scholarly journals Visible Light Spectrum Extraction from Diffraction Images by Deconvolution and the Cepstrum

2021 ◽  
Vol 7 (9) ◽  
pp. 166
Author(s):  
Mikko E. Toivonen  ◽  
Topi Talvitie  ◽  
Chang Rajani  ◽  
Arto Klami 
Keyword(s):  
Visible Light ◽  
Low Cost ◽  
Ground Truth ◽  
Testing Procedure ◽  
Machine Learning Algorithms ◽  
Light Spectrum ◽  
Alternative Processing ◽  
Lighting Conditions ◽  
Degree Of Confidence ◽  
High Degree

Accurate color determination in variable lighting conditions is difficult and requires special devices. We considered the task of extracting the visible light spectrum using ordinary camera sensors, to facilitate low-cost color measurements using consumer equipment. The approach uses a diffractive element attached to a standard camera and a computational algorithm for forming the light spectrum from the resulting diffraction images. We present two machine learning algorithms for this task, based on alternative processing pipelines using deconvolution and cepstrum operations, respectively. The proposed methods were trained and evaluated on diffraction images collected using three cameras and three illuminants to demonstrate the generality of the approach, measuring the quality by comparing the recovered spectra against ground truth measurements collected using a hyperspectral camera. We show that the proposed methods are able to reconstruct the spectrum, and, consequently, the color, with fairly good accuracy in all conditions, but the exact accuracy depends on the specific camera and lighting conditions. The testing procedure followed in our experiments suggests a high degree of confidence in the generalizability of our results; the method works well even for a new illuminant not seen in the development phase.

scholarly journals DESIGN OF A LI-FI TRANSCEIVER .

2020 ◽  
Vol 9 (12) ◽  
pp. 21-37
Keyword(s):  
Visible Light ◽  
Low Cost ◽  
New Technology ◽  
Research Work ◽  
Design Tool ◽  
Spectrum Efficiency ◽  
Digital Data ◽  
Light Spectrum ◽  
Video Signals ◽  
User Demand

The latest uproar in this era is about a technology termed as Light Fidelity or more commonly known as Li-Fi. There are currently two trends being seen: First, the extension or enrichment of wireless services and other being in-creased in user demand for these services, but the available RF spectrum for usage is very limited. So the new technology of Li-Fi came into picture, which uses visible light as a source of communication. Li-Fi is the most recent de-velopment which is resourceful. In this technology, LEDs are used to transmit data in the visible light spectrum. This technology can be compared with that of Wi-Fi and offers advantages like increased accessible spectrum, efficiency, security, low latency and much higher speed. This research paper aims at de-signing a Li-Fi transceiver using Arduino that is able to transmit digital data. The hardware has been designed using Eagle CAD (version 7.1.0) tool and Proteus design tool (version 8). The software coding is done by using Java (version 8). Successful transmission and reception of text, image and video signals is carried out on the transceiver. Hence this research work gives an innovative way of designing a transceiver which works by using off the shelf low cost components and using visible light spectrum.

ILI Performance Verification and Assessment Using Statistical Hypothesis Testing

2006 ◽  
Author(s):  
Guy Desjardins ◽  
Mike Reed ◽  
Randy Nickle
Keyword(s):  
Hypothesis Testing ◽  
Testing Procedure ◽  
Statistical Hypothesis ◽  
Statistical Hypothesis Testing ◽  
Performance Verification ◽  
Certainty Level ◽  
Hypothesis Testing Procedure ◽  
Degree Of Confidence ◽  
High Degree

Following an inspection, API 1163 recommends that operators verify the accuracy of the ILI measurements. This paper examines the performance of an ILI tool from two separate perspectives. The first question is whether the ILI tool’s performance meets expectations and contractual requirements. The second question is to what level of accuracy the ILI tool can be relied upon for making integrity related decisions. This paper develops a method of determining the number of excavations and the number of anomalies to be investigated in the field to verify and assess the accuracy of the ILI reported depths. The verification and assessment of the ILI accuracy are two separate questions, and each is addressed as a hypothesis testing procedure. The first hypothesis states that the tool meets expected and contractual standards. That hypothesis is tested against the excavation data. Its acceptance means that the excavation data is consistent with the expected accuracy of the tool, but it does not specifically verify that accuracy. A second hypothesis states that the tool fails to meet some level accuracy as stated by a tolerance and certainty level. That hypothesis is constructed so that when it is tested against the excavation data it is rejected. Its rejection means that the tool exceeds the stated level of accuracy with a high degree of confidence.

