检索结果-内蒙古大学图书馆

8th IEEE International Conference for Convergence in Technology, I2CT 2023

作者： Rohit, R. Gandheesh, S.A. Suriya, K.S. Basa Pati, Peeta Department of Computer Science & Engineering Amrita School of Engineering Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (纸本)9798350334012

Text from image documents must be recognized for its usage. Various tasks such as plagiarism & error check, language analysis, information capture rely on the accuracy of this text conversion. OCR systems convert the document images to their text equivalent. These OCR systems are prone to introducing errors during the recognition *** work reports a system developed to ingest image documents which is converted to text using available OCR technologies. The recognized text, subsequently, is processed with deep network language models to enhance the accuracy of text. The system consists of a client server architecture with user interface available from web application as well as from mobile app. For the language models, encoder-decoder based BART & MarianMT are used. The results obtained demonstrate a 35% reduction in WER using the BART language model. © 2023 IEEE.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Two Birds with One Stone: A Dense Attentive GAN-based Model for Detecting Alzheimer's and Parkinson's Disorders 14

Two Birds with One Stone: A Dense Attentive GAN-based Model ...

引用

14th International Conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Devika, K. Murthy Oruganti, V. Ramana Amrita School of Engineering Amrita Vishwa Vidyapeetham Department of Electrical and Electronics Engineering Coimbatore India School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amaravati India

ISBN: (纸本)9798350344837

This paper investigates two neurodegenerative disorders in adults - Alzheimer's (AD) and Parkinson's (PD). Most works in the research explored these diseases independently - AD vs. healthy subjects and PD vs. healthy subjects. We consider a one-class framework for capturing the characteristics of healthy subjects. This one-class model views any subject with AD or PD as an outlier. We employ Dense Attentive GAN for the one-class model. T1-weighted longitudinal structural magnetic resonance images (sMRI) are used as input. Furthermore, we use longitudinal samples to train the framework (two scans per subject over a 12-month gap). Most traditional methods relied on cross-sectional data (one scan per subject). The proposed method is analogous to doctor's diagnoses of the subject in different sessions to recognise the disorder. Extensive experimental studies have shown that our proposed method outperforms all other AD and PD-based works in the literature. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Lane Detection for Autonomous Vehicles with Canny Edge Detection and General Filter Convolutional Neural Network 18

Lane Detection for Autonomous Vehicles with Canny Edge Detec...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Kishor, S. Nair, Rekha R. Babu, Tina Sindhu, S. Vishnu Vilashini, S. Department of Computer Applications Mangalore India Alliance University Department of Computer Science and Engineering Bengaluru India Dayananda Sagar University School of Engineering Department of Computer Applications Bengaluru India

ISBN: (纸本)9789380544519

Lane detection has been a complex issue that has garnered the attention of the computer vision community for many years. It is a crucial element for self-driving cars and computer vision in general. Lane detection is used to define the path for autonomous vehicles and prevent the risk of drifting into another lane. So proposed a study to develop a method that can detect lane lines in real-time using the OpenCV library and computer vision concepts. To accomplish this, identify the white markings on both sides of the lane. The proposed work focuses on identifying the road lane lines that autonomous cars must adhere to, ensuring that they do not cross into other lanes or drive in the opposite direction, which could lead to accidents. The performance of the work assessed using actual road images and videos captured by the car's front-mounted camera. So proposing a basic and easy algorithm for tacking and detecting lanes. The lanes have been detected through all competitions based on data from the camera, which is carried by algorithms. The proposed work implementing image processing techniques to capture the exact and accurate lane ways and hough transformation techniques. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Arduino UNO Canny Detection DHT11 Hough Transformation LDR sensor

来源：评论

学校读者我要写书评

暂无评论

Laptop Price Prediction Using Real Time Data 1

Laptop Price Prediction Using Real Time Data

引用

1st International Conference in Advanced Innovation on Smart City, ICAISC 2023

作者： Reddy, Chada Lakshma Reddy, K Bhargav Anil, G.R. Mohanty, Sachi Nandan Basit, Abdul Computer Science & Engineering Vardhaman College of Engineering Hyderabad India VIT-AP University School of Computer Science & Engineering Amaravati India National Urdu University Department of Computer Science & Information Technology Hyderabad India

