检索结果-内蒙古大学图书馆

2023 International Conference on Data science and Network Security, ICDSNS 2023

作者： Adusumilli, Manasa Ramesh, G.P. Katkam, Vijayrani Bhargavi Pareek, Piyush Kumar Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Vaadeswaram India St. Peter's Institute for Higher Education and Research Department of Electronics and Communication Engineering Chennai India Ballari Institute of Technology and Management Department of e and Ce Bellary India Hyderabad Institute of Technology and Management Department of Cse Hyderabad India Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350301595

Identifying demand-side load events is a critical step in lowering energy use in a number of situations. Using wide-deep neural networks and randomised sparse backpropagation algorithms, this study presents a unique way to identify demand-side load events. To detect subtleties in the input data, we employ randomised sparse backpropagation and both shallow and deep network topologies. We also use the ReLU and sigmoid activation functions to improve the performance of our model. We use the Adam optimizer to train the proposed model, using a learning rate of 0.001 per batch and a batch size of 64. The results were compared to those of other popular technologies, such as support vector machines. According to the findings of our studies, the technique we utilised is more precise and efficient than any other option we investigated. The proposed approach combines wide-deep neural networks with randomised sparse backpropagation to simplify demand-side load event identification. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation

arXiv

引用

arXiv 2025年

作者： Gain, Baban Bandyopadhyay, Dibyanayan Ekbal, Asif Department of Computer Science and Engineering IIT Patna India School of AI and Data Science IIT Jodhpur India

The advent of Large Language Models (LLMs) has significantly reshaped the landscape of machine translation (MT), particularly for low-resource languages and domains that lack sufficient parallel corpora, linguistic tools, and computational infrastructure. This survey presents a comprehensive overview of recent progress in leveraging LLMs for MT. We analyze techniques such as few-shot prompting, cross-lingual transfer, and parameter-efficient fine-tuning (e.g., LoRA, adapters) that enable effective adaptation to under-resourced settings. The paper also explores synthetic data generation strategies using LLMs, including back-translation and lexical augmentation. Additionally, we compare LLM-based translation with traditional encoder-decoder models across diverse language pairs, highlighting the strengths and limitations of each. We discuss persistent challenges—such as hallucinations, evaluation inconsistencies, and inherited biases—while also evaluating emerging LLM-driven metrics for translation quality. This survey offers practical insights and outlines future directions for building robust, inclusive, and scalable MT systems in the era of large-scale generative models. © 2025, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Brain Tumor Mri Classification Using Modified Vgg16 Model

Optimizing Brain Tumor Mri Classification Using Modified Vgg...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Mitra, Ankita Sridar, K. Rathna, S. Chowdhury, Rini Kumar, Prashant Glory, E. Dr.BC.Roy Engineering College Department of Ece Durgapur India Veerammal Engineering College Department of Computer Science and Engineering Dindigul India Bannari Amman Institute of Technology Department of Ai&ds Sathyamangalam India Project Circle Bsnl Saltlake Telephone Exchange Department of It India Saveetha School of Engineering Simats Department of Biosciences Chennai India

ISBN: (纸本)9798350360660

Background: Brain MRI is vital for diagnosing brain tumors, yet challenges like variations in tumor size, shape, noise, and artifacts complicate accurate classification. Existing models like ResNet50 and Inception-ResNetV2 often struggle with these complexities. Methods: To address these issues, a modified VGG16 model was developed. This custom model includes multiple convolutional layers designed to effectively extract complex features from MRI images, enhancing its ability to manage the inherent complexities of brain MRI data. Results: The modified VGG16 model outperformed existing models, achieving a high accuracy of 97.2% and a low loss of 0.2. These results indicate its superior performance in classifying brain tumor images, even in the presence of noise and variations. Conclusion: The modified VGG16 model provides a robust solution for brain tumor classification, offering improved accuracy and reliability, which can lead to better patient outcomes. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Text Summarization with Transformer Networks and Reinforcement Learning for English 3

Improving Text Summarization with Transformer Networks and R...

引用

3rd International Conference on Communication, Control, and Intelligent Systems, CCIS 2024

作者： Vijaya Durga, Chinni Bala Arunadevi, V. Pathak, Punit Prema, S. Nair, Hari Nagaraj, P. Potti Sreeramulu Chalavadhi Mallikarjuna Rao College of Engineering & Technology A.P. Vijayawada India Dr.Mahalingam College of Engineering and Technology Department of Science and Humanities India Auro University Department of School of Liberal Arts and Human Sciences Surat India Panimalar Engineering College Department of English Chennai India Department of English and Foreign Languages Andhra Pradesh Bhimavaram India K.Ramakrishnan College of Engineering Department of Ai & Ml Tamil Nadu Trichy India

