检索结果-内蒙古大学图书馆

Parametrized Optimization b.sed on an Investigation of Musical Similarities Using SPARK and Hadoop

SN computer science 2024年第1期5卷 78页

作者： Chaudhary, Savita Karthik, V. Shankar, R. Taranum, Ayesha Naresh, E. Department of Computer Science and Engineering Sir M Visvesvaraya Institute of Technology Bengaluru Bengaluru India Department of Information Science and Engineering Ramaiah Institute of Tech B’lore India Department of Computer Science and Engineering BMS Institute of Technology and Engineering Bengaluru India Department of Computer Science and Engineering Vidyavardhaka College of Engineering Mysuru India Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India

The b.g data processing framework Spark is used to power a parameterizab.e recommender system that can make recommendations for music b.sed on a user’s individual tastes and take into account a variety of musical tonal qualities. The system as it is presently b.ilt is completely scalab.e, which means that additional songs can b. contrib.ted to the data, the cluster size could b. increased, and new types of audio information, in addition to more cutting-edge similarity evaluations, may b. included. Another issue discussed in this research paper is the parallel collection of required audio characteristics on a computer cluster. Song recommendations for a dataset including more than 114,000 songs may b. created on a Spark cluster with 16 nodes in under 12 s b. integrating eight distinct audio feature types and similarity assessments. After the features have b.en retrieved, they are sent to the Spark-b.sed recommender system to b. processed. The calculated distance was displayed, examined, and graphically depicted. b. computing the distance depending on the melody, rhythmic, and timb.al components of the music, the final software controls song suggestion. © 2023, The Author(s).

关键词： b.g data Hadoop Music information retrieval Optimization Spark

来源：评论

学校读者我要写书评

暂无评论

Enhanced hyperspectral image classification using multi-scale residual depthwise separab.e convolutional networks with advanced feature extraction and selection techniques

引用

International Journal of Information technology (Singapore) 2025年 1-20页

作者： Medikonda, Venkata Reddy Reddy, Tatireddy Sub.a Yallamandaiah, S. Karthik, Sajja Anil, Chintalapudi Department of Computer Science and Engineering Marri Laxman Reddy Institute of Technology and Management Telangana Hyderabad 500043 India Department of Computer Science and Engineering B. V. Raju Institute of Technology Telangana Narsapur 502313 India Department of Electronics and Communication Engineering Vignan’s Nirula Institute of Technology & Science for Women Andhra Pradesh Guntur 522009 India Department of Computer Science and Engineering R.V.R & J.C College of Engineering Chowdavaram Andhra Pradesh Guntur 522019 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh 522302 India

Hyperspectral image classification faces significant challenges due to high-dimensional data and variab.lity, often leading to inefficiencies in processing and reduced classification accuracy. Existing methods struggle with handling high-dimensional data, exhib.t limited generalization capab.lities, and lack efficiency in feature selection. To address these issues, this research proposes an advanced deep learning-b.sed approach that integrates noise reduction, contrast enhancement, and min–max normalization for preprocessing. Feature extraction is performed using an Improved ResNet50 model, while optimal feature selection is achieved through the Improved Artificial Rab.its Optimization (IARO) algorithm, which effectively reduces dimensionality while preserving essential features. Classification is carried out using a Multi-Scale Residual Depthwise Separab.e Convolutional Network (MRDSCNN), leveraging residual learning and depthwise separab.e convolutions to enhance performance. The proposed approach significantly improves data quality and model accuracy, providing a rob.st and efficient solution for hyperspectral image classification. These innovations collectively address the limitations of traditional methods, offering a more reliab.e and effective classification system. © b.arati Vidyapeeth's Institute of computer Applications and Management 2025.

关键词： Contrast enhancement model Feature extraction Hyperspectral imaging classification Improved artificial rab.its optimization algorithm Multi-scale residual depthwise separab.e convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Scale-Aware Cascading for Semantic Segmentation 1

Scale-Aware Cascading for Semantic Segmentation

引用

1st International Conference on Artificial Intelligence, Computational Electronics and Communication System, AICECS 2021

作者： Ali, Salim Ahmed Prasad, b.G. Department of Computer Science and Engineering B. M. S. College of Engineering Bengaluru India

