Spatial Distribution Of Features Research Articles

Cannabis consumers in Poland

The purpose of this study is an attempt to answer the following questions: (1) Is there a regional differentiation of cannabis consumers in Poland? (2) What is the scale of this differentiation? (3) What factors affect this differentiation? Our empirical study is based on the analysis of an anonymous online survey. The coefficient of variation, taxonomic measures of similarity, synthetic index and Spearman correlation coefficient are used in the analysis. It is observed that cannabis consumption in Poland is most popular among men, youth and young adults (Generation Y), as well as among those who are well-educated, relatively well-off and live in cities. The structure of selected demographic and socio-economic features of the respondents is poorly differentiated regionally. Regional differentiation in the structure of cannabis consumption frequency is at an average level. The spatial distribution of features characterizing the respondents is highly consistent with the spatial distribution of city dwellers aged 15–44, their sex and 5-year age ranges, the level of education, the size of cities and the level of gross domestic product.

Spatially Regularized Structural Support Vector Machine for Robust Visual Tracking

Structural support vector machine (SSVM) is popular in the visual tracking field as it provides a consistent target representation for both learning and detection. However, the spatial distribution of feature is not considered in standard SSVM-based trackers, therefore leading to limited performance. To obtain a robust discriminative classifier, this paper proposes a novel tracking framework that spatially regularizes SSVM, which yields a new spatially regularized SSVM (SRSSVM). We utilize the spatial regularization prior to penalize the learning classifier with the same size as the target region. The location of classifier spatially located far from the center of region is assigned large weight and vice versa. Then, it is introduced into the SSVM model as a regularization factor to learn the robust discriminative model. Furthermore, an optimizing algorithm with dual coordination descent is presented to efficiently solve the SRSSVM tracking model. Our proposed SRSSVM tracking method has low computational cost like the traditional linear SSVM tracker while can significantly improve the robustness of the discriminative classifier. The experimental results on three popular tracking benchmark data sets show that the proposed SRSSVM tracking method performs favorably against the state-of-the-art trackers.

Global Localization Using Low-frequency Image-based Descriptor and Range Data-based Validation

In image-based global localization, a robot pose is estimated through image association when the robot revisits a previously visited location on a map. Image association is typically performed using high-level local features such as scale invariant feature transform (SIFT) and speeded up robust feature (SURF). However, these methods suffer from false-positive association and high computational load to reject outliers. In this study, we introduce a novel global localization method based on the proposed low-frequency image-based descriptor (LFID) and laser range data. The image is first processed by reducing the range of luminance in the frequency domain. Visual features are then extracted from the processed image through a kernel window. These visual features are described as binary representation for fast association. Because this binary representation includes a spatial distribution of features, it can minimize false-positive association. Nevertheless, false-positive association could occur when scenes appear to be similar from different viewpoints. To address this problem, this study adopts a laser rangefinder to validate the similarity of the place and reject false-positives from the scene recognition. Experimental results confirm the effectiveness of the proposed scheme in actual indoor environments.

Discriminative Deep Feature Learning for Semantic-Based Image Retrieval

Semantic-based image retrieval plays an important role in many practical applications, which aims to look for images with similar contents. Extracting discriminative representations of images is the real crux of this task. Directly utilizing the results of fully connected layers of convolutional neural networks (CNNs) is one of the best feature extraction methods. However, the fully connected layer is only supervised by the softmax loss, which only aims to maximize the accuracy of object classification and hardly pays attention to the spatial distribution of features, especially the intra-class and inter-class feature distances which are of great importance in semantic-based image retrieval. To compensate the performance degradation due to this reason, we try to address the spatial distribution of the features by two different loss functions. The first loss function jointly combines the softmax loss and the center loss in the training of the CNNs, which simultaneously ensures that the features of images with different contents are separable and the features of images in the same class are close. The second loss function is defined as an improved center loss which not only penalizes the distance between the obtained deep feature and the feature center of its own class, but also encourages a far distance between the feature and the feature centers of any other classes. We have conducted experiments on both ILSVRC data set and Caltech256 data set, demonstrated that the deep features got by our approaches can achieve better performance than other methods in semantic-based image retrieval, and the improved center loss can further outperform the joint supervision of the softmax loss and the center loss.

