检索结果-内蒙古大学图书馆

Segmentation of Head and Neck Tumors Using Dual PET/CT Imaging:Comparative Analysis of 2D,2.5D,and 3D Approaches Using UNet Transformer

引用

computer Modeling in engineering & sciences 2024年第12期141卷 2351-2373页

作者： Mohammed A.Mahdi Shahanawaj Ahamad Sawsan A.Saad Alaa Dafhalla Alawi Alqushaibi Rizwan Qureshi Information and Computer Science Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Software Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Computer Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Department of Computer and Information Sciences Universiti Teknologi PetronasSeri Iskandar32610Malaysia Center for Research in Computer Vision(CRCV) University of Central FloridaOrlandoFL 32816USA

The segmentation of head and neck(H&N)tumors in dual Positron Emission Tomography/Computed Tomogra-phy(PET/CT)imaging is a critical task in medical imaging,providing essential information for diagnosis,treatment planning,and outcome *** by the need for more accurate and robust segmentation methods,this study addresses key research gaps in the application of deep learning techniques to multimodal medical ***,it investigates the limitations of existing 2D and 3D models in capturing complex tumor structures and proposes an innovative 2.5D UNet Transformer model as a *** primary research questions guiding this study are:(1)How can the integration of convolutional neural networks(CNNs)and transformer networks enhance segmentation accuracy in dual PET/CT imaging?(2)What are the comparative advantages of 2D,2.5D,and 3D model configurations in this context?To answer these questions,we aimed to develop and evaluate advanced deep-learning models that leverage the strengths of both CNNs and *** proposed methodology involved a comprehensive preprocessing pipeline,including normalization,contrast enhancement,and resampling,followed by segmentation using 2D,2.5D,and 3D UNet Transformer *** models were trained and tested on three diverse datasets:HeckTor2022,AutoPET2023,and *** was assessed using metrics such as Dice Similarity Coefficient,Jaccard Index,Average Surface Distance(ASD),and Relative Absolute Volume Difference(RAVD).The findings demonstrate that the 2.5D UNet Transformer model consistently outperformed the 2D and 3D models across most metrics,achieving the highest Dice and Jaccard values,indicating superior segmentation *** instance,on the HeckTor2022 dataset,the 2.5D model achieved a Dice score of 81.777 and a Jaccard index of 0.705,surpassing other model *** 3D model showed strong boundary delineation performance but exhibited variability across datasets,while the

关键词： PET/CT imaging tumor segmentation weighted fusion transformer multi-modal imaging deep learning neural networks clinical oncology

来源：评论

学校读者我要写书评

暂无评论

MMInstruct: a high-quality multi-modal instruction tuning dataset with extensive diversity

引用

science China(Information sciences) 2024年第12期67卷 36-51页

作者： Yangzhou LIU Yue CAO Zhangwei GAO Weiyun WANG Zhe CHEN Wenhai WANG Hao TIAN Lewei LU Xizhou ZHU Tong LU Yu QIAO Jifeng DAI School of Computer Science Nanjing University School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai AI Laboratory School of Computer Science Fudan University Department of Information Engineering The Chinese University of Hong Kong SenseTime Research Department of Electronic Engineering Tsinghua University

Despite the effectiveness of vision-language supervised fine-tuning in enhancing the performance of vision large language models(VLLMs), existing visual instruction tuning datasets include the following limitations.(1) Instruction annotation quality: despite existing VLLMs exhibiting strong performance,instructions generated by those advanced VLLMs may still suffer from inaccuracies, such as hallucinations.(2) Instructions and image diversity: the limited range of instruction types and the lack of diversity in image data may impact the model's ability to generate diversified and closer to real-world scenarios outputs. To address these challenges, we construct a high-quality, diverse visual instruction tuning dataset MMInstruct,which consists of 973k instructions from 24 domains. There are four instruction types: judgment, multiplechoice, long visual question answering, and short visual question answering. To construct MMInstruct, we propose an instruction generation data engine that leverages GPT-4V, GPT-3.5, and manual correction. Our instruction generation engine enables semi-automatic, low-cost, and multi-domain instruction generation at 1/6 the cost of manual construction. Through extensive experiment validation and ablation experiments,we demonstrate that MMInstruct could significantly improve the performance of VLLMs, e.g., the model fine-tuning on MMInstruct achieves new state-of-the-art performance on 10 out of 12 benchmarks. The code and data shall be available at https://***/yuecao0119/MMInstruct.

