检索结果-内蒙古大学图书馆

2025 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Dharmalingam, Anandhakumar Tirumala, P. Department of Information Technology & Computer Applications Guntur India

ISBN: (纸本)9798331529833

In light of the rapid expansion of voice- activated smart devices, achieving reliable and secure voice authentication across multiple rooms presents complex challenges. Traditional voice authentication methods fall short in differentiating speakers based on their specific locations, raising security risks in shared spaces. This study introduces a room-level voice authentication model that leverages both spatial audio features and machine learning techniques to distinguish users based on their physical environment. By analyzing room-specific acoustic signatures and integrating them with biometric voice characteristics, the proposed approach strengthens access control, offering a scalable solution that addresses the unique demands of multi- room setups. Performance evaluations indicate high accuracy in correctly identifying both speaker and room, confirming the method's potential for secure, location-based voice authentication in smart homes and office spaces. © 2025 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

Rapid Response System Based On Graph Attention Network For Forecasting Clinical Decline In EHR

Rapid Response System Based On Graph Attention Network For F...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2024

作者： Sushma, Budda Divya Sree, Sakhamuri. Srikanth Yadav, M. Department of Information Technology & Computer Applications Guntur India

ISBN: (纸本)9798350348460

Integrating electronic health records (EHR) with advanced predictive systems has revolutionized healthcare by enabling early identification and intervention for patients at risk of clinical deterioration. This abstract introduces a cutting-edge Rapid Response System (RRS) built upon the innovative framework of Graph Attention Networks (GAT) for forecasting a clinical decline in EHR data. The proposed RRS leverages the power of GAT, a deep learning architecture adept at modeling complex relationships within heterogeneous medical data. By treating patient health records as graphs, where nodes represent diverse medical data points, and edges signify interdependencies, the GAT excels in capturing intricate, multilevel interactions critical for clinical outcome prediction. In this system, the EHR graph undergoes comprehensive preprocessing to extract temporal, sequential, and relational features, enhancing the network's ability to discern subtle patterns indicative of deteriorating health status. The GAT architecture employs attention mechanisms, enabling it to dynamically weigh the significance of different nodes and edges, focusing on the most relevant information for accurate forecasting. The RRS's predictive capabilities are refined through continuous learning from diverse patient trajectories bolstered by recurrent updates with real-time EHR inputs. This dynamic adaptability ensures the model remains responsive to evolving patient conditions and adapts to new data, enhancing its robustness and reliability. Evaluation of the proposed system against benchmark datasets and real-world EHR repositories showcases its superior performance in the early detection of clinical decline compared to conventional methods. The RRS demonstrates impressive accuracy, sensitivity, and specificity metrics, underscoring its potential as a valuable tool for clinical decision support. The deployment of this RRS holds immense promise in augmenting healthcare providers' ability to preemptive

关键词： Clinical Decline Forecasting Graph Attention Network Healthcare Predictive Analytics HER Rapid Response System

来源：评论

学校读者我要写书评

暂无评论

Smart Lights With Smart Power In Public Places

Smart Lights With Smart Power In Public Places

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2024

作者： Ameed, Sk. Mohamad Siddardh, R. Naga Sai Ketepalli, Gayatri Department of Information Technology & Computer Applications Guntur India

ISBN: (纸本)9798350348460

The "Smart Lights with Smart Electricity in Public Places"project aims to generate and use power intelligently in public spaces, adapting lights to the surrounding environment without sacrificing efficiency. When compared to older, more inefficient street lighting methods, smart street lighting has many benefits. In addition to being more versatile and energy-efficient, they have several potential uses, including adaptive dimming, motion detection, scheduled illumination, emergency lighting, traffic monitoring, and enhancing public safety and quality of life. Although smart street lighting systems have only been around briefly, they are quickly gaining popularity. Smart streetlights will likely be installed in an increasing number of places worldwide as the price of their components drops, and word gets out about the many advantages of smart street lighting systems. © 2024 IEEE.

关键词： Energy Efficiency Public Spaces Smart Lighting Sustainability technology Integration

来源：评论

学校读者我要写书评

暂无评论

Plant Leaf Disease Detection Using Transfer Learning Approach

Plant Leaf Disease Detection Using Transfer Learning Approac...

