检索结果-内蒙古大学图书馆

6th International Conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 2024

作者： Meena, K. Vadivel, A. Sardar, Tanvir Habib Kotiyal, Arnav Guru Prasad, M.S. Kumar, Utsav Department of Computer Science and Engineering GITAM School of Technology GITAM University Bengaluru562163 India Department of Computer Science and Engineering School of Engineering Dayananda Sagar University Bengaluru562112 India Dehradun India Dehradun India

For applications such as weather forecasting, power grid management, and solar energy integration, accurate solar radiation prediction is essential. Using real-time data from the EU science Hub's Climate Monitoring Satellite Application Facility (CM SAF), this research examines the efficacy of several time series models for hourly solar radiation prediction. The data are subjected to stationarity testing using the Augmented Dickey-Fuller (ADF) test prior to the models being applied. This study uses well-known time series models, including Vector Auto-regression (VAR), Linear Regression, and Autoregressive Integrated Moving Average (ARIMA). The performance of the proposed model is evaluated using Mean Square Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), R-squared, and Mean Absolute Percentage Error (MAPE). It is found that Vector Auto-regression (VAR) is encouraging for predicting solar radiation on hourly basis with least amount of overall error. This analysis has used residual error inspection, error distribution analysis and sample accuracy evaluation using MAPE. This paper highlights the importance of VAR on using time series model for predicting solar radiation. © 2025 The Author(s). Published by Elsevier B.V.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Advancements in Handwritten Text Recognition and Correction: Bridging the Gap Between Analog and Digital Writing 15th

Advancements in Handwritten Text Recognition and Correction:...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Mohan, J. S. Shyam Sathwik, Abbaraju Sai Ganesh, M.N.V.S. Tejaswi, M. Hema Naseeba, Beebi Madhavi, K. Reddy Department of Computer Science and Engineering GITAM University Bangalore India VIT-AP University Amaravati India Department of AI&ML School of Computing Mohan Babu University Tirupati India

ISBN: (纸本)9783031889912

Handwritten text recognition and correction is the process of converting handwritten text into digital form and correcting errors within the recognized text. Natural language processing tools, computer vision methods, and machine learning algorithms are combined to achieve this. The recognition process involves extracting features, and classifying characters or words. The correction process uses a language model to identify errors and suggest corrections based on context and grammar rules. Handwritten text recognition and correction has numerous applications in fields such as document digitization, signature verification, and historical document analysis. However, it remains a challenging task due to the variability of handwriting styles and the complexity of human language. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Evaluating Object Detection Approaches for Fruit Detection in Precision Agriculture: A Comprehensive Review

Evaluating Object Detection Approaches for Fruit Detection i...

引用

Intelligent Computing and Sustainable Innovations in Technology (IC-SIT), International Conference on

作者： Archana Uriti Naga Jyothi Pothabathula Department of Computer Science and Engineering GITAM (Deemed to be University) Vishakhapatnam AP India

ISBN: (数字)9798350369175

ISBN: (纸本)9798350369182

Agricultural automation has become increasingly vital in addressing the growing demand for food and the need for efficient farming practices. Fruit harvesting is crucial in agriculture due to its labor intensity and the challenges of timely, accurate picking under occlusions and varying illumination. Various methods have been developed for accurate fruit detection, but traditional techniques often struggle with occlusions by branches or leaves, as well as challenges posed by climate and fruit maturity. This study reviews existing literature, compares various fruit detection approaches and discusses their strengths and weaknesses. Building on the work of various authors, this paper aims to offer a thorough understanding of the current state of fruit detection technologies in agricultural automation. Additionally, the survey addresses the objective of the proposed work, which is to identify the most promising techniques for improving fruit detection accuracy and efficiency.

关键词： YOLO Surveys Technological innovation Automation Accuracy Reviews Redundancy Lighting Real-time systems Reliability

来源：评论

学校读者我要写书评

暂无评论

Automated Detection and Classification of Cotton Leaf Diseases: A computer Vision Approach

Automated Detection and Classification of Cotton Leaf Diseas...

