You seem to have javascript disabled. Please note that many of the page functionalities won't work as expected without javascript enabled.

Search for Articles:

Title / Keyword

Author / Affiliation / Email

Journal

Article Type

Advanced Search

Section

Special Issue

Volume

Issue

Number

Page

Logical OperatorOperator

Search Text

Search Type

Shape-Memory Property Acting as a Switch to Change the Surface Property of the Film
Image-Based Musculoskeletal Models to Accurately Reproduce a Maximum Voluntary Isometric Contraction Test In Silico
PFAS: The Journey from Wonder Chemicals to Environmental Nightmares and the Search for Solutions
The Use of Electric Vehicles to Support the Needs of the Electricity Grid: A Systematic Literature Review
1D-CLANet: A Novel Network for NLoS Classification in UWB Indoor Positioning System

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 - Q1 (Engineering, Multidisciplinary) / CiteScore - Q1 (General Engineering)
Rapid Publication: manuscripts are peer-reviewed and a first decision is provided to authors approximately 17.8 days after submission; acceptance to publication is undertaken in 2.7 days (median values for papers published in this journal in the first half of 2024).
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: 2.5 (2023); 5-Year Impact Factor: 2.7 (2023)

Imprint Information Journal Flyer Open Access ISSN: 2076-3417

Latest Articles

30 pages, 3766 KiB

Open AccessArticle

An Interpretable Machine Learning-Based Hurdle Model for Zero-Inflated Road Crash Frequency Data Analysis: Real-World Assessment and Validation

by Moataz Bellah Ben Khedher and Dukgeun Yun

Appl. Sci. 2024, 14(23), 10790; https://doi.org/10.3390/app142310790 (registering DOI) - 21 Nov 2024

Road traffic crashes pose significant economic and public health burdens, necessitating an in-depth understanding of crash causation and its links to underlying factors. This study introduces a machine learning-based hurdle model framework tailored for analyzing zero-inflated crash frequency data, addressing the limitations of [...] Read more.

Road traffic crashes pose significant economic and public health burdens, necessitating an in-depth understanding of crash causation and its links to underlying factors. This study introduces a machine learning-based hurdle model framework tailored for analyzing zero-inflated crash frequency data, addressing the limitations of traditional statistical models like the Poisson and negative binomial models, which struggle with zero-inflation and overdispersion. The research employs a two-stage modeling process using CatBoost. The first stage uses binary classification to identify road segments with potential crash occurrences, applying a customized loss function to tackle data imbalance. The second stage predicts crash frequency, also utilizing a customized loss function for count data. SHapley Additive exPlanations (SHAP) analysis interprets the model outcomes, providing insights into factors affecting crash likelihood and frequency. This study validates the model’s performance with real-world crash data from 2011 to 2015 in South Korea, demonstrating superior accuracy in both the classification and regression stages compared to other machine learning algorithms and traditional models. These findings have significant implications for traffic safety research and policymaking, offering stakeholders a more accurate and interpretable tool for crash data analysis to develop targeted safety interventions. Full article

(This article belongs to the Section Transportation and Future Mobility)

► Show Figures

Figure 1

26 pages, 1818 KiB

Open AccessReview

Microbes and Parameters Influencing Dark Fermentation for Hydrogen Production

by Soumya Gupta, Annabel Fernandes, Ana Lopes, Laura Grasa and Jesús Salafranca

Appl. Sci. 2024, 14(23), 10789; https://doi.org/10.3390/app142310789 (registering DOI) - 21 Nov 2024

Dark fermentation is a promising method for hydrogen (H₂) production utilizing the metabolic pathways of diverse microbial communities. This process can be carried out without the need for light, making it easier and more efficient to operate in different environments and [...] Read more.

Dark fermentation is a promising method for hydrogen (H₂) production utilizing the metabolic pathways of diverse microbial communities. This process can be carried out without the need for light, making it easier and more efficient to operate in different environments and at a lower cost. It also utilizes a wide range of substrates, making it highly adaptable to waste-to-energy applications. Clostridium spp. are particularly favored in this method due to their versatile metabolism, ability to utilize a wide range of substrates, and high H₂ yields. Anaerobes and facultative anaerobes are mostly used in studies due to their efficient hydrogenase enzyme activity and metabolic pathways. A pH range of 5.5–6.5 and a temperature of 30–37 °C for mesophiles and 55–60 °C for thermophiles are usually preferred in addition to the other parameters such as hydraulic retention time and substrate used. The highest H₂ yield of 9.39 mol H₂/mol sucrose consumed was obtained by C. beijerinckii using sucrose as a substrate under batch mode conditions at 37 °C and pH 6–7. The review analyzes different bacterial species and examines the influence of optimized parameters required on H₂ yield in different bioreactor operating modes. Full article

(This article belongs to the Section Applied Microbiology)

► Show Figures

Figure 1

14 pages, 1211 KiB

Open AccessArticle

Anxiety Detection System Based on Galvanic Skin Response Signals

by Abeer Al-Nafjan and Mashael Aldayel

Appl. Sci. 2024, 14(23), 10788; https://doi.org/10.3390/app142310788 (registering DOI) - 21 Nov 2024

Anxiety is a significant mental health concern that can be effectively monitored using physiological signals such as galvanic skin response (GSR). While the potential of machine learning (ML) algorithms to enhance the classification of anxiety based on GSR signals is promising, their effectiveness [...] Read more.

