Feasibility Study of Visual Computing and Machine Learning Application for Textile Material Sorting

2021 ◽  
pp. 243-267
Author(s):  
Siu Cheung Ho ◽  
Jiannong Cao
Keyword(s):  
Machine Learning ◽  
Near Infrared ◽  
Identification System ◽  
Textile Fibre ◽  
Recycling Process ◽  
Textile Waste ◽  
Textile Materials ◽  
Waste Reuse ◽  
Visual Computing ◽  
Visual Technology

This project aims to study the feasibility of visual computing (VC) and machine learning (ML) method applied in the textile recycle industry for efficiently manages the post-consumer textile waste. It includes an image-based VC technology for supporting textile waste reuse and resale, and a material identification system for sorting textile materials by using near infrared (NIR)/hyperspectral spectroscopy technology to support efficiently recycling to reuse the textile fibre will be evaluated. The process involved collecting and validating reference samples and applying ML technique to auto recognize the garment type and features applying visual technology; afterward, the sorted garments would be measured and pre-treated by NIR/hyperspectral spectrum and building up the parameters for spectral patterns calculation for recycling process recover the fibre. The main part of the study is to proof of the concept for using VC and ML method for identifying the textile fibre in the recycling process.

scholarly journals Hyperspectral imaging for textile sorting in the visible–near infrared range

2019 ◽  
Author(s):  
Carolina Blanch-Perez-del-Notario ◽  
Wouter Saeys ◽  
Andy Lambrechts
Keyword(s):  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Hierarchical Classification ◽  
Infrared Range ◽  
Chemical Recycling ◽  
Textile Waste ◽  
Textile Materials ◽  
Material Discrimination ◽  
Sample Set ◽  
Near Infrared Range

Recycling of textile materials is becoming important due to the increasing amount of textile waste and its large environmental impact. The Resyntex project aims at dealing with this textile waste by enabling its chemical recycling. To do so, pure textile materials and blends need to be sorted first. In this paper we evaluate the suitability of hyperspectral imaging for pure and blend textile sorting. We also test the discrimination capacity between denim and non-denim textile, since this is required prior to the de-colouration processes. For this purpose, we use a line-scan sensor in the 450–950 nm range, since its cost, compactness and speed characteristics make it suitable for industrial deployment. To deal with the strong colour interference of the textile a hierarchical classification approach is proposed. The results on the available sample set show promising discrimination potential for material discrimination as well as for denim versus non-denim detection.

scholarly journals Textile Recognition and Sorting for Recycling at an Automated Line Using Near Infrared Spectroscopy

Recycling ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 11
Author(s):  
Kirsti Cura ◽  
Niko Rintala ◽  
Taina Kamppuri ◽  
Eetta Saarimäki ◽  
Pirjo Heikkilä
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Automated Recognition ◽  
Textile Materials ◽  
Input Material ◽  
Adequate Quality ◽  
Automated Line

In order to add value to recycled textile material and to guarantee that the input material for recycling processes is of adequate quality, it is essential to be able to accurately recognise and sort items according to their material content. Therefore, there is a need for an economically viable and effective way to recognise and sort textile materials. Automated recognition and sorting lines provide a method for ensuring better quality of the fractions being recycled and thus enhance the availability of such fractions for recycling. The aim of this study was to deepen the understanding of NIR spectroscopy technology in the recognition of textile materials by studying the effects of structural fabric properties on the recognition. The identified properties of fabrics that led non-matching recognition were coating and finishing that lead different recognition of the material depending on the side facing the NIR analyser. In addition, very thin fabrics allowed NIRS to penetrate through the fabric and resulted in the non-matching recognition. Additionally, ageing was found to cause such chemical changes, especially in the spectra of cotton, that hampered the recognition.

scholarly journals Nanoprinted high-neuron-density optical linear perceptrons performing near-infrared inference on a CMOS chip

2021 ◽  
Vol 10 (1) ◽  
Author(s):  
Elena Goi ◽  
Xi Chen ◽  
Qiming Zhang ◽  
Benjamin P. Cumming ◽  
Steffen Schoenhardt ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Speed ◽  
Near Infrared ◽  
Single Layer ◽  
Infrared Region ◽  
Optical Devices ◽  
Medical Diagnostics ◽  
Oxide Semiconductor ◽  
Process Data ◽  
Neuron Density

