检索结果-内蒙古大学图书馆

8th IFIP TC 12 International Conference on Computer, Communication and Signal processing, ICCCSP 2024

ISBN: (纸本)9783031736162

The proceedings contain 36 papers. The special focus in this conference is on Computer, Communication and Signal processing. The topics include: time Series Forecasting for COVID-19 Confirmed Cases Using Transformer Based Stacked LSTM Model;Automated Depression Detection Using CNN and Transformer-Based Pre-trained Language Models;integrating deep learning Frameworks for Automated Medical image Diagnosis;explaining Parkinson's Disease Detection by Ensemble Classifiers with Local Interpretable Features;Mental Stress Assessment in Working Environment for an Individual Using Wearable Sensor of EEG and Pulse Signal Measured with Help of deep learning Algorithm;speech Recording Analysis for Parkinson’s Detection Using Machine learning Approach;Compressed VGGNet for Automatic COVID-19 Disease Detection from CT Scan images;diabetic Foot Ulcer Classification Using deep learning Approach;medisync: Fingerprint-Enabled Authorization of Medical Device Calibration;renal Irregularities Detection Using Convolutional Neural Network;Surveillance and Mitigation of External Stimuli-Induced Sensory Overload in Autism with IoMT: Communicating Insights to Caregivers;a New Innovative Initialization Strategy in Population-Based Evolutionary Optimization Algorithms;AI-Enhanced Sign Language Interpreter;An NLP Based Approach to Automate and Enhance the Systematic Review Within PRISMA Format;closing the Communication Divide: Enhancing Sign Language Recognition with Gesture-to-Text Conversion Through Computer Vision;Evolving GAN-BERT Architecture for Efficient Text Categorization with Minimal Labeled Data;assessing Degradation Levels of Palm Leaf Manuscripts with Random Forest Using Gabor Features;sign Language Recognition System – A Review;Implementing a NFT Based Album Purchasing Web Application Using ReactJs by Integrating with Ethereum Blockchain;a deep learning-Based Algorithm for Predicting the Turning Point of Cloud Workload.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FlowTurbo: Towards real-time Flow-Based image Generation with Velocity Refiner 38

FlowTurbo: Towards Real-time Flow-Based Image Generation wit...

引用

38th Conference on Neural Information processing Systems, NeurIPS 2024

作者： Zhao, Wenliang Shi, Minglei Yu, Xumin Zhou, Jie Lu, Jiwen Department of Automation Tsinghua University China

Building on the success of diffusion models in visual generation, flow-based models reemerge as another prominent family of generative models that have achieved competitive or better performance in terms of both visual quality and inference speed. By learning the velocity field through flow-matching, flow-based models tend to produce a straighter sampling trajectory, which is advantageous during the sampling process. However, unlike diffusion models for which fast samplers are well-developed, efficient sampling of flow-based generative models has been rarely explored. In this paper, we propose a framework called FlowTurbo to accelerate the sampling of flow-based models while still enhancing the sampling quality. Our primary observation is that the velocity predictor's outputs in the flow-based models will become stable during the sampling, enabling the estimation of velocity via a lightweight velocity refiner. Additionally, we introduce several techniques including a pseudo corrector and sample-aware compilation to further reduce inference time. Since FlowTurbo does not change the multi-step sampling paradigm, it can be effectively applied for various tasks such as image editing, inpainting, etc. By integrating FlowTurbo into different flow-based models, we obtain an acceleration ratio of 53.1%∼58.3% on class-conditional generation and 29.8%∼38.5% on text-to-image generation. Notably, FlowTurbo reaches an FID of 2.12 on imageNet with 100 (ms/img) and FID of 3.93 with 38 (ms/img), achieving the real-time image generation and establishing the new state-of-the-art. Code is available at https://***/shiml20/FlowTurbo. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Method for Measuring Strawberry Leaf Area Based on Three-Dimensional Point Cloud Instance Segmentation

引用

IEEE ACCESS 2025年 13卷 25339-25349页

作者： Li, Zhipeng Wang, Shusheng Su, Yuanping Yu, Dongyun Jiangxi Univ Sci & Technol Coll Energy & Mech Engn Nanchang 330013 Peoples R China Jiangxi Prov & Chinese Acad Sci Lushan Bot Garden Jiujiang 332900 Peoples R China

