Balraj Preet Kaur (20370832), Harpreet Singh (677440), Rahul Hans (20370835) et al. · Figshare · 2024
<div><p>In the current era, a lot of research is being done in the domain of disease diagnosis using machine learning. In recent times, one of the deadliest respiratory diseases, COVID-19, which causes serious damage to the lungs has claimed a lot of lives globally. Machine learning-based systems can assist clinicians in the early diagnosis of the disease, which can reduce the deadly effects of the disease. For the successful deployment of these machine learning-based systems, hyperparameter-based optimization and feature selection are important issues. Motivated by the above, in this proposal, we design an improved model to predict the existence of respiratory disease among patients by incorporating hyperparameter optimization and feature selection. To optimize the parameters of the machine learning algorithms, hyperparameter optimization with a genetic algorithm is proposed and to reduce the size of the feature set, feature selection is performed using binary grey wolf optimization algorithm. Moreover, to enhance the efficacy of the predictions made by hyperparameter-optimized machine learning models, an ensemble model is proposed using a stacking classifier. Also, explainable AI was incorporated to define the feature importance by making use of Shapely adaptive explanations (SHAP) values. For the experimentation, the publicly accessible Mexico clinical dataset of COVID-19 was used. The results obtained show that the proposed model has superior prediction accuracy in comparison to its counterparts. Moreover, among all the hyperparameter-optimized algorithms, adaboost algorithm outperformed all the other hyperparameter-optimized algorithms. The various performance assessment metrics, including accuracy, precision, recall, AUC, and F1-score, were used to assess the results.</p></div>
Cited by 0Open access
2021
Cited by 0
Balraj Preet Kaur (20370832), Harpreet Singh (677440), Rahul Hans (20370835) et al. · Figshare · 2024
<div><p>In the current era, a lot of research is being done in the domain of disease diagnosis using machine learning. In recent times, one of the deadliest respiratory diseases, COVID-19, which causes serious damage to the lungs has claimed a lot of lives globally. Machine learning-based systems can assist clinicians in the early diagnosis of the disease, which can reduce the deadly effects of the disease. For the successful deployment of these machine learning-based systems, hyperparameter-based optimization and feature selection are important issues. Motivated by the above, in this proposal, we design an improved model to predict the existence of respiratory disease among patients by incorporating hyperparameter optimization and feature selection. To optimize the parameters of the machine learning algorithms, hyperparameter optimization with a genetic algorithm is proposed and to reduce the size of the feature set, feature selection is performed using binary grey wolf optimization algorithm. Moreover, to enhance the efficacy of the predictions made by hyperparameter-optimized machine learning models, an ensemble model is proposed using a stacking classifier. Also, explainable AI was incorporated to define the feature importance by making use of Shapely adaptive explanations (SHAP) values. For the experimentation, the publicly accessible Mexico clinical dataset of COVID-19 was used. The results obtained show that the proposed model has superior prediction accuracy in comparison to its counterparts. Moreover, among all the hyperparameter-optimized algorithms, adaboost algorithm outperformed all the other hyperparameter-optimized algorithms. The various performance assessment metrics, including accuracy, precision, recall, AUC, and F1-score, were used to assess the results.</p></div>
Cited by 0Open access
Chunyu Dong, Qunfei Zhao, Kun Chen et al. · 2021
Institute of Medical Robotics, Shanghai Jiao Tong University, Shanghai, China Rescaling a feature map could be a key issue of biological image segmentation. Nearly all the existing upsampling strategies concentrate only on local information and attempt to expand the reception field via deepening the network. In this paper, we present Asymmetric Attention Upsampling (AAU) for biological-image segmentation. AAU utilizes the information of low-level feature maps to rescale the high-level feature maps smartly through spatial pooling and attention mechanisms. It consists of two attention variants: Asymmetric Spatial Attention (ASA) and Asymmetric Channel Attention (ACA). The Asymmetric Attention Upsampling Network (AAU-Net) combines several AAU blocks to achieve better segmentation performance. Experiments on the Kvasir-SEG data set reveal the effectiveness of our work. AAU-Net outperforms other state-of-the-art methods for polyp segmentation while not consuming many resources.
