检索结果-内蒙古大学图书馆

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： Sk Khader Basha NagaMalleswara Rao Purimetla D Roja Nagagopiraju Vullam Lavanya Dalavai Sai Srinivas Vellela Dept. of CSE-Data Science Chalapathi Institute of Technology Guntur AP India Dept. of CSE Chalapathi Institute of Technology Guntur AP India Dept. of CSE Chalapathi Institute of Engineering and Technology Guntur AP India

The utilisation of virtualization technologies in conjunction with cloud computing has emerged as a significant and influential trend within the Information Technology (IT) sector. Cloud computing has significantly transformed the development landscape of mobile ubiquitous services by introducing notable attributes such as reliability and cost-effectiveness. Consequently, it has successfully penetrated the market, bringing about substantial changes in the industry. While it is possible to easily convert numerous types of best-effort mobile ubiquitous applications to cloud infrastructures, it is crucial to thoroughly analyse essential elements in order to enhance the effectiveness of cloud computing infrastructures for real-time healthcare applications. When programme clients observe an anomaly, there is a substantial increase in the data transfer rate. Nevertheless, there are inherent issues in the current allocation of computational resources by server-side processes to effectively manage the fluctuating and time-varying data quantities. This article introduces a novel auto-scaling technique for servers, which aims to dynamically allocate virtual resources. The suggested method’s efficacy in scaling virtual resources up and down in response to the number of real-time tasks is evaluated through testing conducted on an Amazon EC2 platform. The obtained findings demonstrate the efficient performance of the mechanism.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Guidelines for Mechatronic Ecosystem Monitoring and Management

Towards Guidelines for Mechatronic Ecosystem Monitoring and ...

引用

2021 Conference on Artificial Life, ALIFE 2021

作者： Dorin, Alan Parry, Hazel Cook, James Computational and Collective Intelligence Group Dept. of Data Science & AI Monash University Australia Agriculture and Food CSIRO Australia Hawkesbury Institute for the Environment Western Sydney University Australia

Mechatronic devices installed as Ecosystem Management and Monitoring Units, EMUs, are an emerging trend with the potential to improve our understanding of natural and agricultural ecosystems. They may improve biodiversity and provide socio-economic benefits, but if poorly implemented such technology can undermine conservation efforts, damage habitat and drive people into poverty. This article proposes draft guidelines that help to ensure EMUs embedded within ecosystems generate more global benefit than harm, preserve the aesthetic and cultural value of their environment, and kill organisms only as a last resort. © 2021 ALIFE. All Rights Reserved.

关键词： agricultural technology Artificial Life ethics biodiversity monitoring ecological robotics species conservation

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Energy Optimization: Household Power Consumption Prediction With LSTM Networks and PyTorch-Ray Tune in Smart IoT Systems

AI-Driven Energy Optimization: Household Power Consumption P...

引用

International Conference on Microelectronics, ICM

作者： Vinoth Kumar Kolluru Yagnesh Challagundla Advaitha Naidu Chintakunta Bappadittya Roy Amine Bermak Renuka Devi S M Department of Data Science Stevens Institute of Technology Hoboken NJ USA Engineering Education Dept. University of Florida USA Department of Computer science and Engineering University of North Carolina Charlotte USA School of Electronics Engineering VIT-AP University Amaravati Andhra Pradesh India College of Science and Engineering Hamad bin Khalifa Universityy Ar-Rayyan Qatar Dept. of ECE G Narayanamma Institute of Technology & Science (for women) Hyderabad

ISBN: (数字)9798350379396

ISBN: (纸本)9798350379402

Energy optimization is critical in smart home systems and IoT networks, necessitating innovative models that reduce energy use. This research presents two Long Short-Term Memory (LSTM) network models for estimating home power consumption using time-series data. The first model employs a standard LSTM technique with multivariate characteristics including global active power, voltage, and sub-metering variables. This technique strikes a balance between prediction accuracy and computing economy, making it ideal for resource-constrained applications. The second model provides an optimized version of the LSTM, which uses PyTorch and Ray Tune for hyperparameter optimization. The optimization focuses on tweaking learning rates, batch sizes, and LSTM layers to improve model accuracy and convergence speed. Using hyperparameter tuning, the Mean Squared Error (MSE) for global active power forecasts is decreased to 0.0018, proving its appropriateness for low-resource IoT systems. Both models are tested on a resampled real-world household electric power consumption dataset for effective training. The study emphasizes the advantages of multivariate time-series analysis and hyperparameter optimization, demonstrating that the optimized LSTM model can accurately predict energy consumption, enhance energy management in smart homes, and lower computing costs. Future work will look into combining more IoT data streams and real-world deployment for further improvement. The findings add to the expanding body of knowledge about energy optimization in IoT environments, addressing the crucial demand for effective, real-time energy management systems.

