Abstract: The Earth's surface is constantly changing through forces of nature and human activities. Reliable, accurate, and timely change detection is critical to environmental monitoring, resource management, and planning activities. Recently, interest in deep learning algorithms, especially convolutional neural networks, has increased in the field of image change detection due to their powerful ability to extract multi-level image features automatically. However, these networks are prone to drawbacks that limit their applications, which reside in their inability to capture spatial relationships between image instances, as this necessitates a large amount of training data. As an alternative, Capsule Network has been proposed to overcome these shortcomings. Although its effectiveness in remote sensing image analysis has been experimentally verified, its application in change detection tasks remains very sparse. Motivated by its greater robustness towards improved hierarchical object representation, this study aims to apply a capsule network for PolSAR image Change Detection. The experimental results demonstrate that the proposed change detection method can yield a significantly higher detection rate compared to methods based on convolutional neural networks.
Abstract: In global navigation satellite system (GNSS) denied settings, such as indoor environments, autonomous mobile robots are often limited to dead-reckoning navigation techniques to determine their position, velocity, and attitude (PVA). Localization is typically accomplished by employing an inertial measurement unit (IMU), which, while precise in nature, accumulates errors rapidly and severely degrades the localization solution. Standard sensor fusion methods, such as Kalman filtering, aim to fuse precise IMU measurements with accurate aiding sensors to establish a precise and accurate solution. In indoor environments, where GNSS and no other a priori information is known about the environment, effective sensor fusion is difficult to achieve, as accurate aiding sensor choices are sparse. However, an opportunity arises by employing a depth camera in the indoor environment. A depth camera can capture point clouds of the surrounding floors and walls. Extracting attitude from these surfaces can serve as an accurate aiding source, which directly combats errors that arise due to gyroscope imperfections. This configuration for sensor fusion leads to a dramatic reduction of PVA error compared to traditional aiding sensor configurations. This paper provides the theoretical basis for the depth camera aiding sensor method, initial expectations of performance benefit via simulation, and hardware implementation thus verifying its veracity. Hardware implementation is performed on the Quanser Qbot 2™ mobile robot, with a Vector-Nav VN-200™ IMU and Kinect™ camera from Microsoft.
Abstract: We present a decision-support tool to assist an operator in the detection and tracking of a suspect vehicle traveling to an unknown target destination. Multiple data sources, such as traffic cameras, traffic information, weather, etc., are integrated and processed in real-time to infer a suspect’s intended destination chosen from a list of pre-determined high-value targets. Previously, we presented our work in the detection and tracking of vehicles using traffic and airborne cameras. Here, we focus on the fusion and processing of that information to predict a suspect’s behavior. The network of cameras is represented by a directional graph, where the edges correspond to direct road connections between the nodes and the edge weights are proportional to the average time it takes to travel from one node to another. For our experiments, we construct our graph based on the greater Los Angeles subset of the Caltrans’s “Performance Measurement System” (PeMS) dataset. We propose a Bayesian approach where a posterior probability for each target is continuously updated based on detections of the suspect in the live video feeds. Additionally, we introduce the concept of ‘soft interventions’, inspired by the field of Causal Inference. Soft interventions are herein defined as interventions that do not immediately interfere with the suspect’s movements; rather, a soft intervention may induce the suspect into making a new decision, ultimately making their intent more transparent. For example, a soft intervention could be temporarily closing a road a few blocks from the suspect’s current location, which may require the suspect to change their current course. The objective of these interventions is to gain the maximum amount of information about the suspect’s intent in the shortest possible time. Our system currently operates in a human-on-the-loop mode where at each step, a set of recommendations are presented to the operator to aid in decision-making. In principle, the system could operate autonomously, only prompting the operator for critical decisions, allowing the system to significantly scale up to larger areas and multiple suspects. Once the intended target is identified with sufficient confidence, the vehicle is reported to the authorities to take further action. Other recommendations include a selection of road closures, i.e., soft interventions, or to continue monitoring. We evaluate the performance of the proposed system using simulated scenarios where the suspect, starting at random locations, takes a noisy shortest path to their intended target. In all scenarios, the suspect’s intended target is unknown to our system. The decision thresholds are selected to maximize the chances of determining the suspect’s intended target in the minimum amount of time and with the smallest number of interventions. We conclude by discussing the limitations of our current approach to motivate a machine learning approach, based on reinforcement learning in order to relax some of the current limiting assumptions.
