A Novel One-Dimensional CNN with Exponential Adaptive Gradients for Air Pollution Index Prediction

Ragab, Mohammed Gamal; Abdulkadir, Said Jadid; Aziz, Norshakirah; Al-Tashi, Qasem; Alyousifi, Yousif; Alhussian, Hitham; Alqushaibi, Alawi

doi:10.3390/su122310090

Cited by 63 publications

(26 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In our proposed work to bring out the novel idea of mask learning, we decided to use the basic GA method. More over GA is widely used in hyper parameter learning of CNN and well accepted in the AI eco system [42] and it is very time effective to use GA for our mask learning development phase to prove the concept.…”

Section: Heuristic Algorithms For Proposed Workmentioning

confidence: 99%

Compressive Domain Deep CNN for Image Classification and Performance Improvement Using Genetic Algorithm-Based Sensing Mask Learning

Ramachandran

2022

Applied Sciences

View full text Add to dashboard Cite

The majority of digital images are stored in compressed form. Generally, image classification using convolution neural network (CNN) is done in uncompressed form rather than compressed one. Training the CNN in the compressed domain eliminates the requirement for decompression process and results in improved efficiency, minimal storage, and lesser cost. Compressive sensing (CS) is one of the effective and efficient method for signal acquisition and recovery and CNN training on CS measurements makes the entire process compact. The most popular sensing phenomenon used in CS is based on image acquisition using single pixel camera (SPC) which has complex design implementation and usually a matrix simulation is used to represent the SPC process in numerical demonstration. The CS measurements using this phenomenon are visually different from the image and to add this in the training set of the compressed learning framework, there is a need for an inverse SPC process that is to be applied all through the training and testing dataset image samples. In this paper we proposed a simple sensing phenomenon which can be implemented using the image output of a standard digital camera by retaining few pixels and forcing the rest of the pixels to zero and this reduced set of pixels is assumed as CS measurements. This process is modeled by a binary mask application on the image and the resultant image still subjectively legible for human vision and can be used directly in the training dataset. This sensing mask has very few active pixels at arbitrary locations and there is a lot of scope to heuristically learn the sensing mask suitable for the dataset. Only very few attempts had been made to learn the sensing matrix and the sole effect of this learning process on the improvement of CNN model accuracy is not reported. We proposed to have an ablation approach to study how this sensing matrix learning improves the accuracy of the basic CNN architecture. We applied CS for two class image dataset by applying a Primitive Walsh Hadamard (PWH) binary mask function and performed the classification experiment using a basic CNN. By retaining arbitrary amount of pixel in the training and testing dataset we applied CNN on the compressed measurements to perform image classification and studied and reported the model performance in terms of training and validation accuracies by varying the amount of pixels retained. A novel Genetic Algorithm-based compressive learning (GACL) method is proposed to learn the PWH mask to optimize the model training accuracy by using two different crossover techniques. In the experiment conducted for the case of compression ratio (CR) 90% by retaining only 10% of the pixels in every images both in training and testing dataset that represent two classes, the training accuracy is improved from 67% to 85% by using diagonal crossover in offspring creation of GACL. The robustness of the method is examined by applying GACL for user defined multiclass dataset and achieved better CNN model accuracies. This work will bring out the strength of sensing matrix learning which can be integrated with advanced training models to minimize the amount of information that is to be sent to central servers and will be suitable for a typical IoT frame work.

show abstract

Section: Heuristic Algorithms For Proposed Workmentioning

confidence: 99%

Compressive Domain Deep CNN for Image Classification and Performance Improvement Using Genetic Algorithm-Based Sensing Mask Learning

