Md. Moniruzzaman Hemal, Atiqur Rahman, Nurjahan, Farhana Islam, Samsuddin Ahmed, M. S. Kaiser, Muhammad Raisuddin Ahmed
The integration of cutting-edge technologies such as the Internet of Things (IoT), robotics, and machine learning (ML) has the potential to significantly enhance the productivity and profitability of traditional fish farming. Farmers using traditional fish farming methods incur enormous economic costs owing to labor-intensive schedule monitoring and care, illnesses, and sudden fish deaths. Another ongoing issue is automated fish species recommendation based on water quality. On the one hand, the effective monitoring of abrupt changes in water quality may minimize the daily operating costs and boost fish productivity, while an accurate automatic fish recommender may aid the farmer in selecting profitable fish species for farming. In this paper, we present AquaBot, an IoT-based system that can automatically collect, monitor, and evaluate the water quality and recommend appropriate fish to farm depending on the values of various water quality indicators. A mobile robot has been designed to collect parameter values such as the pH, temperature, and turbidity from all around the pond. To facilitate monitoring, we have developed web and mobile interfaces. For the analysis and recommendation of suitable fish based on water quality, we have trained and tested several ML algorithms, such as the proposed custom ensemble model, random forest (RF), support vector machine (SVM), decision tree (DT), K-nearest neighbor (KNN), logistic regression (LR), bagging, boosting, and stacking, on a real-time pond water dataset. The dataset has been preprocessed with feature scaling and dataset balancing. We have evaluated the algorithms based on several performance metrics. In our experiment, our proposed ensemble model has delivered the best result, with 94% accuracy, 94% precision, 94% recall, a 94% F1-score, 93% MCC, and the best AUC score for multi-class classification. Finally, we have deployed the best-performing model in a web interface to provide cultivators with recommendations for suitable fish farming. Our proposed system is projected to not only boost production and save money but also reduce the time and intensity of the producer’s manual labor.
{"title":"An Integrated Smart Pond Water Quality Monitoring and Fish Farming Recommendation Aquabot System","authors":"Md. Moniruzzaman Hemal, Atiqur Rahman, Nurjahan, Farhana Islam, Samsuddin Ahmed, M. S. Kaiser, Muhammad Raisuddin Ahmed","doi":"10.3390/s24113682","DOIUrl":"https://doi.org/10.3390/s24113682","url":null,"abstract":"The integration of cutting-edge technologies such as the Internet of Things (IoT), robotics, and machine learning (ML) has the potential to significantly enhance the productivity and profitability of traditional fish farming. Farmers using traditional fish farming methods incur enormous economic costs owing to labor-intensive schedule monitoring and care, illnesses, and sudden fish deaths. Another ongoing issue is automated fish species recommendation based on water quality. On the one hand, the effective monitoring of abrupt changes in water quality may minimize the daily operating costs and boost fish productivity, while an accurate automatic fish recommender may aid the farmer in selecting profitable fish species for farming. In this paper, we present AquaBot, an IoT-based system that can automatically collect, monitor, and evaluate the water quality and recommend appropriate fish to farm depending on the values of various water quality indicators. A mobile robot has been designed to collect parameter values such as the pH, temperature, and turbidity from all around the pond. To facilitate monitoring, we have developed web and mobile interfaces. For the analysis and recommendation of suitable fish based on water quality, we have trained and tested several ML algorithms, such as the proposed custom ensemble model, random forest (RF), support vector machine (SVM), decision tree (DT), K-nearest neighbor (KNN), logistic regression (LR), bagging, boosting, and stacking, on a real-time pond water dataset. The dataset has been preprocessed with feature scaling and dataset balancing. We have evaluated the algorithms based on several performance metrics. In our experiment, our proposed ensemble model has delivered the best result, with 94% accuracy, 94% precision, 94% recall, a 94% F1-score, 93% MCC, and the best AUC score for multi-class classification. Finally, we have deployed the best-performing model in a web interface to provide cultivators with recommendations for suitable fish farming. Our proposed system is projected to not only boost production and save money but also reduce the time and intensity of the producer’s manual labor.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141415296","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}
Ultrasound imaging is an essential tool in anesthesiology, particularly for ultrasound-guided peripheral nerve blocks (US-PNBs). However, challenges such as speckle noise, acoustic shadows, and variability in nerve appearance complicate the accurate localization of nerve tissues. To address this issue, this study introduces a deep convolutional neural network (DCNN), specifically Scaled-YOLOv4, and investigates an appropriate network model and input image scaling for nerve detection on ultrasound images. Utilizing two datasets, a public dataset and an original dataset, we evaluated the effects of model scale and input image size on detection performance. Our findings reveal that smaller input images and larger model scales significantly improve detection accuracy. The optimal configuration of model size and input image size not only achieved high detection accuracy but also demonstrated real-time processing capabilities.