Abstract: Cumbria is a geo-political county in Northwest England within which the Lake District National Park, a UNESCO World Heritage site is located. Whilst the area has a formidable reputation for natural beauty and historic assets, the innovation ecosystem is described as ‘patchy’ for a number of reasons. The county is one of the largest in England by area and is sparsely populated. This paper describes the needs, development and delivery of an SME business-support programme funded by the European Regional Development Fund, Lancaster University and the University of Cumbria. The Cumbria Innovations Platform (CUSP) Project has been designed to respond to the nuanced needs of SMEs in this locale, whilst promoting the adoption of research and innovation. CUSP utilizes a funnel method to support rural businesses with access to university innovation intervention. CUSP has been built on a three-tier model: Communicate, Collaborate and Create. The paper describes this project in detail and presents results in terms of output indicators achieved, a beneficiary telephone survey and wider economic forecasts. From a pragmatic point-of-view, the paper provides experiences and reflections of those people who are delivering and evaluating knowledge exchange. The authors discuss some of the benefits, challenges and implications for both policy makers and practitioners. Finally, the paper aims to serve as an invitation to others who may consider adopting a similar method of university-industry collaboration in their own region.
Abstract: This study explores the practicality of using electroencephalographic (EEG) independent components to predict eight-direction finger movements in pseudo-real-time. Six healthy participants with individual-head MRI images performed finger movements in eight directions with two different arm configurations. The analysis was performed in two stages. The first stage consisted of using independent component analysis (ICA) to separate the signals representing brain activity from non-brain activity signals and to obtain the unmixing matrix. The resulting independent components (ICs) were checked, and those reflecting brain-activity were selected. Finally, the time series of the selected ICs were used to predict eight finger-movement directions using Sparse Logistic Regression (SLR). The second stage consisted of using the previously obtained unmixing matrix, the selected ICs, and the model obtained by applying SLR to classify a different EEG dataset. This method was applied to two different settings, namely the single-participant level and the group-level. For the single-participant level, the EEG dataset used in the first stage and the EEG dataset used in the second stage originated from the same participant. For the group-level, the EEG datasets used in the first stage were constructed by temporally concatenating each combination without repetition of the EEG datasets of five participants out of six, whereas the EEG dataset used in the second stage originated from the remaining participants. The average test classification results across datasets (mean ± S.D.) were 38.62 ± 8.36% for the single-participant, which was significantly higher than the chance level (12.50 ± 0.01%), and 27.26 ± 4.39% for the group-level which was also significantly higher than the chance level (12.49% ± 0.01%). The classification accuracy within [–45°, 45°] of the true direction is 70.03 ± 8.14% for single-participant and 62.63 ± 6.07% for group-level which may be promising for some real-life applications. Clustering and contribution analyses further revealed the brain regions involved in finger movement and the temporal aspect of their contribution to the classification. These results showed the possibility of using the ICA-based method in combination with other methods to build a real-time system to control prostheses.
Abstract: In this work, the laser ultrasound technique has been used for analyzing and imaging the inner defects in metal blocks. To detect the defects in blocks, traditionally the researchers used piezoelectric transducers for the generation and reception of ultrasonic signals. These transducers can be configured into the sparse and phased array. But these two configurations have their drawbacks including the requirement of many transducers, time-consuming calculations, limited bandwidth, and provide confined image resolution. Here, we focus on the non-contact method for generating and receiving the ultrasound to examine the inner defects in aluminum blocks. A Q-switched pulsed laser has been used for the generation and the reception is done by using Laser Doppler Vibrometer (LDV). Based on the Doppler effect, LDV provides a rapid and high spatial resolution way for sensing ultrasonic waves. From the LDV, a series of scanning points are selected which serves as the phased array elements. The side-drilled hole of 10 mm diameter with a depth of 25 mm has been introduced and the defect is interrogated by the linear array of scanning points obtained from the LDV. With the aid of the Synthetic Aperture Focusing Technique (SAFT) algorithm, based on the time-shifting principle the inspected images are generated from the A-scan data acquired from the 1-D linear phased array elements. Thus the defect can be precisely detected with good resolution.
Abstract: Continuously differentiable radial basis functions (RBFs) are meshfree, converge faster as the dimensionality increases, and is theoretically spectrally convergent. When implemented on current single and double precision computers, such RBFs can suffer from ill-conditioning because the systems of equations needed to be solved to find the expansion coefficients are full. However, the Advanpix extended precision software package allows computer mathematics to resemble asymptotically ideal Platonic mathematics. Additionally, full systems with extended precision execute faster graphical processors units and field-programmable gate arrays because no branching is needed. Sparse equation systems are fast for iterative solvers in a very limited number of cases.
