Mismatch Problem Research Articles

Research on virtual color restoration algorithm for printmaking art images based on semantic segmentation and convolutional neural network

Abstract In this paper, semantic segmentation based on a convolutional neural network is used to guide the image color restoration process. In order to avoid the problem of content mismatch, higher-order features are first extracted from the basic dimensions of the input image, and the convolutional operation is done on the feature map by the excitation function. Then the network parameters are optimized and updated by the backpropagation algorithm to minimize the error between the prediction result and the real result. Finally, in image processing, the dilated convolution technique is introduced to perform noise reduction on the semantic segmented image pixels to optimize the restoration quality. In order to prove the effectiveness of the method in this paper, an experimental analysis of the method is conducted. The experimental results show that the peak signal-to-noise ratio of the model proposed in this paper is higher than 42.986db on average, the structural similarity reaches 0.8%, and the fit is around 0.75. And its color difference can reach at least 11.2% with the increase of iterations. It indicates that the reduction algorithm of semantic segmentation and convolutional neural network greatly improves the accuracy of color reduction results and can obtain printmaking images with higher color quality.

Design optimization of energy systems for zero energy buildings based on grid-friendly interaction with smart grid

Zero-energy buildings usually achieve annual net-zero energy balance by generating electricity using on-site renewable energies and interconnecting with the power grid. However, the impact of energy mismatch problem in zero-energy buildings design on the grid is often overlooked, which potentially compromises grid's stability. To address this issue, this paper presents an optimization design method based on "grid-friendly interaction" which optimizes the energy system of zero-energy buildings to ensure better alignment between the building's electricity purchase/sale and grid demand. In this study, an indicator of "grid-friendly interaction", which represents the ratio of the net building friendly interaction power to the total annual interaction power, is firstly established to guide buildings in improving their interaction with the grid. Next, the energy supply, demand, and storage schemes of renewable energy systems in the zero-energy building are iteratively adjusted to achieve the best match with grid's expectations. This optimization design method was applied to a practical case in Hong Kong. Results show that, compared to the benchmark building, the optimal system design scheme increases grid friendliness by 83 %, reduces carbon dioxide emissions by 77 %, but also incurs a total cost increase of 180 %. The optimization design method proposed in this paper can effectively mitigate the impact of zero-energy buildings on the power grid, fostering enhanced interplay between the building structures and the grid. The study significantly contributes to the advancement of exploring the potential for energy flexibility in zero-energy buildings, which is of great significance for the safe and stable operation of future grids. The purpose of this study is to explore the energy flexibility potential of zero-energy buildings, which is of great significance for the safe and stable operation of future grids.

Robust Adaptive Beamformer Based on Constant Modulus Penalty Criteria

In this study, a robust adaptive beamformer based on constant modulus (CM) criteria is developed to improve the robustness of the array beamforming, which is a reconstructing minimal optimization for solving the mismatch problem of weight vector caused by steering vector mismatch. In the global positioning system (GPS) L1 band, firstly, a GPS array signal is modelled by designing a dual-polarized antenna array. Secondly, the distortion problem of beamforming is formulated in the traditional minimum variance distortionless response (MVDR) beamformer. For repairing the weight vector mismatch problem, a novel beamformer based on the CM envelope response is proposed to reconstruct MVDR beamforming in the array processing. Besides, min-max penalty criteria are used to enable the beamformer to allocate more degrees of freedom (DOFs) when penalizing the MVDR beamformer responses. Finally, an auxiliary two-element real variable is designed to plan the proposed beamformer. But it is still a nonconvex quadratic programming problem, so an alternating direction method of multipliers (ADMM) is employed to transform the objective function into several subproblems. Illustrative numerical simulation results are provided for validating the effectiveness of the proposed beamformer by comparing it with other existing approaches.

Automatic Loss Function Search for Adversarial Unsupervised Domain Adaptation

Unsupervised domain adaption (UDA) aims to reduce the domain gap between labeled source and unlabeled target domains. Many prior works exploit adversarial learning that leverages pre-designed discriminators to drive the network for aligning distributions between domains. However, most of them do not consider the degeneration of the domain discriminators caused by the gradually dominating gradients of aligned target samples during training, and they still suffer from the cross-domain semantic mismatch problem in the learned feature space. Hence, this paper attempts to understand and solve both issues from the lens of optimization loss and propose an automatic loss function search for adversarial domain adaptation (ALSDA). First, we extend the common adversarial loss by adding an adjustable hyper-parameter that can re-weight the gradients assigned to target samples, so that the domain discriminator can impose consecutive and influential driving forces for domain alignment. Meanwhile, we upgrade the traditional orthogonality loss with class-wisely adjustable hyper-parameters that can strengthen the cross-domain feature separation. Since manually determining the optimal loss functions requires expensive expert efforts, we leverage the popular AutoML to automatically search for the optimal loss functions from a pre-defined novel and unique search space for UDA. Further, to enable the loss function search when the target domain is unlabeled, we introduce a simple-but-effective entropy-guided search strategy with the aid of REINFORCE learning. Extensive experiments on various typical baselines and benchmark datasets such as Office-Home, Office-31, and Birds-31 have been conducted, and the results validate the generalization and superiority of the proposed ALSDA.

