Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (17,267)

Search Parameters:
Keywords = pre-processing

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
20 pages, 4698 KiB  
Article
Nanostructured Chromium PVD Thin Films Fabricated Through Copper–Chromium Selective Dissolution
by Stefano Mauro Martinuzzi, Stefano Caporali, Rosa Taurino, Lapo Gabellini, Enrico Berretti, Eric Schmeer and Nicola Calisi
Materials 2025, 18(4), 894; https://doi.org/10.3390/ma18040894 - 18 Feb 2025
Abstract
This study investigates the fabrication of nanostructured chromium thin films via selective dissolution of PVD-deposited Cu–Cr thin films. The effects of the deposition parameters on the structural, chemical, and morphological properties of the films are systematically analyzed. Starting from a thin film composed [...] Read more.
This study investigates the fabrication of nanostructured chromium thin films via selective dissolution of PVD-deposited Cu–Cr thin films. The effects of the deposition parameters on the structural, chemical, and morphological properties of the films are systematically analyzed. Starting from a thin film composed of 50 wt.% chromium and 50 wt.% copper, deposited onto a substrate pre-heated to 300 °C, we demonstrate that the following dealloying process carried out in a diluted nitric acid solution yields nanostructured chromium films with high porosity, large surface area, enhanced wettability and neglectable copper content. These findings underline the critical influence of the deposition temperature and alloy composition on achieving optimal film properties. Full article
(This article belongs to the Special Issue Advancements in Thin Film Deposition Technologies)
13 pages, 4955 KiB  
Article
Retinitis Pigmentosa Classification with Deep Learning and Integrated Gradients Analysis
by Hélder Ferreira, Ana Marta, Jorge Machado, Inês Couto, João Pedro Marques, João Melo Beirão and António Cunha
Appl. Sci. 2025, 15(4), 2181; https://doi.org/10.3390/app15042181 - 18 Feb 2025
Abstract
Inherited retinal diseases (IRDs) are genetic disorders affecting photoreceptors and the retinal pigment epithelium, leading to progressive vision loss. Retinitis pigmentosa (RP), the most common IRD, manifests as night blindness, peripheral vision loss, and eventually central vision decline. RP is genetically diverse and [...] Read more.
Inherited retinal diseases (IRDs) are genetic disorders affecting photoreceptors and the retinal pigment epithelium, leading to progressive vision loss. Retinitis pigmentosa (RP), the most common IRD, manifests as night blindness, peripheral vision loss, and eventually central vision decline. RP is genetically diverse and can be categorized into non-syndromic and syndromic. Advanced imaging technologies such as fundus autofluorescence (FAF) and spectral-domain optical coherence tomography (SD-OCT) facilitate diagnosing and managing these conditions. The integration of artificial intelligence in analyzing retinal images has shown promise in identifying genes associated with RP. This study used a dataset from Portuguese public hospitals, comprising 2798 FAF images labeled for syndromic and non-syndromic RP across 66 genes. Three pre-trained models, Inception-v3, ResNet-50, and VGG-19, were used to classify these images, obtaining an accuracy of over 80% in the training data and 54%, 56%, and 54% in the test data for all models. Data preprocessing included class balancing and boosting to address variability in gene representation. Model performance was evaluated using some main metrics. The findings demonstrate the effectiveness of deep learning in automatically classifying retinal images for different RP-associated genes, marking a significant advancement in the diagnostic capabilities of artificial intelligence and advanced imaging techniques in IRD. Full article
(This article belongs to the Special Issue Advances and Applications of Medical Imaging Physics)
Show Figures

