Search Results (139)

This paper provides a comprehensive overview of the application of fractional calculus in modern optimization methods, with a focus on its impact in artificial intelligence (AI) and computational science. We examine how fractional-order derivatives have been integrated into traditional methodologies, including gradient descent, least mean squares algorithms, particle swarm optimization, and evolutionary methods. These modifications leverage the intrinsic memory and nonlocal features of fractional operators to enhance convergence, increase resilience in high-dimensional and non-linear environments, and achieve a better trade-off between exploration and exploitation. A systematic and chronological analysis of algorithmic developments from 2017 to 2025 is presented, together with representative pseudocode formulations and application cases spanning neural networks, adaptive filtering, control, and computer vision. Special attention is given to advances in variable- and adaptive-order formulations, hybrid models, and distributed optimization frameworks, which highlight the versatility of fractional-order methods in addressing complex optimization challenges in AI-driven and computational settings. Despite these benefits, persistent issues remain regarding computational overhead, parameter selection, and rigorous convergence analysis. This review aims to establish both a conceptual foundation and a practical reference for researchers seeking to apply fractional calculus in the development of next-generation optimization algorithms. Full article

Background: Neoadjuvant chemotherapy (NAC) is the important and effective approach to treat locally advanced breast cancer (LABC). The prediction of response to NAC prior to start is an efficient approach to obtaining perspective about the effectiveness of treatment. The objective of this study is to design a machine learning pipeline to predict tumor response to NAC treatment for patients with LABC using the combination of clinical features and radiomics computed tomography (CT) features. Method: A total of 858 clinical and radiomics CT features were determined for 117 patients with LABC to predict the tumor response to NAC treatment. Since the number of features is greater than the number of samples, dimensionality reduction is an indispensable step. To this end, we proposed a novel hybrid feature selection to not only select top features but also optimize the classifier hyperparameters. This hybrid feature selection has two phases. In the first phase, we applied a filter-based strategy feature selection technique using matrix rank theorem to remove all dependent and redundant features. In the second phase, we applied a genetic algorithm which coupled with the SVM classifier. The genetic algorithm determined the optimum number of features and top features. Performance of the proposed technique was assessed by balanced accuracy, accuracy, area under curve (AUC), and F1-score. This is the binary classification task to predict response to NAC. We consider three models for this study including clinical features, radiomics CT features, and a combination of clinical and radiomics CT features. Results: A total of 117 patients with LABC with a mean age of 52 ± 11 were studied in this study. Of these, 82 patients with LABC were the responder group (response to NAC) and 35 were the non-response group to chemotherapy. The best performance was obtained by the combination of clinical and CT radiomics features with Accuracy = 0.88. Conclusion: The results indicate that the combination of clinical features and CT radiomic features is an effective approach to predict response to NAC treatment for patients with LABC. Full article

Early printed books, particularly incunabula, are invaluable archives of the beginnings of modern educational systems. However, their complex layouts, antique typefaces, and page degradation caused by bleed-through and ink fading pose significant challenges for automatic transcription. In this work, we present a modular pipeline that addresses these problems by combining modern layout analysis and language modeling techniques. The pipeline begins with historical layout-aware text segmentation using Kraken, a neural network-based tool tailored for early typographic structures. Initial optical character recognition (OCR) is then performed with Kraken’s recognition engine, followed by post-correction using a fine-tuned ByT5 transformer model trained on manually aligned line-level data. By learning to map noisy OCR outputs to verified transcriptions, the model substantially improves recognition quality. The pipeline also integrates a preprocessing stage based on our previous work on bleed-through removal using robust statistical filters, including non-local means, Gaussian mixtures, biweight estimation, and Gaussian blur. This step enhances the legibility of degraded pages prior to OCR. The entire solution is open, modular, and scalable, supporting long-term preservation and improved accessibility of cultural heritage materials. Experimental results on 15th-century incunabula show a reduction in the Character Error Rate (CER) from around 38% to around 15% and an increase in the Bilingual Evaluation Understudy (BLEU) score from 22 to 44, confirming the effectiveness of our approach. This work demonstrates the potential of integrating transformer-based correction with layout-aware segmentation to enhance OCR accuracy in digital humanities applications. Full article

