检索结果-内蒙古大学图书馆

Distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International Conference on

作者： H. Manoj T. Gadiyar Sivakumar KK Nainee Patel Shadaksharaiah C Amit Lathigara Vanguri Smitha Department of Information Science and Engineering Canara Engineering College Benjanapadavu India School of Liberal Arts and Sciences Mohan Babu University Tirupati India Department of Computer Science & Engineering IES Insititute of Technology and Management IES University Bhopal India Department of Computer Science and Design Bapuji Institute of Engineering & Technology (BIET) Davangere India Department of Computer Science and Engineering School of Engineering RK University Rajkot India Department of Computer Science and Engineering (AI&ML) CMR Engineering College Hyderabad India

ISBN: (数字)9798331533663

ISBN: (纸本)9798331533670

Joining people, processes, data, and gadgets in a sustainable way is called the environmentally friendly Internet of Everything (Green IoE). Traditional encryption techniques, however, face serious security threats from the advent of quantum computing. Discrete logarithmic and factorisation issues make current cryptography systems like RSA and ECC susceptible to quantum attacks. In order to improve Green IoE security without sacrificing energy efficiency, this article suggests using lightweight post-quantum signature methods. The promising members are the ones derived from the lattice, hash, or multivariate quadratic theory when it comes to the choice between security and performance. This research identifies how it is possible to integrate quantum-safe security for Green IoE applications without eradicating the low power requirements inherent in these systems. It is by combining these little post-quantum signatures into Green IoE that it becomes possible to come up with a safe system that meets the set environmental standards. Realizing the need to construct a dependable safety system with Green IoE in the post-quantum period, the research evaluates the strength and speed of the proposed cryptography algorithms.

关键词： Accuracy Quantum computing Green products Stability criteria Robustness Timing Cryptography Sustainable development Streams Standards

来源：评论

学校读者我要写书评

暂无评论

Instagram Reach Analysis using Machine Learning Algorithms

Instagram Reach Analysis using Machine Learning Algorithms

引用

Computational Intelligence for Security, Communication and Sustainable Development (CISCSD), International Conference on

作者： Abhinav G Bhat Tarun Rao K Shridhar B. Devamane Udayaprasad P K Ravindranath R. C Lakshmikantha G C Department of Computer Science Global Academy of Technology Bengaluru Karnataka India Department of AI & ML Global Academy of Technology Bengaluru Karnataka India

ISBN: (数字)9798350365405

ISBN: (纸本)9798350365412

One of the most widely used social media platforms right now is Instagram. Instagram is used professionally by those who want to promote their brands, develop their portfolios and blogs, and produce various types of content. Instagram is a well-known program used by millions of users in multiple niches, and it is constantly evolving to serve both users and content creators better. Nevertheless, as this fluctuates, it impacts the audience for our postings, which has a long-term impact on us. So, a content producer must examine the analytics of their Instagram reach if they hope to succeed on the platform over the long term.

关键词： Machine learning algorithms Social networking (online) Forestry Boosting Web sites Multimedia communication Security Sustainable development Portfolios Computational intelligence

来源：评论

学校读者我要写书评

暂无评论

Empowering Smart Homes with Fog Computing for IoT Connectivity

Empowering Smart Homes with Fog Computing for IoT Connectivi...

引用

2024 International Conference on Decision aid sciences and Applications, DASA 2024

作者： Ahmed, Amjed Abbas Najim, Ali Hamza Mahdi, Ali Jafer Ali Alheeti, Khattab M. Mohd Satar, Nurhizam Safie Abdallah Hashim, aisha Hassan Center for Cyber Security Faculty of Information Science and Technology Universiti Kebangsaan Malaysia Bangi Malaysia Department of Computer Techniques Engineering Baghdad Iraq Department of Computer Technical Engineering Al-Diwaniyah Iraq AI-Zahraa University for Women Department of Scientific Affairs Bangi43600 Malaysia College of Computer and Information Technology University of Anbar Computer Networking Systems Department Anbar Iraq Cyber Security Faculty of Information Science and Technology Bangi43600 Malaysia International Islamic University Malaysia Faculty of Engineering Department of Electrical and Computer Engineering Selangor Malaysia

