scholarly journals Design and Implementation of Fast Spoken Foul Language Recognition with Different End-to-End Deep Neural Network Architectures

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 710
Author(s):  
Abdulaziz Saleh Ba Wazir ◽  
Hezerul Abdul Karim ◽  
Mohd Haris Lye Abdullah ◽  
Nouar AlDahoul ◽  
Sarina Mansor ◽  
...  
Keyword(s):  
Neural Networks ◽  
Short Term Memory ◽  
Intelligent System ◽  
False Negative ◽  
Computational Cost ◽  
False Negative Rate ◽  
High Volume ◽  
Language Recognition ◽  
Deep Convolutional Neural Networks ◽  
Low Performance

Given the excessive foul language identified in audio and video files and the detrimental consequences to an individual’s character and behaviour, content censorship is crucial to filter profanities from young viewers with higher exposure to uncensored content. Although manual detection and censorship were implemented, the methods proved tedious. Inevitably, misidentifications involving foul language owing to human weariness and the low performance in human visual systems concerning long screening time occurred. As such, this paper proposed an intelligent system for foul language censorship through a mechanized and strong detection method using advanced deep Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) through Long Short-Term Memory (LSTM) cells. Data on foul language were collected, annotated, augmented, and analysed for the development and evaluation of both CNN and RNN configurations. Hence, the results indicated the feasibility of the suggested systems by reporting a high volume of curse word identifications with only 2.53% to 5.92% of False Negative Rate (FNR). The proposed system outperformed state-of-the-art pre-trained neural networks on the novel foul language dataset and proved to reduce the computational cost with minimal trainable parameters.

scholarly journals Evaluation of Mixed Deep Neural Networks for Reverberant Speech Enhancement

Biomimetics ◽  
2019 ◽  
Vol 5 (1) ◽  
pp. 1 ◽  
Author(s):  
Michelle Gutiérrez-Muñoz ◽  
Astryd González-Salazar ◽  
Marvin Coto-Jiménez
Keyword(s):  
Neural Networks ◽  
Short Term Memory ◽  
Computational Cost ◽  
Real Life ◽  
Fixed Number ◽  
Training Procedure ◽  
Statistical Validation ◽  
Significant Drop ◽  
Training Time ◽  
Important Solution

Speech signals are degraded in real-life environments, as a product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions. To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combinations of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation was made based on quality measurements of the signal’s spectrum, the training time of the networks, and statistical validation of results. In total, 120 artificial neural networks of eight different types were trained and compared. The results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, given that reduction in training time is on the order of 30%, in processes that can normally take several days or weeks, depending on the amount of data. The results also present advantages in efficiency, but without a significant drop in quality.

scholarly journals Evaluation of Mixed Deep Neural Networks for Reverberant Speech Enhancement

2019 ◽  
Author(s):  
Michelle Gutiérrez-Muñoz ◽  
Astryd González-Salazar ◽  
Marvin Coto-Jiménez
Keyword(s):  
Neural Networks ◽  
Short Term Memory ◽  
Computational Cost ◽  
Real Life ◽  
Fixed Number ◽  
Training Procedure ◽  
Statistical Validation ◽  
Training Time ◽  
Important Solution ◽  
Reverberant Speech

Speech signals are degraded in real-life environments, product of background noise or other factors. The processing of such signals for voice recognition and voice analysis systems presents important challenges. One of the conditions that make adverse quality difficult to handle in those systems is reverberation, produced by sound wave reflections that travel from the source to the microphone in multiple directions.To enhance signals in such adverse conditions, several deep learning-based methods have been proposed and proven to be effective. Recently, recurrent neural networks, especially those with long and short-term memory (LSTM), have presented surprising results in tasks related to time-dependent processing of signals, such as speech. One of the most challenging aspects of LSTM networks is the high computational cost of the training procedure, which has limited extended experimentation in several cases. In this work, we present a proposal to evaluate the hybrid models of neural networks to learn different reverberation conditions without any previous information. The results show that some combination of LSTM and perceptron layers produce good results in comparison to those from pure LSTM networks, given a fixed number of layers. The evaluation has been made based on quality measurements of the signal's spectrum, training time of the networks and statistical validation of results. Results help to affirm the fact that hybrid networks represent an important solution for speech signal enhancement, with advantages in efficiency, but without a significan drop in quality.

