检索结果-内蒙古大学图书馆

4th IEEE International Conference on Data Engineering and Communication Systems, ICDECS 2024

作者： Manimozhi, S. Arumugam, S. Rajeshwari, G. Periyar Maniammai Institute of Science & Technology Vallam Department of Computer Science and Applications Tamilnadu Thanjavur613 403 India

ISBN: (纸本)9798350393354

Counting vehicles is an essential function for smart city applications, traffic management, and surveillance. There are several applications for the technology used to detect vehicles in recorded video. In this research work, the Oriented FAST and Rotated BRIEF (ORB) method is used to develop a rudimentary model for vehicle detection and counting. The video clip used as input, numerous frames are retrieved, and shadow and backdrop are approximated. To identify every moving object from the estimated backdrop, the subsequent frame is subtracted. Vehicles are identified, categorized, and counted for traffic estimation based on moving objects, utilizing object detection methods and OpenCV. When used with OpenCV, the ORB algorithm offers a potential method for identifying and accumulation the number of vehicles in the video stream. The ORB method is well-suited for tracking objects in dynamic settings since it is especially supportive for feature matching. © 2024 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Colored Token Swapping Using Broom 5

Colored Token Swapping Using Broom

引用

5th IEEE Global Conference for Advancement in Technology, GCAT 2024

作者： Ajila, L. Indulekha, T.S. Anuja, G. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Applications Kerala Amritapuri India

ISBN: (纸本)9798350376685

Token swapping, a fundamental problem in computational graph theory involves rearranging tokens at graph vertices through minimal swaps to achieve a desired configuration. This problem finds applications in various fields, including task scheduling, DNA rearrangement, and network reconfiguration. A well-established variant, colored token swapping, assigns distinct colors to tokens residing on vertices in a graph. The complexity of token swapping is NP-hard. Two-colored token swapping is a specific case where there are only two distinct colors for the tokens. This work introduces a novel, efficient algorithm for swapping two-colored tokens on a specific tree called a single broom, achieving a configuration where each token resides in its designated position. Single brooms are constructed by attaching the center vertex of a star(the vertex with degree n-2) to one of the leaf nodes of a path. The suggested algorithm utilizes the inherent properties of the tree structure to streamline the necessary swaps for achieving the desired configuration. © 2024 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Secure Transmission for UAV-Assisted Mobile Edge Computing

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2024年第17期18卷 154-169页

作者： Vijayalakshmi, N. Gulati, Sagar Sujin, B. Ben Rao, B. Madhav Kumar, K. Kiran Department of Computer Science and Applications SRMIST Ramapuram Campus Tamil Nadu Chennai India School of Computer Science and IT JAIN Deemed to be University Karnataka Bengaluru India Computer Engineering Department University of Technology and Applied Sciences Nizwa Oman Department of CSE SIR C R Reddy College of Engineering Andhra Pradesh Eluru India Department of CSE Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram India

The increasing computational demand for real-time mobile applications has led to the development of mobile edge computing (MEC), with support from unmanned aerial vehicles (UAVs), as a promising paradigm for constructing high-throughput line-of-sight links for ground users and pushing computational resources to network edges. Users can reduce processing latency and the load on their local computers by delegating tasks to the UAV in its role as an edge server. The coverage capacity of a single UAV is, however, very limited. Moreover, it will be easy to intercept the data that is transferred to the unmanned aerial vehicle. Thus, for UAV-assisted mobile edge computing, we proposed a transmission technique based on multi-agent deep reinforcement learning in this study. The recommended approach to maximize UAV deployment first applies the particle swarm optimization algorithm. Then, deep reinforcement learning is utilized to optimize the secure offloading to maximize the system utility and minimize the quantity of information eavesdropping, taking into consideration different user task types with diverse preferences for processing time and residual energy of computing equipment. The results of the simulation demonstrate that, in comparison to the single-agent strategy and the benchmark, the multi-agent approach can optimize offloading more successfully and produce higher system utility. © 2024 by the authors of this article.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Credit Risk Assessment with Madaline and Multilayer Perceptrons 6th

Credit Risk Assessment with Madaline and Multilayer Perceptr...

