Enhancement Scheme Research Articles

Feature Enhancement Based Oriented Object Detection in Remote Sensing Images

Since objects in remote sensing imagery often have arbitrary orientations and high densities, the features of small objects are inclined to be contaminated by the background and other instances. To address the issues, we propose a new oriented object detection framework where a series of feature enhancement schemes are implemented so as to improve robustness and accuracy of the detector. Firstly, we design a weighted bidirectional feature pyramid network, which can be used to fuse both high-level semantic features and low-level detail features for effectively handling with multi-scale objects. Accordingly, we apply the convolutional block attention module that exploits both spatial- and channel-wise attention in our detector, and study how to effectively integrate it into the framework for adaptive feature refinement. In the meanwhile, we present a semantic segmentation guided module to generate naive mask, which is used to multiple with pyramid features to filter out background noise and improve feature representation for small objects. The experimental results on two public datasets, i.e., UCAS-AOD and DOTA, validate the effective performance of the proposed method for oriented object detection in remote sensing images.

Physical layer security enhancement scheme for PDM-16QAM system based on seven-dimensional CNN hyperchaotic encryption

The paper presents a secure communication scheme for the optical physical layer based on a seven-dimensional (7-D) Cellular Neural Network (CNN) hyperchaotic encryption. The encryption scheme utilizes a 7-D CNN hyperchaotic system to generate a hyperchaotic sequence as the key source. A portion of this key is selected to encrypt the plaintext image. The proposed scheme has been successfully implemented in a PDM-16QAM system with a data rate of 224 Gbps over a 200 km single-mode fiber (SMF). Experimental results show that authorized users can successfully decrypt the received signal, while eavesdroppers are unable to obtain useful information with a bit error rate (BER) of approximately 0.5. The key space of the scheme is 101792. Through key sensitivity analysis and key space analysis, it is known that the proposed encryption system can effectively resist various attacks by cryptanalysts.

An efficient control scheme for operational performance enhancement of vehicular fuel cell integrated power system

Recent advancements in fuel cell (FC) technology have positioned it as a promising alternative energy source across various stationary, mobile, and transportation applications. As fuel cell vehicles (FCVs) become increasingly prominent in the transportation sector, they also offer the potential to function as supplementary stationary energy providers when parked, thereby contributing to the grid. In this study, a control method to enhance the energy transfer capability of an FCV-integrated grid system is proposed. To manage energy transfer between grid and FCVs, classical strategies using fixed parameter controllers suffer from performance degradation due to the nonlinear and external parameter-dependent nature of the FC stacks. The proposed adaptive fractional-order proportional-integral strategy bears the advantage of self-tuning parameters feature for designing the control parameters of power conditioning unit. Using fractional-order control endows the system with memory and heredity, enhancing its ability to handle nonlinearity and uncertainty. Through case studies, it is demonstrated that the proposed strategy reduces vehicular FC output power variations by over 60 % while enhancing transient response by 50 % compared to classical control methods. Thus, the limitations such as low control flexibility, slow transient response, and high undershoot/overshoot rates addressed by the classical controllers are countered thanks to the developed strategy.

CFD simulation of liquid-liquid extraction mechanism and enhancement schemes in microchannels based on three mass transfer models

Microreactors are highly efficient devices with a large specific surface area to improve the mass transfer efficiency. In this paper, a comprehensive three-dimensional CFD model was constructed based on three mass transfer theories to simulate the liquid-liquid two-phase flow and mass transfer process in a microchannel reactor, and two enhancement schemes were proposed. The multiphase flow and mass transfer characteristics were investigated by visualization and extraction experiments. The results indicated that the extraction efficiencies (E) and overall mass transfer coefficients (KLa) calculated by the penetration model and surface renewal model were within ±15 % errors compared to the experimental values. Moreover, E primarily increases with the increase of fluid residence time, while KLa increases with increasing flow rate. As the flow rate increases from 0.3 ml/min to 1.5 ml/min, E decreases by 15 %, and KLa rises from 0.78 s⁻¹ to 2.65 s⁻¹. Whereas the channel width decreases from 0.8 mm to 0.3 mm, E decreases by 3 %, and KLa rises from 0.44 s⁻¹ to 2.77 s⁻¹. Finally, microchannel with necked structure and baffles in mixing zone both improve the mass transfer efficient to some extent.