引用

2024 IEEE International Students' Conference on Electrical, Electronics and computer Science, SCEECS 2024

作者： Yaswanth, D. Sai Manoj, S. Srikanth Yadav, M. Deepak Chowdary, E. Department of Information Technology & Computer Applications Guntur India

ISBN: (纸本)9798350348460

Plant diseases are a significant hazard to feeding a growing population, but timely detection is challenging due to a lack of infrastructure in many world regions. Finding and detecting plant illness is essential in agricultural production. It takes a great deal of time and effort to find the disease. The agricultural sector can also reap the benefits of machine learning and deep learning. There has been a recent rise in the use of ML & DL techniques in plant disease identification. In this paper, we applied a transfer learning technique for plant disease prediction. We used a 'plant village' dataset with augmentation collected from Kaggle. This abstract presents a comprehensive plant leaf disease detection approach using transfer learning. The proposed method leverages pre-trained deep learning models to extract relevant features from plant leaf images, thereby enhancing the detection accuracy and reducing the need for extensive labelled data. The key components of this approach include data acquisition, pre-processing, model selection, and evaluation. The proposed approach was evaluated using various metrics, including accuracy, precision, recall, and F1 score. The results demonstrated that transfer learning significantly enhanced the models' ability to differentiate between healthy and diseased leaves, with high accuracy and reduced false positives. Moreover, the model's ability to generalise across different plant species and disease types was assessed, highlighting its versatility. © 2024 IEEE.

关键词： Leaf health analysis Machine learning for leaf diseases Plant disease detection Plant pathology diagnosis Transfer learning in agriculture

来源：评论

学校读者我要写书评

暂无评论

Video captioning – a survey

引用

Multimedia Tools and applications 2025年第2期84卷 947-978页

作者： Vaishnavi, J. Narmatha, V. Department of Computer Applications SRM Institute of Science and Technology Trichy India Department of Computer and Information Science Annamalai University Annamalai Nagar Tamilnadu 608002 India

The explosion of the novel phenomenon of the combination of computer vision and Natural language processing is playing a vital role in converting the ordinary world into a more technological pool. Natural language processing and computer vision are the vanguard of Artificial intelligence with the enormous potential currently ruling more fields. The trending Accelerated research of the NLP and CV combo are cancer screening, surgical simulation, visual properties description, visual retrieval, visual description, etc. Video captioning is a task of localizing the event and various features are extracted from the particular event and then the description of the entire event is performed with Natural languages using various techniques. The task of video captioning has some evolution of various techniques from Traditional methods to Deep learning. Currently, Deep learning techniques are ruling the field. Several models are being proposed for the better enhancement of the video captioning task with the default Encoder-Decoder framework and some models with the variance of Attention mechanism and Transfer learning etc., The Attainment of every technique and the accuracy of the generated results are highly dependent on the nature of the problem, diversity, performance of chosen dataset and construction of the technique with various layers, and the amount of data split for train, validate, and test. This survey discusses the captioning types, real-time applications of video captioning, evolution of various methods in video captioning, advanced techniques, different datasets, metrics that are used to evaluate the results, and analysis of the results of the existing models for video captioning. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Hybrid ANN Random Forest Regression Method of Feature Extraction in Time Series Data

引用

SN computer Science 2025年第1期6卷 1-8页

作者： Rekha, M.P. Perumal, K. Department of Computer Applications School of Information Technology Madurai Kamaraj University Tamilnadu Madurai India

A time series is a logical grouping of values about time gleaned from numerous applications. The fundamental properties of the time series data (TSD) include their enormous quantity, high complexity, and traits like trend, cycle, seasonality, and irregularity. Data mining has seen a significant amount of research and development efforts due to the cumulative use of TSD. The effectiveness of various methods of data mining used for time series analysis is closely correlated to the dimension of the time series. In this proposed method, the weather forecasting dataset has been used. The dataset has more number of dimensions and it has been reduce dimensionality using Artificial Neural Network (ANN) and extract the feature with accuracy using Random Forest regression algorithm The study aims to utilize the deep learning (DL) method and feature extraction to minimize the dimensionality in time series data. The proposed approach improves the extraction's effectiveness in reaching our research's goal. The proposal seeks to minimize time series data's high dimensionality. The idea also emphasizes the importance of accurately lowering the dimensionality of time series data. The proposed Random Forest regression method with MAPE (13%), RMSE (9%), and MSE (15%) effectively decreases the dimensionality and extract the feature effectively when compared to existing techniques. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Data mining Deep learning Dimensionality reduction Random Forest Time series data

来源：评论

学校读者我要写书评

暂无评论

Domain Based Medical Image Testing Using Attention Model 2

Domain Based Medical Image Testing Using Attention Model

引用

2nd International Conference on Data Science and information System, ICDSIS 2024

作者： Bhuyan, Hemanta Kumar Kamireddy, Anusha Department Of Information Technology And Computer Applications Andhra Pradesh Guntur India

ISBN: (纸本)9798350381665

Medical image testing is a crucial role in clinical system due to the label based region of interest is used for diagnosis and therapy. As per the domain shift, the segmentation performance is suffered for different unlabeled image modality. While unsupervised domain adaptation (UDA) model is dealing with these issues, current techniques may need some speed tweaks. Transformer's' adaptability is also under observation, even though new Transformer-based approaches to medical image segmentation have quite considered for performance. Thus, we considered domain based Transformer model to construct a cross-modal segmentation approach. This method perform at gaining knowledge long-range dependencies and enrapturing attention-related record. We considered Meta Attention (MA) approach to gain knowledge the level-by-level consistencies with positioning scheme. This model transfer more data between two modalities to execute an attention-based arrangement system. We have extensively tested cross-modality segmentation on three datasets: heart, abdominal organs, and brain tumors. The experimental results demonstrate that, when compared to the cutting-edge UDA approaches, our approach is considerably enhanced the performance. The average value of our model on Dice Similarity Coefficient (DSC) is 80% whereas DAFormer is 77.1%. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Employment dynamics: Exploring job roles, skills, and companies

