检索结果-内蒙古大学图书馆

A novel brain tumor segmentation and classification model using deep neural network over MRI-flair images

Multimedia Tools and Applications 2025年第17期84卷 17645-17676页

作者： Rajendirane, Rajmohan Ananth Kumar, T. Sandhya, S.G. Hu, Yu-Chen Department of Computing Technologies SRM Institute of Science and Technology Kattankulathur Campus Tamil Nadu Kattankulathur India Department of Computer Science and Engineering IFET College of Engineering Tamil Nadu Villupuram India Department of Computer Science and Engineering Annamalai University Chidambaram India Department of Computer Science Tunghai University No. 1727 Sec. 4 Boulevard Xitun District Taichung City407224 Taiwan

Brain tumors pose a significant health concern globally, with their detection and diagnosis being crucial for timely intervention and treatment planning. These abnormal growths can develop within the brain or originate from other parts of the body, spreading to the brain. They can be benign or malignant, and their impact on cognitive and physical function can vary widely depending on their location, size, and type. Detecting brain tumors involves a combination of imaging techniques and clinical assessment. Magnetic Resonance Imaging (MRI) is one of the primary imaging modalities used for this purpose due to its ability to provide detailed images of the brain's anatomy and pathology. Advanced image processing techniques and machine learning algorithms play an increasingly important role in enhancing the accuracy and efficiency of brain tumor detection. This study presents a comprehensive approach for enhancing brain tumor detection in MRI images using a combination of advanced techniques. Firstly, an improved K-means clustering algorithm is introduced to segment tumor regions effectively. Following this, Median Filtering is applied to refine image quality and reduce noise interference. Subsequently, a deep neural network architecture is employed for precise tumor classification utilizing the BRATS dataset. The proposed methodology aims to improve the accuracy and efficiency of brain tumor detection, offering potential advancements in medical image analysis and diagnosis. Experimental results demonstrate promising outcomes, indicating the effectiveness of the proposed approach in accurately identifying tumor regions in MRI scans. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

A Model to Validate Different Inflections of Assamese Verbs

引用

Recent Patents on Engineering 2025年第2期19卷 13-25页

作者： Sarma, Parismita Bhuyan, Manash Pratim Kalita, Chandamita Upadhyaya, Varsha Department of Information Technology Gauhati University Assam Guwahati India Department of Computer Science Dibru College Assam Dibrugarh India

A verb in a sentence defines the action to be performed and keeps the subject of the sentence in motion. Assamese is a language spoken by millions of people in Assam, a North Eastern state of India. In the Assamese language, different inflections of verbs express the tense of the action, whether it is present, past or future. Verbs are inflected according to person, number, gender, tense, and voice, thus showing their existence in different situations. In this research work, we have built a tool to check whether an Assamese verb form is valid or invalid. After checking the validity, it also displays the meaning of the inflected form of the root verb in English. The root verbs are conjugated with the inflectional morphemes, and inflected verb forms are recorded. Background: This work is completely new and done by the authors for the Assamese language. To build this tool, a few research papers on this language were studied, and a summary of them is written in the Related Work section. Methods: In this experiment, 72 root verbs and 132 inflections were used. GUI was designed by using Tkinter in Python. The inflected verb form passed through three modules consisting of different searching techniques. Assamese corpus, Google search, Assamese Wikipedia, and Manual evaluation, respectively. Results: Finally, 662 Assamese valid verb forms were found that have meaning and are used in a different context. Corpus search, Google search, Assamese Wikipedia and Manual Evaluation gave 232, 733, 550 and 112 numbers of overall search results accordingly. Novelty: This paper presents a novel validation framework for Assamese language verb inflections and hence it can be defined as a patent work. This work can help the linguistic community better comprehend verb inflection patterns and linguistic diversity. This patent paper explores the inflections of a lesser-known low-resource language that would be beneficial. This study could be considered as innovative and important because it h

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Ultrasound-based AI for COVID-19 detection: a comprehensive review of public and private lung ultrasound datasets and studies

