检索结果-内蒙古大学图书馆

Human sleep position classification using a lightweight model and acceleration data

SLEEP AND BREATHING 2025年第1期29卷 1-12页

作者： Vu, Hoang-Dieu Tran, Duc-Nghia Pham, Huy-Hieu Pham, Dinh-Dat Can, Khanh-Ly Dao, To-Hieu Tran, Duc-Tan Phenikaa Univ Fac Elect & Elect Engn Hanoi 12116 Vietnam VAST Inst Informat Technol Hanoi Vietnam VinUniv Coll Engn & Comp Sci Hanoi Vietnam GUST VAST Hanoi Vietnam

PurposeThis exploratory study introduces a portable, wearable device using a single accelerometer to monitor twelve sleep positions. Targeted for home use, the device aims to assist patients with mild conditions such as gastroesophageal reflux disease (GERD) by tracking sleep postures, promoting healthier habits, and improving both reflux symptoms and sleep quality without requiring hospital-based *** study developed AnpoNet, a lightweight deep learning model combining 1D-CNN and LSTM, optimized with BN and Dropout. The 1D-CNN captures short-term movement features, while the LSTM identifies long-term temporal dependencies. Experiments were conducted on data from 15 participants performing twelve sleep positions, with each position recorded for one minute at a sampling frequency of 50 Hz. The model was evaluated using 5-Fold cross-validation and unseen participant data to assess *** achieved a classification accuracy of 94.67% +/- 0.80% and an F1-score of 92.94% +/- 1.35%, outperforming baseline models. Accuracy was computed as the mean of accuracies obtained for three participants in the test set, averaged over five independent random seeds. This evaluation approach ensures robustness by accounting for variability in both individual participant performance and model initialization, underscoring its potential for real-world, home-based *** study provides a foundation for a portable system enabling continuous, non-invasive sleep posture monitoring at home. By addressing the needs of GERD patients, the device holds promise for improving sleep quality and supporting positional therapy. Future research will focus on larger cohorts, extended monitoring durations, and user-friendly interfaces for broader adoption.

关键词： Sleep position monitoring Positional therapy Accelerometer-based wearable Sleep posture deep learning classification GERD

来源：评论

学校读者我要写书评

暂无评论

Diagnostic performance of deep learning to exclude coronary stenosis on CT angiography in TAVI patients

引用

INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING 2024年第5期40卷 981-990页

作者： Mehier, Benjamin Mahmoudi, Khalil Veugeois, Aurelie Masri, Alaa Amabile, Nicolas Del Giudice, Costantino Paul, Jean-Francois Inst Mutualiste Montsouris Dept Radiol Cardiac Imaging F-75014 Paris France Inst Mutualiste Montsouris Intervent Cardiol Dept F-75014 Paris France Inst Mutualiste Montsouris Radiol & Intervent Radiol Dept Cardiac Imaging F-75014 Paris France Inst Mutualiste Montsouris Dept Radiol Cardiac Imaging F-75014 Paris France

We evaluated the diagnostic performance of a deep-learning model (DLM) (CorEx (R), Spimed-AI, Paris, France) designed to automatically detect > 50% coronary stenosis on coronary computed tomography angiography (CCTA) images. We studied inter-observer variability as an additional aim. CCTA images obtained before transcatheter aortic valve implantation (TAVI) were assessed by two radiologists and the DLM, and the results were compared to those of invasive coronary angiography (ICA) used as the reference standard. 165 consecutive patients underwent both CCTA and ICA as part of their TAVI work-up. We excluded the 42 (25.5%) patients with a history of stenting or bypass grafting and the 23 (13.9%) patients with low-quality images. We retrospectively subjected the CCTA images from the remaining 100 patients to evaluation by the DLM and compared the DLM and ICA results. All 25 patients with > 50% stenosis by ICA also had > 50% stenosis by DLM evaluation of CCTA: thus, the DLM had 100% sensitivity and 100% negative predictive value. False-positive DLM results were common, yielding a positive predictive value of only 39% (95% CI, 27-51%). Two radiologists with 3 and 25 years' experience, respectively, performed similarly to the DLM in evaluating the CCTA images;thus, accuracy did not differ significantly between each reader and the DLM (p = 0.625 and p = 0.375, respectively). The DLM had 100% negative predictive value for > 50% stenosis and performed similarly to experienced radiologists. This tool may hold promise for identifying the up to one-third of patients who do not require ICA before TAVI.

