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

Refined Anam-Net:Lightweight Deep Learning Model for Improved Segmentation Performance of Optic Cup and Disc for Glaucoma Diagnosis

引用

computers, Materials & Continua 2024年第7期80卷 1381-1405页

作者： Khursheed Aurangzeb Syed Irtaza Haider Musaed Alhussein Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityP.O.Box 51178Riyadh11543Saudi Arabia

In this work,we aim to introduce some modifications to the Anam-Net deep neural network(DNN)model for segmenting optic cup(OC)and optic disc(OD)in retinal fundus images to estimate the cup-to-disc ratio(CDR).The CDR is a reliable measure for the early diagnosis of *** this study,we developed a lightweight DNN model for OC and OD segmentation in retinal fundus *** DNN model is based on modifications to Anam-Net,incorporating an anamorphic depth embedding *** reduce computational complexity,we employ a fixed filter size for all convolution layers in the encoder and decoder stages as the network *** modification significantly reduces the number of trainable parameters,making the model lightweight and suitable for resource-constrained *** evaluate the performance of the developed model using two publicly available retinal image databases,namely RIM-ONE and *** results demonstrate promising OC segmentation performance across most standard evaluation metrics while achieving analogous results for OD *** used two retinal fundus image databases named RIM-ONE and Drishti-GS that contained 159 images and 101 retinal images,*** OD segmentation using the RIM-ONE we obtain an f1-score(F1),Jaccard coefficient(JC),and overlapping error(OE)of 0.950,0.9219,and 0.0781,***,for OC segmentation using the same databases,we achieve scores of 0.8481(F1),0.7428(JC),and 0.2572(OE).Based on these experimental results and the significantly lower number of trainable parameters,we conclude that the developed model is highly suitable for the early diagnosis of glaucoma by accurately estimating the CDR.

关键词： Refined Anam-Net parameter tuning deep learning optic cup optic disc cup-to-disc ratio glaucoma diagnosis

来源：评论

学校读者我要写书评

暂无评论

Drug-Target Interactions Prediction Based on Signed Heterogeneous Graph Neural Networks

引用

Chinese Journal of Electronics 2024年第1期33卷 231-244页

作者： Ming CHEN Yajian JIANG Xiujuan LEI Yi PAN Chunyan JI Wei JIANG College of Information Science and Engineering Hunan Normal University School of Computer Science Shaanxi Normal University Faculty of Computer Science and Control Engineering Shenzhen Institute of Advanced TechnologyChinese Academy of Sciences Computer Science Department BNU-HKBU United International College

Drug-target interactions(DTIs) prediction plays an important role in the process of drug *** computational methods treat it as a binary prediction problem, determining whether there are connections between drugs and targets while ignoring relational types information. Considering the positive or negative effects of DTIs will facilitate the study on comprehensive mechanisms of multiple drugs on a common target, in this work, we model DTIs on signed heterogeneous networks, through categorizing interaction patterns of DTIs and additionally extracting interactions within drug pairs and target protein pairs. We propose signed heterogeneous graph neural networks(SHGNNs), further put forward an end-to-end framework for signed DTIs prediction, called SHGNN-DTI,which not only adapts to signed bipartite networks, but also could naturally incorporate auxiliary information from drug-drug interactions(DDIs) and protein-protein interactions(PPIs). For the framework, we solve the message passing and aggregation problem on signed DTI networks, and consider different training modes on the whole networks consisting of DTIs, DDIs and PPIs. Experiments are conducted on two datasets extracted from Drug Bank and related databases, under different settings of initial inputs, embedding dimensions and training modes. The prediction results show excellent performance in terms of metric indicators, and the feasibility is further verified by the case study with two drugs on breast cancer.

关键词： Drug-target interactions Signed heterogeneous network Link sign prediction Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Clustered Reinforcement Learning

引用

Frontiers of computer Science 2025年第4期19卷 43-57页

作者： Xiao MA Shen-Yi ZHAO Zhao-Heng YIN Wu-Jun LI National Key Laboratory for Novel Software Technology Department of Computer Science and TechnologyNanjing UniversityNanjing 210023China Department of Electrical Engineering and Computer Sciences University of CaliforniaBerkeleyCA 94720-1770USA

Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.

关键词： deep reinforcement learning exploration count-based method clustering K-means

来源：评论

学校读者我要写书评

暂无评论

Received Power Based Unmanned Aerial Vehicles (UAVs) Jamming Detection and Nodes Classification Using Machine Learning

引用

computers, Materials & Continua 2023年第4期75卷 1253-1269页

作者： Waleed Aldosari Department of Computer Engineering College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia

This paper presents a machine-learning method for detecting jamming UAVs and classifying nodes during jamming attacks onWireless Sensor Networks(WSNs).Jamming is a type of Denial of Service(DoS)attack and intentional interference where a malicious node transmits a high-power signal to increase noise on the receiver side to disrupt the communication channel and reduce performance *** defend and prevent such attacks,the first step is to detect *** current detection approaches use centralized techniques to detect jamming,where each node collects information and forwards it to the base *** a result,overhead and communication costs *** this work,we present a jamming attack and classify nodes into different categories based on their location to the jammer by employing a single node *** a result,we introduced a machine learning model that uses distance ratios and power received as features to detect such ***,we considered several types of jammers transmitting at different power levels to evaluate the proposed metrics using *** a detection accuracy of 99.7%for the k-nearest neighbors(KNN)algorithm and average testing accuracy of 99.9%,the presented solution is capable of efficiently and accurately detecting jamming attacks in wireless sensor networks.

