Journal Description
Applied Sciences
Applied Sciences
is an international, peer-reviewed, open access journal on all aspects of applied natural sciences published semimonthly online by MDPI.
- Open Access— free for readers, with article processing charges (APC) paid by authors or their institutions.
- High Visibility: indexed within Scopus, SCIE (Web of Science), Inspec, CAPlus / SciFinder, and other databases.
- Journal Rank: JCR - Q2 (Engineering, Multidisciplinary) / CiteScore - Q1 (General Engineering )
- Rapid Publication: manuscripts are peer-reviewed and a first decision is provided to authors approximately 16.9 days after submission; acceptance to publication is undertaken in 2.6 days (median values for papers published in this journal in the second half of 2023).
- Recognition of Reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.
- Testimonials: See what our authors say about Applied Sciences.
- Companion journals for Applied Sciences include: Applied Nano, AppliedChem, Applied Biosciences, Virtual Worlds, Spectroscopy Journal and JETA.
Impact Factor:
2.7 (2022);
5-Year Impact Factor:
2.9 (2022)
Latest Articles
Prediction of Buildings’ Settlements Induced by Deep Foundation Pit Construction Based on LSTM-RA-ANN
Appl. Sci. 2024, 14(12), 5021; https://doi.org/10.3390/app14125021 (registering DOI) - 8 Jun 2024
Abstract
In view of the shortcomings of existing methods for predicting the settlement of surrounding buildings caused by deep foundation pit construction, this study uses the monitoring data of a foundation pit project in Shanghai and divides the construction process of the pit into
[...] Read more.
In view of the shortcomings of existing methods for predicting the settlement of surrounding buildings caused by deep foundation pit construction, this study uses the monitoring data of a foundation pit project in Shanghai and divides the construction process of the pit into three working conditions, that is, enclosure construction, earthwork excavation, and basement support construction. The attention mechanism and residual update are integrated into the artificial neural network (ANN) model, and the root-mean-square error, average absolute error, and determination coefficient are used as the evaluation indices of the model. The artificial neural network prediction model LSTM-RA-ANN for building settlements in deep foundation pit construction was then established. The prediction performance of the model was also analysed under different working conditions, and the influences of the main factors (including the soil parameter, monitoring point location, activation function, hyperparameter, and input number) on the evaluation index was further explored. The results indicate that the performances of the established LSTM-RA-ANN model are closely related to the construction conditions, the predicted settlements agree well with the monitored ones in three working conditions with the greatest errors occurring at a later time of the working conditions, and the prediction accuracy of the great–small order corresponds to basement support, enclosure construction, and earthwork excavation respectively. The farther the monitoring point is from the edge of the pit, the better the model performance is. The activation function, initial learning rate, and maximum iteration batch have a great influence on the evaluation indices of the model, while the number of input points has little effect on the evaluation indices. These results may serve as a reference for the safe construction and normal operation of foundation pit engineering.
Full article
(This article belongs to the Section Civil Engineering)
►
Show Figures
Open AccessArticle
Toward a Comprehensive Evaluation of Student Knowledge Assessment for Art Education: A Hybrid Approach by Data Mining and Machine Learning
by
Shan Wang, Hongtao Wang, Yijun Lu and Jiandong Huang
Appl. Sci. 2024, 14(12), 5020; https://doi.org/10.3390/app14125020 (registering DOI) - 8 Jun 2024
Abstract
By analyzing students’ understanding of a certain subject’s knowledge and learning process, and evaluating their learning level, we can formulate students’ learning plans and teachers’ curricula. However, the large amount of data processing consumes a lot of manpower and time resources, which increases
[...] Read more.
By analyzing students’ understanding of a certain subject’s knowledge and learning process, and evaluating their learning level, we can formulate students’ learning plans and teachers’ curricula. However, the large amount of data processing consumes a lot of manpower and time resources, which increases the burden on educators. Therefore, this study aims to use a machine learning model to build a model to evaluate students’ learning levels for art education. To improve the prediction accuracy of the model, SVM was adopted as the basic model in this study, and was combined with SSA, ISSA, and KPCA-ISSA algorithms in turn to form a composite model. Through the experimental analysis of prediction accuracy, we found that the prediction accuracy of the KPCA-ISSA-SVMM model reached the highest, at 96.7213%, while that of the SVM model was only 91.8033%. Moreover, by putting the prediction results of the four models into the confusion matrix, it can be found that with an increase in the complexity of the composite model, the probability of classification errors in model prediction gradually decreases. It can be seen from the importance experiment that the students’ achievements in target subjects (PEG) have the greatest influence on the model prediction effect, and the importance score is 9.5958. Therefore, we should pay more attention to this characteristic value when evaluating students’ learning levels.
Full article
(This article belongs to the Special Issue ICT in Education, 2nd Edition)
►▼
Show Figures
Figure 1
Open AccessArticle
CNN-Based Multi-Factor Authentication System for Mobile Devices Using Faces and Passwords
by
Jinho Han
Appl. Sci. 2024, 14(12), 5019; https://doi.org/10.3390/app14125019 (registering DOI) - 8 Jun 2024
Abstract
Multi-factor authentication (MFA) is a system for authenticating an individual’s identity using two or more pieces of data (known as factors). The reason for using more than two factors is to further strengthen security through the use of additional data for identity authentication.
[...] Read more.