关键词： Artificial intelligence deep learning classification Coronary arteries Tomography angiography Coronary artery disease Coronary computed tomography angiography

来源：评论

学校读者我要写书评

暂无评论

A hybrid deep learning skin cancer prediction framework

引用

ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH 2024年 57卷

作者： Farea, Ebraheem Saleh, Radhwan A. A. Abualkebash, Humam Farea, Abdulgbar A. R. Al-antari, Mugahed A. Northeastern Univ Software Coll Shenyang 110169 Peoples R China Kocaeli Univ Dept Mechatron Engn TR-41001 Kocaeli Turkiye Univ A Coruna VARPA Grp CITIC INIBIC La Coruna 15008 Spain Chongqing Univ Sch Big Data & Software Engn Chongqing 401331 Peoples R China Sejong Univ Coll AI Convergence Daeyang AI Ctr Dept Artificial Intelligence & Data Sci Seoul 05006 South Korea

early mitigate its impact. However, the limited availability of medical datasets and the challenge of optimizing learnable parameters in deep learning strategies for medical images pose significant hurdles. To address these challenges, we propose an innovative solution-a hybrid artificial intelligence (AI) framework for skin cancer prediction. This framework consists of two pivotal steps: firstly, a comprehensive skin cancer dataset is curated by combining diverse public datasets encompassing multiple disease types. This facilitates robust weight tuning of Convolutional Neural Networks (CNNs) by enhancing the diversity of the learning process. Subsequently, the optimization of deep learning is meticulously executed through the artificial Bee Colony (ABC) strategy, effectively mitigating the potential adverse effects of initial parameter randomness on AI model performance. Rigorous evaluation of the hybrid framework against eight prominent CNN models, including DenseNet121, InceptionResNetV2, and others, underscores its superior predictive capabilities. The optimized hybrid framework achieves exceptional results, boasting an accuracy of 93.04%, recall of 92.0%, precision of 93.0%, and an impressive F1-score of 93.12%. In summary, our proposed hybrid solution demonstrates a substantial advancement in multi-disease skin cancer classification. It outperforms existing AI models and holds promise as a pragmatic smart solution with far-reaching implications.

关键词： Skin cancer deep learning classification Generalized skin cancer dataset Segmentation Artificial Bee Colony (ABC)

来源：评论

学校读者我要写书评

暂无评论

A Decision Support System for the Identification of Metastases of Metastatic Melanoma Using Whole-Body FDG PET/CT Images

引用

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS 2023年第3期27卷 1397-1408页

作者： Vagenas, Theodoros P. Economopoulos, Theodore L. Sachpekidis, Christos Dimitrakopoulou-Strauss, Antonia Pan, Leyun Provata, Astero Matsopoulos, George K. Natl Tech Univ Athens Sch Elect & Comp Engn Athens Greece Natl Tech Univ Athens Sch Elect & Comp Engn Athens Greece German Canc Res Ctr Clin Cooperat Unit Nucl Med Heidelberg Germany German Canc Res Ctr Clin Cooperat Unit Nucl Med Heidelberg Germany German Canc Res Ctr Clin Cooperat Unit Nucl Med Heidelberg Germany Inst Nanosci & Nanotechnol Natl Ctr Sci Res Athens Greece Natl Tech Univ Athens Sch Elect & Comp Engn Athens Greece

Metastatic Melanoma (MM) is an aggressive type of cancer which produces metastases throughout the body with very poor survival rates. Recent advances in immunotherapy have shown promising results for controlling disease's progression. Due to the often rapid progression, fast and accurate diagnosis and treatment response assessment is vital for the whole patient management. These procedures prerequisite accurate, whole-body tumor identification. This can be offered by the imaging modality Positron Emission Tomography (PET)/Computed Tomography (CT) with the radiotracer F 18-Fluorodeoxyglucose (FDG). However, manual segmentation of PET/CT images is a very time-consuming and labor intensive procedure that requires expert knowledge. Most of the previously published segmentation techniques focus on a specific type of tumor or part of the body and require a great amount of manually labeled data, which is, however, difficult for MM. Multimodal analysis of PET/CT is also crucial because FDG-PET contains only the functional information of tumors which can be complemented by the anatomical information of CT. In this paper, we propose a whole-body segmentation framework capable of efficiently identifying the highly heterogeneous tumor lesions of MM from the whole-body 3D FDG-PET/CT images. The proposed decision support system begins with an Ensemble Unsupervised Segmentation of regions of high FDG-uptake based on Fuzzy C-means and a custom region growing algorithm. Then, a region classification model based on radiomics features and Neural Networks classifies these regions as tumors or not. Experimental results showed high performance in the identification of MM lesions with Sensitivity 83.68%, Specificity 91.82%, F1-score 75.42%, AUC 94.16% and Balanced accuracy 87.75% which were also supported by the public dataset evaluation.