关键词： Jamming attacks machine learning unmanned aerial vehicle(UAV) WSNs

来源：评论

学校读者我要写书评

暂无评论

Enhancing English accent identification in automatic speech recognition using spectral features and hybrid CNN-BiLSTM model

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Ahmed, Ghayas Lawaye, Aadil Ahmad Jain, Vishal Chatterjee, Jyotir Moy Mahajan, Shubham Department of Computer Sciences Baba Ghulam Shah Badshah University J&K Rajouri India Department of Computer Science & Engineering Sharda University Noida India Dehradun India Department of Computer Science & Engineering Amity University Haryana India

Automatic Speech Recognition (ASR) has been the regnant research area in the domain of Natural Language Processing for the last few decades. Past years’ advancement provides progress in this area of research. The accent of spoken is the prominent factor affecting the performance of ASR. Accent is the pronunciation of a word in a distinct way which may vary from specimen to specimen depending upon their social class, formality, age, vocal property, gender, geography, and influence of native or other language. Recognizing an accent requires various complex characteristics and features of voice such as voice quality, prosody, and phoneme pronunciation which are difficult to extract and analyze. To solve these difficulties, the researchers focus their attention on spectral representation such as Mel Spectrogram and Mel-Frequency Cepstral Coefficient (MFCC). In this study, we will analyze which features achieve maximum accuracy for the English accent classification task. Here in this work, we perform our experiments on Log Mel filter bank and MFCC features with four different window function. We extract features from raw audio with various windowing function and train a hybrid model of Convolutional Neural Network and Bidirectional Long Short-term Memory network (CNN-BiLSTM) on a custom dataset having nine different accents of English language namely American, Australian, British, Indian (Oriya, Bangla, Telegu, Malayalam), and Welsh. The accuracy of each feature is evaluated and compared. The log Mel filter bank outputs the highest accuracy of 99.75% and 99.91% of training and validation with Han window function while MFCC with Bartlett window function achieves 99.98% of training and 99.33% of validation accuracy. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Spectrographs

来源：评论

学校读者我要写书评

暂无评论

RSSI-Based 3D Wireless Sensor Node Localization Using Hybrid T Cell Immune and Lotus Optimization

引用

computers, Materials & Continua 2024年第12期81卷 4833-4851页

作者： Weiwei Hu Kiran Sree Pokkuluri Rajesh Arunachalam Bander A.Jabr Yasser A.Ali Preethi Palanisamy School of Information Engineering Technology&MediaUniversity of HenanKaifeng475004China Department of Computer Science and Engineering Shri Vishnu Engineering College forWomenBhimavaram534202Andhra PradheshIndia Department of Electronics and Communication Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesThandalam602105ChennaiIndia Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Science and Engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical SciencesThandalam602105ChennaiIndia

Wireless Sensor Network(WSNs)consists of a group of nodes that analyze the information from surrounding *** sensor nodes are responsible for accumulating and exchanging ***,node local-ization is the process of identifying the target node’s *** this research work,a Received Signal Strength Indicator(RSSI)-based optimal node localization approach is proposed to solve the complexities in the conventional node localization ***,the RSSI value is identified using the Deep Neural Network(DNN).The RSSI is conceded as the range-based method and it does not require special hardware for the node localization process,also it consumes a very minimal amount of cost for localizing the nodes in 3D *** position of the anchor nodes is fixed for detecting the location of the ***,the optimal position of the target node is identified using Hybrid T cell Immune with Lotus Effect Optimization algorithm(HTCI-LEO).During the node localization process,the average localization error is minimized,which is the objective of the optimal node *** the regular and irregular surfaces,this hybrid algorithm effectively performs the localization *** suggested hybrid algorithm converges very fast in the three-dimensional(3D)*** accuracy of the proposed node localization process is 94.25%.