Shift-variant deconvolution beamforming using Implicit Neural Representation for near-field acoustic image measurement

The conventional beamforming (CBF) output can be expressed as a convolution of the source distribution and the array dependent point spread function (PSF), which is defined as the response of the beamformer to a point source. The resolution and accuracy of sound source localization can be improved by deconvolution of CBF. The shift-invariant PSF assumption is only a good approximation when the source region is small compared to the distance between the array and the source. However, the PSF of the near-field underwater acoustic map measurement is shift-variant, whose mismatch with the beam could lead to performance degradation. In this paper, we proposed an optimized deconvolution method by using the neural network called implicit neural representation (INR) to solve the beam mismatch problem, due to its strong performance in learning and reconstructing spatial scenes. Rather than recompute the PSF for each pixel in the scene, INR predicts the complex-valued weight matrix in two-dimensional space that encapsulates both the spatially varying properties of the PSF and the scatter distribution of the scene. Numerical simulations and experimental results verify the effectiveness of our method. And this work can be broadly applied to arrays with shift-variant PSFs.

A Systematic Review of Automated Query Reformulations in Source Code Search

Fixing software bugs and adding new features are two of the major maintenance tasks. Software bugs and features are reported as change requests. Developers consult these requests and often choose a few keywords from them as an ad hoc query. Then they execute the query with a search engine to find the exact locations within software code that need to be changed. Unfortunately, even experienced developers often fail to choose appropriate queries, which leads to costly trials and errors during a code search. Over the years, many studies have attempted to reformulate the ad hoc queries from developers to support them. In this systematic literature review, we carefully select 70 primary studies on query reformulations from 2,970 candidate studies, perform an in-depth qualitative analysis (e.g., Grounded Theory), and then answer seven research questions with major findings. First, to date, eight major methodologies (e.g., term weighting, term co-occurrence analysis, thesaurus lookup) have been adopted to reformulate queries. Second, the existing studies suffer from several major limitations (e.g., lack of generalizability, the vocabulary mismatch problem, subjective bias) that might prevent their wide adoption. Finally, we discuss the best practices and future opportunities to advance the state of research in search query reformulations.

Computation-guided design of flexible piezoelectric composites by optimizing charge-stress transmission

Flexible piezoelectric materials have attracted increasing attention as active components in wearable and flexible electronics, soft robotics and artificial skins or muscles. Although constructing polymer-based composites is becoming a common solution to balance their piezoelectricity and flexibility, challenges associated with the electrical and mechanical mismatch between the polymer matrix and the ceramic fillers remain. Here, taking the piezoelectric composite of lead zirconate titanate-polydimethylsiloxane (PZT/PDMS) as the example, we perform phase-field simulations to spatially and temporally study the electrical and mechanical response. It is found that good connectivity of fillers could provide a load transfer path and break topological restriction of filler morphology on polarization dipoles. Then, we propose an interface design strategy to address the mismatch problem in ‘3–3’ composites, which could greatly enhance the overall piezoelectric response under different modes of compressing, stretching and bending. Finally, we experimentally fabricate high-performance flexible composites with an ultrahigh piezoelectric charge coefficient of 155 pC N−1 and a low Young’s modulus of 63 MPa. This research offers a promising route for designing flexible piezoelectric composites by synergistically regulating connectivity and mismatch problems, which is also expected to guide the optimization of other actuators or sensors related with electromechanical coupling effect.

Machine Translation of Electrical Terminology Constraints

In practical applications, the accuracy of domain terminology translation is an important criterion for the performance evaluation of domain machine translation models. Aiming at the problem of phrase mismatch and improper translation caused by word-by-word translation of English terminology phrases, this paper constructs a dictionary of terminology phrases in the field of electrical engineering and proposes three schemes to integrate the dictionary knowledge into the translation model. Scheme 1 replaces the terminology phrases of the source language. Scheme 2 uses the residual connection at the encoder end after the terminology phrase is replaced. Scheme 3 uses a segmentation method of combining character segmentation and terminology segmentation for the target language and uses an additional loss module in the training process. The results show that all three schemes are superior to the baseline model in two aspects: BLEU value and correct translation rate of terminology words. In the test set, the highest accuracy of terminology words was 48.3% higher than that of the baseline model. The BLEU value is up to 3.6 higher than the baseline model. The phenomenon is also analyzed and discussed in this paper.