Challenges and Opportunities of VLC Application in Intelligent Transportation Systems

2021 ◽  
pp. 1051-1064
Author(s):  
Aleksandra Kostic-Ljubisavljevic ◽  
Branka Mikavica
Keyword(s):  
Visible Light ◽  
Intelligent Transportation Systems ◽  
Early Stage ◽  
Low Cost ◽  
Large Data ◽  
Visible Light Communication ◽  
Intelligent Transportation ◽  
Transportation Systems ◽  
Light Spectrum ◽  
Challenges And Opportunities

With the development of light emitting diodes (LEDs), the communication in visible light spectrum, visible light communication (VLC), becomes an alternative to the existing wireless technologies. Integration of VLC systems with intelligent transportation systems (ITS) can significantly improve many aspects of transportation and traffic. The use of unlicensed bandwidth and wider implementation of VLC LED lighting, both in infrastructure and in vehicles, provide an energy-efficient data transmission with sufficiently large data rates at low cost. The application of VLC systems is still at an early stage of the development. However, due to numerous advantages, the wider adoption of VLC systems is expected in near future. This chapter presents an analysis of the possibilities of VLC application in ITS scenarios. Main characteristics of VLC in ITS in terms of architecture, modulation and standardization are addressed. Some challenges and open issues are also emphasized.

scholarly journals Passive Visible Light Sensing of Retroreflective Foils on a Moving Object for Indoor Application

Proceedings ◽  
2021 ◽  
Vol 56 (1) ◽  
pp. 42
Author(s):  
Andreas Peter Weiss ◽  
Franz-Peter Wenzl
Keyword(s):  
Visible Light ◽  
Low Cost ◽  
Moving Object ◽  
Light Spectrum ◽  
Active Sensors ◽  
Light Sensing ◽  
Novel Approach ◽  
Low Complex ◽  
Processing Device ◽  
Training Effort

We present a novel approach to perform passive visible light sensing of retroreflective foils mounted on a moving object by utilizing low-cost hardware combined with a self-developed, low complex software algorithm with minimal training effort for successful classification. Therewith, we show the feasibility of utilizing the visible light spectrum not only for illumination, but also to perform sensing tasks, which consequently will lead to less energy consumption, no need for active sensors on the moving object, and finally no necessity of wireless radio frequency communication between the object and the processing device.

Senior Living - Lighting, Circadian Rhythm and Dementia I

2019 ◽  
pp. 4-8
Author(s):  
Tadej Glažar ◽  
Marjeta Zupancic ◽  
Samo Kralj ◽  
Robert Peternelj
Keyword(s):  
The Elderly ◽  
Living Environment ◽  
Elderly Persons ◽  
Light Spectrum ◽  
Average Life Expectancy ◽  
The Real Estate ◽  
Lighting Conditions ◽  
Light Levels ◽  
Joint Fracture ◽  
Lease Contracts

The Real Estate Fund of Pension and Disability Insurance (Nepremicninski Sklad) in Slovenia, founded in1997 is the owner of 3255 properties in 116 locations throughout the country and is intended for solving housing issues of pensioners of 65 years or older and other elderly persons who are allowed independently to live. The lease contracts are concluded for an indefinite period of time. The aim and vision of the Fund is to improve the quality of life for the elderly tenants by adapting the living environment, the flats and surroundings according to the physical needs of aging tenants. Homes for seniors often have low light levels and poor light spectrum caused by fluorescent or incandescent lighting. Demographic changes in most European countries show rising average life expectancy which means that the number of people with weak visual capacity or visual impairment is increasing. Equally the risks of injuries due to poor lighting conditions are increasing, e.g. missing a step resulting in a hip joint fracture. Better lighting conditions are of critical importance for aging population, as stated also in the recently published CIE227:2017. To facilitate safe environment for the elderly, the Fund in 2013 initiated a lighting research study that should provide facts and evidence for a lighting standard for their own premises.

Drug Target Group Prediction with Multiple Drug Networks

2020 ◽  
Vol 23 (4) ◽  
pp. 274-284 ◽  
Author(s):  
Jingang Che ◽  
Lei Chen ◽  
Zi-Han Guo ◽  
Shuaiqun Wang ◽  
Aorigele
Keyword(s):  
Drug Target ◽  
Low Cost ◽  
Machine Learning Algorithms ◽  
Classification Model ◽  
Support Vector ◽  
Multiple Drug ◽  
Property A ◽  
Multiple Networks ◽  
Proposed Model ◽  
The One

Background: Identification of drug-target interaction is essential in drug discovery. It is beneficial to predict unexpected therapeutic or adverse side effects of drugs. To date, several computational methods have been proposed to predict drug-target interactions because they are prompt and low-cost compared with traditional wet experiments. Methods: In this study, we investigated this problem in a different way. According to KEGG, drugs were classified into several groups based on their target proteins. A multi-label classification model was presented to assign drugs into correct target groups. To make full use of the known drug properties, five networks were constructed, each of which represented drug associations in one property. A powerful network embedding method, Mashup, was adopted to extract drug features from above-mentioned networks, based on which several machine learning algorithms, including RAndom k-labELsets (RAKEL) algorithm, Label Powerset (LP) algorithm and Support Vector Machine (SVM), were used to build the classification model. Results and Conclusion: Tenfold cross-validation yielded the accuracy of 0.839, exact match of 0.816 and hamming loss of 0.037, indicating good performance of the model. The contribution of each network was also analyzed. Furthermore, the network model with multiple networks was found to be superior to the one with a single network and classic model, indicating the superiority of the proposed model.

scholarly journals Fig Plant Segmentation from Aerial Images Using a Deep Convolutional Encoder-Decoder Network