Stripe noise along the scanning direction significantly degrades the quality of high-resolution infrared line-scan images and impairs downstream tasks such as target detection and radiometric analysis. This paper presents a lightweight, single-frame, reference-free non-uniformity correction (NUC) method tailored for such images. The proposed approach enhances the directionality of stripe noise by projecting the 2D image into a 1D row-mean signal, followed by adaptive guided filtering driven by local median absolute deviation (MAD) to ensure spatial adaptivity and structure preservation. A spectral-entropy-constrained frequency-domain masking strategy is further introduced to suppress periodic and non-periodic interference. Extensive experiments on simulated and real datasets demonstrate that the method consistently outperforms six state-of-the-art algorithms across multiple metrics while maintaining the fastest runtime. The proposed method is highly suitable for real-time deployment in airborne, satellite-based, and embedded infrared imaging systems. It provides a robust and interpretable framework for future infrared enhancement tasks. Full article

Underwater object detection with Synthetic Aperture Sonar (SAS) images faces many problems, including low contrast, blurred edges, high-frequency noise, and missed small objects. To improve these problems, this paper proposes a high-accuracy underwater object detection algorithm for SAS images, named the HAUOD algorithm. First, considering SAS image characteristics, a sonar preprocessing module is designed to enhance the signal-to-noise ratio of object features. This module incorporates three-stage processing for image quality optimization, and the three stages include collaborative adaptive Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement, non-local mean denoising, and frequency-domain band-pass filtering. Subsequently, a novel C2fD module is introduced to replace the original C2f module to strengthen perception capabilities for low-contrast objects and edge-blurred regions. The proposed C2fD module integrates spatial differential feature extraction, dynamic feature fusion, and Enhanced Efficient Channel Attention (Enhanced ECA). Furthermore, an underwater multi-scale contextual attention mechanism, named UWA, is introduced to enhance the model’s discriminative ability for multi-scale objects and complex backgrounds. The proposed UWA module combines noise suppression, hierarchical dilated convolution groups, and dual-dimensional attention collaboration. Experiments on the Sonar Common object Detection dataset (SCTD) demonstrate that the proposed HAUOD algorithm achieves superior performance in small object detection accuracy and multi-scenario robustness, attaining a detection accuracy of $95.1\%$, which is $8.3\%$ higher than the baseline model (YOLOv8n). Compared with YOLOv8s, the proposed HAUOD algorithm can achieve $6.2\%$ higher accuracy with only $50.4\%$ model size, and reduce the computational complexity by half. Moreover, the HAUOD method exhibits significant advantages in balancing computational efficiency and accuracy compared to mainstream detection models. Full article

Photovoltaic (PV) technology, as a crucial source of clean energy, can effectively mitigate the impact of climate change caused by fossil fuel-based power generation. However, improper use of PV installations may encroach upon agricultural land, grasslands, and other land uses, thereby affecting local ecosystems. Exploring the spatial characteristics of centralized or distributed PV installations is essential for quantifying the development of clean energy and protecting agricultural land. Due to the distinct characteristics of centralized and distributed PV installations, large-scale mapping methods based on satellite remote sensing are insufficient for creating detailed PV distribution maps. This study proposes a model called Joint Semi-Supervised Weighted Adaptive PV Panel Recognition Model (JSWPVI)to achieve reliable PV mapping using UAV datasets. The JSWPVI employs a semi-supervised approach to construct and optimize a comprehensive segmentation network, incorporating the Spatial and Channel Weight Adaptive Model (SCWA) module to integrate different feature layers by reconstructing the spatial and channel weights of feature maps. Finally, a guided filtering algorithm is used to minimize non-edge noise while preserving edge integrity. Our results demonstrate that JSWPVI can accurately extract PV panels in both centralized and distributed scenarios, with an average extraction accuracy of 91.1% and a mean Intersection over Union of 77.7%. The findings of this study will assist regional policymakers in better quantifying renewable energy potential and assessing environmental impacts. Full article

Simultaneous Localization and Mapping (SLAM) is an effective method for estimating and correcting the pose of the mobile robot. However, a large amount of external noise and observed outliers in complex unknown environments often lead to a decrease in the estimation accuracy and robustness of the SLAM algorithm. To improve the performance of the Square Root Unscented Kalman Filter SLAM (SRUKF-SLAM), this paper proposes the Maximum Correntropy Square Root Unscented Kalman Filter SLAM (MCSRUKF-SLAM) algorithm. The method first generates an estimate of the predicted state and covariance matrix through the Unscented Transform (UT), and then obtains the square root matrix of the covariance through Cholesky and QR decomposition to replace the original covariance, effectively preserving the positive definiteness of the covariance and improving the accuracy of the algorithm. Moreover, the proposed MCSRUKF-SLAM recharacterizes measurement information at the cost of the Maximum Correntropy (MC) instead of the Minimum Mean Square Error (MMSE), effectively improving the SLAM algorithm’s ability to suppress non-Gaussian noise. The simulation results show that compared with EKF-SLAM, UKF-SLAM, SRUKF-SLAM, and MCUKF-SLAM, the accuracy of the proposed MCSRUKF-SLAM in Gaussian mixture noise improves by 81.8%, 80.9%, 78.7%, and 63.6%, and the accuracy of the proposed MCSRUKF-SLAM in colored noise improves by 50.3%, 39.9%, 38.2%, and 36.3%. Full article