With effective protective covering and microclimate control, greenhouse crops offer significant advantages, such as high yield and quality, remaining unaffected by seasonal variations and meeting the demand for diverse agricultural products. Efficient production relies on precise automatic control of the environment and nutrients, and the leaf area index is a crucial growth parameter that affects indoor microclimate and nutrient transport within plants. Therefore, real-time monitoring of leaf area is essential for adjusting control strategies. This study introduces a strawberry three-dimensional point cloud instance segmentation method to address the challenge of stem and leaf instance segmentation in calculating plant leaf area using three-dimensional point cloud data. High-quality point cloud data were obtained using a three-dimensional scanner, and feature enhancement was achieved through the Leaf Vein and Boundary Preserving Sampling method. The network achieved an average precision of 90.41% for instance segmentation, with the precision of leaf segmentation reaching 93.63%. The Mean Absolute Error of the reconstructed leaf area, calculated using the Poisson surface reconstruction method with boundary processing, was 5.51 cm2, with a Root Mean Square Error of 6.91 cm2 and a Coefficient of Determination of 0.867. These findings provide valuable technical support and references for greenhouse cultivation and smart agriculture applications. The source code and dataset can be accessed at https://***/suyangsuluo/SGC.

关键词： Point cloud compression Three-dimensional displays image segmentation Crops Instance segmentation Object segmentation Green products Nutrients Area measurement Optical variables measurement Leaf area point clouds instance segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

Unveiling Touristic Pulse: Harnessing Social Sensing for Dynamic Insights 29

Unveiling Touristic Pulse: Harnessing Social Sensing for Dyn...

引用

29th IEEE Symposium on Computers and Communications (IEEE ISCC)

作者： Perez de Lucia, Jose Giner Fernandez-Pedauye, Julio Celdran-Bernabeu, Marco A. Mazon, Jose-Norberto Cecilia, Jose M. Univ Politecn Valencia Valencia Spain Sensing Tools Valencia Spain Univ Alicante Alicante Spain

ISBN: (纸本)9798350354249;9798350354232

This paper explores the use of social sensing to analyze tourism dynamics in Torrevieja (Alicante), a tourist coastal city in Spain. By leveraging advancements in Natural Language processing (NLP) and deep learning (DL), this study classifies Twitter data into ten thematic areas outlined in Torrevieja's Tourism Development Strategy. We aim to develop a tourism-social barometer that allows real-time monitoring of significant issues impacting tourist cities, as identified through user-generated content. This analysis provides in-depth and real-time insights into public perceptions of Torrevieja as a tourist destination, factors affecting visitor experiences, and subsequent implications for destination management and marketing strategies. Employing an interdisciplinary approach that integrates tourism studies, social media analytics, and data science, our findings reveal critical themes and patterns emerging from the social media discourse. These insights enhance understanding of local tourism dynamics and also inform broader destination management practices.

关键词： Social Sensing Smart Tourism Destinations Destination Management Natural Language processing User-Generated Content

来源：评论

学校读者我要写书评

暂无评论

Recognition and localization of freshwater fish heads and tails based on lightweight neural networks

引用

INTERNATIONAL JOURNAL OF FOOD PROPERTIES 2023年第1期26卷 1290-1303页

作者： Chen, Yan Peng, Xianhui Cai, Lu Jiao, Ming Fu, Dandan Jiang, Yajun Hu, Zhigang Wuhan Polytech Univ Sch Mech Engn Wuhan Peoples R China

The quality of fish pre-treatment processing directly affected the production competitiveness of the fish industry. The removal of heads and tails is one of the key technologies in the fish processing. This study proposed an identification method of fish head and tail, and the original YOLOV3 model was improved by replacing the backbone feature extraction network of the YOLOV3 model with the lightweight neural network MobileNetv3. Firstly, a freshwater fish image dataset was created and divided into the training, validation and test sets with the assigned ratio of 6:2:2. Next, the freshwater fish dataset was trained using the target detector YOLOV3. Finally, the average accuracy mAP (mean of Average Precision) and the average image detection time were used as the accuracy and speed indexes to evaluate the detection effect of the model. In addition, the SSD-MobileNetv3 and SSD-VGG16 were introduced into present study and they were compared with the improved algorithm. The experimental results showed that the detection speed of the YOLOV3 model with MobileNetV3 was significantly improved. The mAP of YOLOV3-MobileNetv3 model was 98.36%, the inference speed was 28.2 ms, which was 5.09%, 4.24% and 2.07% higher than the mAP of other three models (SSD-VGG16, SSD-MobileNetv3 and YOLOV3-Darknet-53), and the average detection time shortened by 86%, 9.99% and 29%, respectively. Therefore, this experimental method of head and tail of freshwater fish could achieve real-time detection and recognition of various kinds of freshwater fish, which had the great advantages of high detection accuracy and fast detection speed.

