Search Results (21)

The quality and price of navel oranges vary depending on their geographical origin, thus providing a financial incentive for origin fraud. To prevent this phenomenon, it is necessary to explore a fast, non-destructive, and precise method for tracing the origin of navel oranges. In this study, a total of 490 Newhall navel oranges were selected from five major production regions in China, and the diffuse reflectance near-infrared spectrum in 4000–10,000 cm⁻¹ were non-invasively collected. We examined seven preprocessing techniques for the spectra, including Savitzky–Golay (SG) smoothing, first derivative (FD), multiplicative scattering correction (MSC), combinations of SG with MSC (SG+MSC), SG with FD (SG+FD), MSC with FD (MSC+FD), and three combined (SG+MSC+FD). A one-dimensional convolutional neural network (1DCNN) deep learning model for geographical origin tracing of navel orange was established, and five machine learning algorithms, i.e., partial least squares discriminant analysis (PLS-DA), linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF), and back-propagation neural network (BPNN), were compared with 1DCNN. The results show that the 1DCNN model based on the SG+FD preprocessing method achieved the optimal performance for the testing set, with prediction accuracy, precision, recall, and F1-score of 97.92%, 98%, 97.95%, and 97.90%, respectively. Therefore, NIRS combined with deep learning has a significant research and application value in the rapid, nondestructive, and accurate geographical origin traceability of agricultural products. Full article

The dermoscopic rainbow pattern (RP), also known as polychromatic pattern, is characterized by a multicolored appearance, resulting from the dispersion of polarized light as it penetrates various tissue components. Its separation into different wavelengths occurs according to the physics principles of scattering, absorption, and interference of light, creating the optical effect of RP. Even though the RP is regarded as a highly specific dermoscopic indicator of Kaposi’s sarcoma, in the medical literature, it has also been documented as an atypical dermoscopic finding of other non-Kaposi skin entities. We aim to present two distinct cases—a pigmented basal cell carcinoma (pBCC) and an aneurysmatic dermatofibroma—that exhibited RP in dermoscopy and to conduct a thorough review of skin conditions that display RP, revealing any predisposing factors that could increase the likelihood of its occurrence in certain lesions. We identified 33 case reports and large-scale studies with diverse entities characterized by the presence of RP, including skin cancers (Merkel cell carcinoma, BCC, melanoma, etc.), adnexal tumors, special types of nevi (blue, deep penetrating), vascular lesions (acroangiodermatitis, strawberry angioma, angiokeratoma, aneurismatic dermatofibromas, etc.), granulation tissue, hypertrophic scars and fibrous lesions, skin infections (sporotrichosis and cutaneous leishmaniasis), and inflammatory dermatoses (lichen simplex and stasis dermatitis). According to our results, the majority of the lesions exhibiting the RP were located on the extremities. Identified precipitating factors included the nodular shape, lesion composition and vascularization, skin pigmentation, and lesions’ depth and thickness. These parameters lead to increased scattering and interference of light, producing a spectrum of colors that resemble a rainbow. Full article

Free-space optics communication (FSO) can be used as a transmission medium for fiber optic sensing signals to make fiber optic sensing easier to implement; however, interference with the sensing signals caused by the optical turbulence and scattering of airborne particles in the FSO path is a potential problem. This work aims to deep denoise sensed signals from fiber Bragg grating (FBG) sensors based on FSO link transmission using advanced denoising deep learning techniques, such as stacked denoising autoencoders (SDAE). Furthermore, it will demodulate the sensed wavelength of FBGs by applying the deep belief network (DBN) technique. This is the first time the real FBG sensing experiment has utilized the actual noise interference caused by the environmental turbulence from an FSO link rather than adding noise through numerical processing. Consequently, the spectrum of the FBG sensors is clearly modulated by the noise and the issue with peak power variation. This complicates the determination of the center wavelengths of multiple stacked FBG spectra, requiring the use of machine learning techniques to predict these wavelengths. The results indicate that SDAE is efficient in denoising from the FBG spectrum, and DBN is effective in demodulating the central wavelength of the overlapped FBG spectrum. Thus, it is beneficial to implement an FSO link-based FBG sensing system in adverse weather conditions or atmospheric turbulence. Full article