关键词： Sensor node localization received signal strength indicator 3D wireless sensor network deep neural network average localization error and hybrid T cell immune with lotus effect optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation and Random Multi-Model Deep Learning for Data Classification

引用

computers, Materials & Continua 2023年第3期74卷 5191-5207页

作者： Fatma Harby Adel Thaljaoui Durre Nayab Suliman Aladhadh Salim EL Khediri Rehan Ullah Khan Computer Science Department Future Academy-Higher Future Institute for Specialized Technological StudiesEgypt Department of Computer Systems Engineering Faculty of Electrical and Computer EngineeringUniversity of Engineering and TechnologyPeshawar25120Pakistan Department of Information Technology College of ComputerQassim UniversityBuraydahSaudi Arabia Department of Computer Sciences Faculty of Sciences of GafsaUniversity of GafsaGafsaTunisia

In the machine learning(ML)paradigm,data augmentation serves as a regularization approach for creating ML *** increase in the diversification of training samples increases the generalization capabilities,which enhances the prediction performance of classifiers when tested on unseen *** learning(DL)models have a lot of parameters,and they frequently ***,to avoid overfitting,data plays a major role to augment the latest improvements in ***,reliable data collection is a major limiting ***,this problem is undertaken by combining augmentation of data,transfer learning,dropout,and methods of normalization in *** this paper,we introduce the application of data augmentation in the field of image classification using Random Multi-model Deep Learning(RMDL)which uses the association approaches of multi-DL to yield random models for *** present a methodology for using Generative Adversarial Networks(GANs)to generate images for data *** experiments,we discover that samples generated by GANs when fed into RMDL improve both accuracy and model *** across both MNIST and CIAFAR-10 datasets show that,error rate with proposed approach has been decreased with different random models.

关键词： Data augmentation generative adversarial networks classification machine learning random multi-model deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimized deep autoencoder and BiLSTM for intrusion detection in IoTs-Fog computing

引用

Multimedia Tools and Applications 2025年第8期84卷 4907-4943页

作者： Alqahtani, Abdullah Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University KSA Al-Kharj16278 Saudi Arabia

Our world is rapidly evolving toward the Internet of Things (IoT), that connects all gadgets to digital services and simplifies our lives. As IoT devices expand, network vulnerabilities may rise, leading to more network threats. An intrusion detection system (IDS) with low latency and high accuracy is essential in this dynamic IoT environment to identify threats. Many IDSs utilize deep learning (DL) methods, but adjusting parameters for different environments can be challenging. This work proposes an improved hybrid Deep autoencoder (DAE) and Bidirectional long short-term memory (BiLSTM) for fog item installation to protect vital networks from prompt and efficient malicious threat detection. Determining the hyperparameters of complicated DL networks is tough. Low accuracy, efficiency, and performance in high-dimensional models afflict existing approaches. Therefore, the Sparrow Search Optimization Algorithm (SSOA) is adopted to enhance model hyperparameters. Employing IoT-based data, we assess the effectiveness of our suggested model. The outcome of the experiment obtained by analyzing the suggested IDS utilizing CICIDS2017 and BoT-IoT datasets attested to their supremacy over modern systems that are currently available in terms of precision, accuracy, FAR, error rate, and detection rate (DR). To learn more about how well our model works, added two additional metrics: Cohen's Kappa coefficients and Mathew correlation. The proposed optimization model demonstrated its ability to work well with various platforms, adapt to changing requirements, and handle larger workloads. In addition, it is possible to enhance the intrusion detection rate by minimizing both the error rate and computational time. Based on the experiments conducted, the proposed method yields superior results in terms of detection accuracy and reduced latency. © 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

Enhancing the efficiency of lung cancer screening: predictive models utilizing deep learning from CT scans

引用

Neural Computing and Applications 2025年 1-19页

作者： Tawfeek, Medhat A. Alrashdi, Ibrahim Alruwaili, Madallah Shaban, Warda M. Talaat, Fatma M. Department of Computer Science Faculty of Computers and Information Menoufia University Shebin Elkom32511 Egypt Department of Computer Science College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Department of Computer Engineering and Networks College of Computer and Information Sciences Jouf University Sakakah Saudi Arabia Department of Communication and Electronics Engineering Nile Higher Institute for Engineering and Technology Mansoura Egypt Faculty of Artificial Intelligence Kafrelsheikh University Kafrelsheikh Egypt Faculty of Computer Science and Engineering New Mansoura University Gamasa35712 Egypt

Lung cancer is the most lethal form of cancer. This paper introduces a novel framework to discern and classify pulmonary disorders such as pneumonia, tuberculosis, and lung cancer by analyzing conventional X-ray and CT scan images called lung cancer risk prediction (LCRP) model. LCRP has four modules, namely data collection and preprocessing, data augmentation module, image segmentation module, and prediction module. Actually, LCRP employs three deep learning models;sequential model, functional model, and transfer model on publicly available training datasets. Convolutional neural networks (CNNs) have emerged as a highly effective field in machine learning, particularly for image datasets in the field of biomedical applications. The primary goal is to validate these models by comparing their performance with other models in order to determine their effectiveness in addressing challenging datasets. Our research has revealed a noteworthy enhancement in the efficiency of binary and multi-class classification using mask R-CNN image segmentation. During the model training process, a combination of Adam and stochastic gradient descent dual optimizers has been used to improve performance. LCRP have outperformed current pre-trained models by minimizing training parameters, computational costs, and overhead. It introduces 98.5% accuracy, 88.7% specificity, 89% sensitivity, 89.2% precision, and 89.09% F-measure. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Lung cancer

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：