检索结果-内蒙古大学图书馆

Improved Load-Balanced Clustering for Energy-Aware Routing(ILBC-EAR)in WSNs

computer Systems science & engineering 2023年第1期44卷 99-112页

作者： D.Loganathan M.Balasubramani R.Sabitha S.Karthik Department of Electronics and Communication Engineering Info Institute of EngineeringCoimbatore641107India Department of Computer Science and Engineering SNS College of TechnologyCoimbatore641035India

Sensors are considered as important elements of electronic *** many applications and service,Wireless Sensor Networks(WSNs)are involved in significant data sharing that are delivered to the sink node in energy efficient man-ner using multi-hop ***,the major challenge in WSN is the nodes are having limited battery resources,it is important to monitor the consumption rate of energy is very much ***,reducing energy con-sumption can increase the network lifetime in effective *** that,clustering methods are widely used for optimizing the rate of energy consumption among the sensor *** that concern,this paper involves in deriving a novel model called Improved Load-Balanced Clustering for Energy-Aware Routing(ILBC-EAR),which mainly concentrates on optimal energy utilization with load-balanced process among cluster heads and member *** providing equal rate of energy consumption among nodes,the dimensions of framed clusters are ***,the model develops a Finest Routing Scheme based on Load-Balanced Clustering to transmit the sensed info.mation to the sink or base *** evaluation results depict that the derived energy aware model attains higher rate of life time than other works and also achieves balanced energy rate among head ***,the model also provides higher throughput and minimal delay in delivering data packets.

关键词： Wireless sensor networks energy consumption load balanced clustering finest routing

来源：评论

学校读者我要写书评

暂无评论

SESAME: Toward Medical Image Segmentation via Foundation Model-assisted Semi-supervised Learning

SESAME: Toward Medical Image Segmentation via Foundation Mod...

引用

2024 IEEE International Conference on Bioinfo.matics and Biomedicine, BIBM 2024

作者： Hu, Qiyun Shen, Junao Ji, Jinkang Wang, Xinyu Feng, Tian Cui, Hui Zhejiang University School of Software Technology Hangzhou China La Trobe University Department of Computer Science and Info. Tech. Melbourne Australia

ISBN: (纸本)9798350386226

Medical image segmentation is essential for diagnosis but requires expensive and time-consuming labeled data. Semi-supervised learning (SSL) mitigates this issue by using unlabeled data to improve generalization. However, current SSL methods encounter issues with inadaptive perturbations and low-quality pseudo-labels. Vision foundation models, such as SAM, have shown promise in segmentation. We propose SESAME, an SSL method integrating SAM and U-Net to improve labeling accuracy through a foundation model-assisted pipeline. In particular, we introduce a reliability score to address low-quality pseudo-labels and employ strategies for utilizing both reliable and unreliable images. Reliable images are associated with refined pseudo-labels via a conflict resolving strategy, whereas unreliable ones undergo a mutual region swapping strategy. Extensive experiments demonstrate that our SESAME outperforms representative methods for medical image segmentation. © 2024 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Genetic Programming Models in computer-Aided Diagnosis of Skin Cancer Images 13

Exploring Genetic Programming Models in Computer-Aided Diagn...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Ain, Qurrat Ui Al-Sahaf, Harith Xue, Bing Zhang, Mengjie School of Engineering and Computer Science Victoria University of Wellington PO Box 600 Wellington New Zealand College of Engineering and Info. Technology AlShaab University Dep. of Cybersecurity Engineering Baghdad Iraq

