Search results

Conventional image super-resolution reconstruction by the conventional deep learning architectures suffers from the problems of hard training and gradient disappearing. In order to solve such problems, the purpose of this paper is to propose a novel image super-resolution algorithm based on improved generative adversarial networks (GANs) with Wasserstein distance and gradient penalty.

The proposed algorithm first introduces the conventional GANs architecture, the Wasserstein distance and the gradient penalty for the task of image super-resolution reconstruction (SRWGANs-GP). In addition, a novel perceptual loss function is designed for the SRWGANs-GP to meet the task of image super-resolution reconstruction. The content loss is extracted from the deep model’s feature maps, and such features are introduced to calculate mean square error (MSE) for the loss calculation of generators.

To validate the effectiveness and feasibility of the proposed algorithm, a lot of compared experiments are applied on three common data sets, i.e. Set5, Set14 and BSD100. Experimental results have shown that the proposed SRWGANs-GP architecture has a stable error gradient and iteratively convergence. Compared with the baseline deep models, the proposed GANs models have a significant improvement on performance and efficiency for image super-resolution reconstruction. The MSE calculated by the deep model’s feature maps gives more advantages for constructing contour and texture.

Compared with the state-of-the-art algorithms, the proposed algorithm obtains a better performance on image super-resolution and better reconstruction results on contour and texture.

This paper aims to provide insight into mediation as an Alternative Dispute Resolution (ADR) to resolve interpersonal conflicts for undergraduate students in Hong Kong.

Mixed methods research approach was utilised to examine university students' understanding of dispute resolution at their respective universities in Hong Kong, and factors that may influence their decision to utilize ADR on campus.

The tendency for university students in Hong Kong to voice criticisms was low due to: (1) unawareness of proper grievance channels; and (2) fear of potential academic retribution from the institution. This may be the result of inadequate promotion and transparency in the existing higher education dispute resolution framework. Academic staff acknowledged the limitation of the existing closed-door dispute resolution system and the need for an alternative conflict management system which emphasises on restoration of harmony in the university community.

As there is a lack of study focusing on ADR practices in Hong Kong universities, this paper provides insight into the feasibility of integrating ADR into the existing dispute resolution processes in resolving interpersonal conflicts at universities in Hong Kong.

The purpose of this paper is to collect data from humans as they generate insights from the visualised results of computational fluid dynamics (CFD) scientific simulation. The authors hypothesise the behaviour of their insight errors (IEs) and proceed to quantify the IEs provided by the crowd participants. They then use the insight framework to model the behaviours of the errors. Using the crowd responses and models from the framework, they test the hypotheses and use the results to validate the framework for the speedup of CFD applications.

The authors use a randomised between-subjects experiment with blocking. CFD grid resolution is the independent variable while IE is the dependent variable. The experiment has one treatment factor with five levels. In case varying timestamps has an effect on insight variance levels, the authors block the responses by timestep. In total, 150 participants are randomly assigned to one of five groups and also randomly assigned to one of five blocks within a treatment. Participants are asked to complete a benchmark and open-ended task.

The authors find that the variances of insight and perception errors have a U-shaped relationship with grid resolution, that similar to the previously studied visualisation applications, the IE framework is valid for insights generated from CFD results and grid resolution can be used to predict the variance of IE resulting from observing CFD post-processing results.

To the best of the authors’ knowledge, no other work has measured IE variance to present it to simulation users so that they can use it as a feedback metric for selecting the ideal grid resolution when using grid resolution to speedup CFD simulation.

The purpose of this paper is to investigate the influence of the resolution with which interfaces of fractal geometry are represented, on the contact area and consequently on the contact interfacial stresses. The study is based on a numerical approach. The paper focuses on the differences between the cases of elastic and inelastic materials having as primary parameter the resolution of the interface.

A multi‐resolution parametric analysis is performed for fractal interfaces dividing a plane structure into two parts. On these interfaces, unilateral contact conditions are assumed to hold. The computer‐generated surfaces adopted here are self‐affine curves, characterized by a precise value of the resolution δ of the fractal set. Different contact simulations are studied by applying a horizontal displacement s on the upper part of the structure. For every value of s, a solution is taken in terms of normal forces and displacements at the interface. The procedure is repeated for different values of the resolution δ. At each scale, a classical Euclidean problem is solved by using finite element models. In the limit of the finest resolution, fractal behaviour is achieved.

