检索结果-内蒙古大学图书馆

An effective object detection and tracking using automated image annotation with inception based faster R-CNN model

International Journal of Cognitive Computing in engineering 2024年第1期5卷 343-356页

作者： Vijiyakumar, K. Govindasamy, V. Akila, V. Department of Computing Technologies School of computing SRM institute of Science and Technology Kattankulathur campus Tamilnadu Chengalpattu district India Department of Information Technology Pondicherry Engineering College Pondicherry India Department of Computer Science and Engineering Pondicherry Engineering College Pondicherry India

The present study advances object detection and tracking techniques by proposing a novel model combining Automated Image Annotation with Inception v2-based Faster RCNN (AIA-IFRCNN). The research methodology utilizes the DCF-CSRT model for image annotation, Faster RCNN for object detection, and the inception v2 model for feature extraction, followed by a softmax layer for image classification. The proposed AIA-IFRCNN model is evaluated on three benchmark datasets: Bird (Dataset 1), UCSDped2 (Dataset 2), and Under Water (Dataset 3), to determine prediction accuracy, annotation time, Center Location Error (CLE), and Overlap Rate (OR). The experimental results indicate that the AIA-IFRCNN model outperformed existing models regarding detection accuracy and tracking performance. Notably, it achieved a maximum detection accuracy of 95.62 % on Dataset 1, outperforming other models. Additionally, it achieved minimum average CLE values of 4.16, 5.78, and 3.54, and higher overlap rates of 0.92, 0.90, and 0.94 on the respective datasets (1, 2 and 3). Hence, this research work on object detection and tracking using the AIA-IFRCNN model is essential for improving system efficiency and fostering innovation in the field of computer vision and object tracking. © 2024

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Clustered Input Oriented Salp Swarm Algorithm in Cloud Computing

引用

computers, Materials & Continua 2024年第12期81卷 4659-4690页

作者： Juliet A.Murali Brindha T. Department of Computer Science and Engineering Noorul Islam Centre for Higher EducationKumaracoil629180India Department of Information Technology Noorul Islam Centre for Higher EducationKumaracoil629180India

Infrastructure as a Service(IaaS)in cloud computing enables flexible resource distribution over the Internet,but achieving optimal scheduling remains a *** resource allocation in cloud-based environments,particularly within the IaaS model,poses persistent *** methods often struggle with slow opti-mization,imbalanced workload distribution,and inefficient use of available *** limitations result in longer processing times,increased operational expenses,and inadequate resource deployment,particularly under fluctuating *** overcome these issues,a novel Clustered Input-Oriented Salp Swarm Algorithm(CIOSSA)is *** approach combines two distinct strategies:Task Splitting Agglomerative Clustering(TSAC)with an Input Oriented Salp Swarm Algorithm(IOSSA),which prioritizes tasks based on urgency,and a refined multi-leader model that accelerates optimization processes,enhancing both speed and *** continuously assessing system capacity before task distribution,the model ensures that assets are deployed effectively and costs are *** dual-leader technique expands the potential solution space,leading to substantial gains in processing speed,cost-effectiveness,asset efficiency,and system throughput,as demonstrated by comprehensive *** a result,the suggested model performs better than existing approaches in terms of makespan,resource utilisation,throughput,and convergence speed,demonstrating that CIOSSA is scalable,reliable,and appropriate for the dynamic settings found in cloud computing.

关键词： Cloud computing clustering resource allocation scheduling swam algorithms optimization common with in the subject discipline

来源：评论

学校读者我要写书评

暂无评论

Automating Optimal Healthcare Delivery Through Hyper Spectral Imaging in Sustainable Medical Environments

Automating Optimal Healthcare Delivery Through Hyper Spectra...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Seth, Jyoti Kavitha, R. Yadav, Dhyan Chandra Vivekananda Global University Department of Computer Science & Engineering Jaipur India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