Raman spectroscopy provides detailed information about the molecular composition of a sample. The classical identification of components in a multi-component sample typically involves comparing the preprocessed spectrum with a known reference stored in a database using various spectral matching or machine-learning techniques or relies on universal models based on a two-step analysis including first, the component identification, and then the decomposition of the mixed signal. However, although large databases and universal models cover a wide range of target materials, they may be not optimized to the variability required in a specific application. In this study, we propose a single-step method using deep learning (DL) modeling to decompose a simulated mixture of real measurements of Raman scattering into relevant individual components regardless of noise, baseline and the number of components involved and quantify their ratios. We hypothesize that training a custom DL model for applications with a fixed set of expected components may yield better results than applying a universal quantification model. To test this hypothesis, we simulated 12,000 Raman spectra by assigning random ratios to each component spectrum within a library containing 13 measured spectra of organic solvent samples. One of the DL methods, a fully connected network (FCN), was designed to work on the raw spectra directly and output the contribution of each component of the library to the input spectrum in form of a component ratio. The developed model was evaluated on 3600 testing spectra, which were simulated similarly to the training dataset. The average component identification accuracy of the FCN was 99.7%, which was significantly higher than that of the universal custom trained DeepRaman model, which was 83.1%. The average mean absolute error for component ratio quantification was 0.000562, over one order of magnitude smaller than that of a well-established non-negative elastic net (NN-EN), which was 0.00677. The predicted non-zero ratio values were further used for component identification. Under the assumption that the components of a mixture are from a fixed library, the proposed method preprocesses and decomposes the raw data in a single step, quantifying every component in a multicomponent mixture, accurately. Notably, the single-step FCN approach has not been implemented in the previously reported DL studies. Full article

Water scarcity is one of the most significant environmental factors that inhibits photosynthesis and decreases the growth and productivity of plants. Using the deep learning convolutional neural network (CNN) model, this study evaluates the ability of spectroscopy to estimate leaf water content (LWC) in fruit trees. During midday, spectral data were acquired from leaf samples obtained from three distinct varieties of fruit trees, encompassing the spectral range spanning from 350 to 2500 nm. Then, for spectral preprocessing, the fractional order derivative (FOD) and continuous wavelet transform (CWT) algorithms were used to reduce the effects of scattering and noise on the collected spectra. Finally, the CNN model was developed to predict LWC in different fruit trees. The results showed that: (1) The spectra treated with CWT and FOD could improve the spectrum expression ability by improving the correlation between spectra and LWC. The correlation level of FOD treatment was higher than that of CWT treatment. (2) The CNN model was developed using FOD _1.2, and CWT ₃ performed better than other traditional machine learning methods, such as RFR, SVR, and PLSR. (3) Further validation using additional samples demonstrated that the CNN model had good stability and quantitative prediction capability for the LWC of fruit trees (R² > 0.95, root mean square error (RMSE) < 1.773%, and relative percentage difference (RPD) > 4.26). The results may provide an effective way to predict fruit LWC using a CNN-based model. Full article

In space application, hybrid pixel detectors of the Timepix family have been considered mainly for the measurement of radiation levels and dosimetry in low earth orbits. Using the example of the Space Application of Timepix Radiation Monitor (SATRAM), we demonstrate the unique capabilities of Timepix-based miniaturized radiation detectors for particle separation. We present the incident proton energy spectrum in the geographic location of SAA obtained by using Bayesian unfolding of the stopping power spectrum measured with a single-layer Timepix. We assess the measurement stability and the resiliency of the detector to the space environment, thereby demonstrating that even though degradation is observed, data quality has not been affected significantly over more than 10 years. Based on the SATRAM heritage and the capabilities of the latest-generation Timepix series chips, we discuss their applicability for use in a compact magnetic spectrometer for a deep space mission or in the Jupiter radiation belts, as well as their capability for use as single-layer X- and $\gamma$-ray polarimeters. The latter was supported by the measurement of the polarization of scattered radiation in a laboratory experiment, where a modulation of 80% was found. Full article

Organic fluorophores operating in the optical window of biological tissues, namely in the deep-red and near-infrared (NIR) region of the electromagnetic spectrum, offer several advantages for fluorescence bioimaging applications owing to the appealing features of long-wavelength light, such as deep tissue penetration, lack of toxicity, low scattering, and reduced interference with cellular autofluorescence. Among these, COUPY dyes based on non-conventional coumarin scaffolds display suitable photophysical properties and efficient cellular uptake, with a tendency to accumulate primarily in mitochondria, which renders them suitable probes for bioimaging purposes. In this study, we have explored how the photophysical properties and subcellular localization of COUPY fluorophores can be modulated through the modification of the coumarin backbone. While the introduction of a strong electron-withdrawing group, such as the trifluoromethyl group, at position 4 resulted in an exceptional photostability and a remarkable redshift in the absorption and emission maxima when combined with a julolidine ring replacing the N,N-dialkylaminobenzene moiety, the incorporation of a cyano group at position 3 dramatically reduced the brightness of the resulting fluorophore. Interestingly, confocal microscopy studies in living HeLa cells revealed that the 1,1,7,7-tetramethyl julolidine-containing derivatives accumulated in the mitochondria with much higher specificity. Overall, our results provide valuable insights for the design and optimization of new COUPY dyes operating in the deep-red/NIR region. Full article

