Applied Sciences最新文献_第3页

Lightweight Frequency Recalibration Network for Diabetic Retinopathy Multi-Lesion Segmentation 用于糖尿病视网膜病变多病灶分割的轻量级频率重新校准网络

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166941

Yinghua Fu, Mangmang Liu, Ge Zhang, Jiansheng Peng

{"title":"Lightweight Frequency Recalibration Network for Diabetic Retinopathy Multi-Lesion Segmentation","authors":"Yinghua Fu, Mangmang Liu, Ge Zhang, Jiansheng Peng","doi":"10.3390/app14166941","DOIUrl":"https://doi.org/10.3390/app14166941","url":null,"abstract":"Automated segmentation of diabetic retinopathy (DR) lesions is crucial for assessing DR severity and diagnosis. Most previous segmentation methods overlook the detrimental impact of texture information bias, resulting in suboptimal segmentation results. Additionally, the role of lesion shape is not thoroughly considered. In this paper, we propose a lightweight frequency recalibration network (LFRC-Net) for simultaneous multi-lesion DR segmentation, which integrates a frequency recalibration module into the bottleneck layers of the encoder to analyze texture information and shape features together. The module utilizes a Gaussian pyramid to generate features at different scales, constructs a Laplacian pyramid using a difference of Gaussian filter, and then analyzes object features in different frequency domains with the Laplacian pyramid. The high-frequency component handles texture information, while the low-frequency area focuses on learning the shape features of DR lesions. By adaptively recalibrating these frequency representations, our method can differentiate the objects of interest. In the decoder, we introduce a residual attention module (RAM) to enhance lesion feature extraction and efficiently suppress irrelevant information. We evaluate the proposed model’s segmentation performance on two public datasets, IDRiD and DDR, and a private dataset, an ultra-wide-field fundus images dataset. Extensive comparative experiments and ablation studies are conducted across multiple datasets. With minimal model parameters, our approach achieves an mAP_PR of 60.51%, 34.83%, and 14.35% for the segmentation of EX, HE, and MA on the DDR dataset and also obtains excellent results for EX and SE on the IDRiD dataset, which validates the effectiveness of our network.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"1 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141925692","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Estimation of Effective Length of Type-A Grounding System According to IEC 62305-3 Using a Machine Learning Regression Model 使用机器学习回归模型根据 IEC 62305-3 估算 A 类接地系统的有效长度

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166945

Dino Lovrić, Ivan Krolo, I. Jurić-Grgić

{"title":"Estimation of Effective Length of Type-A Grounding System According to IEC 62305-3 Using a Machine Learning Regression Model","authors":"Dino Lovrić, Ivan Krolo, I. Jurić-Grgić","doi":"10.3390/app14166945","DOIUrl":"https://doi.org/10.3390/app14166945","url":null,"abstract":"Two types of grounding systems are recommended for use in the international standard IEC 62305-3, Part 3: Physical damage to structures and life hazard. One of these is a radial-based grounding system (type-A), which is used in soil resistivities of up to 3000 Ωm and is considered in this paper. It is a well-known fact that during lightning strikes, only a part of the grounding wire contributes to dissipating the lightning current into the surrounding soil. This effective part of the grounding system depends on several features, such as soil resistivity, burial depth, and rise time of the dissipated lightning current. The effect of all of these features on the effective length of the type-A grounding system is explored in this paper. A suitable supervised machine learning regression model is developed, which will enable readers to accurately approximate the effective length of the type-A grounding system for realistic values of input features. The trained model in the paper yielded an R2 value of 0.99998 on the test set. In addition, two simple mathematical formulas are also provided, which produce similar but less accurate results (R2 values of 0.989883 and 0.998557, respectively).","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"17 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928323","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Applicability of Magnetic Susceptibility Measurements on Cave Sediments in Karst Areas: Insight from Dinaric Karst (Velebit Mt., Croatia) 岩溶地区洞穴沉积物磁感应强度测量的适用性：迪纳拉岩溶（克罗地亚韦莱比特山）的启示