Cited by 1
Ziyang Ma, Kaiming He, Yichen Wei et al. · 2015
Fig. 1-5 show more results of clip-art JPEG artifact removal. (a) input (c) ours(b) L0 regularized Figure 1. More results on clip-art JPEG compression artifact removal. (a) Input. (b) The L0 regularized method [2]. (c) Ours. 1 (a) input (c) ours(b) L0 regularized Figure 2. More results on clip-art JPEG compression artifact removal. (a) Input. (b) The L0 regularized method [2]. (c) Ours. (a) input (c) ours(b) L0 regularized Figure 3. More results on clip-art JPEG compression artifact removal. (a) Input. (b) The L0 regularized method [2]. (c) Ours. (a) input (c) ours(b) L0 regularized Figure 4. More results on clip-art JPEG compression artifact removal. (a) Input. (b) The L0 regularized method [2]. (c) Ours. (a) input (c) ours(b) L0 regularized Figure 5. More results on clip-art JPEG compression artifact removal. (a) Input. (b) The L0 regularized method [2]. (c) Ours.
Cited by 0
Xu Ma (45624), Xiangwu Deng (6612770), Long Qi (1537096) et al. · Figshare · 2019
Cited by 0Open access
Johannes Kopf, Michael F. Cohen, Dani Lischinski et al. · ACM Transactions on Graphics · 2007
Image analysis and enhancement tasks such as tone mapping, colorization, stereo depth, and photomontage, often require computing a solution (e.g., for exposure, chromaticity, disparity, labels) over the pixel grid. Computational and memory costs often require that a smaller solution be run over a downsampled image. Although general purpose upsampling methods can be used to interpolate the low resolution solution to the full resolution, these methods generally assume a smoothness prior for the interpolation.
Cited by 48
Johannes Kopf, Michael F. Cohen, Dani Lischinski et al. · ACM Transactions on Graphics · 2007
Image analysis and enhancement tasks such as tone mapping, colorization, stereo depth, and photomontage, often require computing a solution (e.g., for exposure, chromaticity, disparity, labels) over the pixel grid. Computational and memory costs often require that a smaller solution be run over a downsampled image. Although general purpose upsampling methods can be used to interpolate the low resolution solution to the full resolution, these methods generally assume a smoothness prior for the interpolation. We demonstrate that in cases, such as those above, the available high resolution input image may be leveraged as a prior in the context of a joint bilateral upsampling procedure to produce a better high resolution solution. We show results for each of the applications above and compare them to traditional upsampling methods.
Cited by 818
Shuangbing Song, Fan Zhong, Tianju Wang et al. · ACM Transactions on Graphics · 2023
Guided upsampling is an effective approach for accelerating high-resolution image processing. In this paper, we propose a simple yet effective guided upsampling method. Each pixel in the high-resolution image is represented as a linear interpolation of two low-resolution pixels, whose indices and weights are optimized to minimize the upsampling error. The downsampling can be jointly optimized in order to prevent missing small isolated regions. Our method can be derived from the color line model and local color transformations. Compared to previous methods, our method can better preserve detail effects while suppressing artifacts such as bleeding and blurring. It is efficient, easy to implement, and free of sensitive parameters. We evaluate the proposed method with a wide range of image operators, and show its advantages through quantitative and qualitative analysis. We demonstrate the advantages of our method for both interactive image editing and real-time high-resolution video processing. In particular, for interactive editing, the joint optimization can be precomputed, thus allowing for instant feedback without hardware acceleration.