{"title":"Investigation of Appropriate Scaling of Networks and Images for Convolutional Neural Network-Based Nerve Detection in Ultrasound-Guided Nerve Blocks","authors":"T. Sugino, Shinya Onogi, Rieko Oishi, Chie Hanayama, Satoki Inoue, Shinjiro Ishida, Yuhang Yao, Nobuhiro Ogasawara, Masahiro Murakawa, Yoshikazu Nakajima","doi":"10.3390/s24113696","DOIUrl":"https://doi.org/10.3390/s24113696","url":null,"abstract":"Ultrasound imaging is an essential tool in anesthesiology, particularly for ultrasound-guided peripheral nerve blocks (US-PNBs). However, challenges such as speckle noise, acoustic shadows, and variability in nerve appearance complicate the accurate localization of nerve tissues. To address this issue, this study introduces a deep convolutional neural network (DCNN), specifically Scaled-YOLOv4, and investigates an appropriate network model and input image scaling for nerve detection on ultrasound images. Utilizing two datasets, a public dataset and an original dataset, we evaluated the effects of model scale and input image size on detection performance. Our findings reveal that smaller input images and larger model scales significantly improve detection accuracy. The optimal configuration of model size and input image size not only achieved high detection accuracy but also demonstrated real-time processing capabilities.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"11 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141392340","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}
Andrea Valerio, D. Demarchi, Brendan O’Flynn, Paolo Motto Ros, Salvatore Tedesco
Comprehending the regulatory mechanisms influencing blood pressure control is pivotal for continuous monitoring of this parameter. Implementing a personalized machine learning model, utilizing data-driven features, presents an opportunity to facilitate tracking blood pressure fluctuations in various conditions. In this work, data-driven photoplethysmograph features extracted from the brachial and digital arteries of 28 healthy subjects were used to feed a random forest classifier in an attempt to develop a system capable of tracking blood pressure. We evaluated the behavior of this latter classifier according to the different sizes of the training set and degrees of personalization used. Aggregated accuracy, precision, recall, and F1-score were equal to 95.1%, 95.2%, 95%, and 95.4% when 30% of a target subject’s pulse waveforms were combined with five randomly selected source subjects available in the dataset. Experimental findings illustrated that incorporating a pre-training stage with data from different subjects made it viable to discern morphological distinctions in beat-to-beat pulse waveforms under conditions of cognitive or physical workload.