关键词： Decision support system deep learning classification metastatic melanoma multimodal analysis unsupervised FDG-PET/CT segmentation

来源：评论

学校读者我要写书评

暂无评论

Grey wolf optimization technique with U-shaped and capsule networks-A novel framework for glaucoma diagnosis

引用

METHODSX 2025年 14卷 103285页

作者： Govindharaj, I Ramesh, T. Poongodai, A. Senthilkumar, K. P. Udayasankaran, P. Ravichandran, S. Vel Tech Rangarajan Dr Sagunthala R&D Inst Sci & T Dept Comp Sci & Engn Morai 600062 Tamil Nadu India RMK Engn Coll Dept Comp Sci & Engn Thiruvallur 601206 Tamil Nadu India Madanapalle Inst Technol & Sci Dept Comp Sci & Engn Artificial Intelligence Madanapalle 517325 Andhra Pradesh India Kings Engn Coll Dept Artificial Intelligence & Data Sci Chennai 602117 Tamil Nadu India Kings Engn Coll Dept Artificial Intelligence & Machine Learning Chennai 602117 Tamil Nadu India

The worldwide prevalence of glaucoma makes it a major reason for blindness thus proper early diagnosis remains essential for preventing major vision deterioration. Current glaucoma screening methods that need expert handling prove to be time-intensive and complicated before yielding appropriate diagnosis and treatment. Our system addresses these difficulties through an automated glaucoma screening platform which combines advanced segmentation methods with classification approaches. A hybrid segmentation method combines Grey Wolf Optimization Algorithm with U-Shaped Networks to obtain precise extraction of the optic disc regions in retinal fundus images. Through GWOA the network achieves optimal segmentation by adopting wolf-inspired behaviors such as circular and jumping movements to identify diverse image textures. The glaucoma classification depends on CapsNet as a deep learning model that provides exceptional image detection to ensure precise diagnosis. The combination of our method delivers 96.01 % segmentation together with classification precision which outstrips traditional approaches while indicating strong capabilities for discovering glaucoma at early stages. This automated diagnosis system elevates clinical accuracy levels through an automated screening method that solves manual process limitations. The detection framework produces better accuracy to improve clinical results in a strong effort to minimize glaucoma-induced blindness worldwide and display its capabilities in real clinical environments. center dot Hybrid GWOA-UNet ++ for precise optic disc segmentation. center dot CapsNet-based classification for robust glaucoma detection. center dot Achieved 96.01 % accuracy, surpassing existing methods.

关键词： Glaucoma detection Optic disc segmentation Grey wolf optimization U-Net ++ Capsule network deep learning classification Vision loss

来源：评论

学校读者我要写书评

暂无评论

Empowering Data Centers with Computational Storage Drive-Based deep learning Inference Functionality to Combat Ransomware 54

Empowering Data Centers with Computational Storage Drive-Bas...

引用

54th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)

作者： Friday, Kurt Bou-Harb, Elias Lee, Ron Peethambaran, Pramod Saxena, Mayank Louisiana State Univ Baton Rouge LA 70803 USA Samsung Memory Solut Lab San Francisco CA USA

ISBN: (纸本)9798350395716;9798350395709

The exponential increase in data has significantly burdened data centers with heightened operational demands and challenges in managing, storing, and processing information. Computational Storage Drives (CSDs) mitigate these issues by accelerating processes, reducing energy consumption, and liberating CPU resources for other data center tasks. In light of the notable increase in harnessing the pattern recognition capabilities of Machine learning (ML) for a variety of data center applications coupled with the aforementioned advantages of leveraging CSDs in data center environments, we build upon the state-of-the-art in CSD development via proposing a unique method for offloading ML inference to CSDs, such as Samsung's SmartSSD. Using various parallelization and optimization techniques, we demonstrate that the proposed CSD-based ML inference method surpasses the inference speed of a high-performance GPU by 344.6x. We further showcase the ability of the presented approach to promptly detect ransomware with high accuracy, precision, recall, and F1 scores, enabling effective and timely mitigation directly within the CSD. Indeed, this ML inference strategy offers the potential to enhance an assortment of other data center tasks.

