Supervised feature selection through Deep Neural Networks with pairwise connected structure

Huang, Yingkun; Jin, Weidong; Yu, Zhibin; Li, Bing

doi:10.1016/j.knosys.2020.106202

Cited by 36 publications

(23 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This also constrains the range of possible 3D coordinates for these keypoints between -1 and 1, allowing the final function of our generators to be a bounded activation function which helps improve adversarial learning [34]. Though feature selection [13,46] can be used to find an optimal amount of spatially independent segments to split a 2D pose into, for simplicity we split our pose up into two during training, the torso and legs. Therefore, two generators will be trained using our adversarial approach and one final generator will be trained using knowledge distillation.…”

Section: Methodsmentioning

confidence: 99%

"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation

Hardy¹,

Dasmahapatra²,

Kim³

2022

Preprint

View full text Add to dashboard Cite

We present TIPSy-GAN, a new approach to improve the accuracy and stability in unsupervised adversarial 2D to 3D human pose estimation. In our work we demonstrate that the human kinematic skeleton should not be assumed as a single spatially codependent structure; in fact, we posit when a full 2D pose is provided during training, there is an inherent bias learned where the 3D coordinate of a keypoint is spatially codependent on the 2D coordinates of all other keypoints. To investigate our hypothesis we follow previous adversarial approaches but train two generators on spatially independent parts of the kinematic skeleton, the torso and the legs. We find that improving the self-consistency cycle is key to lowering the evaluation error and therefore introduce new consistency constraints during training. A TIPSy model is produced via knowledge distillation from these generators which can predict the 3D ordinates for the entire 2D pose with improved results. Furthermore, we address an unanswered question in prior work of how long to train in a truly unsupervised scenario. We show that for two independent generators training adversarially has improved stability than that of a solo generator which collapses. TIPSy decreases the average error by 17% when compared to that of a baseline solo generator on the Human3.6M dataset. TIPSy improves upon other unsupervised approaches while also performing strongly against supervised and weakly-supervised approaches during evaluation on both the Human3.6M and MPI-INF-3DHP datasets. Code and weights of our model will be made available * https://www.ecs.soton.ac.uk/people/ptdh1c20 Preprint. Under review.

show abstract

Section: Methodsmentioning

confidence: 99%

"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation

Hardy¹,

Dasmahapatra²,

Kim³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This research presented different feature selection approaches based on the RNN architecture: long shortterm memory (LSTM), bidirectional LSTM, and gated recurrent unit (GRU). Also, a deep neural network-based feature selection (NeuralFS) was presented in [20]. Another supervised feature selection approach based on developing the first layer in DNN has been presented in [21] and [6].…”

Section: Literature Reviewmentioning

confidence: 99%

“…[28] Random forest [8] Adaptive group lasso [15] Pairwise constraints-based method for feature selection [16] DNN and multilayer bi-directional long short-term memory [18] Deep CNN based on Pearson correlation coefficient [19] Deep learning method for feature selection based on the automatic modulation classification (AMC) scheme [20] Deep Neural network-based Feature Selection [22] Innovative dual-network architecture [30] Term frequency/inverse document frequency, report length, and a bag of words as feature engineering techniques, and LR with multinomial Naïve Bayes as a classifier [31] Naïve-Bayes machine learning model [32] MLP, XGBoost, and LR [1] Filter selection based on GA [33] MLP and LR (Continued)…”

Section: Literature Reviewmentioning

confidence: 99%

An Improved DeepNN with Feature Ranking for Covid-19 Detection

El-Attar¹,

Sabbeh²,

Fasihuddin³

et al. 2022

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

The outbreak of Covid-19 has taken the lives of many patients so far. The symptoms of COVID-19 include muscle pains, loss of taste and smell, coughs, fever, and sore throat, which can lead to severe cases of breathing difficulties, organ failure, and death. Thus, the early detection of the virus is very crucial. COVID-19 can be detected using clinical tests, making us need to know the most important symptoms/features that can enhance the decision process. In this work, we propose a modified multilayer perceptron (MLP) with feature selection (MLPFS) to predict the positive COVID-19 cases based on symptoms and features from patients' electronic medical records (EMR). MLPFS model includes a layer that identifies the most informative symptoms to minimize the number of symptoms base on their relative importance. Training the model with only the highest informative symptoms can fasten the learning process and increase accuracy. Experiments were conducted using three different COVID-19 datasets and eight different models, including the proposed MLPFS. Results show that MLPFS achieves the best feature reduction across all datasets compared to all other experimented models. Additionally, it outperforms the other models in classification results as well as time.

show abstract

“…In this phase, the initial feature set is retained, and a new feature set, the main feature set, is generated using a wrapper-based feature selection strategy that calculates the relative importance of the features in the model and filters out those that are redundant or irrelevant. As linear models are unable to capture the nonlinear relationships between the features and the targets [33], both linear (LR) and nonlinear models (RF and Xgboost) are used to generate the new feature set. First, a backward feature elimination process based LR and t test are applied to select the linear features that have significant linear relationships with the prediction target, TP.…”

Section: Phasementioning

confidence: 99%

A Novel Stacking Heterogeneous Ensemble Model with Hybrid Wrapper‐Based Feature Selection for Reservoir Productivity Predictions

Zhou¹,

Zhou²,

Liu³

et al. 2021

Complexity

View full text Add to dashboard Cite

Acid fracturing is the most important stimulation method in the carbonate reservoir. Due to the high cost and high risk of acid fracturing, it is necessary to predict the reservoir productivity before acid fracturing, which can provide support to optimize the parameters of acid fracturing. However, the productivity of a single well is affected by various construction parameters and geological conditions. Overfitting can occur when performing productivity prediction tasks on the high-dimension, small-sized reservoir, and acid fracturing dataset. Therefore, this study developed a stacking heterogeneous ensemble model with a hybrid wrapper-based feature selection strategy to forecast reservoir productivity, resolve the overfitting problem, and improve productivity prediction. Compared to other baseline models, the proposed model was found to have the best predictive performances on the test set and effectively deal with the overfitting. The results proved that the hybrid wrapper-based feature selection strategy introduced in this study reduced data acquisition costs and improved model comprehensibility without reducing model performance.

show abstract

Supervised feature selection through Deep Neural Networks with pairwise connected structure

Cited by 36 publications

References 25 publications

"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation

"Teaching Independent Parts Separately" (TIPSy-GAN) : Improving Accuracy and Stability in Unsupervised Adversarial 2D to 3D Pose Estimation

An Improved DeepNN with Feature Ranking for Covid-19 Detection

A Novel Stacking Heterogeneous Ensemble Model with Hybrid Wrapper‐Based Feature Selection for Reservoir Productivity Predictions

Contact Info

Product

Resources

About