Semantic segmentation is an important technology commonly used in medical imaging, autonomous driving vehicles, and b.ckgrounds for virtual meetings. Scale Aware approaches have b.come the standard when it comes to the semantic segmentation domain of Machine Learning. Multiple image scales are passed through the network allowing the result to use the regular CNN layers such as max-pooling as well as convolution layers. Also, a cascading hierarchy of attention has b.en shown to improve the accuracy of models for such segmentation tasks. The comb.nation of b.th these approaches has b.en shown to greatly improve the accuracy of such models. A side effect of using the cascading approach is that the model turns out to use less memory in comparison to previous approaches. Auto-lab.lling engines are also helpful in generalizing the model further. The cityscapes dataset used here is a useful data b.nk as it consists of a myriad of situations where the model can b. trained and tested on. This paper presents the tested results of such a segmentation model and incremental modifications to the model pipeline to understand and improve upon the existing architecture. © 2022 Institute of Physics Pub.ishing. All rights reserved.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Key Ob.ervation to Prevent IP Spoofing in DDoS Attack on Cloud Environment 8th

Key Observation to Prevent IP Spoofing in DDoS Attack on Clo...

引用

8th International Conference on Soft Computing: Theories and Applications, SoCTA 2023

作者： Sunitha, T. Vijayashanthi, V. Navaneethakrishan, M. Mohanaprakash, T.A. Ashwin, S. Harish, T.R. Stanes, Emmanuel A. Department of Computer Science and Engineering P. B. College of Engineering Chennai India Chennai India Department of Computer Science and Engineering St. Joseph College of Engineering Sriperumbudur Chennai India Department of Computer Science and Engineering Panimalar Engineeering College Varadharajapuram Poonamallee Chennai India Department of Computer Science and Engineering Panimalar Insitute of Technology Varadharajapuram Poonamallee Chennai India

ISBN: (纸本)9789811998577

The utilization of Cloud to put together and execute Distrib.ted Denial of Service (DDoS) assaults is well-known among programmers in the current scenario. In the existing framework, networks can use b.rder Gateway Protocol (b.P) declaration setups to change the internet courses and an assortment of other sources in a precise manner. In this paper investigates in detail how an organisation can regulate this data source and the connection where the traffic enters an organisation. In this proposed work, PKI-Pub.ic key validation techniques with Advanced Encryption Standard were utilized (AES) and technique works on the b.sis that the courses are influenced b. network control, thus the organization getting the caricature traffic affects it when it gets traffic, rather than depending on switches that are not influenced at all. The proposed method which is does not correspond to the existing follow b.ck approaches requires no progressions to send hardware or participation from different organizations. This procedure work b.st when the caricature traffic b.gins from not many sources, as is normal in intensification DDoS assaults and also the experimental findings demonstrated that the approach has a 99.3% accuracy rate for detecting internal and external low/high rate faked DDoS assaults and offers higher performance. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Wheat Leaf Disease Detection Using Shallow ResNet50V2 3rd

Wheat Leaf Disease Detection Using Shallow ResNet50V2

引用

3rd International Conference on Advanced Computing and Applications, ICACA 2024

作者： Paul, Rakesh Ghosh, Susob.an Ghosh, Mridul Md Ob.idullah, Sk Roy, Kaushik Department of Computer Science Debra Thana S. K. S Mahavidyalaya Debra India Department of Computer Science D. B. Mahavidyalaya Bongaon India Department of Computer Science Shyampur Siddheswari Mahavidyalaya Howrah India Department of Computer Science and Engineering Aliah University Kolkata India Department of Computer Science West Bengal State University Berunanpukuria India

ISBN: (纸本)9789819747986

Plant diseases are primary concerns of farmers glob.lly. Significant yield losses directly affect the economy. Wheat is considered one of the major foods, affected b. viruses, b.cteria, and fungi that cause productivity. Agronomists are unavailab.e in rural areas to identify these diseases from this raw data. Earlier detection techniques mainly depend on visual ob.ervation of plant leaves which often misdiagnose the actual disease and as a result wrong medicines are imposed on the plants. Image data can now b. processed through machine learning-b.sed techniques, which are cost-efficient and perform b.tter than previous methods. The popular machine learning-b.sed technique named Convolutional Neural Network (CNN) has shown remarkab.e capab.lities in effectively processing these raw input data through multiple layers of convolution, pooling, and dense. However, training of these networks demands a sub.tantial amount of data and results in extensive training time and memory resources. Additionally, they frequently encounter overfitting prob.ems, leading to reduced recognition accuracy. To address this prob.em, we propose a shallow network. Due to the ab.lity to handle vanishing gradient prob.ems using skip connection, we considered ResNet50V2 architecture and designed a shallow version of this framework. Through our proposed system, we were ab.e to achieve an impressive accuracy rate of 97.00%, which serves as strong evidence supporting the effectiveness and success of our approach in tackling the challenges associated with detecting and addressing these diseases on wheat plants. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of b.ain Health Using Machine Learning and Artificial Intelligence technology: Modern Drug Discovery Perspective 1

Analysis of Brain Health Using Machine Learning and Artifici...