ISBN: (纸本)9781665472753

Online laptop sales are at an all-time high as a result of the pandemic. A laptop is a must-have for working from home, as well as e-learning and other activities. The buyer is aided in making a purchasing decision by a feature-based pricing prediction algorithm. Based on real-time data scraped from an e-commerce website, this study proposes a model for predicting laptop costs. The suggested method collects data from a real-time environment and predicts the model's pricing with high accuracy. This study employs Support Vector Regression, Decision Tree Regression and Multi-Linear Regression to forecast laptop price. © 2023 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Fixed-Time Consensus of Second-Order Nonlinear Multi-Agent Systems with Delay and Switching Topologies

引用

Journal of Shanghai Jiaotong university(science) 2024年第4期29卷 625-639页

作者： XING Youjing GAO Jinfeng LIU Xiaoping WU Ping School of Information Science and Engineering Zhejiang Sci-Tech UniversityHangzhou310018China Department of Systems and Computer Engineering Carleton UniversityOttawaK1S 5B6Canada

To address fixed-time consensus problems of a class of leader-follower second-order nonlinear multi-agent systems with uncertain external disturbances,the event-triggered fixed-time consensus protocol is ***,the virtual velocity is designed based on the backstepping control method to achieve the system consensus and the bound on convergence time only depending on the system ***,an event-triggered mechanism is presented to solve the problem of frequent communication between agents,and triggered condition based on state information is given for each *** is available to save communication resources,and the Zeno behaviors are ***,the delay and switching topologies of the system are also ***,the system stabilization is analyzed by Lyapunov stability ***,simulation results demonstrate the validity of the presented method.

关键词： event-triggered mechanism fixed-time consensus multi-agent systems switching topologies

来源：评论

学校读者我要写书评

暂无评论

Text Recognition in Images and Converting Recognized Text to Speech - Image Processing 10

Text Recognition in Images and Converting Recognized Text to...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Singh, Yadwinder Sharma, Vikrant Singh, Arun Shruti Rakhra, Manik Singh, Prerna Yadidya, Desu Singh, Dalwinder Verma, Vikas Singh, Adwit Lovely Professional University Department of Computer Science and Engineering Phagwara India Graphic Era Hill University Department of Computer Science &engineering Dehradun India Lovely Professional University Department of Computer Science and Engineering Punjab Phagwara India School of Computer Science and Engineering Lovely Professional University Phagwara India Lovely Professional University Computer Science and Engineering Phagwara India University of Spain Department of Computer Science and Engineering Spain

ISBN: (纸本)9798350382471

This review article provides an overview of recent advancements in image-based text recognition and converting recognized text to speech using image processing techniques. The article covers various techniques for text recognition in images, including Optical Character Recognition, Convolutional Neural Networks (CNN), and Recurrent Neural Networks. Additionally, the process of converting recognized text to speech is discussed, including several Text-to-Speech (TTS) techniques such as concatenative TTS, formant synthesis, and parametric synthesis. © 2023 IEEE.

关键词： convolutional neural networks deep learning image processing machine learning natural language processing speech synthesis Text recognition

来源：评论

学校读者我要写书评

暂无评论

Predictive Modeling of Employee Attrition Using Tree-Based Machine Learning Classifiers

Predictive Modeling of Employee Attrition Using Tree-Based M...

引用

2025 International Conference on Emerging Technologies for Intelligent Systems, ETIS 2025

作者： Cherian, Jerly Akku Simon, Santhosh Sreelatha, Anoop Prabhakaranpillai School of Business Providence College of Engineering Alappuzha Chengannur India Providence College of Engineering Department of Computer Science and Engineering Alappuzha Chengannur India Providence College of Engineering Department of Mechanical Engineering Alappuzha Chengannur India

ISBN: (纸本)9798331507541

Employee attrition poses considerable challenges for organizations by affecting productivity and increasing recruitment costs. This study employs tree-based machine learning classifiers to predict employee attrition, aiming to improve decision-making in human resource management. The J48 decision tree was utilized for feature selection, and several classifiers, including Hoeffding Tree, Rep Tree, J48, Random Forest, LMT, and Random Tree, were evaluated. Among these, the Random Forest classifier achieved the highest accuracy of 87.07%, demonstrating its effectiveness in modeling complex attrition patterns. The study offers insights into the application of machine learning for predicting employee attrition and provides a framework for organizations to maintain workforce stability. Future research could incorporate additional data sources and advanced methods to enhance prediction accuracy. © 2025 IEEE.