The Influence of the Spatial Distribution of 2-D Features on Pose Estimation for a Visual Pipe Mapping Sensor

This paper considers factors which influence the visual motion estimation of a sensor system designed for visually mapping the internal surface of pipework using omnidirectional lenses. In particular, a systematic investigation of the error caused by a non-uniform 2-D spatial distribution of features on the resultant estimate of camera pose is presented. The effect of non-uniformity is known to cause issue and is commonly mitigated using techniques, such as bucketing; however, a rigorous analysis of this problem has not been carried out in the literature. The pipe’s inner surface tends to be uniform and texture poor driving the need to understand and quantify the feature matching process. A simulation environment is described in which the investigation was conducted in a controlled manner. Pose error and uncertainty is considered as a function of the number of correspondences and feature coverage pattern in the form of contiguous and equiangular coverage around a circular image acquired by a fisheye lens. It is established that beyond 16 feature matches between the images, that coverage is the most influential variable, with the equiangular coverage pattern leading to a greater rate of reduction in pose error with increasing coverage. The application of the results of the simulation to a real world data set is also provided.

Detection of Natural and Anthropic Features on Small Islands

ABSTRACT Cappucci, S.; Valentini, E.; Del Monte, M.; Paci, M.; Filipponi, F., and Taramelli, A., 2017. Detection of natural and anthropic features on small islands. In: Martinez, M.L.; Taramelli, A., and Silva, R. (eds.), Coastal Resilience: Exploring the Many Challenges from Different Viewpoints. Journal of Coastal Research, Special Issue No. 77, pp. 73–87. Coconut Creek (Florida), ISSN 0749-0208. Mapping the distribution of seabed habitats, and estimating the spatial distribution of features and biocenosis over land and the seafloor, is particularly important for the analysis of human impacts. The present paper uses an innovative image analysis method that integrates different data sources from airborne remote sensing and in situ measurements for different features, allowing the detection of ecological ‘tipping points’ both in emerged and submerged coastal environments. Results show that it is possible to differentiate between the respective roles of: first, the internal variability of the natural morph...

EEG-based mild depressive detection using feature selection methods and classifiers

Background and objectiveDepression has become a major health burden worldwide, and effectively detection of such disorder is a great challenge which requires latest technological tool, such as Electroencephalography (EEG). This EEG-based research seeks to find prominent frequency band and brain regions that are most related to mild depression, as well as an optimal combination of classification algorithms and feature selection methods which can be used in future mild depression detection. MethodsAn experiment based on facial expression viewing task (Emo_block and Neu_block) was conducted, and EEG data of 37 university students were collected using a 128 channel HydroCel Geodesic Sensor Net (HCGSN). For discriminating mild depressive patients and normal controls, BayesNet (BN), Support Vector Machine (SVM), Logistic Regression (LR), k-nearest neighbor (KNN) and RandomForest (RF) classifiers were used. And BestFirst (BF), GreedyStepwise (GSW), GeneticSearch (GS), LinearForwordSelection (LFS) and RankSearch (RS) based on Correlation Features Selection (CFS) were applied for linear and non-linear EEG features selection. Independent Samples T-test with Bonferroni correction was used to find the significantly discriminant electrodes and features. ResultsData mining results indicate that optimal performance is achieved using a combination of feature selection method GSW based on CFS and classifier KNN for beta frequency band. Accuracies achieved 92.00% and 98.00%, and AUC achieved 0.957 and 0.997, for Emo_block and Neu_block beta band data respectively. T-test results validate the effectiveness of selected features by search method GSW. Simplified EEG system with only FP1, FP2, F3, O2, T3 electrodes was also explored with linear features, which yielded accuracies of 91.70% and 96.00%, AUC of 0.952 and 0.972, for Emo_block and Neu_block respectively. ConclusionsClassification results obtained by GSW + KNN are encouraging and better than previously published results. In the spatial distribution of features, we find that left parietotemporal lobe in beta EEG frequency band has greater effect on mild depression detection. And fewer EEG channels (FP1, FP2, F3, O2 and T3) combined with linear features may be good candidates for usage in portable systems for mild depression detection.

