Survey on Evolving Deep Learning Neural Network Architectures

Bashar, Abul

doi:10.36548/jaicn.2019.2.003

Cited by 155 publications

(40 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On a separate note, [27] deep learning has successfully proved its potential for image processing over the last two decades. One of its significant success was achieved when transfer learning model Alexnet [5] demonstrated its efficacy for image classification tasks on a broader scale.…”

Section: Problem Statementmentioning

confidence: 99%

RansomListener: Ransom Call Sound Investigation Using LSTM and CNN Architectures

Rahman

Hossain

et al. 2021

2021 6th International Conference on Inventive Computation Technologies (ICICT)

View full text Add to dashboard Cite

Getting calls for ransoms are common phenomena in kidnapping and abduction related incidents where the life of the victim remains extremely vulnerable. These phone calls are often analyzed in real-time by law enforcement authorities to quickly identify the suspects and get crucial information for quick action. However, it is often difficult to manually analyze those phone calls due to the quality of sounds and the presence of several background noises. Even with much high-end software in their inventory, it is futile to accurately refine the incoming calls as it takes a huge amount of time to declutter the different layers of noises in the call. This paper proposes a model based on deep convolutional neural network and signal processing for automatic classification of crucial sounds in ransom related phone calls. We have proposed LSTM and 2D CNN customized models and compared their outputs with VGG16 and AlexNet. Moreover, this paper also presents a unique dataset of different sounds in terms of voices like male or female and the environmental sounds where the victim might be in which can be a probable clue for investigation purposes consisting of 17650 audio clips collected from verified online sources. Finally, the models produced very high classification accuracy with the accuracy of LSTM reaching around 93.4%.

show abstract

Section: Problem Statementmentioning

confidence: 99%

RansomListener: Ransom Call Sound Investigation Using LSTM and CNN Architectures

Rahman

Hossain

et al. 2021

2021 6th International Conference on Inventive Computation Technologies (ICICT)

View full text Add to dashboard Cite

show abstract

“…the amount of segmented sections increases the insulating image's segmentation outcomes. Orlando et al [18] did a beautiful job of demonstrating how two different CNNs, OverFeat and VGG-S, might be used as feature extractors. Tey also looked into how the performance of these networks changes when the fundus pictures are subjected to contrastlimited adaptive histogram equalisation (CLAHE) and vessel elimination.…”

Section: IImentioning

confidence: 99%

Diagnosing Chronic Glaucoma Using Watershed and Convolutional Neural Network

Fathima¹

2021

IJRASET

View full text Add to dashboard Cite

Glaucoma is a disease that relates to the vision of human eye,Glaucoma is a disease that affects the human eye's vision. This sickness is regarded as an irreversible condition that causes eyesight degeneration. One of the most common causes of lifelong blindness is glaucoma in persons over the age of 40. Because of its trade-off between portability, size, and cost, fundus imaging is the most often utilised screening tool for glaucoma detection. Fundus imaging is a two-dimensional (2D) depiction of the three-dimensional (3D), semitransparent retinal tissues projected on to the imaging plane using reflected light. The idea plane that depicts the physical display screen through which a user perceives a virtual 3D scene is referred to as the "image plane”. The bulk of current algorithms for autonomous glaucoma assessment using fundus images rely on handcrafted segmentation-based features, which are influenced by the segmentation method used and the retrieved features. Convolutional neural networks (CNNs) are known for, among other things, their ability to learn highly discriminative features from raw pixel intensities. This work describes a computational technique for detecting glaucoma automatically. The major goal is to use a "image processing technique" to diagnose glaucoma using a fundus image as input. It trains datasets using a convolutional neural network (CNN). The Watershed algorithm is used for segmentation and is the most widely used technique in image processing. The following image processing processes are performed: region of interest, morphological procedures, and segmentation. This technique can be used to determine whether or not a person has Glaucoma. Keywords: Recommender system, item-based collaborative filtering, Natural Language Processing, Deep learning.

show abstract

“…DNN is used in this study as one of the DL techniques. Neural network consists of three main parts [10], which are input layer, hidden layer, and output layer; DNN is used here to predict the decision, as shown in Figure 3.…”

Section: Strategies Of Management Modelmentioning

confidence: 99%

Research on Management Model Based on Deep Learning

Zhao

2021

Complexity

View full text Add to dashboard Cite

In this study, the focus was on the development of management models and future prediction for the cost and risk by using an improved deep learning (DL) algorithm. Management model can be defined as the management activities that are interlinked and organized inside organization of institutions. Different opportunities and different organizations are offered by different management models. Proper management models lead to strategies and decisions help to success organization. Deep neural network (DNN) is proposed to make good prediction for organization for increasing the cost and reduce risk in companies and institutions. The error of prediction is updated according to variable hidden layers and nodes within iteration. Improved DNN is used and modify weights that have an effect on the features extracted in advance to increase the accuracy and precisions are used. The proposed method is based on dynamic hidden layers with backpropagation and feedforward. Absolute mean relative error (AMRE) and variance (R2) are used for evaluation in term of accuracy. The training system is used with three available datasets from big company, health issue, and industry. Gained result proves the worth of the proposed system and is suitable for predicting complex data and reducing the risk as possible.

show abstract

Survey on Evolving Deep Learning Neural Network Architectures

Cited by 155 publications

References 21 publications

RansomListener: Ransom Call Sound Investigation Using LSTM and CNN Architectures

RansomListener: Ransom Call Sound Investigation Using LSTM and CNN Architectures

Diagnosing Chronic Glaucoma Using Watershed and Convolutional Neural Network

Research on Management Model Based on Deep Learning

Contact Info

Product

Resources

About