ISBN: (纸本)9798350369106

Innovative grid technology leverages Information and Communication Technology (ICT) to enhance energy efficiency and mitigate losses. This paper introduces a 'novel three-tier hierarchical framework for smart homes within the Internet of Things (IoT)' ecosystem, addressing the current shortage of intelligent solutions that underutilize IoT advantages. Our framework's primary objective is to elevate smart homes to the microgrid level, enabling the seamless integration from the microgrid's renewable distributed energy sources and attaining maximum energy efficiency. In addition to traditional data processing, we propose the application of fog computing in smart homes. Through a rigorous simulation using real smart meter datasets, our study demonstrates that fog computing, mainly when using predictive filtering, may drastically cut down on the amount of data being sent and the load on the home's network. This innovation holds immense potential for revolutionizing energy management and resource allocation in the context of smart homes, thus contributing to a sustainable and efficient future. This research represents a critical step towards harnessing the power of IoT and fog computing in smart grids and homes, offering a promising path towards more intelligent, eco-friendly, and energy-efficient living spaces. © 2024 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Advancing Medical Imaging: A Focus on Efficient Net for Brain Tumor Classification

Advancing Medical Imaging: A Focus on Efficient Net for Brai...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： R Shashidhar R Manasa K M Megha P Priyanga A S Manjunath M Roopa Department of Electronics and Communication Engineering JSS Science and Technology University Mysuru INDIA Department of Electronics and Communication Engineering Dayananda Sagar College of Engineering Bengaluru INDIA Department of Computer Science and Engineering(AI & ML) RNS Institute of Technology Bengaluru INDIA Department of Computer Applications JSS Science and Technology University Mysuru INDIA

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

In the field of medical diagnosis, the increasing occurrence of brain tumors calls for creative approaches to detect and intervene at early stages. This proposed work focus on the Efficient Net (EffNet) architecture to address the challenges associated with brain tumour recognition and sorting from Magnetic Resonance Imaging (MRI) scans. The main objectives are outlined to develop a robust model capable of discriminating between various tumour types and normal brain tissues. Four distinct classes—glioma tumour, pituitary tumour, meningioma tumour, and no tumour compose the dataset, providing diversity for training and evaluation. Using projected method got the accuracy of 98.08% accuracy. Our proposed method detects the all the four classes effectively.

关键词： Training Accuracy Image recognition Magnetic resonance imaging Brain modeling Medical diagnosis Information technology Medical diagnostic imaging Tumors Sorting

来源：评论

学校读者我要写书评

暂无评论

Performance comparison of machine learning algorithms for coronary heart disease prediction

Performance comparison of machine learning algorithms for co...

引用

Computational Intelligence for Security, Communication and Sustainable Development (CISCSD), International Conference on

作者： Bharath RC Aneesh RT Aniruddha GJ Shridhar B. Devamane Ravindranath R.C Lakshmikantha G C Department of Computer Science Global Academy of Technology Bengaluru Karnataka India Department of AI & ML Global Academy of Technology Bengaluru Karnataka India

ISBN: (数字)9798350365405

ISBN: (纸本)9798350365412

The algorithms used in these machine learning models are quite straightforward and easy to understand, and they may produce predictions. These models have numerous business and scientific applications. Machine Learning model predictions are employed across many disciplines, including biology, behavioural sciences, environmental sciences, social sciences, and economics. We have discussed both the theoretical and practical elements in this paper.

关键词： Heart Machine learning algorithms Biological system modeling Social sciences Predictive models Prediction algorithms Security Sustainable development Regression tree analysis Random forests

来源：评论

学校读者我要写书评

暂无评论

Development and Implementation of a Virtual Reality Simulation for an Immersive College Environment Using the Unity Game Engine

Development and Implementation of a Virtual Reality Simulati...

