Abstract: With the development of HyperSpectral Imagery
(HSI) technology, the spectral resolution of HSI became denser,
which resulted in large number of spectral bands, high correlation
between neighboring, and high data redundancy. However, the
semantic interpretation is a challenging task for HSI analysis
due to the high dimensionality and the high correlation of the
different spectral bands. In fact, this work presents a dimensionality
reduction approach that allows to overcome the different issues
improving the semantic interpretation of HSI. Therefore, in order
to preserve the spatial information, the Tensor Locality Preserving
Projection (TLPP) has been applied to transform the original HSI.
In the second step, knowledge has been extracted based on the
adjacency graph to describe the different pixels. Based on the
transformation matrix using TLPP, a weighted matrix has been
constructed to rank the different spectral bands based on their
contribution score. Thus, the relevant bands have been adaptively
selected based on the weighted matrix. The performance of the
presented approach has been validated by implementing several
experiments, and the obtained results demonstrate the efficiency
of this approach compared to various existing dimensionality
reduction techniques. Also, according to the experimental results,
we can conclude that this approach can adaptively select the
relevant spectral improving the semantic interpretation of HSI.
Abstract: Thermal insulating composites help to reduce the total power consumption in a building by creating a barrier between external and internal environment. Such composites can be used in the roofing tiles or wall panels for exterior surfaces. This study purposes to develop lightweight cement-based composites for thermal insulating applications. Waste materials like silica fume (an industrial by-product) and fly ash cenosphere (FAC) (hollow micro-spherical shells obtained as a waste residue from coal fired power plants) were used as partial replacement of cement and lightweight filler, respectively. Moreover, aerogel, a nano-porous material made of silica, was also used in different dosages for improved thermal insulating behavior, while poly vinyl alcohol (PVA) fibers were added for enhanced toughness. The raw materials including binders and fillers were characterized by X-Ray Diffraction (XRD), X-Ray Fluorescence spectroscopy (XRF), and Brunauer–Emmett–Teller (BET) analysis techniques in which various physical and chemical properties of the raw materials were evaluated like specific surface area, chemical composition (oxide form), and pore size distribution (if any). Ultra-lightweight cementitious composites were developed by varying the amounts of FAC and aerogel with 28-day unit weight ranging from 1551.28 kg/m3 to 1027.85 kg/m3. Excellent mechanical and thermal insulating properties of the resulting composites were obtained ranging from 53.62 MPa to 8.66 MPa compressive strength, 9.77 MPa to 3.98 MPa flexural strength, and 0.3025 W/m-K to 0.2009 W/m-K as thermal conductivity coefficient (QTM-500). The composites were also tested for peak temperature difference between outer and inner surfaces when subjected to heating (in a specially designed experimental set-up) by a 275W infrared lamp. The temperature difference up to 16.78 oC was achieved, which indicated outstanding properties of the developed composites to act as a thermal barrier for building envelopes. Microstructural studies were carried out by Scanning Electron Microscopy (SEM) and Energy Dispersive X-ray Spectroscopy (EDS) for characterizing the inner structure of the composite specimen. Also, the hydration products were quantified using the surface area mapping and line scale technique in EDS. The microstructural analyses indicated excellent bonding of FAC and aerogel in the cementitious system. Also, selective reactivity of FAC was ascertained from the SEM imagery where the partially consumed FAC shells were observed. All in all, the lightweight fillers, FAC, and aerogel helped to produce the lightweight composites due to their physical characteristics, while exceptional mechanical properties, owing to FAC partial reactivity, were achieved.
Abstract: According to Naturalistic principles, human destiny in the form of blind chance and determinism, entraps the individual, so man is a defenceless creature unable to escape from the ruthless paws of a stoical universe. In Naturalism; nonetheless, melodrama mirrors a conscious alternative with a peculiar function. A typical American Naturalistic character thus cannot be a subject for social criticism of American society since they are not victims of the ongoing virtual slavery, capitalist system, nor of a ruined milieu, but of their own volition, and more importantly, their character frailty. Through a Postmodern viewpoint, each Naturalistic work can encompass some entropic trends and changes culminating in an entire failure and devastation. Frank Norris in McTeague displays the futile struggles of ordinary men and how they end up brutes. McTeague encompasses intoxication, abuse, violation, and ruthless homicides. Norris’ depictions of the falling individual as a demon represent the entropic dimension of Naturalistic novels. McTeague’s defeat is somewhat his own fault, the result of his own blunders and resolution, not the result of sheer accident. Throughout the novel, each character is a kind of insane quester indicating McTeague’s decadence and, by inference, the decadence of Western civilisation. McTeague seems to designate Norris’ solicitude for a community fabricated by the elements of human negative demeanours and conducts hauling acute symptoms of infectious dehumanisation. The aim of this article is to illustrate how one specific negative human disposition gradually, like a running fire, can spread everywhere and burn everything in itself. The author applies the concept of entropy metaphorically to describe the individual devolutions that necessarily comprise community entropy in McTeague, a dying universe.