scholarly journals CircConv: A Structured Convolution with Low Complexity

2019 ◽  
Vol 33 ◽  
pp. 4287-4294
Author(s):  
Siyu Liao ◽  
Bo Yuan
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Neural Networks ◽  
Computational Cost ◽  
Low Complexity ◽  
Deep Convolutional Neural Networks ◽  
Significant Saving ◽  
Machine Learning Applications ◽  
Fast Multiplication ◽  
Large Model

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation resource and weight storage, thereby limiting the practical deployment of DNNs. To overcome these limitations, this paper proposes to impose the circulant structure to the construction of convolutional layers, and hence leads to circulant convolutional layers (CircConvs) and circulant CNNs. The circulant structure and models can be either trained from scratch or re-trained from a pre-trained non-circulant model, thereby making it very flexible for different training environments. Through extensive experiments, such strong structureimposing approach is proved to be able to substantially reduce the number of parameters of convolutional layers and enable significant saving of computational cost by using fast multiplication of the circulant tensor.

scholarly journals COVID-19 automatic diagnosis with CT images using the novel Transformer architecture

2021 ◽  
Author(s):  
Gabriel Sousa Silva Costa ◽  
Anselmo C. Paiva ◽  
Geraldo Braz Júnior ◽  
Marco Melo Ferreira
Keyword(s):  
Intelligent System ◽  
State Of The Art ◽  
False Negative ◽  
False Negative Rate ◽  
Ct Images ◽  
The Novel ◽  
Chain Reaction ◽  
High False Negative Rate ◽  
Polymerase Chain ◽  
Low Sensitivity

Even though vaccines are already in use worldwide, the COVID-19 pandemic is far from over, with some countries re-establishing the lockdown state, the virus has taken over 2 million lives until today, being a serious health issue. Although real-time reverse transcription-polymerase chain reaction (RTPCR) is the first tool for COVID-19 diagnosis, its high false-negative rate and low sensitivity might delay accurate diagnosis. Therefore, fast COVID-19 diagnosis and quarantine, combined with effective vaccination plans, is crucial for the pandemic to be over as soon as possible. To that end, we propose an intelligent system to classify computed tomography (CT) of lung images between a normal, pneumonia caused by something other than the coronavirus or pneumonia caused by the coronavirus. This paper aims to evaluate a complete selfattention mechanism with a Transformer network to capture COVID-19 pattern over CT images. This approach has reached the state-of-the-art in multiple NLP problems and just recently is being applied for computer vision tasks. We combine vision transformer and performer (linear attention transformers), and also a modified vision transformer, reaching 96.00% accuracy.

scholarly journals Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4

2021 ◽  
Author(s):  
Mohammed Abdulla Salim Al Husaini ◽  
Mohamed Hadi Habaebi ◽  
Teddy Surya Gunawan ◽  
Md Rafiqul Islam ◽  
Elfatih A. A. Elsheikh ◽  
...  
Keyword(s):  
Breast Cancer ◽  
Neural Networks ◽  
Deep Learning ◽  
Convolutional Neural Networks ◽  
Early Stage ◽  
Computational Cost ◽  
Optimization Methods ◽  
Optimization Method ◽  
Deep Convolutional Neural Networks ◽  
Breast Thermography

AbstractBreast cancer is one of the most significant causes of death for women around the world. Breast thermography supported by deep convolutional neural networks is expected to contribute significantly to early detection and facilitate treatment at an early stage. The goal of this study is to investigate the behavior of different recent deep learning methods for identifying breast disorders. To evaluate our proposal, we built classifiers based on deep convolutional neural networks modelling inception V3, inception V4, and a modified version of the latter called inception MV4. MV4 was introduced to maintain the computational cost across all layers by making the resultant number of features and the number of pixel positions equal. DMR database was used for these deep learning models in classifying thermal images of healthy and sick patients. A set of epochs 3–30 were used in conjunction with learning rates 1 × 10–3, 1 × 10–4 and 1 × 10–5, Minibatch 10 and different optimization methods. The training results showed that inception V4 and MV4 with color images, a learning rate of 1 × 10–4, and SGDM optimization method, reached very high accuracy, verified through several experimental repetitions. With grayscale images, inception V3 outperforms V4 and MV4 by a considerable accuracy margin, for any optimization methods. In fact, the inception V3 (grayscale) performance is almost comparable to inception V4 and MV4 (color) performance but only after 20–30 epochs. inception MV4 achieved 7% faster classification response time compared to V4. The use of MV4 model is found to contribute to saving energy consumed and fluidity in arithmetic operations for the graphic processor. The results also indicate that increasing the number of layers may not necessarily be useful in improving the performance.