ISBN: (纸本)9798350308365

Extracting important info.mation from complex skin lesion images is vital to effectively distinguish between different types of skin cancer images. In addition to providing high classification performance, such computer-aided diagnostic methods are needed where the models are interpretable and can provide knowledge about the discriminative features in skin lesion images. This underlying info.mation can significantly assist dermatologists in identifying a particular stage or type of cancer. With its flexible representation and global search abilities, Genetic Programming (GP) is an ideal learning al-gorithm to evolve interpretable models and identify important features with significant info.mation to discriminate between skin cancer classes. This paper provides an in-depth analysis of a recent GP-based feature learning method where different well-developed feature descriptors are integrated into the learning algorithms to extract high-level features for skin cancer image classification. The study explores the effectiveness of utilizing feature learning for this complex task and designing program structure to suit the problem domain as it has shown promising results compared to commonly used feature descriptors and an existing GP-based feature learning method developed for general image classification. This study analyzes the GP-evolved models to identify the prominent features and most effective feature descriptors important for the classification of these skin cancer images. The evolved models are interpretable, they provide knowledge that can assist dermatologists in making diagnoses in real-time clinical situations by identifying prominent skin cancer characteristics captured by the feature descriptors and learned during the evolutionary process. © 2024 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Securing the Silver Surfers: Cybersecurity Awareness Among Older Adults 19

Securing the Silver Surfers: Cybersecurity Awareness Among O...

引用

19th International Conference on Ubiquitous info.mation Management and Communication, IMCOM 2025

作者： Ahmad Nawi, Haslinda Sutan Omar, Siti Fatimah Basaruddin, Suzana Info. Science & Computing Department Management and Science University Selangor Malaysia Software Engineering Section UniKL MIIT Kuala Lumpur Malaysia Informatics & Analytics Section UniKL MIIT Kuala Lumpur Malaysia

ISBN: (纸本)9798331507817

This research investigates the perceptions of cybersecurity among older adults in Malaysia, aged 60 years and above, who are reliant on technology for basic activities. The data from 331 participants showed that 30.8% were online for 4-8 hours daily, while 3.3% were completely disconnected. Interestingly, more than half of the respondents were unaware of cybersecurity threats, especially malware and ransomware, which put their data in jeopardy. While there is some awareness related to unauthorized access and computer fraud, knowledge gaps remain significant, and effective educational interventions are thus needed. info.mal, self-directed learning appears to be a widespread way of acquiring skills in this age group, often supplemented by community workshops and peer networks. Given that almost half of the older adults spend considerable time online, improving their digital skills in tandem with their support systems is an important goal for enhancing their online experiences. It indicates the need for a twin approach: enhancing cybersecurity awareness with specialized educational programs, alongside developing flexible opportunities for info.mal learning. Educational institutions and relevant policies are encouraged to prioritize building hands-on, specific cybersecurity education for seniors. Also, user interface design considering cybersecurity-related issues can make using the technological environment as user-friendly and secure as possible. These strategies will contribute to creating an inclusive digital society, where older adults are confident and safe in using digital technologies while continuously contributing to their personal and professional development. © 2025 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

TAG2TEXT: GUIDING VISION-LANGUAGE MODEL VIA IMAGE TAGGING 12

TAG2TEXT: GUIDING VISION-LANGUAGE MODEL VIA IMAGE TAGGING

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Huang, Xinyu Zhang, Youcai Ma, Jinyu Tian, Weiwei Feng, Rui Zhang, Yuejie Li, Yaqian Guo, Yandong Zhang, Lei Shanghai Key Lab of Intell. Info. Processing School of Computer Science Fudan University China OPPO Research Institute China China Academy for Engineering and Technology Fudan University China

This paper presents Tag2Text, a vision language pre-training (VLP) framework, which introduces image tagging into vision-language models to guide the learning of visual-linguistic features. In contrast to prior works which utilize object tags either manually labeled or automatically detected with an off-the-shelf detector with limited performance, our approach explicitly learns an image tagger using tags parsed from image-paired text and thus provides a strong semantic guidance to vision-language models. In this way, Tag2Text can utilize large-scale annotation-free image tags in accordance with image-text pairs, and provides more diverse tag categories beyond objects. As a result, Tag2Text demonstrates the ability of a foundational image tagging model, with superior zero-shot performance even comparable to fully supervised models. Moreover, by leveraging the tagging guidance, Tag2Text effectively enhances the performance of vision-language models on both generation-based and alignment-based tasks. Across a wide range of downstream benchmarks, Tag2Text achieves state-of-the-art results with similar model sizes and data scales, demonstrating the efficacy of the proposed tagging guidance. Codes, demo and pre-trained models are available at https://***/xinyu1205/recognize-anything. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Detection of Left Ventricular Cavity from Cardiac MRI Images Using Faster R-CNN