Abstract: The separation of speech signals has become a research
hotspot in the field of signal processing in recent years. It has
many applications and influences in teleconferencing, hearing aids,
speech recognition of machines and so on. The sounds received are
usually noisy. The issue of identifying the sounds of interest and
obtaining clear sounds in such an environment becomes a problem
worth exploring, that is, the problem of blind source separation.
This paper focuses on the under-determined blind source separation
(UBSS). Sparse component analysis is generally used for the problem
of under-determined blind source separation. The method is mainly
divided into two parts. Firstly, the clustering algorithm is used to
estimate the mixing matrix according to the observed signals. Then
the signal is separated based on the known mixing matrix. In this
paper, the problem of mixing matrix estimation is studied. This paper
proposes an improved algorithm to estimate the mixing matrix for
speech signals in the UBSS model. The traditional potential algorithm
is not accurate for the mixing matrix estimation, especially for low
signal-to noise ratio (SNR).In response to this problem, this paper
considers the idea of an improved potential function method to
estimate the mixing matrix. The algorithm not only avoids the inuence
of insufficient prior information in traditional clustering algorithm,
but also improves the estimation accuracy of mixing matrix. This
paper takes the mixing of four speech signals into two channels as
an example. The results of simulations show that the approach in this
paper not only improves the accuracy of estimation, but also applies
to any mixing matrix.
Abstract: The near-field synthetic aperture radar (SAR) imaging
is an advanced nondestructive testing and evaluation (NDT&E)
technique. This paper investigates the complex-valued signal
processing related to the near-field SAR imaging system, where
the measurement data turns out to be noncircular and improper,
meaning that the complex-valued data is correlated to its complex
conjugate. Furthermore, we discover that the degree of impropriety
of the measurement data and that of the target image can be highly
correlated in near-field SAR imaging. Based on these observations, A
modified generalized sparse Bayesian learning algorithm is proposed,
taking impropriety and noncircularity into account. Numerical results
show that the proposed algorithm provides performance gain, with the
help of noncircular assumption on the signals.
Abstract: Recently, low-dose computed tomography (CT) has become highly desirable due to increasing attention to the potential risks of excessive radiation. For low-dose CT imaging, ensuring image quality while reducing radiation dose is a major challenge. To facilitate low-dose CT imaging, we propose an improved statistical iterative reconstruction scheme based on the Penalized Weighted Least Squares (PWLS) standard combined with total variation (TV) minimization and sparse dictionary learning (DL) to improve reconstruction performance. We call this method "PWLS-TV-DL". In order to evaluate the PWLS-TV-DL method, we performed experiments on digital phantoms and physical phantoms, respectively. The experimental results show that our method is in image quality and calculation. The efficiency is superior to other methods, which confirms the potential of its low-dose CT imaging.
Abstract: Regions with a significant percentage of non-seismically designed buildings and reduced urban planning are particularly vulnerable to natural hazards. In this context, the project ‘Improved Tools for Disaster Risk Mitigation in Algeria’ (ITERATE) aims at seismic risk mitigation in Algeria. Past earthquakes in North Algeria caused extensive damages, e.g. the El Asnam 1980 moment magnitude (Mw) 7.1 and Boumerdes 2003 Mw 6.8 earthquakes. This paper will address a number of proposed developments and considerations made towards a further improvement of the component of seismic hazard. In specific, an updated earthquake catalog (until year 2018) is compiled, and new conversion equations to moment magnitude are introduced. Furthermore, a network-based method for the estimation of the spatial and temporal distribution of the minimum magnitude of completeness is applied. We found relatively large values for Mc, due to the sparse network, and a nonlinear trend between Mw and body wave (mb) or local magnitude (ML), which are the most common scales reported in the region. Lastly, the resulting b-value of the Gutenberg-Richter distribution is sensitive to the declustering method.
