Domain Algorithm Research Articles

Enhanced pyramidal residual networks for single image super-resolution

Several super-resolution (SR) techniques are introduced in the literature, including traditional and machine learning-based algorithms. Especially, deep learning-based SR approaches emerge with demands for better quality images providing deeper subpixel enhancement. Dealing with the image enhancement task in the satellite images domain, a new SR method for single image SR, namely Enhanced Deep Pyramidal Residual Networks, is introduced in this study. The proposed method overcomes the potential instability problem of Enhanced Deep Residual Networks for Single Image Super-Resolution (EDSR) approach by gradually increasing the feature maps depending upon Pyramidal Residual Networks architecture. The EDSR itself is a good algorithm in the SR domain. However, it has a strict structure for increasing the block size. To overcome this problem with the aim of increasing the algorithm’s performance, the pyramidal residual networks gradually increasing hypothesis is utilized in the proposed approach, which is the main contribution and novelty of this study. Besides, by using the pyramidal residual networks gradually increasing hypothesis in the proposed approach, the parameter size of the models is also reduced, which affects the computational time. Two different models are proposed by considering addition and multiplication manners, and the proposed models are evaluated using well-known remote sensing datasets NWPU-RESISC45 and UC Merced. The results obtained by the proposed model are compared with the results of traditional image enhancement algorithms together with the EDSR itself, EDSR with deeper structure, Super-Resolution Generative Adversarial Networks approach, and Residual Local Feature Networks approach in terms of peak signal to noise ratio (PSNR) and structural similarity index measure (SSIM) metrics and showed that the proposed models present better quality images. Moreover, considering the computational time and complexity, it is shown that some proposed models achieve approximately 27% less output parameter having similar PSNR and SSIM values and computational time for EDSR itself and 65% less output parameter having better PSNR and SSIM values and 16% lower computational time for EDSR with deeper structure.

An Announced Extinction: The Impacts of Mining on the Persistence of Arthrocereus glaziovii, a Microendemic Species of Campos Rupestres

The mountaintops of eastern Brazil harbor the highest rates of plant endemism in South America. However, local biodiversity faces constant threats due to habitat loss and mining activities. About 89 rare and endangered species are exclusive to this region, including the threatened species Arthrocereus glaziovii. This study aims to evaluate the potential distribution of A. glaziovii based on abiotic variables and soil elements and to characterize the distribution of mineral titles that may restrict the species’ occurrence areas. We used the Bioclim, Domain, MaxEnt, GLM, and Random Forest algorithms to model this ecological niche under future climatic scenarios, in addition to modeling the layers of mineral titles corresponding to areas already mined and those slated for future mining projects. Our predictions indicate an expansion in the future distribution of A. glaziovii. Nevertheless, the future predicted occurrence areas of the species are already compromised due to mining. According to our findings, we emphasize the looming threat of the predicted extinction of this species. Therefore, implementing conservation strategies to ensure the survival of A. glaziovii is imperative.

Effectiveness of the Spatial Domain Techniques in Digital Image Steganography

Digital steganography is a new and extremely demanding method for transmitting information securely over the internet while employing a covert device. Since its inception in the 1990s till the present, digital steganography has a lengthy history. Early steganography focused primarily on imperceptibility, security and embedding capacity. In addition to using statistics as a foundation, convolution neural networks (CNN), generative adversarial networks (GAN), coverless approaches, and machine learning are all used to construct steganographic methods. Robustness is becoming a crucial component of many innovative techniques. Spatial, Transform, and Adaptive domains serve as the understructure of those novel methods. This broadens the range of steganographic technique development and often concentrates the implementation of adaptive techniques. As a result, this study helps to analyze the fundamentals of image steganography, a comparative review on the spatial domain algorithms. As using evaluation tools is strongly tied to the effectiveness of steganography, this study also goes into great detail about its application. The purpose of this research is to determine the best and most effective algorithm among the three competitive spatial domain algorithms, which are Least Significant Bit (LSB), Optimum Pixel Adjustment Procedure (OPAP), and Pixel Value Differencing (PVD) which in regard demonstrated the efficacy of spatial domain algorithms.