Anxiety is a significant mental health concern that can be effectively monitored using physiological signals such as galvanic skin response (GSR). While the potential of machine learning (ML) algorithms to enhance the classification of anxiety based on GSR signals is promising, their effectiveness in this context remains largely underexplored. This study addresses this gap by investigating the performance of three commonly used ML algorithms, support vector machine (SVM), K-nearest neighbor (KNN), and random forest (RF), in classifying anxiety and stress activity using a benchmark dataset. We employed two feature extraction methods: traditional statistical feature extraction and an innovative automatic feature extraction approach utilizing a 14-layer autoencoder, aimed at improving classification performance. Our findings demonstrate the effectiveness of using GSR signals and the robust performance of the KNN algorithm in accurately classifying anxiety levels. The KNN algorithm achieved the highest accuracy in both the statistical and automatic feature extraction approaches, with results of 96.9% and 98.2%, respectively. These findings highlight the effectiveness of KNN for anxiety detection and emphasize the need for advanced feature extraction techniques to enhance classification outcomes in mental health monitoring. Full article

(This article belongs to the Special Issue Advanced Technologies and Applications of Emotion Recognition)

► Show Figures

Figure 1

17 pages, 890 KiB

Open AccessArticle

Optimal Task Offloading Strategy for Vehicular Networks in Mixed Coverage Scenarios

by Xuewen He, Yuhao Cen, Yinsheng Liao, Xin Chen and Chao Yang

Appl. Sci. 2024, 14(23), 10787; https://doi.org/10.3390/app142310787 (registering DOI) - 21 Nov 2024

With the rapidly escalating demand for high real-time performance and data throughput capabilities, the limitations of on-board computing resources have rendered traditional computing services inadequate to meet these burgeoning requirements. Vehicular edge computing offers a viable solution to this challenge, yet the roadside [...] Read more.

With the rapidly escalating demand for high real-time performance and data throughput capabilities, the limitations of on-board computing resources have rendered traditional computing services inadequate to meet these burgeoning requirements. Vehicular edge computing offers a viable solution to this challenge, yet the roadside units (RSUs) are prone to overloading in congested traffic conditions. In this paper, we introduce an optimal task offloading strategy under congested conditions, which is facilitated by a mixed coverage scenario with both 5G base stations and RSUs with the aim of enhancing the efficiency of computing resource utilization and reducing the task processing delay. This study employs long short-term memory networks to predict the loading status of base stations. Then, based on the prediction results, we propose an optimized task offloading strategy using the proximal policy optimization algorithm. The main constraint is that the data transmission rates of users should satisfy the quality of service. It effectively alleviates the overload issue of RSUs during congested conditions and improves service quality. The simulation results substantiate the effectiveness of the proposed strategy in reducing the task processing delay and enhancing the quality of service. Full article

► Show Figures

Figure 1

13 pages, 6459 KiB

Open AccessArticle

The Development of Fiber–Cement Flat Sheets by Young and Mature Coconut Fibers to Replace Asbestos for Eco-Friendly Products

by Prachoom Khamput, Tawich Klathae, Chookiat Choosakul and Saofee Dueramae

Appl. Sci. 2024, 14(23), 10786; https://doi.org/10.3390/app142310786 (registering DOI) - 21 Nov 2024

This study investigated young and mature coconut fibers as an asbestos replacement in fiber–cement flat sheets. The ratio of fiber content ranged from 5% to 9.5% in increments of 0.5% by weight of binder. Crushed rock dust (CRD) was also utilized in this [...] Read more.

This study investigated young and mature coconut fibers as an asbestos replacement in fiber–cement flat sheets. The ratio of fiber content ranged from 5% to 9.5% in increments of 0.5% by weight of binder. Crushed rock dust (CRD) was also utilized in this study at a ratio of 50% as sand replacement. The results showed that the addition of young coconut fiber (YCF) and mature coconut fiber (MCF) in flat sheets increased with decreasing bulk density and thermal conductivity. The optimum fiber content was 6.5%–7% by weight of binder for two types of fiber with the highest modulus of rupture of 12–13 MPa. The modulus of rupture and density of fiber–cement flat sheets using YCF were higher than that of fiber–cement flat sheets using MCF, which was clarified by SEM results due to the denser structure of MCF. Moreover, the modulus of rupture was directly proportional to the modulus of elasticity in fiber–cement flat sheets. Full article

(This article belongs to the Special Issue Mechanical Properties and Characterization Technologies of Composite Materials)

► Show Figures

Figure 1

27 pages, 1557 KiB

Open AccessReview

Sustainable Extraction of Bioactive Compounds and Nutrients from Agri-Food Wastes: Potential Reutilization of Berry, Honey, and Chicory Byproducts

by Gregorio Peron, Irene Ferrarese, Nadia Carmo Dos Santos, Filippo Rizzo, Giorgio Gargari, Noemi Bertoli, Emanuela Gobbi, Alvise Perosa, Maurizio Selva and Stefano Dall’Acqua

Appl. Sci. 2024, 14(23), 10785; https://doi.org/10.3390/app142310785 - 21 Nov 2024

Several agri-food byproducts represent valuable sources of compounds to be reutilized for nutritional, nutraceutical, and cosmetic purposes. Examples especially comprise byproducts from the processing of fruits such as pomace, because of their richness in nutrients (e.g., fibers) and bioactive compounds (e.g., polyphenols) that [...] Read more.