引用

Advances in Modern Age Technologies for Health and engineering science (AMATHE), International Conference on

作者： Swastick Ganguly Jathin S M Mohak M Sanjay BM Somashekhar N Shobharani Department of Computer Science Amrita School of Computing Mysuru Campus Dept of Computer Science and Engineering Gitam School of Technology Gitam University Bengaluru Campus

ISBN: (数字)9798350371567

ISBN: (纸本)9798350371574

Cotton plays a vital role in agricultural sustainability, extending beyond its textile applications. Pathogens pose significant threats to cotton plants and farmers' livelihoods, highlighting the critical need for disease detection to maintain crop health and ensure optimal yields. Our research pioneers a novel approach to disease detection in cotton through advanced image analysis techniques. This involves exploring deep learning methodologies specifically tailored for detecting cotton leaf diseases and enhancing accuracy by integrating CNN models, while balancing labor intensity and cost considerations. Leveraging the Convolutional Neural Networks (CNN), the combination of the interpretability of Densenet 121 with the stability of ResNet 50, assessing the strength of their combined algorithm. This hybrid model accurately classifies various cotton plant diseases, enabling fine-grained analysis. With a precision-driven approach, the proposed model achieves exceptional results, accurately identifying six distinct diseases, including fungal, bacterial, and viral pathogens, with an impressive 96% accuracy rate. The research aims to provide a comprehensive and dependable solution for disease management in the cotton industry, ultimately promoting crop health, productivity, and sustainability

关键词： Deep learning Training Plant diseases Pathogens Accuracy Computational modeling Crops

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Based Resource Allocation Strategy in Cloud-Edge Computing System 2

Deep Reinforcement Learning Based Resource Allocation Strate...

引用

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

作者： Adhoni, Zameer Ahmed Habelalmateen, Mohammed I Janardhana, D.R. Sattar, Khalid Nazim Abdul Audah, Lukman Gitam School of Technology Gitam University Department Computer Science Engineering Department Bengaluru Rural India The Islamic University Najaf Iraq Nitte Meenakshi Institute of Technology Dept of Cse Bengaluru India College of Science Majmaah University Department of Csi Al Majmaah Saudi Arabia Universiti Tun Hussein Onn Malaysia Electrical and Electronic Engineering Batu Pahat Johor Parit Raja Malaysia

ISBN: (纸本)9798350382952

A lot of real time processing as well as resource-intensive apps is what is needed more and thus, cloud-edge computing systems require compelling resource allocation schemes. This research focuses on the utility of Multiagent Learning framework with Deep Reinforcement Learning (MAL-DRL) which is used for solution deployment concerning resource allocation in such systems, such that the end user enjoys optimization while operators optimize resource utilization. In this work, the research focus on the simulation testing of the MAL-DRL algorithm against classical Random Allocation (RA) and singe agent DRL methods. This exhibition shows that MAL-DRL improves the average latency more (44% savings) and at the same time more resources are used (35% increase) compared both the alternatives with a combined reward measure score of 0.80. These results show that distributed decision-making and learning styles of MAL-DRL brings together faster resource allocation which can be interpreted as a reduction of users' delay experience and therefore lead to better performance of whole system. Although the article limits simulations in areas to be covered and complexity in training, it brings the prospective benefits of MAL-DRL in the management of cloud-edge resources on the spot. In the course of this undertake, the effect of ensuring communication goals, moving learning strategies, and security measures for the ultimate goal of boosting this method's applicability in real-world antics can be explored. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Flight Fare Prediction Using Machine Learning 1st

Flight Fare Prediction Using Machine Learning

引用

1st International Conference on Computational Intelligence and Smart Communication, ICCISC 2022

作者： Arjun, K.P. Rawat, Tushar Singh, Rohan Sreenarayanan, N.M. Department of Computer Science and Engineering GITAM University Karnataka Bengaluru India School of Computer Science and Engineering Galgotias University Uttar Pradesh Greater Noida India

