Showing papers by "Vincenzo Piuri published in 2023"
TL;DR: In this paper , the authors proposed a Bayesian-backward deep-encoder learning (IBBD) framework to mine deep autoencoder (AE) configurations for data sparsification and determine optimal tradeoffs between information loss and power overhead.
Abstract: Internet of Medical Things (IoMT) is igniting many emerging smart health applications, by continuously streaming the big data for data-driven innovations. One critical obstacle in IoMT big data is the power hungriness of long-term data transmission. Targeting this challenge, we propose a novel framework called, IoMT big-data Bayesian-backward deep-encoder learning (IBBD), which mines deep autoencoder (AE) configurations for data sparsification and determines optimal tradeoffs between information loss and power overhead. More specifically, the IBBD framework leverages an additional external Bayesian-backward loop that recommends AE configurations, on top of a traditional deep learning loop that executes and evaluate the AE quality. The IBBD recommendation is based on confidence to further minimize the regularized metrics that quantify the quality of AE configurations, and it further leverages regularization techniques to allow adjusting error–power tradeoffs in the mining process. We have conducted thorough experiments on a cardiac data streaming application and demonstrated the superiority of IBBD over the common practices such as discrete wavelet transform, and we have further generalized IBBD through validating the optimal AE configurations determined on one user to other users. This study is expected to greatly advance IoMT big data streaming practices toward precision medicine.
1 citations
TL;DR: In this paper , a flexible and diverse contrastive learning (FDCL) framework is proposed to solve the problem of contrastive image classification for steel surface defect images, which consists of two parts, flexible contrast (FiCo) and diverse generative adversarial networks (DGANs).
Abstract: As samples of steel defects are industrially limited, it is challenging for most deep learning methods that rely on ample labeled data to identify steel surface defects. Recently, contrastive learning has achieved good performance in natural image classification tasks with few labeled samples, yet two obstacles prevent its effective application to steel surface defect images. One is that due to the presence of inter-class and intra-class similar samples in steel surface defect, the fixed contrast strength in contrastive learning will destroy the potential semantic information of defect samples. Another is that contrastive learning requires a large amount of unlabeled data, whereas steel surface defect samples are insufficient. To overcome the above-mentioned problems, a novel framework named flexible and diverse contrastive learning (FDCL) is proposed. This framework consists of two parts, flexible contrast (FiCo) and diverse generative adversarial networks (DGANs). Diverse images generated by the DGAN and real images are fed into FiCo for representation learning. In the FiCo, the contrast strength among samples is flexibly adjusted by the proposed variable temperature discrimination and feature reconstruction (FR). In addition, the output features (OF) of FiCo will be used as input to the DGAN generator to improve image quality, thus further facilitating representation learning. The proposed FDCL is implemented on four standard steel surface defect data sets, and the experimental results demonstrated that it achieves superior performance over state-of-the-art methods. Our code is available at: https://github.com-/jiacongc/FDCL.
TL;DR: In this article , the Feminist Research Collective, the WomenWeLove project and this special issue have been introduced, with a special issue dedicated to women's empowerment and women's health.
Abstract: Abstract This paper introduces the Feminist Research Collective, the WomenWeLove project and this special issue.
01 May 2023
TL;DR: CFF-Net as discussed by the authors proposes a cross feature fusion network (CFFNet) for skin lesion segmentation, where the encoder of the network includes dual branches where the CNNs branch aims to extract rich local features while the MLPs branch is used to establish both the global-spatial-dependencies and global-channeldependencies for precise delineation of skin lesions.
Abstract: BACKGROUND AND OBJECTIVE
Melanoma is a highly malignant skin tumor. Accurate segmentation of skin lesions from dermoscopy images is pivotal for computer-aided diagnosis of melanoma. However, blurred lesion boundaries, variable lesion shapes, and other interference factors pose a challenge in this regard.
METHODS
This work proposes a novel framework called CFF-Net (Cross Feature Fusion Network) for supervised skin lesion segmentation. The encoder of the network includes dual branches, where the CNNs branch aims to extract rich local features while MLPs branch is used to establish both the global-spatial-dependencies and global-channel-dependencies for precise delineation of skin lesions. Besides, a feature-interaction module between two branches is designed for strengthening the feature representation by allowing dynamic exchange of spatial and channel information, so as to retain more spatial details and inhibit irrelevant noise. Moreover, an auxiliary prediction task is introduced to learn the global geometric information, highlighting the boundary of the skin lesion.
RESULTS
Comprehensive experiments using four publicly available skin lesion datasets (i.e., ISIC 2018, ISIC 2017, ISIC 2016, and PH2) indicated that CFF-Net outperformed the state-of-the-art models. In particular, CFF-Net greatly increased the average Jaccard Index score from 79.71% to 81.86% in ISIC 2018, from 78.03% to 80.21% in ISIC 2017, from 82.58% to 85.38% in ISIC 2016, and from 84.18% to 89.71% in PH2 compared with U-Net. Ablation studies demonstrated the effectiveness of each proposed component. Cross-validation experiments in ISIC 2018 and PH2 datasets verified the generalizability of CFF-Net under different skin lesion data distributions. Finally, comparison experiments using three public datasets demonstrated the superior performance of our model.
CONCLUSION
The proposed CFF-Net performed well in four public skin lesion datasets, especially for challenging cases with blurred edges of skin lesions and low contrast between skin lesions and background. CFF-Net can be employed for other segmentation tasks with better prediction and more accurate delineation of boundaries.
11 Jun 2023
TL;DR: In this paper , the main solutions adopted to overcome the weaknesses of I2I models and their impact on the performance are discussed, and several approaches to deploy these models on lowpowered devices and weight sharing techniques to reduce the number of parameters and resources used.