了解影响血压控制的调节机制对于持续监测这一参数至关重要。利用数据驱动的特征实施个性化机器学习模型，为方便跟踪各种情况下的血压波动提供了机会。在这项工作中，我们利用从 28 名健康受试者的肱动脉和数字动脉中提取的数据驱动型血压计特征，为随机森林分类器提供数据，试图开发出一种能够跟踪血压的系统。我们根据训练集的不同规模和使用的个性化程度对后一种分类器的行为进行了评估。当 30% 的目标受试者脉搏波形与数据集中随机选择的五个源受试者相结合时，综合准确率、精确率、召回率和 F1 分数分别为 95.1%、95.2%、95% 和 95.4%。实验结果表明，在预训练阶段加入来自不同受试者的数据，可以在认知或体力工作负荷条件下辨别逐次跳动脉搏波形的形态差异。
{"title":"Development of a Personalized Multiclass Classification Model to Detect Blood Pressure Variations Associated with Physical or Cognitive Workload","authors":"Andrea Valerio, D. Demarchi, Brendan O’Flynn, Paolo Motto Ros, Salvatore Tedesco","doi":"10.3390/s24113697","DOIUrl":"https://doi.org/10.3390/s24113697","url":null,"abstract":"Comprehending the regulatory mechanisms influencing blood pressure control is pivotal for continuous monitoring of this parameter. Implementing a personalized machine learning model, utilizing data-driven features, presents an opportunity to facilitate tracking blood pressure fluctuations in various conditions. In this work, data-driven photoplethysmograph features extracted from the brachial and digital arteries of 28 healthy subjects were used to feed a random forest classifier in an attempt to develop a system capable of tracking blood pressure. We evaluated the behavior of this latter classifier according to the different sizes of the training set and degrees of personalization used. Aggregated accuracy, precision, recall, and F1-score were equal to 95.1%, 95.2%, 95%, and 95.4% when 30% of a target subject’s pulse waveforms were combined with five randomly selected source subjects available in the dataset. Experimental findings illustrated that incorporating a pre-training stage with data from different subjects made it viable to discern morphological distinctions in beat-to-beat pulse waveforms under conditions of cognitive or physical workload.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"59 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141408595","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}
Rushil Mojidra, Jian Li, Ali Mohammadkhorasani, Fernando Moreu, C. Bennett, William N. Collins
A significant percentage of bridges in the United States are serving beyond their 50-year design life, and many of them are in poor condition, making them vulnerable to fatigue cracks that can result in catastrophic failure. However, current fatigue crack inspection practice based on human vision is time-consuming, labor intensive, and prone to error. We present a novel human-centered bridge inspection methodology to enhance the efficiency and accuracy of fatigue crack detection by employing advanced technologies including computer vision and augmented reality (AR). In particular, a computer vision-based algorithm is developed to enable near-real-time fatigue crack detection by analyzing structural surface motion in a short video recorded by a moving camera of the AR headset. The approach monitors structural surfaces by tracking feature points and measuring variations in distances between feature point pairs to recognize the motion pattern associated with the crack opening and closing. Measuring distance changes between feature points, as opposed to their displacement changes before this improvement, eliminates the need of camera motion compensation and enables reliable and computationally efficient fatigue crack detection using the nonstationary AR headset. In addition, an AR environment is created and integrated with the computer vision algorithm. The crack detection results are transmitted to the AR headset worn by the bridge inspector, where they are converted into holograms and anchored on the bridge surface in the 3D real-world environment. The AR environment also provides virtual menus to support human-in-the-loop decision-making to determine optimal crack detection parameters. This human-centered approach with improved visualization and human–machine collaboration aids the inspector in making well-informed decisions in the field in a near-real-time fashion. The proposed crack detection method is comprehensively assessed using two laboratory test setups for both in-plane and out-of-plane fatigue cracks. Finally, using the integrated AR environment, a human-centered bridge inspection is conducted to demonstrate the efficacy and potential of the proposed methodology.