ISBN: (纸本)9798331528201

As the volume of text data continues to grow rapidly, efficient and accurate text summarization has become crucial for managing and processing this information. Traditional summarization methods, including extractive and abstractive approaches, face challenges in maintaining relevance, fluency, and factual consistency, particularly in complex domains such as legal documents. In this research, we propose an advanced summarization framework leveraging transformer networks, specifically designed to enhance the quality of English text summaries. The framework begins with the preprocessing of text data, including lowercasing, elimination of punctuation, HTml tags, stopwords, and stemming/lemmatization to standardize the input. Text feature extraction is then performed using the Term Frequency-Inverse Document Frequency (TF-IDF) method, converting textual data into numerical representations that highlight the significance of terms within documents. The core of the framework employs a transformer model that eschews traditional RNNs in favor of multiple attention layers and positional encoding to capture global dependencies and enable parallel processing. The model's encoder-decoder structure uses self-attention mechanisms and multi-head attention layers to effectively encode the sequence and context of words, leading to high-quality abstractive summaries. The proposed architecture's effectiveness is evaluated using the BillSum dataset, which includes over 22,000 U.S. Congressional bills and human-written summaries. The results highlight the superior performance of the proposed Transformer model, which achieved the highest ROUGE-1, ROUGE-2, and ROUGE-L scores, with values of 37.03, 16.89, and 28.34, respectively and the Proposed method is implemented using python software. Our approach demonstrates significant improvements in summary accuracy and relevance compared to existing methods, making it a promising solution for automated summarization tasks across various domains.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

An Emotion Aware Music Recommendation System Using Flask and Convolutional Neural Network

An Emotion Aware Music Recommendation System Using Flask and...

引用

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： Shashank Gajula Tigulla Hruthika Goud Bhawani Sankar Panigrahi M.A. Jabbar Computer Science & Engineering (AI&ML) Vardhaman College of Engineering Hyderabad Hyderabad India Department of Information Technology Mahatma Gandhi Institute Of Technology Hyderabad India

Music has been instrumental in influencing the emotions of a person. Every person develops a choice of music depending on varied factors like- philosophy, situations and personal emotions. Many organizations have been providing different ways to recommend a good playlist of music to their users based on their previous choices and emotion of user but couldn't bridge the gap of personalization and emotion driven recommendation. This paper emphasizes on building this gap by providing a recommendation of music based on user's choices and their current emotions. The proposed model is an innovative approach by harnessing the power of Convolutional Neural Networks (CNN) and music therapy approaches to ensure to provide people with an apt recommendation that enhances the user's experience of music. This model has achieved an accuracy of 71%. It can easily be integrated with music platforms to enhance the user experience and provide better services.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved Sail Fish Optimizer for Energy Efficient Routing in Wireless Sensor Network

Improved Sail Fish Optimizer for Energy Efficient Routing in...

引用

2023 International Conference on Integrated Intelligence and Communication Systems, ICIICS 2023

作者： Aluvala, Srinivas Reddy, Geetha Al-Jawahry, Hassan M. Ramadan, Ghazi Mohamad Pareek, Piyush Kumar SR University School of Computer Science & Artificial Intelligence Warangal India CSE Malla Reddy Engineering College for Women Hyderabad India The Islamic University Najaf Iraq Ahl Al Bayt University College of Mlt Karbala Iraq Nitte Meenakshi Institute of Technology Department of Ai and Ml Bengaluru India

ISBN: (纸本)9798350315455

A Wireless Sensor Network (WSN) is a collection of nodes fitted with small sensors and transceiver elements that are utilized for sensing, tracking, and data collection in a variety of situations. Sensor energy is considered a significant resource due to the difficulty in providing battery a backup to sensors when they are deployed in an uncontrolled or wild area. Integrating clustering & routing strategies are the optimal techniques for saving sensor node energy. In this research, the Improved Sail Fish Optimizer (ISFO) is proposed for the energy efficient routing path selection in WSN to improve the network lifetime. The ISFO algorithm is utilized to identify an accurate routing to sink node for data transmission. The performance of proposed algorithm is evaluated with performance metrics of Packet Delivery Ratio (PDR), Throughput, energy consumption and delay. The proposed algorithm attained high PDR of 96%, high throughput of 97%, less energy consumption of 0.4J and less delay of 3ms which is superior than other existing algorithms. © 2023 IEEE.

关键词： Clustering Improved Sail Fish Optimizer Routing protocol Sensor Nodes and Wireless Sensor Network

来源：评论

学校读者我要写书评

暂无评论

Optical Satellite Networks

Optical Satellite Networks

引用

2023 Optical Fiber Communications Conference and Exhibition, OFC 2023

作者： Chan, Vincent W.S. Massachusetts Institute of Technology Research Laboratory of Electronics Steve Schwarzman College of Computing Ai and Decision System Sector Department of Electrical Engineering and Computer Science United States

We will explore the architecture of optical satellite networks at 100G-1Tbps. The challenge is to architect the system and the network protocols with large bandwidth-delay products and the presence of atmospheric turb... 详细信息

ISBN: (纸本)9781957171180

关键词： Atmospheric turbulence

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Secure Communication Framework for Connected Autonomous Vehicles

Machine Learning-based Secure Communication Framework for Co...

