检索结果-内蒙古大学图书馆

Active Voice Amplifier: On-Device Noisy Environment-Aware Solution for Dialogue Enhancement in real time

JOURNAL OF THE AUDIO ENGINEERING SOCIETY 2023年第3期71卷 129-137页

作者： Cho, Jaeyoun Kim, Sunmin Hwang, Inwoo Samsung Elect Co Ltd Suwon South Korea Samsung Elect Co Ltd Algorithms digital TVs mobiles & sound devices Sound Lab Suwon South Korea

Since a cathode-ray tube television was introduced first to the consumers in the late 1920s, a variety of multimedia device form-factors has appeared in the consumer market until now. Although the values of multimedia devices had been mostly put on picture quality and sound quality in the past, it is undoubtedly told at this moment that user experience is the most important and attractive value for the multimedia products. As for now, almost all outstanding features of the brand-new products are the technologies about user convenience such as voice user interaction, device unlock, contents recommendation, and so on. Likewise, an unprecedented feature of smart TVs, the Active Voice Amplifier, was introduced in the Consumer Electronics Show 2020, and it detects disturbing noise and enhances voice clarity accordingly and automatically. To design this feature and make it work in real time on real devices, state-of-the-art signal processing methods and deep learning technologies are integrated in a function for the novel approach of noisy environment detection and speech extraction from multimedia audio contents. This paper overviews what this function pursues in user experience, describes how it was designed in terms of signal processing methods, and demonstrates how effectively it works on real-time TV systems.

关键词： deep learning

来源：评论

学校读者我要写书评

暂无评论

real-time prediction of hydrodynamic forces and dynamic responses of a generic jack-up platform using deep learning

引用

OCEAN ENGINEERING 2024年 306卷

作者： Miyanawala, T. P. Li, Y. Law, Y. Z. Santo, H. Technol Ctr Offshore & Marine Singapore TCOMS Singapore 118411 Singapore

Irregular ocean waves contribute to random and non-linear hydrodynamic forces on marine and offshore platforms, in particular those made of slender bodies such as jack-ups. Keeping track of the structural fatigue, integrity, and reliability renders benefits to these platforms such as enabling predictive maintenance and riskbased decision support. While computational techniques are useful in providing insights to deepen our understanding of the physics involved, these are resource-intensive and not suited for predictive capabilities. Here we introduce an effective deep learning method based on Long Short time Memory (LSTM) to predict unsteady hydrodynamic forces on jack-up legs, which are mainly governed by non-linear drag forces, as well as dynamic responses of the jack-up in terms of reaction forces and hull motion. The numerical OF-ABAQUS solver (one-way fluid-structure coupling) designed for jack-up by Li et al. (2022, 2023) is used to generate a database for the deep neural network, which takes in wave elevation time series as the input. A leaky non-linear rectification is used to trace the relationship between wave elevation (as the input) and hydrodynamic forces as well as structural responses (as the outputs). The LSTM model is trained using a stochastic gradient descent method, and the results are compared with the full-order numerical simulations. Once the hyper-parameters of the LSTM algorithm are identified, further tuning for each sea-state is not required. Instead, the same LSTM algorithm can be used for different sea-states. The predictions made with our LSTM model are real-time, 96,000 times faster than the fullorder simulations, within a 6% error threshold, and use a negligible amount of central processing unit (CPU) power. This powerful tool can be used to obtain real-time predictions using computers on offshore platforms without high-performance computers inland. Further, the proposed LSTM-based method can be applied to create digital twins for jac

关键词： Machine learning Long short time memory (LSTM) Computational fluid dynamics Finite element analysis Jack-up

来源：评论

学校读者我要写书评

暂无评论

Auto-BCS: A Hybrid System for real-time Breast Cancer Screening from Pathological images

