Spatially Segmented Research Articles

A Priori Spatial Segmentation of Commercial Property Market using Hedonic Price Modelling

Abstract The improvement of property price modelling accuracy using property market segmentation approaches is well documented in the housing market. However, that cannot be said of the commercial property market which is adjudged to be volatile, heterogeneous and thinly traded. This study, therefore, determines if the commercial property market in Malaysia is spatially segmented into submarkets and whether accounting for the submarkets improves the accuracy of price modelling. Using a 11,460 shop-offices transaction dataset, the commercial property submarkets are delineated by using submarket binary dummies in the market-wide model and estimating a separate hedonic model for each submarket. The former method improves the model fit and reduces error by 5.6% and 6.5% respectively. The commercial property submarkets are better delineated by estimating a separate hedonic model for each submarket as it improves the model fit by about 7% and reduces models’ error by more than 10%. This study concludes that the Malaysian commercial property market is spatially segmented into submarkets. Modelling the submarkets improves the accuracy and correctness of price modelling.

Entropy feature and peak-means clustering based slowly moving object detection in head and shoulder video sequences

With the increase in demand for video conferencing and IOT applications, efficient video coding standards are necessary. The performance of MPEG-4 coding scheme depends on the efficiency of the video object plane (VOP) generation methods. In head and shoulder video, such as news reading, video conferencing video sequences, the object has a very little movement in between two consecutive frames. Therefore, traditional segmentation methods could not extract the complete VOP efficiently. In this paper, we propose an efficient spatiotemporal segmentation method to extract the moving object for the generation of VOP in head and shoulder video sequences. First, a motion map of the object at each frame is generated based on the entropy of the temporal change of each pixel. Secondly, each frame is spatially segmented based on peak-means clustering approach. Finally, both motion map and spatial segmentation information are fused to extract the complete shape of the slow moving object. Experimental outcome depicts that the proposed method has highest detection accuracy with average intersection of union (IOU) score of 94.32% per frame and F1 measure of 97.75% per frame.

The Effect of Spatially and Temporally Modulated Plasma Actuation on Cylinder Wake

The wake of a circular cylinder was forced with a temporally modulated and spatially segmented dielectric-barrier-discharge plasma actuator. The temporal modulation was achieved by modulating the applied voltage signal with a square wave whose frequency was twice the vortex shedding frequency. The spatial segmentation was implemented by locating the buried electrodes only at certain spanwise locations along the cylinder in a square-wave pattern. Two blowing ratios (BRs), namely and 0.6, were implemented. In the case of , vortex shedding was significantly attenuated, and the frequencies of the most prominent peaks in the spectra of velocity fluctuations were considerably different along the span. Moreover, the subharmonic mode was found to be stronger behind the non-plasma-forming region compared to the plasma-forming region during forcing with . It also resulted in less drag compared to the unforced case. In the case of , the unsteadiness and the velocity defect in the wake increased compared to the unforced case. Finally, the performance of the segmented actuator was compared with a straight two-dimensional actuator by maintaining the same induced velocity. In this case, a “W”-shaped velocity profile was obtained during both the low- and high-power forcing. Modulated forcing with the straight actuator increased the drag compared to the unforced case.

Studying vocal fold non-stationary behavior during connected speech using high-speed videoendoscopy

Studying voice production during running speech can provide new knowledge about the mechanisms of voice production with and without disorder. Laryngeal high-speed videoendoscopy (HSV) systems are powerful tools for studying laryngeal function and, if coupled with flexible fiberoptic endoscopes, they can provide unique possibilities to measure vocal fold vibration with high temporal resolution during connected speech. Hence, we can measure the non-stationary behaviors of the vocal folds, such as the glottal attack and offset times in running speech. In this study, a custom-built flexible fiberoptic HSV system was used to record a “Rainbow Passage” production from a vocally normal female. Automated temporal and spatial segmentation algorithms were developed to determine the time stamps of the vibrating vocal folds and the edges of the vocal folds during phonation. The glottal attack time and offset times were then measured from the temporally and spatially segmented HSV images. The amplification ratio was computed during the phonation onset and the damping ratio was calculated at the offset of sustained portion of phonation. These measures can be used to describe the laryngeal mechanisms of voice production in connected speech.

Image denoising based on adaptive spatial segmentation and multi-scale correlation in directionlet domain

Directionlet transform DT has become popular over the last few years as an efficient image representation tool due to its fine frequency tiling and directional vanishing moments along any two directions. A novel denoising algorithm based on DT is proposed here for images corrupted with Gaussian noise. The image is first spatially segmented based on the content directionality. Then an undecimated version of DT is applied to effectively capture the directional features and edge information of these segments. The DT coefficients so obtained are then modelled using a bivariate heavy tailed Gaussian distribution and the noise free coefficients are computed using MAP estimator. By employing bivariate probability distribution, the heavy-tail behaviour of natural images is accurately modelled and the interscale properties of DT coefficients are properly exploited. In addition, the local variance parameter of the model is estimated based on classification of DT coefficients within a particular scale using context modelling. Due to this the intrascale dependency of the directionlet coefficients is also well exploited in the enhancement process. The proposed algorithm is competitive with the existing algorithms with better results in terms of output peak signal-to-noise ratio while having comparable computational complexity. It exhibits good capability to preserve edges, contours and textures especially in images with abundant high frequency contents.