关键词： fish head and tail target detection deep learning contrast test MobileNetv3

来源：评论

学校读者我要写书评

暂无评论

Classification of Cutaneous Diseases: A Systematic Study on real-time Captured images Using deep learning 27th

Classification of Cutaneous Diseases: A Systematic Study o...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Kanekar, Bhavik Sawant, Jay Chikhale, Niti Dhotre, Paras Savant, Sushil Nagare, Gajanan Jadhav, Kshitij Koita Centre for Digital Health Indian Institute of Technology Bombay Mumbai India Department of Biomedical Engineering Vidyalankar Institute of Technology Mumbai India The Humanitarian Clinic Mumbai India

ISBN: (纸本)9783031782008

Dermatological infectious diseases pose a significant public health concern due to their highly contagious nature, often characterized by painful sores, fluid-filled blisters, flesh-colored bumps, and itching. Despite their distinct visual symptoms, diagnosing these diseases can be challenging due to their phenotypical similarities and overlapping clinical presentations with other skin conditions. In this paper we introduce a novel and diverse skin lesion dataset comprising patients from India, focusing on prevalent infectious skin conditions such as herpes zoster, herpes simplex, molluscum contagiosum, and non-viral skin disorders. These conditions are particularly common in this geographical region. Furthermore, we test deep learning models using different augmentation techniques, analyze the performance, and evaluate several metrics on different deep models using image augmentations. By assessing the performance of these models and analyzing several metrics across different augmentation methods, our findings demonstrate the capability of deep-learning models in classifying skin images and such computational techniques can be used to enhance healthcare accessibility and effectiveness, in resource-constrained settings like India. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Detection of Liver Tumors from CT Scans using TransUNet Architecture in deep learning 2

Segmentation and Detection of Liver Tumors from CT Scans usi...

引用

2nd International Conference on Intelligent Cyber Physical Systems and Internet of Things (ICoICI)

作者： Sundar, Koushik Manohar, Eashaan Vijay, K. Ravikumar, S. Citibank NA Jersey City NJ 07310 USA Rajalakshmi Engn Coll Dept Comp Sci & Engn Chennai Tamil Nadu India Dr Sagunthala R&D Inst Sci & Technol Dept Comp Sci & Engn Chennai Tamil Nadu India

ISBN: (纸本)9798331540661;9798331540678

Globally, liver tumors and the third major cancer killer and sixth common disease. They occur mostly in people who take tobacco or alcohol very often. These factors are responsible for around 75-85 percent of cases of primary liver cancer. Nonetheless, manual diagnosis of liver tumors is known to be a challenging task due to tumor heterogeneity, diverse shapes and sizes as well as many types of imaging artifacts that can occur with relatively limited annotated data. Diagnosis and treatment planning of liver tumors are highly affected by the critical task of segmenting tumor in medical images. Further, for identifying stages, precision and make a doctor treatment-level understanding of learning characteristics tumor Since the knowledge that has been many feature extraction techniques formulated some frameworks onset detection tumors begun its course which could be fully transformed into applications targeted response type against size as well volume based However, this is an error-prone and time-consuming process. Thus, a solution to overcome these challenges is introduced by using deep learning (DL) with the TransUNet model which belongs to Convolutional Network architecture for instant image processing. Doctors use this system to conveniently detect and segment tumors from images, it is a way of approximating tumor size and stage so that more accurate treatment can be given. To sum up, liver tumors as a worldwide health problem are largely related to alcohol and tobacco consumption. Manual diagnosis is tough however with the help of advanced deep learning methods such as TransUNet we can detect tumors at an early stage and accurately providing better treatment to patients by doctors.