引用

6th International Conference on Soft Computing and Signal Processing, ICSCSP 2023

作者： Tetteh, Maxwell Puthussery, Arundhathi Yamunakrishnan Subbulakshmi, S. Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri Kollam India

ISBN: (纸本)9789819986279

Predictive machine learning algorithms offer an efficient way to perform mundane computations and analysis that otherwise would have taken lots of time and manual effort. In banking and finance, creditors analyze the risk level of loan products in order to set interest rates for potential clients. In this paper, we examine supervised neural network approaches that can be used to automate the risk assessment process on loan applications. Dataset includes customers with potential features who are classified as risky and non-risky. To avoid loss by granting loans to risky customers, classification is done using multiple adaptative neuron network (Madaline) and multiple-layer perceptron (MLP) models, and loan is granted only to non-risky customers. Predictions of Madaline networks are optimized using parameter tuning methods. MLP model handles label imbalance and skewness of data toward one label. Models are trained tested with two datasets containing records of individual customers and companies as debtors. Prediction performance of Madaline and MLP models is assessed using different measures. MLP model showed higher prediction accuracy of 97% and 84% for customer and company dataset, respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Precision Agriculture: Deep and Machine Learning Approaches for Crop Disease Predictions

Precision Agriculture: Deep and Machine Learning Approaches ...

引用

2024 International Conference on Electrical, Electronics and Computing Technologies, ICEECT 2024

作者： Varun, M. Benitta, D. Angeline Tanwar, Sushama Hindustan Institute of Technology and Science Department of Computer Applications Chennai India Manipal University Jaipur India

ISBN: (纸本)9798350378092

Agriculture, a vital sector shaping India's economy, serves as the cornerstone of food production. This study focuses on estimating crop yield by integrating environmental, soil, water, and crop factors. Despite significant efforts in yield prediction, challenges persist, including the effective mapping of raw data to crop yield values and the reliance on feature quality for model performance. To address these challenges, we employ deep learning models for meaningful crop feature extraction. The system utilizes a dataset repository and incorporates diverse classification algorithms such as random forest and convolutional neural networks. Our experimental results highlight the system's accuracy, precision, recall, and scores, providing valuable insights into the agricultural forecasting domain. Through the integration of deep learning techniques and diverse classification algorithms, we successfully estimate crop yield and identify factors impacting agricultural productivity. The findings underscore the importance of leveraging advanced computational methods for crop yield estimation and disease diagnosis, facilitating informed decision-making in agriculture and contributing to sustainable food production and economic growth. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

An Exploration of Code Similarity and Code Replication in Computational Programs 15

An Exploration of Code Similarity and Code Replication in Co...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Mohith, L.S. Manikandan, M. Thushara, M.G. Amrita vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Applications Kerala Amritapuri India

ISBN: (纸本)9798350370249

As software systems become increasingly complex, it is crucial to analyze code similarity and replication patterns. This study investigates how such patterns impact software quality, maintainability, and development processes. We will employ a combination of established techniques and advanced machine-learning models for comprehensive code similarity measurement. The goal is to critically evaluate existing methods and identify avenues for improvement in code similarity analysis techniques. © 2024 IEEE.

关键词： Code Similarity Computational Programs Machine Learning Software Engineering Software Quality

来源：评论

学校读者我要写书评

暂无评论

Unmasking Hypertension Through a Fusion of Human Lifestyle Data using Machine Learning Algorithms 6

Unmasking Hypertension Through a Fusion of Human Lifestyle D...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Vishnu Priya, V. Nisanth, G. Nivethaa, R.P. Vijay, Srinidhi Department of Computer Science and Engineering Kongu Engineering College Erode Perundurai India Department of Computer Applications Kongu Engineering College Erode Perundurai India Department of Computer Technology UG Kongu Engineering College Erode Perundurai India

ISBN: (纸本)9798331522667

Hypertension, also referred to as high blood pressure, is a condition arising from the consistently high blood pressure against artery walls. The volume and output of blood from the heart primarily control blood pressure under stiff or tight arterial conditions. High pulse pressure leads to increased blood pressure, since the pumping of more blood makes the arteries inactive. The World Health Organization has a comprehensive guideline in which an evidence-based pharmacological approach has been recommended for managing adult patients with hypertension, not neglecting to mention lifestyle modification in order to support medicinal treatment. Machine learning may revolutionize the way hypertension treatment is projected for the management of personalized treatment routines for patients based on their characteristics. ML provides great promise in seeking ideal medication and predicting responses thereof against massive sets of data for hypertensive patients. The techniques allow for the determination of the individual risk for hypertension and ensure that treatment protocols are optimal. Compared to methods used to predict hypertension in the past, ML algorithms show a marked improvement in performance. © 2025 IEEE.