Impact of internal lattice structures on the weight and natural frequencies of a low pressure turbine blade

Vibration characteristics play a crucial role in the overall performance of Low-pressure (LP) turbine blades and different techniques are developed to enhance vibrational response by increasing natural frequencies. The present analysis aims to develop a new technique based on the investigation of improvement in natural frequencies and mass reduction of a topology-optimized blade design through location-based integration of lattice structures inside the blades. FE models are developed for three different lattice locations based on mode shape behavior obtained through modal analysis of two different nickel-based alloys at stressed and unstressed conditions. The results show that the internal BCC lattice at specific locations showed better vibrational characteristics compared to other incorporated lattice structures, and validates the location-based integration scheme for enhancement of natural frequencies and reduced mass in applied conditions. By this method, 5.7% mass reduction was achieved from an already 35% mass-reduced blade along with enhancement in the first and second natural frequencies by 8.2% and 5.9% respectively when unstressed. At stressed condition, the natural frequencies increased by ≈7.7% and ≈6.6%.

High-efficiency GaAs TFSC based on Ti plasma enhancement

This study proposed a performance enhancement scheme for GaAs thin-film solar cell (TFSC) based on Ti plasma enhancement. It aims to enhance the light absorption ability of the cell by using surface plasmon excitations of metal nanoparticles, and to predict and optimize the performance of the TFSC using the FDTD method. By introducing Ti nanosphere and pyramid structures on the upper and lower surfaces of the cell, the reflection and transmission losses of light are effectively reduced. This increases the interaction between the cell materials and light, and significantly improves the cell's ability to absorb light. It is shown that Ti nanosphere and pyramid structures can localize the electric field near the metal surface, which greatly enhances the absorption of light on the upper and lower surfaces of the cell. In the wavelength range of 380–1200 nm, the absorption of all bands reaches more than 93 %, with an average absorption rate as high as 97.60 %, and is close to perfect absorption in the wavelength range of 700–900 nm. Meanwhile, the photoelectric conversion efficiency (PCE) of the cell reaches 32.72 %, which significantly improves the overall performance of the cell and provides a compelling design solution for the innovation and development of GaAs TFSC technology.

محاكاة مخططات التصفية المطبقة لتحسين الصور الفوتوغرافية

In signal processing, filters generally play a pivotal role to remove unwanted parts of the signal, such as random noise, or to extract useful parts of the signal, such as the components lying within a certain frequency range to enhance the performance and denoising scenario. This paper presents the implementation of linear and non-linear filtering schemes for noise reduction and images enhancement. This is achieved by performing convolution of a grayscale image with a mask filter of multiple sizes using MATLAB software. The average and median filters are implemented on the same image of an injected salt and pepper noise. In accordance with the findings, the nonlinear filters show more promising performance with a better peak-signal-noise ratio (PSNR) compared to the linear filters.

Face privacy protection scheme by security-enhanced encryption structure and nonlinear dynamics

This article proposes a secure communication enhancement scheme based on face detection and chaotic partition permutation. The scheme uses edge detection technology to detect facial information, which is then used as an encryption object. The hash value of the plaintext image is extracted as the secret key to the chaotic sequence generated by the chaotic system. Then a series of encryption operations are performed on the face image to obtain the final ciphertext image. In this article, two chaotic systems are used to generate pseudo-random chaotic sequences for different encryption steps. The initial key is computed by combining the hash function of the image and external parameters. The experimental results and security analysis show that the algorithm has excellent encryption effectiveness and security performance against various typical attacks.

A physical layer security enhancement scheme for CO-OFDM systems based on 3D Brownian motion and TZBN Joint Scramble

In this paper, we propose a scheme for enhancing the physical layer security and transmission performance of coherent optical orthogonal frequency division multiplexing (CO-OFDM) systems. The scheme for OFDM data first after 3-dimensional (3D) Brownian motion rotational permutation, and then according to the time zone and band number (TZBN) scrambling to achieve the effect of further data perturbation, which through the SHA-256 algorithm and 6-dimensional (6D) hyperchaotic processing to obtain the chaotic keys to enhance the security. After simulation experiment of 16QAM CO-OFDM security system transmitting over 80 km standard single-mode fiber (SSMF) at the symbol rate of 30 Gbaud, it is shown that the encryption scheme can guarantee that the authorized user receives valid data and the eavesdropper obtains the information with the BER of about 0.5. The key space of the scheme is about 2.88×10194, which can effectively resist attacks such as violent attacks and chosen plaintext attacks. And the peak-to-average power ratio (PAPR) can be reduced by about 1.09 dB while the encryption process.

