检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Lu, Lin Zou, Qingzhi Key Laboratory of Computing Power Network and Information Se-curity Ministry of Education Shandong Computer Science Center Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9781665410205

Due to the exceptional performance of Transform-ers in 2D medical image segmentation, recent work has also introduced them into 3D medical segmentation tasks. For instance, Swin UNETR and other hierarchical Transformers have reintroduced prior knowledge from several convolutional networks, further enhancing the volume segmentation capabilities of models. The efficacy of these hybrid methodologies is primarily attributed to the substantial quantity of parameters and the nonlocal self-attention mechanism with a large receptive field. We argue that the behavior of these methods' large receptive fields can be simulated by employing fewer parameters through the utilization of depth-wise convolutions with large kernel. Within this manuscript, we introduce a lightweight volume segmentation model called MedX-Net, which uses convolutional network modules to simulate hierarchical Transformers for robust volume segmentation. Firstly, inspired by the hierarchical Transformer module of Swin UNETR, we investigate large-kernel depth-wise convolutions with different sizes to achieve a reduced model parameter count while maintaining a large global receptive field. Secondly, we replace the multilayer perceptron (MLP) in the hierarchical Transformer module with Inverted Bottleneck with Depthwise Convolution Enhancement(DWCE) to improve model performance with fewer activation and normalization layers, further reducing the parameter count. We validate the effectiveness and efficiency of our model for volume segmentation on three public datasets: Synapse, BTCV and ACDC. On the Synapse dataset, compared to Swin UNETR, our model achieves an improvement from 83.48% to 87.21% in Dice score. Compared to the result of 86.57% achieved by nnFormer, our model achieves superior performance while reducing the model parameter count by 64%. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

A New Approach to Road Incident Detection Leveraging Live Traffic Data: An Empirical Investigation 2

A New Approach to Road Incident Detection Leveraging Live Tr...

引用

2nd International Conference on Machine Learning and Data Engineering, ICMLDE 2023

作者： Kumar Gannina, Aswin Ram Jaffarullah, Aadhil Ahamed Reddy, Tiyyagura Mohit Subba Reddy, Sabbella Manoj Vikas, Ambati Sai Mathi, Senthilkumar Ramalingam, Venkadeshan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Faculty in Information Technology Department University of Technology and Applied Sciences-Shinas Oman

Accidents can have a significant impact on road safety and the efficiency of transport. With the ever-increasing number of vehicles on the road, it is crucial to quickly detect and respond to such events to decrease the impact. The current paper presents a road accident and incident detection solution utilizing traffic API monitoring and continuously analyzing real-time traffic data from various sources like GPS-enabled devices. Consequently, the proposed approach can identify abnormal patterns in the movement of vehicles, such as unexpected road closures or an accident. It numerically analyzes the traffic pattern and identifies incidents and accidents using live traffic data collected from the map service. When the approach identifies any abnormality, it can immediately let the user know, allowing them to act accordingly. It can facilitate authorities in identifying accident-prone areas and deploy safety measures. This can help law enforcement agencies to identify drivers at risk of causing accidents and implement education and enforcement programs targeted towards them. Hence, the proposed approach can aid in reducing the negative impact of traffic incidents, and the public can respond to these incidents more preparedly. © 2024 Elsevier B.V.. All rights reserved.

关键词： Accidents

来源：评论

学校读者我要写书评

暂无评论

IAMS-Net: An Illumination-Adaptive Multi-Scale Lesion Segmentation Network

IAMS-Net: An Illumination-Adaptive Multi-Scale Lesion Segmen...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Zheng, Yisen Huang, Guoheng Zhang, Feng Cheng, Lianglun Yuan, Xiaochen Zhong, Guo Luo, Shenghong School of Computer Science and Technology Guangdong University of Technology Guangzhou China The First Affiliated Hospital of Sun Yat-Sen University Department of Otorhinolaryngology Guangzhou China Macao Polytechnic University Faculty of Applied Sciences China School of Information Science and Technology Guangdong University of Foreign Studies Guangzhou China University of Macau Faculty of Science and Technology China