2019 ◽  
Vol 11 (10) ◽  
pp. 1157 ◽  
Author(s):  
Jorge Fuentes-Pacheco ◽  
Juan Torres-Olivares ◽  
Edgar Roman-Rangel ◽  
Salvador Cervantes ◽  
Porfirio Juarez-Lopez ◽  
...  
Keyword(s):  
Precision Agriculture ◽  
Image Data ◽  
Ground Truth ◽  
Aerial Images ◽  
Aerial Image ◽  
Data Set ◽  
Visual Appearance ◽  
Aerial Robots ◽  
Lighting Conditions ◽  
Convolutional Encoder

Crop segmentation is an important task in Precision Agriculture, where the use of aerial robots with an on-board camera has contributed to the development of new solution alternatives. We address the problem of fig plant segmentation in top-view RGB (Red-Green-Blue) images of a crop grown under open-field difficult circumstances of complex lighting conditions and non-ideal crop maintenance practices defined by local farmers. We present a Convolutional Neural Network (CNN) with an encoder-decoder architecture that classifies each pixel as crop or non-crop using only raw colour images as input. Our approach achieves a mean accuracy of 93.85% despite the complexity of the background and a highly variable visual appearance of the leaves. We make available our CNN code to the research community, as well as the aerial image data set and a hand-made ground truth segmentation with pixel precision to facilitate the comparison among different algorithms.

Solution Processed Sb2S3-based Photocathode with Enhanced Photocatalytic Performance via Constructing Ultrathin TiO2 Overlayer and Noble Metal Modification

2021 ◽  
Author(s):  
Yanwen Wang ◽  
Rong Liang ◽  
Chao Qin ◽  
Lei Ren ◽  
Zhizhen Ye ◽  
...  
Keyword(s):  
Visible Light ◽  
Noble Metal ◽  
Photocatalytic Performance ◽  
Low Cost ◽  
Light Response ◽  
Solution Processed ◽  
Antimony Sulfide ◽  
Visible Light Response ◽  
Absorbing Material

Antimony sulfide (Sb2S3) is a light absorbing material with strong visible light response, which is suitable for efficient and low-cost photoelectrodes. Nano-structured films have unique advantages in constructing photoelectrodes due...

scholarly journals Highly Compact Through-Wire Microstrip to Empty Substrate Integrated Coaxial Line Transition

2021 ◽  
Vol 11 (15) ◽  
pp. 6885
Author(s):  
Marcos D. Fernandez ◽  
José A. Ballesteros ◽  
Angel Belenguer
Keyword(s):  
Printed Circuit Board ◽  
Low Cost ◽  
Coaxial Line ◽  
Circuit Board ◽  
Central Layer ◽  
Printed Circuit ◽  
Integrated Technology ◽  
Low Profile ◽  
The Many ◽  
High Degree

Empty substrate integrated coaxial line (ESICL) technology preserves the many advantages of the substrate integrated technology waveguides, such as low cost, low profile, or integration in a printed circuit board (PCB); in addition, ESICL is non-dispersive and has low radiation. To date, only two transitions have been proposed in the literature that connect the ESICL to classical planar lines such as grounded coplanar and microstrip. In both transitions, the feeding planar lines and the ESICL are built in the same substrate layer and they are based on transformed structures in the planar line, which must be in the central layer of the ESICL. These transitions also combine a lot of metallized and non-metallized parts, which increases the complexity of the manufacturing process. In this work, a new through-wire microstrip-to-ESICL transition is proposed. The feeding lines and the ESICL are implemented in different layers, so that the height of the ESICL can be independently chosen. In addition, it is a highly compact transition that does not require a transformer and can be freely rotated in its plane. This simplicity provides a high degree of versatility in the design phase, where there are only four variables that control the performance of the transition.

scholarly journals Classification of unlabeled online media

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Sakthi Kumar Arul Prakash ◽  
Conrad Tucker
Keyword(s):  
Social Media ◽  
Real World ◽  
Graphical Model ◽  
Ground Truth ◽  
Classification Problem ◽  
Machine Learning Algorithms ◽  
Social Media Networks ◽  
Online Social Media ◽  
Wide Range

AbstractThis work investigates the ability to classify misinformation in online social media networks in a manner that avoids the need for ground truth labels. Rather than approach the classification problem as a task for humans or machine learning algorithms, this work leverages user–user and user–media (i.e.,media likes) interactions to infer the type of information (fake vs. authentic) being spread, without needing to know the actual details of the information itself. To study the inception and evolution of user–user and user–media interactions over time, we create an experimental platform that mimics the functionality of real-world social media networks. We develop a graphical model that considers the evolution of this network topology to model the uncertainty (entropy) propagation when fake and authentic media disseminates across the network. The creation of a real-world social media network enables a wide range of hypotheses to be tested pertaining to users, their interactions with other users, and with media content. The discovery that the entropy of user–user and user–media interactions approximate fake and authentic media likes, enables us to classify fake media in an unsupervised learning manner.

Sign in / Sign up

Export Citation Format

Share Document