关键词： ransomware detection deep learning classification long short-term memory computational storage near-data processing SmartSSD

来源：评论

学校读者我要写书评

暂无评论

Improving deep learning Transparency: Leveraging the Power of LIME Heatmap

Improving Deep Learning Transparency: Leveraging the Power o...

引用

21st International Conference on Service-Oriented Computing (ICSOC)

作者： Farhood, Helia Najafi, Mohammad Saberi, Morteza Macquarie Univ Fac Sci & Engn Sydney NSW Australia Univ Technol Sydney Fac Engn & IT Sydney NSW Australia

ISBN: (纸本)9789819709885;9789819709892

deep learning techniques have recently demonstrated remarkable precision in executing tasks, particularly in image classification. However, their intricate structures make them mysterious even to knowledgeable users, obscuring the rationale behind their decision-making procedures. Therefore, interpreter methodologies have emerged to introduce clarity into these techniques. Among these approaches is the Local Interpretable Model-Agnostic Explanations (LIME), which stands out as a means to enhance comprehensibility. We believe that interpretable deep learning methods have unrealised potential in a variety of application domains, an aspect that has been largely neglected in the existing literature. This research aims to demonstrate the utility of features like the LIME heatmap in advancing classification accuracy within a designated decision-support framework. Real-world contexts take centre stage as we illustrate how the heatmap determines the image segments playing the greatest influence on class scoring. This critical insight empowers users to formulate sensitivity analyses and discover how manipulation of the identified feature could potentially mislead the deep learning classifier. As a second significant contribution, we examine the LIME heatmap data of GoogLeNet and SqueezeNet, two prevalent network models, in an effort to improve the comprehension of these models. Furthermore, we compare LIME with another recognised interpretive method known as Gradient-weighted Class Activation Mapping (GradCAM), evaluating their performance comprehensively. Experiments and evaluations conducted on real-world datasets containing images of fish readily demonstrate the superiority of the method, thereby validating our hypothesis.

关键词： deep learning classification Visual explanation LIME Image classification Interpretable deep learning methods Local Interpretable Model-Agnostic Explanations

来源：评论

学校读者我要写书评

暂无评论

Detecting Pine Trees Damaged by Wilt Disease Using deep learning Techniques Applied to Multi-Spectral Images

引用

IEEE ACCESS 2022年 10卷 39108-39118页

作者： Zhang, Ruirui You, Jie Lee, Joonwhoan Cangzhou Normal Univ Sch Comp Sci & Engn Cangzhou 061001 Hebei Peoples R China Jeonbuk Natl Univ Dept Comp Sci & Engn Artificial Intelligence Lab Jeoju 54896 Jeollabuk Do South Korea

Pine wilt disease (PWD) is responsible for significant damage to East Asia's pine forests, including those in Korea, Japan, and China. Preventing the spread of wilt disease requires early detection and removal of damaged trees. This paper proposes a method of detecting disease-damaged pines using ortho-images corrected from 5-band multi-spectral images captured by unmanned aviation vehicles. The proposed method relies on a ResNet18 backbone network connected to a modified DenseNet module, classifies the 5-band multispectral (RGB, NIR, Red_Edge) ortho-image patches, and visualizes the results as a heat map. The patch-based classifier was retrained with hard negative examples, after which it achieved 98.66% accuracy, an improvement over the 96.0% accuracy associated with the same method applied to RGB images. The resulting heat map reflects the approximate distribution, and movement of the disease. Disease locations are also predicted by local maximums in the heat map. When the distance between a ground truth and the predicted location is less than visible distance, e.g. about 5m, it is counted as a correct detection. The proposed detection which consists of heat map generation followed by localization achieves Recall of 93.39%, Precision of 88.26%, and F1-score of 90.75%.

关键词： Diseases Vegetation deep learning Training Heating systems Forestry Random forests Pine wilt disease multispectral ortho-image heat map deep learning classification

来源：评论

学校读者我要写书评

暂无评论

deep Siamese Domain Adaptation Convolutional Neural Network Optimized with Honey Badger Algorithm for Fetal Arrhythmia Detection and classification from ECG Signals