关键词： Personnel selection

来源：评论

学校读者我要写书评

暂无评论

Growing Insights: Federated Learning CNN's in Combatting Sunflower Leaf Diseases

Growing Insights: Federated Learning CNN's in Combatting Sun...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Suryavanshi, Ankita Mehta, Shiva Malhotra, Sonal Choudhary, Ankur Jain, Vishal Chitkara University Institute of Engineering and Technology Chitkara University Punjab India Graphic Era Hill University Computer Science and Engineering Uttarakhand Dehradun India Graphic Era Deemed to Be University Computer Science and Engineering Uttarakhand Dehradun India Sharda University Computer Science and Engineering Sharda School of Engineering and Technology U.P. Greater Noida India

ISBN: (纸本)9798350361537

It is an issue of great significance in detecting sunflower leaf diseases. This research paper fills that gap using the collective intelligence of distributed data sources through a federated learning (FL) framework. The CNN classifier model is employed for training. With sunflower being an economically important crop and leaf diseases lowering the yield, our research proposes a novel approach where associations are made among data for each client (owning different datasets for five classes of leaf diseases) that are fused to enhance disease detection and produce actionable images. Our FL concept not only protects user privacy and ensures model consistency but also allows customers to support the development of a global model by delivering their data only to a centralized server. It was observed that the proposed approach has the potential to be successful and effective as the experimental results of the presented results confirmed it. The FL model demonstrates an impressive level of performance in the figures on the data on the performance and disease classification shown with macro, micro, and weighted averages, which depict a well-balanced approach. The macro average scores depict the model working well with precision, recall, and the F1-scores of 85.31 to 91.85, respectively, for customers vi-1 through vf-5. The weighted average (with the class imbalance included) also gives high scores, pointing out precision within a range of 85.32 to 91.86, similar to the micro-average values. The only difference is in the range of these values. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

LLDif: Diffusion Models for Low-Light Facial Expression Recognition 27th

LLDif: Diffusion Models for Low-Light Facial Expression Rec...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wang, Zhifeng Zhang, Kaihao Sankaranarayana, Ramesh College of Engineering and Computer Science Australian National University CanberraACT Australia School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9783031782008

This paper introduces LLDif, a novel diffusion-based facial expression recognition (FER) framework tailored for extremely low-light (LL) environments. Images captured under such conditions often suffer from low brightness and significantly reduced contrast, presenting challenges to conventional methods. These challenges include poor image quality that can significantly reduce the accuracy of emotion recognition. LLDif addresses these issues with a novel two-stage training process that combines a Label-aware CLIP (LA-CLIP), an embedding prior network (PNET), and a transformer-based network adept at handling the noise of low-light images. The first stage involves LA-CLIP generating a joint embedding prior distribution (EPD) to guide the LLformer in label recovery. In the second stage, the diffusion model (DM) refines the EPD inference, ultilising the compactness of EPD for precise predictions. Experimental evaluations on various LL-FER datasets have shown that LLDif achieves competitive performance, underscoring its potential to enhance FER applications in challenging lighting conditions. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Smart Agricultural Greenhouse System: A Context-Aware Application

Smart Agricultural Greenhouse System: A Context-Aware Applic...

引用

International Conference on Machine Learning and Big Data Analytics, ICMLBDA 2023

作者： Swain, Sujata Niyogi, Rajdeep School of Computer Engineering Kalinga Institute of Industrial Technology Bhubaneswar India Department of Computer Science IIT Roorkee Roorkee India

ISBN: (纸本)9783031513374

Smart applications are getting more powerful and cheaper cost due to the advancement in sensor technology. In this chapter, we have considered a smart greenhouse application. The important parameters of the smart greenhouse are to control light, temperature, humidity, and water. Greenhouse can provide a favourable growth environment for plants. This smart greenhouse system is a context-aware application. When the context changes in the environment, the application automatically adapts it and does the changes seamlessly without user intervention. In this chapter, we propose a model for the smart greenhouse system. The proposed model can adapt to context changes such as temperature rises, and it automatically turns on the AC seamlessly. The proposed model is based on the machine learning approach. The model maintains the greenhouse temperature, humidity, and sunlight duration in the suitable ranges of the plant. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Context Greenhouse Machine learning NLP Sensors Web service

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：