Optimization Scheme of Measuring Accuracy of Bearing Seat Size Based on Machine Vision

At present, the size measurement of industrial workpieces is mainly manual measurement and CMM measurement, which cannot meet the requirements of high precision, high efficiency and low error rate in industrial production at the same time. In order to solve the above problems, this paper uses monocular vision technology to propose an optimization scheme of workpiece size measurement accuracy based on machine vision, which takes the height and declination Angle between the camera lens and the workpiece as variables. Firstly, the image was captured by camera calibration correction, and morphological methods such as gray-scale, denoising, expansion and corrosion were used for image pre-processing. Secondly, features were extracted using double-threshold canny edge detection algorithm and connected domain algorithm. Finally, the bearing seat size was measured using the minimum external rectangle algorithm. The experiment shows that the higher the distance between the camera lens and the stage, the larger the error is when the image information can be collected completely. The greater the Angle between the center of the camera lens and the center of the workpiece, the greater the error; The device not only meets the precision requirements, but also has the advantages of fast response speed, which can meet the needs of industrial applications.

Algorithm for Surface Wave Suppression on 2D Seismic Data Using the Slant Karhunen–Loeve Transform in a Time-Frequency Domain

Abstract —Surface waves are the main source of coherent noise in land seismic survey, and their suppression is one of the main stages of common depth point data processing designed to improve the quality of tracking primary reflections on time sections. In practice, noise reduction is carried out using procedures from modern software based on numerical modeling of waveforms. However, they are too resource-intensive and have a large number of subjectively customizable parameters. The known algorithms have a common drawback: either the energy of reflected waves is distorted in an interference zone with a noise wave or the noise suppression quality is unsatisfactory. The current research is aimed at improving the filtering algorithm in a time-frequency domain using the slant Karhunen–Loeve transform in order to overcome these limitations, to increase the accuracy and rate of its software implementation, and also to test it when processing profile field data from land-based 2D seismic surveys. The algorithm is modified by developing a new method for determining static corrections for surface wave hodograph rectification in a time-frequency domain and by the application of preprocessing in which the reflected wave signal is removed preliminarily. These and other modifications ensure faster calculations and improve the quality of surface wave interference suppression. In addition, the slant Karhunen–Loeve transform is accelerated by parallelizing calculations across logical processor cores. In this paper, the algorithm is described in detail, its significant advantage over the standard methods of bandpass filtering and F–K filtering is shown, and the results of processing the field data obtained by the SWANA procedure (Geovation 2.0) and by the slant Karhunen–Loeve transform. The result obtained by the slant Karhunen–Loeve transform is superior to the SWANA procedure in terms of the surface wave filtering quality and has only four adjustable parameters (SWANA has 20 parameters)

975 nm multimode semiconductor lasers with high-order Bragg diffraction gratings

The 975 nm multimode diode lasers with high-order surface Bragg diffraction gratings have been simulated and calculated using the 2D finite difference time domain (FDTD) algorithm and the scattering matrix method (SMM). The periods and etch depth of the grating parameters have been optimized. A board area laser diode (BA-LD) with high-order diffraction gratings has been designed and fabricated. At output powers up to 10.5 W, the measured spectral width of full width at half maximum (FWHM) is less than 0.5 nm. The results demonstrate that the designed high-order surface gratings can effectively narrow the spectral width of multimode semiconductor lasers at high output power.