Several agri-food byproducts represent valuable sources of compounds to be reutilized for nutritional, nutraceutical, and cosmetic purposes. Examples especially comprise byproducts from the processing of fruits such as pomace, because of their richness in nutrients (e.g., fibers) and bioactive compounds (e.g., polyphenols) that can be destined for animal and human use. However, in agreement with the principles of circular economy that are being promoted during the most recent years, other understudied agri-food byproducts of both plant and animal origin are being evaluated to assess their possible reutilization and valorization. In this review, we aim at summarizing the most recent research dealing with the extraction of nutrients and bioactive compounds from agri-food byproducts using innovative and sustainable approaches. Specifically, the review is focused on byproducts generated in large amounts (tons/year) by the food industry of Northeast Italy, namely, honey, red fruits (grapes and berries), and chicory, which are especially of interest for their content in phenolic acids, flavonoids, anthocyanins, and dietary fiber. The potential applications of these byproducts and extracts in cosmetic, nutraceutical, and nutritional fields are also discussed, referring to the published literature, as well as their potential utilization as sources of novel bioactive compounds with pharmacological applications. Full article

(This article belongs to the Special Issue Green Extraction and Valorisation of Bioactive Compounds from Food and Food Waste)

► Show Figures

Figure 1

20 pages, 4529 KiB

Open AccessArticle

Robust Segmentation of Partial and Imperfect Dental Arches

by Ammar Alsheghri, Ying Zhang, Golriz Hosseinimanesh, Julia Keren, Farida Cheriet and François Guibault

Appl. Sci. 2024, 14(23), 10784; https://doi.org/10.3390/app142310784 (registering DOI) - 21 Nov 2024

Automatic and accurate dental arch segmentation is a fundamental task in computer-aided dentistry. Recent trends in digital dentistry are tackling the design of 3D crowns using artificial intelligence, which initially requires a proper semantic segmentation of teeth from intraoral scans (IOS). In practice, [...] Read more.

Automatic and accurate dental arch segmentation is a fundamental task in computer-aided dentistry. Recent trends in digital dentistry are tackling the design of 3D crowns using artificial intelligence, which initially requires a proper semantic segmentation of teeth from intraoral scans (IOS). In practice, most IOS are partial with as few as three teeth on the scanned arch, and some of them might have preparations, missing, or incomplete teeth. Existing deep learning-based methods (e.g., MeshSegNet, DArch) were proposed for dental arch segmentation, but they are not as efficient for partial arches that include imperfections such as missing teeth and preparations. In this work, we present the ArchSeg framework that can leverage various deep learning models for semantic segmentation of perfect and imperfect dental arches. The Point Transformer V2 deep learning model is used as the backbone for the ArchSeg framework. We present experiments to demonstrate the efficiency of the proposed framework to segment arches with various types of imperfections. Using a raw dental arch scan with two labels indicating the range of present teeth in the arch (i.e., the first and the last teeth), our ArchSeg can segment a standalone dental arch or a pair of aligned master/antagonist arches with more available information (i.e., die mesh). Two generic models are trained for lower and upper arches; they achieve dice similarity coefficient scores of

0.936 \pm 0.008

and

0.948 \pm 0.007

, respectively, on test sets composed of challenging imperfect arches. Our work also highlights the impact of appropriate data pre-processing and post-processing on the final segmentation performance. Our ablation study shows that the segmentation performance of the Point Transformer V2 model integrated in our framework is improved compared with the original standalone model. Full article

► Show Figures

Figure 1

18 pages, 8779 KiB

Open AccessCase Report

Correlational Research of Strength Parameters of Waste Soils Determined in the Laboratory and In Situ in Cracow

by Jakub Zięba and Elżbieta Pilecka

Appl. Sci. 2024, 14(23), 10783; https://doi.org/10.3390/app142310783 - 21 Nov 2024

This work presents an analysis of the relationship between strength parameters determined in the laboratory and the results of a cone penetration test with pore water pressure measurement (CPTU) of waste soils in the “White Seas” area in Cracow. Anthropogenic soil is an [...] Read more.

This work presents an analysis of the relationship between strength parameters determined in the laboratory and the results of a cone penetration test with pore water pressure measurement (CPTU) of waste soils in the “White Seas” area in Cracow. Anthropogenic soil is an alkaline waste formed during the production of soda ash and deposited in the area of the former Solvay Sodium Plant factory in Cracow, Poland. Due to the large area of the land and numerous investment plans and completed buildings, there was a need to identify reliable functional relationships enabling the determination of the strength parameters of these soils based on the results of the CPTU. Statistical analysis showed that the best correlation with the test results was provided by two logarithmic functions in which the dependent variables were the effective friction angle and effective cohesion. The dependent variable for both cases was the corrected cone resistance q_t. The functional relationship combined data from labour-intensive, long-lasting and costly laboratory measurements with quick and less expensive measurements, i.e., in situ CPTUs. The obtained relationships enable the determination of the strength properties of the subsoil of these anthropogenic soils. Full article

(This article belongs to the Section Civil Engineering)

► Show Figures

Figure 1

43 pages, 4570 KiB

Open AccessArticle

Fine-Tuning Retrieval-Augmented Generation with an Auto-Regressive Language Model for Sentiment Analysis in Financial Reviews

by Miehleketo Mathebula, Abiodun Modupe and Vukosi Marivate

Appl. Sci. 2024, 14(23), 10782; https://doi.org/10.3390/app142310782 - 21 Nov 2024

Sentiment analysis is a well-known task that has been used to analyse customer feedback reviews and media headlines to detect the sentimental personality or polarisation of a given text. With the growth of social media and other online platforms, like Twitter (now branded [...] Read more.