关键词： instruction tuning multi-modal multi-domain dataset vision large language model

来源：评论

学校读者我要写书评

暂无评论

HARDeep: design and evaluation of a deep ensemble model for human activity recognition

引用

International Journal of Innovative Computing and Applications 2023年第3期14卷 155-166页

作者： Subramanian, R. Raja Vasudevan, V. Department of Computer Science and Engineering Kalasalingam Academy of Research and Education India

With the emergence of smartness in various fields including medical science, forensics and security, remote monitoring of human activities has gained more interests in research. The ambulatory health monitoring services includes monitoring the activities of mentally challenged and elderly people. In this research paper, we propose a novel framework for activity recognition from video sequences captured from static cameras and those captured from UAVs. The proposed framework, named HARDeep, consists of three models: an optional scene stabilisation model for UAV captured video sequences, a human detection model leveraging YOLOv3, and, to extract the set of video frames containing humans, an activity recognition model leveraging the ensemble of three deep learning models: GoogleNet, ResNet-50, and ResNet-101. HARDeep is evaluated against three datasets including Hollywood2, KTH and the UCF-ARG dataset, consisting of video sequences captured from UAVs. The recognition accuracies are compared with the various inference models leveraging wide learning paradigms. Copyright © 2023 Inderscience Enterprises Ltd.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Hybrid RMDL-CNN for speech recognition from unclear speech signal

引用

International Journal of Speech Technology 2025年第1期28卷 195-217页

作者： Bhargava, Raja Arivazhagan, N. Babu, Kunchala Suresh Research Scholar Department of Computer Science and Engineering SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computer Science and Engineering Potti Sriramulu Chaluvadi Mallikarjuna Rao college of Engineering and Technology Andhra Pradesh Vijayawada India

ASR is an effectual approach, which converts human speech into computer actions or text format. It involves extracting and determining the noise feature, the audio model, and the language model. The extraction and determination of the noise feature is a crucial aspect of speech recognition, serving as both a process of information compression and signal deconvolution. ASR schemes are mostly employed in smart homes, smart appliances, and biometric schemes. Yet, traditional approaches offer very low performance because of a noisy environment. Moreover, local differences and accents negatively influence the ASR scheme execution during the conversion of the speech signals. This paper introduces a hybrid RMDL-CNN method to address these challenges. At first, the input of unclear speech is carried out by the dataset. Then, signal pre-processing is done by employing a Gaussian filter. After that, voice enhancement is accomplished by employing nonlinear spectral subtraction. Later, the speech word is segmented from the enhanced output based on the Attentional Encoder-Decoder approach and finally, the speech is recognized using the proposed RMDL-CNN. The RMDL-CNN method is devised by the combination of RMDL and CNN. Furthermore, the established RMDL-CNN is accessed for its efficiency based on several values of k-group value, as well as learning data. In addition, the introduced RMDL-CNN approach for speech recognition achieved better accuracy, PPV, as well as NPV of 0.909, 0.947, and 0.917 for dataset 1. Moreover, the RMDL-CNN has achieved the highest accuracy of 0.909, PPV of 0.926 and NPV of 0.888 for dataset 2. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Learning continuous network emerging dynamics from scarce observations via data-adaptive stochastic processes

引用

science China(Information sciences) 2024年第12期67卷 240-255页

作者： Jiaxu CUI Qipeng WANG Bingyi SUN Jiming LIU Bo YANG College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Public Computer Education and Research Center Jilin University Department of Computer Science Hong Kong Baptist University