The paper leads to a number of interesting conclusions. In the case of linear elastic analysis, the contact area and, consequently, the contact interfacial stresses depend strongly on the resolution of the fractal interface. Contrary, in the case of inelastic analysis, this dependence is verified only for the lower resolution values. As the resolution becomes higher, the contact area tends to become independent from the resolution.

The originality of the paper lies on the results and the corresponding conclusions obtained for the case of inelastic material behaviour, while the results for the case of elastic analysis verify the findings of other researchers.

Satellite images can be a powerful source of data for analyses of conflict dynamics and social movements, but sociology has been slow to develop methods and metadata standards for transforming those images into data. We ask: How can satellite images become useful data? What are the key methodological and ethical considerations for incorporating high-resolution satellite images into conflict research? Why are metadata important in this work? We begin with a review of recent developments in satellite-based social scientific work on conflict, then discuss the technical and epistemological issues raised by machine processing of satellite information into user-ready images. We argue that high-resolution images can be useful analytical tools provided they are used with full awareness of their ethical and technical parameters. To support our analysis, we draw on two novel studies of satellite data research practices during the Syrian war. We conclude with a discussion of specific methodological procedures tried and tested in our ongoing work.

A major key success factor regarding proficient Bayes threshold denoising refers to noise variance estimation. This paper focuses on assessing different noise variance estimations in three Bayes threshold models on two different characteristic brain lesions/tumor magnetic resonance imaging (MRIs).

Here, three Bayes threshold denoising models based on different noise variance estimations under the stationary wavelet transforms (SWT) domain are mainly assessed, compared to state-of-the-art non-local means (NLMs). Each of those three models, namely D1, GB and DR models, respectively, depends on the most detail wavelet subband at the first resolution level, on the entirely global detail subbands and on the detail subband in each direction/resolution. Explicit and implicit denoising performance are consecutively assessed by threshold denoising and segmentation identification results.

Implicit performance assessment points the first–second best accuracy, 0.9181 and 0.9048 Dice similarity coefficient (Dice), sequentially yielded by GB and DR; reliability is indicated by 45.66% Dice dropping of DR, compared against 53.38, 61.03 and 35.48% of D1 GB and NLMs, when increasing 0.2 to 0.9 noise level on brain lesions MRI. For brain tumor MRI under 0.2 noise level, it denotes the best accuracy of 0.9592 Dice, resulted by DR; however, 8.09% Dice dropping of DR, relative to 6.72%, 8.85 and 39.36% of D1, GB and NLMs is denoted. The lowest explicit and implicit denoising performances of NLMs are obviously pointed.

A future improvement of denoising performance possibly refers to creating a semi-supervised denoising conjunction model. Such model utilizes the denoised MRIs, resulted by DR and D1 thresholding model as uncorrupted image version along with the noisy MRIs, representing corrupted version ones during autoencoder training phase, to reconstruct the original clean image.

This paper should be of interest to readers in the areas of technologies of computing and information science, including data science and applications, computational health informatics, especially applied as a decision support tool for medical image processing.

In most cases, DR and D1 provide the first–second best implicit performances in terms of accuracy and reliability on both simulated, low-detail small-size region-of-interest (ROI) brain lesions and realistic, high-detail large-size ROI brain tumor MRIs.

The problems of Super resolution are broadly discussed in diverse fields. Rather than the progression toward the super resolution models for real-time images, operating hyperspectral images still remains a challenging problem.

This paper aims to develop the enhanced image super-resolution model using “optimized Non-negative Structured Sparse Representation (NSSR), Adaptive Discrete Wavelet Transform (ADWT), and Optimized Deep Convolutional Neural Network”. Once after converting the HR images into LR images, the NSSR images are generated by the optimized NSSR. Then the ADWT is used for generating the subbands of both NSSR and HRSB images. The residual image with this information is obtained by the optimized Deep CNN. All the improvements on the algorithms are done by the Opposition-based Barnacles Mating Optimization (O-BMO), with the objective of attaining the multi-objective function concerning the “Peak Signal-to-Noise Ratio (PSNR), and Structural similarity (SSIM) index”. Extensive analysis on benchmark hyperspectral image datasets shows that the proposed model achieves superior performance over typical other existing super-resolution models.