Hyperspectral imaging (HSI) is a progressive imaging method being explored, which will aid in the automation of foremost healthcare transport in sustainable scientific environments. HSI requires an enormous variety of spectral bands compared to other spectral imaging methods, including visible mild imaging. This more statistics let in for a greater sure and correct evaluation of the spectral information within an image, presenting more remarkable sturdy outcomes while assessing the health of clinical situations. The information accrued thru HSI can be used to create automatic healthcare shipping models which could autonomously adjust and reply to changes in the clinical situation of an affected person. Similarly, this technology may be used to hit upon ailments, including cancer, offering a treasured perception of a patient's health and considering the selection of timely and appropriate treatments. Moreover, HSI can be used to create green and sustainable clinical surroundings, as it requires reduced personnel, area and fewer patient trips to and from the health facility. This technology can lower prices and improve patient consequences by providing automated selections for healthcare professionals. © 2024 IEEE.

关键词： autonomously Hyperspectral information progressive imaging

来源：评论

学校读者我要写书评

暂无评论

Automating Object Identification from Hyper Spectral Data with Markov Random Fields

Automating Object Identification from Hyper Spectral Data wi...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Chaudhary, Chetan Devrani, Rekha Aadil, Mir Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350383348

Hyper Spectral statistics (HSD) is a type of fact acquired from optical sensors, which include satellites, scanners, and microscopes that captures and measures various wavelengths of energy. Object identification from HSD is problematic because of the high spectral variability in pixels of the image and the great variety of product classes usually present. Markov Random Fields (MRF) is a graphical model that may be used to version spatial dependencies among neighboring pixels which can assist in decorating the object identification process. This summary explores the feasibility of automating item identity from HSD through MRF. We introduce the idea of a priori information, which includes labels assigned to distinct spectral signatures within the image and a classification system that uses MRF as a priori information to enhance object identity accuracy. We describe and demonstrate the exact rules for this challenge via simulation. The consequences of the take look advocate that utilizing the MRF-based category gadget to improve item identification accuracy from HSD is possible. © 2024 IEEE.

关键词： classification consequences Hyper Spectral microscopes neighboring

来源：评论

学校读者我要写书评

暂无评论

Enhanced Neutrosophic Set and Machine Learning Approach for Kidney Disease Prediction

引用

Neutrosophic Sets and Systems 2025年 80卷 465-477页

作者： Al-Doori, Humam M. Alkellezli, Tareef S. Abdelhafeez, Ahmed Eassaa, Mohamed Sawah, Mohamed S. El-Douh, Ahmed A. Cybersecurity Sciences Department College of Science Ashur University Baghdad Iraq Cybersecurity Engineering Department College of Engineering Ashur University Baghdad Iraq Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Science Faculty of Information Technology Ajloun National University P.O.43 Ajloun26810 Jordan Cybersecurity Technology Engineering Department College of Engineering Technology Ashur University Baghdad Iraq

Kidney disease (KD) is a gradually increasing global health concern. It is a chronic illness linked to higher rates of morbidity and mortality, a higher risk of cardiovascular disease and numerous other illnesses, and expensive medical expenses. The machine learning (ML) models are applied for KD prediction with higher accuracy and precision. The KD dataset has uncertainty and vague information, so, we used the neutrosophic set (NS) to deal with vague and uncertainty information in the KD dataset. The KD dataset is converted into the N-KD dataset with three membership functions: truth, indeterminacy, and falsity. Three ML models are used in this study such as logistic regression (LR), support vector machine (SVM), and k-nearest neighbor (KNN). These ML models are applied to the N-KD dataset. The results show the LR has higher accuracy and precision on the N-KD dataset than the original KD dataset. © 2025, University of New Mexico. All rights reserved.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Investigating and Implementing the Efficiency of Image Restoration Techniques in Digital Image Processing