The early impact of large wood introduction on the morphology and sediment characteristics of a lowland river

• Sediment properties are examined in five location types in a wood-restored channel. • Channels with restored large wood are morphologically more complex. • Sediment retained around restored large wood is finer and organic-rich. • Fine sediment retained around wood jams contains relatively more plant propagules. • Large wood is a potential self-restoration tool for degraded river channels. Habitat degradation in river ecosystems has considerably increased over the past decades, resulting in detrimental effects on aquatic and riparian communities. During the last two decades, the value of large wood as a resource for river restoration and recovery has been increasingly documented. However, post-project appraisal of the associations between restored large wood, morphological complexity and river ecology as a result of river restoration is extremely rare and thus scientific knowledge is essential. To investigate restored wood-induced morphological response and sediment complexity in an overwidened reach along a low gradient lowland river (River Bure, UK), two sub-reaches containing 12 jams initiated by wood emplacement in 2008 and 2010 and a sub-reach free of wood were studied. Wood surveys recording the dimensions and number of wood pieces in jams, geomorphological mapping of the reach illustrating the spatial distribution of features in and around the jams and in a section free of wood, and sediment sampling (analysed for particle size, organic content and plant propagule abundance) of five recurring patch types surrounding each jam (two wood-related patches and three representing the broader river environment) were performed. Wood jams partially spanned the river channel and contained large pieces of wood that created more open structures than naturally-formed wood jams. Where no wood was introduced, the channel remains wide and the gravel bed is buried by sand and finer sediment. In the restored reaches, fine sediment has accumulated in and around the wood jams and has been stabilised by vegetation colonisation, enhancing flow velocities in the narrowed channel sufficiently to mobilise fine sediment and expose the gravel bed. Sediment analysis reveals sediment fining with time since wood emplacement, largely achieved within the two wood-related patch types. Fine sediment retained around the wood shows a relatively higher plant propagule content than other patch types, suitable for sustaining plant succession as the vegetated side bars aggrade. Although channel narrowing and morphological adjustment has occurred surprisingly rapidly in this low energy, over-widened reach following wood introduction (2–4 years), sustaining the recovery in the longer term to suitably support flora and fauna communities depends on the continued delivery of wood by ensuring a natural supply of sufficiently large wood pieces from riparian trees both upstream and within the reach.

A graph kernel method for DNA-binding site prediction.

BackgroundProtein-DNA interactions play important roles in many biological processes. Computational methods that can accurately predict DNA-binding sites on proteins will greatly expedite research on problems involving protein-DNA interactions.ResultsThis paper presents a method for predicting DNA-binding sites on protein structures. The method represents protein surface patches using labeled graphs and uses a graph kernel method to calculate the similarities between graphs. A new surface patch is predicted to be interface or non-interface patch based on its similarities to known DNA-binding patches and non-DNA-binding patches. The proposed method achieved high accuracy when tested on a representative set of 146 protein-DNA complexes using leave-one-out cross-validation. Then, the method was applied to identify DNA-binding sties on 13 unbound structures of DNA-binding proteins. In each of the unbound structure, the top 1 patch predicted by the proposed method precisely indicated the location of the DNA-binding site. Comparisons with other methods showed that the proposed method was competitive in predicting DNA-binding sites on unbound proteins.ConclusionsThe proposed method uses graphs to encode the feature's distribution in the 3-dimensional (3D) space. Thus, compared with other vector-based methods, it has the advantage of taking into account the spatial distribution of features on the proteins. Using an efficient kernel method to compare graphs the proposed method also avoids the demanding computations required for 3D objects comparison. It provides a competitive method for predicting DNA-binding sites without requiring structure alignment.