Accurate indoor localization in wireless sensor networks remains a non-trivial challenge, particularly in complex environments characterized by signal variability and multipath propagation. This study presents a ZigBee-based localization approach that integrates multi-stage preprocessing of received signal strength indicator (RSSI) data with a reliability-aware extension of the maximum likelihood estimation (MLE) algorithm. To improve measurement stability, a hybrid filtering framework combining Kalman filtering, Dixon’s Q test, Gaussian smoothing, and mean averaging is applied to reduce the influence of noise and outliers. Building on the filtered data, the proposed method introduces a noise and link quality indicator (LQI)-based dynamic weighting mechanism that adjusts the contribution of each distance estimate during localization. The approach was evaluated under simulated and semi-physical non-line-of-sight (NLOS) indoor conditions designed to reflect practical deployment scenarios. While based on a limited set of representative test points, the method yielded improved positioning consistency and achieved an average accuracy gain of 11.7% over conventional MLE in the tested environments. These results suggest that the proposed method may offer a feasible solution for resource-constrained localization applications requiring robustness to signal degradation. Full article

Worldwide, the yellow-fleshed kiwifruit (Actinidia chinensis) is an important crop that possesses great economic significance due to its nutritional, medicinal and ornamental values. The call for the expansion of the kiwifruit industry in South Africa, due to rising local and international market demand, resulted in the introduction of new plant species in sub-mountainous areas, where soil and climate conditions are more suitable for intensive kiwifruit production than in lowland areas. Consequently, a need to develop suitable commercial protocols for mass propagation of A. chinensis emerged. This study introduces an optimized micropropagation protocol for A. chinensis, facilitating seed germination, seedling development and multiple shoot induction. For seed germination, the effect of cold stratification (CS) and gibberellic acid (GA₃) alone and in combination on in vitro germination of A. chinensis seeds was studied. Sterile seeds were stratified at 4 °C for 28 and 42 days. Batches of stratified and non-stratified (control) seeds were germinated on plant growth regulator-free Murashige and Skoog (MS) media and also on sterile filter paper bridges moistened with dH₂O and GA₃ concentrations of 500, 1000, 1500, 2000 and 2500 ppm. Seeds from the control and the CS treatments alone did not germinate on MS medium. However, on filter paper bridges, seeds cold stratified for 28 days yielded only a 20% germination percentage (GP), whereas CS for 42 days did not promote germination. A maximum GP of 64% and a mean germination time (MGT) of 27.52 days were achieved at a 2000 ppm GA₃ concentration. Cold stratification (28 days) followed by GA₃ treatments yielded an optimum GP of 80% and optimum MGT of 18.94 days at GA₃ concentrations of 500 ppm. In contrast, CS (42 days) followed by GA₃ yielded a maximum GP of 72% and MGT of 18.80 days at a GA₃ of 500 ppm. Conclusively, CS alone had little effect on germination, whereas CS (28 and 42 days) followed by GA₃ significantly (p ≤ 0.05) improved GP. Germinated seeds on moist filter paper can produce seedlings when sub-cultured on MS medium for seedling development. For multiple shoot induction, in vitro shoot culture of A. chinensis was carried out using apical and basal shoot explants from the above in vitro-produced seedlings. These explants were cultured on MS supplemented with 2.2 µM and 4.4 µM 6-Benzylaminopurine (BAP) for shoot multiplication. Axillary shoot proliferation was not observed on apical shoot explants after 4 weeks of culture on MS medium with 2.2 µM BAP. In contrast, the basal shoot explants produced 2–3 axillary shoots, tendrils and calluses at the base on the same medium. The highest number (3–4) of multiple shoots was attained from these basal shoot explants after subculture (10–12 weeks) in the same culture medium. In contrast, only elongation and rooting of apical shoot explants, without axillary shoot induction, occurred after the subculture. Regenerated plantlets derived from both apical and basal shoot explants were successfully acclimatised under a controlled environment at 24 ± 2 °C and 16 h photoperiod of 150–200 µmol m⁻² s⁻¹ light intensity. A similar response was observed for both types of explants of A. chinensis when cultured on MS with 4.4 µM BAP, although the higher concentration of BAP affected the morphological appearance of the regenerated plantlets that had shorter stems and smaller and narrower leaves compared to plantlets derived from 2.2 µM BAP. Full article

