Full color generation with Fano-type resonant HfO2 nanopillars designed by a deep-learning approach

Here, for the first time to our knowledge, a Fano resonance metasurface made of HfO2 is experimentally demonstrated to generate a wide range of colors. We use a novel deep-learning technique to design and optimize the metasurface.

Download Full-text

RSSI-Based for Device-Free Localization Using Deep Learning Technique

Smart Cities ◽

10.3390/smartcities3020024 ◽

2020 ◽

Vol 3 (2) ◽

pp. 444-455

Author(s):

Abdul Syafiq Abdull Sukor ◽

Latifah Munirah Kamarudin ◽

Ammar Zakaria ◽

Norasmadi Abdul Rahim ◽

Sukhairi Sudin ◽

...

Keyword(s):

Deep Learning ◽

Machine Learning Algorithms ◽

Learning Approach ◽

Statistical Features ◽

Received Signal Strength Indicator ◽

Privacy Concerns ◽

Physical Discomfort ◽

Learning Technique ◽

Device Free ◽

The Internet Of Things

Device-free localization (DFL) has become a hot topic in the paradigm of the Internet of Things. Traditional localization methods are focused on locating users with attached wearable devices. This involves privacy concerns and physical discomfort especially to users that need to wear and activate those devices daily. DFL makes use of the received signal strength indicator (RSSI) to characterize the user’s location based on their influence on wireless signals. Existing work utilizes statistical features extracted from wireless signals. However, some features may not perform well in different environments. They need to be manually designed for a specific application. Thus, data processing is an important step towards producing robust input data for the classification process. This paper presents experimental procedures using the deep learning approach to automatically learn discriminative features and classify the user’s location. Extensive experiments performed in an indoor laboratory environment demonstrate that the approach can achieve 84.2% accuracy compared to the other basic machine learning algorithms.

Download Full-text

Virtual Healthcare Center for COVID-19 Patient Detection Based on Artificial Intelligence Approaches

Canadian Journal of Infectious Diseases and Medical Microbiology ◽

10.1155/2022/6786203 ◽

2022 ◽

Vol 2022 ◽

pp. 1-15

Author(s):

Seifeddine Messaoud ◽

Soulef Bouaafia ◽

Amna Maraoui ◽

Lazhar Khriji ◽

Ahmed Chiheb Ammari ◽

...

Keyword(s):

Deep Learning ◽

Health Resources ◽

Disease Diagnosis ◽

Public Health Issue ◽

X Ray ◽

Poor Countries ◽

Healthcare Center ◽

Learning Techniques ◽

Learning Technique ◽

First Time

At the end of 2019, the infectious coronavirus disease (COVID-19) was reported for the first time in Wuhan, and, since then, it has become a public health issue in China and even worldwide. This pandemic has devastating effects on societies and economies around the world, and poor countries and continents are likely to face particularly serious and long-lasting damage, which could lead to large epidemic outbreaks because of the lack of financial and health resources. The increasing number of COVID-19 tests gives more information about the epidemic spread, and this can help contain the spread to avoid more infection. As COVID-19 keeps spreading, medical products, especially those needed to perform blood tests, will become scarce as a result of the high demand and insufficient supply and logistical means. However, technological tests based on deep learning techniques and medical images could be useful in fighting this pandemic. In this perspective, we propose a COVID-19 disease diagnosis (CDD) tool that implements a deep learning technique to provide automatic symptoms checking and COVID-19 detection. Our CDD scheme implements two main steps. First, the patient’s symptoms are checked, and the infection probability is predicted. Then, based on the infection probability, the patient’s lungs will be diagnosed by an automatic analysis of X-ray or computerized tomography (CT) images, and the presence of the infection will be accordingly confirmed or not. The numerical results prove the efficiency of the proposed scheme by achieving an accuracy value over 90% compared with the other schemes.

