检索结果-内蒙古大学图书馆

2nd International Conference on Edge Computing and Applications, ICECAA 2023

作者： Banik, Arnob Mishra, Divakar Manikandan, N. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India School of Computer Science and Engineering Vellore Institute of Technology Department of Database Systems Tamil Nadu Vellore India

ISBN: (纸本)9798350347579

Internet of Things (IoT) has lately been expanded across various applications, drawing significant attention to its design, where a loud industrial atmosphere can exist in the mining area. The central essence of this project was to detect hazardous events and to design a perfect, smart helmet that ensures the safety of workers. We have decided to implement a system that could be embedded in the helmets of the mine workers. Workers would be alerted via a helmet buzzer, so necessary action was taken on time. The critical feature of this project was that the model presented uses an application interface to detect real-time data and display it. The administrators outside may monitor the dynamic data from the system using a website and a mobile application. In contrast, the Android app displays or informs the data or alerts. The miners and the administrators can monitor real-time data that constantly changes according to the changes in the environment. They could also monitor the changes in temperature and humidity through graphs continuously updated on the applications. 'Rescue with Flexibility' was the main motto of our project. Thus, this project offers a directional platform that would bring a revolutionary change in this industry. © 2023 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

ViT-CD: A Vision Transformer Approach to Vehicle Collision Detection

ViT-CD: A Vision Transformer Approach to Vehicle Collision D...

引用

2023 IEEE Global Conference on Information Technologies and Communications, GCITC 2023

作者： Dalwai, Fahad Salim Kumar, Goutham Senthil Sharief, Zain Sharief Ashraf Narayanan, Swathi Jamjala Vellore Institute of Technology Vellore School of Computer Science and Engineering Tamil Nadu Vellore India

ISBN: (纸本)9798350308167

Traditional methods for accident detection often struggle to handle the complexities of dynamic scenes and varying lighting conditions, leading to sub-optimal performance in accident detection. Subsequently, Vision Transformers' self-attention mechanisms can be utilized to capture spatial relationships and contextual information within video frames, introducing an innovative solution for real-time vehicle collision detection in CCTV footage. The model proposed in this paper aims to utilize attention mechanisms within transformers to analyze and interpret visual data, presenting an efficient method for identifying potential collisions. The findings demonstrate the efficiency and accuracy of the proposed approach in relatively improving accident detection accuracy conclude with high-level insights into future research directions highlight the potential impact of ViT-based systems on enhancing road safety and underscore the need for their continued exploration and development. © 2023 IEEE.

关键词： CCTV footage computer vision Crash detection Feature extraction Image classification Self-attention mechanism

来源：评论

学校读者我要写书评

暂无评论

ReAD: Reliability aware data

引用

Materials Today: Proceedings 2022年 62卷 4844-4852页

作者： Sriraman, Harini Ravikumar, Aswathy Pattabiraman, V. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

As transistor technology scales beyond 32 nm, the reliability of the processors and servers reduces at an exponential rate. In recent times, the qualification of reliability of servers has reduced from 5 years to 3 years. With this current trend, the lifetime of servers can be expected to shrink further. In a cloud data center, with hundreds and hundreds of servers, the ill effect of shorter lifetime reliability will be magnified. Reliability of servers influences the performance, cost and power efficiency of a cloud data center. In this paper, a cost-effective technique to continuously monitor the reliability of servers and scheduling tasks based on these reliability values is proposed. The proposed technique monitors the hardware parameters for the current executing workload to calculate the reliability metrics. The reliability metric used in ReAD is MTTF (Mean Time to Fail) and this is calculated for individual servers. The load balancer reads the MTTF of individual servers and performs the load balance, considering reliability as one of the parameters. The proposed technique is non-invasive in nature and does not require the server to go into a special test mode. This saves the testing time. The experimental analysis shows on an average 25% improvement in Server Usage Metric with the minimum improvement around 5% and the maximum is around 50%. © 2022

关键词： Reliability

来源：评论

学校读者我要写书评

暂无评论

Enhancing Question Answer Generation from PDFs: A Fusion of BERT, RAKE, T5 and DistilBERT with RQUGE Evaluation 5th

Enhancing Question Answer Generation from PDFs: A Fusion of ...