Grape quality and ripeness play a crucial role in producing exceptional wines with high-value characteristics, which requires an effective assessment of grape ripeness. The primary purpose of this research is to explore the possible application of visible–near-infrared spectral (Vis-NIR) technology for classifying the maturity stages of wine grapes based on quality indicators. The reflection spectra of Cabernet Sauvignon grapes were recorded using a spectrometer in the spectral range of 400 nm to 1029 nm. After measuring the soluble solids content (SSC), total acids (TA), total phenols (TP), and tannins (TN), the grape samples were categorized into five maturity stages using a spectral clustering method. A traditional supervised classification method, a support vector machine (SVM), and two deep learning techniques, namely stacked autoencoders (SAE) and one-dimensional convolutional neural networks (1D-CNN), were employed to construct a discriminant model and investigate the association linking grape maturity stages and the spectral responses. The spectral data went through three commonly used preprocessing methods, and feature wavelengths were extracted using a competitive adaptive reweighting algorithm (CARS). The spectral data model preprocessed via multiplicative scattering correction (MSC) outperformed the other two preprocessing methods. After preprocessing, a comparison was made between the discriminant models established with full and effective spectral data. It was observed that the SAE model, utilizing the feature spectrum, demonstrated superior overall performance. The classification accuracies of the calibration and prediction sets were 100% and 94%, respectively. This study showcased the dependability of combining Vis-NIR spectroscopy with deep learning methods for rapidly and accurately distinguishing the ripeness stage of grapes. It has significant implications for future applications in wine production and the development of optoelectronic instruments tailored to the specific needs of the winemaking industry. Full article

Infrared (IR) spectroscopy has greatly improved the ability to study biomedical samples because IR spectroscopy measures how molecules interact with infrared light, providing a measurement of the vibrational states of the molecules. Therefore, the resulting IR spectrum provides a unique vibrational fingerprint of the sample. This characteristic makes IR spectroscopy an invaluable and versatile technology for detecting a wide variety of chemicals and is widely used in biological, chemical, and medical scenarios. These include, but are not limited to, micro-organism identification, clinical diagnosis, and explosive detection. However, IR spectroscopy is susceptible to various interfering factors such as scattering, reflection, and interference, which manifest themselves as baseline, band distortion, and intensity changes in the measured IR spectra. Combined with the absorption information of the molecules of interest, these interferences prevent direct data interpretation based on the Beer–Lambert law. Instead, more advanced data analysis approaches, particularly artificial intelligence (AI)-based algorithms, are required to remove the interfering contributions and, more importantly, to translate the spectral signals into high-level biological/chemical information. This leads to the tasks of spectral pre-processing and data modeling, the main topics of this review. In particular, we will discuss recent developments in both tasks from the perspectives of classical machine learning and deep learning. Full article

This paper presents an effective method for measuring oil debris with high confidence to ensure the wear monitoring of aero-engines, which suffers from severe noise interference, weak signal characteristics, and false detection. First, an improved variational mode decomposition algorithm is proposed, which combines wavelet transform and interval threshold processing to suppress the complex noise interference on the signal. Then, a long-short-term memory neural network with deep scattering spectrum preprocessing is used to identify the signal characteristics under the multi-resolution analysis framework. The optimal hyperparameters are automatically configured using Bayesian optimization to solve the problem of weak, distorted, and hard-to-extract signal characteristics. Finally, a detection algorithm based on multi-window fusion judgment is applied to improve the confidence of the detection process, reduce the false detection and false alarm rate, and calculate the debris size information according to the sensor principle. The experimental results show that the proposed method can extract debris signals from noise with a signal-to-noise ratio improvement of more than 9 dB, achieve a high recognition accuracy of 99.76% with a missed detection rate of 0.24%, and output size information of debris to meet the need for aero-engine oil debris measurement. Full article

Rain can have a detrimental effect on optical components, leading to the appearance of streaks and halos in images captured during rainy conditions. These visual distortions caused by rain and mist contribute significant noise information that can compromise image quality. In this paper, we propose a novel approach for simultaneously removing both streaks and halos from the image to produce clear results. First, based on the principle of atmospheric scattering, a rain and mist model is proposed to initially remove the streaks and halos from the image by reconstructing the image. The Deep Memory Block (DMB) selectively extracts the rain layer transfer spectrum and the mist layer transfer spectrum from the rainy image to separate these layers. Then, the Multi-scale Convolution Block (MCB) receives the reconstructed images and extracts both structural and detailed features to enhance the overall accuracy and robustness of the model. Ultimately, extensive results demonstrate that our proposed model JDDN (Joint De-rain and De-mist Network) outperforms current state-of-the-art deep learning methods on synthetic datasets as well as real-world datasets, with an average improvement of 0.29 dB on the heavy-rainy-image dataset. Full article