Cited by 4
Xiao Wang (19312), Ting Yang (189879), Yuntao Zou (13036680) · Figshare · 2024
<div><p>The article presents an innovative approach for detecting defects in insulators used in high-voltage power transmission lines, employing an enhanced Detection Transformer (DETR) model, termed IF-DETR. The study addresses the significant challenges in traditional insulator defect detection methods, such as the loss of small defect features and confusion with background features. Firstly, we propose a multi-scale backbone network to better extract features of small objects. Secondly, as the contextual information surrounding objects plays a critical role in detecting small objects, we introduce a fusion module composed of ECA-Net and SAU to replace the original attention module for improved contextual information extraction. Lastly, we introduce the insulator defect (IDIoU) loss to optimize the instability in the matching process caused by small defects. Extensive experiments demonstrate the model’s effectiveness, particularly in detecting small defects, marking a notable advancement in insulator defect detection technology. The IF-DETR achieved a 2.3% increase in AP compared to existing advanced methods. This method not only enhances the accuracy of defect detection, crucial for maintaining the reliability and safety of power transmission systems but also has broader implications for the maintenance and inspection of high-voltage power infrastructure.</p></div>
Cited by 0Open access
Xin Chen (14149), Liqi Ji (22311934), Zhen Wang (72451) et al. · Figshare · 2025
Compared with FourierUP [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0332904#pone.0332904.ref016" target="_blank">16</a>], the proposed FDEDiff has significant advantages. The images produced by FourierUP [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0332904#pone.0332904.ref016" target="_blank">16</a>] are less natural (as seen in d) than those produced by our method (as seen in a). Compared to our method (as seen in e), FourierUP [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0332904#pone.0332904.ref016" target="_blank">16</a>] does not introduce any additional high-frequency information, while our method achieves better texture details (as seen in b). FourierUP [<a href="http://www.plosone.org/article/info:doi/10.1371/journal.pone.0332904#pone.0332904.ref016" target="_blank">16</a>] requires calculations in the complex domain (as seen in c), while our method performs calculations in the real domain, resulting in lower computational cost (as seen in f).
Cited by 0Open access
Zhuangzi Li, Ge Li, Thomas H. Li et al. · IEEE Transactions on Multimedia · 2022
Downsampled sparse point clouds are beneficial for data transmission and storage, but they are detrimental for semantic tasks due to information loss. In this paper, we examine an upsampling methodology that significantly reconstructs sparse clouds’ semantic representations. Specifically, we propose a novel semantic point cloud upsampling (SPU) framework for sparse point cloud classification. An SPU consists of two networks, i.e. an upsampling network and a classification network. They are skillfully unified to intensify semantic representations acting on the upsampling process. In the upsampling network, we first propose a novel graph aggregation convolution to construct hierarchical relations on sparse point clouds. To enhance stability and diversity during point upsampling, we then combine point shuffling and pre-interpolation technologies to build an enhanced upsampling module. Furthermore, we adopt the semantic prior information provided by a sparse point cloud to enhance its upsampling quality. The prior information is applied to an attention mechanism that can highlight key positions of the point cloud. We investigate different loss functions and conduct experiments on classical deep point networks, which effectively demonstrate the promising performance of our framework.
Cited by 63
José V. Manjón, Pierrick Coupé, Antoni Buades et al. · Medical Image Analysis · 2010
Cited by 271Open access
Yixing Zhang (9658704), Ziyan Mo (21526723), Zhuan Xin (21526726) et al. · Figshare · 2025
<div> Solar panel defect detection, a crucial quality control task in the manufacturing process, often faces challenges such as varying defect sizes, severe image background interference, and imbalanced data sample distribution. To address these issues, this paper proposes the EBBA-Detector. The core of the model lies in an enhanced balanced attention framework, which includes an Enhanced Bidirectional Feature Pyramid Network (EBFPN) and a Balanced-Attention Module (B-A Module). The EBFPN captures defect features of different sizes, significantly improving the recognition ability for small defects, while the B-A Module suppresses background interference, guiding the model to focus more on defect locations. Additionally, this paper designs a Scaled Dynamic Focal Loss (SDFL) function, which enables the model to pay more attention to minority and hard-to-identify defect samples under imbalanced data distribution. Through experimental validation on a large-scale electroluminescence (EL) dataset, the proposed method has achieved significant improvements in detection performance, with a mean Average Precision (mAP) of 89.85%, outperforming other models in multiple defect category detections. Therefore, the EBBA-Detector not only effectively detects small target objects but also demonstrates good handling capabilities for large targets and imbalanced data, providing an efficient and accurate solution for solar panel defect detection. </div>