Spatial segmentation of MALDI FT-ICR MSI data: a powerful tool to explore the head and neck tumor in situ lipidome.

Matrix-assisted laser desorption/ionization mass spectrometric imaging (MALDI MSI) is a well-established analytical technique for determining spatial localization of lipids in biological samples. The use of Fourier-transform ion cyclotron resonance (FT-ICR) mass spectrometers for the molecular imaging of endogenous compounds is gaining popularity, since the high mass accuracy and high mass resolving power enables accurate determination of exact masses and, consequently, a more confident identification of these molecules. The high mass resolution FT-ICR imaging datasets are typically large in size. In order to analyze them in an appropriate timeframe, the following approach has been employed: the FT-ICR imaging datasets were spatially segmented by clustering all spectra by their similarity. The resulted spatial segmentation maps were compared with the histologic annotation. This approach facilitates interpretation of the full datasets by providing spatial regions of interest. The application of this approach, which has originally been developed for MALDI-TOF MSI datasets, to the lipidomic analysis of head and neck tumor tissue revealed new insights into the metabolic organization of the carcinoma tissue.

Moving object detection using Markov Random Field and Distributed Differential Evolution

In this article, we present an algorithm for detecting moving objects from a given video sequence. Here, spatial and temporal segmentations are combined together to detect moving objects. In spatial segmentation, a multi-layer compound Markov Random Field (MRF) is used which models spatial, temporal, and edge attributes of image frames of a given video. Segmentation is viewed as a pixel labeling problem and is solved using the maximum a posteriori (MAP) probability estimation principle; i.e., segmentation is done by searching a labeled configuration that maximizes this probability. We have proposed using a Differential Evolution (DE) algorithm with neighborhood-based mutation (termed as Distributed Differential Evolution (DDE) algorithm) for estimating the MAP of the MRF model. A window is considered over the entire image lattice for mutation of each target vector of the DDE; thereby enhancing the speed of convergence. In case of temporal segmentation, the Change Detection Mask (CDM) is obtained by thresholding the absolute differences of the two consecutive spatially segmented image frames. The intensity/color values of the original pixels of the considered current frame are superimposed in the changed regions of the modified CDM to extract the Video Object Planes (VOPs). To test the effectiveness of the proposed algorithm, five reference and one real life video sequences are considered. Results of the proposed method are compared with four state of the art techniques and provide better spatial segmentation and better identification of the location of moving objects.

Entropy based region selection for moving object detection

This article addresses a problem of moving object detection by combining two kinds of segmentation schemes: temporal and spatial. It has been found that consideration of a global thresholding approach for temporal segmentation, where the threshold value is obtained by considering the histogram of the difference image corresponding to two frames, does not produce good result for moving object detection. This is due to the fact that the pixels in the lower end of the histogram are not identified as changed pixels (but they actually correspond to the changed regions). Hence there is an effect on object background classification. In this article, we propose a local histogram thresholding scheme to segment the difference image by dividing it into a number of small non-overlapping regions/windows and thresholding each window separately. The window/block size is determined by measuring the entropy content of it. The segmented regions from each window are combined to find the (entire) segmented image. This thresholded difference image is called the change detection mask (CDM) and represent the changed regions corresponding to the moving objects in the given image frame. The difference image is generated by considering the label information of the pixels from the spatially segmented output of two image frames. We have used a Markov Random Field (MRF) model for image modeling and the maximum a posteriori probability (MAP) estimation (for spatial segmentation) is done by a combination of simulated annealing (SA) and iterated conditional mode (ICM) algorithms. It has been observed that the entropy based adaptive window selection scheme yields better results for moving object detection with less effect on object background (mis) classification. The effectiveness of the proposed scheme is successfully tested over three video sequences.

Modified Maximum Likelihood Classifications of Urban Land Use: Spatial Segmentation of Prior Probabilities

A technique for improving the classification of urban land use by modifying the standard maximum likelihood discriminant function within spatially segmented urban parameters is introduced. The methodology examines how population census data can be used to modify prior probabilities, not at the global or regional scales, but at the intra‐urban local level. This involves spatial segmentation of a Landsat TM image by areal census collection boundaries from which prior probabilities are generated with respect to varying proportions of three housing types. Consistent improvements over classifications produced by standard equal prior probabilities are evident on four settlements in southwest England. Total absolute error is lower under modified prior probabilities, but no one housing type has consistently lower area estimation error. Evidence suggests that high density housing is under‐estimated (less pixels classified), and conversely that low density housing is over‐estimated (more pixels classified).

Modeling of Phytoplankton in Saginaw Bay: I. Calibration Phase

A deterministic, spatially segmented, multi‐class phytoplankton model is calibrated to an extensive set of field data acquired on Saginaw Bay, Lake Huron, during 1974 and 1975. Significant differences between observed mean values from the field data, and mean values computed by the model, are determined using a simple Student's t test. For the final calibration results, there are no significant differences between model output and field data for 86% of the sampling cruises in the principal spatial segments. Seasonal mean values between model output and field data are also compared because the hydrological and productivity cycles in the bay are characterized by distinct seasonal patterns. Discrepancies occur for water column total phosphorus concentrations because they appear to be strongly influenced by wind‐induced sediment resuspension. The resuspension mechanism in the calibrated model accounts for 36 and 68%, respectively, of the computed spring and fall average total phosphorus concentrations.