State estimation for one‐dimensional agro‐hydrological processes with model mismatch

AbstractThe importance of accurate soil moisture data for the development of modern closed‐loop irrigation systems cannot be overstated. Due to the diversity of soil, it is difficult to obtain an accurate model for the agro‐hydrological system. In this study, soil moisture estimation in one‐dimensional (1D) agro‐hydrological systems with model mismatch is the focus. To address the problem of model mismatch, a nonlinear state‐space model derived from the Richards equation is utilized, along with additive unknown inputs. The determination of the number of sensors required is achieved through sensitivity analysis and the orthogonalization projection method. To estimate states and unknown inputs in real‐time, a recursive expectation maximization (EM) algorithm derived from the conventional EM algorithm is employed. During the E‐step, the extended Kalman filter (EKF) is used to compute states and covariance in the recursive Q‐function, while in the M‐step, unknown inputs are updated by locally maximizing the recursive Q‐function. The estimation performance is evaluated using comprehensive simulations. Through this method, accurate soil moisture estimation can be obtained, even in the presence of model mismatch.

Research on the Impact of Tourism on the Urban-rural Income Disparity and Countermeasures

At present, the most important issue for economic development is how to ensure the coordinated development of all aspects. At present, the country's focus has shifted from all-round moderate prosperity to the issue of average development. Therefore, how to ensure and implement the average of resources and the exploration of implementation plans are currently more important research. Tourism is a recent emerging economic industry and plays a great role in promoting China's economic level. Starting from the current development status of China, this paper comprehensively analyzes whether tourism will affect the income difference between urban and rural residents through literature retrieval and case analysis. Explore how this element can be positively promoted. After research, we conclude that the development of tourism can indeed promote the balance of urban and rural development, but at the same time, it will also cause the problem of improper resource development and mismatch between the speed of tourism development. Therefore, countries need to respond to the situation. For example, strengthen the management of tourism resources, strengthen the publicity and governance of scenic areas, and so on. These optimization policies will definitely effectively alleviate and optimize the existing differences and differences, and realize the average quality of life of residents as soon as possible.

Optimization model for home energy management system of rural dwellings

In the context of the increasing popularity of distributed energy, this paper proposes a home energy management system method considering the working state of flexible load to deal with the problem of mismatch between home energy supply and demand. Specifically, in this paper, the flexible load in the system is studied, and the model of flexible load and its working state are established. On this basis, combined with the real-time electricity price of the grid, the model of home energy management system is constructed to minimize the electricity purchase cost and improve the utilization rate of renewable energy, the genetic algorithm is used to solve it, and the influence of time step, flexible load ratio and whether to use energy storage equipment on the optimization degree of the model are analyzed. The research results show that, while meeting the requirements of human comfort and electricity demand, the daily electricity purchase cost of the system with flexible load scheduling is 22.5% lower than that of the system without flexible load scheduling, and the utilization rate of renewable energy is increased by 16.5%. In terms of model optimization, shortening the prediction time step, increasing the proportion of flexible load and using energy storage equipment can further reduce the electricity purchase cost. The case study confirms the effectiveness of the proposed home energy management system model, which can provide an efficient optimal scheduling scheme for household energy saving.

Optimal design of high frequency magnetic links for power conversion used in grid connected solar and wind power plants

The high-frequency standard magnetic links were recently considered viable candidates for construction of the medium-voltage power converters, rather than link with the common dc specialized magnetic materials, like nano-crystalline and the amorphous materials. This provides a new route of portable and lightweight incorporation of renewable systems into the direct grid, stepping-up transformer. The main objective is to propose an ideal design approach for magnetic links and to validate their viability by the evaluation of a sample. This will discuss a specific approach to design, research, and implementation. The predicted result is that the proposed architecture strategy will be implemented effectively in the future with clean energy generation schemes and intelligent grids. The current approaches have some critical disadvantages, including voltage mismatch, minimum overall power extraction, and general mode problems because of several direct grid and common dc connections. With emphasis on implementing renewable energies, exploring different forms of configuring structures for efficiency and output is becoming increasingly relevant. Both technologies employ grid-based voltage converters, but conventional equipment poses several problems in terms of voltage balance and maximum power output. Magnetic connections are a viable solution to minimize the costs, reliability, and consistency of the network. Instead of several dc links, these can be solved. Thus, the plan will depend on its optimal design to monitor system costs while improving efficiency by adding a new magnet-powered voltage converter. Particularly the voltage mismatch and typical mode problems of converter systems are minimized. The electromagnetically designed common magnetic links are, however, a multi-physics challenge, affecting device performance and costs. The paper objectives are to propose an ideal design approach for magnetic links and to validate their viability by the evaluation of a sample.