Figure 1

18 pages, 5759 KiB  
Article
Hybrid Tool Holder by Laser Powder Bed Fusion of Dissimilar Steels: Towards Eliminating Post-Processing Heat Treatment
by Faraz Deirmina, Ville-Pekka Matilainen and Simon Lövquist
J. Manuf. Mater. Process. 2025, 9(2), 64; https://doi.org/10.3390/jmmp9020064 - 18 Feb 2025
Abstract
The hybridization of additive manufacturing (AM) with conventional manufacturing processes in tooling applications allows the customization of the tool. Examples include weight reduction, improving the vibration-dampening properties, or directing the coolant to the critical zones through intricate conformal cooling channels aimed at extending [...] Read more.
The hybridization of additive manufacturing (AM) with conventional manufacturing processes in tooling applications allows the customization of the tool. Examples include weight reduction, improving the vibration-dampening properties, or directing the coolant to the critical zones through intricate conformal cooling channels aimed at extending the tool life. In this regard, metallurgical challenges like the need for a post-processing heat treatment in the AM segment to meet the thermal and mechanical properties requirements persist. Heat treatment can destroy the dimensional accuracy of the pre-manufactured heat-treated wrought segment, on which the AM part is built. In the case of dissimilar joints, heat treatment may further impact the interface properties through the ease of diffusional reactions at elevated temperatures or buildup of residual stresses at the interface due to coefficient of thermal expansion (CTE) mismatch. In this communication, we report on the laser powder bed fusion (L-PBF) processing of MAR 60, a weldable carbon-free maraging powder, to manufacture a hybrid tool holder for general turning applications, comprising a wrought segment in 25CrMo4 low-alloy carbon-bearing tool steel. After L-PBF process optimization and manipulation, as-built (AB) MAR 60 steel was characterized with a hardness and tensile strength of ~450 HV (44–45 HRC) and >1400 MPa, respectively, matching those of pre-manufactured wrought 25CrMo4 (i.e., 42–45 HRC and 1400 MPa). The interface was defect-free with strong metallurgical bonding, showing slight microstructural and hardness variations, with a thickness of less than 400 µm. The matching strength and high Charpy V-notch impact energy (i.e., >40 J) of AB MAR 60 eliminate the necessity of any post-manufacturing heat treatment in the hybrid tool. Full article
(This article belongs to the Special Issue Advances in Dissimilar Metal Joining and Welding)
25 pages, 4211 KiB  
Article
Numerical Analysis of the Characteristic Chemical Timescale of a C2H4/O2 Non-Premixed Rotating Detonation Engine
by Mohammed Niyasdeen Nejaamtheen, Bu-Kyeng Sung and Jeong-Yeol Choi
Energies 2025, 18(4), 989; https://doi.org/10.3390/en18040989 - 18 Feb 2025
Abstract
A three-dimensional numerical investigation using ethylene–oxygen was conducted to examine the characteristics of detonation waves in a non-premixed rotating detonation engine (RDE) across three equivalence ratio conditions: fuel-lean, stoichiometric, and fuel-rich. The study aims to identify the distinct timescales associated with detonation wave [...] Read more.
A three-dimensional numerical investigation using ethylene–oxygen was conducted to examine the characteristics of detonation waves in a non-premixed rotating detonation engine (RDE) across three equivalence ratio conditions: fuel-lean, stoichiometric, and fuel-rich. The study aims to identify the distinct timescales associated with detonation wave propagation within the combustor and to analyze their impact on detonation wave behavior, emphasizing the influence of equivalence ratio and injector behavior on detonation wave characteristics. The results indicate that the wave behavior varies with mixture concentration, with the ethylene injector demonstrating greater stiffness compared to the oxygen injector. In lean mixtures, characterized by excess oxidizer, waves exhibit less intensity and slower progression toward equilibrium, resulting in prolonged reaction times. Rich mixtures, with excess fuel, also show a delayed approach to equilibrium and an extended chemical reaction timescale. In contrast, the near-stoichiometric mixture achieves efficient combustion with the highest thermicity, rapidly reaching equilibrium and exhibiting the shortest chemical reaction timescale. Overall, the induction timescale is generally 2–3 times longer than its respective chemical reaction timescale, while the equilibrium timescale spans a broad range, reflecting the complex, rapid dynamics inherent in these chemical processes. This study identifies the role of the characteristic chemical timescale in influencing the progression of pre-detonation deflagration in practical RDEs. Prolonged induction times in non-ideal conditions, such as those arising from equivalence ratio variations, promote incomplete reactions, thereby contributing to pre-detonation phenomena and advancing our understanding of the underlying flow physics. Full article
21 pages, 8230 KiB  
Article
Cloud Detection in Remote Sensing Images Based on a Novel Adaptive Feature Aggregation Method
by Wanting Zhou, Yan Mo, Qiaofeng Ou and Shaowei Bai
Sensors 2025, 25(4), 1245; https://doi.org/10.3390/s25041245 - 18 Feb 2025
Abstract
Cloud detection constitutes a pivotal task in remote sensing preprocessing, yet detecting cloud boundaries and identifying thin clouds under complex scenarios remain formidable challenges. In response to this challenge, we designed a network model, named NFCNet. The network comprises three submodules: the Hybrid [...] Read more.
Cloud detection constitutes a pivotal task in remote sensing preprocessing, yet detecting cloud boundaries and identifying thin clouds under complex scenarios remain formidable challenges. In response to this challenge, we designed a network model, named NFCNet. The network comprises three submodules: the Hybrid Convolutional Attention Module (HCAM), the Spatial Pyramid Fusion Attention (SPFA) module, and the Dual-Stream Convolutional Aggregation (DCA) module. The HCAM extracts multi-scale features to enhance global representation while matching channel importance weights to focus on features that are more critical to the detection task. The SPFA module employs a novel adaptive feature aggregation method that simultaneously compensates for detailed information lost in the downsampling process and reinforces critical information in upsampling to achieve more accurate discrimination between cloud and non-cloud pixels. The DCA module integrates high-level features with low-level features to ensure that the network maintains its sensitivity to detailed information. Experimental results using the HRC_WHU, CHLandsat8, and 95-Cloud datasets demonstrate that the proposed algorithm surpasses existing optimal methods, achieving finer segmentation of cloud boundaries and more precise localization of subtle thin clouds. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

