Search Results (47)

While deep learning methods are increasingly applied in the field of DOA estimation, existing approaches generally feed the real and imaginary parts of the covariance matrix directly into neural networks without optimizing the input features, which prevents classical attention mechanisms from improving accuracy. This paper proposes a spatio-temporal fusion model named DACL-Net for DOA estimation. The spatial branch applies a two-dimensional Fourier transform (2D-FT) to the covariance matrix, causing angles to appear as peaks in the magnitude spectrum. This operation transforms the original covariance matrix into a dark image with bright spots, enabling the convolutional neural network (CNN) to focus on the bright-spot components via an attention module. Additionally, a spectrum attention mechanism (SAM) is introduced to enhance the extraction of temporal features in the time branch. The model learns simultaneously from two data branches and finally outputs DOA results through a linear layer. Simulation results demonstrate that DACL-Net outperforms existing algorithms in terms of accuracy, achieving an RMSE of 0.04° at an SNR of 0 dB. Full article

This study presents a compact bulb-shaped ultra-wideband microstrip patch antenna designed for microwave imaging applications, more specifically, breast tumor detection. Traditional antenna design methods for medical applications are time-consuming. The proposed antenna, designed in CST Microwave Studio 2019 on a Rogers RT 5880 substrate with a slotted ground plane, achieves a bandwidth of 11.1 GHz, a gain of 6.2 dBi, and an efficiency above 80%. In response to the limitations of conventional antenna design approaches, this study introduces a novel machine learning-based approach to accelerate the design process, where a custom CatBoost model predicts key dimensions—feedline width, large circle radius, and small circle radius, based on the performance metrics such as resonant frequency, minimum reflection coefficient, bandwidth, real and imaginary part of impedance. The model achieves a cross-validation score of 95.13% with a mean absolute error of 0.0166 mm, outperforming conventional machine learning approaches. Shapley Additive exPlanations analysis is applied to interpret feature contributions. A prototype is fabricated using the prediction of a machine learning model. The bulb-shaped antenna structure, wide operational bandwidth, consistent gain, and strong sensitivity to tissue dielectric variations enhance its effectiveness for breast tumor detection compared with conventional antennas. Furthermore, experiments with a breast phantom confirmed the prototype’s suitability for detecting dielectric contrasts in tissue, establishing a foundation for machine learning-assisted antenna design in medical imaging. Full article

Gastronomic tourism is a strategic tool for territorial development, as it promotes cultural heritage, supports local economies and encourages environmentally responsible consumption. This study attempts to analyse the evolution of key gastronomic products through digital marketing tools, reflecting on the need to know this real data in order to carry out sustainable territorial and tourism planning. To do so, it uses a methodology based on the analysis of data obtained through Google Trends, taking as a reference a set of terms related to seafood, traditional meats and wines with designation of origin. The study examines the seasonal patterns and geographical distribution of interest in these terms, evaluating their impact both inside and outside Galicia as a replicable methodological case. The results show significant differences between categories. In addition, there is a generalised decrease in the search for gastronomic terms, which may indicate a reduction in the relative weight of this element as a factor in the creation of the image of the territories. In conclusion, the article demonstrates the capacity of this methodology to propose more sustainable tourism, territorial and economic planning strategies based on the transformation of qualitative imaginaries into quantitative data and trends. Full article

Synthetic aperture radar (SAR) image target recognition has important application values in security reconnaissance and disaster monitoring. However, due to speckle noise and target orientation sensitivity in SAR images, traditional spatial domain recognition methods face challenges in accuracy and robustness. To effectively address these challenges, we propose a dual-branch spatial-frequency domain fusion recognition method with cross-attention, achieving deep fusion of spatial and frequency domain features. In the spatial domain, we propose an enhanced multi-scale feature extraction module (EMFE), which adopts a multi-branch parallel structure to effectively enhance the network’s multi-scale feature representation capability. Combining frequency domain guided attention, the model focuses on key regional features in the spatial domain. In the frequency domain, we design a hybrid frequency domain transformation module (HFDT) that extracts real and imaginary features through Fourier transform to capture the global structure of the image. Meanwhile, we introduce a spatially guided frequency domain attention to enhance the discriminative capability of frequency domain features. Finally, we propose a cross-domain feature fusion (CDFF) module, which achieves bidirectional interaction and optimal fusion of spatial-frequency domain features through cross attention and adaptive feature fusion. Experimental results demonstrate that our method achieves significantly superior recognition accuracy compared to existing methods on the MSTAR dataset. Full article

