Efficient fog prediction with multi-objective evolutionary neural networks

Durán-Rosal, Antonio Manuel; Fernández, Juan Carlos Fernández; Casanova-Mateo, C.; Sanz-Justo, J.; Salcedo‐Sanz, Sancho; Hervás-Martı́nez, César

doi:10.1016/j.asoc.2018.05.035

Cited by 24 publications

(11 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…So, basically saying that a machine acquires artificial intelligence via machine learning. They are suitable for now-casting because of their short computing time (Durán-Rosal et al 2018 ; Dutta and Chaudhuri 2015 ).…”

Section: Fog Forecasting and Detectionmentioning

confidence: 99%

“…Another case study of Wamena Airport utilised a bunch of algorithms including Xtreme Randomized Tree (XRT), Generalized Linear Model (GLM), Gradient Boosting Machine (GBM), Deep Learning (DP, Distributed Random Forest (DRF), and stacked Ensemble comprising of all the model’s aforementioned which gave the best result (Dewi and Harsa 2020 ). Performance of various hybrid neural networks in predicting radiation fog events from the fog from the meteorological data collected from the Valladolid airport was compared, the Multiobjective Evolutionary training algorithms performed best, and the importance of each meteorological parameter considered was also presented in terms of prediction (Durán-Rosal et al 2018 ). A method for short term fog forecasting applying the LSTM (Long Short Term Memory) was suggested by Miao et al ( 2020 ) to train the model better; instead of using the observed meteorological data directly, the data was converted into a set of four datasets depending upon its duration, the algorithm was tested and was later compared with the output of other models where its performance was best, thus proving its effectiveness in short term prediction.…”

Section: Fog Forecasting and Detectionmentioning

confidence: 99%

“…Complex functions can be simulated easily in a more extensive network by increasing the number of nodes in the hidden layer of MLP (Fabbian et al 2007 ). It overpowers basic statistical models because of its ability to handle complex non-linear interactions between input and objective variables (Durán-Rosal et al 2018 ). However, for predicting onset and clearance times of fog, MLPs development is required.…”

Section: Fog Forecasting and Detectionmentioning

confidence: 99%

See 2 more Smart Citations

A review on factors influencing fog formation, classification, forecasting, detection and impacts

Lakra

Avishek

2022

Rend. Fis. Acc. Lincei

View full text Add to dashboard Cite

With the changing climate and environment, the nature of fog has also changed and because of its impact on humans and other systems, study of fog becomes essential. Hence, the study of its controlling factors such as the characteristics of condensation nuclei, microphysics, air–surface interaction, moisture, heat fluxes and synoptic conditions also become crucial, along with research in the field of prediction and detection. The current review expands for the period between 1976 to 2021, however, especially focused on the research articles published in the last two decades. It considers 250 research papers/research letters, 24 review papers, four book chapters/manuals, five news articles, 15 reports, six conference papers and five other online readings. This review is a compilation of the pros and cons of the techniques used to determine the factors influencing fog formation, its classification, tools and techniques available for its detection and forecast. Some recent advanced are also discussed in this review: role of soil properties on fogs, application of microwave communication links in the detection of fog, new class of smog, and how the cognitive abilities of humans are affected by fog. Recently India and China are facing an emergence and repetitions of fog haze/smog and thus their policies initiatives are also briefly discussed. It is concluded that the complexity in fog forecasting is high due to multiple factors playing a role at multiple levels. Most of the researchers have worked upon the role of humidity, temperature, wind, and boundary layer to predict fogs. However, the role of global wind circulations, soil properties, and anthropogenic heat requires further investigations. Literature shows that fog is being harnessed to address water insecurity in various countries, however, coastal areas of Angola, Namibia and South Africa, Kenya, Eastern Yemen, Oman, China, India, Sri Lanka, Mexico, along with the mountainous regions of Peru, Chile, and Ecuador, are some of the potential sites that can benefit from the installation of fog water harvesting systems.

show abstract

Section: Fog Forecasting and Detectionmentioning

confidence: 99%

Section: Fog Forecasting and Detectionmentioning

confidence: 99%

Section: Fog Forecasting and Detectionmentioning

confidence: 99%

See 1 more Smart Citation

A review on factors influencing fog formation, classification, forecasting, detection and impacts

Lakra

Avishek

2022

Rend. Fis. Acc. Lincei

View full text Add to dashboard Cite

show abstract

“…Predictive modeling is the use of data to forecast future events by capturing relationships between explanatory variables and predicted variables from past events, and applying them to predict future outcomes [34]. Artificial neural networks (ANNs) are among the most popular predictive methods in analyzing occupational incidents [1,35,36] predicting causes and severity of injuries [37,38], and determining the underlying factors that influence workplace incidents [39][40][41].…”