12 pages, 5726 KiB  
Article
Computer-Assisted Evaluation of Zygomatic Fracture Outcomes: Case Series and Proposal of a Reproducible Workflow
by Simone Benedetti, Andrea Frosolini, Flavia Cascino, Laura Viola Pignataro, Leonardo Franz, Gino Marioni, Guido Gabriele and Paolo Gennaro
Tomography 2025, 11(2), 19; https://doi.org/10.3390/tomography11020019 - 18 Feb 2025
Abstract
Background: Zygomatico-maxillary complex (ZMC) fractures are prevalent facial injuries with significant functional and aesthetic implications. Computer-assisted surgery (CAS) offers precise surgical planning and outcome evaluation. The study aimed to evaluate the application of CAS in the analysis of ZMC fracture outcomes and to [...] Read more.
Background: Zygomatico-maxillary complex (ZMC) fractures are prevalent facial injuries with significant functional and aesthetic implications. Computer-assisted surgery (CAS) offers precise surgical planning and outcome evaluation. The study aimed to evaluate the application of CAS in the analysis of ZMC fracture outcomes and to propose a reproducible workflow for surgical outcome assessment using cephalometric landmarks. Methods: A retrospective cohort study was conducted on 16 patients treated for unilateral ZMC fractures at the Maxillofacial Surgery Unit of Siena University Hospital (2017–2024). Inclusion criteria included ZMC fractures classified as Zingg B or C, treated via open reduction and internal fixation (ORIF). Pre- and post-operative CT scans were processed for two- and three-dimensional analyses. Discrepancies between CAS-optimized reduction and achieved surgical outcomes were quantified using cephalometric landmarks and volumetric assessments. Results: Out of the 16 patients (69% male, mean age 48.1 years), fractures were predominantly on the right side (81%). CAS comparison between the post-operative and the contralateral side revealed significant asymmetries along the X and Y axes, particularly in the fronto-zygomatic suture (FZS), zygo-maxillary point (MP), and zygo-temporal point (ZT). Computer-assisted comparison between the post-operative and the CAS-simulated reductions showed statistical differences along all three orthonormal axes, highlighting the challenges in achieving ideal symmetry despite advanced surgical techniques. CAS-optimized reductions demonstrated measurable improvements compared to traditional methods, underscoring their utility in outcome evaluation. Conclusions: CAS technology enhances the precision of ZMC fracture outcome evaluation, allowing for detailed comparison between surgical outcomes and virtual simulations. Its application underscores the potential for improved surgical planning and execution, especially in complex cases. Future studies should focus on expanding sample size, refining workflows, and integrating artificial intelligence to automate processes for broader clinical applicability. Full article
Show Figures