引用

North Karnataka Subsection Flagship International Conference (NKCon), IEEE

作者： Ashwin Raj Lendalay Rupesh Pabba Sudheer Reddy Katta Mohd Afnan Ahmed R U Karthik Kowdodi Siva Prasad Computer Science With AI & ML Hyderabad Institute of Technology and Management Hyderabad India Mechanical Engineering Hyderabad Institute of Technology and Management Hyderabad India

ISBN: (数字)9798350364569

ISBN: (纸本)9798350364576

Virtual Reality (VR) simulation has emerged as a transformative technology with applications spanning various fields such as education, healthcare, training, and entertainment. This research paper explores the advancements, methodologies, and impacts of VR simulation, providing a comprehensive review of current technologies and their *** paper details the development and implementation of a Virtual Reality (VR) walkthrough simulation of a college environment using the Unity game engine. The project aims to offer users an immersive and interactive experience that closely mirrors the sensation of navigating through a physical establishment. The simulation integrates lifelike visuals, intuitive navigation, and interactive elements to create a compelling virtual environment. Through this innovative approach, users can experience a realistic and engaging representation of the college, enhancing their understanding and exploration of the space. Traditional architectural models, typically rendered with pen-and-paper blueprints or clay models, often lack detailed visualization and feasibility for quick modifications. This research explores the advantages of utilizing Virtual Reality (VR) for visualizing architectural models of college environments with significantly enhanced detail, both exterior and interior. VR technology allows for the immediate identification and correction of errors, facilitating rapid and efficient updates. Unlike traditional methods, which require redrawing entire blueprints for minor changes, VR’s layered structure permits individual modifications without impacting the whole model. Leveraging the Unity game engine, multiple architects can collaborate seamlessly, working together with clients to develop a satisfactory and detailed VR model of the building. This approach not only improves design accuracy but also enhances collaborative efforts, demonstrating the substantial benefits of VR in modern architectural practices.

关键词： Solid modeling Visualization Accuracy Navigation Virtual environments Games Space exploration Stakeholders Engines Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

The tale of two sides in the 2019 anti-CAA protest—An analytical framework

引用

International Journal of Information Management Data Insights 2024年第2期4卷

作者： Das, Bhaskarjyoti Ragothaman, Krithika Kesari, Raghav T. Sudarshan, T.S.B. Department of Computer Science and Engineering in AI & ML PES University Banashankari Stage III Bengaluru 560085 India Department of Computer Science and Engineering PES University Banashankari Stage III Bengaluru 560085 India

The 2019 anti-CAA protest in India witnessed massive Twitter participation from people on both sides. It was unique compared to most online social movements that showcase people's movements against authority. The article offers a framework for a big data-driven outside-in analysis of such online social movements. Unlike most existing research focusing on a particular aspect of such a movement, the framework presented examines mobilization and counter-mobilization from various angles. The work systematically juxtaposes the proponents and opponents using statistical analysis, text mining, and graph analysis techniques. Different aspects such as users, content, themes and focus of the conversations, conversational patterns, instrumentation of virality, leadership styles, emotions, and toxicity of the discourse have been considered. The study also examines them as types of frame alignment effort as per Frame Alignment Theory. The framework proposed by this work can be successfully employed to understand any future online social movement and any inductive research using user-generated Big Data. © 2024 The Authors

关键词： Analytical framework Conversation patterns Emotion and toxicity Frame alignment Hashtag virality Leadership style Lexical divergence Online social movement

来源：评论

学校读者我要写书评

暂无评论

Converging to a Lingua Franca: Evolution of Linguistic Regions and Semantics Alignment in Multilingual Large Language Models 31

Converging to a Lingua Franca: Evolution of Linguistic Regio...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zeng, Hongchuan Han, Senyu Chen, Lu Yu, Kai X-LANCE Lab Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence SJTU AI Institute Shanghai Jiao Tong University Shanghai China Suzhou Laboratory Suzhou China

ISBN: (纸本)9798891761964

Large language models (LLMs) have demonstrated remarkable performance, particularly in multilingual contexts. While recent studies suggest that LLMs can transfer skills learned in one language to others, the internal mechanisms behind this ability remain unclear. We observed that the neuron activation patterns of LLMs exhibit similarities when processing the same language, revealing the existence and location of key linguistic regions. Additionally, we found that neuron activation patterns are similar when processing sentences with the same semantic meaning in different languages. This indicates that LLMs map semantically identical inputs from different languages into a "Lingua Franca", a common semantic latent space that allows for consistent processing across languages. This semantic alignment becomes more pronounced with training and increased model size, resulting in a more language-agnostic activation pattern. Moreover, we found that key linguistic neurons are concentrated in the first and last layers of LLMs, becoming denser in the first layers as training progresses. Experiments on BLOOM and LLaMA2 support these findings, highlighting the structural evolution of multilingual LLMs during training and scaling up. This paper provides insights into the internal workings of LLMs, offering a foundation for future improvements in their cross-lingual capabilities. The codes are available at: https://***/X-LANCE/LinguaFranca. © 2025 Association for Computational Linguistics.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

A Comparative Study of Machine Learning Algorithms for Predicting Customer Churn: Analyzing Sequential, Random Forest, and Decision Tree Classifier Models

A Comparative Study of Machine Learning Algorithms for Predi...