Section: Artificial Neural Network In Occupational Safetymentioning

confidence: 99%

Use of Neural Networks to Identify Safety Prevention Priorities in Agro-Manufacturing Operations within Commercial Grain Elevators

2019

View full text Add to dashboard Cite

The grain handling industry plays a significant role in U.S. agriculture by storing, distributing, and processing a variety of agricultural commodities. Commercial grain elevators are hazardous agro-manufacturing work environments where workers are prone to severe injuries, due to the nature of the activities and workplace. Safety incidents in agro-manufacturing operations generally arise from a combination of factors, rather than a single cause, therefore, research on occupational incidents must look deeper into identifying the underlying causes, through the application of advanced analyses methods. In occupational safety, it is possible to estimate and predict probability of safety risks through developing artificial neural network predictive models. Due to the significance of safety risk assessment in the design and prioritization of effective prevention measures, this study aimed at classifying and predicting causes of occupational incidents in grain elevator agro-manufacturing operations in the Midwest region of the United States. Workers’ compensation claims data, from 2008 to 2016, were utilized for training multilayer perceptron (MLP) and radial basis function (RBF) neural networks. Both MLP and RBF models could predict the probability of safety risks with a high overall accuracy of 60%, 61%. Based on values of AUC (area under the curve) from the ROC (receiving operating charts), both models predicted the probability of individual safety risks with a high accuracy rate of between 71.5% and 99.2%. In addition, sensitivity analysis showed that nature of injury is the most significant determinant of safety risks probability, along with type of injury. The novelty of this study is the use of the artificial neural network methodology to analyze multi-level causes of occupational incidents as the sources of safety risks in bulk storage facilities. The results confirm that artificial neural networks are useful in safety risk estimation, and identifying the incidents’ risk factors. The implementation of safety measures in grain elevators can help in preventing occupational injuries, saving lives, and reducing the occurrence and severity of such incidents in industrial work environments.

show abstract

“…GAs have been successfully applied in a number of applications in various fields due to three widely acknowledged advantages: (a) the capability of searching the global optimal solution, (b) high adaptability to multiobjective optimization problems, and (c) ease of implementation (Ardestani, Moazen, & Jin, 2014). Compared with matrix multiplications in SGD, GAs do not involve heavy computations (Durán-Rosal et al, 2018). As a result, GAs have been extensively employed in optimizing NNs (Bukharov & Bogolyubov, 2015;Huang, Li, & Xiao, 2015), focusing on the network architecture setting (Liu et al, 2017) and the connection weight optimization (Tang et al, 2016).…”

Section: Gas and Gas For Evolving Nnsmentioning

confidence: 99%

Endoscopy report mining for intelligent gastric cancer screening

et al. 2019

View full text Add to dashboard Cite

Endoscopy is an important tool for gastric cancer screening. Due to the lack of effective decision support system for endoscopy, the detection of gastric cancer in the clinic is usually with low sensitivity. In this paper, we propose a Genetic Algorithm optimized Neural Network (GAoNN) approach for gastric cancer detection based on endoscopy reports mining. Considering the fact that gastric cancer sensitivity can significantly improve the 5‐year survival rate of patients, both the prediction accuracy and the sensitivity are employed to construct a multiobjective optimization model for enhancing the classification performance of GAoNN. In particular, we extended an effective genetic algorithm Nondominated Sorting Genetic Algorithm II (NSGA‐II) to train a neural network and reduced the complexity in training hyperparameters and improved the efficiency by substituting the computationally intensive stochastic gradient descent (SGD) algorithm in a neural network. Specifically, we designed the novel crossover and mutation operators and modified the nondominated ranking and crowding distance sorting procedures in NSGA‐II for GAoNN. Through testing on 8,546 real‐world endoscopy reports, we show that GAoNN achieves a prediction accuracy up to 83.74%, which is better than several competitors by significantly increasing sensitivity to 83.14%. GAoNN also reduces the training time by 30.94% when compared with conventional SGD‐based training, which indicates the feasibility of GAoNN in clinical practice.

show abstract

Efficient fog prediction with multi-objective evolutionary neural networks

Cited by 24 publications

References 46 publications

A review on factors influencing fog formation, classification, forecasting, detection and impacts

A review on factors influencing fog formation, classification, forecasting, detection and impacts

Use of Neural Networks to Identify Safety Prevention Priorities in Agro-Manufacturing Operations within Commercial Grain Elevators

Endoscopy report mining for intelligent gastric cancer screening

Contact Info

Product

Resources

About