scholarly journals An Efficient Methodology for Object Classification Using Light Weight Deep Convolutional Neural Networks

2019 ◽  
Vol 8 (2) ◽  
pp. 5965-5968
Keyword(s):  
Neural Networks ◽  
Object Detection ◽  
Computational Cost ◽  
Computational Time ◽  
Video Frame ◽  
Surveillance Systems ◽  
Light Weight ◽  
Deep Convolutional Neural Networks ◽  
Deep Convolution Neural Network ◽  
Improving Accuracy

In current era, deep convolution neural networks (DCNNs) have good break-through in processing images while reducing computational cost and increasing accuracy. Proposed approach focuses on object detection using classification with DCNN model. This model uses feature map for pre-processing the images and convolution layers helps to minimize the processing using deep learning perceptron’s. After that the proposed approach uses Light – Weight Deep Convolution Neural Network(LW_DCNN) Model which includes less number of convolution layers, Max Pooling layers with relevant parameters and Dense, flatten layers to train the data using Leaky ReLU function for improving accuracy. The proposed methodology LW_DCNN is highly efficient compared to traditional classification techniques and presenting simple and powerful model for object detection in Video Surveillance Systems. This model also tested on GPU systems and proved efficiency in less computational time. Obtained Results are clearly shows that model is more efficient in classifying the objects intern classifying the working condition of the overhead power polls insulators in real time video frame sequences.

scholarly journals IDS-attention: an efficient algorithm for intrusion detection systems using attention mechanism

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
FatimaEzzahra Laghrissi ◽  
Samira Douzi ◽  
Khadija Douzi ◽  
Badr Hssina
Keyword(s):  
Intrusion Detection ◽  
Intrusion Detection System ◽  
Short Term Memory ◽  
Detection System ◽  
False Negative ◽  
False Negative Rate ◽  
Attention Mechanism ◽  
Intrusion Detection Systems ◽  
Network Attacks ◽  
Detection Systems

AbstractNetwork attacks are illegal activities on digital resources within an organizational network with the express intention of compromising systems. A cyber attack can be directed by individuals, communities, states or even from an anonymous source. Hackers commonly conduct network attacks to alter, damage, or steal private data. Intrusion detection systems (IDS) are the best and most effective techniques when it comes to tackle these threats. An IDS is a software application or hardware device that monitors traffic to search for malevolent activity or policy breaches. Moreover, IDSs are designed to be deployed in different environments, and they can either be host-based or network-based. A host-based intrusion detection system is installed on the client computer, while a network-based intrusion detection system is located on the network. IDSs based on deep learning have been used in the past few years and proved their effectiveness. However, these approaches produce a big false negative rate, which impacts the performance and potency of network security. In this paper, a detection model based on long short-term memory (LSTM) and Attention mechanism is proposed. Furthermore, we used four reduction algorithms, namely: Chi-Square, UMAP, Principal Components Analysis (PCA), and Mutual information. In addition, we evaluated the proposed approaches on the NSL-KDD dataset. The experimental results demonstrate that using Attention with all features and using PCA with 03 components had the best performance, reaching an accuracy of 99.09% and 98.49% for binary and multiclass classification, respectively.

A prospective study to evaluate the accuracy of axillary staging using ultrasound and USG-guided fine needle aspiration cytology in early breast cancer patients in a high-volume center.