美国有相当一部分桥梁的使用寿命已超过 50 年的设计寿命，其中许多桥梁的状况很差，很容易出现疲劳裂缝，从而导致灾难性的故障。然而，目前基于人工视觉的疲劳裂缝检测方法费时费力，而且容易出错。我们提出了一种新颖的以人为本的桥梁检测方法，通过采用计算机视觉和增强现实（AR）等先进技术来提高疲劳裂缝检测的效率和准确性。特别是，我们开发了一种基于计算机视觉的算法，通过分析 AR 头显移动摄像头记录的短视频中的结构表面运动，实现近乎实时的疲劳裂缝检测。该方法通过跟踪特征点和测量特征点对之间的距离变化来监测结构表面，从而识别与裂缝开合相关的运动模式。与改进前的位移变化相比，测量特征点之间的距离变化无需对摄像头进行运动补偿，因此可以利用非稳态 AR 头显进行可靠且计算效率高的疲劳裂纹检测。此外，还创建了一个 AR 环境，并与计算机视觉算法集成。裂缝检测结果被传输到桥梁检测人员佩戴的 AR 头显，在那里被转换成全息图，并固定在三维真实世界环境中的桥梁表面上。AR 环境还提供虚拟菜单，支持人在回路中决策，以确定最佳裂缝检测参数。这种以人为本的方法改进了可视化和人机协作，有助于检测人员在现场以接近实时的方式做出明智的决策。针对平面内和平面外疲劳裂纹，使用两个实验室测试装置对所提出的裂纹检测方法进行了全面评估。最后，利用集成的 AR 环境，进行了一次以人为中心的桥梁检测，以证明所提方法的功效和潜力。
{"title":"Computer Vision and Augmented Reality for Human-Centered Fatigue Crack Inspection","authors":"Rushil Mojidra, Jian Li, Ali Mohammadkhorasani, Fernando Moreu, C. Bennett, William N. Collins","doi":"10.3390/s24113685","DOIUrl":"https://doi.org/10.3390/s24113685","url":null,"abstract":"A significant percentage of bridges in the United States are serving beyond their 50-year design life, and many of them are in poor condition, making them vulnerable to fatigue cracks that can result in catastrophic failure. However, current fatigue crack inspection practice based on human vision is time-consuming, labor intensive, and prone to error. We present a novel human-centered bridge inspection methodology to enhance the efficiency and accuracy of fatigue crack detection by employing advanced technologies including computer vision and augmented reality (AR). In particular, a computer vision-based algorithm is developed to enable near-real-time fatigue crack detection by analyzing structural surface motion in a short video recorded by a moving camera of the AR headset. The approach monitors structural surfaces by tracking feature points and measuring variations in distances between feature point pairs to recognize the motion pattern associated with the crack opening and closing. Measuring distance changes between feature points, as opposed to their displacement changes before this improvement, eliminates the need of camera motion compensation and enables reliable and computationally efficient fatigue crack detection using the nonstationary AR headset. In addition, an AR environment is created and integrated with the computer vision algorithm. The crack detection results are transmitted to the AR headset worn by the bridge inspector, where they are converted into holograms and anchored on the bridge surface in the 3D real-world environment. The AR environment also provides virtual menus to support human-in-the-loop decision-making to determine optimal crack detection parameters. This human-centered approach with improved visualization and human–machine collaboration aids the inspector in making well-informed decisions in the field in a near-real-time fashion. The proposed crack detection method is comprehensively assessed using two laboratory test setups for both in-plane and out-of-plane fatigue cracks. Finally, using the integrated AR environment, a human-centered bridge inspection is conducted to demonstrate the efficacy and potential of the proposed methodology.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141399542","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}
E. Melnik, Steffen Kurzhals, G. Mutinati, Valerio Beni, Rainer Hainberger
Hydrogels are of great importance for functionalizing sensors and microfluidics, and poly(ethylene glycol) dimethacrylate (PEG-DMA) is often used as a viscosifier for printable hydrogel precursor inks. In this study, 1–10 kDa PEG-DMA based hydrogels were characterized by gravimetric and electrochemical methods to investigate the diffusivity of small molecules and proteins. Swelling ratios (SRs) of 14.43–9.24, as well as mesh sizes ξ of 3.58–6.91 nm were calculated, and it was found that the SR correlates with the molar concentration of PEG-DMA in the ink (MCI) (SR = 0.1127 × MCI + 8.3256, R2 = 0.9692) and ξ correlates with the molecular weight (Mw) (ξ = 0.3382 × Mw + 3.638, R2 = 0.9451). To investigate the sensing properties, methylene blue (MB) and MB-conjugated proteins were measured on electrochemical sensors with and without hydrogel coating. It was found that on sensors with 10 kDa PEG-DMA hydrogel modification, the DPV peak currents were reduced to 92 % for MB, 73 % for MB-BSA, and 23 % for MB-IgG. To investigate the diffusion properties of MB(-conjugates) in hydrogels with 1–10 kDa PEG-DMA, diffusivity was calculated from the current equation. It was found that diffusivity increases with increasing ξ. Finally, the release of MB-BSA was detected after drying the MB-BSA-containing hydrogel, which is a promising result for the development of hydrogel-based reagent reservoirs for biosensing.