Abstract: Image-to-image (I2I) translation models are widely employed in several fields, e.g., computer vision, security or medicine. Their goal is to map images from a source domain to a target domain while preserving content information. Despite their success, these models suffer from multiple weaknesses. For example, many practical scenarios do not consent to collect a sufficient amount of images, leading to imbalanced domains. Furthermore, mode collapse and training instability require a careful design and further discourage their deployment on edge devices. Finally, I2I models need an intensive computation to learn conditional probability distributions and are difficult to adapt to different contexts. These drawbacks mainly limit their large scale applicability. In this work, we want to shed light on the main solutions adopted to overcome the above issues and their impact on the performance. We also investigate several approaches to deploy these models on low-powered devices and weight sharing techniques to reduce the number of parameters and resources used.
TL;DR: In this article , the authors proposed a dual-consistency alignment-based self-supervised learning framework for synthetic aperture radar (SAR) target recognition, which can adapt to different intensities of speckle noise, and maintain a high recognition rate even in small-sample learning.
Abstract: Deep-learning-based on convolutional neural networks (CNN) has been widely applied in synthetic aperture radar (SAR) target recognition and made significant progress. However, due to the physical effects of the equipment used to collect images, various degrees of speckle noise will be introduced into SAR images. Traditional CNN-based SAR target recognition methods are premised on the same noise intensity in the training and testing set, which is contrary to the target recognition in practice. To alleviate this problem, we propose a novel speckle noise resistant framework for SAR target recognition, called dual-consistency-alignment-based self-supervised learning. First, original SAR images are randomly added to speckle noise with different thresholds through multiplicative noise, after which contrastive pretraining is performed on unlabeled data. During this period, we combine instance pseudolabel consistency alignment and feature consistency alignment to align multiple threshold speckle noise views with original views under the same targets. Finally, the pretrained model is migrated to the downstream SAR speckle noise target recognition task. In this article, speckle noise modeling is conducted based on moving and stationary target capture and recognition data testing set, and experiment results reveal that this method can adapt to different intensities of speckle noise, is robust to modeled SAR image recognition, and maintains a high recognition rate even in small-sample learning.
TL;DR: In this paper , a multi-task learning DL model for ALL detection, trained using a cross-dataset transfer learning approach, was proposed, which achieves a higher accuracy in detecting ALL with respect to existing methods, even when not using manual labels for the source domain.
Abstract: Methods for the detection of Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) are increasingly considering Deep Learning (DL) due to its high accuracy in several fields, including medical imaging. In most cases, such methods use transfer learning techniques to compensate for the limited availability of labeled data. However, current methods for ALL detection use traditional transfer learning, which requires the models to be fully trained on the source domain, then fine-tuned on the target domain, with the drawback of possibly overfitting the source domain and reducing the generalization capability on the target domain. To overcome this drawback and increase the classification accuracy that can be obtained using transfer learning, in this paper we propose our method named “Deep Learning for Acute Lymphoblastic Leukemia” (DL4ALL), a novel multi-task learning DL model for ALL detection, trained using a cross-dataset transfer learning approach. The method adapts an existing model into a multi-task classification problem, then trains it using transfer learning procedures that consider both source and target databases at the same time, interleaving batches from the two domains even when they are significantly different. The proposed DL4ALL represents the first work in the literature using a multi-task cross-dataset transfer learning procedure for ALL detection. Results on a publicly-available ALL database confirm the validity of our approach, which achieves a higher accuracy in detecting ALL with respect to existing methods, even when not using manual labels for the source domain.
TL;DR: In this article , technological innovations in wearable, implantable, mobile, and remote healthcare that include Internet of Things (IoT), sensor informatics, and patient monitoring applications are presented.
Abstract: The papers presented in this special issue focus on technological innovations in wearable, implantable, mobile, and remote healthcare that include Internet of Things (IoT), sensor informatics, and patient monitoring applications. These new technologies are used to track the key signs of people’s health to improve their lifestyle and health disorders. Innovations in IoT devices play a vital role in assisting patients in managing their health conditions. Thanks to the advent of modern communication technologies and Internet of Things (IoT) paradigms that have made the implementation of biomedical devices nearly universal. Now with the evolving industrial revolution, patients and healthcare providers are expecting something more. Practically speaking, healthcare wearables have experienced tremendous growth in the past few years, and it is expected to grow even more shortly, making it an ideal space for the biomedical informatics research community to solve complex healthcare problems and more informed decision making to improve human health.
TL;DR: In this article , Chen et al. introduce the special section on Internet of Behavior for Emerging Technologies (IBBE) and propose a citation alert system to notify users whenever a record that they have chosen has been cited.
Abstract: introduction Share on Introduction to the Special Section on Internet of Behavior for Emerging Technologies Authors: Mu-Yen Chen National Cheng Kung University, Taiwan National Cheng Kung University, Taiwan 0000-0002-3945-4363View Profile , Vincenzo Piuri University of Milan, Italy University of Milan, Italy 0000-0003-3178-8198View Profile , Alireza Souri Haliç University, Turkey Haliç University, Turkey 0000-0001-8314-9051View Profile , Mohammad Shojafar University of Surrey, UK University of Surrey, UK 0000-0003-3284-5086View Profile Authors Info & Claims ACM Transactions on Sensor NetworksVolume 19Issue 2Article No.: 23pp 1–3https://doi.org/10.1145/3589021Published:16 May 2023Publication History 0citation21DownloadsMetricsTotal Citations0Total Downloads21Last 12 Months21Last 6 weeks21 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access