Figure 1

23 pages, 11853 KiB  
Article
GDPGO-SAM: An Unsupervised Fine Segmentation of Desert Vegetation Driven by Grounding DINO Prompt Generation and Optimization Segment Anything Model
by Shuzhen Hua, Biao Yang, Xinchang Zhang, Ji Qi, Fengxi Su, Jing Sun and Yongjian Ruan
Remote Sens. 2025, 17(4), 691; https://doi.org/10.3390/rs17040691 - 18 Feb 2025
Abstract
Desert encroachment significantly threatens the living and activity space of humanity, and undertaking human-directed vegetation restoration is one of the effective ways to prevent desert expansion. In the process of desert vegetation restoration, counting the number of tree saplings for rapidly assessing the [...] Read more.
Desert encroachment significantly threatens the living and activity space of humanity, and undertaking human-directed vegetation restoration is one of the effective ways to prevent desert expansion. In the process of desert vegetation restoration, counting the number of tree saplings for rapidly assessing the survival rate of vegetation (such as Haloxylon ammodendron) is a critical task within the restoration process. However, traditional ground-based statistical methods are resource-intensive and time-consuming. This paper proposed a novel unsupervised fine segmentation framework driven by Grounding DINO prompt generation and optimization segment anything model, termed GDPGO-SAM, designed for the segmentation of desert vegetation from UAV-derived remote sensing imagery, thereby facilitating the rapid inventory of tree saplings counts. The framework combines the Grounding DINO object detector and the pre-trained visual model SAM, employing a task-prior-based prompt optimization mechanism to effectively capture the innate features of desert vegetation. This method achieves zero-sample instance segmentation of desert vegetation with an overall accuracy (OA) of 96.56%, a mean Intersection over Union (mIoU) of 81.50%, and a kappa coefficient (kappa) of 0.782, successfully overcoming the limitations of traditional supervised models that rely on passive memorization rather than true recognition. This research significantly enhances the precision of vegetation extraction and canopy depiction, providing strong support for the management of desert vegetation restoration and combating desert expansion. Full article
Show Figures

Figure 1

15 pages, 1877 KiB  
Article
GraphEPN: A Deep Learning Framework for B-Cell Epitope Prediction Leveraging Graph Neural Networks
by Feng Wang, Xiangwei Dai, Liyan Shen and Shan Chang
Appl. Sci. 2025, 15(4), 2159; https://doi.org/10.3390/app15042159 - 18 Feb 2025
Abstract
B-cell epitope prediction is crucial for advancing immunology, particularly in vaccine development and antibody-based therapies. Traditional experimental techniques are hindered by high costs, time consumption, and limited scalability, making them unsuitable for large-scale applications. Computational methods provide a promising alternative, enabling high-throughput screening [...] Read more.
B-cell epitope prediction is crucial for advancing immunology, particularly in vaccine development and antibody-based therapies. Traditional experimental techniques are hindered by high costs, time consumption, and limited scalability, making them unsuitable for large-scale applications. Computational methods provide a promising alternative, enabling high-throughput screening and accurate predictions. However, existing computational approaches often struggle to capture the complexity of protein structures and intricate residue interactions, highlighting the need for more effective models. This study presents GraphEPN, a novel B-cell epitope prediction framework combining a vector quantized variational autoencoder (VQ-VAE) with a graph transformer. The pre-trained VQ-VAE captures both discrete representations of amino acid microenvironments and continuous structural embeddings, providing a comprehensive feature set for downstream tasks. The graph transformer further processes these features to model long-range dependencies and interactions. Experimental results demonstrate that GraphEPN outperforms existing methods across multiple datasets, achieving superior prediction accuracy and robustness. This approach underscores the significant potential for applications in immunodiagnostics and vaccine development, merging advanced deep learning-based representation learning with graph-based modeling. Full article
Show Figures