A 2-D Frequency-Domain Algorithm to Remove GRACE Stripe Noise

A 2-D Frequency-Domain Algorithm to Remove GRACE Stripe Noise

Group Intelligent City Mobile Communication Network's Control Strategy based on Cellular Internet of Things

Mobile communication network optimization heavily depends on power control technology, which impacts the effectiveness of the network. This paper aims to enhance control over nonlinear mobile communication networks and achieve superior performance by applying the particle swarm optimization (PSO) algorithm in the control domain. Addressing limitations in the basic PSO algorithm, improvements are made and applied to urban mobile communication networks. The methodology involves modifying the PSO algorithm to address identified issues and applying the enhanced algorithm to communication network scenarios. Simulation results indicate that with an initial particle count of 10 and 100 iterations, the optimized values for and are 0.691 and 0.486, respectively, resulting in an objective function value of 55.514. This achievement validates the successful implementation of the optimization process for mobile communication network control. The findings reveal that the proposed grad particle swarm optimization (Grad-PSO) algorithm exhibits mobile network optimization by robust search capability and rapid convergence.

Exploring academic influence of algorithms by co-occurrence network based on full-text of academic papers

PurposeIn the era of artificial intelligence (AI), algorithms have gained unprecedented importance. Scientific studies have shown that algorithms are frequently mentioned in papers, making mention frequency a classical indicator of their popularity and influence. However, contemporary methods for evaluating influence tend to focus solely on individual algorithms, disregarding the collective impact resulting from the interconnectedness of these algorithms, which can provide a new way to reveal their roles and importance within algorithm clusters. This paper aims to build the co-occurrence network of algorithms in the natural language processing field based on the full-text content of academic papers and analyze the academic influence of algorithms in the group based on the features of the network.Design/methodology/approachWe use deep learning models to extract algorithm entities from articles and construct the whole, cumulative and annual co-occurrence networks. We first analyze the characteristics of algorithm networks and then use various centrality metrics to obtain the score and ranking of group influence for each algorithm in the whole domain and each year. Finally, we analyze the influence evolution of different representative algorithms.FindingsThe results indicate that algorithm networks also have the characteristics of complex networks, with tight connections between nodes developing over approximately four decades. For different algorithms, algorithms that are classic, high-performing and appear at the junctions of different eras can possess high popularity, control, central position and balanced influence in the network. As an algorithm gradually diminishes its sway within the group, it typically loses its core position first, followed by a dwindling association with other algorithms.Originality/valueTo the best of the authors’ knowledge, this paper is the first large-scale analysis of algorithm networks. The extensive temporal coverage, spanning over four decades of academic publications, ensures the depth and integrity of the network. Our results serve as a cornerstone for constructing multifaceted networks interlinking algorithms, scholars and tasks, facilitating future exploration of their scientific roles and semantic relations.

Integration of deep learning and improved multi-objective algorithm to optimize reservoir operation for balancing human and downstream ecological needs

Dam (reservoir)-induced alterations of flow and water temperature regimes can threaten downstream fish habitats and native aquatic ecosystems. Alleviating the negative environmental impacts of dam-reservoir and balancing the multiple purposes of reservoir operation have attracted wide attention. While previous studies have incorporated ecological flow requirements in reservoir operation strategies, a comprehensive analysis of trade-offs among hydropower benefits, ecological flow, and ecological water temperature demands is lacking. Hence, this study develops a multi-objective ecological scheduling model, considering total power generation, ecological flow guarantee index, and ecological water temperature guarantee index simultaneously. The model is based on an integrated multi-objective simulation-optimization (MOSO) framework which is applied to Three Gorges Reservoir. To that end, first, a hybrid long short-term memory and one-dimensional convolutional neural network (LSTM_1DCNN) model is utilized to simulate the dam discharge temperature. Then, an improved epsilon multi-objective ant colony optimization for continuous domain algorithm (ε-MOACOR) is proposed to investigate the trade-offs among the competing objectives. Results show that LSTM _1DCNN outperforms other competing models in predicting dam discharge temperature. The conflicts among economic and ecological objectives are often prominent. The proposed ε-MOACOR has potential in resolving such conflicts and has high efficiency in solving multi-objective benchmark tests as well as reservoir optimization problem. More realistic and pragmatic Pareto-optimal solutions for typical dry, normal and wet years can be generated by the MOSO framework. The ecological water temperature guarantee index objective, which should be considered in reservoir operation, can be improved as inflow discharge increases or the temporal distribution of dam discharge volume becomes more uneven.