Multi-factor authentication (MFA) is a system for authenticating an individual’s identity using two or more pieces of data (known as factors). The reason for using more than two factors is to further strengthen security through the use of additional data for identity authentication. Sequential MFA requires a number of steps to be followed in sequence for authentication; for example, with three factors, the system requires three authentication steps. In this case, to proceed with MFA using a deep learning approach, three artificial neural networks (ANNs) are needed. In contrast, in parallel MFA, the authentication steps are processed simultaneously. This means that processing is possible with only one ANN. A convolutional neural network (CNN) is a method for learning images through the use of convolutional layers, and researchers have proposed several systems for MFA using CNNs in which various modalities have been employed, such as images, handwritten text for authentication, and multi-image data for machine learning of facial emotion. This study proposes a CNN-based parallel MFA system that uses concatenation. The three factors used for learning are a face image, an image converted from a password, and a specific image designated by the user. In addition, a secure password image is created at different bit-positions, enabling the user to securely hide their password information. Furthermore, users designate a specific image other than their face as an auxiliary image, which could be a photo of their pet dog or favorite fruit, or an image of one of their possessions, such as a car. In this way, authentication is rendered possible through learning the three factors—that is, the face, password, and specific auxiliary image—using the CNN. The contribution that this study makes to the existing body of knowledge is demonstrating that the development of an MFA system using a lightweight, mobile, multi-factor CNN (MMCNN), which can even be used in mobile devices due to its low number of parameters, is possible. Furthermore, an algorithm that can securely transform a text password into an image is proposed, and it is demonstrated that the three considered factors have the same weight of information for authentication based on the false acceptance rate (FAR) values experimentally obtained with the proposed system.
Full article
(This article belongs to the Special Issue Integrating Artificial Intelligence in Renewable Energy Systems)
►▼
Show Figures
Figure 1
Open AccessArticle
Linear Contact Load Law of an Elastic–Perfectly Plastic Half-Space vs. Sphere under Low Velocity Impact
by
Hao Yuan, Xiaochun Yin, Hui Wang, Yuanyuan Guo, Changliang Wang, Hao Zhou, Cheng Gao, Huaiping Ding and Xiaokai Deng
Appl. Sci. 2024, 14(12), 5018; https://doi.org/10.3390/app14125018 (registering DOI) - 8 Jun 2024
Abstract
The impact of contact between two elastic–plastic bodies is highly complex, with no established theoretical contact model currently available. This study investigates the problem of an elastic–plastic sphere impacting an elastic–plastic half-space at low speed and low energy using the finite element method
[...] Read more.
The impact of contact between two elastic–plastic bodies is highly complex, with no established theoretical contact model currently available. This study investigates the problem of an elastic–plastic sphere impacting an elastic–plastic half-space at low speed and low energy using the finite element method (FEM). Existing linear contact loading laws exhibit significant discrepancies as they fail to consider the impact of elasticity and yield strength on the elastic–plastic sphere. To address this limitation, a novel linear contact loading law is proposed in this research, which utilizes the concept of equivalent contact stiffness rather than the conventional linear contact stiffness. The theoretical expressions of this new linear contact loading law are derived through FEM simulations of 150 sphere and half-space impact cases. The segmental linear characteristics of the equivalent contact stiffness are identified and fitted to establish the segmental expressions of the equivalent contact stiffness. The new linear contact loading law is dependent on various factors, including the yield strain of the half-space, the ratio of elastic moduli between the half-space and sphere, and the ratio of yield strengths between the half-space and sphere. The accuracy of the proposed linear contact loading law is validated through extensive Finite Element Method simulations, which involve an elastic–plastic half-space being struck by elastic–plastic spheres with varying impact energies, sizes, and material combinations.
Full article
(This article belongs to the Section Mechanical Engineering)
►▼
Show Figures
Figure 1
Open AccessArticle
A Conceptual Model for Depicting the Relationships between Toluene Degradation and Fe(III) Reduction with Different Fe(III) Phases as Terminal Electron Acceptors
by
He Di, Min Zhang, Zhuo Ning, Ze He, Changli Liu and Jiajia Song
Appl. Sci. 2024, 14(12), 5017; https://doi.org/10.3390/app14125017 (registering DOI) - 8 Jun 2024
Abstract
Iron reduction is one of the most crucial biogeochemical processes in groundwater for organic contaminants biodegradation, especially in the iron-rich aquifers. Previous research has posited that the reduction of iron and the biodegradation of organic substances occur synchronously, with their processes adhering to
[...] Read more.
Iron reduction is one of the most crucial biogeochemical processes in groundwater for organic contaminants biodegradation, especially in the iron-rich aquifers. Previous research has posited that the reduction of iron and the biodegradation of organic substances occur synchronously, with their processes adhering to specific quantitative relationships. However, discrepancies between the observed values of iron reduction and organic compound degradation during the reaction and their theoretical counterparts have been noted. To find out the relationship between organic substance biodegradation and iron reduction, this study conducted batch experiments utilizing toluene as a typical organic compound and electron donor, with various iron minerals serving as electron acceptors. Results indicate that toluene degradation follows first-order kinetic equations with different degradation rate constants under different iron minerals, but the generation of the iron reduction product Fe(II) was not uniform. Based on these dynamic relationships, a conceptual model was developed, which categorizes the reactions into two phases: the transformation of toluene to an intermediate-state dominated phase and the mineralization of the intermediate-state dominated phase. This model revealed the relationships between toluene oxidation and Fe(II) formation in the toluene biodegradation through iron reduction. The coupling mechanism of toluene degradation and iron reduction was revealed, which is expected to improve our ability to accurately assess the attenuation of organic contaminants in groundwater.