Ramachandran

2022

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Three types of models were evaluated for the forecasting task: Recurrent Neural Networks with Long Short-Term Memory units (LSTM), Recurrent Neural Networks with Gated Recurrent Units (GRU), and 1D Convolutional Neural Networks (CNN). These neural network architectures have shown recently interesting results on air quality forecasting applications (Krishan et al, 2019;Tao et al, 2019;Ragab et al, 2020;Yan et al, 2021;Kristiani et al, 2022). Although most of these works show predictive advantages over classical methods, it is not clear which of them is more suitable for our system, since the data used in the publications have been collected under different conditions of our system (differences on: input variables, target pollutants, meteorological and pollution conditions, sample size, temporal granularity, forecast time, etc.).…”

Section: Forecasting Model Selectionmentioning

confidence: 99%

An Air Quality Monitoring and Forecasting System for Lima City With Low-Cost Sensors and Artificial Intelligence Models

Montalvo

Fosca²,

Paredes³

et al. 2022

Front. Sustain. Cities

View full text Add to dashboard Cite

Monitoring air quality is very important in urban areas to alert the citizens about the risks posed by the air they breathe. However, implementing conventional monitoring networks may be unfeasible in developing countries due to its high costs. In addition, it is important for the citizen to have current and future air information in the place where he is, to avoid overexposure. In the present work, we describe a low-cost solution deployed in Lima city that is composed of low-cost IoT stations, Artificial Intelligence models, and a web application that can deliver predicted air quality information in a graphical way (pollution maps). In a series of experiments, we assessed the quality of the temporal and spatial prediction. The error levels were satisfactory when compared to reference methods. Our proposal is a cost-effective solution that can help identify high-risk areas of exposure to airborne pollutants and can be replicated in places where there are no resources to implement reference networks.

show abstract

“…A detailed list of hyperparameters and search bounds are shown in Table 2. For the neural network training, we trained it through a variant of adaptive optimizers like Adam, RMSprop, AdaBound, and EAG [93] with initial learning rate of 10 −4 , β 1 = 0.90 and β 2 = 0.99, f ilter = 128, and kernal = 2. We used an initial value of 0.25 as dropout probability in the ninth layer to prevent network overfitting at the training stage.…”

Section: Hyperparameter Tuningmentioning

confidence: 99%

An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification

et al. 2021

Self Cite

View full text Add to dashboard Cite

With the growth of deep learning in various classification problems, many researchers have used deep learning methods in environmental sound classification tasks. This paper introduces an end-to-end method for environmental sound classification based on a one-dimensional convolution neural network with Bayesian optimization and ensemble learning, which directly learns features representation from the audio signal. Several convolutional layers were used to capture the signal and learn various filters relevant to the classification problem. Our proposed method can deal with any audio signal length, as a sliding window divides the signal into overlapped frames. Bayesian optimization accomplished hyperparameter selection and model evaluation with cross-validation. Multiple models with different settings have been developed based on Bayesian optimization to ensure network convergence in both convex and non-convex optimization. An UrbanSound8K dataset was evaluated for the performance of the proposed end-to-end model. The experimental results achieved a classification accuracy of 94.46%, which is 5% higher than existing end-to-end approaches with fewer trainable parameters. Four measurement indices, namely: sensitivity, specificity, accuracy, precision, recall, F-measure, area under ROC curve, and the area under the precision-recall curve were used to measure the model performance. The proposed approach outperformed state-of-the-art end-to-end approaches that use hand-crafted features as input in selected measurement indices and time complexity.

show abstract

A Novel One-Dimensional CNN with Exponential Adaptive Gradients for Air Pollution Index Prediction

Cited by 63 publications

References 82 publications

Compressive Domain Deep CNN for Image Classification and Performance Improvement Using Genetic Algorithm-Based Sensing Mask Learning

Compressive Domain Deep CNN for Image Classification and Performance Improvement Using Genetic Algorithm-Based Sensing Mask Learning

An Air Quality Monitoring and Forecasting System for Lima City With Low-Cost Sensors and Artificial Intelligence Models

An Ensemble One Dimensional Convolutional Neural Network with Bayesian Optimization for Environmental Sound Classification

Contact Info

Product

Resources

About