Cited by 0Open access
Rare & Special e-Zone (The Hong Kong University of Science and Technology) · 2008
Cited by 0
Caihong Feng (446341), Zheng Luo (284622), Deyao Kong (20854763) et al. · Figshare · 2025
<div> With the continuous advancement of education informatization, classroom behavior analysis has become an important tool to improve teaching quality and student learning outcomes. However, student classroom behavior recognition methods still face challenges such as occlusion, small objects, and environmental interference, resulting in low recognition accuracy and lightweight performance. To address the above problems, this study proposes a lightweight student behavior recognition model based on Inverted Residual Mobile Block (IMRMB-Net). Specifically, this study designs a lightweight feature extraction module, IMRMB, from the images of the backbone network to be able to better capture contextual information and improve the recognition of occluded objects while saving computational resources. Using DySample, the neck network reconsiders the initial sampling position and the moving range of the offset from the point sampling perspective to accurately recognize small object behaviors in course scenes. Meanwhile, a new loss function, Focaler-ShapeIoU, is designed in this study, aiming to improve the learning ability and robustness of the model to different samples thus further solving the occlusion problem. Experiments in UK_Dataset show that IMRMB-Net has high accuracy (mAP@50 = 93.3%, mAP@50:95 = 78.7%) and lightweight performance (FPS = 60.37, Params = 7.32MB, GFLOPs = 23.8G). Meanwhile, this study verifies that IMRMB-Net can effectively solve the occlusion problem in classroom scenarios through experiments on the UK_Dataset and SCB_Dataset occlusion subsets. In addition, this study verifies the generalization ability and the ability to recognize small targets of IMRMB-Net on the VisDrone2021 dataset. </div>
Cited by 0Open access
Nick Schneider, Lukas Schneider, Peter Pinggera et al. · Lecture notes in computer science · 2016
Cited by 87
Chenxuan Huang, Lei Wang · Lecture notes in computer science · 2025
Cited by 0
Hao Wu (65943), Yanxi Liu (467386), Zhongyang Jin (17896517) et al. · Figshare · 2024
<div><p>An optimization algorithm based on the LMPEC algorithm is proposed to rectify the nameplate image to address the problem that overexposure and underexposure of the nameplate image of electrical equipment will make subsequent nameplate recognition difficult. In the network structure, the PS-UNet++ network is based on the sub-pixel convolution upsampling module, and the UNet++ network is constructed as the feature extraction sub-network of the optimization algorithm to extract more detailed information from the model. Smooth L1 loss is substituted for L1 loss in the loss function to prevent model oscillation. In addition, to increase the robustness of the model, an improved method built on the multi-scale training method is applied. The experimental results indicate that, among all comparison algorithms, the optimized algorithm performs the best on the data set of electrical equipment nameplate exposure the experimenter generated. Compared to the original LMPEC algorithm, the SSIM, PSNR, and PI image evaluation indices are enhanced by 5.6%, 5.1%, and 7.96%, respectively.</p></div>
Cited by 0Open access
Kaiyue Zhou, Ming Dong, Suzan Arslanturk · 2022 IEEE International Conference on Multimedia and Expo (ICME) · 2022
Recent supervised point cloud upsampling methods are re-stricted by the size of training data and are limited in terms of covering all object shapes. Besides the challenges faced due to data acquisition, the networks also struggle to gener-alize on unseen records. In this paper, we present an internal point cloud upsampling approach at a holistic level referred to as “Zero-Shot” Point Cloud Upsampling (ZSPU). Our approach is data agnostic and relies solely on the internal infor-mation provided by a particular point cloud without patching in both self-training and testing phases. This single-stream design significantly reduces the training time by learning the relation between low resolution (LR) point clouds and their high (original) resolution (HR) counterparts. This association will then provide super resolution (SR) outputs when origi-nal point clouds are loaded as input. ZSPU achieves com-petitive/superior quantitative and qualitative performances on benchmark datasets when compared with other upsampling methods.
Cited by 13