Sentiment analysis is a well-known task that has been used to analyse customer feedback reviews and media headlines to detect the sentimental personality or polarisation of a given text. With the growth of social media and other online platforms, like Twitter (now branded as X), Facebook, blogs, and others, it has been used in the investment community to monitor customer feedback, reviews, and news headlines about financial institutions’ products and services to ensure business success and prioritise aspects of customer relationship management. Supervised learning algorithms have been popularly employed for this task, but the performance of these models has been compromised due to the brevity of the content and the presence of idiomatic expressions, sound imitations, and abbreviations. Additionally, the pre-training of a larger language model (PTLM) struggles to capture bidirectional contextual knowledge learnt through word dependency because the sentence-level representation fails to take broad features into account. We develop a novel structure called language feature extraction and adaptation for reviews (LFEAR), an advanced natural language model that amalgamates retrieval-augmented generation (RAG) with a conversation format for an auto-regressive fine-tuning model (ARFT). This helps to overcome the limitations of lexicon-based tools and the reliance on pre-defined sentiment lexicons, which may not fully capture the range of sentiments in natural language and address questions on various topics and tasks. LFEAR is fine-tuned on Hellopeter reviews that incorporate industry-specific contextual information retrieval to show resilience and flexibility for various tasks, including analysing sentiments in reviews of restaurants, movies, politics, and financial products. The proposed model achieved an average precision score of 98.45%, answer correctness of 93.85%, and context precision of 97.69% based on Retrieval-Augmented Generation Assessment (RAGAS) metrics. The LFEAR model is effective in conducting sentiment analysis across various domains due to its adaptability and scalable inference mechanism. It considers unique language characteristics and patterns in specific domains to ensure accurate sentiment annotation. This is particularly beneficial for individuals in the financial sector, such as investors and institutions, including those listed on the Johannesburg Stock Exchange (JSE), which is the primary stock exchange in South Africa and plays a significant role in the country’s financial market. Future initiatives will focus on incorporating a wider range of data sources and improving the system’s ability to express nuanced sentiments effectively, enhancing its usefulness in diverse real-world scenarios. Full article

(This article belongs to the Special Issue Applications of Data Science and Artificial Intelligence)

► Show Figures

Figure 1

21 pages, 10351 KiB

Open AccessArticle

TSViT: A Time Series Vision Transformer for Fault Diagnosis of Rotating Machinery

by Shouhua Zhang, Jiehan Zhou, Xue Ma, Susanna Pirttikangas and Chunsheng Yang

Appl. Sci. 2024, 14(23), 10781; https://doi.org/10.3390/app142310781 - 21 Nov 2024

Efficient and accurate fault diagnosis of rotating machinery is extremely important. Fault diagnosis methods using vibration signals based on convolutional neural networks (CNNs) have become increasingly mature. They often struggle with capturing the temporal dynamics of vibration signals. To overcome this, the application [...] Read more.

Efficient and accurate fault diagnosis of rotating machinery is extremely important. Fault diagnosis methods using vibration signals based on convolutional neural networks (CNNs) have become increasingly mature. They often struggle with capturing the temporal dynamics of vibration signals. To overcome this, the application of Transformer-based Vision Transformer (ViT) methods to fault diagnosis is gaining attraction. Nonetheless, these methods typically require extensive preprocessing, which increases computational complexity, potentially reducing the efficiency of the diagnosis process. Addressing this gap, this paper presents the Time Series Vision Transformer (TSViT), tailored for effective fault diagnosis. The TSViT incorporates a convolutional layer to extract local features from vibration signals alongside a transformer encoder to discern long-term temporal patterns. A thorough experimental comparison of three diverse datasets demonstrates the TSViT’s effectiveness and adaptability. Moreover, the paper delves into the influence of hyperparameter tuning on the model’s performance, computational demand, and parameter count. Remarkably, the TSViT achieves an unprecedented 100% average accuracy on two of the test sets and 99.99% on the other, showcasing its exceptional fault diagnosis capabilities for rotating machinery. The implementation of this model will bring significant economic benefits. Full article

(This article belongs to the Special Issue Signal Acquisition and Processing for Measurement and Testing)

► Show Figures

Figure 1

13 pages, 1217 KiB

Open AccessArticle

Predicting the Open Porosity of Industrial Mortar Applied on Different Substrates: A Machine Learning Approach

by Rafael Travincas, Maria Paula Mendes, Isabel Torres and Inês Flores-Colen

Appl. Sci. 2024, 14(23), 10780; https://doi.org/10.3390/app142310780 - 21 Nov 2024

This study aims to evaluate the potential of machine learning algorithms (Random Forest and Support Vector Machine) in predicting the open porosity of a general-use industrial mortar applied to different substrates based on the characteristics of both the mortar and substrates. This study’s [...] Read more.