Investigating and Implementing the Efficiency of Image Resto...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Seth, Jyoti Ojha, Ananta Singh, Vaishali Vivekananda Global University Department of Computer Science & Engineering Jaipur India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

photo restoration is restoring the advent and pleasantness of a picture that has been degraded in various manners. Photo healing strategies are extensively used in digital picture processing for recovering pics degraded due to noise, blur, and artifacts. These techniques are based on restoring the underlying records compromised by the degradation. Photo restoration intends to repair the image and make it look nice. This research investigates and implements the performance of photo restoration strategies in virtual picture processing. An assessment and contrast of various photograph restoration strategies consisting of Wiener filter, Tikhonov regularization, and overall variant regularization are performed with the usage of numerous criteria, which include top Signal-to-Noise Ratio (PSNR) and suggest rectangular mistakes (MSE). The results of photograph healing techniques are also evaluated in terms of the first-rate of the restored picture. A test is conducted on a selected photograph to illustrate the effectiveness of the numerous strategies. The outcomes of the experiments and critiques exhibit that photo recuperation techniques can effectively repair first-class degraded photos. The effectiveness of those techniques relies upon the type of degraded image and the noise present in it. Wiener filter out is powerful for pics corrupted by additive white Gaussian noise;simultaneously, Tikhonov regularization and total version regularization are most appropriate for images corrupted by impulsive noise. Consequently, this research provides a perception of the overall performance and efficiency of photo healing techniques to facilitate the choice of the best method for various picture recuperation programs. © 2024 IEEE.

关键词： degraded efficiency facilitate restoration technique

来源：评论

学校读者我要写书评

暂无评论

RAPID-AV: Realtime Adaptive and Intelligent Detection For AV's Against DDoS Attacks 18

RAPID-AV: Realtime Adaptive and Intelligent Detection For AV...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Kotha, Aditya Venkanna, U. International Institute of Information Technology Department of Computer Science and Engineering Naya Raipur India National Institute of Technology Department of Computer Science and Engineering Warangal India

ISBN: (纸本)9798350391725

Autonomous vehicles (AVs) increasingly rely on vehicle-to-everything (V2X) networks for communication. However, due to the devices' heterogeneity, they are more susceptible to attacks like distributed denial of service (DDoS), resulting in packet loss and transmission delays. Existing solutions to these issues often create bottlenecks and lack post-attack recovery mechanisms. To solve these problems, this paper proposes RAPID-AV, an ML-based approach that uses programmable P4 switches for real-time detection and mitigation of DDoS attacks in AV networks. The proposed system uses a threefold strategy: collect traffic statistics from AV, use P4-based programmable packet processing for anomaly detection, and use majority voting to mitigate attacks. In our experiments, we found that the decision tree algorithm achieves an accuracy of 94.33% in distinguishing traffic from DDoS traffic. In addition, RAPID-AV demonstrated a nearly 10% reduction in CPU load during attacks and maintained consistent communication between AV and RSU. This approach can help improve AV network security while addressing the limitations of existing solutions. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Exploration of the Impact of 5G on Mobile Communication Systems

Exploration of the Impact of 5G on Mobile Communication Syst...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Singh, Akhilendra Pratap Seth, Jyoti Kamalraj, R. Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350383348

The fifth era (5G) of cell communication systems is a progressive jump forward in the evolution of wireless networks. It promises to deliver a brand new user enjoyment, characterized by using quicker speeds and greater capability, with improved energy efficiency. The increased speed and efficiency of 5G networks could have a big impact on a wide variety of packages, which includes stepped forward user revel, advanced great of provider, and green use of sources. This paper explores the ability impact of 5G on cellular communique systems by inspecting the important thing demanding situations and case studies that highlight specific advantages that may be realized. We evaluate the primary technological advances that will make contributions to the success of 5G structures, including millimeter waves, large MIMO and beamforming, and community cutting. The paper also considers the capability effect that 5G will have on modern-day network architectures, regulatory and policy frameworks, and new enterprise fashions in order to be taken into consideration. Through a variety of case research, we pick out the potential possibilities and challenges that 5G might also carry and provide concrete suggestions on how first-rate to ensure successful deployment. In the end, we present the concept that 5G can be the most effective engine of digital transformation, furnishing the right mixture of innovation, investment, and partnership. © 2024 IEEE.