From the analysis, the overall analysis of the suggested and the conventional super resolution models relies that the PSNR of the improved O-BMO-(NSSR+DWT+CNN) was 38.8% better than bicubic, 11% better than NSSR, 16.7% better than DWT+CNN, 1.3% better than NSSR+DWT+CNN, and 0.5% better than NSSR+FF-SHO-(DWT+CNN). Hence, it has been confirmed that the developed O-BMO-(NSSR+DWT+CNN) is performing well in converting LR images to HR images.

This paper adopts a latest optimization algorithm called O-BMO with optimized Non-negative Structured Sparse Representation (NSSR), Adaptive Discrete Wavelet Transform (ADWT) and Optimized Deep Convolutional Neural Network for developing the enhanced image super-resolution model. This is the first work that uses O-BMO-based Deep CNN for image super-resolution model enhancement.

EBT2 film, a convenient quality assurance (QA) tool with high 2D dosimetry resolution, has been widely used in the dosimetry application of radiation therapy with lots of benefits especially its self-development, water equivalent, energy independent and high spatial resolution. However, the higher inhomogeneity between the pixels of EBT2 image, needed to be averaged out according to the traditional method, but it could sacrifice the spatial resolution. To solve this problem, the purpose of this paper is to introduce a Wiener filter (WF) technique applied with a multi-channel (MC) method.

The EBT2 film was calibrated by using the percentage depth dose method combined with the WF technique and a MC method. Then the calculated film doses were compared with the measurement doses by the edge detector with the water phantom.

With high spatial resolution to be 0.2 mm, the results demonstrate that the EBT2 film calibration through both of the WF technique and MC method has higher accuracy (within 2 percent) and lower uncertainty.

A new technique of WF with MC method was presented to calibrate the dosimetry system of EBT2 film. With high spatial resolution (0.2 mm), the studies show that the combination of WF technique with MC method can have high accuracy with low noises to calibrate EBT2 film. This method can also be applied to all the QAs of treatment planning of radiation therapy by using the EBT2 film.

Drawing on information processing theory, the linkage between buffering and bridging and the ability on the part of procurement to resolve demand–supply imbalances is investigated, as well as contexts in which these strategies may be particularly useful or detrimental. Buffering may be achieved through demand change or redundancy, while bridging may be achieved by the means of collaboration or monitoring.

This study employs a hierarchical regression analysis of a survey of 150 Finnish and Swedish procurement and sales and operations planning professionals, each responding from the perspective of their own area of supply responsibility.

Both the demand change and redundancy varieties of buffering are associated with procurement's ability to resolve demand–supply imbalances without delivery disruptions, but not with cost-efficient resolution. Bridging is associated with the cost-efficient resolution of imbalances: while collaboration offers benefits, monitoring seems to make things worse. Dynamism diminishes, while the co-management of procurement in S&OP improves procurement's ability to resolve demand–supply imbalances. The most potent strategy for tackling problematic contexts appears to be buffering via demand change.

The results highlight the importance of procurement in the S&OP process and suggest tactical measures that can be taken to resolve and reduce the effects of supply and demand imbalances.

The results contribute to the procurement and S&OP literature by increasing knowledge regarding the role and integration of procurement to the crucial process of balancing demand and supply operations.

This paper aims to explore the influence of entrepreneur’s political involvement on private-own enterprises’ (POEs’) selection of two inter-organizational conflict resolutions approaches (private approach and public approach), in the context of China’s transition economy.

Drawing on a sample of POEs operating in China’s transition economy in the year 2000, this study investigates the possible association between the entrepreneur’s political involvement and the approach chosen to resolve inter-organizational conflicts. A further step is taken to look into the implications of such a choice.

The empirical study reveals that those POEs with greater entrepreneurial political involvement have the propensity to rely on public approach. In general, POEs are more satisfied with the private approach than the public approach when managing conflicts. Besides, the study shows that the positive effects derived from the entrepreneur’s satisfaction on private approach will be weakened in more established institutions.

This paper has its unique contribution in highlighting the significance of how entrepreneurs’ political involvement interferes with inter-organizational conflict resolution.