2019 ◽  
Vol 37 (15_suppl) ◽  
pp. e12060-e12060
Author(s):  
Rashpal Singh ◽  
Ekta Dhamija ◽  
SVS Deo ◽  
Sandeep Mathur ◽  
Sanjay Thulkar
Keyword(s):  
Breast Cancer ◽  
Cancer Patients ◽  
Early Breast Cancer ◽  
False Negative ◽  
False Negative Rate ◽  
High Volume ◽  
Axillary Staging ◽  
Axillary Lymph ◽  
Breast Cancer Patients ◽  
Developing Nation

e12060 Background: In breast cancer, axillary lymph node involvement directly impacts the patient survival and prognosis.Sentinel lymph node biopsy (SLNB) is a procedure of choice for axillary staging in early breast cancer. Currently, management options for axilla management are ALND & SLNB in node positive & in node negative respectively. In developing nation like India,where resource constraints, logistics issues and over burden health institutes create difficulty in managing patients, our study address this issue by implementing USG and USG-FNAC in early breast cancer patients in developing nation. Methods: All early breast cancer patients were screend by ultrasound axilla to categorise the nodes as suspicious or non suspicious. Suspicious nodes underwent USG & FNAC using vascualr pedicle based nodal mapping for node targeted on USG-FNAC, if node found to be positive, patient underwent ALND & negative node patients underwent SLNB.All non-suspicious nodes patient underwent SLNB. Final histopathology was taken as gold standard. The sensitivity, specificity, accuracy, positive predictive value and negative predictive value, accuacy and false negative rate calculated for USG & USG-FNAC. Results: Total 100 patients included in which 58 were non-suspicious and 42 suspicious nodes on USG. Among suspicious group, 24 were positive on USG-FNAC & 18 were negative.In non suspicious SLNB done in all. False negative rate of USG & USG-FNAC was 38% and 17% respectively. Conclusions: Our study indicates the feasibility of USG & USG-FNAC in a high volume centre with good accuracy of around 70- 80%.Overall, 24 % of total patients can be taken up for ALND without performing SLNB.This study can guide us to utilize ultrasound and ultrasound-guided FNAC as a routine evaluation tool in the pre operative assessment of axillary lymph nodes in early breast cancer. Our study showed good and acceptable result (75%) in isolating and retrieving the targeted node by just following the Vascular pedicle based node mapping of axilla to locate the suspicious node without using any tagging or marking of node from where FNAC was performed. This finding can act as a good practicing tool in a busy high volume, logistics issue and and resource constraint hospitals.[Table: see text]

scholarly journals Evaluation of Deep Learning Neural Networks for Surface Roughness Prediction Using Vibration Signal Analysis

2019 ◽  
Vol 9 (7) ◽  
pp. 1462 ◽  
Author(s):  
Wan-Ju Lin ◽  
Shih-Hsuan Lo ◽  
Hong-Tsu Young ◽  
Che-Lun Hung
Keyword(s):  
Neural Networks ◽  
Surface Roughness ◽  
Fourier Transform ◽  
Deep Learning ◽  
Fast Fourier Transform ◽  
Short Term Memory ◽  
Intelligent System ◽  
Milling Process ◽  
Vibration Signals ◽  
One Dimensional

The use of surface roughness (Ra) to indicate product quality in the milling process in an intelligent monitoring system applied in-process has been developing. From the considerations of convenient installation and cost-effectiveness, accelerator vibration signals combined with deep learning predictive models for predicting surface roughness is a potential tool. In this paper, three models, namely, Fast Fourier Transform-Deep Neural Networks (FFT-DNN), Fast Fourier Transform Long Short Term Memory Network (FFT-LSTM), and one-dimensional convolutional neural network (1-D CNN), are used to explore the training and prediction performances. Feature extraction plays an important role in the training and predicting results. FFT and the one-dimensional convolution filter, known as 1-D CNN, are employed to extract vibration signals’ raw data. The results show the following: (1) the LSTM model presents the temporal modeling ability to achieve a good performance at higher Ra value and (2) 1-D CNN, which is better at extracting features, exhibits highly accurate prediction performance at lower Ra ranges. Based on the results, vibration signals combined with a deep learning predictive model could be applied to predict the surface roughness in the milling process. Based on this experimental study, the use of prediction of the surface roughness via vibration signals using FFT-LSTM or 1-D CNN is recommended to develop an intelligent system.

Sign in / Sign up

Export Citation Format

Share Document