ISBN: (纸本)9783031229145

The price of airline tickets can fluctuate gradually and generally with the same aircraft, independent of, in the seats that are closest together inside the same cabinet. Customers have the expectation that they will pay decreased expenses, whereas airlines work to maintain or even increase their overall earnings while also working to improve their profitability. To maximise their payload, airlines employ a variety of mathematical methods, such as guessing and suitable classification, among others. Models that estimate the best open door buy and models that anticipate the cost of a basic ticket are the two sorts of client-side models that various industry professionals recommend in order to save clients money. Both of these models fall under the category of client-side predictive models. According to our research, models on both sides depend on the restricted performance of several components, such as actual ticket price data, the date the ticket was purchased, and the date the passenger exited the venue. Many individuals take flights on a regular basis, and as a result, they are familiar with the times of year that provide the best deals on airline tickets. Despite this, there are a great number of individuals who have recently purchased tickets but wind up falling prey to the snares made by organisations, as a result of which they wind up spending more money than they should have. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Stock Trading using LSTM Approach 3

Intelligent Stock Trading using LSTM Approach

引用

3rd IEEE India Council International Subsections Conference, INDISCON 2022

作者： Saraswathi, Pedada Rao, Patruni Muralidhara Rajkumar, G V S GITAM Institute of Technology Department of Computer Science and Engineering Visakhapatnam530045 India Vellore Institute of Technology School of Computer Science and Engineering Vellore632014 India

ISBN: (数字)9781665466011

ISBN: (纸本)9781665466011

Everyone deals with money daily. As the famous saying goes, it's not what you earn but what you save. For the past few generations, people in India have believed that putting all the surplus money in FDs was the best way to invest. But considering the tax reductions and return rates recently, people have started to switch to better ways of investment. One of these ways is pumping money into direct equity and Mutual Funds/SIPs. For this, Indians rely heavily on CAs and financial advisors that charge a lot of compensation for their consultation and advice. We propose a system that replaces these advisors by using state-of-The-Art Machine Learning approaches. We implement a Long Short-Term Memory (LSTM) network that takes input of historic prices of a pre-specified company and predict a future price which will enable the user to make smart decision of investing in the company or to choose a different approach of utilizing their surplus income. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Enhancing User Experience and Mitigating BIAS in Electronic Device Recommendations on e-Commerce Platforms: Leveraging NLP and GPT Technologies

Enhancing User Experience and Mitigating BIAS in Electronic ...

引用

Sustainable Expert Systems (ICSES), International Conference on

作者： Pavan Gunda Thirupathi Rao Komati Department of Computer Science & Engineering GITAM School of Technology GITAM Deemed to be University Visakhapatnam Andhra Pradesh India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Electronic devicerecommendations on e-commerce sites enhance the user experience by assisting users in finding products that suit their requirements, interests, and preferences. By providing them with pertinent options, it helps users who are looking for specific gadgets save time and effort. Electronic devices commonly saw shorter product lifecycles due to the regular introduction of updated and new models. Users may feel under pressure to update to newer versions in order to access the newest features or upgrades, which could cause obsolescence problems. Previously NLP techniques are utilized for recommending electronic gadgets. Biased recommendations may result from NLP models inheriting biases found in the training set of data. As a result, there may be unfair or discriminatory consequences, such as more product recommendations for particular demographic groups or the reinforcement of preexistingpreconceptions. GPT may be used to construct chatbots or AIs that engage with customers using natural language. These assistance systems driven by AI are able to help customers make purchases, answer their questions, and make personalized product suggestions. Companies can improve the customer experience by responding quickly and giving useful information. One can use GPT to simplify customer service tasks like answering common questions and fixing problems right away. This can help companies help customers around the clock, speed up reaction times, and give human support workers less work to do. Support systems driven by GPT can also learn from exchanges with customers over time, making them better at what they do. High-quality material may be produced by GPT for use in blog entries, social media postings, marketingand copy, including product descriptions. One can use this material to get people interested in and buying from your e-commerce sites, show off product attributes and advantages, and attract new customers. We can also make GPT-generated content search engine