{"title":"Electrochemical Diffusion Study in Poly(Ethylene Glycol) Dimethacrylate-Based Hydrogels","authors":"E. Melnik, Steffen Kurzhals, G. Mutinati, Valerio Beni, Rainer Hainberger","doi":"10.3390/s24113678","DOIUrl":"https://doi.org/10.3390/s24113678","url":null,"abstract":"Hydrogels are of great importance for functionalizing sensors and microfluidics, and poly(ethylene glycol) dimethacrylate (PEG-DMA) is often used as a viscosifier for printable hydrogel precursor inks. In this study, 1–10 kDa PEG-DMA based hydrogels were characterized by gravimetric and electrochemical methods to investigate the diffusivity of small molecules and proteins. Swelling ratios (SRs) of 14.43–9.24, as well as mesh sizes ξ of 3.58–6.91 nm were calculated, and it was found that the SR correlates with the molar concentration of PEG-DMA in the ink (MCI) (SR = 0.1127 × MCI + 8.3256, R2 = 0.9692) and ξ correlates with the molecular weight (Mw) (ξ = 0.3382 × Mw + 3.638, R2 = 0.9451). To investigate the sensing properties, methylene blue (MB) and MB-conjugated proteins were measured on electrochemical sensors with and without hydrogel coating. It was found that on sensors with 10 kDa PEG-DMA hydrogel modification, the DPV peak currents were reduced to 92 % for MB, 73 % for MB-BSA, and 23 % for MB-IgG. To investigate the diffusion properties of MB(-conjugates) in hydrogels with 1–10 kDa PEG-DMA, diffusivity was calculated from the current equation. It was found that diffusivity increases with increasing ξ. Finally, the release of MB-BSA was detected after drying the MB-BSA-containing hydrogel, which is a promising result for the development of hydrogel-based reagent reservoirs for biosensing.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"1995 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141400869","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}
Despite advancements in creating barrier-free environments, many buildings still have stairs, making accessibility a significant concern for wheelchair users, the majority of whom check for accessibility information before venturing out. This paper focuses on developing a transformable quadruped wheelchair to address the mobility challenges posed by stairs and steps for wheelchair users. The wheelchair, inspired by the Unitree B2 quadruped robot, combines wheels for flat surfaces and robotic legs for navigating stairs and is equipped with advanced sensors and force detectors to interact with its surroundings effectively. This research utilized reinforcement learning, specifically curriculum learning, to teach the wheelchair stair-climbing skills, with progressively increasing complexity in a simulated environment crafted in the Unity game engine. The experiments demonstrated high success rates in both stair ascent and descent, showcasing the wheelchair’s potential in overcoming mobility barriers. However, the current model faces limitations in tackling various stair types, like spiral staircases, and requires further enhancements in safety and stability, particularly in the descending phase. The project illustrates a significant step towards enhancing mobility for wheelchair users, aiming to broaden their access to diverse environments. Continued improvements and testing are essential to ensure the wheelchair’s adaptability and safety across different terrains and situations, underlining the ongoing commitment to technological innovation in aiding individuals with mobility impairments.
{"title":"Transformable Quadruped Wheelchairs Capable of Autonomous Stair Ascent and Descent","authors":"Atsuki Akamisaka, Katashi Nagao","doi":"10.3390/s24113675","DOIUrl":"https://doi.org/10.3390/s24113675","url":null,"abstract":"Despite advancements in creating barrier-free environments, many buildings still have stairs, making accessibility a significant concern for wheelchair users, the majority of whom check for accessibility information before venturing out. This paper focuses on developing a transformable quadruped wheelchair to address the mobility challenges posed by stairs and steps for wheelchair users. The wheelchair, inspired by the Unitree B2 quadruped robot, combines wheels for flat surfaces and robotic legs for navigating stairs and is equipped with advanced sensors and force detectors to interact with its surroundings effectively. This research utilized reinforcement learning, specifically curriculum learning, to teach the wheelchair stair-climbing skills, with progressively increasing complexity in a simulated environment crafted in the Unity game engine. The experiments demonstrated high success rates in both stair ascent and descent, showcasing the wheelchair’s potential in overcoming mobility barriers. However, the current model faces limitations in tackling various stair types, like spiral staircases, and requires further enhancements in safety and stability, particularly in the descending phase. The project illustrates a significant step towards enhancing mobility for wheelchair users, aiming to broaden their access to diverse environments. Continued improvements and testing are essential to ensure the wheelchair’s adaptability and safety across different terrains and situations, underlining the ongoing commitment to technological innovation in aiding individuals with mobility impairments.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"10 6","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141396992","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}