引用

Electronics and Sustainable Communication Systems (ICESC), 2020 International Conference on

作者： Ratnam Dodda C. Raghavendra Marpu Aashritha Hima Varshini Macherla Anusha Reddy Kuntla Department of CSE (AI&ML) CVR College of Engineering Hyderabad India Department of CSE (DS) CVR College of Engineering Hyderabad India Department of Computer Science and Information Technology CVR College of Engineering Hyderabad India

ISBN: (数字)9798350379945

ISBN: (纸本)9798350379952

Predicting customer churn is vital for businesses aiming to retain their customer base and enhance profitability. This study investigates the effectiveness of three prominent machine learning algorithms Sequential, Random Forest, and Decision Tree Classifier in forecasting customer churn. Utilizing a dataset encompassing historical customer information such as demographics, transaction records, and interaction patterns, we preprocess the data by addressing missing values, encoding categorical variables, and scaling numerical features. Subsequently, each model is trained on the processed dataset, and their performance is assessed using accuracy as the evaluation metric. Our findings demonstrate promising predictive capabilities, with the Sequential model achieving an accuracy score of 94%, followed by Random Forest with 92%, and Decision Tree Classifier with 91%. Additionally, we conduct a comparative analysis of these models, focusing on interpretability, computational complexity, and robustness. While the Sequential model excels in predictive accuracy by capturing temporal dependencies in sequential data, Random Forest and Decision Tree Classifiers offer simplicity and interpretability, catering to scenarios where model transparency is paramount.

关键词： Analytical models Accuracy Machine learning algorithms Computational modeling Predictive models Prediction algorithms Data models Numerical models Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Investigating Large Language Models for Prompt-Based Open-Ended Question Generation in the Technical Domain

引用

SN computer science 2024年第8期5卷 1-32页

作者： Maity, Subhankar Deroy, Aniket Sarkar, Sudeshna Centre of Excellence in Artificial Intelligence (AI) Indian Institute of Technology Kharagpur West Bengal Kharagpur 721302 India Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal Kharagpur 721302 India

We explore the automated generation of open-ended questions from technical domain textbooks. These questions are more diverse than those typically examined in the field of question generation (QG) for reading comprehension. To facilitate this endeavor, we curate engineeringQ, a prompt-based QG dataset that contains triples of (1) Context: a segment from which the questions are formed;(2) Prompt: a prompt is a concise and specific keyphrase that serves as a short guiding reference to generate a question based on a given context;(3) Question: a question that aligns with the context and is coherent with the prompt. We evaluate the performance of several fine-tuned encoder-decoder based large language models (LLMs), including Pegasus, BART, Flan-T5, and T5 on engineeringQ. We introduce a novel prompt-tuning method for these encoder-decoder based LLMs. We also investigate the potential of general-purpose decoder-only LLMs such as GPT-3.5 Turbo, text-davinci-003, and GPT-4 in zero-shot setting. Evaluation involves automated metrics and human evaluation by domain experts. Extending our study beyond engineeringQ, we apply these methods to subjects such as biology, chemistry, earth science, and physics. Furthermore, we investigate the potential for domain adaptation by fine-tuning the best-performing LLM on school-level subjects and assessing its effectiveness on undergraduate-level computer science and information technology subjects for zero-shot and few-shot QG. To gain insights into generated question complexity, we also utilize Bloom’s revised taxonomy to categorize questions into different levels, enhancing our understanding of their educational value. Experimental results highlight T5_LARGE’s superiority in automated evaluation metrics and text-davinci-003’s excellence in human evaluation metrics in engineeringQ. For subjects such as biology, chemistry, earth science, and physics, Flan-T5_BASE excels in automated metrics, while GPT-4 leads in human

关键词： Automated question generation (AQG) Bloom’s revised taxonomy Education Large language models (LLMs) Prompt

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：