Analysis of Skin Marks Through the Use of Intelligent Things

Połap, Dawid

doi:10.1109/access.2019.2947354

Cited by 41 publications

(22 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Petnik et al describes the implementation of KNX technology for controlling and monitoring operational and technical functions in SHs within the IoT cloud platform [6]. The SHC platform and health care platform [7,8] are being prepared to use the IoT concepts within the fifth generation of the mobile network standard [9].…”

Section: Related Workmentioning

confidence: 99%

Wavelet-Based Filtration Procedure for Denoising the Predicted CO2 Waveforms in Smart Home within the Internet of Things

Vaňuš

Fiedorova

Kubíček

et al. 2020

Sensors

View full text Add to dashboard Cite

The operating cost minimization of smart homes can be achieved with the optimization of the management of the building’s technical functions by determination of the current occupancy status of the individual monitored spaces of a smart home. To respect the privacy of the smart home residents, indirect methods (without using cameras and microphones) are possible for occupancy recognition of space in smart homes. This article describes a newly proposed indirect method to increase the accuracy of the occupancy recognition of monitored spaces of smart homes. The proposed procedure uses the prediction of the course of CO2 concentration from operationally measured quantities (temperature indoor and relative humidity indoor) using artificial neural networks with a multilayer perceptron algorithm. The mathematical wavelet transformation method is used for additive noise canceling from the predicted course of the CO2 concentration signal with an objective increase accuracy of the prediction. The calculated accuracy of CO2 concentration waveform prediction in the additive noise-canceling application was higher than 98% in selected experiments.

show abstract

Section: Related Workmentioning

confidence: 99%

Wavelet-Based Filtration Procedure for Denoising the Predicted CO2 Waveforms in Smart Home within the Internet of Things

Vaňuš

Fiedorova

Kubíček

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Taking classification algorithms as an example, text data is often semi-structured or unstructured [13], then the structured text feature dimension can be reach thousands of dimensions, which not only leads to high resource consumption in the classification algorithms, but also leads to extract inaccurate information from the document, resulting in poor classification performance [16,44,48]. Therefore, the most critical element in improving the accuracy and efficiency of text classification is dimensionality reduction [28,37,38,40].…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Text Feature Learning via Deep Variational Auto-encoder

Liu

Xie

Chen

2020

ITC

View full text Add to dashboard Cite

Dimensionality reduction plays an important role in the data processing of machine learning and data mining, which makes the processing of high-dimensional data more efficient. Dimensionality reduction can extract the low-dimensional feature representation of high-dimensional data, and an effective dimensionality reduction method can not only extract most of the useful information of the original data, but also realize the function of removing useless noise. The dimensionality reduction methods can be applied to all types of data, especially image data. Although the supervised learning method has achieved good results in the application of dimensionality reduction, its performance depends on the number of labeled training samples. With the growing of information from internet, marking the data requires more resources and is more difficult. Therefore, using unsupervised learning to learn the feature of data has extremely important research value. In this paper, an unsupervised multilayered variational auto-encoder model is studied in the text data, so that the high-dimensional feature to the low-dimensional feature becomes efficient and the low-dimensional feature can retain mainly information as much as possible. Low-dimensional feature obtained by different dimensionality reduction methods are used to compare with the dimensionality reduction results of variational auto-encoder (VAE), and the method can be significantly improved over other comparison methods.

show abstract

“…Extracting key information from a photo entered into the system and returning them to a specialist of the domain is quite a difficult task, because the system of information extraction should know what to look for, how to search, as well as remove unwanted elements in the image. For that purpose, the system requires an artificial intelligence, like the use of neural networks and intelligent things [37,38].…”

Section: Introductionmentioning

confidence: 99%

Neural Network-based System for Automatic Passport Stamp Classification

Zaaboub¹,

Tlig²,

Sayadi³

et al. 2020

ITC

View full text Add to dashboard Cite

The international tourism growth forces governments to make a big effort to improve the security of national borders. The compulsory passport stamping is used in guaranteeing the safekeeping of the entry point of the border. For each passenger, the border police must check the existence of exit stamps and/or the entry stamps of the country that the passenger visits, in all the pages of his passport. However, the systematic control considerably slows the operations of the border police. Protecting the borders from illegal immigrants and simplifying border checkpoints for law-abiding citizens and visitors is a delicate compromise. The purpose of this paper is to perform a flexible and scalable system that ensures faster, safer and more efficient stamp controlling. An automatic system of stamp extraction for travel documents is proposed. We incorporate several methods from the field of artificial intelligence, image processing and pattern recognition. At first, texture feature extraction is performed in order to find potential stamps. Next, image segmentation aimed at detecting objects of specific textures are employed. Then, isolated objects are extracted and classified using multi-layer perceptron artificial network. Promising results are obtained in terms of accuracy, with a maximum average of 0.945 among all the images, improving the performance of MLP neural network in all cases.

show abstract

Analysis of Skin Marks Through the Use of Intelligent Things

Cited by 41 publications

References 24 publications

Wavelet-Based Filtration Procedure for Denoising the Predicted CO2 Waveforms in Smart Home within the Internet of Things

Wavelet-Based Filtration Procedure for Denoising the Predicted CO2 Waveforms in Smart Home within the Internet of Things

Unsupervised Text Feature Learning via Deep Variational Auto-encoder

Neural Network-based System for Automatic Passport Stamp Classification

Contact Info

Product

Resources

About