检索结果-内蒙古大学图书馆

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

作者： Adharsh, C. Benitta, D. Angeline Eliyas, Sherin Balamurugan Hindustan Institute of Technology and Science Department of Computer Applications Chennai India Shivnadar University Chennai India

ISBN: (纸本)9798350378092

Gamification is a blooming technology that transforms stereotypical academics into interesting game-like elements. Through gamification, educators motivate the students to involve themselves in the game design for entertainment and adopt the features of the game design in an educational setting for enhanced learning. This work focuses on an educational digital game for learning sorting algorithms and concepts from data structures. The game is designed based on constructivism learning theory and the MDA framework, aiming to promote active and student-centered learning. The game challenges players to rearrange a sequence of unsorted aliens by using a set of commands, such as comparing, swapping, and moving. The game also records players' actions and performance through log data, which can be analyzed for learning behavior, and outcomes. It describes the game design and development process, as well as the potential benefits and limitations of using the game in computer science education, and also discusses how the game can facilitate the development of computational thinking skills such as problem formulation, abstraction, algorithmic thinking, and generalization. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

The Analysis of Srgb Color Space Based Density for Brain Tumor Segmentation 7th

The Analysis of Srgb Color Space Based Density for Brain Tum...

引用

7th International Symposium on Intelligent Informatics, ISI 2022

作者： Gangadharappa, S. Naveena, C. Aradhya, V. N. Manjunath Department of Computer Science and Engineering SJBIT Karnataka Bengaluru India Department of Computer Applications JSS Science and Technology University Mysuru Mysore India

ISBN: (纸本)9789811980930

Medical image processing is one of the significant fields to identify the diseases as earlier to diagnose them appropriately. The brain tumor segmentation process is sub branch of a medical image processing field. The computer vision and machine learning techniques provide an effective channel for the medical practitioners for diagnosing the diseases in an effective method. This research article implements the Srgb-based density analysis for isolating the brain tumor space in MRI images. Intensity values of a given input are normalized using Srgb color space and Gaussian filter to distinguish the tumor region from the background. The adaptive threshold technique helps identify the possible tumor space in brain MRI samples. The actual brain tumor space is extracted by performing the region properties such as area and density function. Finally, the accurate tumor space is detected by applying morphological functions with eliminating possible false positives. Performance metrics including recall, precision, and F-measure are used to assess the effectiveness of the proposed approach. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular Disease Detection Using Intelligent Systems: A Cursory Survey 1st

Cardiovascular Disease Detection Using Intelligent Systems: ...

引用

1st International Conference on Data Engineering and Machine Intelligence, ICDEMI 2023

作者： Jayaraman, Muralidharan Shanmugavadivu, P. Department of Computer Science and Applications The Gandhigram Rural Institute Deemed to be University Tamil Nadu Dindigul India

ISBN: (纸本)9789819776153

Globally, cardiovascular diseases, comprising a range of ailments, continue to demonstrate increasing mortality rates. Despite collaborative endeavors to predict and initiate timely treatment, achieving the necessary diagnostic accuracy poses a challenge due to the diverse lifestyles prevalent in the population. As a result, intensive research is directed toward formulating a model that gains acceptance within the medical community. In this context, we elucidate the operational principles of each machine learning model, as detailed in the selected articles for our review, including their mathematical aspects. This literature survey delves into comprehending the breadth of conducted research, providing insights into the prevailing emphasis. Notably, every article consistently underscores the need for a hybrid model, acknowledging the limitations of the efficacy of single models. Each study, in its pursuit of optimization, begins with meticulous pre-processing, hyperpa-rameter tuning, and the application of statistical models, showcasing commendable efforts. A straightforward comparison of the selected models is presented, along with their respective results, implications, strengths, and limitations. However, despite these commendable initiatives, there is still considerable room for improving accuracy and further advancing diverse hybrid models, marking an ongoing trajectory of progress in this field. This article aims to be a convenient reference for researchers and practitioners interested in the application of machine learning for cardiovascular disease detection. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

The Role of the Italian Museum System on Economic Development: A Latent Transition Analysis Proposal

The Role of the Italian Museum System on Economic Developmen...

引用

International Symposium on Networks, Markets and People, NMP 2024

作者： Galluccio, Carla Giambona, Francesca Grassini, Laura Department of Statistics Computer Science Applications "G. Parenti" University of Florence Florence50134 Italy

ISBN: (纸本)9783031746079

Museums and cultural heritage are a resource for local development as they can help attract tourists, generate revenue, to promote inclusion and cultural diversity. The management of museums and cultural heritage can be traced back to some traditional concepts of economic theory. These goods, in fact, satisfy needs that improve a country's civilisation level, providing positive externalities, as cultural heritage positively affects employment in economic sectors (such as tourism) and determines an improvement in human and social capital. In this way, the ability of museums to achieve their purposes of conservation and valorisation of artistic and cultural heritage takes particular relevance. The Italian Survey on Museums and similar institutions, carried out by the Italian Statistical Institute (Istat), the Ministry of Cultural Heritage and Activities and Tourism, the Regions and the Autonomous Provinces since 2011, provides a wide range of information for museums and similar structures. The main research areas analysed are heritage conservation, accessibility to exhibition spaces, visitor orientation, and relations with the external context. The availability of longitudinal data (annually since 2017) allows to analyse the evolution of the Italian museum sector from 2017 to 2021, paying particular attention to territorial detail. From a methodological point of view, a latent class transition analysis is applied. Indeed, as long as longitudinal data has to be analysed, research questions deal not only with museums’ classification but also with respect to classification changes over time. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Cultural heritage Latent Class Transition analysis Temporal analysis