Recent advancements in applications of deep neural network for bearing fault diagnosis under variable operating conditions have shown promising outcomes. However, these approaches are limited in practical applications due to the complexity of neural networks, which require substantial computational resources, thereby hindering the advancement of automated diagnostic tools. To overcome these limitations, this study introduces a new fault diagnosis framework that incorporates a tri-channel preprocessing module for multidimensional feature extraction, coupled with an innovative diagnostic architecture known as the Lightweight Ghost Enhanced Feature Attention Network (GEFA-Net). This system is adept at identifying rolling bearing faults across diverse operational conditions. The FFE module utilizes advanced techniques such as Fast Fourier Transform (FFT), Frequency Weighted Energy Operator (FWEO), and Signal Envelope Analysis to refine signal processing in complex environments. Concurrently, GEFA-Net employs the Ghost Module and the Efficient Pyramid Squared Attention (EPSA) mechanism, which enhances feature representation and generates additional feature maps through linear operations, thereby reducing computational demands. This methodology not only significantly lowers the parameter count of the model, promoting a more streamlined architectural framework, but also improves diagnostic speed. Additionally, the model exhibits enhanced diagnostic accuracy in challenging conditions through the effective synthesis of local and global data contexts. Experimental validation using datasets from the University of Ottawa and our dataset confirms that the framework not only achieves superior diagnostic accuracy but also reduces computational complexity and accelerates detection processes. These findings highlight the robustness of the framework for bearing fault diagnosis under varying operational conditions, showcasing its broad applicational potential in industrial settings. The parameter count was decreased by 63.74% compared to MobileVit, and the recorded diagnostic accuracies were 98.53% and 99.98% for the respective datasets.
{"title":"Lightweight Ghost Enhanced Feature Attention Network: An Efficient Intelligent Fault Diagnosis Method under Various Working Conditions","authors":"Huaihao Dong, Kai Zheng, Siguo Wen, Zheng Zhang, Yuyan Li, Bobin Zhu","doi":"10.3390/s24113691","DOIUrl":"https://doi.org/10.3390/s24113691","url":null,"abstract":"Recent advancements in applications of deep neural network for bearing fault diagnosis under variable operating conditions have shown promising outcomes. However, these approaches are limited in practical applications due to the complexity of neural networks, which require substantial computational resources, thereby hindering the advancement of automated diagnostic tools. To overcome these limitations, this study introduces a new fault diagnosis framework that incorporates a tri-channel preprocessing module for multidimensional feature extraction, coupled with an innovative diagnostic architecture known as the Lightweight Ghost Enhanced Feature Attention Network (GEFA-Net). This system is adept at identifying rolling bearing faults across diverse operational conditions. The FFE module utilizes advanced techniques such as Fast Fourier Transform (FFT), Frequency Weighted Energy Operator (FWEO), and Signal Envelope Analysis to refine signal processing in complex environments. Concurrently, GEFA-Net employs the Ghost Module and the Efficient Pyramid Squared Attention (EPSA) mechanism, which enhances feature representation and generates additional feature maps through linear operations, thereby reducing computational demands. This methodology not only significantly lowers the parameter count of the model, promoting a more streamlined architectural framework, but also improves diagnostic speed. Additionally, the model exhibits enhanced diagnostic accuracy in challenging conditions through the effective synthesis of local and global data contexts. Experimental validation using datasets from the University of Ottawa and our dataset confirms that the framework not only achieves superior diagnostic accuracy but also reduces computational complexity and accelerates detection processes. These findings highlight the robustness of the framework for bearing fault diagnosis under varying operational conditions, showcasing its broad applicational potential in industrial settings. The parameter count was decreased by 63.74% compared to MobileVit, and the recorded diagnostic accuracies were 98.53% and 99.98% for the respective datasets.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"71 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141408518","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}
F. Egaña, U. Mutilba, J. Yagüe-Fabra, E. Gomez-Acedo
Large machine tools are critically affected by ambient temperature fluctuations, impacting their performance and the quality of machined products. Addressing the challenge of accurately measuring thermal effects on machine structures, this study introduces the Machine Tool Integrated Inverse Multilateration method. This method offers a precise approach for assessing geometric error parameters throughout a machine’s working volume, featuring a low level of uncertainty and high speed suitable for effective temperature change monitoring. A significant innovation is found in the capability to automatically realise the volumetric error characterisation of medium- to large-sized machine tools at intervals of 40–60 min with a measurement uncertainty of 10 µm. This enables the detailed study of thermal errors which are generated due to variations in ambient temperature over extended periods. To validate the method, an extensive experimental campaign was conducted on a ZAYER Arion G™ large machine tool using a LEICA AT960™ laser tracker with four wide-angle retro-reflectors under natural workshop conditions. This research identified two key thermal scenarios, quasi-stationary and changing environments, providing valuable insights into how temperature variations influence machine behaviour. This novel method facilitates the optimization of machine tool operations and the improvement of product quality in industrial environments, marking a significant advancement in manufacturing metrology.
