10.1117/12.2306194 fatcat:u7kemeon4vcoxns7youpbqtmwy

Soybean Yield Preharvest Prediction Based on Bean Pods and Leaves Image Recognition Using Deep Learning Neural Network Combined With GRNN

Wei Lu, Rongting Du, Pengshuai Niu, Guangnan Xing, Hui Luo, Yiming Deng, Lei Shu
2022 Frontiers in Plant Science  
This paper proposed a soybean yield in-field prediction method based on bean pods and leaves image recognition using a deep learning algorithm combined with a generalized regression neural network (GRNN  ...  The results show that it is feasible to predict the soybean yield of plants in situ with high precision by fusing the number of leaves and different type soybean pods recognized by a deep neural network  ...  This paper proposed a soybean yield in-field prediction method based on bean pods and leaves image recognition using a deep learning algorithm combined with a generalized regression neural network (GRNN  ... 
doi:10.3389/fpls.2021.791256 pmid:35095964 pmcid:PMC8792930 fatcat:uoe4unlnpvcrhizonvlaabvsb4

Neural Network Based Brain Tumor Detection Using Wireless Infrared Imaging Sensor

P. Mohamed Shakeel, Tarek E. El. Tobely, Haytham Al-Feel, Gunasekaran Manogaran, S. Baskar
2019 IEEE Access  
INDEX TERMS Wireless infrared imaging sensor, infra-red sensor, principal component analysis gray level covariance matrix, machine learning based neural networks.  ...  Then, the computational multifaceted nature of neural distinguishing proof incredibly diminished when the entire framework is deteriorated into a few subsystems.  ...  The comparison between Adaboost Classifier and the machine learning based Back Propagating Neural Network on the following parameters has been made.  ... 
doi:10.1109/access.2018.2883957 fatcat:ypo7ytrc7fgc7kgg6uanhgd74a

Research on the Application of GA-ELM Model in Carbon Trading Price – An Example of Beijing

Yanmei Li, Jiawei Song
2021 Polish Journal of Environmental Studies  
Finally, according to the analysis results, it provides a useful theoretical reference for carbon market decision makers and participants.  ...  Therefore, it is of great practical significance to study the influencing factors of carbon price fluctuations and to predict future carbon prices.  ...  Declaration of Competing Interest We declare that we do not have any commercial or associative interest that represents a conflict of interest in connection with the work submitted.  ... 
doi:10.15244/pjoes/138357 fatcat:5pw774mrlrcoljdtimcycueyga

Chemometrics in analytical chemistry – an overview of applications from 2014 to 2018

Mônica Cardoso Santos, Paloma Andrade Martins Nascimento, Wesley Nascimento Guedes, Edenir Rodrigues Pereira-Filho, Érica Regina Filletti, Fabíola Manhas Verbi Pereira
2019 Eclética química  
, prediction, analytical chemistry, artificial neural networks (ANN), design of experiments (DoE) and factorial design.  ...  A compilation of papers published between 2014 and 2018 was evaluated.  ...  , prediction, analytical chemistry, artificial neural networks (ANN), design of experiments (DoE) and factorial design.  ... 
doi:10.26850/1678-4618eqj.v44.2.2019.p11-25 fatcat:5jofiy77kbcszntm3c524hyg5i

Yolo-Based Traffic Sign Recognition Algorithm

Ming Li, Li Zhang, Linlin Li, Wenlong Song, Zhao Kaifa
2022 Computational Intelligence and Neuroscience  
Finally, the proposed recognition algorithm is tested with the data set based on the German traffic sign recognition standard and compared with other baseline algorithms.  ...  The processed pictures are input into the optimized convolutional neural network to subdivide the categories to obtain the specific categories.  ...  It is a nonlinear model with good robustness and fault tolerance. Common artificial neural networks include three-layer BP neural network, Hopfield neural network algorithm, etc.  ... 
doi:10.1155/2022/2682921 pmid:35965751 pmcid:PMC9365537 fatcat:q4mqjvtzwjddnim22zaxkywpvq

Ensemble of Deep Learning-Based Multimodal Remote Sensing Image Classification Model on Unmanned Aerial Vehicle Networks

Gyanendra Prasad Joshi, Fayadh Alenezi, Gopalakrishnan Thirumoorthy, Ashit Kumar Dutta, Jinsang You
2021 Mathematics  
The design of the HCO algorithm for hyperparameter optimization and SSA for parameter tuning of the RELM model helps to increase the classification outcome to a maximum level considerably.  ...  In addition, an ensemble of DL models, namely VGG-19, Capsule Network (CapsNet), and MobileNet, is used for feature extraction.  ...  A multilayer artificial convolutional neural network (CNN) allows automatic extraction of higher-level features from a labeled image.  ... 
doi:10.3390/math9222984 fatcat:6ic5yr344nedzbxnrumoxb7u7i

Learning an Adaptive Model for Extreme Low-light Raw Image Processing [article]

Qingxu Fu, Xiaoguang Di, Yu Zhang
2020 arXiv   pre-print
The proposed method can be divided into two sub-models: Brightness Prediction (BP) and Exposure Shifting (ES).  ...  In quantitative tests, it is shown that the proposed method has the lowest Noise Level Estimation (NLE) score compared with the state-of-the-art low-light algorithms, suggesting a superior denoising performance  ...  In stage one, a Brightness Prediction Network (BPN) was introduced to estimate a proper exposure time based on the content of images as well as Exif (Exchangeable image file) metadata.  ... 
arXiv:2004.10447v1 fatcat:62e3jdv6gjgi3jpvxbc2mtuhpm

MSDRN: Pansharpening of Multispectral Images via Multi-Scale Deep Residual Network

Wenqing Wang, Zhiqiang Zhou, Han Liu, Guo Xie
2021 Remote Sensing  
Various pansharpening methods that are based on convolutional neural networks (CNN) with different architectures have been introduced by prior works.  ...  A series of experiments are conducted on the QuickBird and GeoEye-1 datasets.  ...  For the CS-based methods, the algorithms including IHS, PCA and BDSD achieve high spatial resolution on two datasets.  ... 
doi:10.3390/rs13061200 fatcat:u7v7ksrnxrdavmooha6k4fwydy
« Previous Showing results 1 — 15 out of 50 results