This study aims to evaluate the potential of machine learning algorithms (Random Forest and Support Vector Machine) in predicting the open porosity of a general-use industrial mortar applied to different substrates based on the characteristics of both the mortar and substrates. This study’s novelty lies in predicting the mortar’s porosity considering the substrate’s influence on which this mortar is applied. For this purpose, an experimental database comprising 1592 datapoints of industrial mortar applied to five different substrates (hollowed ceramic brick, solid ceramic brick, concrete block, concrete slab, and lightweight concrete block) was generated using an experimental program. The samples were characterized by bulk density, open porosity, capillary water absorption coefficient, drying index, and compressive strength. This database was then used to train and test the machine learning algorithms to predict the open porosity of the mortar. The results indicate that it is possible to predict the open porosity of mortar with good prediction accuracy, and that both Random Forest (RF) and Support Vector Machine (SVM) algorithms (RF = 0.880; SVM = 0.896) are suitable for this task. Regarding the main characteristics that influence the open porosity of the mortar, the bulk density and open porosity of the substrate are significant factors. Furthermore, this study employs a straightforward methodology with a machine learning no-code platform, enhancing the replicability of its findings for future research and practical implementations. Full article

(This article belongs to the Special Issue AI Horizons: Present Status and Visions for the Next Era)

► Show Figures

Figure 1

14 pages, 2284 KiB

Open AccessArticle

Preamble-Based Noncoherent Synchronization in Molecular Communication: A Machine Learning Approach

by Seok-Hwan Moon, Pankaj Singh and Sung-Yoon Jung

Appl. Sci. 2024, 14(23), 10779; https://doi.org/10.3390/app142310779 - 21 Nov 2024

In the field of wireless communication, there is growing interest in molecular communication (MC), which integrates nano-, bio-, and communication technologies. Inspired by nature, MC uses molecules to transmit data, especially in environments where EM waves struggle to penetrate. In MC, signals can [...] Read more.

In the field of wireless communication, there is growing interest in molecular communication (MC), which integrates nano-, bio-, and communication technologies. Inspired by nature, MC uses molecules to transmit data, especially in environments where EM waves struggle to penetrate. In MC, signals can be distinguished based on molecular concentration, known as concentrated-encoded molecular communication (CEMC). These molecules diffuse through an MC channel and are received via ligand–receptor binding mechanisms. Synchronization in CEMC is critical for minimizing errors and enhancing communication performance. This study introduces a novel preamble-based noncoherent synchronization method, specifically designed for resource-constrained environments like nanonetworks. The method’s simple, low-complexity structure makes it suitable for nanomachines, while machine learning (ML) techniques are used to improve synchronization accuracy by adapting to the nonlinear characteristics of the channel. The proposed approach leverages ML to achieve robust performance. Simulation results demonstrate a synchronization probability of 0.8 for a transmitter-receiver distance of 1 cm, given a molecular collection time duration four times the pulse duration. These results confirm the significant benefits of integrating ML, showcasing improved synchronization probability and reduced mean square error. The findings contribute to the advancement of efficient and practical MC systems, offering insights into synchronization and error reduction in complex environments. Full article

► Show Figures

Figure 1

18 pages, 1337 KiB

Open AccessSystematic Review

The Use of Smart Rings in Health Monitoring—A Meta-Analysis

by Matteo Fiore, Alessandro Bianconi, Gaia Sicari, Alice Conni, Jacopo Lenzi, Giulia Tomaiuolo, Flavia Zito, Davide Golinelli and Francesco Sanmarchi

Appl. Sci. 2024, 14(23), 10778; https://doi.org/10.3390/app142310778 - 21 Nov 2024

Smart Rings (SRs) are user-friendly devices capable of measuring various health parameters, making them suitable for remote continuous monitoring in diverse clinical settings. Since the available evidence on the accuracy of SRs recording health data is highly heterogeneous, this systematic review, conducted in [...] Read more.

Smart Rings (SRs) are user-friendly devices capable of measuring various health parameters, making them suitable for remote continuous monitoring in diverse clinical settings. Since the available evidence on the accuracy of SRs recording health data is highly heterogeneous, this systematic review, conducted in accordance with PRISMA guidelines, searched for articles evaluating the efficacy of SRs for sleep, respiratory, and cardiovascular monitoring across the PubMed, SCOPUS, and ProQuest databases. Meta-analyses were conducted for health outcomes evaluated in at least three studies with a comparable study population and design, and the same comparison device. Nineteen articles were included: eleven analyses focused on sleep quality, eight on cardiovascular parameters, and one on oxygen saturation. Studies analysing cardiovascular outcomes found a good accuracy of SRs in measuring heart rate (HR) with a mean bias of −0.4 bpms (limits of agreement (LoAs): −2.7; 1.8). The meta-analyses showed variability in SRs’ efficacy in monitoring total sleep time (mean bias: −21.3 min, LoAs: −69.9, 27.4) and REM duration (mean bias: −18.2 min, LoAs: −33.3, −3.1). The results highlighted the promising potential of SRs for HR monitoring. Further research is needed to clarify the reliability of SRs in monitoring sleep quality and their use directed to a broader range of health parameters. With further development, SRs could become valuable tools for healthcare professionals. Full article

(This article belongs to the Special Issue Advanced Technologies for Health Improvement)

► Show Figures

Figure 1

20 pages, 9191 KiB

Open AccessArticle

EMF Assessment Utilizing Low-Cost Mobile Applications

by Spyridon Delidimitriou, Dimitrios Babas, Athanasios Manassas, Joe Wiart and Theodoros Samaras

Appl. Sci. 2024, 14(23), 10777; https://doi.org/10.3390/app142310777 - 21 Nov 2024

This study introduces a low-cost alternative method for mapping the electric field strength from 4G LTE base stations and identifies areas where this mapping is more accurate. A drive test campaign was conducted in the urban environment of Thessaloniki, Greece, using data obtained [...] Read more.