引用

INTERNATIONAL JOURNAL OF PATTERN RECOGNITION AND ARTIFICIAL INTELLIGENCE 2024年第9期38卷

作者： Joel, T. Sethukarasi, T. RMK Engn Coll Dept Elect & Commun Engn Kavaraipettai Tamil Nadu India RMK Engn Coll Dept Comp Sci & Engn Kavaraipettai Tamil Nadu India

deep learning classification is commonly used to assess biomedical data. Fetal heart rate (FHR) signal data monitor the health of both the mother and the fetus and prevent mobility and death in fetuses at risk of hypoxia. But, the data imbalance is a major problem and happens frequently. To overcome this problem, a deep Siamese domain adaptation convolutional Neural Network optimized with Honey Badger Algorithm (HBA) is proposed in this paper for Fetal Arrhythmia Detection and classification from ECG signals (DSDACNN-HBA-FAC). The input ECG signals are collected from the fetal ECG dataset. Then, the ECG data are pre-processed using coherence shock filtering (CSF), which eliminates artifacts, like baseline drift, contact noise, muscle artifacts, electrode motion, electromyography artifacts. Using the improved non-subs sampled Shearlet transform (INSST) method, the pre-processed ECG data recover the mean, standard deviation, root mean square, skewness, kurtosis, zero-crossing, autoregressive coefficients, estimated entropy, and Higuchi's fractal dimension. The DSDACNN classifier utilizes the features extracted to categorize the output as normal and arrhythmia. In general, DSDACNN does not agree on any optimization techniques to define the optimum parameters and to ensure accurate classification. Therefore, HBA is employed to optimize the DSDACNN weight parameters. The proposed method is implemented in MATLAB. The performance metrics, like sensitivity, precision, recall, f-measure, specificity, accuracy, computation time, RoC, and error rate are evaluated. The performance of DSDACNN-HBA-FAC achieves 3.101%, 7.12%, 7.73% high accuracy, 51.136%, 59.04%, 44.51% lower computation Time and 2.292%, 5.365%, 1.551% greater AUC compared with the existing techniques, like Fetal Arrhythmia Detection with classification from ECG Signals: A NonInvasive Method (ANN-FAC), Semi-supervised active transfer learning for fetal ECG arrhythmia identification (DNN-FAC), fetal arrhythmia dete

关键词： Coherence shock filtering improved non-subsampled Shearlet transform deep learning classification

来源：评论

学校读者我要写书评

暂无评论

Boosting Breast Cancer classification from Microscopic Images Using Attention Mechanism

Boosting Breast Cancer Classification from Microscopic Image...

引用

International Conference on Decision Aid Sciences and Applications (DASA)

作者： Ukwuoma, Chiagoziem C. Urama, Gilbert C. Qin, Zhiguang Bin Heyat, Md Belal Khan, Haider Mohammed Akhtar, Faijan Masadeh, Mahmoud S. Ibegbulam, Chukwuemeka S. Delali, Fiasam Linda AlShorman, Omar Univ Elect Sci & Technol China Sch Informat & Software Engn Chengdu Sichuan Peoples R China Univ Elect Sci & Technol China Sch Comp Sci & Engn Chengdu Sichuan Peoples R China Shenzhen Univ Coll Comp Sci & Software Engn IoT Res Ctr Shenzhen Guangdong Peoples R China Sichuan Univ West China Hosp Dept Orthoped Surge Chengdu Sichuan Peoples R China Yarmouk Univ Hijjawi Fac Engn Comp Engn Dept Irbid Jordan Fed Univ Technol Owerri Dept Polymer & Text Engn Owerri Imo State Nigeria Najran Univ Fac Engn Najran Saudi Arabia Najran Univ AlShrouk Traiding Co Najran Saudi Arabia

ISBN: (纸本)9781665495011

Attention mechanism is one of the foremost later and effective deep learning methods which have shown tremendous performance in detection and classification tasks, including medical imaging. Breast cancer is a primary cause of women's cancer-related morbidity and mortality globally;thus, early identification of this malignancy will help to reduce the number of fatalities. The accurate classification of a mild and deadly cancer in microscopic breast images can give an efficient and relatively low-cost technique for breast cancer early detection. This paper proposes a deep learning model based on an attention mechanism. The proposed attention mechanism derives its input features from pre-trained models and passes its output through a Multilinear perceptron and SoftMax for classification. We trained all models on the ICIAR2018 Grand challenge Breast Cancer dataset and compared them with the pre-trained and ensemble models. For quantitative analysis, validation tests were conducted using the performance metrics for each approach. The suggested approach is proven successful, with classification results improving by +1-6%, potentially reducing human errors in the diagnosis process. Furthermore, the proposed method outperforms the state-of-the-art accuracy, with a +3-8% improvement in performance results.

关键词： Breast Cancer Attention Mechanism deep learning classification Microscopic Images Multilinear Perceptron

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：