检索结果-内蒙古大学图书馆

Medical Imaging 2024: Image Perception, Observer Performance, and Technology Assessment

作者： Hu, Mingzhe Li, Yuheng Yang, Xiaofeng Department of Computer Science and Informatics Emory University AtlantaGA United States Department of Biomedical Engineering Emory University AtlantaGA United States Department of Radiation Oncology Winship Cancer Institute School of Medicine Emory University AtlantaGA United States

ISBN: (纸本)9781510671621

Skin cancer is a prevalent and potentially fatal disease that requires accurate and efficient diagnosis and treatment. Although manual tracing is the current standard in clinics, automated tools are desired to reduce human labor and improve accuracy. However, developing such tools is challenging due to the highly variable appearance of skin cancers and complex objects in the background. In this paper, we present SkinSAM, a fine-tuned model based on the Segment Anything Model that showed outstanding segmentation performance. The models are validated on HAM10000 dataset which includes 10015 dermatoscopic images. While larger models (ViT_L, ViT_H) performed better than the smaller one (ViT_b), the finetuned model (ViT_b_finetuned) exhibited the greatest improvement, with a Mean pixel accuracy of 0.945, Mean dice score of 0.8879, and Mean IoU score of 0.7843. Among the lesion types, vascular lesions showed the best segmentation results. Our research demonstrates the great potential of adapting SAM to medical image segmentation tasks. © 2024 SPIE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Convolutional Neural Network-Based Tattoo Detection

Evaluation of Deep Convolutional Neural Network-Based Tattoo...

引用

Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC), V Congreso Internacional en

作者： E. Jiménez-Delgado C. Quesada-López A Méndez-Porras A Lara-Petitdemange J Alfaro-Velasco Graduate Program in Computer Science and Informatics University of Costa Rica Computer Engineering Department Technological Institute of Costa Rica School of Computer Science and Informatics University of Costa Rica

ISBN: (数字)9798350364538

ISBN: (纸本)9798350364545

In this study, two deep learning models for automatic tattoo detection were analyzed; a modified Convolutional Neural Network (CNN) and pre-trained ResNet-50 model. In order to achieve this, ResNet-50 uses transfer learning with fine-tuning. The purpose of this study was to evaluate the accuracy, precision, recall, F1-score, and computational efficiency of the system being considered. To augment the dataset included 1000 photos that were equally divided between those showing tattoos and those that did not show tattoos. A k-fold cross-validation approach was employed in training and testing the models. Although custom CNNs are effective, utilizing pre-trained ones like ResNet-50 can offer even better outcomes. Specifically, ResNet-50 attained a higher accuracy (0.86 compared to 0.79), precision (0.85 versus 0.78), recall (0.91 against 0.86), and F1-score (0.91 vis-a-vis 0.86) as compared to custom CNNs. In selecting these models for examination, two main motivations were considered. The first motivation is to see whether transfer learning with a pre-trained ResNet-50 model does well when compared with a customized CNN designed specifically for tattoo detection. Secondly,the intent of this study is to know what advantages can be derived from each approach and their demerits too. Furthermore, it seeks to determine if transfer learning can provide an alternative in contrast to the common CNN techniques with regards to precision and computational efficiency. In this research, two models will be evaluated in order to answer the question of what is better for tattoo detection: transfer learning or designing custom architectures.

关键词： Training Analytical models Accuracy Computational modeling Transfer learning computer architecture Real-time systems Computational efficiency Convolutional neural networks Tuning

来源：评论

学校读者我要写书评

暂无评论

(POSTER) A Holistic IoT-Enabled Approach for Indoor Air Quality Control

(POSTER) A Holistic IoT-Enabled Approach for Indoor Air Qual...

引用

International Conference on Distributed Computing in Sensor Systems (DCOSS)

作者： Fotios Kalioras Gabriel Filios Stylianos Karatzas Sotiris Nikoletseas Department of Computer Engineering and Informatics University of Patras Greece Department of Computer Engineering and Informatics University of Patras Computer Technology Institute and Press “Diophantus” Greece Department of Civil Engineering University of Patras Greece