Figure 1

18 pages, 3749 KiB  
Article
Machine Learning-Driven Prediction of Vitamin D Deficiency Severity with Hybrid Optimization
by Usharani Bhimavarapu, Gopi Battineni and Nalini Chintalapudi
Bioengineering 2025, 12(2), 200; https://doi.org/10.3390/bioengineering12020200 - 18 Feb 2025
Abstract
There is a growing need to predict the severity of vitamin D deficiency (VDD) through non-invasive methods due to its significant global health concerns. For vitamin D-level assessments, the 25-hydroxy vitamin D (25-OH-D) blood test is the standard, but it is often not [...] Read more.
There is a growing need to predict the severity of vitamin D deficiency (VDD) through non-invasive methods due to its significant global health concerns. For vitamin D-level assessments, the 25-hydroxy vitamin D (25-OH-D) blood test is the standard, but it is often not a practical test. This study is focused on developing a machine learning (ML) model that is clinically acceptable for accurately detecting vitamin D status and eliminates the need for 25-OH-D determination while addressing overfitting. To enhance the capacity of the classification system to predict multiple classes, preprocessing procedures such as data reduction, cleaning, and transformation were used on the raw vitamin D dataset. The improved whale optimization (IWOA) algorithm was used for feature selection, which optimized weight functions to improve prediction accuracy. To gauge the effectiveness of the proposed IWOA algorithm, evaluation metrics like precision, accuracy, recall, and F1-score were used. The results showed a 99.4% accuracy, demonstrating that the proposed method outperformed the others. A comparative analysis demonstrated that the stacking classifier was the superior choice over the other classifiers, highlighting its effectiveness and robustness in detecting deficiencies. Incorporating advanced optimization techniques, the proposed method’s promise for generating accurate predictions is highlighted in the study. Full article
Show Figures

Graphical abstract

20 pages, 16736 KiB  
Article
Numerical Simulation of Mechanical Response of Tunnel Breakage in the Construction of Cross Passages by Mechanical Excavation Method Using Flat-Face Cutterhead
by Bingyi Li, Xianghong Li and Songyu Liu
Appl. Sci. 2025, 15(4), 2153; https://doi.org/10.3390/app15042153 - 18 Feb 2025
Abstract
Mechanical construction has gradually been applied in cross passages of metro lines, but more mechanical mechanisms should be revealed. The section between Jingrong Street Station and Kunjia Road Station in Suzhou Metro Line 11 adopts a mechanical construction method to construct a cross [...] Read more.
Mechanical construction has gradually been applied in cross passages of metro lines, but more mechanical mechanisms should be revealed. The section between Jingrong Street Station and Kunjia Road Station in Suzhou Metro Line 11 adopts a mechanical construction method to construct a cross passage. A novel flat-face cutterhead, which is different from curved cutter head is first used to cut and break the main tunnel in construction of cross passage. Based on the background of practical engineering, the finite element method was applied to simulate the breaking process of the main tunnel to explore the dynamic variation in the mechanical response of the segments cut by the flat-face cutterhead. The results indicate that the maximum vertical displacement caused by cutting mainly concentrates on the top of the fully cut rings. The maximum horizontal displacement occurs at the waist on the side of the tunnel portal in the semi-cut rings. The axial force level inside both types of segment rings reaches its peak after the tunnel is formed. The maximum axial force exists at the bottom and top of the fully cut ring and semi-cut ring, respectively. The change in the displacement around the portal is not substantial before the third stage, and it begins to increase significantly from the moment the concrete at the portal is penetrated. The existence of the pre-support system effectively controls the displacement of the third and fourth fully cut rings. Emphasis should be placed on reinforcing the soil near the top and waist of the second to fifth rings. The findings demonstrate that the application of flat-face cutterhead in mechanical construction of cross passages is safe, reliable, and efficient, and can provide valuable suggestions for further cutting parameters and soil reinforcement as well. Full article
(This article belongs to the Section Civil Engineering)
Show Figures