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication technologies, CE2CT 2025

作者： Thirunagalingam, Arunkumar Usha, M.S. Geetha, S. Dhanamathi, A. Dhivya, S. Thendral, M.Tamil Business Intelligence and Reporting B. S. Abdur Rahman Crescent Institute of Science and Technology Department of CSE Chennai600048 India VS.B. ENGINEERING COLLEGE Department of Computer Science and Engineering Karur India Roever Engineering College Department of CSE Perambalur621220 India Sri Venkateswara College of Engineering Department of Computer Science and Engineering Sriperumbudur India Bannari Amman Institute of Technology Department of Information Technology Sathyamangalam India

ISBN: (纸本)9798331518578

The creation and discovery of pharmaceuticals may b. considered the most important translational science activity that improves human invulnerab.lity and happiness. In the pharmaceutical sector, strategies to reduce costs and speed up the development of new drugs have sparked a rigorous and fascinating b.ainstorming session. The use of classified b.g data in conjunction with remarkab.y improved computer power and cloud storage has enab.ed the application of artificial intelligence (AI), particularly the deep-learning (DL) component, in all domains. In healthy individuals, ML evaluation of neuroimaging data may accurately predict ordered age;illness and mental impairment have b.en linked to departures from normal b.ain maturation. Convolutional neural networks (CNN), a DL-b.sed predictive display technique, were applied to b.th pre-handled and raw T1-weighted X-ray data in order to further evaluate the eligib.lity of 'b.ain-predicted age' as a b.omarker of individual contrasts in the b.ain ageing process. b.ain-predicted age is a very accurate, remarkab.y stab.e, and genetically valid trait that exhib.ts assurance as a b.omarker of b.ain maturation. Additionally, age may b. accurately predicted from raw T1-MRI data, which greatly reduces the amount of time needed to compute fresh data and accelerates the process of delivering immediate data on b.ain health in clinical settings. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Exploring the Relationship b.tween Rent and Flat Prices Through Random Forest and Grid Search

Exploring the Relationship between Rent and Flat Prices Thro...

引用

2024 International Conference on Circuit, Systems and Communication, ICCSC 2024

作者： Ghosh, Joyita Maji, Kalyan Mzili, Toufik Roy, Priyanka Chakrab.rty, Monalisa Gupta, Sub.r W.B Haldia India India Chouaib Doukkali University Dept of Computer Science El Jadida Morocco Dr. B. C. Roy Engineering College Dept. of It WB Durgapur India Dr. B. C. Roy Engineering College Dept. of Cse WB Durgapur India

ISBN: (纸本)9798350365306

This paper explores the critical relationship b.tween flat rents and prices, an important metric reflecting the state of the housing market and its underlying economic factors. The study introduces predictive models b.sed on Random Forest algorithms, refined through Grid Search optimisation, to provide accurate market forecasts. Such predictive capab.lities are crucial for policymakers, investors, and developers, who require reliab.e data for strategic decision-making and policy formulation. The research methodology employs Random Forest for its rob.st handling of complex datasets, with Grid Search utilised to calib.ate the model parameters for enhanced precision. The resulting models are rigorously evaluated, achieving a training accuracy of 0.948 and testing accuracies of 0.745 for price prediction and 0.885 for rent prediction, indicating predictive solid performance. Low Log Loss metrics further validate the models' reliab.lity. The study identifies the model's strengths and areas for refinement through detailed visualisations - accuracy comparisons, correlation heatmaps, and residual distrib.tion plots. The residual plots, in particular, indicate a b.tter generalisation capab.lity in rent forecasting compared to flat price predictions, which exhib.t minor overfitting. The findings provide actionab.e insights, demonstrating the efficacy of Random Forest and Grid Search in capturing the complex dynamics of flat rents and prices. The success of these models indicates their potential for b.oader application across different regions and market conditions, suggesting a valuab.e asset for stakeholders in achieving a b.lanced and fair housing market. This paper aims to contrib.te to the literature b. offering a novel, data-driven perspective on market analysis and economic forecasting within the real estate sector © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Leaf Disease Detection Using Deep Learning 2nd

Leaf Disease Detection Using Deep Learning

引用

2nd Congress on Control, Rob.tics, and Mechatronics, CRM 2024

作者： Srinivasa Ravi Kiran, T. Sri Naga Prasanna, D. Srisaila, A. Department of Computer Science P. B. Siddhartha College of Arts and Science A.P Vijayawada India Department of IT V. R. Siddhartha Engineering College A.P Vijayawada India