Background and Objectives: Retromode is a relatively new retinal-imaging technique that is based on the transillumination principle and is obtained with a scanning laser ophthalmoscope that uses light in the infrared spectrum. The laser light penetrates into the deep retinal layers and the choroid. Retromode images are captured with a laterally displaced aperture, and the detector captures only the scattered light. The result is a high-contrast pseudo-three-dimensional image. Age-related macular degeneration (AMD) is a disabling retinal disease. AMD is characterized in its early stage by small and intermediate drusen formation, while the signs of intermediate AMD are large drusen and/or pigmentary abnormalities. Late AMD has two forms, geographic atrophy, which is the advanced form of dry AMD, and wet AMD. Most of the lesions of AMD are located in the outer layers of the retina. This new imaging method can provide a glimpse of the deep retinal layers’ topographic changes in a non-invasive, fast, and effective way that can match the other imaging tools available. Materials and Methods: The literature review was performed by searching the PubMed database using the following combination of keywords: retromode imaging and age-related macular degeneration. Relevant images similar to the ones in the literature were identified and used as models. Results: The purpose of this article is to highlight the utility of incorporating retromode imaging into the multimodal evaluation of the retina in patients with AMD and to gather and integrate these findings into a brief but comprehensive paper. Conclusions: Retromode imaging is a good screening, diagnosis, and monitoring tool for patients with AMD. Full article

This paper investigates the underwater optical image restoration method under the background of underwater target detection based on optical vision in AUVs. The light source used for AUV detection is different when the AUV operates in different depths. The natural light source is used in shallow water and the artificial light source is used in deep water. This paper investigates underwater optical image restoration in these two light conditions. Aiming at the problem of image blurring in underwater optical images, the traditional underwater image restoration method based on scattering model can obtain satisfactory image restoration performance in natural light conditions. However, it cannot obtain the same image restoration result in artificial light conditions. To solve this problem, this paper presents an improved underwater optical image restoration method based on the scattering model. The scattering model and power spectrum are used to solve the initial parameters of the filter, and the parameters are optimized based on an evaluation index. The index of image definition is introduced to evaluate the restoration performance and to achieve the satisfactory image restoration result in both natural light and artificial light conditions. The effectiveness of the presented method is verified by experiments. Full article

Long-range propagation of sound pulses in the deep ocean is considered. A new method for the estimation of the pulse angular spectrum is presented. The method is based on the Husimi transform of a wave field and can be realized with a short vertical array of nondirectional hydrophones. As a result, one obtains a diagram of the arrival pattern in the time–angle plane. The method is applied to a model of the underwater sound channel in the Sea of Japan. Special attention is paid to sound scattering on a cold synoptic eddy along the waveguide. It is shown that the synoptic eddy leads to a splitting of the individual ray’s arrivals into clusters with close angles and times. The random sound-speed perturbation induced by internal waves blurs these clusters into a fuzzy background and simultaneously broaden the angular spectrum of pulses. Nevertheless, it is found that the latter effect is relatively weak for short vertical arrays. In particular, it is shown that increasing the array length from 10 to 30 m results in the separation of the arrivals with opposite angles. Full article

Most methodologies for fault detection and diagnosis in prognostics and health management (PHM) systems use machine learning (ML) or deep learning (DL), in which either some features are extracted beforehand (in the case of typical ML approaches) or the filters are used to extract features autonomously (in the case of DL) to perform the critical classification task. In particular, in the fault detection and diagnosis of industrial robots where the primary sources of information are electric current, vibration, or acoustic emissions signals that are rich in information in both the temporal and frequency domains, techniques capable of extracting meaningful information from non-stationary frequency-domain signals with the ability to map the signals into their constituent components with compressed information are required. This has the potential to minimise the complexity and size of traditional ML- and DL-based frameworks. The deep scattering spectrum (DSS) is one of the approaches that use the Wavelet Transform (WT) analogy for separating and extracting information embedded in a signal’s various temporal and frequency domains. Therefore, the primary focus of this work is the investigation of the efficacy and applicability of the DSS’s feature domain relative to fault detection and diagnosis for the mechanical components of industrial robots. For this, multiple industrial robots with distinct mechanical faults were studied. Data were collected from these robots under different fault conditions and an approach was developed for classifying the faults using DSS’s low-variance features extracted from input signals. The presented approach was implemented on the practical test benches and demonstrated satisfactory performance in fault detection and diagnosis for simple and complex classification problems with a classification accuracy of 99.7% and 88.1%, respectively. The results suggest that, similarly to other ML techniques, the DSS offers significant potential in addressing fault classification challenges, especially for cases where the data are in the form of signals. Full article