关键词： Personalized medicine

来源：评论

学校读者我要写书评

暂无评论

Network Intrusion Detection System Using Machine Learning 3rd

Network Intrusion Detection System Using Machine Learning

引用

3rd International Conference on "Emerging Trends and Technologies on Intelligent Systems" (ETTIS-2023)

作者： Kumar, Sudesh Pathak, Prashant Agrawal, Karan Goswami, Vedant Mahindru, Arvind Department of Computer Science Shri Mata Vaishno Devi University Katra India Department of Computer Science and Applications DAV University Jalandhar India

ISBN: (纸本)9789819939626

In the past decade, we had moved from the telephonic era to the Internet era and the advancement of networking increased the network size and complexity. Side by side, there is also advancement in malicious activity such as monitoring the network or interrupting the services in the network. One way to get secure from this is to limit user access, but this result in decreased efficiency of intended users, so the solution to this problem is an intrusion detection system. Intrusion detection systems can be designed by using various ways, but the machine learning approach is best as it can detect attacks that are developing every day. The goal of this paper is to use various machine learning techniques such as Naïve Bayes, random forest, SVM, decision tree, KNN, and XGBoost on the CICIDS-2018 dataset and develop an IDS that can detect any type of attack that is listed currently or can be developed in the future. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

mHAR: a novel convolutional recurrent model for recognizing motion-based human activity 12

mHAR: a novel convolutional recurrent model for recognizing ...

引用

12th International Young Scientists Conference in Computational science, YSC 2023

作者： Kumar, Prabhat Suresh, S. Department of Computer Science Institute of Science Banaras Hindu University Varanasi221 005 India Department of Computer Engineering & Applications GLA University Mathura281406 India Department of Computer Applications National Institute of Technology Kurukshetra136119 India

With sensors built into smartphones and wearable devices, Human Activity Recognition (HAR) makes it possible to identify regular activities. One of the challenges is to access the motion information from activity data and extract the features from this information. A general model trained without motion features may perform poorly while recognizing the contextual patterns in human activities. In this paper, we proposed the mHAR (motion HAR) model for recognizing static, gradual, and dynamic motion activity to address this challenge. We examine the impact of the proposed model against the general non-convolutional and convolutional recurrent networks in terms of accuracy rates and F1 score. As an experimental dataset, the publicly accessible WISDM was employed. Additionally, the findings of the experiments demonstrate that, in contrast to the unbalanced class problem, motion features play a significant role in activity recognition by achieving accuracy rates of 92.29% and an average F1 score of 83.33%. © 2023 The Authors. Published by Elsevier B.V.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network Based Intelligent Advertisement Search Framework for Online English Newspapers

引用

Recent Patents on Engineering 2022年第4期16卷 109-127页

作者： Jain, Pooja Taneja, Kavita Taneja, Harmunish Department of Computer Science and Applications Punjab University Punjab Chandigarh160014 India Department of Computer Science and Information Technology DAV College Punjab Chandigarh India

Background: Instant access to desired information is the key element for building an intelligent environment creating value for people and steering towards society 5.0. Online newspapers are one such example which provide instant access to information anywhere and anytime on our mobiles, tablets, laptops, desktops, etc. But when it comes to searching for a specific advertisement in newspapers, online newspapers do not provide easy advertisement search options. Also, there are no specialized search portals which can provide for keyword-based advertisement search across multiple online newspapers. As a result, to find a specific advertisement in multiple newspapers, a sequential manual search is required across a range of online newspapers. Objective: This research paper proposes a keyword-based advertisement search framework to provide an instant access to the relevant advertisements from online English newspapers in a category of reader’s choice. Methods: First, an image extraction algorithm is proposed which can identify and extract the images from online newspapers without using any rules on advertisement placement and/or size. It is followed by a proposed deep learning Convolutional Neural Network (CNN) model named ‘Adv_Recognizer’ which is used to separate the advertisement images from non-advertisement images. Another CNN Model, ‘Adv_Classifier’, is proposed, which classifies the advertisement images into four pre-defined categories. Finally, Optical Character Recognition (OCR) technique is used to perform keyword-based advertisement searches in various categories across multiple newspapers. Results: The proposed image extraction algorithm can easily extract all types of well-bounded images from different online newspapers and this algorithm is used to create ‘English newspaper image dataset’ of 11,000 images, including advertisements and non-advertisements. The proposed ‘Adv_Recognizer’ model separates advertisement and non-advertisement images with an accurac

关键词： Convolutional neural networks

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：