Unsupervised Learning Based On Artificial Neural Network: A Review

Dike, Happiness Ugochi; Zhou, Yimin; Deveerasetty, Kranthi Kumar; Wu, Qingtian

doi:10.1109/cbs.2018.8612259

Cited by 118 publications

(67 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike supervised learning, unsupervised learning focuses on discovering the hidden patterns within the dataset without any interference and supervision from humans. This means that the unsupervised algorithms use unlabeled datasets, which are complex and unrelated, and organize them in meaningful ways [7]. Unsupervised learning includes various techniques and some of these techniques are presented in the next sections and their performances have been evaluated for the NDT of printed samples.…”

Section: The Unsupervised Learning and Clustering Resultsmentioning

confidence: 99%

“…The obtained raw data have been then processed using the matched filter technique and further processed by the median filter to attenuate noise level and improve the acquired results [6]. After obtaining the SAR images of the sample layers, these images have been further directed to a clustering process using the concept of the unsupervised learning [7]. The unsupervised learning is a machine learning branch that includes different techniques which allow the model to deal with unlabeled data and discover information based on its own [7].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Investigation on the scattering characteristics and unsupervised clustering of 3D printed samples

Elsaadouny

Barowski

Jebramcik

et al. 2020

Int. J. Microw. Wireless Technol.

View full text Add to dashboard Cite

In this work, the scattering characteristics of 3D-printed samples are being investigated by using a single-polarized and a cross-polarized radar system. The 3D-printed technology participates in a wide range of applications nowadays. The idea of synthetic aperture radar (SAR) has been utilized to investigate the reflected electromagnetic energy from the 3D-printed samples by setting each of the radar systems in a fixed position and the mounting sample on an x-y positioning table which has been used to achieve rectangular-scan mode for SAR. The data have been ported and processed by the matched filter approach. For better image interpretation, the data have been further processed by the median filter in order to reduce noise level while preserving the main image details. Afterwards, the data have been further investigated for determining and classifying any possible defects. This process has been accomplished by deploying the unsupervised learning concept to cluster the SAR responses into two groups, compromising the defected positions responses and the non-defected responses. The obtained results of both radar sensors have been compared and evaluated using different quality assessment factors. Moreover, unsupervised learning techniques have been investigated and the obtained results show a high degree of efficiency in clustering the SAR responses.

show abstract

Section: The Unsupervised Learning and Clustering Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Investigation on the scattering characteristics and unsupervised clustering of 3D printed samples

Elsaadouny

Barowski

Jebramcik

et al. 2020

Int. J. Microw. Wireless Technol.

View full text Add to dashboard Cite

show abstract

“…The data prepared previously was used to train neural networkbased models in order to make predictions. Once a neural network has structured for a particular application, it may instantly be used for training purpose [45].…”

Section: Data Encodingmentioning

confidence: 99%

Discovering software developer's coding expertise through deep learning

et al. 2020

View full text Add to dashboard Cite

The field of software development is growing rapidly and prevailing in every walk of life. The role of software developers in such a challenging and complex activity is very much important. The allocation of right software developers (i.e. who possesses appropriate coding skills) to projects is one of the crucial factors for successful software development. The problem is that it is very difficult for a client, project manager, as well as for software development organisations to find out an appropriate developer and assign him/her to a particular project. To achieve this, there is a need for such a sound mechanism that could detect the level of software developer coding expertise. This study has formulated criteria for novice and expert developers and carried out such criteria to discover the level of coding expertise of software developers using three different models of deep learning. These models include long short-term memory (LSTM), convolution 1D and hybrid (a combination of LSTM and convolution 1D). The deep learning models have analysed software developers' previously written source code collected from the GitHub repository. An experiment was conducted to evaluate the performance of models. The results showed that the LSTM model performed better in comparison to other models by achieving 96.25% accuracy.

show abstract

“…Machine learning can be divided into three categories: Supervised learning [21], unsupervised learning [22] and reinforcement learning. The supervised learning algorithm is based on the budget to access the desired output of the limited input (training tag), and optimizes the selection of the input it receives for the training tag.…”

Section: Machine Learningmentioning

confidence: 99%

Traffic Light Cycle Configuration of Single Intersection Based on Modified Q-Learning

et al. 2019

View full text Add to dashboard Cite

In recent years, within large cities with a high population density, traffic congestion has become more and more serious, resulting in increased emissions of vehicles and reducing the efficiency of urban operations. Many factors have caused traffic congestion, such as insufficient road capacity, high vehicle density, poor urban traffic planning and inconsistent traffic light cycle configuration. Among these factors, the problems of traffic light cycle configuration are the focal points of this paper. If traffic lights can adjust the cycle dynamically with traffic data, it will reduce degrees of traffic congestion significantly. Therefore, a modified mechanism based on Q-Learning to optimize traffic light cycle configuration is proposed to obtain lower average vehicle delay time, while keeping significantly fewer processing steps. The experimental results will show that the number of processing steps of this proposed mechanism is 11.76 times fewer than that of the exhaustive search scheme, and also that the average vehicle delay is only slightly lower than that of the exhaustive search scheme by 5.4%. Therefore the proposed modified Q-learning mechanism will be capable of reducing the degrees of traffic congestions effectively by minimizing processing steps.

show abstract

Unsupervised Learning Based On Artificial Neural Network: A Review

Cited by 118 publications

References 18 publications

Investigation on the scattering characteristics and unsupervised clustering of 3D printed samples

Investigation on the scattering characteristics and unsupervised clustering of 3D printed samples

Discovering software developer's coding expertise through deep learning

Traffic Light Cycle Configuration of Single Intersection Based on Modified Q-Learning

Contact Info

Product

Resources

About