引用

JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024年第4期37卷 1752-1766页

作者： Ekta, Vandana Bhatia, Vandana Netaji Subhas Univ Technol Delhi India

Breast cancer is recognized as a prominent cause of cancer-related mortality among women globally, emphasizing the critical need for early diagnosis resulting improvement in survival rates. Current breast cancer diagnostic procedures depend on manual assessments of pathological images by medical professionals. However, in remote or underserved regions, the scarcity of expert healthcare resources often compromised the diagnostic accuracy. Machine learning holds great promise for early detection, yet existing breast cancer screening algorithms are frequently characterized by significant computational demands, rendering them unsuitable for deployment on low-processing-power mobile devices. In this paper, a real-time automated system "Auto-BCS" is introduced that significantly enhances the efficiency of early breast cancer screening. The system is structured into three distinct phases. In the initial phase, images undergo a pre-processing stage aimed at noise reduction. Subsequently, feature extraction is carried out using a lightweight and optimized deep learning model followed by extreme gradient boosting classifier, strategically employed to optimize the overall performance and prevent overfitting in the deep learning model. The system's performance is gauged through essential metrics, including accuracy, precision, recall, F1 score, and inference time. Comparative evaluations against state-of-the-art algorithms affirm that Auto-BCS outperforms existing models, excelling in both efficiency and processing speed. Computational efficiency is prioritized by Auto-BCS, making it particularly adaptable to low-processing-power mobile devices. Comparative assessments confirm the superior performance of Auto-BCS, signifying its potential to advance breast cancer screening technology.

关键词： Breast cancer screening deep learning Classification models Hybrid system On-device image recognition

来源：评论

学校读者我要写书评

暂无评论

Fast real-time Brain Tumor Detection Based on Stimulated Raman Histology and Self-Supervised deep learning Model

引用

JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024年第3期37卷 1160-1176页

作者： Wang, Zijun Han, Kaitai Liu, Wu Wang, Zhenghui Shi, Chaojing Liu, Xi Huang, Mengyuan Sun, Guocheng Liu, Shitou Guo, Qianjin Beijing Inst Petrochem Technol Acad Artificial Intelligence Beijing 102617 Peoples R China

In intraoperative brain cancer procedures, real-time diagnosis is essential for ensuring safe and effective care. The prevailing workflow, which relies on histological staining with hematoxylin and eosin (H&E) for tissue processing, is resource-intensive, time-consuming, and requires considerable labor. Recently, an innovative approach combining stimulated Raman histology (SRH) and deep convolutional neural networks (CNN) has emerged, creating a new avenue for real-time cancer diagnosis during surgery. While this approach exhibits potential, there exists an opportunity for refinement in the domain of feature extraction. In this study, we employ coherent Raman scattering imaging method and a self-supervised deep learning model (VQVAE2) to enhance the speed of SRH image acquisition and feature representation, thereby enhancing the capability of automated real-time bedside diagnosis. Specifically, we propose the VQSRS network, which integrates vector quantization with a proxy task based on patch annotation for analysis of brain tumor subtypes. Training on images collected from the SRS microscopy system, our VQSRS demonstrates a significant speed enhancement over traditional techniques (e.g., 20-30 min). Comparative studies in dimensionality reduction clustering confirm the diagnostic capacity of VQSRS rivals that of CNN. By learning a hierarchical structure of recognizable histological features, VQSRS classifies major tissue pathological categories in brain tumors. Additionally, an external semantic segmentation method is applied for identifying tumor-infiltrated regions in SRH images. Collectively, these findings indicate that this automated real-time prediction technique holds the potential to streamline intraoperative cancer diagnosis, providing assistance to pathologists in simplifying the process.

关键词： Stimulated Raman histology SRS imaging system Brain tumor subtype classification Intraoperative diagnosis Vector quantization Generative deep learning

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stage Progressive Pansharpening Network Based on Detail Injection with Redundancy Reduction

引用

SENSORS 2024年第18期24卷 6039页

作者： Wen, Xincan Ma, Hongbing Li, Liangliang Xinjiang Univ Sch Comp Sci & Technol Urumqi 830046 Peoples R China Xinjiang Univ Key Lab Signal Detect & Proc Urumqi 830046 Peoples R China Tsinghua Univ Dept Elect Engn Beijing 100084 Peoples R China Beijing Inst Technol Sch Informat & Elect Beijing 100081 Peoples R China

In the field of remote sensing image processing, pansharpening technology stands as a critical advancement. This technology aims to enhance multispectral images that possess low resolution by integrating them with high-spatial-resolution panchromatic images, ultimately producing multispectral images with high resolution that are abundant in both spatial and spectral details. Thus, there remains potential for improving the quality of both the spectral and spatial domains of the fused images based on deep-learning-based pansharpening methods. This work proposes a new method for the task of pansharpening: the Multi-Stage Progressive Pansharpening Network with Detail Injection with Redundancy Reduction Mechanism (MSPPN-DIRRM). This network is divided into three levels, each of which is optimized for the extraction of spectral and spatial data at different scales. Particular spectral feature and spatial detail extraction modules are used at each stage. Moreover, a new image reconstruction module named the DRRM is introduced in this work;it eliminates both spatial and channel redundancy and improves the fusion quality. The effectiveness of the proposed model is further supported by experimental results using both simulated data and real data from the QuickBird, GaoFen1, and WorldView2 satellites;these results show that the proposed model outperforms deep-learning-based methods in both visual and quantitative assessments. Among various evaluation metrics, performance improves by 0.92-18.7% compared to the latest methods.