Analysis and Evaluation of Tourism Climate Resources in Turpan Region

The article analyzes Turpan average temperature, relative humidity and wind speed the change characteristics of the climate elements and their travel to the comfort of climate influence mechanism and gets the conclusion: temperature, relative humidity, wind speed of Xinjiang tourism is the effect of climate comfort of main elements of sunshine. So from the average temperature, relative humidity, wind speed on average three climate elements start, select the suitable for Turpan tourism climate comfort evaluation index of the grain, and puts forward some concrete methods of tourism scenic area as part of the site, focus on the discussion were in Xinjiang tourism climate comfort of the temporal and spatial distribution of feature, make pleasant climate degrees in time and space more comparability. For the development of tourism resources, tourist season choice more objective and scientific guidance and practical. For the comfort of the climate in Turpan, it can arrange for the tour operator for tourism activities, visitors to choose the proper place and time travel and tourism destination development planning to provide the necessary guidance. It can also for the further development of the tourism industry in Turpan development space and offer scientific basis.

P.2.d.019 Prefrontal oscillation associated with randomised, placebo-controlled treatment with agomelatine and psychotherapy

Depression has become a major health burden worldwide, and effectively detection of such disorder is a great challenge which requires latest technological tool, such as Electroencephalography (EEG). This EEG-based research seeks to find prominent frequency band and brain regions that are most related to mild depression, as well as an optimal combination of classification algorithms and feature selection methods which can be used in future mild depression detection.An experiment based on facial expression viewing task (Emo_block and Neu_block) was conducted, and EEG data of 37 university students were collected using a 128 channel HydroCel Geodesic Sensor Net (HCGSN). For discriminating mild depressive patients and normal controls, BayesNet (BN), Support Vector Machine (SVM), Logistic Regression (LR), k-nearest neighbor (KNN) and RandomForest (RF) classifiers were used. And BestFirst (BF), GreedyStepwise (GSW), GeneticSearch (GS), LinearForwordSelection (LFS) and RankSearch (RS) based on Correlation Features Selection (CFS) were applied for linear and non-linear EEG features selection. Independent Samples T-test with Bonferroni correction was used to find the significantly discriminant electrodes and features.Data mining results indicate that optimal performance is achieved using a combination of feature selection method GSW based on CFS and classifier KNN for beta frequency band. Accuracies achieved 92.00% and 98.00%, and AUC achieved 0.957 and 0.997, for Emo_block and Neu_block beta band data respectively. T-test results validate the effectiveness of selected features by search method GSW. Simplified EEG system with only FP1, FP2, F3, O2, T3 electrodes was also explored with linear features, which yielded accuracies of 91.70% and 96.00%, AUC of 0.952 and 0.972, for Emo_block and Neu_block respectively.Classification results obtained by GSW + KNN are encouraging and better than previously published results. In the spatial distribution of features, we find that left parietotemporal lobe in beta EEG frequency band has greater effect on mild depression detection. And fewer EEG channels (FP1, FP2, F3, O2 and T3) combined with linear features may be good candidates for usage in portable systems for mild depression detection.