Download Full-text

Deep PPG: Large-Scale Heart Rate Estimation with Convolutional Neural Networks

Sensors ◽

10.3390/s19143079 ◽

2019 ◽

Vol 19 (14) ◽

pp. 3079 ◽

Cited By ~ 16

Author(s):

Attila Reiss ◽

Ina Indlekofer ◽

Philip Schmidt ◽

Kristof Van Laerhoven

Keyword(s):

Heart Rate ◽

Deep Learning ◽

Large Scale ◽

Learning Approach ◽

Frequency Spectra ◽

Time Frequency ◽

Rate Estimation ◽

Wide Range ◽

Public Datasets ◽

Heart Rate Estimation

Photoplethysmography (PPG)-based continuous heart rate monitoring is essential in a number of domains, e.g., for healthcare or fitness applications. Recently, methods based on time-frequency spectra emerged to address the challenges of motion artefact compensation. However, existing approaches are highly parametrised and optimised for specific scenarios of small, public datasets. We address this fragmentation by contributing research into the robustness and generalisation capabilities of PPG-based heart rate estimation approaches. First, we introduce a novel large-scale dataset (called PPG-DaLiA), including a wide range of activities performed under close to real-life conditions. Second, we extend a state-of-the-art algorithm, significantly improving its performance on several datasets. Third, we introduce deep learning to this domain, and investigate various convolutional neural network architectures. Our end-to-end learning approach takes the time-frequency spectra of synchronised PPG- and accelerometer-signals as input, and provides the estimated heart rate as output. Finally, we compare the novel deep learning approach to classical methods, performing evaluation on four public datasets. We show that on large datasets the deep learning model significantly outperforms other methods: The mean absolute error could be reduced by 31 % on the new dataset PPG-DaLiA, and by 21 % on the dataset WESAD.

Download Full-text

Machine Learning Predictions of Transition Probabilities in Atomic Spectra

Atoms ◽

10.3390/atoms9010002 ◽

2021 ◽

Vol 9 (1) ◽

pp. 2

Author(s):

Joshua J. Michalenko ◽

Christopher M. Murzyn ◽

Joshua D. Zollweg ◽

Lydia Wermer ◽

Alan J. Van Omen ◽

...

Keyword(s):

Machine Learning ◽

Deep Learning ◽

Transition Probabilities ◽

Theoretical Calculations ◽

Model Performance ◽

Theoretical Models ◽

Order Effects ◽

Learning Approach ◽

Atomic Spectra ◽

Wide Range

Forward modeling of optical spectra with absolute radiometric intensities requires knowledge of the individual transition probabilities for every transition in the spectrum. In many cases, these transition probabilities, or Einstein A-coefficients, quickly become practically impossible to obtain through either theoretical or experimental methods. Complicated electronic orbitals with higher order effects will reduce the accuracy of theoretical models. Experimental measurements can be prohibitively expensive and are rarely comprehensive due to physical constraints and sheer volume of required measurements. Due to these limitations, spectral predictions for many element transitions are not attainable. In this work, we investigate the efficacy of using machine learning models, specifically fully connected neural networks (FCNN), to predict Einstein A-coefficients using data from the NIST Atomic Spectra Database. For simple elements where closed form quantum calculations are possible, the data-driven modeling workflow performs well but can still have lower precision than theoretical calculations. For more complicated nuclei, deep learning emerged more comparable to theoretical predictions, such as Hartree–Fock. Unlike experiment or theory, the deep learning approach scales favorably with the number of transitions in a spectrum, especially if the transition probabilities are distributed across a wide range of values. It is also capable of being trained on both theoretical and experimental values simultaneously. In addition, the model performance improves when training on multiple elements prior to testing. The scalability of the machine learning approach makes it a potentially promising technique for estimating transition probabilities in previously inaccessible regions of the spectral and thermal domains on a significantly reduced timeline.

Download Full-text

Real Time Object Recognition and Classification using Deep Learning

International Journal of Scientific Research in Computer Science Engineering and Information Technology ◽

10.32628/cseit195262 ◽

2019 ◽

pp. 355-359

Author(s):

Kiruthiga N ◽

Divya E ◽

Haripriya R ◽

Haripriya V.