Full article
(This article belongs to the Special Issue The Mobilization, Speciation and Transformation of Organic and Inorganic Contaminants in Soil-Groundwater Ecosystems)
►▼
Show Figures
Figure 1
Open AccessArticle
Adaptive CAPTCHA: A CRNN-Based Text CAPTCHA Solver with Adaptive Fusion Filter Networks
by
Xing Wan, Juliana Johari and Fazlina Ahmat Ruslan
Appl. Sci. 2024, 14(12), 5016; https://doi.org/10.3390/app14125016 (registering DOI) - 8 Jun 2024
Abstract
Text-based CAPTCHAs remain the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs), are the mainstream approach for text CAPTCHA recognition and are widely used in CAPTCHA vulnerability assessment and data
[...] Read more.
Text-based CAPTCHAs remain the most widely adopted security scheme, which is the first barrier to securing websites. Deep learning methods, especially Convolutional Neural Networks (CNNs), are the mainstream approach for text CAPTCHA recognition and are widely used in CAPTCHA vulnerability assessment and data collection. However, verification code recognizers are mostly deployed on the CPU platform as part of a web crawler and security assessment; they are required to have both low complexity and high recognition accuracy. Due to the specifically designed anti-attack mechanisms like noise, interference, geometric deformation, twisting, rotation, and character adhesion in text CAPTCHAs, some characters are difficult to efficiently identify with high accuracy in these complex CAPTCHA images. This paper proposed a recognition model named Adaptive CAPTCHA with a CNN combined with an RNN (CRNN) module and trainable Adaptive Fusion Filtering Networks (AFFN), which effectively handle the interference and learn the correlation between characters in CAPTCHAs to enhance recognition accuracy. Experimental results on two datasets of different complexities show that, compared with the baseline model Deep CAPTCHA, the number of parameters of our proposed model is reduced by about 70%, and the recognition accuracy is improved by more than 10 percentage points in the two datasets. In addition, the proposed model has a faster training convergence speed. Compared with several of the latest models, the model proposed by the study also has better comprehensive performance.
Full article
(This article belongs to the Special Issue Advanced Technologies in Data and Information Security III)
►▼
Show Figures
Figure 1
Open AccessArticle
Laminated Steel Fiber-Reinforced Concrete Hingeless Arch: Research on Damage Evolution Laws
by
Zhongchu Tian, Ye Dai, Tao Peng, Zujun Zhang, Yue Cai and Binlin Xu
Appl. Sci. 2024, 14(12), 5015; https://doi.org/10.3390/app14125015 (registering DOI) - 8 Jun 2024
Abstract
In the context of reinforced concrete (RC) arch bridges, while the incorporation of full sections of steel fibers can enhance the bridge’s toughness, cracking resilience, and bearing capacity, achieving an optimal balance between structural performance and economic viability in this manner remains challenging.
[...] Read more.
In the context of reinforced concrete (RC) arch bridges, while the incorporation of full sections of steel fibers can enhance the bridge’s toughness, cracking resilience, and bearing capacity, achieving an optimal balance between structural performance and economic viability in this manner remains challenging. This article introduces a novel computational approach—the distributed steel fiber concrete (LSFRC) arch—which considers the spatial distribution of damage in RC arches. The static performance of SFRC elements and LSFRC beams was compared and analyzed using the concrete plastic damage model (CDP) in ABAQUS software. This study validated the rationality of the model and investigated the impact of varying steel fiber volume ratios and steel fiber layer heights on the damage evolution of LSFRC arches. The results of this study demonstrate that the cracking load and bearing capacity of an RC arch can be effectively enhanced through the addition of steel fibers to a local area under static loading. Furthermore, the deflection and damage to the arch waist and arch roof can be significantly reduced. Furthermore, the incorporation of steel fibers at an increased volume rate and at a greater height within the doped section can effectively slow the rate of damage evolution within the section. This results in the inhibition of crack extensions and in an improvement in the ductility and reliability of the damage stage. The LSFRC arches offer superior economic and practical advantages over their full cross-section doped steel fiber (FRC) counterparts. This study offers novel insights and methodological guidance for the design and implementation of concrete arch bridges.
Full article
Open AccessArticle
Research on Hybrid Vibration Sensor for Measuring Downhole Drilling Tool Vibrational Frequencies
by
Jiangbin Liu, Guangzhi Pan, Chuan Wu and Yanjun Feng
Appl. Sci. 2024, 14(12), 5014; https://doi.org/10.3390/app14125014 (registering DOI) - 8 Jun 2024
Abstract
The vibration parameters during drilling play a critical role in enhancing drilling speed and ensuring safety. However, traditional downhole vibration sensors face limitations in their power supply methods, hindering widespread adoption. To address this challenge, our research introduces a novel solution: a hybrid
[...] Read more.