AbstractOptical machine learning has emerged as an important research area that, by leveraging the advantages inherent to optical signals, such as parallelism and high speed, paves the way for a future where optical hardware can process data at the speed of light. In this work, we present such optical devices for data processing in the form of single-layer nanoscale holographic perceptrons trained to perform optical inference tasks. We experimentally show the functionality of these passive optical devices in the example of decryptors trained to perform optical inference of single or whole classes of keys through symmetric and asymmetric decryption. The decryptors, designed for operation in the near-infrared region, are nanoprinted on complementary metal-oxide–semiconductor chips by galvo-dithered two-photon nanolithography with axial nanostepping of 10 nm1,2, achieving a neuron density of >500 million neurons per square centimetre. This power-efficient commixture of machine learning and on-chip integration may have a transformative impact on optical decryption3, sensing4, medical diagnostics5 and computing6,7.

ANOMALY DETECTION IN VESSEL TRACKING – A BAYESIAN NETWORKS (BNs) APPROACH

2021 ◽  
Vol 157 (A3) ◽  
Author(s):  
D Handayani ◽  
W Sediono ◽  
A Shah
Keyword(s):  
Machine Learning ◽  
Bayesian Networks ◽  
Expert Knowledge ◽  
Machine Learning Techniques ◽  
Automatic Identification ◽  
Identification System ◽  
International Convention ◽  
Learning Techniques ◽  
Reporting Data ◽  
Vessel Anomaly

The paper describes the supervised method approach to identifying vessel anomaly behaviour. The vessel anomaly behaviour is determined by learning from self-reporting maritime systems based on the Automatic Identification System (AIS). The AIS is a real world vessel reporting data system, which has been recently made compulsory by the International Convention for the Safety of Life and Sea (SOLAS) for vessels over 300 gross tons and most commercial vessels such as cargo ships, passenger vessels, tankers, etc. In this paper, we describe the use of Bayesian networks (BNs) approach to identify the behaviour of the vessel of interest. The BNs is a machine learning technique based on probabilistic theory that represents a set of random variables and their conditional independencies via directed acyclic graph (DAG). Previous studies showed that the BNs have important advantages compared to other machine learning techniques. Among them are that expert knowledge can be included in the BNs model, and that humans can understand and interpret the BNs model more readily. This work proves that the BNs technique is applicable to the identification of vessel anomaly behaviour.

scholarly journals Machine learning enables discovery of DNA-carbon nanotube sensors for serotonin

2021 ◽  
Author(s):  
Payam Kelich ◽  
Sanghwa Jeong ◽  
Nicole Navarro ◽  
Jaquesta Adams ◽  
Xiaoqi Sun ◽  
...  
Keyword(s):  
Machine Learning ◽  
Carbon Nanotube ◽  
Dna Sequences ◽  
Regression Models ◽  
Near Infrared ◽  
Optical Response ◽  
Support Vector ◽  
Single Walled Carbon Nanotube ◽  
Nir Fluorescence ◽  
Selective Evolution

AbstractDNA-wrapped single walled carbon nanotube (SWNT) conjugates have remarkable optical properties leading to their use in biosensing and imaging applications. A critical limitation in the development of DNA-SWNT sensors is the current inability to predict unique DNA sequences that confer a strong analyte-specific optical response to these sensors. Here, near-infrared (nIR) fluorescence response datasets for ~100 DNA-SWNT conjugates, narrowed down by a selective evolution protocol starting from a pool of ~1010 unique DNA-SWNT candidates, are used to train machine learning (ML) models to predict new unique DNA sequences with strong optical response to neurotransmitter serotonin. First, classifier models based on convolutional neural networks (CNN) are trained on sequence features to classify DNA ligands as either high response or low response to serotonin. Second, support vector machine (SVM) regression models are trained to predict relative optical response values for DNA sequences. Finally, we demonstrate with validation experiments that integrating the predictions of ensembles of the highest quality CNN classifiers and SVM regression models leads to the best predictions of both high and low response sequences. With our ML approaches, we discovered five new DNA-SWNT sensors with higher fluorescence intensity response to serotonin than obtained previously. Overall, the explored ML approaches introduce an important new tool to predict useful DNA sequences, which can be used for discovery of new DNA-based sensors and nanobiotechnologies.