Adversarial EM for variational deep learning: Application to semi-supervised image quality enhancement in low-dose PET and low-dose CT

In positron emission tomography (PET) and X-ray computed tomography (CT), reducing radiation dose can cause significant degradation in image quality. For image quality enhancement in low-dose PET and CT, we propose a novel theoretical adversarial and variational deep neural network (DNN) framework relying on expectation maximization (EM) based learning, termed adversarial EM (AdvEM). AdvEM proposes an encoder–decoder architecture with a multiscale latent space, and generalized-Gaussian models enabling datum-specific robust statistical modeling in latent space and image space. The model robustness is further enhanced by including adversarial learning in the training protocol. Unlike typical variational-DNN learning, AdvEM proposes latent-space sampling from the posterior distribution, and uses a Metropolis–Hastings scheme. Unlike existing schemes for PET or CT image enhancement which train using pairs of low-dose images with their corresponding normal-dose versions, we propose a semi-supervised AdvEM (ssAdvEM) framework that enables learning using a small number of normal-dose images. AdvEM and ssAdvEM enable per-pixel uncertainty estimates for their outputs. Empirical analyses on real-world PET and CT data involving many baselines, out-of-distribution data, and ablation studies show the benefits of the proposed framework.

Fuzzy C-Means clustering based selective edge enhancement scheme for improved road crack detection

One of the most serious problems currently in the world is road cracking, which could lower traffic safety and raise the risk of road accidents. A substantial sum of money is spent annually on maintaining and fixing the roads. However, manual crack detection is less accurate and takes longer. The focus of this study is on how artificial intelligence can be applied to image processing to improve crack detection. This study introduces the pixel classification enhancement fuzzy C-Means clustering, a new fuzzy C-Means clustering algorithm. The road crack detection from image is achieved automatically by utilizing second order pixel differences, an exponentially varying intensity dependent edge pixel enhancement scaling factor and intensity-based edge & non-edge fuzzy factors that helps to detect the cracks even in low contrast photos. This method doesn't necessitate training with image datasets. In addition, it can recognize edges or fractures in a range of unseen images. According to standard performance parameters, the experimental results demonstrate that the novel fuzzy C-Means segmentation-based approach performs better than many of the existing methods for contaminated or non-contaminated images in identifying patholes, transverse, and longitudinal cracks from road photos, as well as alligator cracks. The proposed method can assist managers or maintenance engineers in preventing further damage and quickly identifying different types of cracks with less manual labor and expense.

Enhancement layout optimisation of grid structures with stability constraints

Grid structures have found widespread use in civil and mechanical engineering owing to their ability of covering long spans with an outstanding strength-to-weight ratio. However, their shallow structural depth and slender members make them susceptible to buckling failures. Therefore, it is crucial to enhance the stability of grid structures. An under-explored way to achieve this is by optimally configuring enhancement materials. This paper addresses the challenges of identifying the optimal enhancement layouts for grid structures by solving a density-based topology optimisation problem. The problem formulation is based on the SIMP approach, minimising compliance while satisfying constraints on material volume and structural stability. The stability constraint is expressed using buckling load factors obtained from a linear eigenvalue analysis. Two types of enhancement schemes, involving in-plane and out-of-plane elements, are developed for the single-layer base grid structures. The efficiency of the proposed method is evaluated by performing enhancement layout optimisation for a flat and three curved square grid structures, subject to a uniformly distributed vertical load and a half-span load. The optimisation results shed light on the impact of in-plane and out-of-plane enhancements on the stability of grid structures, providing insights on optimally configuring enhancement materials to achieve desired stability. In addition, comparative analysis between the case studies indicates that for curved structures, a higher curvature normally leads to greater achievable stability. In contrast, the flat grid structure exhibits the broadest range of customisable stability due to its primarily bending-dominant load-carrying mechanism. Furthermore, the outcomes of geometric non-linear analysis confirm the load-carrying capacity of the optimal structures, with non-linear critical loads typically showing a positive correlation with linear buckling loads.