Multi-scale Transformer-CNN domain adaptation network for complex processes fault diagnosis

Despite the breakthroughs in deep neural network-based fault diagnosis, the model mismatch problem owing to the changes in data distribution remains challenging. To fuse deep features for cross-mode feature modeling, a Transformer-convolutional neural network (TrCNN) based multi-scale distribution alignment network is proposed. In the source domain stage, a concatenated structure of Transformer and convolutional neural network (CNN) extracts deep diagnostic information by combining global and local approaches. In the transfer stage, alignment is performed on the complex features extracted from different CNN substructures at multiple scales. Multi-scale feature alignment allows aligning information from various aspects while maintaining the discriminability of the data. The effectiveness and feasibility of the proposed method were demonstrated through experiments conducted on the Tennessee-Eastman (TE) process and industrial three-phase flow (TFF) equipment.

Multi-source excited travelling-wave bowtie antenna based on a meander series of YBCO bicrystal Josephson junctions

Series superconducting Josephson junctions (JJs), as terahertz (THz) mixers, have attracted increasing attentions due to their advantages in solving the saturation problem of superconducting mixers, achieving higher mixing harmonics and higher sensitivity in THz band. However, the normal-state resistances of the series JJs are so low that there exists an impedance mismatch between the coupled antenna and the JJs. In this paper, a meander embedding travelling-wave bowtie antenna is proposed for a series of bicrystal JJs. With this antenna, not only the problem of impedance mismatch can be solved, but also more series JJs can be inserted into the antenna. Five and even seven series JJs in the meander match the proposed antenna well. Furthermore, combined current distribution, far-field radiation patterns and parameter study are investigated in the numerical simulation to analyze this antenna.

Flexible and broadband colloidal quantum dots photodiode array for pixel-level X-ray to near-infrared image fusion

Combining information from multispectral images into a fused image is informative and beneficial for human or machine perception. Currently, multiple photodetectors with different response bands are used, which require complicated algorithms and systems to solve the pixel and position mismatch problem. An ideal solution would be pixel-level multispectral image fusion, which involves multispectral image using the same photodetector and circumventing the mismatch problem. Here we presented the potential of pixel-level multispectral image fusion utilizing colloidal quantum dots photodiode array, with a broadband response range from X-ray to near infrared and excellent tolerance for bending and X-ray irradiation. The colloidal quantum dots photodiode array showed a specific detectivity exceeding 1012 Jones in visible and near infrared range and a favorable volume sensitivity of approximately 2 × 105 μC Gy−1 cm−3 for X-ray irradiation. To showcase the advantages of pixel-level multispectral image fusion, we imaged a capsule enfolding an iron wire and soft plastic, successfully revealing internal information through an X-ray to near infrared fused image.

Range ambiguity suppression under high-resolution estimation using the MUSIC-AP algorithm for pulse-Doppler radar

Range ambiguity is a significant challenge in conventional pulse-Doppler radar systems with medium or high pulse repetition frequencies, greatly impacting radar detection and imaging capabilities. The classic approaches such as waveform diversity and compressed sensing are based on the isolation between pulses. However, these methods encounter issues like residual ambiguity and grid mismatch, resulting in poor range ambiguity suppression performance. In this paper, the multiple signal classification-alternating projection (MUSIC-AP) method is proposed to address these challenges and achieve high-resolution estimation. The proposed method converts the range-velocity estimate into a spectrum estimate, enabling the utilization of the MUSIC algorithm to solve the grid mismatch problem and improve echo reconstruction. Then, to mitigate the effect of ambiguous energy on reconstruction, the MUSIC reconstruction subprocess is embedded into the AP framework. Through iterative approximation, the method gradually suppresses ambiguous and noise energy, thereby further enhancing the echo reconstruction accuracy and range ambiguity suppression performance. Simulations demonstrate the effectiveness of the proposed method. Moreover, algorithm analysis is conducted, considering aspects such as resolution, robustness, and sparsity, which provides a basis for parameter selection and applicability conditions.