This study introduces a low-cost alternative method for mapping the electric field strength from 4G LTE base stations and identifies areas where this mapping is more accurate. A drive test campaign was conducted in the urban environment of Thessaloniki, Greece, using data obtained from three identical smartphones, each connected to a different mobile operator and an exposimeter. The smartphones used a mobile application to record Reference Signal Received Power (RSRP) values, while the exposimeter measured the electric field strength in selected frequency bands. In the first part, the variability of the received power over different periods within certain areas was studied, and the reasons for this variability were identified. In the second part, a linear factor was calculated to convert RSRP values into electric field strength using data from both the application and the exposimeter. The converted RSRP values were subsequently compared with the exposimeter data for validation. The results indicate that in areas where the variability of the received power is lower, the linear relationship between smartphone and exposimeter data is statistically stronger resulting in calculated electric field strength values are closer to the measured. Full article

► Show Figures

Figure 1

22 pages, 4118 KiB

Open AccessArticle

Empirical Evidence Regarding Few-Shot Learning for Scene Classification in Remote Sensing Images

by Valdivino Alexandre de Santiago Júnior

Appl. Sci. 2024, 14(23), 10776; https://doi.org/10.3390/app142310776 - 21 Nov 2024

Few-shot learning (FSL) is a learning paradigm which aims to address the issue of machine/deep learning techniques which traditionally need huge amounts of labelled data to work out. The remote sensing (RS) community has explored this paradigm with numerous published studies to date. [...] Read more.

Few-shot learning (FSL) is a learning paradigm which aims to address the issue of machine/deep learning techniques which traditionally need huge amounts of labelled data to work out. The remote sensing (RS) community has explored this paradigm with numerous published studies to date. Nevertheless, there is still a need for clear pieces of evidence on FSL-related issues in the RS context, such as which of the inference approaches is more suitable: inductive or transductive? Moreover, how does the number of epochs used during training, based on the meta-training (base) dataset, relate to the number of unseen classes during inference? This study aims to address these and other relevant questions in the context of FSL for scene classification in RS images. A comprehensive evaluation was conducted considering eight FSL approaches (three inductive and five transductive) and six scene classification databases. Some conclusions of this research are as follows: (1) transductive approaches are better than inductive ones. In particular, the transductive technique Transductive Information Maximisation (TIM) presented the best overall performance, where in 20 cases it got the first place; (2) a larger number of training epochs is more beneficial when there are more unseen classes during the inference phase. The most impressive gains occurred particularly considering the AID (6-way) and RESISC-45 (9-way) datasets. Notably, in the AID dataset, a remarkable 58.412% improvement was achieved in 1-shot tasks going from 10 to 200 epochs; (3) using five samples in the support set is statistically significantly better than using only one; and (4) a higher similarity between unseen classes (during inference) and some of the training classes does not lead to an improved performance. These findings can guide RS researchers and practitioners in selecting optimal solutions/strategies for developing their applications demanding few labelled samples. Full article

(This article belongs to the Topic Computational Intelligence in Remote Sensing: 2nd Edition)

► Show Figures

Figure 1

13 pages, 2583 KiB

Open AccessArticle

Detection of Pest Feeding Traces on Industrial Wood Surfaces with 3D Imaging

by Andrzej Sioma, Keiko Nagashima, Bartosz Lenty, Arkadiusz Hebda, Yasutaka Nakata and Kiichi Harada

Appl. Sci. 2024, 14(23), 10775; https://doi.org/10.3390/app142310775 - 21 Nov 2024

This paper presents a method for detecting holes and grooves made by wood-boring pests. As part of the production process automation, wood delivered from sawmills is checked for defects visible on its surface. One of the critical defects that disqualifies wood from further [...] Read more.

This paper presents a method for detecting holes and grooves made by wood-boring pests. As part of the production process automation, wood delivered from sawmills is checked for defects visible on its surface. One of the critical defects that disqualifies wood from further processing is the presence of feeding marks left by various types of pests on its surface. This paper proposes a method for detecting this type of damage based on analysis of three-dimensional images of the wood surface. Three-dimensional imaging methods and the image resolutions resulting from the adopted imaging system’s configurations are discussed. An analysis of the advantages and disadvantages of the methods investigated is presented, together with an assessment of their potential use in the implementation of the assigned control task, i.e., the detection of holes and grooves made by pests. Three-dimensional image parameters and interferences affecting the quality of the recorded image are described, along with the designed algorithm for identifying holes and grooves and the parametric description of the identified defect. The imaging effects for selected surfaces bearing signs of pest damage and the parameters describing the effectiveness of the present industrial solution are also presented. This paper demonstrates that it is possible to build a three-dimensional image to identify damage effectively within a minimum diameter of 1mm. It makes it possible to observe the damage carried out by most wood-boring pests. Full article

(This article belongs to the Special Issue Applications of Vision Measurement System on Product Quality Control)

► Show Figures

Figure 1

22 pages, 4119 KiB

Open AccessArticle

Fast Detection of Idler Supports Using Density Histograms in Belt Conveyor Inspection with a Mobile Robot

by Janusz Jakubiak and Jakub Delicat

Appl. Sci. 2024, 14(23), 10774; https://doi.org/10.3390/app142310774 - 21 Nov 2024

The automatic inspection of belt conveyors gathers increasing attention in the mining industry. The utilization of mobile robots to perform the inspection allows increasing the frequency and precision of inspection data collection. One of the issues that needs to be solved is the [...] Read more.