Figure 1

20 pages, 1828 KiB  
Article
Research on Sentiment Analysis of Online Public Opinion Based on RoBERTa–BiLSTM–Attention Model
by Jiangao Deng and Yue Liu
Appl. Sci. 2025, 15(4), 2148; https://doi.org/10.3390/app15042148 - 18 Feb 2025
Abstract
Public opinion comments are important for the public to express their emotions and demands. Accordingly, identifying the public emotions contained in comments and taking corresponding countermeasures according to the changes in the emotions are of great theoretical and practical significance to online public [...] Read more.
Public opinion comments are important for the public to express their emotions and demands. Accordingly, identifying the public emotions contained in comments and taking corresponding countermeasures according to the changes in the emotions are of great theoretical and practical significance to online public opinion management. This study took a public opinion event at a college as an example. Firstly, the microblogs and comment data related to the event were crawled with Python coding, and pre-processing operations such as cleaning, word splitting, and de-noising were carried out; then, the stage of public opinion was divided into phases based on the daily public opinion sound volume, Baidu index, and key time points of the event. Secondly, for sentiment analysis, a supplementary sentiment dictionary of the event was constructed based on the SO-PMI algorithm and merged with the commonly used sentiment dictionary to pre-annotate the sentiment corpus; then, the RoBERTa–BiLSTM–Attention model was constructed to classify the sentiment of microblog comments; after that, four evaluation indexes were selected and ablation experiments were set up to verify the performance of the model. Finally, based on the results of the sentiment classification, we drew public opinion trends and sentiment evolution graphs for analysis. The results showed that the supplementary dictionary constructed based on the SO-PMI algorithm significantly improved the pre-labelling accuracy. The RoBERTa–BiLSTM–Attention model achieved 91.56%, 90.87%, 91.07%, and 91.17% in accuracy, precision, recall, and F1-score, respectively. The situation notification, expert response, regulatory dynamics, and secondary public opinion will trigger significant fluctuations in the volume of public opinion and public sentiment. Full article
Show Figures

Figure 1

18 pages, 5677 KiB  
Article
Computer Vision-Based Concrete Crack Identification Using MobileNetV2 Neural Network and Adaptive Thresholding
by Li Hui, Ahmed Ibrahim and Riyadh Hindi
Infrastructures 2025, 10(2), 42; https://doi.org/10.3390/infrastructures10020042 - 18 Feb 2025
Viewed by 1
Abstract
Concrete is widely used in different types of buildings and bridges; however, one of the major issues for concrete structures is crack formation and propagation during its service life. These cracks can potentially introduce harmful agents into concrete, resulting in a reduction in [...] Read more.
Concrete is widely used in different types of buildings and bridges; however, one of the major issues for concrete structures is crack formation and propagation during its service life. These cracks can potentially introduce harmful agents into concrete, resulting in a reduction in the overall lifespan of concrete structures. Traditional methods for crack detection primarily hinge on manual visual inspection, which relies on the experience and expertise of inspectors using tools such as magnifying glasses and microscopes. To address this issue, computer vision is one of the most innovative solutions for concrete cracking evaluation, and its application has been an area of research interest in the past few years. This study focuses on the utilization of the lightweight MobileNetV2 neural network for concrete crack detection. A dataset including 40,000 images was adopted and preprocessed using various thresholding techniques, of which adaptive thresholding was selected for developing the crack evaluation algorithm. While both the convolutional neural network (CNN) and MobileNetV2 indicated comparable accuracy levels in crack detection, the MobileNetV2 model’s significantly smaller size makes it a more efficient selection for crack detection using mobile devices. In addition, an advanced algorithm was developed to detect cracks and evaluate crack widths in high-resolution images. The effectiveness and reliability of both the selected method and the developed algorithm were subsequently assessed through experimental validation. Full article
(This article belongs to the Special Issue Advances in Artificial Intelligence for Infrastructures)
Show Figures