Unsupervised Domain Adaptation with CycleGAN: Adapting Image Style and Content for Improved Cross-Domain Performance

Abstract: In order to improve model performance while transferring information from a source domain to an unlabelled target domain, unsupervised domain adaptation is a crucial problem in deep learning. The CycleGAN design, a well-known generative adversarial network architecture, is used in this study to explore the domain adaptation challenge. Improved cross-domain performance is the goal, and both picture style and content adaptation are being focused on. In this study, we explore the use of CycleGAN to modify images from a source domain to more closely reflect the look and feel of a target domain. With no need for paired data, the architecture's built-in capacity to learn domain mappings makes it easier to transfer knowledge between dissimilar domains. By placing a strong emphasis on content and style adaptation, we hope to get beyond the problems of domain shift and distribution mismatch, which will improve generalization and classification accuracy in the target domain. We extensively experiment on benchmark datasets to show the efficacy of the suggested approach. Comparing cross-domain performance to baseline models and other adaption strategies, quantitative evaluation using known measures demonstrates the significant improvement attained. Additionally, qualitative assessments demonstrate the successful alteration of images, demonstrating CycleGAN's competence in adjusting both visual appeal and semantic information. By highlighting the need of simultaneously addressing visual style and content, this study makes a contribution to the field of unsupervised domain adaptation. The outcomes highlight CycleGAN's potential as a formidable domain adaptation tool, opening the door for improved knowledge transfer and performance in real-world settings across several domains

A novel adaptive beamforming scheme for array signal data processing

When the desired signal data exists in the array received data or the steering vector has a mismatch problem, the current traditional adaptive beamformers will suffer from the effect of the desired signal cancelation phenomenon, resulting in a sharp decline in performance. To address the occurrence of desired signal cancelation, an improved matrix projection-based efficient beamforming method is proposed. Firstly, based on spatial partitioning (SP) technology, a significant projection matrix for interference-plus-noise space (INS) is constructed. Secondly, using the constructed key projection matrix, the sample data covariance matrix is projected into the INS to achieve the goal of suppressing the desired signal data information. Finally, the weight data vector is calculated by Capon beamformer. The proposed algorithm does not require an iterative search for the optimal solution, which has the advantage of a small amount of calculation. Simulation experiments have verified that the proposed method has significant advantages in suppressing the desired data signals. Especially when the desired data signal has large power, the signal-to-interference-plus-noise ratio (SINR) of the proposed algorithm is better than that of the compared algorithms under the conditions of random directionality errors or local scattering errors between the desired signal and interference.

An Improved Vibe Algorithm Based on Adaptive Thresholding and the Deep Learning-Driven Frame Difference Method

Foreground detection is the main way to identify regions of interest. The detection effectiveness determines the accuracy of subsequent behavior analysis. In order to enhance the detection effect and optimize the problems of low accuracy, this paper proposes an improved Vibe algorithm combining the frame difference method and adaptive thresholding. First, we adopt a shallow convolutional layer of VGG16 to extract the lower-level features of the image. Features images with high correlation are fused into a new image. Second, adaptive factors based on the spatio-temporal domain are introduced to divide the foreground and background. Finally, we construct an inter-frame average speed value to measure the moving speed of the foreground, which solves the mismatch problem between background change rate and model update rate. Experimental results show that our algorithm can effectively solve the drawback of the traditional method and prevent the background model from being contaminated. It suppresses the generation of ghosting, significantly improves detection accuracy, and reduces the false detection rate.

Hyperspectral Image Dimensionality Reduction Algorithm Based on Spatial–Spectral Adaptive Multiple Manifolds

Hyperspectral images contain rich spatial–spectral information and have high dimensions, which can lead to challenges related to feature extraction for classification tasks, resulting in suboptimal performance. We propose a hyperspectral image dimensionality reduction algorithm based on spatial–spectral adaptive multiple manifolds to address the problem of small differences between features of dissimilar samples in the subspace caused by the uniform projection transformation in traditional dimensionality reduction methods. Firstly, to address spatial boundary mismatch problems caused by re-characterizing a pixel using pixels in a fixed area around it as its near neighbors in traditional algorithms, an adaptive weight representation method based on super-pixel segmentation is proposed, which enhances the similarity of similar samples and the dissimilarity of dissimilar samples. Secondly, to address the problem that a single manifold cannot completely characterize the near neighbor between samples of different categories, an adaptive multi-manifold representation method is proposed. The feature representation of the entire hyperspectral data in the low-dimensional subspace is obtained by adaptively fusing the intra- and inter-manifold maps constructed for each category of samples in the spatial and spectral dimensions. Experimental results on two public datasets show that the proposed method achieves better results when performing the hyperspectral image dimensionality reduction task.