关键词： Power demand Accuracy computational modeling Biological system modeling Smart homes Predictive models Hyperparameter optimization Real-time systems Long short term memory Optimization

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Word2Vec, FastText, and Glove Embeddings for Synonym Identification in Bugis Language

Comparative Study of Word2Vec, FastText, and Glove Embedding...

引用

Informatics International Conference (BTS-I2C), Beyond Technology Summit on

作者： Wahyu Ramadhan Arianto Yuyun Ahmad Abrar Najirah Umar Nasrullah Nurfaedah Gusnawaty Asril Jarin Dept. of informatics engineering Handayani University of Makassar Makassar Indonesia Research center for data and information science National Research and Innovation Agency Bandung Indonesian Dept. of informatics management Handayani University of Makassar Makassar Indonesia Dept. of Regional Literature Hasanuddin University Makassar Indonesia

ISBN: (数字)9798331508579

ISBN: (纸本)9798331508586

This research aims to analyze the performance of word vectors generated by three pre-trained word embedding models, namely Word2Vec, Fast'Text, and Glove, to detect synonyms at the word level in the Bugis language. The word vectors from each model were integrated with a Bugis language dataset containing 12,060 monolingual texts, and then trained using the Long Short-Term Memory (LSTM) model. The results show that Word2Vec has the highest accuracy of 0.9412, followed by Glove with 0.9353 and FastText with 0.9262. Additional experiments with cosine similarity revealed that Glove performed best for predicting synonyms across all word occurrence frequency categories, while FastText and Word2Vec had inferior results. These findings indicate that although high training accuracy is achieved, it does not always imply that the model will excel in predicting synonyms.

关键词： Training Measurement Accuracy Semantics Predictive models Transformers Vectors Informatics Long short term memory Context modeling

来源：评论

学校读者我要写书评

暂无评论

OpenRAND: A Performance Portable, Reproducible Random Number Generation Library for Parallel Computations

SSRN

引用

SSRN 2023年

作者： Khan, Shihab Shahriar Palmer, Bryce Edelmaier, Christopher Aktulga, Hasan Metin Dept. of Computer Science Michigan State University East LansingMI48824 United States Dept. of Mechanical Engineering Michigan State University East LansingMI48824 United States Dept. of Computational Mathematics Science and Engineering Michigan State University East LansingMI48824 United States Center for Computational Biology Flatiron Institute New YorkNY10010 United States

We introduce OpenRAND, a C++17 library aimed at facilitating reproducible scientific research through the generation of statistically robust and yet replicable random numbers. OpenRAND accommodates single and multi-threaded applications on CPUs and GPUs and offers a simplified, user-friendly API that complies with the C++ standard's random number engine interface. It is portable: it functions seamlessly as a lightweight, header-only library, making it adaptable to a wide spectrum of software and hardware platforms. It is statistically robust: a suite of built-in tests ensures no pattern exists within single or multiple streams. Despite the simplicity and portability, it is remarkably performant\textemdash matching and sometimes even outperforming native libraries by a significant margin. Our tests, including a Brownian walk simulation, affirm its reproducibility and highlight its computational efficiency, outperforming CUDA's cuRAND by up to 1.8 times. © 2023, The Authors. All rights reserved.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

An Extensive Machine Learning Framework Employing Ensemble Classifiers for Heart Disease Detection

An Extensive Machine Learning Framework Employing Ensemble C...

引用

International Conference on Innovative Mechanisms for Industry Applications (ICIMIA)

作者： E. Chandralekha S. Vinodhini V Kandasamy P. Rama S Ravikumar T.R Saravanan Dept.of CSE Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Dept. of Information Technology Velammal Engineering College Chennai India Dept. of Information Technology Panimalar Engineering College Chennai India Dept. of Computing Technologies College of Engineering and Technology Faculty of Engineering and Technology SRM Institute of Science and Technology Chennai India Dept. of Computational Intelligence SRM Institute of Science and Technology Chennai India

Heart disease is a significant global health challenge, impacting many lives and often being a leading cause of mortality and illness. Detecting heart disease accurately and promptly is essential for effective medical care. Due to the complex interplay of risk factors and the intricate nature of diagnosis, advanced technologies like machine learning are being explored. This study introduces a comprehensive framework that employs machine learning techniques for heart disease detection. The framework involves critical stages such as data preprocessing, feature selection, and training ensemble classifiers. Experimental results highlight the importance of specific attributes in each classifier, offering insights into predictions. Notably, attributes like oldpeak, thalach, ca, cp, and thal are key features in the Random Forest classifier, while Gradient Boosting underscores ca, cp, thal, oldpeak, and age. AdaBoost and the Extra Trees Classifier reveal similar significant attributes. Evaluation metrics emphasize the models’ robust performance, with the Extra Trees Classifier achieving the highest accuracy. This research contributes to a practical heart disease detection framework with potential for improving medical decision-making.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Study of Inductive Graph Neural Network Models for Text Classification

Comparative Study of Inductive Graph Neural Network Models f...