Light scattering by textured transparent electrodes for thin-film silicon solar cells

A model is presented to quantify key surface characteristics and simulate light scattering by textured transparent conducting oxides—an important class of materials for thin-film silicon (Si) solar cells. The characterization routine is solely based on the atomic force microscopy (AFM) height-encoded data and eliminates the need for time-consuming measurements of angle resolved scattering (ARS) and spectrally resolved scattering (SRS) of light. The presented method is intended for fast and precise inline monitoring of textured transparent electrodes for superstrate thin-film single- and tandem-junction Si solar cells in the production environment. Root-mean-square roughness, mean inclination angle and a fit parameter of three-dimensional Fast Fourier Transform (3D FFT) with the information on spatial feature distribution can be routinely measured with a high precision from a single AFM scan and are used to simulate both ARS and SRS dependencies. The model explains the observed difference in peak position and width of the ARS of surfaces with different morphologies. Special focus is on chemically textured aluminum-doped zinc oxide (AZO). Results on traditional monolithic AZO and new multi-layer stack designs are presented. The effect of an ‘insertion’ layer on light scattering properties and 3D FFT ‘fingerprints’ is also discussed.

Analysis of Feature Point Distributions for Fast Image Mosaicking Algorithms

In many algorithms the registration of image pairs is done by feature point matching. After the feature detection is performed, all extracted interest points are usually used for the registration process without further feature point distribution analysis. However, in the case of small and sparse sets of feature points of fixed size, suitable for real-time image mosaicking algorithms, a uniform spatial feature distribution across the image becomes relevant. Thus, in this paper we discuss and analyze algorithms which provide different spatial point distributions from a given set of SURF features. The evaluations show that a more uniform spatial distribution of the point matches results in lower image registration errors, and is thus more beneficial for fast image mosaicking algorithms.

Robust Affine Invariant Feature Extraction for Image Matching

A new approach is presented to extract more robust affine invariant features for image matching. The novelty of our approach is a hierarchical filtering strategy for affine invariant feature detection, which is based on information entropy and spatial dispersion quality constraints. The concept of spatial dispersion quality is introduced to quantify the spatial distribution of features. Moreover, an integrated algorithm combined by the filtering strategy, maximally stable extremal region (MSER) and scale invariant feature transform, is introduced for affine invariant feature extraction. Since Mikolajczyk et al. identified that MSER is the best detector in many cases, we design an experiment to compare our approach (ED-MSER) with the standard MSER. By using two stereo pairs and an image sequence with different types of imagery, the experiment indicates that ED-MSER can always get much higher repeatability and matching score compared to the standard MSER and other algorithms, thus benefiting the subsequent image matching and many other applications.

Predicting the Performance of Cooperative Simultaneous Localization and Mapping (C-SLAM)

In this paper we study the time evolution of the position estimates’ covariance in Cooperative Simultaneous Localization and Mapping (C-SLAM), and obtain analytical upper bounds for the positioning uncertainty. The derived bounds provide descriptions of the asymptotic positioning performance of a team of robots in a mapping task, as a function of the characteristics of the proprioceptive and exteroceptive sensors of the robots, and of the graph of relative position measurements recorded by the robots. A study of the properties of the Riccati recursion, which describes the propagation of uncertainty through time, yields (i) the guaranteed accuracy for a robot team in a given C-SLAM application, as well as (ii) the maximum expected steady-state uncertainty of the robots and landmarks, when the spatial distribution of features in the environment can be modeled by a known distribution. The theoretical results are validated both in simulation and experimentally.

RECOGNIZING PARTIALLY OCCLUDED OBJECTS USING MARKOV MODEL

A novel method to recognize occluded objects using Markov model is proposed in this paper. In addition to Markov model having a high tolerance to noise, spatial distribution of features can be incorporated into Markov model in a natural and elegant way. Thus, high recognition accuracy can be achieved by the proposed method. More specifically, for each occluded object in the scene image, its translation, rotation and scale parameters can all be determined by our method even when it may have transformation parameters different from others or it may be duplicated in the scene image with transformation parameters different from each other. Moreover, the recognition process can be performed step by step to find out all of the objects in the scene image according to the confidence measure. Finally, the recognition process can be terminated automatically without knowing the number of objects included in the scene image since hypothesis verification and termination test are performed in our method. Actually, the solution of our method is useful for depth-search applications such as inspection of printed circuit board with multiple layers, underwater diving for searching objects, underground drilling for exploring mine, etc. The proposed method has been applied on two types of databases: puzzle and tool. The effectiveness and practicability of the proposed approach have been proven by various experimental results.

