Pub Date : 2024-01-23DOI: 10.3390/technologies12020016
Su Myat Thwin, S. Malebary, A. Abulfaraj, Hyun-Seok Park
Globally, breast cancer (BC) is considered a major cause of death among women. Therefore, researchers have used various machine and deep learning-based methods for its early and accurate detection using X-ray, MRI, and mammography image modalities. However, the machine learning model requires domain experts to select an optimal feature, obtains a limited accuracy, and has a high false positive rate due to handcrafting features extraction. The deep learning model overcomes these limitations, but these models require large amounts of training data and computation resources, and further improvement in the model performance is needed. To do this, we employ a novel framework called the Ensemble-based Channel and Spatial Attention Network (ECS-A-Net) to automatically classify infected regions within BC images. The proposed framework consists of two phases: in the first phase, we apply different augmentation techniques to enhance the size of the input data, while the second phase includes an ensemble technique that parallelly leverages modified SE-ResNet50 and InceptionV3 as a backbone for feature extraction, followed by Channel Attention (CA) and Spatial Attention (SA) modules in a series manner for more dominant feature selection. To further validate the ECS-A-Net, we conducted extensive experiments between several competitive state-of-the-art (SOTA) techniques over two benchmarks, including DDSM and MIAS, where the proposed model achieved 96.50% accuracy for the DDSM and 95.33% accuracy for the MIAS datasets. Additionally, the experimental results demonstrated that our network achieved a better performance using various evaluation indicators, including accuracy, sensitivity, and specificity among other methods.
在全球范围内，乳腺癌（BC）被认为是女性死亡的主要原因。因此，研究人员使用各种基于机器学习和深度学习的方法，利用 X 射线、核磁共振成像和乳房 X 射线摄影图像模式对其进行早期准确检测。然而，机器学习模型需要领域专家来选择最佳特征，获得的准确率有限，而且由于手工特征提取，假阳性率较高。深度学习模型克服了这些局限性，但这些模型需要大量的训练数据和计算资源，因此需要进一步提高模型性能。为此，我们采用了一种名为 "基于集合的通道和空间注意网络（ECS-A-Net）"的新型框架，对 BC 图像中的感染区域进行自动分类。拟议的框架包括两个阶段：在第一阶段，我们采用不同的增强技术来增大输入数据的大小，而第二阶段则包括一种集合技术，它并行利用修改后的 SE-ResNet50 和 InceptionV3 作为特征提取的骨干，然后以串联的方式利用通道注意（CA）和空间注意（SA）模块来进行更主要的特征选择。为了进一步验证 ECS-A-Net 的有效性，我们在两个基准（包括 DDSM 和 MIAS）上对几种具有竞争力的最先进（SOTA）技术进行了广泛的实验，结果表明所提出的模型在 DDSM 数据集上的准确率达到 96.50%，在 MIAS 数据集上的准确率达到 95.33%。此外，实验结果表明，我们的网络在准确率、灵敏度和特异性等各种评估指标上都取得了更好的性能。
{"title":"Attention-Based Ensemble Network for Effective Breast Cancer Classification over Benchmarks","authors":"Su Myat Thwin, S. Malebary, A. Abulfaraj, Hyun-Seok Park","doi":"10.3390/technologies12020016","DOIUrl":"https://doi.org/10.3390/technologies12020016","url":null,"abstract":"Globally, breast cancer (BC) is considered a major cause of death among women. Therefore, researchers have used various machine and deep learning-based methods for its early and accurate detection using X-ray, MRI, and mammography image modalities. However, the machine learning model requires domain experts to select an optimal feature, obtains a limited accuracy, and has a high false positive rate due to handcrafting features extraction. The deep learning model overcomes these limitations, but these models require large amounts of training data and computation resources, and further improvement in the model performance is needed. To do this, we employ a novel framework called the Ensemble-based Channel and Spatial Attention Network (ECS-A-Net) to automatically classify infected regions within BC images. The proposed framework consists of two phases: in the first phase, we apply different augmentation techniques to enhance the size of the input data, while the second phase includes an ensemble technique that parallelly leverages modified SE-ResNet50 and InceptionV3 as a backbone for feature extraction, followed by Channel Attention (CA) and Spatial Attention (SA) modules in a series manner for more dominant feature selection. To further validate the ECS-A-Net, we conducted extensive experiments between several competitive state-of-the-art (SOTA) techniques over two benchmarks, including DDSM and MIAS, where the proposed model achieved 96.50% accuracy for the DDSM and 95.33% accuracy for the MIAS datasets. Additionally, the experimental results demonstrated that our network achieved a better performance using various evaluation indicators, including accuracy, sensitivity, and specificity among other methods.","PeriodicalId":504839,"journal":{"name":"Technologies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139604442","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}
Pub Date : 2024-01-23DOI: 10.3390/technologies12020014
Shwetabh Gupta, Gururaj Parande, M. Gupta
Magnesium and its composites have been used in various applications owing to their high specific strength properties and low density. However, the application is limited to room-temperature conditions owing to the lack of research available on the ability of magnesium alloys to perform in sub-zero conditions. The present study attempted, for the first time, the effects of two cryogenic temperatures (−20 °C/253 K and −196 °C/77 K) on the physical, thermal, and mechanical properties of a Mg/2wt.%CeO2 nanocomposite. The materials were synthesized using the disintegrated melt deposition method followed by hot extrusion. The results revealed that the shallow cryogenically treated (refrigerated at −20 °C) samples display a reduction in porosity, lower ignition resistance, similar microhardness, compressive yield, and ultimate strength and failure strain when compared to deep cryogenically treated samples in liquid nitrogen at −196 °C. Although deep cryogenically treated samples showed an overall edge, the extent of the increase in properties may not be justified, as samples exposed at −20 °C display very similar mechanical properties, thus reducing the overall cost of the cryogenic process. The results were compared with the data available in the open literature, and the mechanisms behind the improvement of the properties were evaluated.