{"title":"A Novel Methodology for Measuring Ambient Thermal Effects on Machine Tools","authors":"F. Egaña, U. Mutilba, J. Yagüe-Fabra, E. Gomez-Acedo","doi":"10.3390/s24072380","DOIUrl":"https://doi.org/10.3390/s24072380","url":null,"abstract":"Large machine tools are critically affected by ambient temperature fluctuations, impacting their performance and the quality of machined products. Addressing the challenge of accurately measuring thermal effects on machine structures, this study introduces the Machine Tool Integrated Inverse Multilateration method. This method offers a precise approach for assessing geometric error parameters throughout a machine’s working volume, featuring a low level of uncertainty and high speed suitable for effective temperature change monitoring. A significant innovation is found in the capability to automatically realise the volumetric error characterisation of medium- to large-sized machine tools at intervals of 40–60 min with a measurement uncertainty of 10 µm. This enables the detailed study of thermal errors which are generated due to variations in ambient temperature over extended periods. To validate the method, an extensive experimental campaign was conducted on a ZAYER Arion G™ large machine tool using a LEICA AT960™ laser tracker with four wide-angle retro-reflectors under natural workshop conditions. This research identified two key thermal scenarios, quasi-stationary and changing environments, providing valuable insights into how temperature variations influence machine behaviour. This novel method facilitates the optimization of machine tool operations and the improvement of product quality in industrial environments, marking a significant advancement in manufacturing metrology.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"133 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140760209","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}
Hossein Gohari, Mahmoud Hassan, Bin Shi, Ahmad Sadek, Helmi Attia, Rachid M’Saoubi
The fifth Industrial revolution (I5.0) prioritizes resilience and sustainability, integrating cognitive cyber-physical systems and advanced technologies to enhance machining processes. Numerous research studies have been conducted to optimize machining operations by identifying and reducing sources of uncertainty and estimating the optimal cutting parameters. Virtual modeling and Tool Condition Monitoring (TCM) methodologies have been developed to assess the cutting states during machining processes. With a precise estimation of cutting states, the safety margin necessary to deal with uncertainties can be reduced, resulting in improved process productivity. This paper reviews the recent advances in high-performance machining systems, with a focus on cyber-physical models developed for the cutting operation of difficult-to-cut materials using cemented carbide tools. An overview of the literature and background on the advances in offline and online process optimization approaches are presented. Process optimization objectives such as tool life utilization, dynamic stability, enhanced productivity, improved machined part quality, reduced energy consumption, and carbon emissions are independently investigated for these offline and online optimization methods. Addressing the critical objectives and constraints prevalent in industrial applications, this paper explores the challenges and opportunities inherent to developing a robust cyber–physical optimization system.