Transform Domain-Based Perceptual Detection and Reduction of Blocking Artifacts

In this paper, provide a simple and effective method for measuring blocking artefacts with an ideal 2-D step function in this study. First, a basic edge detection technique for measuring blocking artefacts is proposed. The ideal 2-D step function is chosen based on the presence of blocking artefacts in the edge image. The blocking artefact reduction algorithm in frequency domain is designed to extract all of the parameters required to detect the presence of blocking artefacts and replace the optimal step function with a ramp function by replacing the coefficient of the first row of horizontal blocks with the coefficient of the shifted block. The proposed strategy was tested on various standard benchmark photos and found to increase the perceptual quality of JPEG compressed images after blocking artefact removal with the proposed method.

Multiuser medical image encryption algorithm using phase-only CGH in the gyrator domain.

In this paper, a multiuser medical image encryption algorithm is proposed. The proposed algorithm utilizes polar decomposition, which enables multiuser features in the proposed algorithm. A computer-generated hologram (CGH) improves the security of the proposed algorithm in the gyrator domain. The phase-only CGH-based multiuser algorithm offers advantages such as storing a large amount of information in a compact space, resistance to counterfeiting, and enhanced security. The proposed method is validated with various statistical metrics, such as information entropy, mean squared error, correlation coefficient, histogram, and mesh plots. Results confirm that the proposed algorithm is secure and robust against potential attacks, such as plaintext attacks, iterative attacks, and contamination attacks. The proposed method has a large keyspace, which makes it very difficult to be breached in real-time with existing computational power.

W-Band FMCW MIMO System for 3-D Imaging Based on Sparse Array

Multiple-input multiple-output (MIMO) technology is widely used in the field of security imaging. However, existing imaging systems have shortcomings such as numerous array units, high hardware costs, and low imaging resolutions. In this paper, a sparse array-based frequency modulated continuous wave (FMCW) millimeter wave imaging system, operating in the W-band, is presented. In order to reduce the number of transceiver units of the system and lower the hardware cost, a linear sparse array with a periodic structure was designed using the MIMO technique. The system operates at 70~80 GHz, and the high operating frequency band and 10 GHz bandwidth provide good imaging resolution. The system consists of a one-dimensional linear array, a motion control system, and hardware for signal generation and image reconstruction. The channel calibration technique was used to eliminate inherent errors. The system combines mechanical and electrical scanning, and uses FMCW signals to extract distance information. The three-dimensional (3-D) fast imaging algorithm in the wave number domain was utilized to quickly process the detection data. The 3-D imaging of the target in the near-field was obtained, with an imaging resolution of 2 mm. The imaging ability of the system was verified through simulations and experiments.

Cloud Assisted IoT-Operated Small Residential Microgrid with Collusive Model Approach for Energy Trading

This article explores a strategic approach for an energy-self-sufficient and economically sustainable small residential community, powered by rooftop solar photovoltaics. This community plays the role of a microgrid (MG) with a microgrid operator (MO). It operates in two distinct modes: within the MG (peer-to-peer or P2P) and with the utility grid. The P2P transfer is experimentally performed with open-source Internet of Things (IoT) applications from the cloud. This will enable a low-cost MG operation for developing countries. Residents from the community are elected considering their support towards community welfare, and they are considered as delegates. The MO with delegates, control the energy transfer operation. This approach distributes generated energy among community members at low prices if there is energy demand, minimizing carbon footprint. The action of selling energy by a prosumer during the need of fellow resident is considered as the token of social service towards the community. A social service counter (SSC) is chosen to identify services for each prosumer in the MG. When a seller sells energy within the community, the SSC increases. This count rewards the prosumer in several ways. MO only allows prosumers to participate in energy trading with the grid during the high-demand hours of the day. Delegates play an essential role in protecting the community's interest while selling energy outside the community. They try to form a coalition among participants to reduce installation costs and maximize the cumulative payoff. A comparative study between the proposed coordination game and two competitive game approaches, namely Cournot and Stackelberg's algorithm in the restricted domain, reveals that the proposed method is well suited for a small residential MG. Shapley value is a tool that identifies each delegate's contribution during the game. The paper employed this method for the overall coordination game to identify the most acceptable payoff for individual players.