This study focuses on the topographic structure of optical anisotropy maps (theziograms) of dehydrated blood plasma films (facies) to identify and utilize markers for diagnosing self-similarity (multifractality) in the birefringence parameters of supramolecular protein networks. The research is based on the Jones-matrix analytical framework, which describes the formation of polarization-structural speckle fields in polycrystalline blood plasma facies. In the proposed model, algorithms were developed to relate the real and imaginary parts of the complex elements of the Jones matrix to the theziograms of linear and circular birefringence. To experimentally implement these algorithms, a novel optical technology was introduced for polarization-interference registration and phase scanning of the laser speckle field of blood plasma facies. The laser-based Jones-matrix layer-by-layer theziography relies on polarization filtration and the digital recording of interference patterns from microscopic images of blood plasma facies. This process includes digital 2D Fourier reconstruction and phase-by-phase scanning of the object field of complex amplitudes, enabling the acquisition of phase sections of laser polarization-structural speckle field components scattered with varying multiplicities. Jones-matrix images of supramolecular networks, along with their corresponding theziograms of linear and circular birefringence, were obtained for each phase plane. The experimental data derived from laser layer-by-layer Jones-matrix theziography were quantitatively analyzed using two complementary approaches: statistical analysis (central moments of the 1st to 4th orders) and multifractal analysis (spectra of fractal dimension distributions). As a result, the most sensitive markers—namely asymmetry and kurtosis—were identified, highlighting changes in the statistical and scale self-similar structures of the theziograms of linear and circular birefringence in blood plasma facies. The practical aspect of this work is to evaluate the diagnostic potential of the Jones-matrix theziography method for identifying and differentiating changes in the birefringence of supramolecular networks in blood plasma facies caused by the long-term effects of COVID-19. For this purpose, a control group (healthy donors) and three experimental groups of patients, confirmed to have had COVID-19 one-to-three years prior, were formed. Within the framework of evidence-based medicine, the operational characteristics of the method—sensitivity, specificity, and accuracy—were assessed. The method demonstrated excellent accuracy in the differential diagnosis of the long-term effects of COVID-19. This was achieved by statistically analyzing the spectra of fractal dimensions of Jones-matrix theziograms reconstructed in the phase plane of single scattering within the volume of blood plasma facies. Full article

Although image captioning has gained remarkable interest, privacy concerns are raised because it relies heavily on images, and there is a risk of exposing sensitive information in the image data. In this study, a privacy-preserving image captioning framework that leverages partial encryption using Double Random Phase Encoding (DRPE) and deep learning is proposed to address privacy concerns. Unlike previous methods that rely on full encryption or masking, our approach involves encrypting sensitive regions of the image while preserving the image’s overall structure and context. Partial encryption ensures that the sensitive regions’ information is preserved instead of lost by masking it with a black or gray box. It also allows the model to process both encrypted and unencrypted regions, which could be problematic for models with fully encrypted images. Our framework follows an encoder–decoder architecture where a dual-stream encoder based on ResNet50 extracts features from the partially encrypted images, and a transformer architecture is employed in the decoder to generate captions from these features. We utilize the Flickr8k dataset and encrypt the sensitive regions using DRPE. The partially encrypted images are then fed to the dual-stream encoder, which processes the real and imaginary parts of the encrypted regions separately for effective feature extraction. Our model is evaluated using standard metrics and compared with models trained on the original images. Our results demonstrate that our method achieves comparable performance to models trained on original and masked images and outperforms models trained on fully encrypted data, thus verifying the feasibility of partial encryption in privacy-preserving image captioning. Full article