The vibration parameters during drilling play a critical role in enhancing drilling speed and ensuring safety. However, traditional downhole vibration sensors face limitations in their power supply methods, hindering widespread adoption. To address this challenge, our research introduces a novel solution: a hybrid downhole vibration sensor (HDV-TENG) utilizing triboelectric nanogenerators. This sensor not only enables the measurement of low- to medium–high-frequency vibrations using self-power but also serves to energize other downhole devices. We utilized a self-constructed vibration simulator to replicate downhole drilling tool vibrations and conducted a comprehensive series of sensor tests. The test results indicate that the frequency measurement bandwidth of the HDV-TENG spans from 0 to 200 kHz. Especially, the measurement errors for vibrations within the low-frequency range of 0 to 10 Hz and the high-frequency range of 10 to 200 k Hz are less than 5% and 8%, respectively. Additionally, the experimental findings regarding load matching demonstrate that the HDV-TENG achieves an output power level in the milliwatt range, representing a significant improvement over the output power of traditional triboelectric nanogenerators. Unlike traditional downhole vibration measurement sensors, HDV-TENG operates without requiring any external power supply, thereby conserving downhole space and significantly enhancing drilling efficiency. Furthermore, HDV-TENG not only offers a broad measurement range but also amplifies output power through the synergy of a triboelectric nanogenerator (TENG), piezoelectric nanogenerator (PENG), and electromagnetic power generator (EMG). This capability enables its utilization as an emergency power source for other micropower equipment downhole. The introduction of HDV-TENG also holds considerable implications for the development of self-powered underground sensors with high-frequency measurement capabilities.
Full article
(This article belongs to the Section Electrical, Electronics and Communications Engineering)
►▼
Show Figures
Figure 1
Open AccessArticle
Super-Resolution Image Reconstruction Method between Sentinel-2 and Gaofen-2 Based on Cascaded Generative Adversarial Networks
by
Xinyu Wang, Zurui Ao, Runhao Li, Yingchun Fu, Yufei Xue and Yunxin Ge
Appl. Sci. 2024, 14(12), 5013; https://doi.org/10.3390/app14125013 (registering DOI) - 8 Jun 2024
Abstract
Due to the multi-scale and spectral features of remote sensing images compared to natural images, there are significant challenges in super-resolution reconstruction (SR) tasks. Networks trained on simulated data often exhibit poor reconstruction performance on real low-resolution (LR) images. Additionally, compared to natural
[...] Read more.
Due to the multi-scale and spectral features of remote sensing images compared to natural images, there are significant challenges in super-resolution reconstruction (SR) tasks. Networks trained on simulated data often exhibit poor reconstruction performance on real low-resolution (LR) images. Additionally, compared to natural images, remote sensing imagery involves fewer high-frequency components in network construction. To address the above issues, we introduce a new high–low-resolution dataset GF_Sen based on GaoFen-2 and Sentinel-2 images and propose a cascaded network CSWGAN combined with spatial–frequency features. Firstly, based on the proposed self-attention GAN (SGAN) and wavelet-based GAN (WGAN) in this study, the CSWGAN combines the strengths of both networks. It not only models long-range dependencies and better utilizes global feature information, but also extracts frequency content differences between different images, enhancing the learning of high-frequency information. Experiments have shown that the networks trained based on the GF_Sen can achieve better performance than those trained on simulated data. The reconstructed images from the CSWGAN demonstrate improvements in the PSNR and SSIM by 4.375 and 4.877, respectively, compared to the relatively optimal performance of the ESRGAN. The CSWGAN can reflect the reconstruction advantages of a high-frequency scene and provides a working foundation for fine-scale applications in remote sensing.
Full article
(This article belongs to the Section Earth Sciences)
►▼
Show Figures
Figure 1
Open AccessArticle
Accurate Delimitation of Mine Goaves Using Multi-Attribute Comprehensive Identification and Data Fusion Technologies in 3D Seismic Exploration
by
Junjie Zhou, Yanhui Wu, Qingchao Zhang, Zhen Nie, Tao Ding and Guowei Zhu
Appl. Sci. 2024, 14(12), 5012; https://doi.org/10.3390/app14125012 (registering DOI) - 8 Jun 2024
Abstract
►▼
Show Figures
Existing goaves (e.g., shafts and roadways) in mines represent important hidden dangers during the production of underlying coal seams. In this view, the accurate identification, analysis, and delimitation of the scope of goaves have become important in the 3D seismic exploration of mines.
[...] Read more.
Existing goaves (e.g., shafts and roadways) in mines represent important hidden dangers during the production of underlying coal seams. In this view, the accurate identification, analysis, and delimitation of the scope of goaves have become important in the 3D seismic exploration of mines. In particular, an accurate identification of the boundary swing position of goaves for 3D seismic data volumes within a certain depth interval is key and difficult at the same time. Here, a wide-band and wide-azimuth observation system was used to obtain high-resolution 3D seismic data. The complex structure of a mine was analyzed, and a seismic double processing system was applied to verify the fine processing effect of a goaf and improve the resolution of the 3D seismic data. Based on the seismic attribute identification characteristics of the goaf structure, we decided to adopt multi-attribute comprehensive identification and data fusion technologies to accurately determine the position of the goaf and of its boundary. Combining this information with the mine roadway engineering layout, we verified the accurateness and correctness of the goaf boundary location. Our study provides a good example of the accurate identification of the 3D seismic data of a roadway goaf.