The automatic inspection of belt conveyors gathers increasing attention in the mining industry. The utilization of mobile robots to perform the inspection allows increasing the frequency and precision of inspection data collection. One of the issues that needs to be solved is the location of inspected objects, such as, for example, conveyor idlers in the vicinity of the robot. This paper presents a novel approach to analyze the 3D LIDAR data to detect idler frames in real time with high accuracy. Our method processes a point cloud image to determine positions of the frames relative to the robot. The detection algorithm utilizes density histograms, Euclidean clustering, and a dimension-based classifier. The proposed data flow focuses on separate processing of single scans independently, to minimize the computational load, necessary for real-time performance. The algorithm is verified with data recorded in a raw material processing plant by comparing the results with human-labeled objects. The proposed process is capable of detecting idler frames in a single 3D scan with accuracy above 83%. The average processing time of a single scan is under 22 ms, with a maximum of 75 ms, ensuring that idler frames are detected within the scan acquisition period, allowing continuous operation without delays. These results demonstrate that the algorithm enables the fast and accurate detection and localization of idler frames in real-world scenarios. Full article

(This article belongs to the Special Issue Design, Analysis, Intelligent Control and Optimization of Industrial and Manufacturing Processes)

► Show Figures

Figure 1

19 pages, 7565 KiB

Open AccessArticle

Improving Mechanical Properties of Low-Quality Pure Aluminum by Minor Reinforcement with Fine B₄C Particles and T6 Heat Treatment

by Maxat Abishkenov, Ilgar Tavshanov, Nikita Lutchenko, Nursultan Amanzholov, Daniyar Kalmyrzayev, Zhassulan Ashkeyev, Kayrosh Nogaev, Saltanat Kydyrbayeva and Assylbek Abdirashit

Appl. Sci. 2024, 14(23), 10773; https://doi.org/10.3390/app142310773 - 21 Nov 2024

Pure aluminum, due to its inherent low strength and softness, is unsuitable for most structural applications. However, unlike many aluminum alloys, pure aluminum exhibits high ductility and is often free from expensive alloying elements. This makes it a promising candidate for minor reinforcement [...] Read more.

Pure aluminum, due to its inherent low strength and softness, is unsuitable for most structural applications. However, unlike many aluminum alloys, pure aluminum exhibits high ductility and is often free from expensive alloying elements. This makes it a promising candidate for minor reinforcement to produce cost-effective composites with an optimal balance of strength and ductility. This study assesses the possibility of improving the mechanical performance of pure aluminum specimens by minor reinforcement (~0.36 wt. %) with fine B₄C particles and T6 heat treatment. The composites were obtained using ultrasonic-assisted stir casting and were characterized by assessing their density, microhardness, yield strength (YS), ultimate tensile strength (UTS), and elongation. Light microscopy (LM), scanning electron microscopy (SEM), energy-dispersive spectroscopy (EDS), and X-ray diffraction (XRD) tests were conducted to investigate the presence and distribution of reinforcing particles in the Al matrix. Minor reinforcement of ~0.5–2 μm with B₄C particles without/with subsequent T6 heat treatment resulted in an increase in microhardness by 71.45% and 143.37% and UTS by 71.05% and 140.16%, respectively, while the elongation values of the specimens decreased to 51.98% and 42.38%, respectively, compared with the adopted initial matrix Al specimen. Full article

(This article belongs to the Section Materials Science and Engineering)

► Show Figures

Figure 1

16 pages, 2926 KiB

Open AccessArticle

Few Adjustable Parameters Prediction Model Based on Lightweight Prefix-Tuning: Learning Session Dropout Prediction Model Based on Parameter-Efficient Prefix-Tuning

by Yuantong Lu and Zhanquan Wang

Appl. Sci. 2024, 14(23), 10772; https://doi.org/10.3390/app142310772 - 21 Nov 2024

In response to the challenge of low predictive accuracy in scenarios with limited data, we propose a few adjustable parameters prediction model based on lightweight prefix-tuning (FAP-Prefix). Prefix-tuning is an efficient fine-tuning method that only adjusts prefix vectors while keeping the model’s original [...] Read more.