{"title":"Cyber–Physical Systems for High-Performance Machining of Difficult to Cut Materials in I5.0 Era—A Review","authors":"Hossein Gohari, Mahmoud Hassan, Bin Shi, Ahmad Sadek, Helmi Attia, Rachid M’Saoubi","doi":"10.3390/s24072324","DOIUrl":"https://doi.org/10.3390/s24072324","url":null,"abstract":"The fifth Industrial revolution (I5.0) prioritizes resilience and sustainability, integrating cognitive cyber-physical systems and advanced technologies to enhance machining processes. Numerous research studies have been conducted to optimize machining operations by identifying and reducing sources of uncertainty and estimating the optimal cutting parameters. Virtual modeling and Tool Condition Monitoring (TCM) methodologies have been developed to assess the cutting states during machining processes. With a precise estimation of cutting states, the safety margin necessary to deal with uncertainties can be reduced, resulting in improved process productivity. This paper reviews the recent advances in high-performance machining systems, with a focus on cyber-physical models developed for the cutting operation of difficult-to-cut materials using cemented carbide tools. An overview of the literature and background on the advances in offline and online process optimization approaches are presented. Process optimization objectives such as tool life utilization, dynamic stability, enhanced productivity, improved machined part quality, reduced energy consumption, and carbon emissions are independently investigated for these offline and online optimization methods. Addressing the critical objectives and constraints prevalent in industrial applications, this paper explores the challenges and opportunities inherent to developing a robust cyber–physical optimization system.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"339 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140763689","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}
A. Picciariello, A. Dezi, L. Vincenti, M. Spampinato, Wenzhe Zang, Pamela Riahi, Jared Scott, Ruchi Sharma, Xudong Fan, D. Altomare
Screening methods available for colorectal cancer (CRC) to date are burdened by poor reliability and low patient adherence and compliance. An altered pattern of volatile organic compounds (VOCs) in exhaled breath has been proposed as a non-invasive potential diagnostic tool for distinguishing CRC patients from healthy controls (HC). The aim of this study was to evaluate the reliability of an innovative portable device containing a micro-gas chromatograph in enabling rapid, on-site CRC diagnosis through analysis of patients’ exhaled breath. In this prospective trial, breath samples were collected in a tertiary referral center of colorectal surgery, and analysis of the chromatograms was performed by the Biomedical Engineering Department. The breath of patients with CRC and HC was collected into Tedlar bags through a Nafion filter and mouthpiece with a one-way valve. The breath samples were analyzed by an automated portable gas chromatography device. Relevant volatile biomarkers and discriminant chromatographic peaks were identified through machine learning, linear discriminant analysis and principal component analysis. A total of 68 subjects, 36 patients affected by histologically proven CRC with no evidence of metastases and 32 HC with negative colonoscopies, were enrolled. After testing a training set (18 CRC and 18 HC) and a testing set (18 CRC and 14 HC), an overall specificity of 87.5%, sensitivity of 94.4% and accuracy of 91.2% in identifying CRC patients was found based on three VOCs. Breath biopsy may represent a promising non-invasive method of discriminating CRC patients from HC.
{"title":"Colorectal Cancer Diagnosis through Breath Test Using a Portable Breath Analyzer—Preliminary Data","authors":"A. Picciariello, A. Dezi, L. Vincenti, M. Spampinato, Wenzhe Zang, Pamela Riahi, Jared Scott, Ruchi Sharma, Xudong Fan, D. Altomare","doi":"10.3390/s24072343","DOIUrl":"https://doi.org/10.3390/s24072343","url":null,"abstract":"Screening methods available for colorectal cancer (CRC) to date are burdened by poor reliability and low patient adherence and compliance. An altered pattern of volatile organic compounds (VOCs) in exhaled breath has been proposed as a non-invasive potential diagnostic tool for distinguishing CRC patients from healthy controls (HC). The aim of this study was to evaluate the reliability of an innovative portable device containing a micro-gas chromatograph in enabling rapid, on-site CRC diagnosis through analysis of patients’ exhaled breath. In this prospective trial, breath samples were collected in a tertiary referral center of colorectal surgery, and analysis of the chromatograms was performed by the Biomedical Engineering Department. The breath of patients with CRC and HC was collected into Tedlar bags through a Nafion filter and mouthpiece with a one-way valve. The breath samples were analyzed by an automated portable gas chromatography device. Relevant volatile biomarkers and discriminant chromatographic peaks were identified through machine learning, linear discriminant analysis and principal component analysis. A total of 68 subjects, 36 patients affected by histologically proven CRC with no evidence of metastases and 32 HC with negative colonoscopies, were enrolled. After testing a training set (18 CRC and 18 HC) and a testing set (18 CRC and 14 HC), an overall specificity of 87.5%, sensitivity of 94.4% and accuracy of 91.2% in identifying CRC patients was found based on three VOCs. Breath biopsy may represent a promising non-invasive method of discriminating CRC patients from HC.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"43 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140756532","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：