Research on the Application of SVM in Ideology Analysis and the Enhancement of Ideological and Political Education Effectiveness

Abstract The consciousness and behavior of students in the Ideological and Political Education curriculum generate massive amounts of data information, how to allow educators to quickly obtain information from the massive amount of text data is very important to improve the energy efficiency of classroom education. SVM technology is employed in this paper for data mining and text classification. Firstly, using the web crawler method, the text of messages related to the Ideological and Political Science course posted by students on social networks is collected. The short text was preprocessed before performing sentiment analysis, which mainly included interaction information filtering, word segmentation, and lexical labeling. Then, the SVM model suitable for students’ ideology analysis is constructed, using the Gauss radial basis kernel function to accurately depict the distribution structure of the data, and the L1-SVM model with more stable computational performance is also proposed. The extension method of the classification algorithm in the real number domain is summarized at the end. This algorithm’s accuracy is 78%, and its F1 value is 80%, which is higher than the other three algorithms. DAG-SVM and recall are both optimized to a lesser extent. Overall, the classification efficiency of the algorithm in this paper has been improved. The positive effect of this paper’s algorithm on improving the effectiveness of Ideological and Political Education can be seen in the significant increase in the learning interest of the experimental class.

Neural Network-Based Algorithm for Identification of Recaptured Images

With the improvement of digital image display technology, the “secondary imaging” caused by digital cameras is also gradually popularized, and the quality of the recaptured image formed by this imaging is also getting higher and higher, and this kind of high-quality fake image has caused great threat to digital images security. We propose a neural network-based recaptured image identification algorithm and use the difference between two types of images to build the identification algorithm in the frequency domain. The algorithm uses filtering to obtain the feature images which are the high-frequency and low-frequency filtering images, in order to further distinguish the image differences, the direction of the filtered image obtained from high-frequency images, each direction of the filtered image contains high-frequency information at different angles, and the low-frequency image is downsampled. At the same time, the low-frequency image is downsampled to obtain a multi-scale filtered image. The algorithm extracts the features from previous images as the feature values for classification, and finally uses neural networks for classification to obtain the classification results, and these prove that the algorithm presented is able to differentiate the recaptured images effectively in this paper.

Research on defect recognition technology of transmission line based on visual macromodeling

Abstract In order to improve the defect recognition efficiency of transmission lines, the industry is currently using aerial images for automatic visual defect detection to ensure the safe operation of transmission lines. This paper proposes a method for defect recognition from coarse to fine, based on convolutional neural networks and connected domain algorithms, to improve recognition accuracy. The recognition speed is improved by using the knowledge distillation method of target detection networks based on decoupled features, adversarial features, and attention features. It has been found that the optimized recognition model improves the precision rate by 7%, the recall rate by 8%, and the average accuracy rate by 10%. The FPS of the model optimized by knowledge distillation is 62.5, and the average value of the FPS of other versions of this model is 47.35. It is believed that the two optimization ideas introduced in this paper can enhance the previous transmission line defect recognition algorithm in terms of accuracy and recognition speed.