Abstract: With the rapid development of urbanization process in China, its environmental protection pressure is severely tested. So, analyzing and optimizing the landscape pattern is an important measure to ease the pressure on the ecological environment. This paper takes Wuhan Urban Development Zone as the research object, and studies its landscape pattern evolution and quantitative optimization strategy. First, remote sensing image data from 1990 to 2015 were interpreted by using Erdas software. Next, the landscape pattern index of landscape level, class level, and patch level was studied based on Fragstats. Then five indicators of ecological environment based on National Environmental Protection Standard of China were selected to evaluate the impact of landscape pattern evolution on the ecological environment. Besides, the cost distance analysis of ArcGIS was applied to simulate wildlife migration thus indirectly measuring the improvement of ecological environment quality. The result shows that the area of land for construction increased 491%. But the bare land, sparse grassland, forest, farmland, water decreased 82%, 47%, 36%, 25% and 11% respectively. They were mainly converted into construction land. On landscape level, the change of landscape index all showed a downward trend. Number of patches (NP), Landscape shape index (LSI), Connection index (CONNECT), Shannon's diversity index (SHDI), Aggregation index (AI) separately decreased by 2778, 25.7, 0.042, 0.6, 29.2%, all of which indicated that the NP, the degree of aggregation and the landscape connectivity declined. On class level, the construction land and forest, CPLAND, TCA, AI and LSI ascended, but the Distribution Statistics Core Area (CORE_AM) decreased. As for farmland, water, sparse grassland, bare land, CPLAND, TCA and DIVISION, the Patch Density (PD) and LSI descended, yet the patch fragmentation and CORE_AM increased. On patch level, patch area, Patch perimeter, Shape index of water, farmland and bare land continued to decline. The three indexes of forest patches increased overall, sparse grassland decreased as a whole, and construction land increased. It is obvious that the urbanization greatly influenced the landscape evolution. Ecological diversity and landscape heterogeneity of ecological patches clearly dropped. The Habitat Quality Index continuously declined by 14%. Therefore, optimization strategy based on greenway network planning is raised for discussion. This paper contributes to the study of landscape pattern evolution in planning and design and to the research on spatial layout of urbanization.
Abstract: Permeable pavements have significant benefits like managing runoff, infiltration, and carrying traffic over conventional pavements in terms of sustainability and environmental impact. Some of the countries are using this technique, especially at locations where durability and other parameters are of importance in nature; however, sparse work has been done on this concept. In India, this is yet to be adopted. In this work, the progress in the characterization and development of Permeable Articulated Concrete Blocks (PACB) pavement design is described and discussed with reference to Indian conditions. The experimentation and in-depth analysis was carried out considering conditions like soil erosion, water logging, and dust which are significant challenges caused due to impermeability of pavement. Concrete blocks with size 16.5’’x 6.5’’x 7’’ consisting of arch shape (4’’) at beneath and ½” PVC holes for articulation were casted. These blocks were tested for flexural strength. The articulation process was done with nylon ropes forming series of concrete block system. The total spacing between the blocks was kept about 8 to 10% of total area. The hydraulic testing was carried out by placing the articulated blocks with the combination of layers of soil, geotextile, clean angular aggregate. This was done to see the percentage of seepage through the entire system. The experimental results showed that with the shape of concrete block the flexural strength achieved was beyond the permissible limit. Such blocks with the combination could be very useful innovation in Indian conditions and useful at various locations compared to the traditional blocks as an alternative for long term sustainability.
Abstract: The Traveling salesman problem (TSP) is NP-hard in combinatorial optimization. The research shows the algorithms for TSP on the sparse graphs have the shorter computation time than those for TSP according to the complete graphs. We present an improved iterative algorithm to compute the sparse graphs for TSP by frequency graphs computed with frequency quadrilaterals. The iterative algorithm is enhanced by adjusting two parameters of the algorithm. The computation time of the algorithm is O(CNmaxn2) where C is the iterations, Nmax is the maximum number of frequency quadrilaterals containing each edge and n is the scale of TSP. The experimental results showed the computed sparse graphs generally have less than 5n edges for most of these Euclidean instances. Moreover, the maximum degree and minimum degree of the vertices in the sparse graphs do not have much difference. Thus, the computation time of the methods to resolve the TSP on these sparse graphs will be greatly reduced.
Abstract: A sparse representation speech denoising method based on adapted stopping residue error was presented in this paper. Firstly, the cross-correlation between the clean speech spectrum and the noise spectrum was analyzed, and an estimation method was proposed. In the denoising method, an over-complete dictionary of the clean speech power spectrum was learned with the K-singular value decomposition (K-SVD) algorithm. In the sparse representation stage, the stopping residue error was adaptively achieved according to the estimated cross-correlation and the adjusted noise spectrum, and the orthogonal matching pursuit (OMP) approach was applied to reconstruct the clean speech spectrum from the noisy speech. Finally, the clean speech was re-synthesised via the inverse Fourier transform with the reconstructed speech spectrum and the noisy speech phase. The experiment results show that the proposed method outperforms the conventional methods in terms of subjective and objective measure.