Figure 1

22 pages, 1768 KiB  
Article
A Novel Integrated Biorefinery for the Valorization of Residual Cardoon Biomass: Overview of Technologies and Process Simulation
by Vittoria Fatta, Aristide Giuliano, Maria Teresa Petrone, Francesco Nanna, Antonio Villone, Donatella Barisano, Roberto Albergo, Federico Liuzzi, Diego Barletta and Isabella De Bari
Energies 2025, 18(4), 973; https://doi.org/10.3390/en18040973 - 18 Feb 2025
Viewed by 106
Abstract
Lignocellulosic biomass is currently widely used in many biorefining processes. The full exploitation of biomass from uncultivated or even marginal lands for the production of biobased chemicals has deserved huge attention in the last few years. Among the sustainable biomass-based value chains, cardoon [...] Read more.
Lignocellulosic biomass is currently widely used in many biorefining processes. The full exploitation of biomass from uncultivated or even marginal lands for the production of biobased chemicals has deserved huge attention in the last few years. Among the sustainable biomass-based value chains, cardoon crops could be a feedstock for biorefineries as they can grow on marginal lands and be used as raw material for multipurpose exploitation, including seeds, roots, and epigeous lignocellulosic solid residue. This work focused on the technical analysis of a novel integrated flowsheet for the exploitation of the lignocellulosic fraction through the assessment of thermochemical, biochemical, and extractive technologies and processes. In particular, high-yield thermochemical processes (gasification), innovative biotechnological processes (syngas fermentation to ethanol), and extractive/catalyzed processes for the valorization of cardoon roots to FDCA and residual solid biomass were modeled and simulated. Inulin conversion to 2,5-Furandicarboxylic acid was the main conversion route taken into consideration. Finally, the novel process flowsheet, treating 130,000 t/y of residual biomass and integrating all proposed technologies, was modeled and assessed using process simulation tools to achieve overall mass and energy balances for comparison with alternative options. The results indicated that cardoon biorefining through the proposed flowsheet can produce, per 1000 tons of input dry biomass, 211 kg of 2,5-Furandicarboxylic acid and 140 kg of ethanol through biomass gasification followed by syngas fermentation. Furthermore, a pre-feasibility analysis was conducted, revealing significant and potentially disruptive results in terms of environmental impact (with 40 ktCO2eq saved) and economic feasibility (with an annual gross profit of EUR 30 M/y). Full article
(This article belongs to the Section A4: Bio-Energy)
Show Figures

