Search Results (15)

In remote sensing imagery, objects smaller than $32\times 32$ pixels suffer from three persistent challenges that existing detectors inadequately resolve: (1) their weak signal is easily submerged in background clutter, causing high miss rates; (2) the scarcity of valid pixels yields few geometric or textural cues, hindering discriminative feature extraction; and (3) successive down-sampling irreversibly discards high-frequency details, while multi-scale pyramids still fail to compensate. To counteract these issues, we propose MS-YOLOv11, an enhanced YOLOv11 variant that integrates “frequency-domain detail preservation, lightweight receptive-field expansion, and adaptive cross-scale fusion.” Specifically, a 2D Haar wavelet first decomposes the image into multiple frequency sub-bands to explicitly isolate and retain high-frequency edges and textures while suppressing noise. Each sub-band is then processed independently by small-kernel depthwise convolutions that enlarge the receptive field without over-smoothing. Finally, the Mix Structure Block (MSB) employs the MSPLCK module to perform densely sampled multi-scale atrous convolutions for rich context of diminutive objects, followed by the EPA module that adaptively fuses and re-weights features via residual connections to suppress background interference. Extensive experiments on DOTA and DIOR demonstrate that MS-YOLOv11 surpasses the baseline in mAP@50, mAP@95, parameter efficiency, and inference speed, validating its targeted efficacy for small-object detection. Full article

As a form of non-destructive testing, eddy current testing is widely used for detecting surface micro-damage on metal components in sectors such as aerospace. Conventional frequency-domain analysis techniques often fail to effectively extract defect-related features from non-stationary eddy current signals. This paper proposes an ECT system based on the Discrete Wavelet Transform to address this limitation. In hardware design, the system employs a DDS to generate a 1 MHz excitation signal for the probe. High-precision acquisition of defect response signals is achieved using an IQ demodulator and a 24-bit ADC. For signal processing, the Haar wavelet is applied for single-level decomposition. This method successfully isolates the defect response signal within the high-frequency detail coefficients. Experimental results demonstrate that for a metal surface notch with a depth of 1 mm, the system significantly improves the SNR, resulting in a ΔSNR improvement of 3.64 dB, which is 0.36 dB higher than that achieved using time-domain processing. Full article

The time-fractional generalized Burger–Fisher equation (TF-GBFE) is utilized in many physical applications and applied sciences, including nonlinear phenomena in plasma physics, gas dynamics, ocean engineering, fluid mechanics, and the simulation of financial mathematics. This mathematical expression explains the idea of dissipation and shows how advection and reaction systems can work together. We compare the homotopy perturbation transform method and the new iterative method in the current study. The suggested approaches are evaluated on nonlinear TF-GBFE. Two-dimensional (2D) and three-dimensional (3D) figures are displayed to show the dynamics and physical properties of some of the derived solutions. A comparison was made between the approximate and accurate solutions of the TF-GBFE. Simple tables are also given to compare the integer-order and fractional-order findings. It has been verified that the solution generated by the techniques given converges to the precise solution at an appropriate rate. In terms of absolute errors, the results obtained have been compared with those of alternative methods, including the Haar wavelet, OHAM, and q-HATM. The fundamental benefit of the offered approaches is the minimal amount of calculations required. In this research, we focus on managing the recurrence relation that yields the series solutions after a limited number of repetitions. The comparison table shows how well the methods work for different fractional orders, with results getting closer to precision as the fractional-order numbers get closer to integer values. The accuracy of the suggested techniques is greatly increased by obtaining numerical results in the form of a fast-convergent series. Maple is used to derive the approximate series solution’s behavior, which is graphically displayed for a number of fractional orders. The computational stability and versatility of the suggested approaches for examining a variety of phenomena in a broad range of physical science and engineering fields are highlighted in this work. Full article

