scholarly journals The Study of Noise Effect on CNN-Based Deep Learning from Medical Images

2021 ◽  
Vol 11 (3) ◽  
pp. 202-207
Author(s):  
Kittipat Sriwong ◽  
◽  
Kittisak Kerdprasop ◽  
Nittaya Kerdprasop
Keyword(s):  
Deep Learning ◽  
Learning Algorithm ◽  
Medical Images ◽  
Research Work ◽  
Health Science ◽  
Learning Performance ◽  
Machine Learning Techniques ◽  
Disease Symptoms ◽  
Deep Learning Algorithm ◽  
Learning Techniques

Currently, computational modeling methods based on machine learning techniques in medical imaging are gaining more and more interests from health science researchers and practitioners. The high interest is due to efficiency of modern algorithms such as convolutional neural networks (CNN) and other types of deep learning. CNN is the most popular deep learning algorithm because of its prominent capability on learning key features from images that help capturing the correct class of images. Moreover, several sophisticated CNN architectures with many learning layers are available in the cloud computing environment. In this study, we are interested in performing empirical research work to compare performance of CNNs when they are dealing with noisy medical images. We design a comparative study to observe performance of the AlexNet CNN model on classifying diseases from medical images of two types: images with noise and images without noise. For the case of noisy images, the data had been further separated into two groups: a group of images that noises harmoniously cover the area of the disease symptoms (NIH) and a group of images that noises do not harmoniously cover the area of the disease symptoms (NNIH). The experimental results reveal that NNIH has insignificant effect toward the performance of CNN. For the group of NIH, we notice some effect of noise on CNN learning performance. In NIH group of images, the data preparation process before learning can improve the efficiency of CNN.

scholarly journals An Enhanced Secure Deep Learning Algorithm for Fraud Detection in Wireless Communication

2021 ◽  
Vol 2021 ◽  
pp. 1-14
Author(s):  
Sumaya Sanober ◽  
Izhar Alam ◽  
Sagar Pande ◽  
Farrukh Arslan ◽  
Kantilal Pitambar Rane ◽  
...  
Keyword(s):  
Deep Learning ◽  
Inflation Rate ◽  
Learning Algorithm ◽  
Credit Cards ◽  
Fraud Detection ◽  
Machine Learning Techniques ◽  
Internet Commerce ◽  
Deep Learning Algorithm ◽  
Financial Conditions ◽  
Learning Techniques

In today’s era of technology, especially in the Internet commerce and banking, the transactions done by the Mastercards have been increasing rapidly. The card becomes the highly useable equipment for Internet shopping. Such demanding and inflation rate causes a considerable damage and enhancement in fraud cases also. It is very much necessary to stop the fraud transactions because it impacts on financial conditions over time the anomaly detection is having some important application to detect the fraud detection. A novel framework which integrates Spark with a deep learning approach is proposed in this work. This work also implements different machine learning techniques for detection of fraudulent like random forest, SVM, logistic regression, decision tree, and KNN. Comparative analysis is done by using various parameters. More than 96% accuracy was obtained for both training and testing datasets. The existing system like Cardwatch, web service-based fraud detection, needs labelled data for both genuine and fraudulent transactions. New frauds cannot be found in these existing techniques. The dataset which is used contains transaction made by credit cards in September 2013 by cardholders of Europe. The dataset contains the transactions occurred in 2 days, in which there are 492 fraud transactions out of 284,807 which is 0.172% of all transaction.

scholarly journals Development of Agriculture Chatbot using Machine Learning Techniques

2019 ◽  
Vol 9 (2S) ◽  
pp. 24-28
Keyword(s):  
Question Answering ◽  
Learning Algorithm ◽  
Related Question ◽  
Machine Learning Techniques ◽  
Meaningful Information ◽  
Related Information ◽  
Exact Answer ◽  
Deep Learning Algorithm ◽  
The People ◽  
Learning Techniques

Agriculture data is a main source of country’s economic growth. It is important to provide agriculture related information to all the people who are involved in agriculture activities as and when required. This meaningful information is used by people who supply services to agriculture domain and to take some correct decision related to agriculture to apply for their field. The solutions to this problem are given by the efficient interaction of computer with human. Chatbot system provides ability to extract the exact answer to the queries posed by farmers. The proposed system is called as Agriculture Chatbot system or even it is called as Question-Answering system for agriculture domain, where farmer is asking the agriculture related question which fetches the precise answers for the asked questions by farmers in natural language and processes the query using RNN (Recurrent Neural Network) deep learning algorithm to extract correct answer.

scholarly journals Segmentation for Complex Background Images using Deep Learning Techniques

2019 ◽  
Vol 8 (2) ◽  
pp. 1746-1750
Keyword(s):  
Computer Vision ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Vision System ◽  
Automated Segmentation ◽  
Computer Vision System ◽  
Important Stage ◽  
Deep Learning Algorithm ◽  
Complex Background ◽  
Learning Techniques

Segmentation is an important stage in any computer vision system. Segmentation involves discarding the objects which are not of our interest and extracting only the object of our interest. Automated segmentation has become very difficult when we have complex background and other challenges like illumination, occlusion etc. In this project we are designing an automated segmentation system using deep learning algorithm to segment images with complex background.