关键词： deep learning pansharpening feature extraction image reconstruction multi-stage

来源：评论

学校读者我要写书评

暂无评论

Tinto: Multisensor Benchmark for 3-D Hyperspectral Point Cloud Segmentation in the Geosciences

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2024年 62卷 1页

作者： Afifi, Ahmed J. Thiele, Samuel T. Rizaldy, Aldino Lorenz, Sandra Ghamisi, Pedram Tolosana-Delgado, Raimon Kirsch, Moritz Gloaguen, Richard Heizmann, Michael Helmholtz Zentrum Dresden Rossendorf Helmholtz Inst Freiberg Resource Technol HIF D-09599 Freiberg Germany Karlsruhe Inst Technol KIT Inst Ind Informat Technol IIIT D-76187 Karlsruhe Germany

The increasing use of deep learning techniques has reduced interpretation time and, ideally, reduced interpreter bias by automatically deriving geological maps from digital outcrop models. However, accurate validation of these automated mapping approaches is a significant challenge due to the subjective nature of geological mapping and the difficulty in collecting quantitative validation data. Additionally, many state-of-the-art deep learning methods are limited to 2-D image data, which is insufficient for 3-D digital outcrops, such as hyperclouds. To address these challenges, we present Tinto, a multisensor benchmark digital outcrop dataset designed to facilitate the development and validation of deep learning approaches for geological mapping, especially for nonstructured 3-D data like point clouds. Tinto comprises two complementary sets: 1) a real digital outcrop model from Corta Atalaya (Spain), with spectral attributes and ground-truth data and 2) a synthetic twin that uses latent features in the original datasets to reconstruct realistic spectral data (including sensor noise and processing artifacts) from the ground truth. The point cloud is dense and contains 3242964 labeled points. We used these datasets to explore the abilities of different deep learning approaches for automated geological mapping. By making Tinto publicly available, we hope to foster the development and adaptation of new deep learning tools for 3-D applications in Earth sciences. The dataset can be accessed through this link: https://***/10.14278/rodare.2256.

关键词： deep learning digital outcrop hypercloud hyperspectral point cloud point cloud segmentation remote sensing remote sensing remote sensing synthetic data

来源：评论

学校读者我要写书评

暂无评论

A lightweight deep neural network implemented on MATLAB without using GPU for the automatic monitoring of the plants

引用

MULtimeDIA TOOLS AND APPLICATIONS 2023年第5期82卷 7343-7359页

作者： Gupta, Abhishek Shri Mata Vaishno Devi Univ Sch Comp Sci & Engn Katra 182320 Jammu & Kashmir India

Plants and trees are essential for the human kind which must be preserved and well taken care for the growth of any country. Plants require intensive care which involves monitoring of their size, growth, health, and yield. Manually monitoring of these factors is time consuming. In this regard, computer vision approaches are evolving to monitor the plants for developing better yields. deep learning convolution neural network is the most promising and currently trending tool which can solve the complex problems in the field of image processing and computer vision. However, often these deep learning models are computationally expensive and time-consuming which makes them unsuitable to be used in the real world scenarios. Thus, a lightweight deep learning convolutional neural network was designed and proposed to automatically segment the plant's leaves so that the monitoring of the plants can be done with high speed. Benchmark datasets in four different categories with total of 810 images were collected to train and test the proposed model. Many challenges were associated with those categories under the mentioned dataset for the segmentation of leaves. The proposed light-weight deep learning model was implemented on MATLAB platform tool and trained on a local system without using any GPU (Graphical processing Unit). The training was completed within 13 minutes and 25 sec and provided segmentation accuracy on testing set as 98.26% which is satisfactory for such kind of monitoring applications.