Electromyography (EMG) signals are fundamental in neurorehabilitation as they provide a non-invasive means of capturing the electrical activity of muscles, enabling precise detection of motor intentions. This capability is essential for controlling assistive devices, such as therapeutic exoskeletons, that aim to restore mobility and improve motor function in patients with neuromuscular impairments. The integration of EMG into neurorehabilitation systems allows for adaptive and patient-specific interventions, addressing the variability in motor recovery needs. However, achieving the high fidelity, low latency, and robustness required for real-time control of these devices remains a significant challenge. This paper introduces a novel multi-channel electromyography (EMG) acquisition system implemented on a System-on-Chip (SoC) architecture for robotic neurorehabilitation. The system employs the Zynq-7000 SoC, which integrates an Advanced RISC Machine (ARM) processor, for high-level control and an FPGA for real-time signal processing. The architecture enables precise synchronization of up to eight EMG channels, leveraging high-speed analog-to-digital conversion and advanced filtering techniques implemented directly at the measurement site. By performing filtering and initial signal processing locally, prior to transmission to other subsystems, the system minimizes noise both through optimized processing and by reducing the distance to the muscle, thereby significantly enhancing the signal-to-noise ratio (SNR). A dedicated communication interface ensures low-latency data transfer to external controllers, crucial for adaptive control loops in exoskeletal applications. Experimental results validate the system’s capability to deliver high signal fidelity and low processing delays, outperforming commercial alternatives in terms of flexibility and scalability. This implementation provides a robust foundation for real-time bio-signal processing, advancing the integration of EMG-based control in neurorehabilitation devices. Full article

We focus on detecting anomalies in images where the data distribution is supported by a lower-dimensional embedded manifold. Approaches based on autoencoders have aimed to control their capacity either by reducing the size of the bottleneck layer or by imposing sparsity constraints on their activations. However, none of these techniques explicitly penalize the reconstruction of anomalous regions, often resulting in poor detection. We tackle this problem by adapting a self-supervised learning regime that essentially implements a denoising autoencoder with structured non-i.i.d. noise. Informally, our objective is to regularize the model to produce locally consistent reconstructions while replacing irregularities by acting as a filter that removes anomalous patterns. Formally, we show that the resulting model resembles a nonlinear orthogonal projection of partially corrupted images onto the submanifold of uncorrupted examples. Furthermore, we identify the orthogonal projection as an optimal solution for a specific regularized autoencoder related to contractive and denoising variants. In addition, orthogonal projection provides a conservation effect by largely preserving the original content of its arguments. Together, these properties facilitate an accurate detection and localization of anomalous regions by means of the reconstruction error. We support our theoretical analysis by achieving state-of-the-art results (image/pixel-level AUROC of 99.8/99.2%) on the MVTec AD dataset—a challenging benchmark for anomaly detection in the manufacturing domain. Full article

China’s rail transit system is developing rapidly, but achieving seamless high-precision localization of trains throughout the entire route in closed environments such as tunnels and culverts still faces significant challenges. Traditional localization technologies cannot meet current demands, and the present paper proposes an autonomous localization method for trains based on pulse observation in a tunnel environment. First, the Letts criterion is used to eliminate abnormal gyro data, the CEEMDAN method is employed for signal decomposition, and the decomposed signals are classified using the continuous mean square error and norm method. Noise reduction is performed using forward linear filtering and dynamic threshold filtering, respectively, maximizing the retention of its effective signal components. A SINS/OD integrated localization model is established, and an observation equation is constructed based on velocity matching, resulting in an 18-dimensional complex state space model. Finally, the EM algorithm is used to address Non-Line-Of-Sight and multipath effect errors. The optimized model is then applied in the Kalman filter to better adapt to the system’s observation conditions. By dynamically adjusting the noise covariance, the localization system can continue to maintain continuous high-precision position information output in a tunnel environment. Full article