Abstract: Ship detection is nowadays quite an important issue
in tasks related to sea traffic control, fishery management and ship
search and rescue. Although it has traditionally been carried out
by patrol ships or aircrafts, coverage and weather conditions and
sea state can become a problem. Synthetic aperture radars can
surpass these coverage limitations and work under any climatological
condition. A fast CFAR ship detector based on a robust statistical
modeling of sea clutter with respect to sea states in SAR images
is used. In this paper, the minimum SNR required to obtain a
given detection probability with a given false alarm rate for any
sea state is determined. A Gaussian target model using real SAR
data is considered. Results show that SNR does not depend heavily
on the class considered. Provided there is some variation in the
backscattering of targets in SAR imagery, the detection probability
is limited and a post-processing stage based on morphology would
be suitable.
Abstract: Hyperspectral imagery (HSI) typically provides a
wealth of information captured in a wide range of the
electromagnetic spectrum for each pixel in the image. Hence, a
pixel in HSI is a high-dimensional vector of intensities with a
large spectral range and a high spectral resolution. Therefore, the
semantic interpretation is a challenging task of HSI analysis. We
focused in this paper on object classification as HSI semantic
interpretation. However, HSI classification still faces some issues,
among which are the following: The spatial variability of spectral
signatures, the high number of spectral bands, and the high cost
of true sample labeling. Therefore, the high number of spectral
bands and the low number of training samples pose the problem of
the curse of dimensionality. In order to resolve this problem, we
propose to introduce the process of dimensionality reduction trying
to improve the classification of HSI. The presented approach is a
semi-supervised band selection method based on spatial hypergraph
embedding model to represent higher order relationships with
different weights of the spatial neighbors corresponding to the
centroid of pixel. This semi-supervised band selection has been
developed to select useful bands for object classification. The
presented approach is evaluated on AVIRIS and ROSIS HSIs
and compared to other dimensionality reduction methods. The
experimental results demonstrate the efficacy of our approach
compared to many existing dimensionality reduction methods for
HSI classification.
Abstract: In this study, it was aimed to determine a route for identification of rice cultivation areas within Thrace and Marmara regions of Turkey using remote sensing and GIS. Landsat 8 (OLI-TIRS) imageries acquired in production season of 2013 with 181/32 Path/Row number were used. Four different seasonal images were generated utilizing original bands and different transformation techniques. All images were classified individually using supervised classification techniques and Land Use Land Cover Maps (LULC) were generated with 8 classes. Areas (ha, %) of each classes were calculated. In addition, district-based rice distribution maps were developed and results of these maps were compared with Turkish Statistical Institute (TurkSTAT; TSI)’s actual rice cultivation area records. Accuracy assessments were conducted, and most accurate map was selected depending on accuracy assessment and coherency with TSI results. Additionally, rice areas on over 4° slope values were considered as mis-classified pixels and they eliminated using slope map and GIS tools. Finally, randomized rice zones were selected to obtain maximum-minimum value ranges of each date (May, June, July, August, September images separately) NDVI, LSWI, and LST images to test whether they may be used for rice area determination via raster calculator tool of ArcGIS. The most accurate classification for rice determination was obtained from seasonal LSWI LULC map, and considering TSI data and accuracy assessment results and mis-classified pixels were eliminated from this map. According to results, 83151.5 ha of rice areas exist within study area. However, this result is higher than TSI records with an area of 12702.3 ha. Use of maximum-minimum range of rice area NDVI, LSWI, and LST was tested in Meric district. It was seen that using the value ranges obtained from July imagery, gave the closest results to TSI records, and the difference was only 206.4 ha. This difference is normal due to relatively low resolution of images. Thus, employment of images with higher spectral, spatial, temporal and radiometric resolutions may provide more reliable results.
Abstract: Satellite imagery classification is a challenging problem with many practical applications. In this paper, we designed a deep convolution neural network (DCNN) to classify the satellite imagery. The contributions of this paper are twofold — First, to cope with the large-scale variance in the satellite image, we introduced the inception module, which has multiple filters with different size at the same level, as the building block to build our DCNN model. Second, we proposed a genetic algorithm based method to efficiently search the best hyper-parameters of the DCNN in a large search space. The proposed method is evaluated on the benchmark database. The results of the proposed hyper-parameters search method show it will guide the search towards better regions of the parameter space. Based on the found hyper-parameters, we built our DCNN models, and evaluated its performance on satellite imagery classification, the results show the classification accuracy of proposed models outperform the state of the art method.