Full article
Figure 1
Open AccessArticle
A Bio-Inspired Retinal Model as a Prefiltering Step Applied to Letter and Number Recognition on Chilean Vehicle License Plates
by
John Kern, Claudio Urrea, Francisco Cubillos and Ricardo Navarrete
Appl. Sci. 2024, 14(12), 5011; https://doi.org/10.3390/app14125011 (registering DOI) - 8 Jun 2024
Abstract
This paper presents a novel use of a bio-inspired retina model as a scene preprocessing stage for the recognition of letters and numbers on Chilean vehicle license plates. The goal is to improve the effectiveness and ease of pattern recognition. Inspired by the
[...] Read more.
This paper presents a novel use of a bio-inspired retina model as a scene preprocessing stage for the recognition of letters and numbers on Chilean vehicle license plates. The goal is to improve the effectiveness and ease of pattern recognition. Inspired by the responses of mammalian retinas, this retinal model reproduces both the natural adjustment of contrast and the enhancement of object contours by parvocellular cells. Among other contributions, this paper provides an in-depth exploration of the architecture, advantages, and limitations of the model; investigates the tuning parameters of the model; and evaluates its performance when integrating a convolutional neural network and a spiking neural network into an optical character recognition (OCR) algorithm, using 40 different genuine license plate images as a case study and for testing. The results obtained demonstrate the reduction of error rates in character recognition based on convolutional neural networks (CNNs), spiking neural networks (SNNs), and OCR. It is concluded that this bio-inspired retina model offers a wide spectrum of potential applications to further explore, including motion detection, pattern recognition, and improvement of dynamic range in images, among others.
Full article
Open AccessArticle
The Effect of a Limited Underactuated Posterior Joint on the Speed and Energy Efficiency of a Fish Robot
by
Yanic Heinen, Ivan Tanev and Tatsuaki Kimura
Appl. Sci. 2024, 14(12), 5010; https://doi.org/10.3390/app14125010 (registering DOI) - 8 Jun 2024
Abstract
Autonomous underwater vehicles (AUVs) commonly use screw propellers to move in a water environment. However, compared to the propeller-driven AUV, bio-inspired AUVs feature a higher energy efficiency, longer lifespan (due to a lack of cavitation), and better eco-friendliness (due to lower noise, a
[...] Read more.
Autonomous underwater vehicles (AUVs) commonly use screw propellers to move in a water environment. However, compared to the propeller-driven AUV, bio-inspired AUVs feature a higher energy efficiency, longer lifespan (due to a lack of cavitation), and better eco-friendliness (due to lower noise, a lack of vibrations, and a weaker wake). To generate propulsion, the design of fish robots—viewed as a special case of a bio-inspired AUV—comprise multiple actuated joints. Underactuated joints have also been adopted in bio-inspired AUVs, primarily for the purpose of achieving a simpler design and more realistic and biologically plausible locomotion. In our work, we propose a limitedly underactuated posterior (tail) joint of a fish robot with the intention of achieving a higher swimming speed and better energy efficiency of the robot. The limited underactuation is achieved by allowing the joint to move freely but only within a limited angular range. The experimental results verified that, for relatively small angular ranges, the limitedly underactuated joint is superior to both fully actuated and fully underactuated joints in that it results in faster and more energy-efficient locomotion of the fish robot.
Full article
(This article belongs to the Special Issue Recent Advances in Underwater Vehicles)
►▼
Show Figures
Figure 1
Open AccessArticle
Numerical Simulation of Hydrodynamics and Heat Transfer in a Reactor with a Fluidized Bed of Catalyst Particles in a Three-Dimensional Formulation
by
Nikolai V. Ulitin, Konstantin A. Tereshchenko, Ilya S. Rodionov, Konstantin A. Alekseev, Daria A. Shiyan, Kharlampii E. Kharlampidi and Yaroslav O. Mezhuev
Appl. Sci. 2024, 14(12), 5009; https://doi.org/10.3390/app14125009 (registering DOI) - 8 Jun 2024
Abstract
The hydrodynamics and heat transfer in a reactor with a fluidized bed of catalyst particles and an inert material were simulated. The particle bed (the particle density was 2350 kg/m3, and the particle diameter was 1.5 to 4 mm) was located
[...] Read more.
The hydrodynamics and heat transfer in a reactor with a fluidized bed of catalyst particles and an inert material were simulated. The particle bed (the particle density was 2350 kg/m3, and the particle diameter was 1.5 to 4 mm) was located in a distribution device which was a grid of 90 × 90 × 60 mm vertical baffles. The behavior of the liquefying medium (air) was modeled using a realizable k-ε turbulence model. The behavior of particles was modeled using the discrete element method (DEM). In order to reduce the slugging effect, the particles were divided into four separate horizontal layers. It was determined that with the velocity of the liquefying medium close to the minimum fluidization velocity (1 m/s), slugging fluidization is observed. At a velocity of the liquefying medium of 3 m/s, turbulent fluidization in the lowest particle layer and bubbling fluidization on subsequent particle layers are observed. With an increase in the velocity of the liquefying medium over 3 m/s, entrainment of particles is observed. It was shown that a decrease in the density of the liquefying medium from 1.205 kg/m3 to 0.383 kg/m3 when it is heated from 298 K to 923 K would not significantly affect the hydraulic resistance of the bed. Based on the obtained results, it can be stated that the obtained model is optimal for such problems and is suitable for the further description of experimental data.