Magnetic prospecting at a prehistoric and historic settlement in Maine

Magnetic surveys at a prehistoric and historic site in Maine were performed in order to improve understanding of cultural features identified from excavations that detailed cultural characteristics at discrete locations, but failed to define the geometry and extent of subsurface features. The objective of the magnetic work was to non-invasively define this spatial distribution of features. Such information is required to nominate both sites to the US National Register of Historic Places. Environmental and cultural factors in Maine favour the application of the magnetic method in archaeological prospecting. At the Spiller Farm palaeoamerican site, excavations had revealed a hearth and over 130 fragments of stone tools. The objective of the magnetic survey was to define additional hearths and cultural material within the vicinity. Measurements were made on a 45 by 25 m grid at 1 m intervals. Signal processing improved definition of a +50 nT anomaly that, upon partial excavation, was found to be associated with a sizeable burnt feature. Laminations in the excavated feature, combined with an increase in palaeo-artefact counts around it, indicate that the feature is a palaeo-hearth, rather than a natural burnt feature. At the Fort Hill historic site, previous excavations revealed a hearth, stone debris related to the fort foundations and numerous historic artefacts but did not resolve the fort geometry. Magnetic measurements were performed on a 55 by 45 m grid at 1 m intervals. Linear anomalies (+20 nT) were interpreted primarily as the response to residual metal in the fort foundations. The geometry of the fort and the meeting house, known to exist from historic accounts, were directly inferred from the survey. The hearth location and artefact distribution correlate well with the magnetic data. The dimensions of the fort (41 by 19 m) were found to be considerably larger than that expected from historic references. Copyright © 2000 John Wiley & Sons, Ltd.

Spatial analysis of the Nenumbo (SE‐RF‐2) Lapita site, Solomon Islands

AbstractData on the spatial distribution of features, pottery, lithic materials, fishbones and shellfish are used to examine spatial organization in the SE‐RF‐2 Lapita site (Reef Islands, Southeast Solomons). It is shown that the site is at most a small hamlet and consisted of a large rectilinear central structure with an adjacent cooking area. It is argued that the distribution of imports (pottery, chert, obsidian) with different transport costs cannot be explained in simple economic terms and that their movement was embedded in a set of important social relations.

A bathymetric reappraisal of Loch Muick, Aberdeenshire

Abstract A new bathymetrical survey of Loch Muick, using a recording echosounder coupled with precision radio position‐fixing incorporates data from a dense traverse network of 54.78 km of survey lines. A detailed chart, contoured at 1 m intervals, and constructed with the aid of a digitiser and computer‐graphics package, reveals many subaqueous landforms. Four ‘morphological provinces’, established on the basis of ridge and basin floor topography are identified. The spatial distribution of features within these provinces concurs with earlier suggestions of Late Glacial activity in the Loch Muick basin. The confluence of the tributary Black Burn glacier with the main Glen Muick glacier and further down‐valley extension of the ice limits are adduced.

Measurement of feature clustering in images

The spatial distribution of features in an image is often interesting, but not simple to characterize. Mapping of the image into a different space (e.g., Fourier or Hough) offers direct information on various regularities in feature spacing or alignment, but does not deal directly with the individual features. Two other approaches are available; each has advantages and drawbacks, which are discussed here.Schwarz & Exner determine the spatial coordinates of the centroids of features, and sort them to locate the nearest neighbor for each feature present, constructing a distribution plot of the frequency of nearest neighbor distances. Figures 1 and 2 show an example. The three fields in Figure 1 contain, respectively, features which are well-spaced from each other, randomly arranged on the plane, and clustered together. For the random distribution of points, the histogram of nearest neighbor distances is a Poisson distribution, and the mean value is 0.5/NA1/2, where NA is the number of features divided by the area of the image.