With the development of intelligent modern agriculture, strawberry harvesting robots play an increasingly important role in precision agriculture. However, existing vision systems face multiple challenges in complex farmland environments, including fruit occlusion, difficulties in recognizing fruits at varying ripeness levels, and limited real-time processing capabilities. This study proposes a keypoint detection and 3D localization method for strawberry fruits utilizing a depth camera to address these challenges. By introducing a Haar Wavelet Downsampling (HWD) module and Gold-YOLO neck, the proposed method achieves significant improvements in feature extraction and detection performance. The integration of the HWD module effectively reduces image noise, enhances feature extraction accuracy, and strengthens the method’s ability to recognize fruit stems. Additionally, incorporating the Gold-YOLO neck structure enhances multi-scale feature fusion, improving detection accuracy and enabling the method to adapt to complex environments. To further accelerate inference speed and enable deployment in an embedded system, Layer-adaptive sparsity for Magnitude-based Pruning (LAMP) technology is employed, significantly reducing redundant parameters and thereby enhancing the lightweight performance of the model. Experimental results demonstrate that the proposed method can accurately identify strawberries at different ripeness stages and exhibits strong robustness under various lighting conditions and complex scenarios, achieving an average precision of 97.3% while reducing model parameters to 38.2% of the original model, significantly improving the efficiency of strawberry fruit localization. This method provides robust technical support for the practical application and widespread adoption of agricultural robots. Full article

Surface gravity inversion attempts to recover the density contrast distribution in the 3D Earth model for geological interpretation. Since airborne gravity is characterized by large data volumes, large-scale 3D inversion exceeds the capacity of desktop computing resources, making it difficult to achieve the appropriate depth/lateral resolution for geological interpretation. In addition, gravity data are finite and noisy, and their inversion is ill posed. Especially in the absence of a priori geological information, regularization must be introduced to overcome the difficulty of the non-uniqueness of the solutions to recover the most geologically plausible ones. Because the use of Haar wavelet operators has an edge-preserving property and can preserve the sensitivity matrix structure at each level of the multilevel method to obtain faster solvers, we present a multilevel algorithm for large-scale gravity inversion solved by the re-weighted regularized conjugate gradient (RRCG) algorithm to reduce the inversion computational resources and improve the depth/lateral resolution of the inversion results. The RRCG-based multilevel inversion was then applied to synthetic cases and airborne gravity data from the Quest-South project in British Columbia, Canada. Results from synthetic models and field data show that the RRCG-based multilevel inversion is suitable for obtaining density contrast distributions with appropriate horizontal and vertical resolution, especially for large-scale gravity inversions compared to Occam’s inversion. Full article

To improve the imaging speed of ghost imaging and ensure the accuracy of the images, an adaptive ghost imaging scheme based on 2D-Haar wavelets has been proposed. This scheme is capable of significantly retaining image information even under under-sampling conditions. By comparing the differences in light intensity distribution and sampling characteristics between Hadamard and 2D-Haar wavelet illumination patterns, we discovered that the lateral and longitudinal information detected by the high-frequency 2D-Haar wavelet measurement basis could be used to predictively adjust the diagonal measurement basis, thereby reducing the number of measurements required. Simulation and experimental results indicate that this scheme can still achieve high-quality imaging results with about a 25% reduction in the number of measurements. This approach provides a new perspective for enhancing the efficiency of computational ghost imaging. Full article

In this paper, a hybrid of a Wavelet Decomposition–Generalised Auto-Regressive Conditional Heteroscedasticity–Extreme Value Theory (WD-ARMA-GARCH-EVT) model is applied to estimate the Value at Risk (VaR) of BitCoin (BTC/USD) and the South African Rand (ZAR/USD). The aim is to measure and compare the riskiness of the two currencies. New and improved estimation techniques for VaR have been suggested in the last decade in the aftermath of the global financial crisis of 2008. This paper aims to provide an improved alternative to the already existing statistical tools in estimating a currency VaR empirically. Maximal Overlap Discrete Wavelet Transform (MODWT) and two mother wavelet filters on the returns series are considered in this paper, viz., the Haar and Daubechies (d4). The findings show that BitCoin/USD is riskier than ZAR/USD since it has a higher VaR per unit invested in each currency. At the 99% significance level, BitCoin/USD has average values of VaR of 2.71% and 4.98% for the WD-ARMA-GARCH-GPD and WD-ARMA-GARCH-GEVD models, respectively; and this is slightly higher than the respective 2.69% and 3.59% for the ZAR/USD. The average BitCoin/USD returns of 0.001990 are higher than ZAR/USD returns of −0.000125. These findings are consistent with the mean-variance portfolio theory, which suggests a higher yield for riskier assets. Based on the p-values of the Kupiec likelihood ratio test, the hybrid model adequacy is largely accepted, as p-values are greater than 0.05, except for the WD-ARMA-GARCH-GEVD models at a 99% significance level for both currencies. The findings are helpful to financial risk practitioners and forex traders in formulating their diversification and hedging strategies and ascertaining the risk-adjusted capital requirement to be set aside as a cushion in the event of the occurrence of an actual loss. Full article