引用

Multimedia Tools and Applications 2025年 1-55页

作者： Morshed, Abrar Al Shihab, Abdulla Jahin, Md Abrar Al Nahian, Md Jaber Hossain Sarker, Md Murad Ibne Wadud, Md Sharjis Uddin, Mohammad Istiaq Imtiaz Siraji, Muntequa Anjum, Nafisa Shristy, Sumiya Rajjab Rahman, Tanvin Khatun, Mahmuda Rubel Dewan, Md Hossain, Mosaddeq Sultana, Razia Chakma, Ripel Emon, Sonet Barua Islam, Towhidul Hussain, Mohammad Arafat Department of Computer Science and Engineering Ahsanullah University of Science and Technology Dhaka1208 Bangladesh Department of Electrical and Telecommunication Engineering Daffodil International University Dhaka1216 Bangladesh Khulna9203 Bangladesh Okinawa904-0412 Japan Department of Information and Communication Technology Bangladesh University of Professionals Dhaka1216 Bangladesh Department of Information and Communication Technology Comilla University Cumilla3506 Bangladesh Department of Biomedical Physics and Technology University of Dhaka Dhaka1000 Bangladesh Department of Computer Science and Engineering International Islamic University Chittagong Chittagong4318 Bangladesh Department of Electrical and Electronic Engineering Islamic University of Technology Gazipur1704 Bangladesh Department of Electronics and Telecommunication Engineering Chittagong University of Engineering and Technology Chittagong4349 Bangladesh Department of Computer Science and Engineering Notre Dame University Bangladesh Dhaka1000 Bangladesh Department of Electrical and Electronic Engineering Khulna University of Engineering & Technology Khulna9203 Bangladesh Department of Computer Science and Engineering Institute of Science and Technology Dhaka1209 Bangladesh Department of Electronics and Communication Engineering Institute of Science and Technology Dhaka1209 Bangladesh Department of Mathematics Jahangirnagar University Dhaka1342 Bangladesh Department of Electrical and Electronic Engineering Daffodil International University Dhaka1216 Bangladesh Department of Electrical and Electronic Engineering Dhaka University of Engineering and Technology Gazipur1707 Bangladesh Department of Computer Science and Telecommunication Engineering Noakhali Science and Technology University Noakhali3814 Bangladesh Department of Computer Science and Engineering Northern University Bangladesh Dhaka1230 Bangladesh Boston Children’s Hospital Harvard Medical School BostonMA02

The COVID-19 pandemic has affected millions of people globally, with respiratory organs being strongly affected in individuals with comorbidities. Medical imaging-based diagnosis and prognosis have become increasingly popular in clinical settings for detecting COVID-19 lung infections. Among various medical imaging modalities, ultrasound stands out as a low-cost, mobile, and radiation-safe imaging technology. In this comprehensive review, we focus on AI-driven studies utilizing lung ultrasound (LUS) for COVID-19 detection and analysis. We provide a detailed overview of both publicly available and private LUS datasets and categorize the AI studies according to the dataset they used. Additionally, we systematically analyzed and tabulated the studies across various dimensions, including data preprocessing methods, AI models, cross-validation techniques, and evaluation metrics. In total, we reviewed 60 articles, 41 of which utilized public datasets, while the remaining employed private data. Our findings suggest that ultrasound-based AI studies for COVID-19 detection have great potential for clinical use, especially for children and pregnant women. Our review also provides a useful summary for future researchers and clinicians who may be interested in the field. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Soft-GNN:towards robust graph neural networks via self-adaptive data utilization

引用

Frontiers of computer science 2025年第4期19卷 1-12页

作者： Yao WU Hong HUANG Yu SONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China College of Information and Communication National University of Defense TechnologyWuhan 430019China Department of Computer Science and Operations Research Universitéde MontréalMontreal H3C 3J7Canada

Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high ***,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with *** presents a challenge in learning robust GNNs under noisy *** address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in *** approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global *** better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more *** evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关键词： graph neural networks node classification label noise robustness

来源：评论

学校读者我要写书评

暂无评论

State-of-the-Art in Multi-faceted Feature Matching for E-Commerce: A Comprehensive Analysis

引用

Informatica (Slovenia) 2024年第12期48卷 97-106页

作者： Zareena, Noorbasha Rao, B. Tarakeswara Department of Computer Science and Systems Engineering AUTDR HUB Andhra University India Deparment of Computer Science and Engineering Kallam Haranadhareddy Institute of Technology Andhra Pradesh Guntur India