The efficacy of visual Simultaneous Localization and Mapping (SLAM) diminishes in large-scale environments due to challenges in identifying distant landmarks, leading to a limited perception range and trajectory drift. This paper presents a practical method to enhance the accuracy of feature-based real-time visual SLAM for compact unmanned vehicles by constructing distant map points. By tracking consecutive image features across multiple frames, remote map points are generated with sufficient parallax angles, extending the mapping scope to the theoretical maximum range. Observations of these landmarks from preceding keyframes are supplemented accordingly, improving back-end optimization and, consequently, localization accuracy. The effectiveness of this approach is ensured by the introduction of the virtual map point, a proposed data structure that links relational features to an imaginary map point, thereby maintaining the constrained size of local optimization during triangulation. Based on the ORB-SLAM3 code, a SLAM system incorporating the proposed method is implemented and tested. Experimental results on drone and vehicle datasets demonstrate that the proposed method outperforms ORB-SLAM3 in both accuracy and perception range with negligible additional processing time, thus preserving real-time performance. Field tests using a UGV further validate the efficacy of the proposed method. Full article

The field of multi-source remote sensing observation is becoming increasingly dynamic through the integration of various remote sensing data sources. However, existing deep learning methods face challenges in differentiating between internal and external relationships and capturing fine spatial features. These models often struggle to effectively capture comprehensive information across remote sensing data bands, and they have inherent differences in the size, structure, and physical properties of different remote sensing datasets. To address these challenges, this paper proposes a novel geometric-algebra-based spectral–spatial hierarchical fusion network (GASSF-Net), which uses geometric algebra for the first time to process multi-source remote sensing images, enabling a more holistic approach to handling these images by simultaneously leveraging the real and imaginary components of geometric algebra to express structural information. This method captures the internal and external relationships between remote sensing image features and spatial information, effectively fusing the features of different remote sensing data to improve classification accuracy. GASSF-Net uses geometric algebra (GA) to represent pixels from different bands as multivectors, thus capturing the intrinsic relationships between spectral bands while preserving spatial information. The network begins by deeply mining the spectral–spatial features of a hyperspectral image (HSI) using pairwise covariance operators. These features are then extracted through two branches: a geometric-algebra-based branch and a real-valued network branch. Additionally, the geometric-algebra-based network extracts spatial information from light detection and ranging (LiDAR) to complement the elevation data lacking in the HSI. Finally, a genetic-algorithm-based cross-fusion module is introduced to fuse the HSI and LiDAR data for improved classification. Experiments conducted on three well-known datasets, Trento, MUUFL, and Houston, demonstrate that GASSF-Net significantly outperforms traditional methods in terms of classification accuracy and model efficiency. Full article

Large language models (LLMs) are widely integrated into autonomous driving systems to enhance their operational intelligence and responsiveness and improve self-driving vehicles’ overall performance. Despite these advances, LLMs still struggle between hallucinations—when models either misinterpret the environment or generate imaginary parts for downstream use cases—and taxing computational overhead that relegates their performance to strictly non-real-time operations. These are essential problems to solve to make autonomous driving as safe and efficient as possible. This work is thus focused on symmetrical trade-offs between the reduction of hallucination and optimization, leading to a framework for these two combined and at least specifically motivated by these limitations. This framework intends to generate a symmetry of mapping between real and virtual worlds. It helps in minimizing hallucinations and optimizing computational resource consumption reasonably. In autonomous driving tasks, we use multimodal LLMs that combine an image-encoding Visual Transformer (ViT) and a decoding GPT-2 with responses generated by the powerful new sequence generator from OpenAI known as GPT4. Our hallucination reduction and optimization framework leverages iterative refinement loops, RLHF—reinforcement learning from human feedback (RLHF)—along with symmetric performance metrics, e.g., BLEU, ROUGE, and CIDEr similarity scores between machine-generated answers specific to other human reference answers. This ensures that improvements in model accuracy are not overused to the detriment of increased computational overhead. Experimental results show a twofold improvement in decision-maker error rate and processing efficiency, resulting in an overall decrease of 30% for the model and a 25% improvement in processing efficiency across diverse driving scenarios. Not only does this symmetrical approach reduce hallucination, but it also better aligns the virtual and real-world representations. Full article