Recognition of speech emotion using custom 2D-convolution neural network deep learning algorithm

2020 ◽  
Vol 24 (5) ◽  
pp. 1065-1086
Author(s):  
Kudakwashe Zvarevashe ◽  
Oludayo O. Olugbara
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Convolution Neural Network ◽  
Machine Learning Techniques ◽  
Speech Emotion Recognition ◽  
Modern World ◽  
Emotional Speech ◽  
Deep Learning Algorithm ◽  
Speech Database

Speech emotion recognition has become the heart of most human computer interaction applications in the modern world. The growing need to develop emotionally intelligent devices has opened up a lot of research opportunities. Most researchers in this field have applied the use of handcrafted features and machine learning techniques in recognising speech emotion. However, these techniques require extra processing steps and handcrafted features are usually not robust. They are computationally intensive because the curse of dimensionality results in low discriminating power. Research has shown that deep learning algorithms are effective for extracting robust and salient features in dataset. In this study, we have developed a custom 2D-convolution neural network that performs both feature extraction and classification of vocal utterances. The neural network has been evaluated against deep multilayer perceptron neural network and deep radial basis function neural network using the Berlin database of emotional speech, Ryerson audio-visual emotional speech database and Surrey audio-visual expressed emotion corpus. The described deep learning algorithm achieves the highest precision, recall and F1-scores when compared to other existing algorithms. It is observed that there may be need to develop customized solutions for different language settings depending on the area of applications.

scholarly journals A Deep-Learning-Driven Light-Weight Phishing Detection Sensor

Sensors ◽  
2019 ◽  
Vol 19 (19) ◽  
pp. 4258 ◽  
Author(s):  
Bo Wei ◽  
Rebeen Ali Hamad ◽  
Longzhi Yang ◽  
Xuan He ◽  
Hao Wang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Energy Saving ◽  
Real Time ◽  
Learning Algorithm ◽  
Rapid Development ◽  
Social Engineering ◽  
Machine Learning Techniques ◽  
Light Weight ◽  
Learning Techniques ◽  
Phishing Detection

This paper designs an accurate and low-cost phishing detection sensor by exploring deep learning techniques. Phishing is a very common social engineering technique. The attackers try to deceive online users by mimicking a uniform resource locator (URL) and a webpage. Traditionally, phishing detection is largely based on manual reports from users. Machine learning techniques have recently been introduced for phishing detection. With the recent rapid development of deep learning techniques, many deep-learning-based recognition methods have also been explored to improve classification performance. This paper proposes a light-weight deep learning algorithm to detect the malicious URLs and enable a real-time and energy-saving phishing detection sensor. Experimental tests and comparisons have been conducted to verify the efficacy of the proposed method. According to the experiments, the true detection rate has been improved. This paper has also verified that the proposed method can run in an energy-saving embedded single board computer in real-time.

scholarly journals Effective Deep Learning Based Architecture for Pedestrian Detection from Digital Images

2020 ◽  
Vol 9 (3) ◽  
pp. 1498-1508
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Object Detection ◽  
Learning Algorithm ◽  
Pedestrian Detection ◽  
Single Shot ◽  
Deep Learning Algorithm ◽  
Learning Techniques ◽  
Rgb Images ◽  
Deep Convolution Network

This paper is to present an efficient and fast deep learning algorithm based on neural networks for object detection and pedestrian detection. The technique, called MobileNet Single Shot Detector, is an extension to Convolution Neural Networks. This technique is based on depth-wise distinguishable convolutions in order to build a lightweighted deep convolution network. A single filter is applied to each input and outputs are combined by using pointwise convolution. Single Shot Multibox Detector is a feed forward convolution network that is combined with MobileNets to give efficient and accurate results. MobileNets combined with SSD and Multibox Technique makes it much faster than SSD alone can work. The accuracy for this technique is calculated over colored (RGB images) and also on infrared images and its results are compared with the results of shallow machine learning based feature extraction plus classification technique viz. HOG plus SVM technique. The comparison of performance between proposed deep learning and shallow learning techniques has been conducted over benchmark dataset and validation testing over own dataset in order measure efficiency of both algorithms and find an effective algorithm that can work with speed and accurately to be applied for object detection in real world pedestrian detection application.

scholarly journals Autism spectrum disorder classification on electroencephalogram signal using deep learning algorithm