Keyword(s):

Deep Learning ◽

Object Recognition ◽

Object Detection ◽

Real Time ◽

Visually Impaired ◽

Detection Algorithm ◽

Indoor Environments ◽

Wide Range ◽

Impaired Person ◽

First Time

Navigation in indoor environments is highly challenging for visually impaired person, particularly in spaces visited for the first time. Various solutions have been proposed to deal with this challenge. In this project consider as the real time object Recognition and classification using deep learning algorithms. Object detection mainly deals with identification of real time objects such as people, animals, and objects. Object detection algorithm uses a wide range of image processing applications for extracting the object's desired portion. This enables one to identify the objects and calculate the accuracy of the object and deliver through voice. Using this information, the system determines the user's trajectory and can locate possible obstacles in that route.

Download Full-text

Inter-database validation of a deep learning approach for automatic sleep scoring

PLoS ONE ◽

10.1371/journal.pone.0256111 ◽

2021 ◽

Vol 16 (8) ◽

pp. e0256111

Author(s):

Diego Alvarez-Estevez ◽

Roselyne M. Rijsman

Keyword(s):

Deep Learning ◽

Network Architecture ◽

Data Locality ◽

Learning Approach ◽

Local Models ◽

Sleep Staging ◽

Patient Privacy ◽

Kappa Score ◽

Wide Range ◽

Scalable Design

Study objectives Development of inter-database generalizable sleep staging algorithms represents a challenge due to increased data variability across different datasets. Sharing data between different centers is also a problem due to potential restrictions due to patient privacy protection. In this work, we describe a new deep learning approach for automatic sleep staging, and address its generalization capabilities on a wide range of public sleep staging databases. We also examine the suitability of a novel approach that uses an ensemble of individual local models and evaluate its impact on the resulting inter-database generalization performance. Methods A general deep learning network architecture for automatic sleep staging is presented. Different preprocessing and architectural variant options are tested. The resulting prediction capabilities are evaluated and compared on a heterogeneous collection of six public sleep staging datasets. Validation is carried out in the context of independent local and external dataset generalization scenarios. Results Best results were achieved using the CNN_LSTM_5 neural network variant. Average prediction capabilities on independent local testing sets achieved 0.80 kappa score. When individual local models predict data from external datasets, average kappa score decreases to 0.54. Using the proposed ensemble-based approach, average kappa performance on the external dataset prediction scenario increases to 0.62. To our knowledge this is the largest study by the number of datasets so far on validating the generalization capabilities of an automatic sleep staging algorithm using external databases. Conclusions Validation results show good general performance of our method, as compared with the expected levels of human agreement, as well as to state-of-the-art automatic sleep staging methods. The proposed ensemble-based approach enables flexible and scalable design, allowing dynamic integration of local models into the final ensemble, preserving data locality, and increasing generalization capabilities of the resulting system at the same time.

Download Full-text

Particle Mobility Analysis Using Deep Learning and the Moment Scaling Spectrum

Scientific Reports ◽

10.1038/s41598-019-53663-8 ◽

2019 ◽

Vol 9 (1) ◽

Cited By ~ 7

Author(s):

Marloes Arts ◽

Ihor Smal ◽

Maarten W. Paul ◽

Claire Wyman ◽

Erik Meijering

Keyword(s):

Deep Learning ◽

Time Lapse ◽

Parameter Extraction ◽

Mobility Analysis ◽

Biologically Relevant ◽

Particle Mobility ◽

Wide Range ◽

Novel Method ◽

The Moment ◽

First Time

AbstractQuantitative analysis of dynamic processes in living cells using time-lapse microscopy requires not only accurate tracking of every particle in the images, but also reliable extraction of biologically relevant parameters from the resulting trajectories. Whereas many methods exist to perform the tracking task, there is still a lack of robust solutions for subsequent parameter extraction and analysis. Here a novel method is presented to address this need. It uses for the first time a deep learning approach to segment single particle trajectories into consistent tracklets (trajectory segments that exhibit one type of motion) and then performs moment scaling spectrum analysis of the tracklets to estimate the number of mobility classes and their associated parameters, providing rich fundamental knowledge about the behavior of the particles under study. Experiments on in-house datasets as well as publicly available particle tracking data for a wide range of proteins with different dynamic behavior demonstrate the broad applicability of the method.