由于镁及其复合材料具有高比强度和低密度的特性，因此被广泛应用于各种领域。然而，由于缺乏对镁合金在零度以下条件下性能的研究，其应用仅限于室温条件。本研究首次尝试了两种低温（-20 °C/253 K 和 -196 °C/77 K）对 Mg/2wt.%CeO2 纳米复合材料的物理、热和机械性能的影响。这些材料采用分解熔融沉积法合成，然后进行热挤压。结果表明，与在 -196 °C 的液氮中进行深度低温处理的样品相比，浅度低温处理（-20 °C冷藏）的样品孔隙率降低，耐燃性降低，微硬度、压缩屈服度、极限强度和破坏应变相似。虽然经深度低温处理的样品显示出整体优势，但由于在零下 20 ℃ 暴露的样品显示出非常相似的机械性能，从而降低了低温处理的整体成本，因此性能提高的程度可能并不合理。研究结果与公开文献中的数据进行了比较，并对性能改善背后的机理进行了评估。
{"title":"Comparison of Shallow (−20 °C) and Deep Cryogenic Treatment (−196 °C) to Enhance the Properties of a Mg/2wt.%CeO2 Nanocomposite","authors":"Shwetabh Gupta, Gururaj Parande, M. Gupta","doi":"10.3390/technologies12020014","DOIUrl":"https://doi.org/10.3390/technologies12020014","url":null,"abstract":"Magnesium and its composites have been used in various applications owing to their high specific strength properties and low density. However, the application is limited to room-temperature conditions owing to the lack of research available on the ability of magnesium alloys to perform in sub-zero conditions. The present study attempted, for the first time, the effects of two cryogenic temperatures (−20 °C/253 K and −196 °C/77 K) on the physical, thermal, and mechanical properties of a Mg/2wt.%CeO2 nanocomposite. The materials were synthesized using the disintegrated melt deposition method followed by hot extrusion. The results revealed that the shallow cryogenically treated (refrigerated at −20 °C) samples display a reduction in porosity, lower ignition resistance, similar microhardness, compressive yield, and ultimate strength and failure strain when compared to deep cryogenically treated samples in liquid nitrogen at −196 °C. Although deep cryogenically treated samples showed an overall edge, the extent of the increase in properties may not be justified, as samples exposed at −20 °C display very similar mechanical properties, thus reducing the overall cost of the cryogenic process. The results were compared with the data available in the open literature, and the mechanisms behind the improvement of the properties were evaluated.","PeriodicalId":504839,"journal":{"name":"Technologies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139605279","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}
Pub Date : 2024-01-22DOI: 10.3390/technologies12010012
Daniel Mateu-Gomez, Francisco José Martínez-Peral, Carlos Perez-Vidal
This article addresses the problem of automating a multi-arm pick-and-place robotic system. The objective is to optimize the execution time of a task simultaneously performed by multiple robots, sharing the same workspace, and determining the order of operations to be performed. Due to its ability to address decision-making problems of all kinds, the system is modeled under the mathematical framework of the Markov Decision Process (MDP). In this particular work, the model is adjusted to a deterministic, single-agent, and fully observable system, which allows for its comparison with other resolution methods such as graph search algorithms and Planning Domain Definition Language (PDDL). The proposed approach provides three advantages: it plans the trajectory to perform the task in minimum time; it considers how to avoid collisions between robots; and it automatically generates the robot code for any robot manufacturer and any initial objects’ positions in the workspace. The result meets the objectives and is a fast and robust system that can be safely employed in a production line.