Abstract: Merauke district in Papua, Indonesia has a strategic position and natural potential for the development of agricultural industry. The development of agriculture in this region is being accelerated as part of Indonesian Government’s declaration announcing Merauke as one of future national food barns. Therefore, land-use suitability analysis for Merauke need to be performed. As a result, the mapping for future agriculture-based industries can be done optimally. In this research, a case study is carried out in Semangga sub district. The objective of this study is to determine the suitability of Merauke land for some food crops. A modified agro-ecological zoning is applied to reach the objective. In this research, land cover based on satellite imagery is combined with soil, water and climate survey results to come up with preliminary zoning. Considering the special characteristics of Merauke community, the agricultural zoning maps resulted based on those inputs will be combined with socio-economic information and culture to determine the final zoning map for agricultural industry in Merauke. Examples of culture are customary rights of local residents and the rights of local people and their own local food patterns. This paper presents the results of first year of the two-year research project funded by The Indonesian Government through MP3EI schema. It shares the findings of land cover studies, the distribution of soil physical and chemical parameters, as well as suitability analysis of Semangga sub-district for five different food plants.
Abstract: The aim of this research is to understand how the
emerging power bloc BRICS employs infrastructure development
narratives to construct a new world order. BRICS is an international
body consisting of five emerging countries that collaborate on
economic and political issues: Brazil, Russia, India, China, and South
Africa. This study explores the projection of infrastructure
development narratives through an analysis of BRICS’ attention to
infrastructure investment and financing, its support of the New
Partnership on African Development and the establishment of the
New Development Bank in Shanghai. The theory of Strategic
Narratives is used to explore BRICS’ commitment to infrastructure
development and to distinguish three layers: system narratives
(BRICS as a global actor to propose development reform), identity
narratives (BRICS as a collective identity joining efforts to act upon
development aspirations) and issue narratives (BRICS committed to a
range of issues of which infrastructure development is prominent).
The methodology that is employed is a narrative analysis of BRICS’
official documents, media statements, and website imagery. A
comparison of these narratives illuminates tensions at the three layers
and among the five member states. Identifying tensions among
development infrastructure narratives provides an indication of how
policymaking for infrastructure development could be improved.
Subsequently, it advances BRICS’ ability to act as a global actor to
construct a new world order.
Abstract: Advances in spatial and spectral resolution of satellite
images have led to tremendous growth in large image databases. The
data we acquire through satellites, radars, and sensors consists of
important geographical information that can be used for remote
sensing applications such as region planning, disaster management.
Spatial data classification and object recognition are important tasks
for many applications. However, classifying objects and identifying
them manually from images is a difficult task. Object recognition is
often considered as a classification problem, this task can be
performed using machine-learning techniques. Despite of many
machine-learning algorithms, the classification is done using
supervised classifiers such as Support Vector Machines (SVM) as the
area of interest is known. We proposed a classification method,
which considers neighboring pixels in a region for feature extraction
and it evaluates classifications precisely according to neighboring
classes for semantic interpretation of region of interest (ROI). A
dataset has been created for training and testing purpose; we
generated the attributes by considering pixel intensity values and
mean values of reflectance. We demonstrated the benefits of using
knowledge discovery and data-mining techniques, which can be on
image data for accurate information extraction and classification from
high spatial resolution remote sensing imagery.