Download Full-text

Nuclear Morphology Optimized Deep Hybrid Learning (NUMODRIL): A novel architecture for accurate diagnosis/prognosis of Ovarian Cancer

10.1101/2020.11.23.393660 ◽

2020 ◽

Author(s):

Duhita Sengupta ◽

Sk Nishan Ali ◽

Aditya Bhattacharya ◽

Joy Mustafi ◽

Asima Mukhopadhyay ◽

...

Keyword(s):

Ovarian Cancer ◽

Deep Learning ◽

Cancer Cells ◽

Hybrid Learning ◽

Nuclear Morphology ◽

Learning Approach ◽

Diagnosis And Prognosis ◽

Learning Techniques ◽

Wide Range ◽

Cancer Tissues

AbstractNuclear morphological features are potent determining factors for clinical diagnostic approaches adopted by pathologists to analyse the malignant potential of cancer cells. Considering the structural alteration of nucleus in cancer cells, various groups have developed machine learning techniques based on variation in nuclear morphometric information like nuclear shape, size, nucleus-cytoplasm ratio and various non-parametric methods like deep learning have also been tested for analysing immunohistochemistry images of tissue samples for diagnosing various cancers. Our aim is to study the morphometric distribution of nuclear lamin proteins as a specific parameter in ovarian cancer tissues. Besides being the principal mechanical component of the nucleus, lamins also present a platform for binding of proteins and chromatin thereby serving a wide range of nuclear functions like maintenance of genome stability, chromatin regulation. Altered expression of lamins in different subtypes of cancer is now evident from data across the world. It has already been elucidated that in ovarian cancer, extent of alteration in nuclear shape and morphology can determine degree of genetic changes and thus can be utilized to predict the outcome of low to high form of serous carcinoma. In this work, we have performed exhaustive imaging of ovarian cancer versus normal tissue and introduced a novel Deep Hybrid Learning approach on the basis of the distribution of lamin proteins. Although developed with ovarian cancer datasets in view, this architecture would be of immense importance in accurate and fast diagnosis and prognosis of all types of cancer associated with lamin induced morphological changes and would perform across small/medium to large datasets with equal efficiency.Significance StatementWe have developed a novel Deep Hybrid Learning approach based on nuclear morphology to classify normal and ovarian cancer tissues with highest possible accuracy and speed. Ovarian cancer cells can be easily distinguished from their enlarged nuclear morphology as is evident from lamin A & B distribution pattern. This is the first report to invoke specific nuclear markers like lamin A & B instead of classical haematoxylin-eosin staining in an effort to build parametric datasets. Our approach has been shown to outperform the existing deep learning techniques in training and validation of datasets over a wide range. Therefore this method could be used as a robust model to predict malignant transformations of benign nuclei and thus be implemented in the diagnosis and prognosis of ovarian cancer in future. Most importantly, this method can be perceived as a generalized approach in the diagnosis for all types of cancer.

Download Full-text

REAL TIME OBJECT DETECTION USING YOLO ALGORITHM

International Journal of Computer Science and Mobile Computing ◽

10.47760/ijcsmc.2021.v10i07.009 ◽

2021 ◽

Vol 10 (7) ◽

pp. 61-67

Author(s):

Bobburi Taralathasri ◽

Dammati Vidya Sri ◽

Gadidammalla Narendra Kumar ◽

Annam Subbarao ◽

Palli R Krishna Prasad

Keyword(s):

Computer Vision ◽

Deep Learning ◽

Object Detection ◽

Detection System ◽

Image Data ◽

Image Detection ◽

The Core ◽

Wide Range ◽

Driverless Cars ◽

Learning Technique

The major and wide range applications like Driverless cars, robots, Image surveillance has become famous in the Computer vision .Computer vision is the core in all those applications which is responsible for the image detection and it became more popular worldwide. Object Detection System using Deep Learning Technique” detects objects efficiently based on YOLO algorithm and applies the algorithm on image data to detect objects.

Download Full-text