In response to the challenge of low predictive accuracy in scenarios with limited data, we propose a few adjustable parameters prediction model based on lightweight prefix-tuning (FAP-Prefix). Prefix-tuning is an efficient fine-tuning method that only adjusts prefix vectors while keeping the model’s original parameters frozen. In each transformer layer, the prefix vectors are connected with the internal key-value pair of the transformer structure. By training on the synthesized sequence of the prefix and original input with masked learning, the transformer model learns the features of individual learning behaviors. In addition, it can also discover hidden connections of continuous learning behaviors. During fine-tuning, all parameters of the pre-trained model are frozen, and downstream task learning is accomplished by adjusting the prefix parameters. Continuous trainable prefix vectors can influence subsequent vector representations, leading to the generation of session dropout prediction results. The experiments show that FAP-Prefix significantly outperforms traditional methods in data-limited settings, with AUC improvements of +4.58%, +3.53%, and +8.49% under 30%, 10%, and 1% data conditions, respectively. It also surpasses state-of-the-art models in prediction performance (AUC +5.42%, ACC +5.3%, F1 score +5.68%). Full article

► Show Figures

Figure 1

13 pages, 5059 KiB

Open AccessArticle

Measurement of Ultra-High Speed by Optical Multistage Cascade Frequency Reduction Technology

by Heli Ma, Long Chen, Wei Gu, Cangli Liu, Longhuang Tang, Xing Jia, Tianjiong Tao, Shenggang Liu, Yongchao Chen, Xiang Wang, Jian Wu, Chengjun Li, Dameng Liu, Jidong Weng and Huan Liu

Appl. Sci. 2024, 14(23), 10771; https://doi.org/10.3390/app142310771 - 21 Nov 2024

In order to reduce the frequency of high-frequency Doppler signal light, the electronic bandwidth of a data acquisition system is reduced. This paper mainly describes the principle and experimental verification results of optical multistage cascade frequency reduction technology. The bandwidth requirement of the [...] Read more.

In order to reduce the frequency of high-frequency Doppler signal light, the electronic bandwidth of a data acquisition system is reduced. This paper mainly describes the principle and experimental verification results of optical multistage cascade frequency reduction technology. The bandwidth requirement of the detector and the oscilloscope is reduced by the method of “relaying” the measured beat frequency signal between multiple electronic channels. Aiming to achieve the requirement of ultra-high speed measurement of 22 km/s, the requirement of the original signal frequency as high as 28 GHz electrical bandwidth is reduced to the acquisition and recording system with only 8 GHz bandwidth. A complete velocity profile of up to 11.47 km/s is measured on a three-stage light gas gun with velocity measurement accuracy of 1%. Full article

(This article belongs to the Special Issue Advanced Optical Measurement Techniques and Applications)

► Show Figures

Figure 1

More Articles...

Submit to Applied Sciences Review for Applied Sciences

Journal Menu

Journal Browser

► Journal Browser

Highly Accessed Articles

View More...

Latest Books

More Books and Reprints...

E-Mail Alert

News

14 November 2024
Applied Sciences Webinar | Advanced Vibrational Spectroscopy Technology: Emerging Trends in Biomedical Applications, 27 November 2024

13 November 2024
Meet Us at the 4th Central European Technology Forum, 18–19 November 2024, Krakow, Poland

13 November 2024
Meet Us at the 38^th IEEE International Conference on Micro Electro Mechanical Systems (IEEE MEMS 2025), 19–23 January 2025, Kaohsiung, Taiwan

More News & Announcements...

Topics

Propose a Topic

Topic in Electronics, Applied Sciences, BDCC, Mathematics, Chips

Theory and Applications of High Performance Computing Topic Editors: Pavel Lyakhov, Maxim Deryabin
Deadline: 30 November 2024

Topic in Applied Sciences, JMMP, Materials, Metrology, Sensors, Standards

Measurement Strategies and Standardization in Manufacturing Topic Editors: Manuel Rodríguez-Martín, João Ribeiro, Roberto García Martín
Deadline: 20 December 2024

Topic in Applied Sciences, Clean Technol., Energies, JMSE, Wind

Advances in Wind Energy Technology Topic Editors: Galih Bangga, Martin Otto Laver Hansen
Deadline: 31 December 2024

Topic in Energies, Applied Sciences, Forecasting, Solar, Wind

Solar and Wind Power and Energy Forecasting Topic Editors: Emanuele Ogliari, Alessandro Niccolai, Sonia Leva
Deadline: 1 January 2025

More Topics

Conferences

Announce Your Conference

26–28 November 2024 11th International Electronic Conference on Sensors and Applications

27 November 2024 Applied Sciences Webinar | Advanced Vibrational Spectroscopy Technology: Emerging Trends in Biomedical Applications, 27 November 2024

4–6 December 2024 Welcome from the Chairs

More Conferences...

Special Issues

Propose a Special Issue

Special Issue in Applied Sciences

New Advances, Innovations and Applications in Environmental Geochemistry for the Study of Human Impacts Guest Editors: Ricardas Taraskevicius, Rimantė Zinkutė
Deadline: 25 November 2024

Special Issue in Applied Sciences

Advances of Hyaluronan in Tissue Regeneration Guest Editors: Kaustuv Basu, Paraskevi Heldin, Davide Vigetti
Deadline: 29 November 2024

Special Issue in Applied Sciences

Update on Applications in Medical Imaging and Natural Language Processing Guest Editor: Tariq Rahim
Deadline: 30 November 2024

Special Issue in Applied Sciences

High-Performance Integrated Circuits and Systems Guest Editors: Wang Kang, Biao Pan
Deadline: 30 November 2024

More Special Issues

Topical Collections

Topical Collection in Applied Sciences

Biomedical Optics: From Methods to Applications Collection Editor: Vladislav Toronov

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

The Development and Application of Fuzzy Logic Collection Editors: Seongsoo Cho, Bhanu Shrestha

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

More Topical Collections

Back to TopTop