Learning network dynamics from the empirical structure and spatio-temporal observation data is crucial to revealing the interaction mechanisms of complex networks in a wide range of domains. However,most existing methods only aim at learning network dynamic behaviors generated by a specific ordinary differential equation instance, resulting in ineffectiveness for new ones, and generally require dense *** observed data, especially from network emerging dynamics, are usually difficult to obtain, which brings trouble to model learning. Therefore, learning accurate network dynamics with sparse, irregularly-sampled,partial, and noisy observations remains a fundamental challenge. We introduce a new concept of the stochastic skeleton and its neural implementation, i.e., neural ODE processes for network dynamics(NDP4ND), a new class of stochastic processes governed by stochastic data-adaptive network dynamics, to overcome the challenge and learn continuous network dynamics from scarce observations. Intensive experiments conducted on various network dynamics in ecological population evolution, phototaxis movement, brain activity, epidemic spreading, and real-world empirical systems, demonstrate that the proposed method has excellent data adaptability and computational efficiency, and can adapt to unseen network emerging dynamics, producing accurate interpolation and extrapolation with reducing the ratio of required observation data to only about 6% and improving the learning speed for new dynamics by three orders of magnitude.

关键词： complex networks network dynamics emerging spatio-temporal dynamics neural processes

来源：评论

学校读者我要写书评

暂无评论

Deep Neural Network Empowered Movie Recommender System Using Hesitant Fuzzy Bi Objective Clustering

引用

Journal of The Institution of Engineers (India): Series B 2024年 1-11页

作者： Shrivastava, Vineet Kumar, Suresh Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Haryana Faridabad India

The movie recommender system is a highly influential and practical tool that assists individuals in efficiently choosing films to watch. Although recommender systems have been extensively used in academic research for various objectives, such as suggesting movies and recommending books, there has been a lack of focus on providing personalized movie recommendations for individual users. This research presents a new method for recommending movies that combines the Hesitant Fuzzy Clustering technique with a Convolutional Spiking Neural Network Movie Recommender System. The first phase entails obtaining input data from benchmark datasets such as MovieLens 100 K and MovieLens 1 M. These datasets are analysed using Ternary Pattern and Discrete Wavelet Transforms along with Hesitant Fuzzy Bi-objective Clustering technique to choose clusters depending on the retrieved attributes. After that, recommendation of movies uses a Deep Convolutional Spiking Neural Network to forecast user preferences. The efficiency of the proposed model is specifically compared to recent existing methods, like the Multi-Model Trust Based Movie Recommender Scheme (MT-ML-MRS) and the Graph-Dependent Hybrid Movie Recommendation Scheme (GHRS-MRS), particularly for movie recommendations. The results demonstrate a substantial enhancement, as the suggested model achieves 2.30% and 4.71% greater accuracy for MovieLens 100 k and MovieLens 1 M datasets respectively. The proposed system shows significant improvement over some traditional recommendation models indicating avenues for future research in scalable and intricate systems. © The Institution of Engineers (India) 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Online Convex Optimization with Switching Cost and Delayed Gradients

引用

Performance Evaluation Review 2024年第4期51卷 22-23页

作者： Senapati, Spandan Vaze, Rahul Department of Computer Science & Engineering Indian Institute of Technology Kanpur India School of Technology and Computer Science Tata Institute of Fundamental Research India

We consider the online convex optimization (OCO) problem with quadratic and linear switching cost when at time t only gradient information for functions fτ, τ 16(Lµ+5) for the quadratic switching cost, and also show the bound to be order-wise tight in terms of L, µ. In addition, we show that the competitive ratio of any online algorithm is at least max{Ω(L), Ω(pLµ )} when the switching cost is quadratic. For the linear switching cost, the competitive ratio of the OMGD algorithm is shown to depend on both the path length and the squared path length of the problem instance, in addition to L, µ, and is shown to be order-wise, the best competitive ratio any online algorithm can achieve. Copyright is held by author/owner(s).

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Enhanced mayfly with active elite approach clustering based deep Q learner routing with EBRLWE for IoT-based healthcare monitoring system

引用

Multimedia Tools and Applications 2024年第39期83卷 87129-87152页

作者： Balakrishnan, D. Rajkumar, T. Dhiliphan Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Anand Nagar Tamilnadu Krishnankoil India