Indoor air quality (IAQ) is an important yet often overlooked aspect of public health, with poor IAQ contributing to a significant number of diverse health problems worldwide. Existing air quality standards have failed to fully address the problem, however emerging technologies in the field of IoT have demonstrated promise in effectively addressing this issue. This concept paper advocates a hybrid hierarchy system for IAQ monitoring that incorporates both offline and online connectivity. The system utilizes sensing elements that can perform a wide range of functions, including autocalibration, pollution event detection, and more, autonomously from the network. By combining a gateway device, the system's capabilities are enhanced, providing increased data granularity, additional calibration and sensing options as well as connection with Building Management Systems (BMS). Furthermore, by connecting the gateway to the cloud, the system can perform more advanced data analysis and machine learning, providing users with insights into not only air quality but also general environmental quality. Key features of the envisioned system include the integration of subjective perception of pollution via crowdsourcing, a TinyML technology at the edge, digital twins, and an optimised redundancy of sensors that can alleviate poor accuracy and drift as well as capture the spatial dispersion of pollution.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Information Fusion Technique for Device to Server-Enabled Communication in the Internet of Things:A Hybrid Approach

引用

computers, Materials & Continua 2024年第7期80卷 1305-1323页

作者： Amal Al-Rasheed Rahim Khan Tahani Alsaed Mahwish Kundi Mohamad Hanif Md.Saad Mahidur R.Sarker Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Science AbdulWali Khan University MardanMardan23200Pakistan Faculty of Computing and Informatics University Malaysia SabahKota KinabaluSabah88400Malaysia Applied College Taibah UniversityMadinah41477Saudi Arabia Maynooth International Engineering College Maynooth UniversityCo KildareW23 X021Irland Department of Mechanical Engineering Faculty of Engineering and Built EnvironmentUniversiti Kebangsaan MalaysiaBangiSelangor43600Malaysia Institute of Visual Informatics Universiti Kebangsaan MalaysiaBangiSelangor43600Malaysia University of Design Innovation and Technology(UDIT)Av.Alfonso XIII97Madrid28016Spain

Due to the overwhelming characteristics of the Internet of Things(IoT)and its adoption in approximately every aspect of our lives,the concept of individual devices’privacy has gained prominent attention from both customers,i.e.,people,and industries as wearable devices collect sensitive information about patients(both admitted and outdoor)in smart healthcare *** addition to privacy,outliers or noise are among the crucial issues,which are directly correlated with IoT infrastructures,as most member devices are resource-limited and could generate or transmit false data that is required to be refined before processing,i.e.,***,the development of privacy-preserving information fusion techniques is highly encouraged,especially those designed for smart IoT-enabled *** this paper,we are going to present an effective hybrid approach that can refine raw data values captured by the respectivemember device before transmission while preserving its privacy through the utilization of the differential privacy technique in IoT *** window,i.e.,δi based dynamic programming methodology,is implemented at the device level to ensure precise and accurate detection of outliers or noisy data,and refine it prior to activation of the respective transmission ***,an appropriate privacy budget has been selected,which is enough to ensure the privacy of every individualmodule,i.e.,a wearable device such as a smartwatch attached to the patient’s *** contrast,the end module,i.e.,the server in this case,can extract important information with approximately the maximum level of ***,refined data has been processed by adding an appropriate nose through the Laplace mechanism to make it useless or meaningless for the adversary modules in the *** proposed hybrid approach is trusted from both the device’s privacy and the integrity of the transmitted information *** and analytical results ha

关键词： Internet of things information fusion differential privacy dynamic programming Laplace function

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based License Plate Number Recognition for Smart Cities

引用

computers, Materials & Continua 2022年第1期70卷 2049-2064页

作者： T.Vetriselvi E.Laxmi Lydia Sachi Nandan Mohanty Eatedal Alabdulkreem Shaha Al-Otaibi Amal Al-Rasheed Romany F.Mansour Department of Computer Science and Engineering K.Ramakrishnan College of TechnologyTrichy620002India Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science&Engineering Vardhaman College of Engineering(Autonomous)Hyderabad501218India Department of Informatics and Computing Singidunum UniversitySerbia Computer Science Department College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11564Saudi Arabia Information Systems Department College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11564Saudi Arabia Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharga72511Egypt

Smart city-aspiring urban areas should have a number of necessary elements in place to achieve the intended *** controlling and management of traffic conditions,increased safety and surveillance,and enhanced incident avoidance and management should be top priorities in smart city *** the same time,Vehicle License Plate Number Recognition(VLPNR)has become a hot research topic,owing to several real-time applications like automated toll fee processing,traffic law enforcement,private space access control,and road traffic *** VLPNR is a computer vision-based technique which is employed in the recognition of automobiles based on vehicle number *** current research paper presents an effective Deep Learning(DL)-based VLPNR called DLVLPNR model to identify and recognize the alphanumeric characters present in license *** proposed model involves two main stages namely,license plate detection and Tesseract-based character *** detection of alphanumeric characters present in license plate takes place with the help of fast RCNN with Inception V2 ***,the characters in the detected number plate are extracted using Tesseract Optical Character Recognition(OCR)*** performance of DL-VLPNR model was tested in this paper using two benchmark databases,and the experimental outcome established the superior performance of the model compared to other methods.