This work evaluates the electrical, optical and thermal properties of Sn-doped Ge_xSi_1-xO_y thin films for use as microbolometer sensing materials. The films were prepared using a combination of a radio frequency (RF) magnetron and direct current (DC) sputtering using a Kurt J Leskar Proline PVD-75 series sputtering machine. Thin films were deposited in an O₂+Ar environment at a chamber pressure of 4 mTorr. The thicknesses of the thin films were varied between 300 nm–1.2 µm by varying the deposition time. The morphology and microstructure of thin films were investigated by atomic force microscope (AFM) imaging and X-ray diffraction (XRD), while the atomic composition was determined using the energy dispersive spectroscopy (EDS) function of a scanning electron microscope. The thin film with an atomic composition of Ge_0.45Si_0.05Sn_0.15O_0.35 was found to be amorphous. We used the Arrhenius relationship to determine the activation energy as well as temperature coefficient of resistance of the thin films, which were found to be 0.2529 eV and −3.26%/K, respectively. The noise voltage power spectral density (PSD) of the film was analyzed using a Primarius—9812DX noise analyzer using frequencies ranging from 2 Hz to 10 kHz. The noise voltage PSD of the film was found to be 1.76 × 10⁻¹¹ V²/Hz and 2.78 × 10⁻¹⁴ V²/Hz at 2 Hz and $1\mathrm{K}\mathrm{H}\mathrm{z}$ frequencies, respectively. The optical constants were determined using the ellipsometry reflection data of samples using an RC2 and infrared (IR) VASE Mark-II ellipsometer from J A Woollam. Absorption, transmission and reflection data for a wavelength range of 900 nm–5000 nm were also determined. We also determined the optical constant values such as the real and imaginary parts of refractive index (n and k, respectively) and real and imaginary part of permittivity (${\epsilon }_1$ and ${\epsilon }_{2,}$ respectively) for wavelength ranges between 193 nm to 35 µm. An optical band gap of 1.03 eV was determined from absorption data and using Tauc’s equation. In addition, the thermal conductivity of the film was analyzed using a Linseis thin film analyzer employing the 3ω method. The thermal conductivity of a 780 nm thick film was found to be 0.38 Wm⁻¹K⁻¹ at 300 K. From the data, the Ge-Si-Sn-O alloy was found to be a promising material for use as a sensing material for microbolometers. Full article

The computation of Green’s function is a basic and time-consuming task in realizing seismic imaging using integral operators because the function is the kernel of the integral operators and because every image point functions as the source point of Green’s function. If the perturbation theory is used, the problem of the computation of Green’s function can be transformed into one of solving the Lippmann–Schwinger (L–S) equation. However, if the velocity model under consideration has large scale and strong heterogeneity, solving the L–S equation may become difficult because only numerical or successive approximate (iterative) methods can be used in this case. In the literature, one of these methods is the generalized successive over-relaxation (GSOR) iterative method, which can effectively solve the L–S equation and obtain the desired convergent iterative series. However, the GSOR iterative method may encounter slow convergence when calculating the high-frequency Green’s function. In this paper, we propose a new scheme that utilizes the GSOR iterative with a precondition to solve the complex wavenumber L–S equation in a slightly attenuated medium. The complex wavenumber with imaginary components localizes the energy of the background Green’s function and reduces its singularity by enabling exponential decay. Introduction of the preconditioning operator can further improve the convergence speed of the GSOR iterative series. Then, we provide a preconditioned generalized successive over-relaxation (pre-GSOR) iterative format. Our numerical results show that if an appropriate damping factor and a proper preconditioning operator are selected, the method presented here outperforms the GSOR iterative for the real wavenumber L–S equation in terms of the convergence speed, accuracy, and adaptation to high frequencies. Full article

The double random phase encoding (DRPE) image encryption method has garnered significant attention in color image processing and optical encryption thanks to its R, G, and B parallel encryption. However, DRPE-based color image encryption faces two challenges. Firstly, it disregards the correlation of R, G, and B, compromising the encrypted image’s robustness. Secondly, DRPE schemes relying on Discrete Fourier Transform (DFT) and Discrete Fractional Fourier Transform (DFRFT) are vulnerable to linear attacks, such as Known Plaintext Attack (KPA) and Chosen Plaintext Attack (CPA). Quantum walk is a powerful tool for modern cryptography, offering robust resistance to classical and quantum attacks. Therefore, this study presents an optical color image encryption algorithm that combines two-dimensional quantum walking (TDQW) with 24-bit plane permutation, dubbed OCT. This approach employs pseudo-random numbers generated by TDQW for phase modulation in DRPE and scrambles the encrypted image’s real and imaginary parts using the generalized Arnold transform. The 24-bit plane permutation helps reduce the R, G, and B correlation, while the generalized Arnold transform bolsters DRPE’s resistance to linear attacks. By incorporating TDQW, the key space is significantly expanded. The experimental results validate the effectiveness and security of the proposed method. Full article