引用

computers, Materials & Continua 2023年第1期74卷 1819-1835页

作者： Zakarya Farea Shaaf Muhammad Mahadi Abdul Jamil Radzi Ambar Ahmed Abdu Alattab Anwar Ali Yahya Yousef Asiri Faculty of Electrical and Electronic Engineering Universiti Tun Hussein Onn MalaysiaParit RajaBatu Pahat86400JohorMalaysia Department of Computer Science College of Science and ArtsSharurahNajran UniversityNajran61441Saudi Arabia Department of Computer Science Faculty of Computer Science and Info.SystemsThamar UniversityDhamar87246Yemen Department of Computer Science College of Computer Science and Information SystemsNajran UniversityNajran61441Saudi Arabia

The automatic localization of the left ventricle(LV)in short-axis magnetic resonance(MR)images is a required step to process cardiac images using convolutional neural networks for the extraction of a region of interest(ROI).The precise extraction of the LV’s ROI from cardiac MRI images is crucial for detecting heart disorders via cardiac segmentation or ***,this task appears to be intricate due to the diversities in the size and shape of the LV and the scattering of surrounding tissues across different ***,this study proposed a region-based convolutional network(Faster R-CNN)for the LV localization from short-axis cardiac MRI images using a region proposal network(RPN)integrated with deep feature classification and *** was trained using images with corresponding bounding boxes(labels)around the LV,and various experiments were applied to select the appropriate layers and set the suitable *** experimental findings showthat the proposed modelwas adequate,with accuracy,precision,recall,and F1 score values of 0.91,0.94,0.95,and 0.95,*** model also allows the cropping of the detected area of LV,which is vital in reducing the computational cost and time during segmentation and classification ***,itwould be an ideal model and clinically applicable for diagnosing cardiac diseases.

关键词： Cardiac short-axis MRI images automatic left ventricle localization deep learning models faster R-CNN

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Classification Based on Pixel in Banana Fruit for Disease Detection Using Neural Networks 3

Feature Extraction and Classification Based on Pixel in Bana...

引用

3rd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2023

作者： Mahendran, T. Seetharaman, K. Arignar Anna Government Arts College Department of Computer Applications Tamil Nadu Villupuram605 602 India Annamalai University Department of Computer and Info. Science Tamil Nadu India

ISBN: (纸本)9781665494007

Banana fruit is the most edible and major medicines food in most of the emerging countries. Throughout cultivation of banana has been affected for enormous disease with pesticides. The machine learning techniques in this cultivation area bring improvement in agricultural productivity sectors, particularly with the recent emergence of neural networks, which seems to have increased accuracy levels. So this article proposed the new extraction and classification method in detecting the disease of banana fruit. Initially the image has been pre-processed based on the pixel and to resize the image using ROI selection and this pre-processed image has been segmented using homogenous optimum cut boundary segmentation which is segmented based on the boundary of the training image. The extraction is carried out by gray level co-occurrence matrix (GLCM) and classification is done using Convoluted Deep Neural Networks (CDNN). Banana fruit the simulation has been done efficiently along with the classification of deep learning which can be used in detection of disease for agricultural crops. © 2023 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal LLM Driven computer Interface 8

Multi-Modal LLM Driven Computer Interface

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Sowmiya, R. Revathi, P. Ragunath, D. Sindhuja, S. Gokila, P. Kalaivani, T. Sns College of Engineering Department of Artificial Intelligence and Data Science Tamilnadu Coimbatore India Bannari Amman Institute of Technology Department of Computer Science and Engineering Tamilnadu Sathyamangalam India Tamilnadu Coimbatore India Info Institute of Engineering Department of Computer Science and Engineering Tamilnadu Coimbatore India

ISBN: (数字)9798350376425

ISBN: (纸本)9798350376425

This study presents a framework for multimodal models to control and interact with computers: The Multimodal-driven computer Interface. A decision-making module is used by the framework to determine what actions are acceptable after it processes user input through a variety of modalities, such as speech, text, and gestures, and runs it through a multimodal fusion algorithm. Platform-specific APIs are then used to carry out these operations on the computer. It runs on Linux, Mac, and Windows platforms and is currently integrated with the multimodal LLM. Although the framework shows promising results, there are still issues with adjusting to different user demands and preferences and increasing the accuracy of mouse click position prediction. Potentially revolutionizing human-computer interaction, the Multimodal-driven computer Interface offers new avenues for accessibility, productivity, and pleasure. © 2024 IEEE.