АВТОМАТИЧНИЙ АНАЛІЗ ЗАВАНТАЖЕНОСТІ РАДІОЧАСТОТНОГО СПЕКТРА ТА СЕЛЕКЦІЯ СИГНАЛІВ

Constant increasing of radio-electronic devices number leads to an increase of spectrum occupancy and complication of radio-electronic environment. In such conditions, it is necessary to use automatic algorithms for prompt detection and selection of radio signals in radio monitoring systems. The purpose of the article is to develop algorithms and recommendations for their practical implementation to automate the process of radio frequency spectrum occupancy analysis and signal selection in a wide dynamic range with high occupancy of analyzed frequency band in conditions of a priori uncertainty of noise level. To achieve the stated goal were developed generalized algorithm for radio frequency spectrum analysis, algorithm of frequency domain processing and algorithm for frequency channels analysis. Examples of spectrum bands analysis with high occupancy and recommendations for developed algorithms implementation were represented. Depending on variability of noise power in analyzed frequency band an adaptive change of estimation time interval is provided, which will reduce the computational complexity. In conditions of no uniform noise level or a wide dynamic range of signals, it is proposed to use special test statistics to determine fullness of analyzed frequency channels. In the course of experimental studies, the analysis of recordings in frequency bands of 900 MHz, 1800 MHz and 2100 MHz was carried out. It was established that the developed algorithms provide a correct estimation of radio frequency spectrum occupancy and selection of signals with a dynamic range of at least 35 dB and occupancy of up to 92%. Developed algorithms do not require calibration of the equipment in case of fluctuations in characteristics of separate system elements and changes in radio-electronic environment and can be implemented in existing and perspective automatic radio monitoring systems. Keywords: radio frequency spectrum; spectrum occupancy; signal selection; test statistics; frequency channel.

Using Computer Technique for Developing Method for Vibration Damage Estimation Under Combined Random and Deterministic Loading

Abstract This paper is focusses on developing a novel method for vibration damage estimation for military helicopters, fighter aircrafts and any other aircraft exposed to combined stochastic and deterministic loading. The first stage of the research focused on frequency domain damage prediction, which is the legacy method proposed by Bishop and developed by Sweitzer, Schlesinger, Woodward, Kerr, Murthy, Datta and, Atkins. The mentioned frequency domain-based method is used in commercial software, e.g., MSC CAE Fatigue. Frequency domain damage prediction is based on superposition of spectral moments and Dirlik method of Rainflow Cycle Counting algorithm in frequency domain. The first phase of the research showed the legacy algorithm based on transfer function developed using FEM (Finite Element Method) method in Abaqus environment and is very conservative. The second stage of the research aims to develop a novel method which allowing for more robust and accurate damage estimation. For this purpose, the Monte Carlo method for retrieving random signal in the time domain from signal in frequency domain was used. To obtain the system transfer function, – the 1 g load harmonic system response was obtained using FEM analysis. It was subsequently scaled linearly by the PSD input curve for random loading and sine wave, or sine sweep function for deterministic loading to calculate the cumulative system response of the linear system. The research allows the development of a novel method to precisely estimate vibration damage using combined time and frequency domains approach, based on effective frequency domain FEM analysis of the linear system. The new proposed method can be also used for precise replication of test conditions via considering signal clipping and frequency resolution used for real testing.

Experimental research on global active rotor noise control using near-field acoustic holography and sound field reproduction

This study employs a 1.6 m diameter rotor to validate the global active noise control method, developed from our previously work, which is based on near-field acoustic holography and sound field reproduction. The validation is conducted through experiments in an anechoic chamber. Additionally, we achieved control over nearly all acoustic modal components of multiple blade passing frequency (BPF) noises of the rotor by extending the time-domain least mean square (LMS) to the acoustic modal domain. The experimental results from near-field acoustic holography revealed that each BPF noise contained 3–4 main acoustic modal components, accounting for almost 90 % of the sound power. The global active noise control experiments demonstrated that the adaptive algorithm in the acoustic modal domain effectively mitigates the influence of rotation speed fluctuations, resulting in steady-state global noise reduction through sound field reproduction. Furthermore, for the first 3 BPF noise, our method achieved noise reduction of 9, 11, and 6 dB by controlling the first 3–4 main acoustic modal components, respectively. The concurrent reduction of various harmonic noises at all observation points validates the method's capability to globally control multiple harmonic noises.