Research on performance enhancement scheme of optical camera communication based on adaptive exponential weighted moving average algorithm

AbstractWhen the COMS camera of optical camera communication (OCC) system acquired the information image, the grayscale value of pixels fluctuated due to the influence of blooming effect and light noise, so that the data logic could not be correctly judged by the decision threshold, which affected the bit error rate (BER) performance transmission distance and data rate, and degraded the system performance. In this paper, the adaptive exponential weighted moving average algorithm is proposed, and the optimal grayscale value matrix of signal demodulation is verified by experiment, so as to reduce the fluctuation of grayscale value and improve the performance of OCC system. The experimental results show that for data processing and analysis based on ZYNQ7020 experimental platform, a 7% forward error correction（BER = 3.8 × 10−3）requirements can be satisfied at 150 cm when the data rate is 3 Kbps, and a 7% forward error correction（BER = 3.8 × 10−3）requirements can be satisfied at 100 cm when the data rate is 5 Kbps.

A machine-learning architecture with two strategies for low-speed impact localization of composite laminates

In this paper, a machine-learning architecture with the integration of two strategies including data enhancement and adaptive generation scheme for Impact Localization (IL) are developed to address the aforementioned issues for location identification of impacts on composite laminates. Two main contributions are included in this research: First, response signals collected from low-speed impact experiments under various working conditions are denoised using Adaptive Sparse Noise Reduction Algorithm (ASNRA), which aims at maximizing the preservation of the original signal amplitude, thereby avoiding the underestimation of pulse features during denoising. Then a RIME-optimized Dual-layer Support Vector Regression (RDSVR) method for the real-time update of hyperparameters is implemented in the machine-learning architecture to realize IL. The superior performances of the IL architecture over different IL models are validated throughout the numerical examples in terms of stability and efficiency. Results demonstrate that proposed architecture has the ability to realize the accurate and robust IL of composite laminates.

Implementation of companding scheme for performance enhancement of optical OFDM structure

Abstract Due to its great spectral efficiency and resistance to multi-path fading, OFDM, or orthogonal frequency division multiplexing, is commonly utilized in optical communication systems. However, because of nonlinear distortions in optical components, OFDM signals are prone to a high peak-to-average power ratio (PAPR), which can severely impair bit error rate (BER) performance. This paper introduces a companding scheme to address high PAPR in optical OFDM systems and improve BER performance. The proposed scheme uses a nonlinear transformation to compress signal peaks and expand valleys, effectively reducing PAPR. Specifically, we investigate the µ-law companding technique, known for its simplicity and effectiveness in handling the active range of OFDM signals in optical communication. The companded signals are transmitted through an optical link and demodulated at the receiver. Simulation results show that the µ-law companding technique substantially reduces PAPR, leading to a significant improvement in BER performance. The companding process maintains signal integrity and spectral efficiency with minimal computational complexity and implementation cost. By mitigating nonlinearities introduced by optical components, this companding scheme enhances the overall reliability and efficiency of the optical OFDM system. An SNR gain of 2 dB–3 dB was achieved at a BER of 10−3.

Twist detection Mach-Zehnder interferometer based on optical vernier effect and its phase demodulation system

Fiber interferometric sensor can achieve sensing enhancement of various physical quantities based on the optical vernier effect, but there are currently no proposed torsion detection enhancement schemes. In this paper, we control the number of cladding modes in the sensing single-mode fiber by graded index fiber collimator and form a dual beam interference with the core mode, resulting in a transmission spectrum with regular waveform. The experimental results indicate that the sensing Mach-Zehnder interferometer (MZI) has a torsional sensitivity of −0.014 nm/(rad/m) within a large detection range of 0–60 rad/m. After amplification by optical cursor effect, it reaches −0.361 nm/(rad/m) with an amplification factor of 25.8 times, the detection limit for envelope valley is 0.345 rad/m. The sensor has a relatively small response to other physical quantities, with a strain sensitivity of 20.4 pm/με, a temperature sensitivity of 1.792 nm/℃, and a refractive index sensitivity of 77.885 nm/RIU, exhibiting excellent anti refractive index crosstalk performance. In addition, we discuss the phase demodulation scheme for interferometric sensor based on optical vernier effect sensitivity enhancement for the first time, which can filter out noise caused by dispersion or loss, eliminate the influence of the initial phase of the sensing system, and evaluate the direction of improving the detection performance of the phase demodulation system.