引用

IEEE Potentials 2025年第1期44卷 23-29页

作者： Saroja, S. Jinwal, Swathi the Department of Computer Applications National Institute of Technology Trichy620015 India data/information ma nagement analyst with Citi Bengaluru560001 India

Are which which better jobyouisjobs skills career, mostcurious are to relevant and learn trending, aboutwhich for to a your skills along with your probability of selection? This research article addresses these questions comprehensively. The first phase employs web scraping techniques to gather data from prominent job websites, constructing a current dataset. This dataset captures emerging job roles, in-demand skills, geographic job distributions, experience requirements, and related insights. In the subsequent phase, a job recommendation system is developed. Leveraging natural language processing (NLP) techniques such as term frequency–inverse document frequency (TF-IDF) vectorization and cosine similarity, the system matches user-provided skills with job descriptions to recommend relevant job opportunities. Additionally, the recommendation system estimates the probability of selection for each candidate. This project serves as a valuable resource for understanding contemporary job market dynamics, facilitating informed career decisions, and providing insights into emerging job trends and skill requirements crucial for success in the evolving job market. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Reducing noise using neighbourhood pixel analysis and interpretable custom kernel in CNN model for CP handwritten digit recognition

引用

International Journal of information technology (Singapore) 2024年 1-11页

作者： Muthureka, K. Srinivasulu Reddy, U. Janet, B. Machine Learning and Data Analytics Lab Department of Computer Applications National Institute of Technology Tiruchirappalli India Information Processing Lab Department of Computer Applications National Institute of Technology Tiruchirappalli India

Individuals with Cerebral Palsy (CP) are impacted lifetime barriers in their everyday activities, especially in writing phrase, which results from innate neural motor in co-ordination. Numerous studies have focused on recognizing normal people’s handwritten digits using benchmark datasets. However, there has been limited exploration into recognizing handwritten digits by individuals with CP. The handwriting of CP individuals is significantly more difficult to recognize than that of normal people because the CP digits are inaccurate, uneven, and complex to recognize. In this study, the authors improve the digit recognition accuracy of existing Convolutional Neural Network (CNN) models on collected CP handwritten digit’s dataset using two notable methods, first one is to reduce the noise using neighbourhood pixel analysis through Fast Non-Local Means (FNLM) algorithm and second one is to extract the feature using customized kernel technique. The experimental results show that the accuracy of existing state of art models are improved by 3% to 7.14% with the integration of aforementioned techniques. Moreover, a custom CNN model hybridised with the Prewit, Laplacian, Sobel filters, and custom kernel has following CP digit recognition accuracy values of 97.96%, 98.08%, 99.17%, and 99.60% respectively. © Bharati Vidyapeeth's Institute of computer applications and Management 2024.

关键词： Cerebral Palsy CNN Customized kernel initialization Edge detection Handwritten digit recognition

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Analysis of Knowledge Graph-based Social Recommendation System 1

A Comprehensive Analysis of Knowledge Graph-based Social Rec...

引用

1st International Conference on Intelligent Systems and Computational Networks, ICISCN 2025

作者： Navuluri, Madhavilatha Bhuyan, Hemanta Kumar RGUKT-IIIT Department of Computer Science and Engineering Ongole India Department of Information Technology and Computer Applications Guntur India

ISBN: (纸本)9798331529246

Recommendation systems are crucial due to their high relevance in terms of interpretability and performance. A Social Recommendation system explores how social relations influence user choices and how users select items. In this system, user-embeddings are learned from Knowledge graphs to enhance the recommendations. The social recommendation system can be categorized into three main areas: user recommendation, movie recommendation, and explainable recommendation. User recommendation focusses on providing users with personalized services, movie recommendation enhances the movie-watching experience, and explainable recommendation aims to provide the reasoning behind the suggested items. Data sparsity and the cold start problem are significant challenges faced by RS. The Social RS model addresses these issues by leveraging both user-item interactions and user-user social relationships, thereby improving the overall quality of social network-based recommendations. Methods such as Light Graph Convolutional Network (LGCN), Hyperbolic Recommender (HSR), and Knowledge Enhanced Graph Neural Networks (KEGNN) have been proposed to enhance social recommendation performance. Evaluation metrics such as recall @N, precision @N are commonly used to assess and estimate the effectiveness of recommendation systems. © 2025 IEEE.

关键词： Knowledge graph

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：