引用

2023 IEEE Globecom Workshops, GC Wkshps 2023

作者： Jivani, Dirgha Gajjar, Harshal Gupta, Rajesh Jadav, Nilesh Kumar Tanwar, Sudeep Bhatia, Jitendra Trivedi, Harshal Institute of Technology Nirma University Department of Computer Science and Engineering Gujarat Ahmedabad India Tusker Ai Pvt. Ltd It Support and Services Ahmedabad380015 India

ISBN: (纸本)9798350370218

As connected autonomous vehicles (CAVs) gain popularity, new challenges emerge in ensuring secure network connectivity. In this study, we present a machine learning (ml)-based secure communication system for autonomous vehicles. Our main goal is to distinguish between harmful and non-malicious message transfers in order to strengthen communication channel security. We used a unique framework to bin float values to make them more suitable for classification. We then fed these values into a classifier model. The framework utilizes a dataset comprising 63 features and 450,000 records. Among various ml models evaluated, random forest (RF) emerged superior in classifying CAVs messages. The RF model, trained on this dataset, achieved an impressive accuracy of 94.26%. This underscores the potential of ml techniques, especially RF, in fortifying the security of networked autonomous vehicles. This study contributes to ongoing efforts to establish secure and reliable communication systems for CAV networks. © 2023 IEEE.

关键词： Connected Autonomous Vehicles Machine Learning Secure Message Exchange Security

来源：评论

学校读者我要写书评

暂无评论

LEARNING CONTINUOUS NORMALIZING FLOWS FOR FASTER CONVERGENCE TO TARGET DISTRIBUTION VIA ASCENT REGULARIZATIONS 11

LEARNING CONTINUOUS NORMALIZING FLOWS FOR FASTER CONVERGENCE...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Chen, Shuangshuang Ding, Sihao Karayiannidis, Yiannis Björkman, Mårten School of Electrical Engineering and Computer Science Royal Institute of Technology Sweden AI Lab Volvo Car Corporation Sweden Department of Automatic Control Lund University Sweden

Normalizing flows (NFs) have been shown to be advantageous in modeling complex distributions and improving sampling efficiency for unbiased *** this work, we propose a new class of continuous NFs, ascent continuous normalizing flows (ACNFs), that makes a base distribution converge faster to a target *** solving such a flow is non-trivial and barely possible, we propose a practical implementation to learn flexibly parametric ACNFs via ascent regularization and apply it in two learning cases: maximum likelihood learning for density estimation and minimizing reverse KL divergence for unbiased sampling and variational *** learned ACNFs demonstrate faster convergence towards the target distributions, therefore, achieving better density estimations, unbiased sampling and variational approximation at lower computational ***, the flows show to stabilize themselves to mitigate performance deterioration and are less sensitive to the choice of training flow length T. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Maximum likelihood estimation

来源：评论

学校读者我要写书评

暂无评论

Fault Classification based on Deep Learning for Photovoltaic Systems 2

Fault Classification based on Deep Learning for Photovoltaic...

引用

2nd International Conference on Distributed Computing and Optimization Techniques, ICDCOT 2024

作者： Kelin, A. R. Darshika Sudhakar, K. Surekha, Pothireddy Palanivel, R. Al-Jawahry, Hassan M. Karunya Institute of Technology and Sciences Data Science and Cyber Security Karunya Nagar Coimbatore India Department Electronics and Communication Engineering Telangana Hyderabad India Griet Department of Computer Science and Engineering Telangana Hyderabad India Nitte Meenakshi Institute of Technology Department of Ai and Ds Bengaluru India The Islamic University Najaf Iraq

ISBN: (纸本)9798350382952

In general, high power electronic converters such as Multilevel Inverters (mlI), that find their use in many applications, create difficulties of augmented switch count, capacitor flow current and reverse current flowing from inductive loads. above problems, in turn, result in faults, without which mlI reliability is unattainable. Therefore, fault classification and tolerance strategies are of paramount contribute to keeping reliability of inverters. Herein we present a deep learning (DL)-based fault classification approach for 15-level CHB Multi-level Inverter. proposed system includes pre-processing based on Adaptive Hilbert-Huang filtering, segmentation by a Partial Differential Equation (PDE), feature extraction utilizing Scale-Invariant Feature Transform (SIFT), and fault signal classification being performed by a Convolutional Neural Network (CNN) trained with a Honey Badger Optimization Algorithm (HBOA). MATLAB was applied to our method of identifying a set of four complex fault types for purpose of measurement. results of HBOA-optimized CNN have demonstrated highest accuracy rate of 99.91%. © 2024 IEEE.

关键词： Electric inverters

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：