In this paper we provided an insightful exploration into the critical role of feature matching in enhancing the efficacy of e-commerce recommendation systems. By meticulously analyzing user data and product characteristics, feature matching significantly improves the personalization of product suggestions, thereby augmenting user experience and engagement in online shopping platforms. The paper reviews existing methodologies, including collaborative filtering, content-based filtering, hybrid models, and advanced deep learning approaches, which have collectively advanced the domain of personalized recommendations. Despite these advancements, the paper identifies key limitations such as scalability challenges, the cold start problem, over-specialization versus diversity in recommendations, and concerns over user privacy and data security. Through this comprehensive analysis, the survey makes substantial contributions by delineating the current state of the art, pinpointing critical gaps, and suggesting avenues for future research. The paper particularly emphasizes the need for dynamic adaptation in recommendation systems to keep pace with the fast-evolving e-commerce sector and changing consumer behaviors. Future research directions highlighted include the exploration of unsupervised and reinforcement learning models, the development of cross-domain recommendation systems, and the integration of emerging technologies, all aimed at fostering more nuanced, adaptable, and ethically responsible recommendation mechanisms. © 2024 Slovene Society Informatika. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Metaverse: open possibilities

Iraqi Journal for Computer Science and Mathematics

引用

Iraqi Journal for computer science and Mathematics 2023年第3期4卷 79-86页

作者： Aljanabi, Mohammed Mohammed, Sahar Yousif Department of Computer College of Education Al-Iraqia University Baghdad10011 Iraq Computer Science Department Computer Science &Information Technology College Anbar University Anbar31001 Iraq

To create a completely immersive, highly spatiotemporal, and self-sustaining virtual shared place for humans to play, work, and interact, the Metaverse is an emerging paradigm of the next-generation Internet. Metaverse is transitioning from science fiction to a near-future reality thanks to recent developments in new technologies like extended reality, artificial intelligence, and *** this study, we investigate the Metaverse, a shared, fully immersive virtual environment that could serve as a model for the Internet’s future generation. Safety, education, games, entertainment, social effects, the economy, ethics, and future issues are just few of the many areas covered. The Metaverse’s innovative tools for communication and collaboration may have a profound impact on people’s daily lives and the way society operates as a whole. However, there are obstacles that must be addressed before it can be implemented. If the Metaverse is accepted, a far different digital future is possible. © 2023 Authors. All rights reserved.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Holo4Care: a MR framework for assisting in activities of daily living by context-aware action recognition

引用

Multimedia Tools and Applications 2024年 1-25页

作者： Benavent-Lledo, Manuel Mulero-Pérez, David Garcia-Rodriguez, Jose Martinez-Martin, Ester Vizcaya-Moreno, Flores Department of Computer Technology University of Alicante Alicante Spain Department of Computer Science and Artificial Intelligence University of Alicante Alicante Spain Department of Nursery University of Alicante Alicante Spain

The evolution of virtual and augmented reality devices in recent years has encouraged researchers to develop new systems for different fields. This paper introduces Holo4Care, a context-aware mixed reality framework designed for assisting in activities of daily living (ADL) using the HoloLens 2. By leveraging egocentric cameras embedded in these devices, which offer a close-to-wearer perspective, our framework establishes a congruent relationship, facilitating a deeper understanding of user actions and enabling effective assistance. In our approach, we extend a previously established action estimation architecture after conducting a thorough review of state-of-the-art methods. The proposed architecture utilizes YOLO for hand and object detection, enabling action estimation based on these identified elements. We have trained new models on well-known datasets for object detection, incorporating action recognition annotations. The achieved mean Average Precision (mAP) is 33.2% in the EpicKitchens dataset and 26.4% on the ADL dataset. Leveraging the capabilities of the HoloLens 2, including spatial mapping and 3D hologram display, our system seamlessly presents the output of the action recognition architecture to the user. Unlike previous systems that focus primarily on user evaluation, Holo4Care emphasizes assistance by providing a set of global actions based on the user’s field of view and hand positions that reflect their intentions. Experimental results demonstrate Holo4Care’s ability to assist users in activities of daily living and other domains. © The Author(s) 2024.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Joint Frame Drop and Object Detection Task Offloading for Mobile Devices via RL With Lyapunov Optimization

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6168-6182页

作者： Sohn, Vaughn Kim, Suhwan Lee, Hyang-Won Korea Advanced Institute of Science and Technology Department of Electrical Engineering Daejeon34141 Korea Republic of Konkuk University Department of Computer Science and Engineering Seoul05029 Korea Republic of