关键词： Convolution neural network deep learning Plant's leaf segmentation Semantic segmentation Lightweight training-based system

来源：评论

学校读者我要写书评

暂无评论

real-time image analysis in IoT-based home security system

Real-time image analysis in IoT-based home security system

引用

Conference on real-time image processing and deep learning

作者： Villarreal, A. Mehrubeoglu, M. Davila, L. McLauchlan, L. Texas A&M Univ Corpus Christi Dept Engn Corpus Christi TX 78412 USA Texas A&M Univ Kingsville Dept Elect Engn & Comp Sci Kingsville TX USA

ISBN: (数字)9781510661714

ISBN: (纸本)9781510661707;9781510661714

Internet of Things (IoT) uses cloud-enabled data sharing to connect physical objects to sensors, processing software, and other technologies via the Internet. IoT allows a vast network of communication amongst these physical objects and their corresponding data. This study investigates the use of an IoT development board for real-time sensor data communication and processing, specifically images from a camera. The IoT development board and camera are programmed to capture images for object detection and analysis. Data processing is performed on board which includes the microcontroller and wireless communication with the sensor. The IoT connectivity and simulated test results to verify real-time signal communication and processing will be presented.

关键词： Internet of things IoT Arduino BeagleBone home security

来源：评论

学校读者我要写书评

暂无评论

Accelerating fast and accurate instantaneous segmentation with YOLO-v8 for remote sensing image analysis

引用

REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT 2025年 37卷

作者： Silpalatha, G. Jayadeva, T. S. REVA Univ Sch ECE Bangalore Karnataka India

With increasing complexity of remote sensing data, there is growing demand for more accurate and efficient techniques;thus, this forms a big challenge for conventional deep learning-based models. Most of the traditional segmentation models face some of the crucial problems such as high computational costs, slow processing times, and limited processing accuracy due to diversified and complex image features. Such a defect usually performs badly while pursuing real-time performance and maintaining high quality in practical applications. This paper will be focused on such challenges by proposing a new YOLOv8-based instantaneous image segmentation model. The proposed model leverages the latest novelty in the YOLO architecture to optimize the same for both speed and accuracy on remote sensing image segmentation tasks. Contrary to existing models with potential trade-offs between model accuracy and computational efficiency, in this paper, an approach has been presented to utilize a YOLOv8-based model to achieve superior segmentation performance with considerably reduced processing times. This work contributes by developing a real-time, high-performance segmentation model that can handle the geometric complexity in image data with accuracy;thus, such a model fits into time-sensitive applications like satellite imagery analysis and emergency response. The model was evaluated against the WHDLD dataset-a general benchmark for the task of remote sensing image segmentation. Experimental results have been presented for the proposed model, which has improved accuracy, precision, recall, and IoU compared to traditional segmentation methods. In addition, the results provide a decent improvement in processing time, by which the proposed network makes faster predictions than traditional methods. The key findings of the study are that the YOLOv8 model has great potential in advancing remote sensing image segmentation toward a solid solution that can balance between computational effici

关键词： image segmentation Remote sensing images Instantaneous segmentation deep learning Yolo V8 And semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

SegNet: A segmented deep learning based Convolutional Neural Network approach for drones wildfire detection

引用

REMOTE SENSING APPLICATIONS-SOCIETY AND ENVIRONMENT 2024年 34卷

作者： Jonnalagadda, Aditya, V Hashim, Hashim A. Carleton Univ Dept Mech & Aerosp Engn Ottawa ON K1S 5B6 Canada

This research addresses the pressing challenge of enhancing processing times and detection capabilities in Unmanned Aerial Vehicle (UAV)/drone imagery for global wildfire detection, despite limited datasets. Proposing a Segmented Neural Network (SegNet) selection approach, we focus on reducing feature maps to boost both time resolution and accuracy significantly advancing processing speeds and accuracy in real-time wildfire detection. This paper contributes to increased processing speeds enabling real-time detection capabilities for wildfire, increased detection accuracy of wildfire, and improved detection capabilities of early wildfire, through proposing a new direction for image classification of amorphous objects like fire, water, smoke, etc. Employing Convolutional Neural Networks (CNNs) for image classification, emphasizing on the reduction of irrelevant features vital for deep learning processes, especially in live feed data for fire detection. Amidst the complexity of live feed data in fire detection, our study emphasizes on image feed, highlighting the urgency to enhance real-time processing. Our proposed algorithm combats feature overload through segmentation, addressing challenges arising from diverse features like objects, colors, and textures. Notably, a delicate balance of feature map size and dataset adequacy is pivotal. Several research papers use smaller image sizes, compromising feature richness which necessitating a new approach. We illuminate the critical role of pixel density in retaining essential details, especially for early wildfire detection. By carefully selecting number of filters during training, we underscore the significance of higher pixel density for proper feature selection. The proposed SegNet approach is rigorously evaluated using real -world dataset obtained by a drone flight and compared to state-of-the-art literature.

关键词： Segment Neural Network Machine learning Unmanned Aerial Vehicle Convolution Neural Network Wildfire Detection Computer vision

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：