ISBN: (纸本)9781665410205

In recent years, many Lesion segmentation (LS) models based on UNet have been proposed. However, existing researches rarely consider the influence of illumination change leads to the weak boundary area. Such as melanomas and polyps, the demarcation of the boundary between the diseased area and the surrounding tissue remains particularly challenging. To overcome these challenges, we propose an IlluminationAdaptive Multi-scale Lesion Segmentation Network (IAMS-Net). In IAMS-Net, we integrate Illumination-Adaptive MultiStream Attention (IAMA) and Contour Perception Module (CPM). In the decoding stage, the IAMA is used as a bridge between the encoder and the decoder to solve the adverse effects of illumination changes on the segmentation of weak boundary lesions. In order to further enhance the boundary features lost due to illumination change in the low-contrast lesion area, we introduce the CPM to improve the perception of the integrity of the lesion area. Subsequently, we performed comparison and ablation experiments using the publicly available ISIC2018 dataset and the individually collected data set BoreIllumination(BI). © 2024 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Meta-heuristics for Feature Selection and Classification in Diagnostic Breast Cancer

引用

computers, Materials & Continua 2022年第10期73卷 749-765页

作者： Doaa Sami Khafaga Amel Ali Alhussan El-Sayed M.El-kenawy Ali E.Takieldeen Tarek M.Hassan Ehab A.Hegazy Elsayed Abdel Fattah Eid Abdelhameed Ibrahim Abdelaziz A.Abdelhamid Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Faculty of Artificial Intelligence Delta University for Science and TechnologyMansoura35712Egypt Communications and Computers Engineering Department Faculty of EngineeringDelta University for Science and TechnologyInternational Coastal RoadGamasa CityDakhliyaEgypt Faculty of Applied Health Science Technology Delta University for Science and TechnologyMansoura35712Egypt Faculty of Medicine Head of Internal Medicine DepartmentDelta University for Science and TechnologyMansouraEgypt Computer Engineering and Control Systems Department Faculty of EngineeringMansoura University35516MansouraEgypt Department of Computer Science Faculty of Computer and Information SciencesAin Shams University11566CairoEgypt Department of Computer Science College of Computing and Information TechnologyShaqra University11961Saudi Arabia

One of the most common kinds of cancer is breast *** early detection of it may help lower its overall rates of *** this paper,we robustly propose a novel approach for detecting and classifying breast cancer regions in thermal *** proposed approach starts with data preprocessing the input images and segmenting the significant regions of *** addition,to properly train the machine learning models,data augmentation is applied to increase the number of segmented regions using various scaling *** the other hand,to extract the relevant features from the breast cancer cases,a set of deep neural networks(VGGNet,ResNet-50,AlexNet,and GoogLeNet)are *** resulting set of features is processed using the binary dipper throated algorithm to select the most effective features that can realize high classification *** selected features are used to train a neural network to finally classify the thermal images of breast *** achieve accurate classification,the parameters of the employed neural network are optimized using the continuous dipper throated optimization *** results show the effectiveness of the proposed approach in classifying the breast cancer cases when compared to other recent approaches in the ***,several experiments were conducted to compare the performance of the proposed approach with the other *** results of these experiments emphasized the superiority of the proposed approach.

关键词： Breast cancer image segmentation dipper throated optimization feature selection meta-heuristics

来源：评论

学校读者我要写书评

暂无评论

An Empirical Investigation on Employing Machine Learning for Balancing Home Agent Loads in Next Generation IP Mobility 2

An Empirical Investigation on Employing Machine Learning for...

引用

2nd International Conference on Machine Learning and Data Engineering, ICMLDE 2023

作者： Khatri, Anshu Mathi, Senthilkumar Ashiq Sheriff, A. Deepthika, R. Naveen Raaghavendran, G. Ramalingam, Venkadeshan Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Coimbatore India Faculty in Information Technology Department University of Technology and Applied Sciences-Shinas Oman

Mobile IPv6 is a key technology to enable the mobility of devices on next-generation internet protocol networks. Home agents provide simple services to registered mobile nodes. In addition, the use of multiple domestic operators for load-balancing devices faces problems of synchronization and signalling overhead. Thus, most of the existing load balancing methods present a significant delay in the transmission of data packets. The machine learning approach provides an efficient hardware storage solution for balancing the load of the home agent by improving the state-work schedule. It provides a method for dynamic load balancing based on the research-consumption system. Thus, the present paper investigates the use of machine learning, specifically reinforcement learning, to enhance home agent load balancing in next-generation IP traffic. The reinforcement learning-based home agent decisions, guided by mobile node speed and registration queries, reduce latency, improve network performance, and provide dynamic solutions. The proposed method significantly reduces the delay for packet delivery by balancing the home agent load with the incorporation of reward parameters. The empirical investigation found a remarkable improvement in network reliability, as manifested by a 2.31% increase in packet delivery ratio compared to systems with existing methods. © 2024 Elsevier B.V.. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Inter-Stream Dependencies in Time-Sensitive Networking 28

