Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Detecting cracks is a very interesting field of research used to address a large number of issues, 
including the detection of road and other structural cracks to strengthen the prevention of damages 
and planning of maintenance and repairs. It is also used to facilitate the authentication of paintings.
In most cases, the detection is only performed on simple images while multi-spectral images are increasingly 
used in many research areas, including Medicine, given their high potential for providing
more accurate information. This work responds to a request by the "Lumiere Technology Multispectral Institute" 
which indicated an interest in using multi-spectral images to detect cracks in paintings.
Its objective is to analyse if applying detections on multi-spectral images can help improve
the quality and efficiency of maintenance and restoration of paintings. To meet this objective,
we work with the Cytomine application, an "Open-source rich Internet application for collaborative
analysis of multi-gigapixel images", developed by researchers at the Montefiore Institute of the University of Liège.
We more specifically use the recently-developed extension supporting the utilisation of multi-spectral images
to apply machine learning algorithms on wide-banded multi-spectral images. The "Musées royaux des beaux-arts de Belgique"
have provided the paintings which are analysed in this work. 

To carry out our analysis: i) we implement the Cytomine’s Extractor and Spectral Reader and complement
the application’s new extension by adding ways to optimise the extraction, storage and use of data from multi-spectral image, 
ii) based on this implementation, we present three softwares which we designed to enable us
to make a feature analysis of the data, to fit a model using data from extit{Cytomine},
or to use a fitted model to make predictions, iii) we test two dimension reduction methods,
PCA (Principal Components Analysis) and TSNE (T-distributed Stochastic Neighbour Embedding)
and three feature importance measures to help reducing the large size of datasets created by multi-spectral images,
and iv) we conduct experiments on three datasets to find how machine learning performs
on multi-spectral images: one small dataset based on a multi-spectral image of biological cells,
one small dataset based on a multi-spectral image where we have extracted two different tones of red,
and a third dataset based on a multi-spectral image where we have labelled cracks and undamaged parts
on the painting extit{Portrait of Flautist François Devienne} of Jacques-Louis David. 

These experiments evidence that: i) TSNE is a possible solution to reduce the dimension of multi-spectral images
if the necessary resources, i.e. memory and computational power, are available, and ii) using multi-spectral images
has an advantage over simply using standard RGB images, even if the increase in computation time implies
that a pre-processing is needed to reduce the number of bands. We therefore encourage further research based
on the new tools developed in this work, for instance to try Boosting methods or Deep Neural Networks.

painting --- cytomine --- multi spectral --- image --- crack --- Ingénierie, informatique & technologie > Sciences informatiques

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The continuous miniaturization of products and the growing complexity of their embedded multifunctionalities necessitates continuous research and development efforts regarding micro components and related micro manufacturing technologies. Highly miniaturized systems, manufactured using a wide variety of materials, have found application in key technological fields, such as healthcare devices, micro implants, mobility, communications, optics, and micro electromechanical systems. Innovations required for the high-precision manufacturing of micro components can specifically be achieved through optimizations using post-process (i.e., offline) and in-process (i.e., online) metrology of both process input and output parameters, as well as geometrical features of the produced micro parts. However, it is of critical importance to reduce the metrology and optimization efforts, since process and product quality control can represent a significant portion of the total production time in micro manufacturing. To solve this fundamental challenge, research efforts have been undertaken in order to define, investigate, implement, and validate the so-called “product/process manufacturing fingerprint” concept. The “product manufacturing fingerprint” concept refers to those unique dimensional outcomes (e.g., surface topography, form error, critical dimensions, etc.) on the produced component that, if kept under control and within specifications, ensure that the entire micro component complies to its specifications. The “process manufacturing fingerprint” is a specific process parameter or feature to be monitored and controlled, in order to maintain the manufacture of products within the specified tolerances. By integrating both product and process manufacturing fingerprint concepts, the metrology and optimization efforts are highly reduced. Therefore, the quality of the micro products increases, with an obvious improvement in production yield. Accordingly, this Special Issue seeks to showcase research papers, short communications, and review articles that focus on novel methodological developments and applications in micro- and sub-micro-scale manufacturing, process monitoring and control, as well as micro and sub-micro product quality assurance. Focus will be on micro manufacturing process chains and their micro product/process fingerprint, towards full process optimization and zero-defect micro manufacturing.

n/a --- Fresnel lenses --- Electro sinter forging --- micro-injection moulding --- surface roughness --- charge relaxation time --- optimization --- gratings --- plasma-electrolytic polishing --- micro structures replication --- micro-grinding --- electrical discharge machining --- injection molding --- quality control --- commercial control hardware --- electrical current --- damping --- process monitoring --- fingerprints --- impact analysis --- current monitoring --- process control --- quality assurance --- surface integrity --- microfabrication --- microinjection moulding --- electro chemical machining --- superhydrophobic surface --- surface modification --- haptic actuator --- electrical discharge machining (EDM) --- surface morphology --- inline metrology --- optical quality control --- finishing --- flow length --- precision injection molding --- laser ablation --- micro metrology --- Halbach linear motor --- 2-step analysis --- computer holography --- PeP --- satellite drop --- process fingerprint --- materials characterisation --- current density --- micro drilling --- multi-spectral imaging --- lithography --- manufacturing signature --- artificial compound eye --- electrohydrodynamic jet printing --- ECM --- positioning platform --- diffractive optics --- bioceramics --- resistance sintering --- uncertainty budget --- product fingerprint --- confocal microscopy --- spectral splitting --- dental implant --- desirability function --- injection compression molding --- electrochemical machining (ECM) --- high strain rate effect --- process fingerprints