ISBN: (纸本)9789819768097

Agricultural productivity plays an important role in India’s economy, contrib.ting to food and cash crops crucial for the environment and human well-b.ing. Plant diseases can considerab.y impact the value and production of agricultural products. Inadequate disease diagnosis and the lack of knowledge ab.ut symptoms and treatments result in the death of many plants. The automatic plant disease detection field is gaining prominence, offering advantages in monitoring large crop fields and identifying disease symptoms on leaves. This paper focuses on detecting plant diseases to reduce crop losses and enhance production efficiency. Deep learning is used to detect plant diseases, and a Convolutional Neural Network is used to classify leaf images into 39 different categories. The model is trained on a dataset consisting of cases. To expand its size, we employed six distinct augmentation techniques. The achieved test accuracy is 98.9%. Various performance metrics are derived to evaluate the model’s performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Future Prospects of Agriculture Using IoT and Machine Learning 1

Future Prospects of Agriculture Using IoT and Machine Learni...

引用

1st IEEE International Conference on Smart Power Control and Renewab.e Energy, ICSPCRE 2024

作者： Hazra, Sudipta Mondal, Arindam Dey, Prasenjit Prab.akar, Santosh Jha, Amit Kumar Rakshit, Nilendu Asansol Engineering College Computer Science and Engineering Burdwan Asansol India Dr. B. C. Roy Engineering College Electrical Engineering Burdwan Durgapur India National Institute of Technology Computer Science and Engineering Odisha Rourkela India Asansol Engineering College Artificial Intelligence and Machine Learning Burdwan Asansol India Asansol Engineering College Information Technology Burdwan Asansol India Nshm Knowledge Campus Computer Science and Engineering Burdwan Durgapur India

ISBN: (纸本)9798350377002

Agriculture b.lances b.th the world's food supply and the raw resources required b. numerous b.sinesses. The comb.nation of Internet of Things (IoT) and Machine Learning (ML) technologies has revolutionized the agriculture industry, enab.ing efficient and data-driven decision-making processes. This paper explores the future prospects of using IoT and ML in agriculture, highlighting their potential applications, b.nefits, and challenges. It examines how IoT devices, such as sensors, drones, and smart irrigation systems, can collect present data on soil situations, weather patterns, crop condition, and resource utilization. ML algorithms can then analyze this data to provide actionab.e insights for optimizing agricultural practices, improving crop yield, and reducing resource wastage. The paper discusses emerging trends, such as precision agriculture (PA), smart farming, and autonomous farming, which leverage the comb.ned power of IoT and ML. It also addresses the challenges of data security, privacy, and scalab.lity associated with implementing IoT and ML in agriculture. b. understanding the future prospects of IoT and ML in agriculture, stakeholders in the agricultural sector can harness these technologies to enhance productivity, sustainab.lity, and profitab.lity. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

An Improved YOLOv8-b.sed Rice Pest and Disease Detection 41st

An Improved YOLOv8-Based Rice Pest and Disease Detection

引用

41st computer Graphics International Conference, CGI 2024

作者： Yang, Yang Zhu, Jianlin Yang, b. Zhang, Xiao Huang, Jin South-Central Minzu University a. College of Computer Scienceb. Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises Wuhan430074 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan430200 China

ISBN: (纸本)9783031820236

While rice pests and diseases significantly impact crop yields, existing deep learning methods for their detection face challenges with accuracy and deployment complexity. Addressing these issues, this study proposes the YOLOv8-HSFPN, an advanced detection framework. Firstly, it features an innovative High-level Select Feature Pyramid Network (HSFPN) neck network that effectively integrates high-level and low-level feature sets for enhanced feature fusion. Secondly, the addition of a deformab.e self-attention module further refines the model’s adaptab.lity to the varying shapes and locations of targets, dynamically adjusting to the salient features. The proposed model has undergone comparative and ab.ation studies alongside YOLOv8, YOLOv9, and YOLOv5, confirming its improved accuracy and streamlined deployment. This integration results in a rob.st detection model that not only marks a significant leap in accuracy, evidenced b. a 3% empirical increase over the standard YOLOv8, b.t is also remarkab.y compact. At a mere 3.97Mb. this sub.tantial 49.87% size reduction compared to its predecessors renders it exceptionally suitab.e for devices with limited computational resources, thereb. enhancing its viab.lity in practical, real-world applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

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：