Inter-Stream Dependencies in Time-Sensitive Networking

引用

28th Conference on Innovation in Clouds, Internet and Networks, ICIN 2025

作者： Chahed, Hamza Yarvis, Mark Frick, Florian Kassler, Andreas Intel Deutschland GmbH Germany Intel Corporation United States Department of Mathematics and Computer Science Karlstad University Karlstad Sweden Institute for Control Technology of Machine Tools and Manufacturing Equipment University of Stuttgart Germany Faculty of Applied Computer Science Deggendorf Institute of Technology Deggendorf Germany

ISBN: (纸本)9798331542399

Effective configuration of Time-Sensitive Networks is crucial for providing timeliness and reliability guarantees for real-time industrial applications, where many inter-dependent streams may co-exist. However, existing methods for specifying the characteristics of real-time streams to the Centralized Network Configuration element (CNC) do not allow the specification of stream dependencies. Consequently, the CNC may schedule the real-time streams in a sub-optimal way, leading to low number of real-time applications supported. To address this pressing issue, we present methods that allow to model and express such inter-stream dependencies and propose extensions to the user network interface (UNI) to convey these dependencies to the CNC, transforming it into an intent-based UNI. We define a novel metric to evaluate a specific network configuration regarding the latency budget available for scheduling the transmission of a stream. Using a set of numerical simulations, we show that when exploiting the knowledge of inter-stream dependencies, we can derive better network schedules, which results in significant increase in applications onboarding up to 2.2x and increased network utilization for real-time streams up to 3x. © 2025 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Recognition and Classification of Apple and Sugarcane Plant Leaf Diseases using SVM with DAE Models 2

Recognition and Classification of Apple and Sugarcane Plant ...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Sunil Kumar, V. Jyothi, A.P. Sumanth, S. Nagamani, H.S. Nitte Meenakshi Institute of Technology Department of Artificial Intelligence and Machine Learning Bengaluru India Ramaiah University of Applied Sciences Faculty of Engineering and Technology Department of Cse Peenya Bengaluru India Department of Computer Science and Computer Applications Kolar India Department of Computer Science Karnataka Bengaluru India

ISBN: (纸本)9798350382952

For this leaf disease study, apple and sugarcane plants are identified and classified using a mix of character features and in-depth automated coding. Farm sugar cane leaves were copied for the online apple Plant Village Dataset. Pre-process images to reduce size and improve HLG filters. Image segmentation using DWT and GLCM feature extraction follows. Like the Low-Low (LL) band, DWT images produce 4-orthogonal subbands. Deep Auto Encoder and SVM algorithms retrieved subgroup functions and identified diseases from training data. If classification findings are ignored, the division stage receives data with HL, LH, and HH bands to explain approach consistency. Deep Auto encoder classifies illness using training data after extracting sub-band features. The Auto Encoder and SVM classifier demonstrated that the proposed model outperformed alternatives in LL band. Other subbands performed worse than the LL band. This study found that LL sub band data provided fine image data for better sickness categorization than HH, HL, and LH sub band data. © 2024 IEEE.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Video Summarization Approach Based on Binary Robust Invariant Scalable Keypoints and Bisecting K-Means

引用

computers, Materials & Continua 2024年第3期78卷 3565-3583页

作者： Sameh Zarif Eman Morad Khalid Amin Abdullah Alharbi Wail S.Elkilani Shouze Tang Department of Information Technology Faculty of Computers and InformationMenoufia UniversityMenoufia32511Egypt Department of Artificial Intelligence Faculty of Artificial IntelligenceEgyptian Russian UniversityBader11829Egypt Department of Computer Science Community CollegeKing Saud UniversityRiyadh11362Saudi Arabia College of Applied Computer Science King Saud UniversityAl-Muzahmiya19676Saudi Arabia School of Communication and Information Engineering Chongqing University of Posts and TelecommunicationsChongqing400065China