关键词： Windows operating system

来源：评论

学校读者我要写书评

暂无评论

Integrating Structural info.mation: Comparing Classification-Based and Segmentation-Based Predictors in Bioinfo.matics (case study: protein-peptide region residue-level interaction) using structural info.mation 29

Integrating Structural Information: Comparing Classification...

引用

29th International computer Conference, computer Society of Iran, CSICC 2025

作者： Shafiee, Shima Fathi, Abdolhossein Safari, Faezeh Department of Computer Engineering and Information Technology Razi University Kermanshah Iran School of Electrical Eng. and Computer Science Faculty of Eng. Architecture and Info. Tech University of Queensland BrisbaneQLD Australia

ISBN: (纸本)9798331523114

Understanding the regions where proteins bind to peptides is vital for studying diseases like cancer, as it sheds light on various cellular processes and aids in drug discovery. Although researchers can experimentally investigate protein-peptide interactions at the region level by analyzing the structures of their complexes, only a limited number of these structures are known. Additionally, experiments to determine these interactions can be both costly and time-consuming. Computational methods provide an alternative and complementary approach to experimental techniques. As a result, using computational methods to predict peptide-binding regions can significantly enhance the efficiency and cost-effectiveness of experimental research. To leverage these advantages, this study introduces a new method named Structure-based Prediction of Residue-level Interaction of Peptides (SPRINT-Pep), designed to pinpoint the binding regions between proteins and peptides. This approach leverages two distinct predictive models: a classification-based model combining DeepResNet with a Support Vector Machine (SVM) and a segmentation-based model called DeepU-Net. Our predictions outperform other state-of-the-art methods in terms of F-measures (by at least 23%), precision (by at least 3.7%), and the balance between sensitivity and specificity (by about 7.7%). These findings demonstrate the proficiency of the proposed method. © 2025 IEEE.

关键词： Bioinfo.matics

来源：评论

学校读者我要写书评

暂无评论

Security Coding Scheme for Satellite Communications

Security Coding Scheme for Satellite Communications

引用

2024 International Symposium on Intelligent Signal Processing and Communication Systems, ISPACS 2024

作者： Chen, Jong-Shin Sheu, Yung-Hoh Yang, Cheng-Ying Yao, Jenq-Foung J.F. Hwang, Min-Shiang Dept. of Info. and Comm. Eng. Chaoyang Uni. of Tech Taichung Taiwan Department of Computer Science and Information Engineering National Formosa University Yunlin Taiwan Department of Computer Science University of Taipei Taipei Taiwan Dept of Computer Science Georgia College and State University Milledgeville United States Dept. of C.S. & Info. Eng. Fintech and Blockchain Research Center Asia University Taichung Taiwan Dept. of Medical Research University Hospital China Medical University Taichung Taiwan

ISBN: (纸本)9798350389210

The major goal of a secure coding is to enable the authentic receiver could successfully recover the original message from the source. However. the satellite communications provide an open wireless environment. It hardly protects the transmitted info.mation from the eavesdroppers. Usually, the secure system employs the encryption, authorization and authentication schemes to avoid from the attacks. However, the undesired attacks have been continuously developed. In order to reduce the computing resource exhausted in the encryptions. Physical layer security coding based on Shannon's perfect secrecy, error-free cryptogram, might be applied to the satellite communications. Moreover, the coding scheme could reach the required critical security capacity. Also, it could approach the low error probability. However, the info.mation rate and the coding rate will suffer the system performance. To tradeoff the security level, info.mation rate and coding rate could be the important issue in the satellite communications. © 2024 IEEE.

关键词： Coding rate info.mation rate Physical-layer security Coding Secrecy capacity Shannon theorem

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：