Background: Glioblastoma (GBM) is a highly aggressive, invasive, and growth factor-independent grade IV glioma. Survival following the diagnosis is generally poor, with a median survival of approximately 15 months, and it is considered the most aggressive and lethal central nervous system tumor. Conventional treatments based on surgery, chemotherapy, and radiation therapy only delay progression, and death is inevitable. Malignant glioma cells are resistant to traditional therapies, potentially due to a subpopulation of glioma stem cells that are invasive and capable of rapid regrowth. Methods: This is a literature review. The systematic retrieval of information was performed on PubMed, Embase, and Google Scholar. Specified keywords were used in PubMed and the articles retrieved were published in peer-reviewed scientific journals and were associated with brain GBM cancer and the sodium iodide symporter (NIS). Additionally, the words ‘radionuclide therapy OR mesenchyma, OR radioiodine OR iodine-131 OR molecular imaging OR gene therapy OR translational imaging OR targeted OR theranostic OR symporter OR virus OR solid tumor OR combined therapy OR pituitary OR plasmid AND glioblastoma OR GBM OR GB OR glioma’ were also used in the appropriate literature databases of PubMed and Google Scholar. A total of 68,244 articles were found in this search on Mesenchymal Stem Cell Sodium Iodide Symporter and GBM. These articles were found till 2024. To study recent advances, a filter was added to include articles only from 2014 to 2024, duplicates were removed, and articles not related to the title were excluded. These came out to be 78 articles. From these, nine were not retrieved and only seven were selected after the removal of keyword mismatched articles. Appropriate studies were isolated, and important information from each of them was understood and entered into a database from which the information was used in this article. Results: As a result of their natural capacity to identify malignancies, MSCs are employed as tumor therapy vehicles. Because MSCs may be transplanted using several methods, they have been proposed as the ideal vehicles for NIS gene transfer. MSCs have been used as a delivery vector for anticancer drugs in many tumor models due to their capacity to move precisely to malignancies. Also, by directly injecting radiolabeled MSCs into malignant tumors, a therapeutic dosage of beta radiation may be deposited, with the added benefit that the tumor would only localize and not spread to the surrounding healthy tissues. Conclusion: The non-invasive imaging-based detection of glioma stem cells presents an alternate means to monitor the tumor and diagnose and evaluate recurrence. The sodium iodide symporter gene is a specific gene in a variety of human thyroid diseases that functions to move iodine into the cell. In recent years, an increasing number of studies related to the sodium iodide symporter gene have been reported in a variety of tumors and as therapeutic vectors for imaging and therapy. Gene therapy and nuclear medicine therapy for GBM provide a new direction. In all the preclinical studies reviewed, image-guided cell therapy led to greater survival benefits and, therefore, has the potential to be translated into techniques in glioblastoma treatment trials. Full article

The labor shortage and rising costs in the greenhouse industry have driven the development of automation, with the core of autonomous operations being positioning and navigation technology. However, precise positioning in complex greenhouse environments and narrow aisles poses challenges to localization technologies. This study proposes a multi-sensor fusion positioning and navigation robot based on ultra-wideband (UWB), an inertial measurement unit (IMU), odometry (ODOM), and a laser rangefinder (RF). The system introduces a confidence optimization algorithm based on weakening non-line-of-sight (NLOS) for UWB positioning, obtaining calibrated UWB positioning results, which are then used as a baseline to correct the positioning errors generated by the IMU and ODOM. The extended Kalman filter (EKF) algorithm is employed to fuse multi-sensor data. To validate the feasibility of the system, experiments were conducted in a Chinese solar greenhouse. The results show that the proposed NLOS confidence optimization algorithm significantly improves UWB positioning accuracy by 60.05%. At a speed of 0.1 m/s, the root mean square error (RMSE) for lateral deviation is 0.038 m and for course deviation is 4.030°. This study provides a new approach for greenhouse positioning and navigation technology, achieving precise positioning and navigation in complex commercial greenhouse environments and narrow aisles, thereby laying a foundation for the intelligent development of greenhouses. Full article

Noise in computed tomography (CT) is inevitably generated, which lowers the accuracy of disease diagnosis. The non-local means approach, a software technique for reducing noise, is widely used in medical imaging. In this study, we propose a noise reduction algorithm based on fast non-local means (FNLMs) and apply it to CT images of a phantom created using 3D printing technology. The self-produced phantom was manufactured using filaments with similar density to human brain tissues. To quantitatively evaluate image quality, the contrast-to-noise ratio (CNR), coefficient of variation (COV), and normalized noise power spectrum (NNPS) were calculated. The results demonstrate that the optimized smoothing factors of FNLMs are 0.08, 0.16, 0.22, 0.25, and 0.32 at 0.001, 0.005, 0.01, 0.05, and 0.1 of noise intensities, respectively. In addition, we compared the optimized FNLMs with noisy, local filters and total variation algorithms. As a result, FNLMs showed superior performance compared to various denoising techniques. Particularly, comparing the optimized FNLMs to the noisy images, the CNR improved by 6.53 to 16.34 times, COV improved by 6.55 to 18.28 times, and the NNPS improved by 10⁻² mm² on average. In conclusion, our approach shows significant potential in enhancing CT image quality with anthropomorphic phantoms, thus addressing the noise issue and improving diagnostic accuracy. Full article