scholarly journals Use of modern methods of fibre surface modification to obtain the multifunctional properties of textile materials

2003 ◽  
Vol 57 (10) ◽  
pp. 491-499 ◽  
Author(s):  
Dragan Jocic ◽  
Petar Jovancic ◽  
Maja Radetic ◽  
Tatjana Topalovic ◽  
Zoran Petrovic
Keyword(s):  
Surface Modification ◽  
Surface Topography ◽  
Fibre Surface ◽  
Enzyme Treatment ◽  
Textile Fibre ◽  
Textile Materials ◽  
Chemical Surface ◽  
Angle Measurements ◽  
Physico Chemical ◽  
Physical And Chemical

The modern textile fibre treatments aim to obtain the required level of beneficial effect while attempting to confine the modification to the fibre surface. Recently, much attention has been focused on different physical methods of fibre surface modification, cold plasma treatment being considered as very useful. Moreover, there are efficient chemical methods available, such as peroxide, biopolymer and enzyme treatment. Some interesting combinations of these physical and chemical surface modification methods as means to modify fibre surface topography and thus controlling the surface-related properties of the fibre are presented in this paper. The properties obtained are discussed on the basis of the physico-chemical changes in the surface layer of the fibre, being assessed by wettability and contact angle measurements, as well as by FTIR-ATR and XPS analysis. The SEM and AFM technique are used to assess the changes in the fibre surface topography and to correlate these changes to the effectiveness, uniformity and severity of the textile fibre surface modification treatments.

Applying machine learning to satellite imagery and vessel-tracking data to detect chronic oil pollution from ships at sea and identify the polluters

2021 ◽  
Author(s):  
Jona Raphael ◽  
Ben Eggleston ◽  
Ryan Covington ◽  
Tatianna Evanisko ◽  
Sasha Bylsma ◽  
...  
Keyword(s):  
Machine Learning ◽  
Oil Spills ◽  
Oil Pollution ◽  
Satellite Image ◽  
Petroleum Products ◽  
Training Data ◽  
Automatic Identification ◽  
Identification System ◽  
Sar Imagery ◽  
Pollution Events

<p><strong>Operational oil discharges from ships</strong>, also known as “bilge dumping,” have been identified as a major source of petroleum products entering our oceans, cumulatively exceeding the largest oil spills, such as the Exxon Valdez and Deepwater Horizon spills, even when considered over short time spans. However, we still don’t have a good estimate of</p><ul><li>How much oil is being discharged;</li> <li>Where the discharge is happening;</li> <li>Who the responsible vessels are.</li> </ul><p>This makes it difficult to prevent and effectively respond to oil pollution that can damage our marine and coastal environments and economies that depend on them.</p><p> </p><p>In this presentation we will share SkyTruth’s recent work to address these gaps using machine learning tools to detect oil pollution events and identify the responsible vessels when possible. We use a convolutional neural network (CNN) in a ResNet-34 architecture to perform <strong>pixel segmentation</strong> on all incoming <strong>Sentinel-1 synthetic aperture radar</strong> (SAR) imagery to classify slicks. Despite the satellites’ incomplete oceanic coverage, we have been detecting an average of <strong>135 vessel slicks per month</strong>, and have identified several geographic hotspots where oily discharges are occurring regularly. For the images that capture a vessel in the act of discharging oil, we rely on an <strong>Automatic Identification System</strong> (AIS) database to extract details about the ships, including vessel type and flag state. We will share our experience</p><ul><li>Making sufficient training data from inherently sparse satellite image datasets;</li> <li>Building a computer vision model using PyTorch and fastai;</li> <li>Fully automating the process in the Amazon Web Services (AWS) cloud.</li> </ul><p>The application has been running continuously since August 2020, has processed over 380,000 Sentinel-1 images, and has populated a database with more than 1100 high-confidence slicks from vessels. We will be discussing <strong>preliminary results</strong> from this dataset and remaining challenges to be overcome.</p><p> </p><p>Our objective in making this information and the underlying code, models, and training data <strong>freely available to the public</strong> and governments around the world is to enable public pressure campaigns to improve the prevention of and response to pollution events. Learn more at https://skytruth.org/bilge-dumping/</p>

Sign in / Sign up

Export Citation Format

Share Document