关键词： deep learning Liver Tumor Segmentation TransUNet Tumor Size Estimation

来源：评论

学校读者我要写书评

暂无评论

Explainable Machine learning Models and Architectures 1

引用

2023年

作者： Suman Lata Tripathi Mufti Mahmud

ISBN: (数字)9781394186570

ISBN: (纸本)9781394185849

EXPLAINABLE MACHINE learning MODELS AND ARCHITECTURES This cutting-edge new volume covers the hardware architecture implementation, the software implementation approach, and the efficient hardware of machine learning applications. Machine learning and deep learning modules are now an integral part of many smart and automated systems where signal processing is performed at different levels. Signal processing in the form of text, images, or video needs large data computational operations at the desired data rate and accuracy. Large data requires more use of integrated circuit (IC) area with embedded bulk memories that further lead to more IC area. Trade-offs between power consumption, delay and IC area are always a concern of designers and researchers. New hardware architectures and accelerators are needed to explore and experiment with efficient machine-learning models. Many real-time applications like the processing of biomedical data in healthcare, smart transportation, satellite image analysis, and IoT-enabled systems have a lot of scope for improvements in terms of accuracy, speed, computational powers, and overall power consumption. This book deals with the efficient machine and deep learning models that support high-speed processors with reconfigurable architectures like graphic processing units (GPUs) and field programmable gate arrays (FPGAs), or any hybrid system. Whether for the veteran engineer or scientist working in the field or laboratory, or the student or academic, this is a must-have for any library.

关键词： VLSI Design Machine learning Algorithm Neural Network VLSI Architecture Hardware Trojan Trojan Detection and Prevention FPGA SOC Hardware Accelerator Edge Accelerator In memory Computing On Chip Computing SRAM in ML Novel Material Memristor Neuromorphic

来源：评论

学校读者我要写书评

暂无评论

A Multi-Modal Non-Invasive deep learning Framework for Progressive Prediction of Seizures 20

A Multi-Modal Non-Invasive Deep Learning Framework for Progr...

引用

20th International Conference on Body Sensor Networks

作者： Saeizadeh, Ali Schonholtz, Douglas Neimat, Joseph S. Johari, Pedram Melodia, Tommaso Northeastern Univ Inst Wireless Internet Things Boston MA 02115 USA Univ Louisville Louisville KY 40292 USA

ISBN: (纸本)9798331530143

This paper introduces an innovative framework designed for progressive (granular in time to onset) prediction of seizures through the utilization of a deep learning (DL) methodology based on non-invasive multi-modal sensor networks. Epilepsy, a debilitating neurological condition, affects an estimated 65 million individuals globally, with a substantial proportion facing drug-resistant epilepsy despite pharmacological interventions. To address this challenge, we advocate for predictive systems that provide timely alerts to individuals at risk, enabling them to take precautionary actions. Our framework employs advanced DL techniques and uses personalized data from a network of non-invasive electroencephalogram (EEG) and electrocardiogram (ECG) sensors, thereby enhancing prediction accuracy. The algorithms are optimized for real-time processing on edge devices, mitigating privacy concerns and minimizing data transmission overhead inherent in cloud-based solutions, ultimately preserving battery energy. Additionally, our system predicts the countdown time to seizures (with 15-minute intervals up to an hour prior to the onset), offering critical lead time for preventive actions. Our multi-modal model achieves 95% sensitivity, 98% specificity, and 97% accuracy, averaged among 29 patients.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Research on the Construction of image Similarity Calculation Model Based on Convolutional Neural Network

Research on the Construction of Image Similarity Calculation...

引用

2024 International Conference on Remote Sensing, Mapping, and image processing, RSMIP 2024

作者： Liu, Qingxiu Yu, Yijia Guo, Yaqin Chongqing College of Architecture and Technology Chongqing401331 China

ISBN: (纸本)9781510680012

With the update iteration of deep learning technology, the necessity of image similarity calculation in image retrieval, target detection and tracking has become more and more prominent, and it has become an important force to promote the development of computer vision and artificial intelligence. In the face of increasingly complex and diverse application scenarios, the traditional image similarity detection technology has obvious shortcomings in calculation accuracy, and the image feature extraction needs manual assistance in the calculation process, so that the overall robustness of the technology is poor and cannot meet the practical application requirements. In view of this, this paper integrates the powerful image feature extraction ability of convolutional neural network, and constructs an image similarity calculation model based on VGG16-Siamese neural network, aiming at improving the accuracy of image similarity calculation and providing data support for the next technical application. Practice has proved that the VGG16 part of the model is used as the backbone feature extraction network to obtain the feature vector of the image. The Siamese neural network can use the feature vectors of two images to construct the distance similarity function at the same time, so as to calculate the similarity of the two images. The final experimental results show that the image similarity calculation model of VGG16-Siamese neural network has a precision of 90.84% and a recall rate of 91.88%, which meets the design expectation and has certain application and promotion value. © 2024 SPIE.

关键词： Feature extraction

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：