引用

Advancements in Smart, Secure and Intelligent Computing (ASSIC), International Conference on

作者： Saran Pandian Uttkarsh Chaurasia Shudhanshu Ranjan Shefali Saxena Data Science DAIICT Gandhinagar India Dept. of Computer Science and Engineering NIT Hamirpur India Dept. of Computer Science and Engineering Presidency University Banglore India Dept. of Electronics and Communication NIT Hamirpur India

Graph neural networks(GNN) are a special variant of neural networks which help in dealing with unstructured data such as graph data. The advent of the GNN has helped in dealing with problems in different domains, especially in the domain of Natural Language Processing(NLP). In NLP, GNNs are used to implement tasks such as text classification which has a wide variety of applications. There are two ways to represent the text data using GNN namely, Inductive and transductive. In this paper, we apply the approach of the inductive model using different variants of GNN. We observed that the GAT variant gave better performance compared to other variants. Moreover, we observed that the complexity of the model and the dataset size influences the entropy of the output.

关键词： computational modeling Text categorization Natural languages Graph neural networks Entropy Complexity theory Task analysis

来源：评论

学校读者我要写书评

暂无评论

Computer Vision Based Drone Detection Using Mask R-CNN 2

Computer Vision Based Drone Detection Using Mask R-CNN

引用

2nd IEEE International Conference on Artificial Intelligence in Everything, AIE 2022

作者： Mubarak, Auwalu Saleh Vubangsi, M. Al-Turjman, Fadi Ameen, Zubaida Said Mahfudh, Abdulmunaim Saleh Alturjman, Sinem Near East University Ai and Robotics Institute Artificial Intelligence Engineering Dept. Mersin10 Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Mersin10 Turkey University of Bamenda Computational Materials Science Lab Htttc Bambili Cameroon

ISBN: (数字)9781665474009

ISBN: (纸本)9781665474009

Security of private and military areas is very important, drones are becoming more available day by day even though they are used for different purposes. In no-fly zones like metros, airports, private properties and so on, unauthorized drones can be detected using computer vision models, in this study Mask-RCNN with two different backbones (ResNet-50 and MobileNet) was employed to detect drones. It was observed that the Mask-RCNN with ResNet-50 as backbone achieves mAP of 0.965, mAP-50 of 0.991, mAP-75 of 0.958 and recall of 0.961. © 2022 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Cybernated Watermarking Approach on Image with Cryptographic Encryption

Cybernated Watermarking Approach on Image with Cryptographic...

引用

Computer, Communication and Control (IC4), International Conference on

作者： R. Sivasankari T Veeramakali S M Mustafa Nawaz P. Prakash P Umadevi A Alvin Ancy Dept. of Computer Science and Engineering B.S.Abdur Rahman Crescent Institute of Science and Technology Dept of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Tamilnadu Dept of Computer Science and Engineering Sri Sai Ram Institute of Technology Dept of Electronics and Communication Engineering Sri Sai Ram Engineering College Department of S & H KPR Institute of Engineering and Technology Coimbatore Dept of Electronics and Communication Engineering Anna University Chennai

Digital watermarking of interactive media content has become an active experimentation field in recent years. In addition to reviewing some of the methods that have been developed for various media types; a general structure for watermark engrafting and identification is outlined. We highlight a few of these application-oriented differences, including copyright protection, substantiation, tamper identification, and data hiding, as well as the technological and system conditions for different media types such as digital photos, digital files, digital audio, and text. We describe a general structure for digital watermarking-based image copyright protection in this approach. In this paper, we outline the pre-processing and implementation of tide marking technique where Twofish algorithm and double encryption is described. The image processing toolbox is also specified by comparing five different image processing techniques. In addition, the post implementation is carried out with the wavelet toolbox and matlab coder to analyze signal, image properties and generate the efficient code for embedding the text.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OpenRAND: A Performance Portable, Reproducible Random Number Generation Library for Parallel Computations

arXiv

引用

arXiv 2023年

We introduce OpenRAND, a C++17 library aimed at facilitating reproducible scientific research through the generation of statistically robust and yet replicable random numbers. OpenRAND accommodates single and multi-threaded applications on CPUs and GPUs and offers a simplified, user-friendly API that complies with the C++ standard’s random number engine interface. It is portable: it functions seamlessly as a lightweight, header-only library, making it adaptable to a wide spectrum of software and hardware platforms. It is statistically robust: a suite of built-in tests ensures no pattern exists within single or multiple streams. Despite the simplicity and portability, it is remarkably performant—matching and sometimes even outperforming native libraries by a significant margin. Our tests, including a Brownian walk simulation, affirm its reproducibility and highlight its computational efficiency, outperforming CUDA’s cuRAND by up to 1.8 times. © 2023, CC BY.

关键词： Random number generation

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：