关键词： Training Sentiment analysis Social networking (online) Natural languages Companies Search engines Feature extraction User experience Electronic commerce Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Object Detection Robustness In Adverse Weather Conditions

引用

Procedia computer science 2025年 252卷 1014-1024页

作者： Shaik Yacoob D. Phani Kumar G.G.S. Harshitha V.Y. Sai Teja C.H. Satya Veni K. Mahidhar Reddy Senior Assistant Professor Department of Computer Science and Engineering Godavari Global University Rajahmahendravaram-533296 India Assistant Professor Department of Computer Science and Engineering Godavari Global University Rajahmahendravaram-533296 India

Fundamental applications in autonomous cars, robots, and surveillance systems include object detection for safety reasons such as recognizing vehicles, pedestrians, trees, street poles, and buildings. However, one of the major challenges it faces from adverse weather conditions like rain, haze, and fog through deterioration of accuracy and an increase in safety risks such as traffic accidents. This paper proposes an enhanced object detection system to improve its robustness and accuracy in challenging environments. The proposed approach effectively addresses the problem of poor image quality due to adverse weather conditions by using unsupervised domain adaptation and including a Quasi-Translation Network and Feature Calibration Network in the YOLO(You Only Look Once) framework. It attempts to leverage the success made in CNNs(Convolutional Neural Networks) and mass amounts of datasets in order to adapt YOLO-series detectors in the best possible way, achieving object detection under challenging environmental conditions with precision and speed. Experimental results demonstrate that the solution proposed outperforms existing models in terms of adaptability and accuracy, providing a scalable and reliable solution for autonomous systems to enhance overall safety and operational efficiency in real-world environments.

关键词： Convolutional Neural Networks (CNN) Object Detection YOLO Quasi-Translation Network (QTNet) Feature Calibration Network (FCNet)

来源：评论

学校读者我要写书评

暂无评论

Framework Development and Testing to Identify the Risk in Business by using NLP 3

Framework Development and Testing to Identify the Risk in Bu...

引用

3rd International Conference on Advancement in Electronics and Communication engineering, AECE 2023

作者： Srivastava, Anima Subhashini, P. Dhongde, Siddharth Rajendra Saravanan, D. Kutty, Noora Mohamed Parthiban, R. University of Allahabad Department of Electronics and Communication Prayagraj India Vel Tech Multi Tech Dr.Rangarajan Dr. Sakunthala Engineering College Department of Information Technology Chennai India Gitam School of Business Gitam University Department of Finance vishakhapatnam India Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India Psmo College Department of Commerce and Management Studies Tirurangadi India Ifet College of Engineering Department of Computer Science and Engineering Villupuram India

ISBN: (纸本)9798350330724

The growing reliance of individuals on computer-assisted systems has prompted academics to prioritize the development of communication technologies that can replicate comprehend natural languages, human interactions, and interpret human emotions. The issue of information overload is pervasive across several sectors, including business, healthcare, education, and more. This phenomenon has resulted in a notable surge in unstructured data, often seen as lacking use or usefulness. In this particular domain, integrating natural language processing (NLP) with sophisticated technologies like machine learning, deep learning and artificial intelligence, have shown to be a successful approach for enhancing the comprehension and manipulation of natural language. This has the potential to enhance human-computer interaction in a more efficient manner, while also facilitating the analysis and organization of extensive quantities of unstructured and non-utilizable data/text across several sectors. This approach is expected to provide significant results that may enhance the process of decision-making and therefore boost operational efficiency. This section give an summary of the idea of Natural Language Processing (NLP), tracing its historical evolution and discussing its applicability across several industrial sectors. © 2023 IEEE.

关键词： Decision making

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：