Full article
(This article belongs to the Special Issue Fluid Flow and Heat Transfer: Latest Advances and Prospects)
Open AccessArticle
Driving Style and Traffic Prediction with Artificial Neural Networks Using On-Board Diagnostics and Smartphone Sensors
by
Ghaith Al-refai, Mohammed Al-refai and Ahmad Alzu’bi
Appl. Sci. 2024, 14(12), 5008; https://doi.org/10.3390/app14125008 (registering DOI) - 8 Jun 2024
Abstract
Driving style and road traffic play pivotal roles in the development of smart cities, influencing traffic flow, safety, and environmental sustainability. This study presents an innovative approach for detecting road traffic conditions and driving styles using On-Board Diagnostics (OBD) data and smartphone sensors.
[...] Read more.
Driving style and road traffic play pivotal roles in the development of smart cities, influencing traffic flow, safety, and environmental sustainability. This study presents an innovative approach for detecting road traffic conditions and driving styles using On-Board Diagnostics (OBD) data and smartphone sensors. This approach offers an inexpensive implementation of prediction, as it utilizes existing vehicle data without requiring additional setups. Two Artificial Neural Network (ANN) models were employed: the first utilizes a forward neural network architecture, while the second leverages bootstrapping or bagging neural networks to enhance detection accuracy for low-labeled classes. Support Vector Machine (SVM) is implemented to serve as a baseline for comparison. Experimental results demonstrate that ANNs exhibit significant improvements in detection accuracy compared to SVM. Moreover, the neural network with bagging model showcases enhanced recall values and a substantial improvement in accurately detecting instances belonging to low-labeled classes in both driving style road traffic.
Full article
(This article belongs to the Special Issue Applications of Artificial Intelligence in Transportation Engineering)
Open AccessArticle
WSPolyp-SAM: Weakly Supervised and Self-Guided Fine-Tuning of SAM for Colonoscopy Polyp Segmentation
by
Tingting Cai, Hongping Yan, Kun Ding, Yan Zhang and Yueyue Zhou
Appl. Sci. 2024, 14(12), 5007; https://doi.org/10.3390/app14125007 (registering DOI) - 8 Jun 2024
Abstract
Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully supervised, requiring extensive, precise, manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains
[...] Read more.
Ensuring precise segmentation of colorectal polyps holds critical importance in the early diagnosis and treatment of colorectal cancer. Nevertheless, existing deep learning-based segmentation methods are fully supervised, requiring extensive, precise, manual pixel-level annotation data, which leads to high annotation costs. Additionally, it remains challenging to train large-scale segmentation models when confronted with limited colonoscopy data. To address these issues, we introduce the general segmentation foundation model—the Segment Anything Model (SAM)—into the field of medical image segmentation. Fine-tuning the foundation model is an effective approach to tackle sample scarcity. However, current SAM fine-tuning techniques still rely on precise annotations. To overcome this limitation, we propose WSPolyp-SAM, a novel weakly supervised approach for colonoscopy polyp segmentation. WSPolyp-SAM utilizes weak annotations to guide SAM in generating segmentation masks, which are then treated as pseudo-labels to guide the fine-tuning of SAM, thereby reducing the dependence on precise annotation data. To improve the reliability and accuracy of pseudo-labels, we have designed a series of enhancement strategies to improve the quality of pseudo-labels and mitigate the negative impact of low-quality pseudo-labels. Experimental results on five medical image datasets demonstrate that WSPolyp-SAM outperforms current fully supervised mainstream polyp segmentation networks on the Kvasir-SEG, ColonDB, CVC-300, and ETIS datasets. Furthermore, by using different amounts of training data in weakly supervised and fully supervised experiments, it is found that weakly supervised fine-tuning can save 70% to 73% of annotation time costs compared to fully supervised fine-tuning. This study provides a new perspective on the combination of weakly supervised learning and SAM models, significantly reducing annotation time and offering insights for further development in the field of colonoscopy polyp segmentation.
Full article
Open AccessArticle
Integrated Optimization of Train Diagrams and Rolling Stock Circulation with Full-Length and Short-Turn Routes of Virtual Coupling Trains in Urban Rail Transit
by
Fang Lu, Liyu Wang, Jiangfeng Hu, Qi Zhang and Xiaojuan Li
Appl. Sci. 2024, 14(12), 5006; https://doi.org/10.3390/app14125006 (registering DOI) - 8 Jun 2024
Abstract
The advancement of virtual coupling technology in urban rail transit has facilitated the online coupling and decoupling of trains, enabling a range of flexible transportation configurations, including various route types and adjustable formations. This study targets the fluctuating passenger demands on urban rail
[...] Read more.
The advancement of virtual coupling technology in urban rail transit has facilitated the online coupling and decoupling of trains, enabling a range of flexible transportation configurations, including various route types and adjustable formations. This study targets the fluctuating passenger demands on urban rail lines, aiming to minimize both passenger travel and operational costs. The model integrates constraints associated with virtual coupling, train operations, rolling stock circulation, and the interaction between virtually coupled trains and passenger arrivals. New decision variables are introduced to depict the train formation state under virtual coupling scenarios. An integrated optimization model for train diagrams and rolling stock circulation under virtual coupling conditions is developed, employing a genetic-simulated annealing algorithm informed by train operation simulations. A case study on an urban rail line during the morning peak examines the optimization of train diagrams for full-length and short-turn routes. Findings confirm that virtual coupling technology effectively adapts to lines with uneven passenger flow distribution, significantly enhancing the match between supply and demand, equalizing spatial and temporal traffic variations, and harmonizing the quality of passenger services with operational efficiency.