Abstract: Spatial, Temporal, and Spectral Resolution (STSR) are three key characteristics of Earth observation satellite sensors; however, any single satellite sensor cannot provide Earth observations with high STSR simultaneously because of the hardware technology limitations of satellite sensors. On the other hand, a conflicting circumstance is that the demand for high STSR has been growing with the remote sensing application development. Although image fusion technology provides a feasible means to overcome the limitations of the current Earth observation data, the current fusion technologies cannot enhance all STSR simultaneously and provide high enough resolution improvement level. This study proposes a Hybrid Spatial-Temporal-Spectral image Fusion Model (HSTSFM) to generate synthetic satellite data with high STSR simultaneously, which blends the high spatial resolution from the panchromatic image of Landsat-8 Operational Land Imager (OLI), the high temporal resolution from the multi-spectral image of Moderate Resolution Imaging Spectroradiometer (MODIS), and the high spectral resolution from the hyper-spectral image of Hyperion to produce high STSR images. The proposed HSTSFM contains three fusion modules: (1) spatial-spectral image fusion; (2) spatial-temporal image fusion; (3) temporal-spectral image fusion. A set of test data with both phenological and land cover type changes in Beijing suburb area, China is adopted to demonstrate the performance of the proposed method. The experimental results indicate that HSTSFM can produce fused image that has good spatial and spectral fidelity to the reference image, which means it has the potential to generate synthetic data to support the studies that require high STSR satellite imagery.
Abstract: Mixing in the hyperspectral imaging occurs due to the low spatial resolutions of the used cameras. The existing pure materials “endmembers” in the scene share the spectra pixels with different amounts called “abundances”. Unmixing of the data cube is an important task to know the present endmembers in the cube for the analysis of these images. Unsupervised unmixing is done with no information about the given data cube. Sparsity is one of the recent approaches used in the source recovery or unmixing techniques. The l1-norm optimization problem “basis pursuit” could be used as a sparsity-based approach to solve this unmixing problem where the endmembers is assumed to be sparse in an appropriate domain known as dictionary. This optimization problem is solved using proximal method “iterative thresholding”. The l1-norm basis pursuit optimization problem as a sparsity-based unmixing technique was used to unmix real and synthetic hyperspectral data cubes.
Abstract: In this work, we exploit two assumed properties of the abundances of the observed signatures (endmembers) in order to reconstruct the abundances from hyperspectral data. Joint-sparsity is the first property of the abundances, which assumes the adjacent pixels can be expressed as different linear combinations of same materials. The second property is rank-deficiency where the number of endmembers participating in hyperspectral data is very small compared with the dimensionality of spectral library, which means that the abundances matrix of the endmembers is a low-rank matrix. These assumptions lead to an optimization problem for the sparse unmixing model that requires minimizing a combined l2,p-norm and nuclear norm. We propose a variable splitting and augmented Lagrangian algorithm to solve the optimization problem. Experimental evaluation carried out on synthetic and real hyperspectral data shows that the proposed method outperforms the state-of-the-art algorithms with a better spectral unmixing accuracy.
Abstract: The convergence rate of the least-mean-square (LMS)
algorithm deteriorates if the input signal to the filter is correlated.
In a system identification problem, this convergence rate can be
improved if the signal is white and/or if the system is sparse. We
recently proposed a sparse transform domain LMS-type algorithm
that uses a variable step-size for a sparse system identification.
The proposed algorithm provided high performance even if the
input signal is highly correlated. In this work, we investigate the
performance of the proposed TD-LMS algorithm for a large number
of filter tap which is also a critical issue for standard LMS algorithm.
Additionally, the optimum value of the most important parameter is
calculated for all experiments. Moreover, the convergence analysis
of the proposed algorithm is provided. The performance of the
proposed algorithm has been compared to different algorithms in a
sparse system identification setting of different sparsity levels and
different number of filter taps. Simulations have shown that the
proposed algorithm has prominent performance compared to the other
algorithms.
Abstract: In this paper, we extend the versatility and usefulness of GIS as a methodology for any river basin hydrologic characteristics analysis (HCA). The Gurara River basin located in North-Central Nigeria is presented in this study. It is an on-going research using spatial Digital Elevation Model (DEM) and Arc-Hydro tools to take inventory of the basin characteristics in order to predict water abstraction quantification on streamflow regime. One of the main concerns of hydrological modelling is the quantification of runoff from rainstorm events. In practice, the soil conservation service curve (SCS) method and the Conventional procedure called rational technique are still generally used these traditional hydrological lumped models convert statistical properties of rainfall in river basin to observed runoff and hydrograph. However, the models give little or no information about spatially dispersed information on rainfall and basin physical characteristics. Therefore, this paper synthesizes morphometric parameters in generating runoff. The expected results of the basin characteristics such as size, area, shape, slope of the watershed and stream distribution network analysis could be useful in estimating streamflow discharge. Water resources managers and irrigation farmers could utilize the tool for determining net return from available scarce water resources, where past data records are sparse for the aspect of land and climate.