An end‐to‐end joint learning scheme of image compression and quality enhancement with improved entropy minimization

AbstractRecently, learned image compression methods based on entropy minimization have achieved superior results compared with conventional image codecs such as BPG and JPEG2000. However, they leverage single Gaussian models, which have a limited ability to approximate various irregular distributions of transformed latent representations, resulting in suboptimal coding efficiency. Furthermore, existing methods focus on constructing effective entropy models, rather than utilizing modern architectural techniques. In this paper, we propose a novel joint learning scheme called JointIQ‐Net that incorporates image compression and quality enhancement technologies with improved entropy minimization based on a newly adopted Gaussian mixture model. We also exploit global context to estimate the distributions of latent representations precisely. The results of extensive experiments demonstrate that JointIQ‐Net achieves remarkable performance improvements in terms of coding efficiency compared with existing learned image compression methods and conventional codecs. To the best of our knowledge, ours is the first learned image compression method that outperforms VVC intra‐coding in terms of both PSNR and MS‐SSIM.

Flutter Characteristics of a Modified Z-Shaped Folding Wing Using a New Non-Intrusive Model

Unmanned aerial vehicles (UAVs) with folding wings can serve in multiple mission profiles, usually accompanied by sudden changes in flight speed. These bring great challenges to the aeroelastic design of UAVs, especially in the calculation of flutter characteristics. This paper developed a new non-intrusive aeroelastic model to quickly calculate the flutter characteristics of Z-shaped folding wings at different folding angles. First, the original Z-shaped folding wing was designed to be enhanced. Beams and ribs were arranged inside each wing segment to enhance the structural strength performance. Control surfaces were arranged in the middle-wing and outer-wing to enhance the aerodynamic control performance. Second, a parametric aeroelastic model at any folding angle was reconstructed based on the input file of Nastran software for the flutter calculation of the folding wing in the unfolded state. Finally, the effects of parameters such as folding angle, hinge stiffness between different wing segments, and hinge stiffness of the control surfaces on the flutter characteristics of the folding wing were investigated. The results show that the enhancement scheme could significantly increase the flutter speed and flutter frequency of the folding wing. The hinge stiffness between each wing segment had a significant impact on the flutter characteristics of the folding wing, but flutter at the control surface basically did not occur.

Differentially private federated learning with Laplacian smoothing

Federated learning aims to protect data privacy by collaboratively learning a model without sharing private data among users. However, an adversary may still be able to infer the private training data by attacking the released model. Differential privacy provides a statistical protection against such attacks at the price of significantly degrading the accuracy or utility of the trained models. In this paper, we investigate a utility enhancement scheme based on Laplacian smoothing for differentially private federated learning (DP-Fed-LS), to improve the statistical precision of parameter aggregation with injected Gaussian noise without losing privacy budget. Our key observation is that the aggregated gradients in federated learning often enjoy a type of smoothness, i.e. sparsity in a graph Fourier basis with polynomial decays of Fourier coefficients as frequency grows, which can be exploited by the Laplacian smoothing efficiently. Under a prescribed differential privacy budget, convergence error bounds with tight rates are provided for DP-Fed-LS with uniform subsampling of heterogeneous non-iid data, revealing possible utility improvement of Laplacian smoothing in effective dimensionality and variance reduction, among others. Experiments over MNIST, SVHN, and Shakespeare datasets show that the proposed method can improve model accuracy with DP-guarantee and membership privacy under both uniform and Poisson subsampling mechanisms.

Dynamic stability analysis of laminated cylindrical shells considering fluid–structure interaction

This paper investigates the dynamic stability of laminated cylindrical shell submerged in a fluid. Assuming that the fluid is incompressible satisfying the Laplace equation, the coupling relationship between the external pressure from fluid acting on the cylindrical shell and the velocity potential function of the fluid is deduced by using Bernoulli law. Based on Kárman-Donnell’s thin shell theory, the governing equations for dynamic buckling of the composite laminated cylinder are established by introducing the constitutive relationship for laminated composite structures. Likely functions of the displacement and the stress function for cylindrical shell are proposed to construct Mathieu-Hill equation for dynamic stability of laminated cylindrical shell with fluid–structure interaction and the first three order dynamic instability regions are derived. A good agreement between the solutions from the proposed analysis and from the available literatures justified the accuracy and validity of the proposed analysis. With the established analysis, the influence of various parameters on the dynamic stability of cylinders are analyzed, from which a dynamic stability enhancement scheme suitable for composite laminated cylinders is summarized. It is found that the fluid–structure interaction will greatly reduce the excitation frequency of laminated cylindrical shells but has no effect on their vibration modes.