Wavelet decomposition in signal processing has been widely used in the literature. The popularity of machine learning (ML) algorithms is increasing day by day in agriculture, from irrigation scheduling and yield prediction to price prediction. It is quite interesting to study wavelet-based stochastic and ML models to appropriately choose the most suitable wavelet filters to predict agricultural commodity prices. In the present study, some popular wavelet filters, such as Haar, Daubechies (D4), Coiflet (C6), best localized (BL14), and least asymmetric (LA8), were considered. Daily wholesale price data of onions from three major Indian markets, namely Bengaluru, Delhi, and Lasalgaon, were used to illustrate the potential of different wavelet filters. The performance of wavelet-based models was compared with that of benchmark models. It was observed that, in general, the wavelet-based combination models outperformed other models. Moreover, wavelet decomposition with the Haar filter followed by application of the random forest (RF) model gave better prediction accuracy than other combinations as well as other individual models. Full article

The quantitative defect detection of wire rope is crucial to guarantee safety in various application scenes, and sophisticated inspection conditions usually lead to the accurate testing of difficulties and challenges. Thus, a magnetic flux leakage (MFL) signal analysis and convolutional neural networks (CNNs)-based wire rope defect recognition method was proposed to solve this challenge. Typical wire rope defect inspection data obtained from one-dimensional (1D) MFL testing were first analyzed both in time and frequency domains. After the signal denoising through a new combination of Haar wavelet transform and differentiated operation and signal preprocessing by normalization, ten main features were used in the datasets, and then the principles of the proposed MFL and 1D-CNNs-based wire rope defect classifications were presented. Finally, the performance of the novel method was evaluated and compared with six machine learning methods and related algorithms, which demonstrated that the proposed method featured the highest testing accuracy (>98%) and was valid and feasible for the quantitative and accurate detection of broken wire defects. Additionally, the considerable application potential as well as the limitations of the proposed methods, and future work, were discussed. Full article

Three-dimensional object detection is crucial for autonomous driving to understand the driving environment. Since the pooling operation causes information loss in the standard CNN, we designed a wavelet-multiresolution-analysis-based 3D object detection network without a pooling operation. Additionally, instead of using a single filter like the standard convolution, we used the lower-frequency and higher-frequency coefficients as a filter. These filters capture more relevant parts than a single filter, enlarging the receptive field. The model comprises a discrete wavelet transform (DWT) and an inverse wavelet transform (IWT) with skip connections to encourage feature reuse for contrasting and expanding layers. The IWT enriches the feature representation by fully recovering the lost details during the downsampling operation. Element-wise summation was used for the skip connections to decrease the computational burden. We trained the model for the Haar and Daubechies (Db4) wavelets. The two-level wavelet decomposition result shows that we can build a lightweight model without losing significant performance. The experimental results on KITTI’s BEV and 3D evaluation benchmark show that our model outperforms the PointPillars-based model by up to 14% while reducing the number of trainable parameters. Full article

Utilizing antenna diversity techniques has become a well-known approach to improve the performance of wireless communication systems. Multiple antenna arrays with half-length spacing, such as a uniform linear array (ULA), have been taken into consideration. Since 60 GHz is an unlicensed frequency band and ideal for local propagation, it is where the technology is being used. The transmitter and receiver both accomplish QAM modulation and demodulation. The performance in terms of bit error rate (BER) was tested in MATLAB simulation software for all antenna diversity scenarios: the single input and single output (SISO) DWT, multiple input and single output (MISO) DWT, single input and multiple output (SIMO) DWT, and multiple input and multiple output (MIMO) DWT. The MIMO DWT was shown to be the best of them. The performance of MIMO OFDM using various wavelets was also simulated, and the performance of the Haar wavelet transform was 2 dB better than that of the other wavelet transform. Compared to simulation results, the analytical results showed good agreement with little discrepancy. Full article