IoT-based healthcare (HC) systems face security and efficiency challenges. Existing solutions, such as secure transmission models, enhanced security protocols, and secure frameworks, neglect patient authentication and rely on resource-intensive cryptography, leading to vulnerabilities and increased energy consumption. The use of Exponential Key-based Elliptical Curve Cryptography (EKECC) in previous work raises concerns about its long-term viability against quantum computing threats. Additionally, the Path-Weighted Q Reinforcement Learning (PWQRL) technique is limited to discrete action spaces, hindering its applicability in IoT-based HC systems with continuous action spaces. To address these issues, Enhanced Mayfly with Active elite approach Clustering based Deep Q Learner Routing with Enhanced Binary ring-learning-with-errors (EMACDQLEB) protocol is proposed in this paper. EMACDQLEB incorporates a quantum-resistant cryptographic scheme based on Enhanced Binary Ring-Learning-with-Errors (EBRLWE) and a routing algorithm using Deep Q-Networks (DQN). EBRLWE employs an additional encryption key to enhance data security against quantum threats. DQN enables optimal path selection for data transmission by using a Deep Neural Network (DNN) to approximate the Q-value function, improving routing efficiency. Experimental results show that EMACDQLEB outperforms previous methods in average energy consumption, reliability, and communication overhead. This paper aims to mitigate vulnerabilities and improve the HC infrastructure in the IoT era. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

FSCIL-EACA: Few-Shot Class-Incremental Learning Network Based on Embedding Augmentation and Classifier Adaptation for Image Classification

引用

Chinese Journal of Electronics 2024年第1期33卷 139-152页

作者： Ruru ZHANG Haihong E Meina SONG School of Computer Science Beijing University of Posts and Telecommunications Education Department Information Network Engineering Research Center Beijing University of Posts and Telecommunications

The ability to learn incrementally is critical to the long-term operation of AI systems. Benefiting from the power of few-shot class-incremental learning(FSCIL), deep learning models can continuously recognize new classes with only a few samples. The difficulty is that limited instances of new classes will lead to overfitting and exacerbate the catastrophic forgetting of the old classes. Most previous works alleviate the above problems by imposing strong constraints on the model structure or parameters, but ignoring embedding network transferability and classifier adaptation(CA), failing to guarantee the efficient utilization of visual features and establishing relationships between old and new classes. In this paper, we propose a simple and novel approach from two perspectives: embedding bias and classifier bias. The method learns an embedding augmented(EA) network with cross-class transfer and class-specific discriminative abilities based on self-supervised learning and modulated attention to alleviate embedding bias. Based on the adaptive incremental classifier learning scheme to realize incremental learning capability,guiding the adaptive update of prototypes and feature embeddings to alleviate classifier bias. We conduct extensive experiments on two popular natural image datasets and two medical datasets. The experiments show that our method is significantly better than the baseline and achieves state-of-the-art results.

关键词： Few-shot class-incremental learning Embedding augmentation Classifier adaptation Image classification

来源：评论

学校读者我要写书评

暂无评论

OptiFog: A Framework for Acquiring State Information and Predicting Resource Availability for Task Offloading in Cooperative Fog-Networks

引用

IEEE Transactions on Services Computing 2024年 1-13页

作者： Alam, Mehbub Ahmed, Nurzaman Ghosh, Shyamal Matam, Rakesh Barbhuiya, Ferdous Ahmed Department of Computer Science and Engineering Indian Institute of Information Technology Guwahati India Department of Computer Science Dartmouth College Hanover USA School of Data Science Indian Institute of Science Education and Research Thiruvananthapuram India

The primary objective of fog computing is to minimize the reliance of IoT devices on the cloud by leveraging the resources of fog network. Typically, IoT devices offload computation tasks to fog to meet different task requirements such as latency in task execution, computation costs, etc. So, selecting such a fog node that meets task requirements is a crucial challenge. To choose an optimal fog node, access to each node's resource availability information is essential. Existing approaches often assume state availability or depend on a subset of state information to design mechanisms tailored to different task requirements. In this paper, OptiFog: a cluster-based fog computing architecture for acquiring the state information followed by optimal fog node selection and task offloading mechanism is proposed. Additionally, a continuous time Markov chain based stochastic model for predicting the resource availability on fog nodes is proposed. This model prevents the need to frequently synchronize the resource availability status of fog nodes, and allows to maintain an updated state information. Extensive simulation results show that OptiFog lowers task execution latency considerably, and schedules almost all the tasks at the fog layer compared to the existing state-of-the-art. IEEE

关键词： computer architecture

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：