Full article
(This article belongs to the Special Issue Transportation Planning, Management and Optimization)
Open AccessArticle
Efficient and Secure EMR Storage and Sharing Scheme Based on Hyperledger Fabric and IPFS
by
Jinxi Guo, Kui Zhao, Zhiwei Liang and Kai Min
Appl. Sci. 2024, 14(12), 5005; https://doi.org/10.3390/app14125005 (registering DOI) - 8 Jun 2024
Abstract
This study examines the issues of privacy protection, data security, and query efficiency in blockchain-based electronic medical record (EMR) sharing. It proposes a secure storage and sharing scheme for EMR based on Hyperledger Fabric and the InterPlanetary File System (IPFS). To mitigate the
[...] Read more.
This study examines the issues of privacy protection, data security, and query efficiency in blockchain-based electronic medical record (EMR) sharing. It proposes a secure storage and sharing scheme for EMR based on Hyperledger Fabric and the InterPlanetary File System (IPFS). To mitigate the privacy risks of data mining that could reveal patient identities, we establish an attribution channel in Hyperledger Fabric to store EMR ownership information and a data channel to store the storage location, digest, and usage records of medical data. Encrypted medical data are stored in the IPFS. To improve query efficiency in the blockchain, we integrate queryable medical data attributes into a composite key for conditional queries, avoiding complex data filtering processes. Additionally, we use a zero-knowledge proof combined with smart contracts for decentralized identity verification, eliminating reliance on third-party centralized verification services and enhancing system security. We also integrate AES and proxy re-encryption techniques to ensure data security during sharing. This scheme provides a more secure, efficient, and privacy-preserving approach for EMR systems, with significant practical implications and broad application potential.
Full article
(This article belongs to the Special Issue Advanced Technologies in Data and Information Security III)
Open AccessArticle
Coarse–Fine Combined Bridge Crack Detection Based on Deep Learning
by
Kaifeng Ma, Mengshu Hao, Xiang Meng, Jinping Liu, Junzhen Meng and Yabing Xuan
Appl. Sci. 2024, 14(12), 5004; https://doi.org/10.3390/app14125004 (registering DOI) - 8 Jun 2024
Abstract
The crack detection of concrete bridges is an important link in the safety evaluation of bridge structures, and the rapid and accurate identification and detection of bridge cracks is a prerequisite for ensuring the safety and long-term stable use of bridges. To solve
[...] Read more.
The crack detection of concrete bridges is an important link in the safety evaluation of bridge structures, and the rapid and accurate identification and detection of bridge cracks is a prerequisite for ensuring the safety and long-term stable use of bridges. To solve the incomplete crack detection and segmentation caused by the complex background and small proportion in the actual bridge crack images, this paper proposes a coarse–fine combined bridge crack detection method of “double detection + single segmentation” based on deep learning. To validate the effect and practicality of fine crack detection, images of old civil bridges and viaduct bridges against a complex background and images of a bridge crack against a simple background are used as datasets. You Only Look Once V5(x) (YOLOV5(x)) was preferred as the object detection network model (ODNM) to perform initial and fine detection of bridge cracks, respectively. Using U-Net as the optimal semantic segmentation network model (SSNM), the crack detection results are accurately segmented for fine crack detection. The test results showed that the initial crack detection using YOLOV5(x) was more comprehensive and preserved the original shape of bridge cracks. Second, based on the initial detection, YOLOV5(x) was adopted for fine crack detection, which can determine the location and shape of cracks more carefully and accurately. Finally, the U-Net model was used to segment the accurately detected cracks and achieved a maximum accuracy (AC) value of 98.37%. The experiment verifies the effectiveness and accuracy of this method, which not only provides a faster and more accurate method for fine detection of bridge cracks but also provides technical support for future automated detection and preventive maintenance of bridge structures and has practical value for bridge crack detection engineering.
Full article
(This article belongs to the Special Issue Advances in Intelligent Bridge: Maintenance and Monitoring)
►▼
Show Figures
Figure 1
Open AccessArticle
Strength and Deformation of Pillars during Mining in the Shaft Pillar
by
Jindřich Šancer, Vladimír Petroš, Vlastimil Hudeček and Pavel Zapletal
Appl. Sci. 2024, 14(12), 5003; https://doi.org/10.3390/app14125003 (registering DOI) - 8 Jun 2024
Abstract
This study of the strength and deformation of coal samples was triggered by the need to define the stress–strain characteristics of pillars during room and pillar mining in the shaft protective pillar at the ČSM Mine. It was probably the world’s deepest deployment
[...] Read more.
This study of the strength and deformation of coal samples was triggered by the need to define the stress–strain characteristics of pillars during room and pillar mining in the shaft protective pillar at the ČSM Mine. It was probably the world’s deepest deployment of this mining method in a coal mine. In order to solve the bearing capacity of pillars, the dependence of coal strength on the slenderness ratio is used. For this reason, coal samples with different slenderness ratios were investigated. After considering the purpose of this research, slenderness ratios (width/height) of 1 to 7.7 were chosen. At the same time, the modulus of deformation as a function of the slenderness ratio was determined, and the vertical deformation of the pillars and the safety factor were calculated. Attention is also paid to the influence of sampling on the results of measured coal strengths.