Object detection has become an increasingly important application for mobile devices. However, state-of-the-art object detection relies heavily on deep neural network, which is often burdensome to compute on mobile devices. To this end, we develop a layering framework for joint video frame drop and object detection task offloading. In the lower layer, by invoking Lyapunov optimization, we devise an algorithm for partitioning and offloading the computation tasks of deep neural networks. This algorithm also specifies the flow control for admitting the application traffic into the network. In the upper layer, we use the flow control as a form of guidance in the action space in order to develop a reinforcement learning (RL) algorithm that selectively drops video frames with object detection performance in consideration. By the nature of design, this Lyapunov-guided RL guarantees the network stability. We show through simulations that our Lyapunov-guided RL drops video frames with reasonable object detection performance and reduced latency while keeping the network stable. We also implemented our algorithm on the remote-controlled (RC) car equipped with microprocessor and GPU, and demonstrate the applicability of our algorithm to real-time object detection tasks from the video stream generated as the RC car moves. © 2002-2012 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Throughput Prediction Using LS-SVM For 4g-LTE Network and Beyond

Throughput Prediction Using LS-SVM For 4g-LTE Network and Be...

引用

2024 International Conference on Telecommunications and Intelligent Systems, ICTIS 2024

作者： Hamdani, Mostefa Sahnoune, Ahmed Merzougui, Mokhtar Douara, Abdelmalek Khatemi, Fouad University El Wancharissi Laboratory of Electronics Computer Science and Applied Mathematics Faculty of Science and Technology Department of Mathematics and Computer Science Algeria University El Wancharissi Laboratory of Electronics Computer Science and Applied Mathematics Faculty of Science and Technology Department of Science and Technology Algeria

ISBN: (纸本)9798331527396

The integration of Artificial Intelligence(AI) with Long-Term Evolution (LTE) networks offers substantial potential for improving communication infrastructure. By harnessing AI algorithms, it is possible to dynamically optimize network parameters, proactively predict and mitigate equipment failures, and enhance Quality of Service (QoS) by prioritizing critical services through real-time analysis of key performance indicators. This study focuses on predicting network throughput using Least Square Support Vector Machine (LS-SVM). The predictive models developed can trigger adaptive network reconfigurations, ensuring that the network responds promptly to changing conditions. Simulation results reveal that the integration of LS-SVM significantly improves prediction accuracy, enabling more effective implementation of self-organizing network strategies in real-time. © 2024 IEEE.

关键词： Long Term Evolution (LTE)

来源：评论

学校读者我要写书评

暂无评论

BAHGRF^(3):Human gait recognition in the indoor environment using deep learning features fusion assisted framework and posterior probability moth flame optimisation

引用

CAAI Transactions on Intelligence technology 2025年第2期10卷 387-401页

作者： Muhammad Abrar Ahmad Khan Muhammad Attique Khan Ateeq Ur Rehman Ahmed Ibrahim Alzahrani Nasser Alalwan Deepak Gupta Saima Ahmed Rahin Yudong Zhang Foundation University Islamabad IslamabadPakistan Department of Artificial Intelligence College of Computer Engineering and SciencePrince Mohammad Bin Fahd UniversityAl KhobarSaudi Arabia Computer Science Department Community CollegeKing Saud UniversityRiyadhSaudi Arabia Department of Computer Science Maharaja Agrasen Institute of TechnologyDelhiIndia United International University DhakaBangladesh School of Informatics University of LeicesterLeicesterUK

Biometric characteristics are playing a vital role in security for the last few *** gait classification in video sequences is an important biometrics attribute and is used for security purposes.A new framework for human gait classification in video sequences using deep learning(DL)fusion assisted and posterior probability-based moth flames optimization(MFO)is *** the first step,the video frames are resized and finetuned by two pre-trained lightweight DL models,EfficientNetB0 and *** models are selected based on the top-5 accuracy and less number of ***,both models are trained through deep transfer learning and extracted deep features fused using a voting *** the last step,the authors develop a posterior probabilitybased MFO feature selection algorithm to select the best *** selected features are classified using several supervised learning *** CASIA-B publicly available dataset has been employed for the experimental *** this dataset,the authors selected six angles such as 0°,18°,90°,108°,162°,and 180°and obtained an average accuracy of 96.9%,95.7%,86.8%,90.0%,95.1%,and 99.7%.Results demonstrate comparable improvement in accuracy and significantly minimize the computational time with recent state-of-the-art techniques.

关键词： deep learning feature fusion feature optimization gait classification indoor environment 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：