关键词： Deep learning smart city tesseract computer vision vehicle license plate recognition

来源：评论

学校读者我要写书评

暂无评论

Modeling Parking Occupancy Using Algorithm of 3D Visibility Network

引用

IEEE Access 2025年 13卷 84424-84434页

作者： Matej Babič Branko Šter Ladislav Hluchý Giuliana Baiamonte Michele Calì Faculty of Information Studies Novo Mesto Slovenia Faculty of Computer and Informatics University of Ljubljana Ljubljana Slovenia Slovak Academy of Sciences Institute of Informatics Bratislava Slovakia Electric Electronics and Computer Engineering Department University of Catania Catania Italy

The modernization of the information communication infrastructure of the regional data transmission network has advanced in order to increase the maximum transmission speed of existing transport routes, ensuring the quality of the service and its reliability. In the present research work, a new approach for the 3D visibility network algorithm has been developed, showing how graph theory applied to wireless sensor networks (WSNs) enables technological development for new solutions in areas such as public infrastructure. The possibility of determining in such networks whether an area of interest is sufficiently covered by a given set of sensors by means of the Voronoi diagram is discussed. The parking dynamics and parking system were modeled with cellular neural networks (CNNs) based on weather conditions, and magnetic parking sensors were replaced with pillar sensors. The proposed method has proven its effectiveness in determining the position of the minimum sensors covering the area of interest, in order to find a solution in the occupation of parking spaces in the presence of different weather conditions. The proposed approach and experimental results offer potential applications in various fields such as lighting and rendering, motion planning, pattern recognition, computer graphics and computational geometry, in order to conduct studies on problems and perspectives of pillar sensor technology while reducing costs compared to magnetic ones.

关键词： Sensors Magnetic sensors Three-dimensional displays Wireless sensor networks Meteorology Computational modeling Automata Path planning Urban areas Sensor phenomena and characterization

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Multi-Contrast Dixon MRI and CT for Abdominal Fat and Muscle Segmentation Using a UNet CNN

Performance Evaluation of Multi-Contrast Dixon MRI and CT fo...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Heller, Andrew Liu, Andrew Chang, Lin-Ching Cohen, Gregg Jones, Elizabeth C. Hsu, Li-Yueh National Institutes of Health Clinical Center BethesdaMD United States Catholic University of America Department of Electrical Engineering and Computer Science WashingtonDC United States New Jersey Institute of Technology Department of Informatics NewarkNJ United States

ISBN: (纸本)9798350362480

We evaluate the performance of a deep learning framework for segmenting abdominal fat and muscle using multi-contrast Dixon magnetic resonance (MR) and computed tomography (CT) images. We aim to compare MR image segmentation by testing Dixon fat-only, water-only, and combination of both types of images and comparing the results with CT images. Nineteen subjects underwent abdominal CT and Dixon MR imaging on the same day. For each participant, three pairs of matched axial images from both CT and MR were selected at the intervertebral levels of L2-L3, L3-L4, and L4-L5 for analysis. References labels were generated through semi-automated segmentation of subcutaneous adipose tissue, visceral adipose tissue, and muscle areas. They were then used to train and evaluate a U-Net based Convolutional Neural Network (CNN) framework with a 3-fold cross-validation to compare the segmentation performance across CT, Dixon fat-only and water-only MR images. Combining the fat-only and water-only MR image inputs produced superior results in all labels. Our study demonstrates that CNN-based segmentation performance for abdominal fat and muscle improves with the inclusion of additional input channels, such as combining Dixon fat-only and water-only MR images. While CT results represent the gold standard in abdominal image segmentation, increasing the number of input image channels used in MR segmentation can approach, and even match, the results of CT. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Meta-learning in Healthcare: A Survey