来源：评论

学校读者我要写书评

暂无评论

A Privacy Preservation Framework Using Integration of Blockchain and Federated Learning

引用

SN computer science 2023年第6期4卷 703页

作者： Sameera, K.M. Rafidha Rehiman, K.A. Vinod, P. Department of Computer Applications Cochin University of Science and Technology Ernakulam Kerala Kochi 682022 India

Over the last few years, end devices’ rapid proliferation and development have placed obstacles on existing networks. New technologies have prompted attention to developing distributed and intelligent systems that protect data privacy. Federated Learning (FL) is a privacy-enhanced collaborative learning strategy that offers a model-based sharing mechanism rather than actual data to solve the hurdles of data privacy issues of participants’ data. This work suggested a blockchain-based FL system to replace the central server in conventional federated learning. We also verify the participants’ local model to detect the malicious model. This study examines the system performance by considering the participants’ IID and non-IID data distributions. To demonstrate the reliability of our suggested technique, we conducted an extensive experiment with popular datasets such as MNIST, EMNIST, CIFAR-10, and Fashion-MNIST. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Federated learning, blockchain Independent identically distributed data (IID) Non-independent identically distributed data (non-IID) Privacy preservation

来源：评论

学校读者我要写书评

暂无评论

Classified Dynamic Hierarchical Load Balancer for Cloud Data Centers

引用

SN computer science 2025年第3期6卷 1-11页

作者： Patni, Sakshi Kumar, Jitendra Saxena, Deepika Kumar Singh, Ashutosh Department of Computing Gachon University Seongnam South Korea Department of Computer Applications MANIT MP Bhopal India Department of Computer Science University of AIZU Aizu Japan Director and Head IIIT Bhopal MP Bhopal India

Cloud data centers face critical challenges in resource allocation efficiency. We propose C-DHLB (Classified Dynamic Hierarchical Load Balancer), a novel framework that optimizes resource allocation through intelligent classification of application requirements and dynamic load balancing. Our approach addresses traffic scalability by developing an optimized VM placement strategy that considers multiple resource dimensions and constraints. C-DHLB analyzes resource consumption patterns in dimensions of CPU, memory, energy, and bandwidth, implementing a weighted scoring mechanism for optimal VM placement. Our experimental results demonstrate significant improvements: 83.62% reduction in resource wastage, 72.58% decrease in network traffic, and 45% lower response time compared to conventional methods. This comprehensive evaluation across 200 physical machines validates C-DHLB’s effectiveness in enhancing cloud data center performance while maintaining SLA requirements. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Cloud data centers Load balancing Performance optimization Resource allocation Resource management

来源：评论

学校读者我要写书评

暂无评论

An ingenious method for estimating future crop prices that emphasises machine learning and deep learning models

引用

International Journal of Information Technology (Singapore) 2023年第8期15卷 4291-4313页

作者： Banerjee, Saikat Mondal, Abhoy Chand The Department of Computer Applications Vivekananda Mahavidyalaya Haripal West Bengal Hooghly India The Department of Computer Science The University of Burdwan West Bengal Burdwan India

Forecasting prices for dripping crops, such as vegetables, holds significant implications for farmers, traders, and consumers. A timely and accurate price forecast enables farmers to make informed decisions regarding selecting nearby markets for selling their produce, maximizing their chances of obtaining favorable prices. Farmers can utilize the provided information to make informed decisions regarding the optimal timing of their marketing strategies. Various statistical models have been used in the past to forecast the prices of agricultural commodities. However, it is essential to acknowledge that these models are subject to certain limitations regarding their underlying assumptions. We have taken the regression model, a machine learning classification technique, and long short-term memory, a deep learning technique to predict the crop price. The parameters for price prediction are crop type, nutrient value, minimum support price, crop variety, and location. This study proposes and implements a mechanism to predict crop prices from historical data. The chosen input variables utilize to develop regression and long-short-term memory models. The performance of these models evaluates using standard assessment metrics, including Mean Square Error, Root Mean Square Error, and Mean Absolute Percentage Error. Based on the experimental findings, it is evident that the Long-short-term memory model exhibits an outstanding level of fit and demonstrates a high degree of accuracy in predicting outcomes, surpassing other models and prior research. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer applications and Management.