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166973

Uroš Barudžija, Ana Kamenski, Dalibor Paar, T. Malvić

{"title":"Applicability of Magnetic Susceptibility Measurements on Cave Sediments in Karst Areas: Insight from Dinaric Karst (Velebit Mt., Croatia)","authors":"Uroš Barudžija, Ana Kamenski, Dalibor Paar, T. Malvić","doi":"10.3390/app14166973","DOIUrl":"https://doi.org/10.3390/app14166973","url":null,"abstract":"Magnetism in Croatian caves has been significantly underexplored, despite the well-documented preservation of cave sediments. This study investigates whether magnetic susceptibility can be effectively recorded in Croatian caves and, if so, whether there are differences between in situ and laboratory measurements, as well as the extent of these differences. The focus is on two prominent sites within the Velebit Mountain range of the Dinaric Karst: the deep Slovačka Cave and the extensive Crnopac Cave System (ex. Kita Gaćešina Cave). Magnetic susceptibility was measured in soft sediments using the Kappameter KM-7 for in situ assessments and the Bartington MS2B System for laboratory analyses. The comparison of the two devices aimed to evaluate the feasibility of detecting magnetic susceptibility variations within carbonate sediments. Sampling locations were selected based on preliminary assessments of magnetic susceptibility variations and accessibility for sampling. Characteristic samples from each profile underwent X-ray powder diffraction analysis. Results revealed significant variations in magnetic susceptibility across each profile under both in situ and laboratory conditions. In situ measurements ranged from −45 × 10−5 SI to 120 × 10−5 SI, while laboratory measurements ranged from 4.00 × 10−5 SI to 99.40 × 10−5 SI. The portable Kappameter KM-7 provided satisfactory results for preliminary investigations, while the Bartington MS2B System demonstrated high precision in analyzing these variations in detail. These findings support the potential for further investigations into magnetic susceptibility in karst cave environments, with an emphasis on understanding depositional history and the timeline of climate and tectonic changes.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"36 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141928773","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Correction: Gao et al. A Thermal Error Prediction Method of High-Speed Motorized Spindle Based on Pelican Optimization Algorithm and CNN-LSTM. Appl. Sci. 2024, 14, 381 改正：基于鹈鹕优化算法和 CNN-LSTM 的高速电主轴热误差预测方法.应用科学，2024，14，381

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166942

Ying Gao, Xiaojun Xia, Yinrui Guo

引用次数: 0

From Customer’s Voice to Decision-Maker Insights: Textual Analysis Framework for Arabic Reviews of Saudi Arabia’s Super App 从客户声音到决策者洞察：沙特阿拉伯超级应用程序阿拉伯语评论的文本分析框架

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166952

Bodoor Alrayani, Manal Kalkatawi, M. Abulkhair, Felwa A. Abukhodair

{"title":"From Customer’s Voice to Decision-Maker Insights: Textual Analysis Framework for Arabic Reviews of Saudi Arabia’s Super App","authors":"Bodoor Alrayani, Manal Kalkatawi, M. Abulkhair, Felwa A. Abukhodair","doi":"10.3390/app14166952","DOIUrl":"https://doi.org/10.3390/app14166952","url":null,"abstract":"Recently, business sectors have focused on offering a wide variety of services through utilizing different modern technologies such as super apps in order to fulfill customers’ needs and create a satisfactory user experience. Accordingly, studying the user experience has become one of the most popular trends in the research field due to its essential role in business prosperity and continuity. Thus, many researchers have dedicated their efforts to exploring and analyzing the user experience across social media, blogs, and websites, employing a variety of research methods such as machine learning to mine users’ reviews. However, there are limited studies concentrated on analyzing super app users’ experiences and specifically mining Arabic users’ reviews. Therefore, this paper aims to analyze and discover the most important topics that affect the user experience in the super app environment by mining Arabic business sector users’ reviews in Saudi Arabia using biterm topic modeling, CAMeL sentiment analyzer, and doc2vec with k-means clustering. We explore users’ feelings regarding the extracted topics in order to identify the weak aspects to improve and the strong aspects to enhance, which will promote a satisfactory user experience. Hence, this paper proposes an Arabic text annotation framework to help the business sector in Saudi Arabia to determine the important topics with negative and positive impacts on users’ experience. The proposed framework uses two approaches: topic modeling with sentiment analysis and topic modeling with clustering. As a result, the proposed framework reveals four important topics: delivery and payment, customer service and updates, prices, and application. The retrieved topics are thoroughly studied, and the findings show that, in most topics, negative comments outweigh positive comments. These results are provided with general analysis and recommendations to help the business sector to improve its level of services.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"1 4","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141926072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Evaluation of Selected Artificial Aging Protocols for Dental Composites Including Fatigue and Fracture Tests 评估牙科复合材料的特定人工老化协议，包括疲劳和断裂测试

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166964

A. Szczesio-Włodarczyk, M. Fronczek, K. Ranoszek-Soliwoda, Jerzy Sokołowski, K. Bociong

{"title":"Evaluation of Selected Artificial Aging Protocols for Dental Composites Including Fatigue and Fracture Tests","authors":"A. Szczesio-Włodarczyk, M. Fronczek, K. Ranoszek-Soliwoda, Jerzy Sokołowski, K. Bociong","doi":"10.3390/app14166964","DOIUrl":"https://doi.org/10.3390/app14166964","url":null,"abstract":"The durability and performance of dental composites are essential for ensuring long-lasting dental restorations. However, there is a lack of a standardized procedure for evaluating the lifespan of dental materials. Our proposal assumed that dental materials should be tested under aggressive aging conditions to accelerate materials’ degradation in vitro and such an approach should simulate prolonged material usage in the oral cavity. A comprehensive examination of the impacts of three aging methodologies on various mechanical properties, including the flexural strength (FS), diametral tensile strength (DTS), hardness (HV), fracture toughness (FT), flexural fatigue limit (FFL), and microstructure of selected dental materials (Resin F, Flow-Art and Arkon), was conducted. The findings revealed that preformed aging results in an average reduction of 30% in the mechanical strength properties of the dental composites when compared to the control. Notably, a strong correlation was identified between FS and FFL post-aging whereas no such relationship was observed between these parameters and FT. This paper highlights the significance of aging tests for new dental composites and recommends a focus on flexural strength and fracture toughness to optimize costs and time efficiency. Furthermore, the establishment of a standardized test for fracture toughness in dental composites is recommended. It is proposed that a minimum flexural strength of more than 32–48 MPa after aging should be maintained. A more extensive analysis of commercially available materials is suggested to refine the proper evaluation methods for composite materials.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"30 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141926963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Multi-Format, Multi-Wavelength Erbium-Doped Fiber Ring Laser Using a Tunable Delay Line Interferometer 使用可调谐延迟线干涉仪的多格式、多波长掺铒光纤环形激光器