引用

SN computer Science 2024年第6期5卷 791页

作者： Rafiei, Alireza Moore, Ronald Jahromi, Sina Hajati, Farshid Kamaleswaran, Rishikesan Department of Computer Science Emory University Atlanta GA United States Department of Mechatronics Engineering University of Tehran Tehran Iran School of Science and Technology University of New England Armidale NSW Australia Department of Biomedical Informatics Emory University School of Medicine Atlanta GA United States Department of Biomedical Engineering Georgia Institute of Technology Atlanta GA United States

As a subset of machine learning, meta-learning, or learning to learn, aims at improving the model’s capabilities by employing prior knowledge and experience. A meta-learning paradigm can appropriately tackle the conventional challenges of traditional learning approaches, such as insufficient number of samples, domain shifts, and generalization. These unique characteristics position meta-learning as a suitable choice for developing influential solutions in various healthcare contexts, where the available data is often insufficient, and the data collection methodologies are different. This survey discusses meta-learning broad applications in the healthcare domain to provide insight into how and where it can address critical healthcare challenges. We first describe the theoretical foundations and pivotal methods of meta-learning. We then divide the employed meta-learning approaches in the healthcare domain into two main categories of multi/single-task learning and many/few-shot learning and survey the studies. Finally, we highlight the current challenges in meta-learning research, discuss the potential solutions, and provide future perspectives on meta-learning in healthcare. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Automated medicine Clinical decision support system Few-shot learning Healthcare Meta-leaning Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Enabled IOT System for Football Identification in a Football Match 14th

Artificial Intelligence Enabled IOT System for Football Iden...

引用

12th International Advanced Computing Conference, IACC 2022

作者： Singh, Mahesh Kumar Singh, Akhilesh Kumar Singh, Pushpendra Kalpana Rishi, Om Prkash Department of Computer Science ABES Engineering College Ghaziabad201009 India Department of Computer Science and Engineering Jaypee Institute of Information Technology Noida India Department of Information Technology GL Bajaj Institute of Technology and Management Uttar Pradesh Gr Noida201306 India Department of Information Technology Raj Kumar Goel Institute of Technology Uttar Pradesh Ghaziabad201003 India Department of Computer Science Informatics University of Kota Rajasthan Kota324010 India

ISBN: (纸本)9783031356438

Due to growth of AI enabled IOT devices, their use in sports feature identification can be beneficial in terms of recognition quality. computer Vision is a powerful tool for moving object recognition and tracking. Football identification and recognition problem can be implemented using OpenCV libraries with the help of a programming language like Java, Python etc. OpenCV has special modules that contain specific algorithms and features for moving object recognition and tracking. Internet of things provides a way to connect hardware components through software implementation. In the proposed model the automatic camera module has been implemented through IoT with the help of a servo motor and raspberry pi. The main aim of this paper is to automate the work of a cameraman in a football match by automatically tracking and recognizing the football and broadcasting it with the help of an automatic camera. The initial loss was about 1749, and after 1600+ epochs iterations, the loss reduced to 0.09 in the final model. © 2023, Springer Nature Switzerland AG.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Extreme Learning Machine for Parking Slot Recognition in Smart Parking System 8

Extreme Learning Machine for Parking Slot Recognition in Sma...

引用

8th International Conference on Electrical, Telecommunication and computer engineering, ELTICOM 2024

作者： Rahmat, Romi Fadillah Faza, Sharfina Syahputra, Ilham Nainggolan, Pauzi Ibrahim Sulaiman, Riza Rahman, Mohd Amiruddin Abd Universitas Sumatera Utara Department of Information Technology Medan Indonesia Politeknik Negeri Medan Department of Computer Engineering and Informatics Medan Indonesia Universitas Sumatera Utara Department of Computer Science Medan Indonesia Institute of IR 4.0 Universiti Kebangsaan Malaysia Bangi Malaysia Universiti Putra Malaysia Faculty of Science Selangor Malaysia

ISBN: (纸本)9798331531249

In the modern era, technology has become an integral part of human life, particularly in image processing. This advanced technology is now applied to parking areas to identify vacant parking spaces. The application is designed to detect empty parking slots in real time using image data captured by a camera as input. The system then automatically scans for available parking spaces, displaying the results on the interface with green indicators for empty slots and red for occupied ones. The process involves several key stages, such as image pre-processing, image segmentation, and object detection. The system employs the Extreme Learning Machine (ELM) method to enhance its object detection capabilities. This system achieves a high accuracy rate of 94%under well-lit conditions. This novel technology optimizes parking management, providing an effective and dependable method to monitor parking availability in real time. © 2024 IEEE.

关键词： Adversarial machine learning

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：