This article is devoted to the development of methodological supports and experimental software tools for accuracy analysis and information processing in control stochastic systems (CStS) with complex shock disturbances (ShD) by means of wavelet Haar–Galerkin technologies. Basic new results include methods and algorithms of stochastic covariance analysis and modeling on the basis of the Galerkin method and wavelet expansion for linear, linear with parametric noises, and quasilinear CStS with ShD. Results are illustrated by an information-control system at ShD. New stochastic effects accumulation for systematic and random errors are detected and investigated. Full article

Hyperspectral image classification is an emerging and interesting research area that has attracted several researchers to contribute to this field. Hyperspectral images have multiple narrow bands for a single image that enable the development of algorithms to extract diverse features. Three-dimensional discrete wavelet transform (3D-DWT) has the advantage of extracting the spatial and spectral information simultaneously. Decomposing an image into a set of spatial–spectral components is an important characteristic of 3D-DWT. It has motivated us to perform the proposed research work. The novelty of this work is to bring out the features of 3D-DWT applicable to hyperspectral images classification using Haar, Fejér-Korovkin and Coiflet filters. Three-dimensional-DWT is implemented with the help of three stages of 1D-DWT. The first two stages of 3D-DWT are extracting spatial resolution, and the third stage is extracting the spectral content. In this work, the 3D-DWT features are extracted and fed to the following classifiers (i) random forest (ii) K-nearest neighbor (KNN) and (iii) support vector machine (SVM). Exploiting both spectral and spatial features help the classifiers to provide a better classification accuracy. A comparison of results was performed with the same classifiers without DWT features. The experiments were performed using Salinas Scene and Indian Pines hyperspectral datasets. From the experiments, it has been observed that the SVM with 3D-DWT features performs better in terms of the performance metrics such as overall accuracy, average accuracy and kappa coefficient. It has shown significant improvement compared to the state of art techniques. The overall accuracy of 3D-DWT+SVM is 88.3%, which is 14.5% larger than that of traditional SVM (77.1%) for the Indian Pines dataset. The classification map of 3D-DWT + SVM is more closely related to the ground truth map. Full article

Human activity recognition (HAR) has been an active area in computer vision with a broad range of applications, such as education, security surveillance, and healthcare. HAR is a general time series classification problem. LSTMs are widely used for time series classification tasks. However, they work well with high-dimensional feature vectors, which reduce the processing speed of LSTM in real-time applications. Therefore, dimension reduction is required to create low-dimensional feature space. As it is experimented in previous study, LSTM with dimension reduction yielded the worst performance among other classifiers, which are not deep learning methods. Therefore, in this paper, a novel scale and rotation invariant human activity recognition system, which can also work in low dimensional feature space is presented. For this purpose, Kinect depth sensor is employed to obtain skeleton joints. Since angles are used, proposed system is already scale invariant. In order to provide rotation invariance, body relative direction in egocentric coordinates is calculated. The 3D vector between right hip and left hip is used to get the horizontal axis and its cross product with the vertical axis of global coordinate system assumed to be the depth axis of the proposed local coordinate system. Instead of using 3D joint angles, 8 number of limbs and their corresponding 3D angles with X, Y, and Z axes of the proposed coordinate system are compressed with several dimension reduction methods such as averaging filter, Haar wavelet transform (HWT), and discrete cosine transform (DCT) and employed as the feature vector. Finally, extracted features are trained and tested with LSTM (long short-term memory) network, which is an artificial recurrent neural network (RNN) architecture. Experimental and benchmarking results indicate that proposed framework boosts the performance of LSTM by approximately 30% accuracy in low-dimensional feature space. Full article

Compressive sensing (CS) is a recent technique that promises to dramatically speed up the radar acquisition. Previous works have already tested CS for ground-based synthetic aperture radar (GBSAR) performing preliminary simulations or carrying out measurements in controlled environments. The aim of this article is a systematic study on the effective applicability of CS for GBSAR with data acquired in real scenarios: an urban environment (a seven-storey building), an open-pit mine, and a natural slope (a glacier in the Italian Alps). The authors tested the most popular sets of orthogonal functions (the so-called ‘basis’) and three different recovery methods (l1-minimization, l2-minimization, orthogonal pursuit matching). They found that Haar wavelets as orthogonal basis is a reasonable choice in most scenarios. Furthermore, they found that, for any tested basis and recovery method, the quality of images is very poor with less than 30% of data. They also found that the peak signal–noise ratio (PSNR) of the recovered images increases linearly of 2.4 dB for each 10% increase of data. Full article