Abstract: Indonesia has experienced annual forest fires that have
rapidly destroyed and degraded its forests. Fires in the peat swamp
forests of Riau Province, have set the stage for problems to worsen,
this being the ecosystem most prone to fires (which are also the most
difficult, to extinguish). Despite various efforts to curb deforestation,
and forest degradation processes, severe forest fires are still
occurring. To find an effective solution, the basic causes of the
problems must be identified. It is therefore critical to have an indepth
understanding of the underlying causal factors that have
contributed to deforestation and forest degradation as a whole, in
order to attain reductions in their rates. An assessment of the drivers of deforestation and forest
degradation was carried out, in order to design and implement
measures that could slow these destructive processes. Research was
conducted in Giam Siak Kecil–Bukit Batu Biosphere Reserve
(GSKBB BR), in the Riau Province of Sumatera, Indonesia. A
biosphere reserve was selected as the study site because such reserves
aim to reconcile conservation with sustainable development. A
biosphere reserve should promote a range of local human activities,
together with development values that are in line spatially and
economically with the area conservation values, through use of a
zoning system. Moreover, GSKBB BR is an area with vast peatlands,
and is experiencing forest fires annually. Various factors were
analysed to assess the drivers of deforestation and forest degradation
in GSKBB BR; data were collected from focus group discussions
with stakeholders, key informant interviews with key stakeholders,
field observation and a literature review. Landsat satellite imagery was used to map forest-cover changes
for various periods. Analysis of landsat images, taken during the
period 2010-2014, revealed that within the non-protected area of core
zone, there was a trend towards decreasing peat swamp forest areas,
increasing land clearance, and increasing areas of community oilpalm
and rubber plantations. Fire was used for land clearing and most
of the forest fires occurred in the most populous area (the transition
area). The study found a relationship between the deforested/
degraded areas, and certain distance variables, i.e. distance from
roads, villages and the borders between the core area and the buffer
zone. The further the distance from the core area of the reserve, the
higher was the degree of deforestation and forest degradation. Research findings suggested that agricultural expansion may be
the direct cause of deforestation and forest degradation in the reserve,
whereas socio-economic factors were the underlying driver of forest
cover changes; such factors consisting of a combination of sociocultural,
infrastructural, technological, institutional (policy and governance), demographic (population pressure) and economic
(market demand) considerations. These findings indicated that local
factors/problems were the critical causes of deforestation and
degradation in GSKBB BR. This research therefore concluded that
reductions in deforestation and forest degradation in GSKBB BR
could be achieved through ‘local actor’-tailored approaches such as
community empowerment.
Abstract: In this paper, we present a four-step ortho-rectification
procedure for real-time geo-referencing of video data from a low-cost
UAV equipped with a multi-sensor system. The basic procedures for
the real-time ortho-rectification are: (1) decompilation of the video
stream into individual frames; (2) establishing the interior camera
orientation parameters; (3) determining the relative orientation
parameters for each video frame with respect to each other; (4)
finding the absolute orientation parameters, using a self-calibration
bundle and adjustment with the aid of a mathematical model. Each
ortho-rectified video frame is then mosaicked together to produce a
mosaic image of the test area, which is then merged with a well
referenced existing digital map for the purpose of geo-referencing
and aerial surveillance. A test field located in Abuja, Nigeria was
used to evaluate our method. Video and telemetry data were collected
for about fifteen minutes, and they were processed using the four-step
ortho-rectification procedure. The results demonstrated that the
geometric measurement of the control field from ortho-images is
more accurate when compared with those from original perspective
images when used to pin point the exact location of targets on the
video imagery acquired by the UAV. The 2-D planimetric accuracy
when compared with the 6 control points measured by a GPS receiver
is between 3 to 5 metres.
Abstract: There have been rigorous research and development
of unmanned aerial vehicles in the field of search and rescue (SAR)
operation recently. UAVs reduce unnecessary human risks while
assisting rescue efforts through aerial imagery, topographic mapping
and emergency delivery. The application of UAVs in offshore and
nearshore marine SAR missions is discussed in this paper. Projects
that integrate UAV technology into their systems are introduced to
highlight the great advantages and capabilities of UAVs. Scenarios
where UAVs could provide invaluable assistance are also suggested.
Abstract: Cerebellar ataxia is a steadily progressive
neurodegenerative disease associated with loss of motor control,
leaving patients unable to walk, talk, or perform activities of daily
living. Direct motor instruction in cerebella ataxia patients has limited
effectiveness, presumably because an inappropriate closed-loop
cerebellar response to the inevitable observed error confounds motor
learning mechanisms. Could the use of EEG based BCI provide
advanced biofeedback to improve motor imagery and provide a
“backdoor” to improving motor performance in ataxia patients? In
order to determine the feasibility of using EEG-based BCI control in
this population, we compare the ability to modulate mu-band power
(8-12 Hz) by performing a cued motor imagery task in an ataxia
patient and healthy control.
Abstract: This study investigates the use of a time-series of
MODIS NDVI data to identify agricultural land cover change on an
annual time step (2007 - 2012) and characterize the trend. Following
an ISODATA classification of the MODIS imagery to selectively
mask areas not agriculture or semi-natural, NDVI signatures were
created to identify areas cereals and vineyards with the aid of
ancillary, pictometry and field sample data for 2010. The NDVI
signature curve and training samples were used to create a decision
tree model in WEKA 3.6.9 using decision tree classifier (J48)
algorithm; Model 1 including ISODATA classification and Model 2
not. These two models were then used to classify all data for the
study area for 2010, producing land cover maps with classification
accuracies of 77% and 80% for Model 1 and 2 respectively. Model 2
was subsequently used to create land cover classification and change
detection maps for all other years. Subtle changes and areas of
consistency (unchanged) were observed in the agricultural classes
and crop practices. Over the years as predicted by the land cover
classification. Forty one percent of the catchment comprised of
cereals with 35% possibly following a crop rotation system.