关键词： Crop Linear regression Long short-term memory (LSTM) Minimum support price (MSP) Recurrent neural networks (RNN) Ridge regression

来源：评论

学校读者我要写书评

暂无评论

Adaptive Grasshopper Optimization Algorithm based Dynamic Cluster Head Selection and Energy Efficient Routing for Wireless Sensor Network (WSN) 3

Adaptive Grasshopper Optimization Algorithm based Dynamic Cl...

引用

3rd International Conference on Applied Artificial Intelligence and Computing, ICAAIC 2024

作者： Kanimozhi, T. Belina, S. Sara, V.J. Srm Institute of Science and Technology Faculty of Science and Humanities Department of Computer Science Tamil Nadu Chennai India Srm Institute of Science and Technology Faculty of Science and Humanities Department of Computer Applications Tamil Nadu Chennai India

ISBN: (纸本)9798350375190

Wireless Sensor Network (WSN) clustering is useful for developing routing algorithms that improves the scalability and longevity of the network. Cluster Head (CH) is essential for data transmission in the clustered WSN paradigm. Thus several cluster-based routing protocols have been introduced recently. As such, energy constraints affect both the duration of the network and energy-efficient routing. In this paper, Adaptive Grasshopper Optimization Algorithm (AGOA) is introduced for cluster-based routing and CH selection which increases routing efficiency, and maximizes network lifetime. Furthermore, high convergence rate and lower parameter complexity as compared to other optimization techniques. Here, Residual Energy (RE), distance to the Base Station (BS), distance to neighbors, node degree, and node centrality has been used for choosing the best CH. Additionally, the path between the BS and CH can be determined using AGOA. Lastly, the results routing protocols are evaluated using metrics including Packet Delivery Ratio (PDR), Packet Loss Ratio (PLR), Average energy consumption, and Network Lifetime. © 2024 IEEE.

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Forensic handwriting analysis: a hybrid classification framework for writer identification in Devanagari script

引用

Multimedia Tools and applications 2025年 1-12页

作者： Sethi, Monika Kumar, Munish Jindal, M.K. Department of Computer Science and Application Panjab University Chandigarh India P.G. Department of Information Technology Goswami Ganesh Dutta Sanatan Dharma College Chandigarh India Department of Computational Sciences Maharaja Ranjit Singh Punjab Technical University Punjab Bathinda India Department of Computer Science and Applications Panjab University Regional Centre Muktsar India

In a period marked by swift technological progress, the task of identifying writers through handwriting holds significant importance across various domains, including forensic investigation, plagiarism detection, and historical research. The importance of this endeavor has been further magnified by the widespread influence of digitalization. This study employs a hybrid approach that integrates cutting-edge deep learning techniques, specifically Convolutional Neural Networks (CNNs), with traditional machine learning methodologies, such as Support Vector Machines (SVM) and Random Forest (RF). Deep learning techniques are particularly valuable for analyzing extensive handwriting samples because they can automatically discern complex features and patterns from large datasets. In this research, we synthesize predictions from deep learning models and employ machine learning classification for writer identification based on handwriting analysis. Central to our study is a comprehensive dataset of Devanagari characters, collected from 220 unique writers. This dataset has been thoughtfully curated to validate the methodology we have employed. Our hybrid classification approach, combining CNN with SVM and CNN with RF, achieves remarkable accuracy rates of 91.49% and 88.78%, respectively—significantly surpassing the performance of standalone SVM and RF models, which achieved accuracies of 59.52% and 59%, respectively. Through a series of comprehensive experiments, we demonstrate the enhanced effectiveness and precision of our proposed methodology in the domain of Devanagari script writer identification. The findings of this study not only underscore the potential of our methodology but also represent a substantial advancement in the fields of pattern recognition and machine learning technology. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Underwater Packet Scheduling based on Modified Priority Backpressure and Peak Age of Information approach

International Journal of Systematic Innovation

引用

International Journal of Systematic Innovation 2023年第5期7卷 55-62页

作者： Mary, A. Caroline Kumar, A. V. Senthil Chennamma, H.R. Department of Computer Science Hindusthan College of Arts and Science Coimbatore India Department of MCA Hindusthan College of Arts and Science Coimbatore India Department of Computer Applications Sri Jayachamarajendra College of Engineering India

Objective: To develop an effective underwater packet scheduling algorithm considering the freshness of information. Underwater Communication has gained interest in recent days and Energy consumption, Freshness of information is considered to be an important metric. applications include defense-based applications, environmental monitoring, pollution detection, and ocean study. This paper works on the Age of Information-based concepts to ensure that information’s freshness is sustained. Peak AoI is used as an important metric to assign priority to the packets resulting in less packet delay and loss. Congestion is reduced as it works on the principle of backlog. And normalized class-based AoI helps in giving importance according to the importance of packets. As the value of information reduces over time, the proposed technique helps to maintain freshness. By varying the number of nodes and speed of nodes simulation results are shown, and delay, throughput, packet delivery ratio, and energy consumed are calculated. Energy consumed is almost reduced to two third and as Information freshness is given importance, packet loss and delay are reduced. © 2023, International Journal of Systematic Innovation. All rights reserved.

关键词： Backpressure Peak AoI Priority Underwater

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：