The humanistic-geographical associations of popular music foster the potential to articulate the production and reproduction of an activity-centered politicized ontology of space in the everyday social life of any creative communitarian framework where an alternative set of lifestyles, choices, and tastes engage in a constant play. A cursory glimpse at the (counter-)cultural artistic productions of the American 1970s shows that the lyrical construction of real and imaginary geographical locales has remained a distinguishing motif in the song-writing techniques of the celebrated rock poets. In the case of Bruce Springsteen, whether it is the ‘badlands’, constituting the rebellious and notorious young adults, or the ‘promised land’, which is the desired destination of all his characters, his lyrical oeuvre has numerously provided an alternative sense of place. Springsteen’s lyrical and musical characterization of fleeting urban images like alleys, hotels, engines, streets, neon, pavements, locomotives, cars, etc., have not only captured the American cities under the changing regime of capital accumulation but also contributed to the inseparability of everyday social lives and modern urban experiences. Against the backdrop of this argument, this article seeks to explore how the socio-political and cultural aesthetics of Springsteen’s song stories unfurl distinct spatial poetics through their musical language. Also, the article attempts to delineate how Springsteen’s unabashed celebration of the working-class geography of the American 1970s unveils a site of cultural struggle, wherein existing social values are reconstructed amidst imaginary landscapes and discursive strategies of resistance are weaved. Full article

Metamaterial-based coded aperture imaging (MCAI) is a forward-looking radar imaging technique based on wavefront modulation. The scattering coefficients of the target can resolve as an ill-posed inverse problem. Data-based deep-learning methods provide an efficient, but expensive, way for target reconstruction. To address the difficulty in collecting paired training data, an untrained deep radar-echo-prior-based MCAI (DMCAI) optimization model is proposed. DMCAI combines the MCAI model with a modified U-Net for predicting radar echo. A joint loss function based on deep-radar echo prior and total variation is utilized to optimize network weights through back-propagation. A target reconstruction strategy by alternatively using the imaginary and real part of the radar echo signal (STAIR) is proposed to solve the DMCAI. It makes the target reconstruction task turn into an estimation from an input image by the U-Net. Then, the optimized weights serve as a parametrization that bridges the input image and the target. The simulation and experimental results demonstrate the effectiveness of the proposed approach under different SNRs or compression measurements. Full article

Inspired by the success of Convolutional Neural Network (CNN)-based deep learning methods for optical image segmentation, there is a growing interest in applying these methods to Polarimetric Synthetic Aperture Radar (PolSAR) data. However, effectively utilizing well-established real-valued CNNs for PolSAR image segmentation requires converting complex-valued data into real-valued representations. This paper presents a systematic comparison of 14 different real-valued representations used as CNN input in the literature. These representations encompass various approaches, including the use of coherency matrix elements, hand-crafted feature vectors, polarimetric features based on target decomposition, and combinations of these methods. The goal is to assess the impact of the choice of PolSAR data representation on segmentation performance and identify the most suitable representation. Four test configurations are employed to achieve this, involving different CNN architectures (U-Net with ResNet-18 or EfficientNet backbone) and PolSAR data acquired in different frequency bands (S- and L-band). The results emphasize the importance of selecting an appropriate real-valued representation for CNN-based PolSAR image segmentation. This study’s findings reveal that combining multiple polarimetric features can potentially enhance segmentation performance but does not consistently improve the results. Therefore, when employing this approach, careful feature selection becomes crucial. In contrast, using coherency matrix elements with amplitude and phase representation consistently achieves high segmentation performance across different test configurations. This representation emerges as one of the most suitable approaches for CNN-based PolSAR image segmentation. Notably, it outperforms the commonly used alternative approach of splitting the coherency matrix elements into real and imaginary parts. Full article