A Non-monotonic Activation Function for Neural Networks Validated on Benchmark Tasks

Mishra, Anuradha; Chandra, P.; Ghose, Udayan

doi:10.1007/978-3-030-68291-0_25

Cited by 32 publications

(36 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Finally, the convolutional layers of SegMENT use the Mish activation function (except for the last layers that use a sigmoid activation function). This activation function was selected to replace the traditional Relu activation function as it was shown to provide better performance ( 34 ). The decoder section accepts the encoder outputs with the three resized (16×16, 32×32, and 64×64 pixels) images.…”

Section: Methodsmentioning

confidence: 99%

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images

et al. 2022

View full text Add to dashboard Cite

IntroductionNarrow Band Imaging (NBI) is an endoscopic visualization technique useful for upper aero-digestive tract (UADT) cancer detection and margins evaluation. However, NBI analysis is strongly operator-dependent and requires high expertise, thus limiting its wider implementation. Recently, artificial intelligence (AI) has demonstrated potential for applications in UADT videoendoscopy. Among AI methods, deep learning algorithms, and especially convolutional neural networks (CNNs), are particularly suitable for delineating cancers on videoendoscopy. This study is aimed to develop a CNN for automatic semantic segmentation of UADT cancer on endoscopic images.Materials and MethodsA dataset of white light and NBI videoframes of laryngeal squamous cell carcinoma (LSCC) was collected and manually annotated. A novel DL segmentation model (SegMENT) was designed. SegMENT relies on DeepLabV3+ CNN architecture, modified using Xception as a backbone and incorporating ensemble features from other CNNs. The performance of SegMENT was compared to state-of-the-art CNNs (UNet, ResUNet, and DeepLabv3). SegMENT was then validated on two external datasets of NBI images of oropharyngeal (OPSCC) and oral cavity SCC (OSCC) obtained from a previously published study. The impact of in-domain transfer learning through an ensemble technique was evaluated on the external datasets.Results219 LSCC patients were retrospectively included in the study. A total of 683 videoframes composed the LSCC dataset, while the external validation cohorts of OPSCC and OCSCC contained 116 and 102 images. On the LSCC dataset, SegMENT outperformed the other DL models, obtaining the following median values: 0.68 intersection over union (IoU), 0.81 dice similarity coefficient (DSC), 0.95 recall, 0.78 precision, 0.97 accuracy. For the OCSCC and OPSCC datasets, results were superior compared to previously published data: the median performance metrics were, respectively, improved as follows: DSC=10.3% and 11.9%, recall=15.0% and 5.1%, precision=17.0% and 14.7%, accuracy=4.1% and 10.3%.ConclusionSegMENT achieved promising performances, showing that automatic tumor segmentation in endoscopic images is feasible even within the highly heterogeneous and complex UADT environment. SegMENT outperformed the previously published results on the external validation cohorts. The model demonstrated potential for improved detection of early tumors, more precise biopsies, and better selection of resection margins.

show abstract

Section: Methodsmentioning

confidence: 99%

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Mish activation function is a self-regularizing non-monotonic activation function and have outperformed activation functions namely, Swish, GELU, ReLU, ELU, Leaky ReLU, SELU, SoftPlus, SReLU, ISRU, and RReLU in object classification tasks [30] . Mathematically, Mish activation function can be represented by Eq.…”

Section: Methodsmentioning

confidence: 99%

ETL-YOLO v4: A face mask detection algorithm in era of COVID-19 pandemic

Kumar

Kalia

2022

Optik

View full text Add to dashboard Cite

“…Following the segment

{\mathscr{A}}

, a similar structure is stacked in the segment

{\rm{ {\mathcal B} }}

for the purpose of predicting the potential state of the observed mobile robot. To extract the data features and improve the prediction, two fully connected layers with the Mish activation function 20 are introduced in segment

{\mathscr{C}}

. Finally, the number of the prediction time horizon steps is also set as

{N}^{+}=20

in this study, and the predicted trajectory of the near‐future position is given by

{{\boldsymbol{X}}}_{\,\text{r}\,,k}^{* N+}

.…”

Section: Methodsmentioning

confidence: 99%

An LSTM‐based approach to precise landing of a UAV on a moving platform

Luo

Ebel

Eberhard

2022

Int Journal of Mech Sys Dyn

View full text Add to dashboard Cite

A machine learning‐based method for the precise landing of an unmanned aerial vehicle on a moving mobile platform is proposed. The proposed approach attempts to predict the mobile platform's future trajectory based on the past states of the mobile platform. To that end, it combines a long short‐term memory‐based neural network with a Kalman filter. Hence, it aims at combining the advantages of a machine learning method with those of a state estimation method from established control theory. Based on the predicted trajectory, the unmanned aerial vehicle attempts to land precisely on the moving mobile platform. The experiment is conducted in the Gazebo simulation platform with a quadrotor and an omnidirectional mobile robot, and the proposed method is compared with the single‐method approaches of using only either the Kalman filter or the machine learning method alone.

show abstract

A Non-monotonic Activation Function for Neural Networks Validated on Benchmark Tasks

Cited by 32 publications

References 9 publications

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images

Videomics of the Upper Aero-Digestive Tract Cancer: Deep Learning Applied to White Light and Narrow Band Imaging for Automatic Segmentation of Endoscopic Images

ETL-YOLO v4: A face mask detection algorithm in era of COVID-19 pandemic

An LSTM‐based approach to precise landing of a UAV on a moving platform

Contact Info

Product

Resources

About