Due to the exponential growth of video data,aided by rapid advancements in multimedia *** became difficult for the user to obtain information from a large video *** process of providing an abstract of the entire video that includes the most representative frames is known as static video *** method resulted in rapid exploration,indexing,and retrieval of massive video *** propose a framework for static video summary based on a Binary Robust Invariant Scalable Keypoint(BRISK)and bisecting K-means clustering *** current method effectively recognizes relevant frames using BRISK by extracting keypoints and the descriptors from video *** video frames’BRISK features are clustered using a bisecting K-means,and the keyframe is determined by selecting the frame that is most near the cluster *** applying any clustering parameters,the appropriate clusters number is determined using the silhouette *** were carried out on a publicly available open video project(OVP)dataset that contained videos of different *** proposed method’s effectiveness is compared to existing methods using a variety of evaluation metrics,and the proposed method achieves a trade-off between computational cost and quality.

关键词： BRISK bisecting K-mean video summarization keyframe extraction shot detection

来源：评论

学校读者我要写书评

暂无评论

Innovative Approaches to Arabic Author Identification: A Comprehensive Evaluation of Classical and Deep Learning Approaches 2

Innovative Approaches to Arabic Author Identification: A Com...

引用

2nd International Conference of Intelligent Methods, Systems and Applications, IMSA 2024

作者： Almanaseer, Waref Alsekait, Deema Mohammed Gomaa, Ibrahim A Zeid, Magdy Abd-Elghany Abdelaziz, Amr Elsabbagh, Belal Essam, George Nader, Nour Abdelminaam, Diaa Salama Applied Science Private University Faculty of Information Technology Amman11931 Jordan Applied College Princess Nourah Bint Abdulrahman University Department of Computer Science and Information Technology Riyadh11671 Saudi Arabia Alobour high institute for computer and informatics Computer Science Department Cairo Egypt Misr International University Faculty of Computer Science Cairo Egypt Jadara University Jadara Research Center Irbid21110 Jordan Benha University Faculty of Computers and Artificial Intelligence Benha Egypt MEU Research Unit Middle East University Amman11831 Jordan

ISBN: (纸本)9798350362633

The amount of written text on the internet has grown exponentially. When pairing that with the difficulties in sourcing the author of a text, a need emerges to be able to verify claimed author of text and attribute anonymous text to its author. These tasks fall under the umbrella of author identification, which is the process of identifying who, among a set of authors, wrote a given text. For many reasons, it is a challenging task in the field of Natural Language Processing (NLP). This paper compares the performance of different machine learning and deep learning models on the task of Arabic author identification between. The results surprisingly show that most models failed except for the feedforward neural network and Convolutional Neural Network (CNN). © 2024 IEEE.

关键词： Arabic Deep Learning Machine Learning Natural Language Processing

来源：评论

学校读者我要写书评

暂无评论

Classification Models and Variable Selection for SME Credit Risk Assessment in Balance the Data Set 10

Classification Models and Variable Selection for SME Credit ...

引用

10th International Conference on Digital Arts, Media and technology and 8th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications Engineering, ECTI DAMT and NCON 2025

作者： Intharasompong, Sornthun Jitpattanakul, Anuchit Mekruksavanich, Sakorn Wongwiwat, Piyada Phaphan, Wikanda King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Applied Statistics Bangkok10800 Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Mathematics Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Thailand University of Phayao School of Information and Communication Department of Computer Engineering 56000 Thailand Suansunandha Rajabhat University Faculty of Science and Technology Bangkok10800 Thailand Research Group in Statistical Learning and Inference Thailand

ISBN: (纸本)9798331543273

Small and medium-sized enterprises (SMEs) are frequently considered high credit risk, making it difficult to obtain loans from banks. A viable substitute for assessing borrower creditworthiness more impartially is using machine learning-based credit risk assessment (CRA) algorithms. This study evaluated the performance of five machine learning techniques: decision tree, support vector machine, gradient boosting, K-nearest neighbor, and Naïve Bayes. We evaluated each model with K-fold cross-validation and utilized the Stepwise selection method for the variable selection. To address the underlying data imbalance, we balanced the dataset with the SMOTE technique, which showed that normal loans were more widespread than Non-Performing Loans (NPLs). After balancing the data, the Gradient Boosting model displayed the best accuracy, F-measure, and robustness without variable selection, making it the most effective model for predicting SME loans. © 2025 IEEE.

关键词： Risk assessment

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

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

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：