关键词： Beamforming Communication Efficiency Enterprise Networks Partnership

来源：评论

学校读者我要写书评

暂无评论

The Smart Attitude Analysis of Network Interference User using Recursive Neural Framework

The Smart Attitude Analysis of Network Interference User usi...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Agarwal, Ankita Devrani, Rekha Kannagi, A. Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Vivekananda Global University Department of Computer Science & Engineering Jaipur India Department of Computer Science and Information Technology Bangalore India

ISBN: (纸本)9798350383348

This paper proposes a Recursive Neural framework for the clever mindset evaluation of network interference customers. Our technique builds on previous work achieved in sentiment analysis using extracting a person's man or woman mindset from complicated and incomplete statistics streams. The framework, to begin with, gets the sentiment layers based on consumer interactions from the datasets, after which it integrates this fact with various Recursive Neural networks to seize the sentiment of a single user. The community extracts capabilities associated with the user and learns to distinguish between the behaviors of two users inside the community. Once the community is educated on the datasets, it may classify the sentiment of users based on various contextual cues. We evaluated our framework through crowd-sourced sentiment annotation datasets from a web forum, and it confirmed superior overall performance than different present approaches. We proposed a Recursive Neural framework that utilizes contextual schemas and sentiment to analyze user attitudes and behaviors for community interference scenarios. It can open up promising new opportunities for observing consumer mindset and behavior in online networks. This paper offers a recursive neural framework for competent mindset evaluation of network interference customers. Recursive Neural Networks, broadly carried out in natural language processing responsibilities with sentiment analysis, combine word embeddings with a recursive architecture to gain a perception of the syntactic shape of sentences. On this, look at the Recursive Neural Network (RNN) architecture tailored to research the sentiment mindset of community interference users. The information amassed from Twitter, Weibo, and different open-supply platforms had been pre-processed using the frequency inverted report frequency technique before constructing an RNN for its modeling. Checks at the built community proved that the proposed model furnished pleasant c

关键词： efficacy evaluation extracting practitioners recognize

来源：评论

学校读者我要写书评

暂无评论

The Smart Predictive Analysis of Stock Market Performance using Restricted Boltzmann Machines

The Smart Predictive Analysis of Stock Market Performance us...

引用

2024 International Conference on Optimization Computing and Wireless Communication, ICOCWC 2024

作者： Devrani, Rekha Mahajan, Prerna Kumar, Dinesh Vivekananda Global University Department of Computer Science & Engineering Jaipur India Department of Computer Science and Information Technology Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India

ISBN: (纸本)9798350383348

Restricted Boltzmann Machines (RBMs) are a system getting-to-know algorithm that may be used to predict the overall performance of inventory markets. This painting aims to analyze the overall performance of inventory markets via growing an RBM version. The RBM version will benefit from the temporal correlation of stock marketplace information and put it to use to make more correct predictions. The version is educated using historical facts, and the model parameters are adjusted to optimize the prediction accuracy. This painting demonstrates the use of an RBM model for predicting the returns of stocks and analyzing the stock marketplace's overall performance. The outcomes from these paintings show that the proposed RBM version effectively predicts the overall performance of inventory markets and provides an alternative version for forecasting stock markets. Confined Boltzmann Machines (RBMs) are a form of synthetic neural network which can be used for unsupervised studying tasks consisting of dimensionality discount, function mastering, and collaborative filtering. RBMs have been correctly used in numerous applications, including sentiment evaluation, natural language processing, and computer imagination and prescient. In current years, there was a surge of hobby in using RBMs to expect inventory market overall performance. On the way to expand a predictive model, RBMs extract separable functions from the uncooked market data, which can be pattern inputs. The extracted capabilities are used because of the input to a supervised mastering version to predict stock marketplace overall performance based on previous statistics. A vital advantage of using RBMs for feature extraction is that they can identify latent components of the facts, which would, in any other case, remain hidden from the consumer. By combining RBMs with supervised learning, it is viable to develop models which can be more powerful than those using either technique for my part. Because of this reality,

关键词： algorithms correlations historical inventory stock

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：