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166933

C. Yao, A. Dehnaw, Peng Peng

引用次数: 0

Measurement of Water Drop Sizes Generated by a Dripping Rainfall Simulator with Drippers in the Form of Hypodermic Needles 测量带有皮下注射针形式滴水器的滴水降雨模拟器产生的水滴大小

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166969

Vukašin Rončević, Nikola Živanović, John H. van Boxel, T. Iserloh, Nevena Antić, C. Ferreira, Marko Spasić

{"title":"Measurement of Water Drop Sizes Generated by a Dripping Rainfall Simulator with Drippers in the Form of Hypodermic Needles","authors":"Vukašin Rončević, Nikola Živanović, John H. van Boxel, T. Iserloh, Nevena Antić, C. Ferreira, Marko Spasić","doi":"10.3390/app14166969","DOIUrl":"https://doi.org/10.3390/app14166969","url":null,"abstract":"Dripping rainfall simulators (DRS) for soil research generate water drops with different types of drippers, but metal tubes are most commonly used, often in the form of hypodermic needles. However, scientific papers using dripping rainfall simulators are often incomplete in terms of data on hypodermic needle characteristics, as well as data on drops produced by hypodermic needles under different water pressures. This study determines which drop sizes and dripping speeds are generated by various hypodermic needles at different water pressures. For the purpose of this study, a dripping rainfall simulator was designed and constructed for laboratory use. Water drops were generated with 11 different needles, ranging in size from 16 G to 32 G (tube gauge number), at different water pressures. Measured water drop sizes ranged from 1.42 to 3.69 mm at a dripping speed between 10 and 360 drops per minute and water head from 14 to over 1970 mm. Measured drop sizes, supplemented with data from previous studies, provided information on the relation between drop sizes and the size of the hypodermic needles. Van Boxel’s numerical model provided estimations of the fall velocity for different drop diameters and their kinetic energy for falling heights up to 11.5 m. The results of this research can be used to design dripping rainfall simulators for soil research.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"21 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141927263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

FN-GNN: A Novel Graph Embedding Approach for Enhancing Graph Neural Networks in Network Intrusion Detection Systems FN-GNN：在网络入侵检测系统中增强图神经网络的新型图嵌入方法

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166932

Dinh-Hau Tran, Minho Park

{"title":"FN-GNN: A Novel Graph Embedding Approach for Enhancing Graph Neural Networks in Network Intrusion Detection Systems","authors":"Dinh-Hau Tran, Minho Park","doi":"10.3390/app14166932","DOIUrl":"https://doi.org/10.3390/app14166932","url":null,"abstract":"With the proliferation of the Internet, network complexities for both commercial and state organizations have significantly increased, leading to more sophisticated and harder-to-detect network attacks. This evolution poses substantial challenges for intrusion detection systems, threatening the cybersecurity of organizations and national infrastructure alike. Although numerous deep learning techniques such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and graph neural networks (GNNs) have been applied to detect various network attacks, they face limitations due to the lack of standardized input data, affecting model accuracy and performance. This paper proposes a novel preprocessing method for flow data from network intrusion detection systems (NIDSs), enhancing the efficacy of a graph neural network model in malicious flow detection. Our approach initializes graph nodes with data derived from flow features and constructs graph edges through the analysis of IP relationships within the system. Additionally, we propose a new graph model based on the combination of the graph neural network (GCN) model and SAGEConv, a variant of the GraphSAGE model. The proposed model leverages the strengths while addressing the limitations encountered by the previous models. Evaluations on two IDS datasets, CICIDS-2017 and UNSW-NB15, demonstrate that our model outperforms existing methods, offering a significant advancement in the detection of network threats. This work not only addresses a critical gap in the standardization of input data for deep learning models in cybersecurity but also proposes a scalable solution for improving the intrusion detection accuracy.","PeriodicalId":502388,"journal":{"name":"Applied Sciences","volume":"30 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141925981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

In Situ Monitoring and Analysis of the Development Characteristics of Separation in Internal Overburden 现场监测和分析内部覆盖层分离的发展特征

Applied Sciences Pub Date : 2024-08-08 DOI: 10.3390/app14166935

Jianlin Xie, Xiaozhen Wang, Wei Qiao

引用次数: 0