Full article
(This article belongs to the Topic Complex Rock Mechanics Problems and Solutions)
►▼
Show Figures
Figure 1
Open AccessArticle
Improved YOLOv8-Seg Based on Multiscale Feature Fusion and Deformable Convolution for Weed Precision Segmentation
by
Zhuxi Lyu, Anjiang Lu and Yinglong Ma
Appl. Sci. 2024, 14(12), 5002; https://doi.org/10.3390/app14125002 - 7 Jun 2024
Abstract
Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges
[...] Read more.
Laser-targeted weeding methods further enhance the sustainable development of green agriculture, with one key technology being the improvement of weed localization accuracy. Here, we propose an improved YOLOv8 instance segmentation based on bidirectional feature fusion and deformable convolution (BFFDC-YOLOv8-seg) to address the challenges of insufficient weed localization accuracy in complex environments with resource-limited laser weeding devices. Initially, by training on extensive datasets of plant images, the most appropriate model scale and training weights are determined, facilitating the development of a lightweight network. Subsequently, the introduction of the Bidirectional Feature Pyramid Network (BiFPN) during feature fusion effectively prevents the omission of weeds. Lastly, the use of Dynamic Snake Convolution (DSConv) to replace some convolutional kernels enhances flexibility, benefiting the segmentation of weeds with elongated stems and irregular edges. Experimental results indicate that the BFFDC-YOLOv8-seg model achieves a 4.9% increase in precision, an 8.1% increase in recall rate, and a 2.8% increase in mAP50 value to 98.8% on a vegetable weed dataset compared to the original model. It also shows improved mAP50 over other typical segmentation models such as Mask R-CNN, YOLOv5-seg, and YOLOv7-seg by 10.8%, 13.4%, and 1.8%, respectively. Furthermore, the model achieves a detection speed of 24.8 FPS on the Jetson Orin nano standalone device, with a model size of 6.8 MB that balances between size and accuracy. The model meets the requirements for real-time precise weed segmentation, and is suitable for complex vegetable field environments and resource-limited laser weeding devices.
Full article
(This article belongs to the Section Agricultural Science and Technology)
Journal Menu
► ▼ Journal Menu-
- Applied Sciences Home
- Aims & Scope
- Editorial Board
- Reviewer Board
- Topical Advisory Panel
- Instructions for Authors
- Special Issues
- Topics
- Sections & Collections
- Article Processing Charge
- Indexing & Archiving
- Editor’s Choice Articles
- Most Cited & Viewed
- Journal Statistics
- Journal History
- Journal Awards
- Society Collaborations
- Conferences
- Editorial Office
Journal Browser
► ▼ Journal BrowserHighly Accessed Articles
Latest Books
E-Mail Alert
News
Topics
Topic in
Applied Sciences, Electricity, Electronics, Energies, Sensors
Power System Protection
Topic Editors: Seyed Morteza Alizadeh, Akhtar KalamDeadline: 20 June 2024
Topic in
Applied Sciences, Energies, Machines, Sensors, Vehicles
Vehicle Dynamics and Control
Topic Editors: Peter Gaspar, Junnian WangDeadline: 30 June 2024
Topic in
Applied Sciences, Electronics, Photonics, Remote Sensing, Technologies
Emerging Terahertz Technologies for Integrated Sensing and Communication
Topic Editors: Jianjun Ma, Xiue Bao, Bin Li, Suman MukherjeeDeadline: 31 July 2024
Topic in
Applied Sciences, Cancers, Cells, Electronics, AI
Explainable AI for Health
Topic Editors: Yudong Zhang, Juan Manuel Gorriz, Zhengchao DongDeadline: 8 August 2024
Conferences
Special Issues
Special Issue in
Applied Sciences
Alternative Fuels in Future Energy System
Guest Editor: Krzysztof BiernatDeadline: 10 June 2024
Special Issue in
Applied Sciences
Elastic Waves and Acoustic Emission for Innovative Monitoring of Structures and Engineering Systems
Guest Editors: Kanji Ono, Victor GiurgiutiuDeadline: 30 June 2024
Special Issue in
Applied Sciences
Synthesis and Applications of Metal-Organic Frameworks (MOFs)
Guest Editors: Stephen David Worrall, Julia LinnemannDeadline: 20 July 2024
Special Issue in
Applied Sciences
Cryptology and Information Security in Open and Convergent Environment
Guest Editors: Shaojing Fu, Yuchuan LuoDeadline: 30 July 2024
Topical Collections
Topical Collection in
Applied Sciences
Structural Dynamics and Aeroelasticity
Collection Editors: Sergio Ricci, Paolo Mantegazza, Alessandro De Gaspari, Jonathan E. Cooper, Afzal Suleman, Hector Climent
Topical Collection in
Applied Sciences
Distributed Energy Systems
Collection Editor: Rodolfo Dufo-López
Topical Collection in
Applied Sciences
Intelligent Transportation Systems II: Beyond Intelligent Vehicles
Collection Editors: Javier Alonso Ruiz, Jeroen Ploeg, Angel Llamazares, Noelia Hernández Parra, Carlota Salinas, Rubén Izquierdo
Topical Collection in
Applied Sciences
Optical Design and Engineering
Collection Editors: Zhi-Ting Ye, Pin Han, Chun Hung Lai, Yi Chin Fang