Vineyards largely remained constant with only one percent
conversion to vineyard from other land cover classes.
Abstract: Maize constitutes a major agrarian production for use
by the vast population but despite its economic importance; it has not
been produced to meet the economic needs of the country. Achieving
optimum yield in maize can meaningfully be supported by land
suitability analysis in order to guarantee self-sufficiency for future
production optimization. This study examines land suitability for
maize production through the analysis of the physicochemical
variations in soil properties and other land attributes over space using
a Geographic Information System (GIS) framework.
Physicochemical parameters of importance selected include slope,
landuse, physical and chemical properties of the soil, and climatic
variables. Landsat imagery was used to categorize the landuse,
Shuttle Radar Topographic Mapping (SRTM) generated the slope and
soil samples were analyzed for its physical and chemical components.
Suitability was categorized into highly, moderately and marginally
suitable based on Food and Agricultural Organisation (FAO)
classification, using the Analytical Hierarchy Process (AHP)
technique of GIS. This result can be used by small scale farmers for
efficient decision making in the allocation of land for maize
production.
Abstract: It has become an increasing evident that large
development influences the climate. There are concerns that rising
temperature over developed areas could have negative impact and
increase living discomfort within city boundaries. Temperature trends
in Ibadan city have received little attention, yet the area has
experienced heavy urban expansion between 1972 and 2014. This
research aims at examining the impact of landuse change on surface
temperature knowing that the built-up environment absorb and store
solar energy, resulting into the Urban Heat Island (UHI) effect. The
Landsat imagery was used to examine the landuse change for a
period of 42 years (1972-2014). Land Surface Temperature (LST)
was obtained by converting the thermal band to a surface temperature
map and zonal statistic analyses was used to examine the relationship
between landuse and temperature emission. The results showed that
the settlement area increased to a large extent while the area covered
by vegetation reduced during the study period. The spatial and
temporal trends of surface temperature are related to the gradual
change in urban landuse/landcover and the settlement area has the
highest emission. This research provides useful insight into the
temporal behavior of the Ibadan city.
Abstract: Generally the natural environment is made up of air,
water and soil. The release of emission of industrial waste into
anyone of the components of the environment causes pollution.
Industrial pollution significantly threatens the inherent right of
people, to the enjoyment of a safe and secure environment. The aim
of this paper is to assess the effect of environmental pollution and
health risks of residents living near Ewekoro cement factory. The
research made use of IKONOS imagery for Geographical
Information System (GIS) to buffer and extract buildings that are less
than 1km to the factory, within 1km to 5km and above 5km to the
factory. Also questionnaire was used to elicit information on the
socio-economic factors, effect of environmental pollution on
residents and measures adopted to control industrial pollution on the
residents. Findings show that most buildings that fall between less
than 1km and 1km to 5km to the factory have high health risk in the
study area. The study recommended total relocation for the residents
of the study area to reduce health risk problems.
Abstract: In healthy humans, the cortical brain rhythm shows
specific mu (~6-14 Hz) and beta (~18-24 Hz) band patterns in the
cases of both real and imaginary motor movements. As cerebellar
ataxia is associated with impairment of precise motor movement
control as well as motor imagery, ataxia is an ideal model system in
which to study the role of the cerebellocortical circuit in rhythm
control. We hypothesize that the EEG characteristics of ataxic patients
differ from those of controls during the performance of a
Brain-Computer Interface (BCI) task. Ataxia and control subjects
showed a similar distribution of mu power during cued relaxation.
During cued motor imagery, however, the ataxia group showed
significant spatial distribution of the response, while the control group
showed the expected decrease in mu-band power (localized to the
motor cortex).
Abstract: One of the most important tasks in urban remote
sensing is the detection of impervious surfaces (IS), such as roofs and
roads. However, detection of IS in heterogeneous areas still remains
one of the most challenging tasks. In this study, detection of concrete
roof using an object-based approach was proposed. A new rule-based
classification was developed to detect concrete roof tile. This
proposed rule-based classification was applied to WorldView-2
image and results showed that the proposed rule has good potential to
predict concrete roof material from WorldView-2 images, with 85%
accuracy.