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Spruce budworm (Choristoneura fumiferana (Clem.)) outbreaks are a dominant natural disturbance in the forests of Canada and northeastern USA. Widespread, severe defoliation by this native insect results in large-scale mortality and growth reductions of spruce (Picea sp.) and balsam fir (Abies balsamea (L.) Mill.) forests, and largely determines future age–class structure and productivity. The last major spruce budworm outbreak defoliated over 58 million hectares in the 1970s–1980s, and caused 32–43 million m3/year of timber volume losses from 1978 to 1987, in Canada. Management to deal with spruce budworm outbreaks has emphasized forest protection, spraying registered insecticides to prevent defoliation and keep trees alive. Other tactics can include salvage harvesting, altering harvest schedules to remove the most susceptible stands, or reducing future susceptibility by planting or thinning. Chemical insecticides are no longer used, and protection strategies use biological insecticides Bacillus thuringiensis (B.t.) or tebufenozide, a specific insect growth regulator. Over the last five years, a $30 million research project has tested another possible management tactic, termed an ‘early intervention strategy’, aimed at area-wide management of spruce budworm populations. This includes intensive monitoring to detect ‘hot spots’ of rising budworm populations before defoliation occurs, targeted insecticide treatment to prevent spread, and detailed research into target and non-target insect effects. The objective of this Special Issue is to compile the most recent research on protection strategies against spruce budworm. A series of papers will describe results and prospects for the use of an early intervention strategy in spruce budworm and other insect management.

pheromone mating disruption --- spruce budworm --- insecticide application --- multi-spectral remote sensing --- simulation --- apparent fecundity --- Choristoneura fumiferana (Clemens) --- Pinaceae --- Choristoneura fumiferana --- circadian rhythm --- forest protection --- early intervention strategy --- insect population management --- moth --- survival --- Phialocephala scopiformis --- moths --- optimized treatment design --- spatial-temporal patterns --- monitoring --- modelling --- science communication --- decision support system --- population control --- area-wide management --- tortricidae --- insect susceptibility --- egg recruitment --- annual defoliation --- treatment threshold --- Maine --- dispersal --- growth rate --- forest pests --- Choristoneura fumiferana (Clem.) --- mixed effect models --- intertree variance --- endophytic fungi --- Acadian region --- insecticides --- defoliation --- Abies balsamea --- Picea glauca --- immigration --- defoliation prediction --- early intervention --- Quebec --- phenology --- aerobiology --- economic losses --- spatial autocorrelation --- foliage protection --- computable general equilibrium model --- economic and ecological cost: benefit analyses --- hardwood content --- plant tolerance --- Lepidoptera --- migration

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Remote sensing plays a pivotal role in understanding where and how floods and glacier geohazards occur; their severity, causes and types; and the risk that they may pose to populations, activities and properties. By providing a spectrum of imaging capabilities, resolutions and temporal and spatial coverage, remote sensing data acquired from satellite, aerial and ground-based platforms provide key geo-information to characterize and model these processes. This book includes research papers on novel technologies (e.g., sensors, platforms), data (e.g., multi-spectral, radar, laser scanning, GPS, gravity) and analysis methods (e.g., change detection, offset tracking, structure from motion, 3D modeling, radar interferometry, automated classification, machine learning, spectral indices, probabilistic approaches) for flood and glacier imaging. Through target applications and case studies distributed globally, these articles contribute to the discussion on the current potential and limitations of remote sensing in this specialist research field, as well as the identification of trends and future perspectives.

glacier surge --- glacier collapse --- rock-slope instability --- hazard --- Landsat --- Sentinel 2 --- Tibet --- flood extent mapping --- supervised classification --- NDWI --- synthetic aperture radar (SAR) --- web application --- synthetic aperture radar --- offset tracking --- displacements --- Sentinel-1 --- glacier monitoring --- flood mapping --- damage assessment --- SAR image --- Landsat-8 --- Google Earth Engine --- GEE --- Bangladesh --- SAR intensity time series --- urban flood mapping --- double bounce effect --- Hurricane Matthew --- flood --- FPI --- GRACE --- terrestrial water storage anomaly --- storage deficit --- mass balance --- snow depth --- glacier retreat --- surface DEM --- elevation change --- Sentinel --- Secchi disk --- chlorophyll a --- sediments --- phytoplankton --- floods --- remote sensing --- GIS --- disaster mapping --- Lower Chenab Plain --- laserscanning --- UAV—structure from Motion --- multi-spectral satellite data --- synthetic Aperture Radar --- glacier lake evolution --- glacier river --- slope processes --- rock fall --- cryosphere --- fusion --- inundation probability --- Hurricane Harvey --- ADCIRC --- n/a --- UAV-structure from Motion