Figure 1

27 pages, 5597 KiB  
Article
Smart Organization of Imbalanced Traffic Datasets for Long-Term Traffic Forecasting
by Mustafa M. Kara, H. Irem Turkmen and M. Amac Guvensan
Sensors 2025, 25(4), 1225; https://doi.org/10.3390/s25041225 - 18 Feb 2025
Viewed by 129
Abstract
Predicting traffic speed is an important issue, especially in urban regions. Precise long-term forecasts would enable individuals to conserve time and financial resources while diminishing air pollution. Despite extensive research on this subject, to our knowledge, no publications investigate or tackle the issue [...] Read more.
Predicting traffic speed is an important issue, especially in urban regions. Precise long-term forecasts would enable individuals to conserve time and financial resources while diminishing air pollution. Despite extensive research on this subject, to our knowledge, no publications investigate or tackle the issue of imbalanced datasets in traffic speed prediction. Traffic speed data are often biased toward high numbers because low traffic speeds are infrequent. The temporal aspect of traffic carries two important factors for low-speed value. The daily population movement, captured by the time of day, and the weather data, recorded by month, are both considered in this study. Hour-wise Pattern Organization and Month-wise Pattern Organization techniques were devised, which organize the speed data using these two factors as a metric with a view to providing a superior representation of data characteristics that are in the minority. In addition to these two methods, a Speed-wise Pattern Organization strategy is proposed, which arranges train and test samples by setting boundaries on speed while taking the volatile nature of traffic into consideration. We evaluated these strategies using four popular model types: long short-term memory (LSTM), gated recurrent unit networks (GRUs), bi-directional LSTM, and convolutional neural networks (CNNs). GRU had the best performance, achieving a MAPE (Mean Absolute Percentage Error) of 13.51%, whereas LSTM demonstrated the lowest performance, with a MAPE of 13.74%. We validated their robustness through our studies and observed improvements in model accuracy across all categories. While the average improvement was approximately 4%, our methodologies demonstrated superior performance in low-traffic speed scenarios, augmenting model prediction accuracy by 11.2%. The presented methodologies in this study are applied in the pre-processing steps, allowing their application with various models and additional pre-processing procedures to attain comparable performance improvements. Full article
(This article belongs to the Section Navigation and Positioning)
Show Figures

Figure 1

18 pages, 1223 KiB  
Article
GazeCapsNet: A Lightweight Gaze Estimation Framework
by Shakhnoza Muksimova, Yakhyokhuja Valikhujaev, Sabina Umirzakova, Jushkin Baltayev and Young Im Cho
Sensors 2025, 25(4), 1224; https://doi.org/10.3390/s25041224 - 17 Feb 2025
Viewed by 69
Abstract
Gaze estimation is increasingly pivotal in applications spanning virtual reality, augmented reality, and driver monitoring systems, necessitating efficient yet accurate models for mobile deployment. Current methodologies often fall short, particularly in mobile settings, due to their extensive computational requirements or reliance on intricate [...] Read more.
Gaze estimation is increasingly pivotal in applications spanning virtual reality, augmented reality, and driver monitoring systems, necessitating efficient yet accurate models for mobile deployment. Current methodologies often fall short, particularly in mobile settings, due to their extensive computational requirements or reliance on intricate pre-processing. Addressing these limitations, we present Mobile-GazeCapsNet, an innovative gaze estimation framework that harnesses the strengths of capsule networks and integrates them with lightweight architectures such as MobileNet v2, MobileOne, and ResNet-18. This framework not only eliminates the need for facial landmark detection but also significantly enhances real-time operability on mobile devices. Through the innovative use of Self-Attention Routing, GazeCapsNet dynamically allocates computational resources, thereby improving both accuracy and efficiency. Our results demonstrate that GazeCapsNet achieves competitive performance by optimizing capsule networks for gaze estimation through Self-Attention Routing (SAR), which replaces iterative routing with a lightweight attention-based mechanism, improving computational efficiency. Our results show that GazeCapsNet achieves state-of-the-art (SOTA) performance on several benchmark datasets, including ETH-XGaze and Gaze360, achieving a mean angular error (MAE) reduction of up to 15% compared to existing models. Furthermore, the model maintains a real-time processing capability of 20 milliseconds per frame while requiring only 11.7 million parameters, making it exceptionally suitable for real-time applications in resource-constrained environments. These findings not only underscore the efficacy and practicality of GazeCapsNet but also establish a new standard for mobile gaze estimation technologies. Full article
(This article belongs to the Section Sensor Networks)
Show Figures

Figure 1

Back to TopTop