{"title":"Multi-Arm Trajectory Planning for Optimal Collision-Free Pick-and-Place Operations","authors":"Daniel Mateu-Gomez, Francisco José Martínez-Peral, Carlos Perez-Vidal","doi":"10.3390/technologies12010012","DOIUrl":"https://doi.org/10.3390/technologies12010012","url":null,"abstract":"This article addresses the problem of automating a multi-arm pick-and-place robotic system. The objective is to optimize the execution time of a task simultaneously performed by multiple robots, sharing the same workspace, and determining the order of operations to be performed. Due to its ability to address decision-making problems of all kinds, the system is modeled under the mathematical framework of the Markov Decision Process (MDP). In this particular work, the model is adjusted to a deterministic, single-agent, and fully observable system, which allows for its comparison with other resolution methods such as graph search algorithms and Planning Domain Definition Language (PDDL). The proposed approach provides three advantages: it plans the trajectory to perform the task in minimum time; it considers how to avoid collisions between robots; and it automatically generates the robot code for any robot manufacturer and any initial objects’ positions in the workspace. The result meets the objectives and is a fast and robust system that can be safely employed in a production line.","PeriodicalId":504839,"journal":{"name":"Technologies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139607396","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}
Pub Date : 2024-01-11DOI: 10.3390/technologies12010009
Yuehan Zhu, T. Fukuda, N. Yabuki
In contemporary society, “Indoor Generation” is becoming increasingly prevalent, and spending long periods of time indoors affects well-being. Therefore, it is essential to research biophilic indoor environments and their impact on occupants. When it comes to existing building stocks, which hold significant social, economic, and environmental value, renovation should be considered before new construction. Providing swift feedback in the early stages of renovation can help stakeholders achieve consensus. Additionally, understanding proposed plans can greatly enhance the design of indoor environments. This paper presents a real-time system for architectural designers and stakeholders that integrates mixed reality (MR), diminished reality (DR), and generative adversarial networks (GANs). The system enables the generation of interior renovation drawings based on user preferences and designer styles via GANs. The system’s seamless integration of MR, DR, and GANs provides a unique and innovative approach to interior renovation design. MR and DR technologies then transform these 2D drawings into immersive experiences that help stakeholders evaluate and understand renovation proposals. In addition, we assess the quality of GAN-generated images using full-reference image quality assessment (FR-IQA) methods. The evaluation results indicate that most images demonstrate moderate quality. Almost all objects in the GAN-generated images can be identified by their names and purposes without any ambiguity or confusion. This demonstrates the system’s effectiveness in producing viable renovation visualizations. This research emphasizes the system’s role in enhancing feedback efficiency during renovation design, enabling stakeholders to fully evaluate and understand proposed renovations.
在当代社会，"室内一代 "日益盛行，长时间呆在室内会影响身心健康。因此，研究亲生物室内环境及其对居住者的影响至关重要。现有建筑具有重要的社会、经济和环境价值，在新建建筑之前，应考虑对其进行翻新。在翻新的早期阶段迅速提供反馈意见有助于利益相关者达成共识。此外，了解拟议的计划也能大大提高室内环境的设计水平。本文为建筑设计师和利益相关者介绍了一个实时系统，该系统集成了混合现实（MR）、减弱现实（DR）和生成对抗网络（GANs）。该系统可根据用户偏好和设计师风格，通过 GAN 生成室内装修图纸。该系统将 MR、DR 和 GAN 无缝集成，为室内装修设计提供了一种独特的创新方法。然后，MR 和 DR 技术将这些二维图纸转化为身临其境的体验，帮助利益相关者评估和理解翻新方案。此外，我们还使用全参考图像质量评估（FR-IQA）方法对 GAN 生成的图像质量进行了评估。评估结果表明，大多数图像显示出中等质量。在 GAN 生成的图像中，几乎所有物体的名称和用途都能被识别，没有任何歧义或混淆。这表明该系统能有效地生成可行的翻新可视化图像。这项研究强调了该系统在提高翻新设计过程中的反馈效率方面的作用，使利益相关者能够充分评估和理解拟议的翻新工程。
{"title":"A Mixed Reality Design System for Interior Renovation: Inpainting with 360-Degree Live Streaming and Generative Adversarial Networks after Removal","authors":"Yuehan Zhu, T. Fukuda, N. Yabuki","doi":"10.3390/technologies12010009","DOIUrl":"https://doi.org/10.3390/technologies12010009","url":null,"abstract":"In contemporary society, “Indoor Generation” is becoming increasingly prevalent, and spending long periods of time indoors affects well-being. Therefore, it is essential to research biophilic indoor environments and their impact on occupants. When it comes to existing building stocks, which hold significant social, economic, and environmental value, renovation should be considered before new construction. Providing swift feedback in the early stages of renovation can help stakeholders achieve consensus. Additionally, understanding proposed plans can greatly enhance the design of indoor environments. This paper presents a real-time system for architectural designers and stakeholders that integrates mixed reality (MR), diminished reality (DR), and generative adversarial networks (GANs). The system enables the generation of interior renovation drawings based on user preferences and designer styles via GANs. The system’s seamless integration of MR, DR, and GANs provides a unique and innovative approach to interior renovation design. MR and DR technologies then transform these 2D drawings into immersive experiences that help stakeholders evaluate and understand renovation proposals. In addition, we assess the quality of GAN-generated images using full-reference image quality assessment (FR-IQA) methods. The evaluation results indicate that most images demonstrate moderate quality. Almost all objects in the GAN-generated images can be identified by their names and purposes without any ambiguity or confusion. This demonstrates the system’s effectiveness in producing viable renovation visualizations. This research emphasizes the system’s role in enhancing feedback efficiency during renovation design, enabling stakeholders to fully evaluate and understand proposed renovations.","PeriodicalId":504839,"journal":{"name":"Technologies","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2024-01-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139625917","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：