2020 ◽  
Vol 9 (1) ◽  
pp. 91
Author(s):  
Nur Alisa Ali
Keyword(s):  
Autism Spectrum Disorder ◽  
Pattern Recognition ◽  
Deep Learning ◽  
Learning Algorithm ◽  
Research Work ◽  
Autism Spectrum ◽  
Performance Measure ◽  
Spectrum Disorder ◽  
Font Size ◽  
Deep Learning Algorithm

<span style="color: black; font-family: 'Times New Roman',serif; font-size: 9pt; mso-fareast-font-family: 'Times New Roman'; mso-themecolor: text1; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;" lang="EN-US">Autism Spectrum Disorder (ASD) is a neurodevelopmental that impact the social interaction and communication skills. Diagnosis of ASD is one of the difficult problems facing researchers. This research work aimed to reveal the different pattern between autistic and normal children via electroencephalogram (EEG) by using the deep learning algorithm. The brain signal database used pattern recognition where the extracted features will undergo the multilayer perceptron network for the classification process. The promising method to perform the classification is through a deep learning algorithm, which is currently a well-known and superior method in the pattern recognition field. The performance measure for the classification would be the accuracy. The higher percentage means the more effectiveness for the ASD diagnosis. </span><span style="color: black; font-family: 'Times New Roman',serif; font-size: 9pt; mso-fareast-font-family: 'Times New Roman+FPEF'; mso-themecolor: text1; mso-ansi-language: EN-US; mso-fareast-language: EN-US; mso-bidi-language: AR-SA;" lang="EN-US">This can be seen as the ground work for applying a new algorithm for further development diagnosis of autism to see how the treatment is working as well in future.</span>

scholarly journals Change Detection using Deep Learning and Machine Learning Techniques for Multispectral Satellite Images

2019 ◽  
Vol 9 (1S) ◽  
pp. 90-93
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Change Detection ◽  
Research Work ◽  
Machine Learning Techniques ◽  
Remote Sensing Images ◽  
Detection Analysis ◽  
Learning Techniques ◽  
And Performance

Change detection is used to find whether the changes happened or not between two different time periods using remote sensing images. We can use various machine learning techniques and deep learning techniques for the change detection analysis using remote sensing images. This paper mainly focused on computational and performance analysis of both techniques in the application of change detection .For each approach, we considered ten different kinds of algorithms and evaluated the performance. Moreover, in this research work, we have analyzed merits and demerits of each method which have used to change detection.

scholarly journals Vision-Based Deep Learning Algorithm for Detecting Potholes

2021 ◽  
Author(s):  
Kanushka Gajjar ◽  
Theo van Niekerk ◽  
Thomas Wilm ◽  
Paolo Mercorelli
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Autonomous Vehicles ◽  
Learning Algorithm ◽  
Detection System ◽  
Detection Methods ◽  
Deep Learning Algorithm ◽  
Learning Techniques ◽  
Pothole Detection ◽  
Adequate Data

Potholes on roads pose a major threat to motorists and autonomous vehicles. Driving over a pothole has the potential to cause serious damage to a vehicle, which in turn may result in fatal accidents. Currently, many pothole detection methods exist. However, these methods do not utilize deep learning techniques to detect a pothole in real-time, determine the location thereof and display its location on a map. The success of determining an effective pothole detection method, which includes the aforementioned deep learning techniques, is dependent on acquiring a large amount of data, including images of potholes. Once adequate data had been gathered, the images were processed and annotated. The next step was to determine which deep learning algorithms could be utilized. Three different models, including Faster R-CNN, SSD and YOLOv3 were trained on the custom dataset containing images of potholes to determine which network produces the best results for real-time detection. It was revealed that YOLOv3 produced the most accurate results and performed the best in real-time, with an average detection time of only 0.836s per image. The final results revealed that a real-time pothole detection system, integrated with a cloud and maps service, can be created to allow drivers to avoid potholes.

scholarly journals Faultless Decision Making for False Information in Online: A Systematic Approach

2021 ◽  
Vol 2 (4) ◽  
pp. 226-235
Author(s):  
Yasir Babiker Hamdan ◽  
Sathish
Keyword(s):  
Decision Making ◽  
Deep Learning ◽  
Systematic Approach ◽  
Learning Algorithm ◽  
Research Work ◽  
High Accuracy ◽  
Fake News ◽  
False Information ◽  
Q Learning ◽  
Deep Learning Algorithm

An identifying the news are real or fake instantly with high accuracy is a challenging work. The deep learning algorithm is implementing here to acquire very accurate separation of real and fake news rather than other methods. This research work constructs naïve bayes and CNN classifiers with Q-learning decision making. The two different approaches detect fake news in online and it gives to decision making section which is designed at tail in our research. The deep decision making section compares the input and make the decision wisely and it provides the more accurate output rather than single classifiers in deep learning. This research work comprises compare between our proposed works with single classifiers.

Sign in / Sign up

Export Citation Format

Share Document