引用

5th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2024

作者： Mary, A. C. Akshitha Acharya, Prachi Rakshinee, R. Jeyaseelan, Stefani Nandakumar, Thanvitha Sakthivel, V. Prakash, P. School of Computer Science and Engineering Vellore Institute of Technology Vandalur-Kelambakkam Road Chennai India

ISBN: (纸本)9789819788606

In educational institutes worldwide, the process of formulating questions for assessments and educational materials poses a recurring challenge. Traditional methods often involve manual question creation or keyword-based searches, leading to time-consuming and often inefficient processes, especially when dealing with extensive PDF documents. Addressing this prevalent issue, the research introduces a comprehensive approach to question–answer generation (QAG) from PDF documents. The system uses the most recent Natural Language Processing (NLP) models to extract text from PDFs using pdfplumber, create document summaries using BERT, extract keywords with RAKE, and create questions using a retrained T5 model. DistilBERT is then used to generate the answers. The RQUGE metric is used to assess the system’s performance. The outcomes indicate how well the suggested method generates pertinent queries and precise responses, highlighting its potential for use in information retrieval and document comprehension. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

Mapping of City Development and Urban Flooding Using Deep Learning Model for Chennai City Study Area 5th

Mapping of City Development and Urban Flooding Using Deep Le...

引用

5th International Conference on Computing and Network Communications, CoCoNet 2023

作者： Senthilkumar, Pavithraa Arthur, Menaka Pushpa School of Computer Science and Engineering Vellore Institute of Technology Chennai Campus Chennai600127 India

ISBN: (纸本)9789819747108

People’s lives and property are put in jeopardy by extreme weather occurrences such as floods, but key infrastructures, which must work even under subpar conditions, are also severely damaged. There have been a number of attempts to use deep learning algorithms to map the urban flood regions. In order to determine how vulnerable an area is to catastrophic flooding, it is critical to evaluate the flood-prone zones. Using Sentinel satellite photos, along with deep learning model, can help to map flood-prone areas and assess their vulnerability. Flood hazard mapping was evaluated using a Convolutional Neural Network (CNN) model. The response variable was a flood inventory of Chennai Corporation’s flooded and non-flooded areas, while the predictor variables were flood-affecting factors. The flooded areas were then randomly divided into sections for the purpose of constructing flood models and testing them. According to the training and testing classification accuracy, the models were evaluated on their ability to predict outcomes. Flood protection and risk assessment might benefit from the use of the model. As a result, if a flood inventory is available, this method might be used to create a flood danger map for metropolitan areas. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Predicting and Curing Depression Using Long Short Term Memory and Global Vector

引用

computers, Materials & Continua 2023年第3期74卷 5837-5852页

作者： Ayan Kumar Abdul Quadir Md J.Christy Jackson Celestine Iwendi School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India School of Creative Technologies University of BoltonBoltonUK

In today’s world, there are many people suffering from mentalhealth problems such as depression and anxiety. If these conditions are notidentified and treated early, they can get worse quickly and have far-reachingnegative effects. Unfortunately, many people suffering from these conditions,especially depression and hypertension, are unaware of their existence until theconditions become chronic. Thus, this paper proposes a novel approach usingBi-directional Long Short-Term Memory (Bi-LSTM) algorithm and GlobalVector (GloVe) algorithm for the prediction and treatment of these *** and fitness bands can be equipped with these algorithms whichcan share data with a variety of IoT devices and smart systems to betterunderstand and analyze the user’s condition. We compared the accuracy andloss of the training dataset and the validation dataset of the two modelsnamely, Bi-LSTM without a global vector layer and with a global vector *** was observed that the model of Bi-LSTM without a global vector layer hadan accuracy of 83%,while Bi-LSTMwith a global vector layer had an accuracyof 86% with a precision of 86.4%, and an F1 score of 0.861. In addition toproviding basic therapies for the treatment of identified cases, our model alsohelps prevent the deterioration of associated conditions, making our methoda real-world solution.

关键词： Emotion dynamics depression heart rate internet of things global vector long short term memory machine learning sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Disease Detection in Tomato Plant Leaf Using Deep Learning Techniques 8th

Disease Detection in Tomato Plant Leaf Using Deep Learning T...

引用

8th International Symposium on Intelligent Informatics, ISI 2023

作者： Choudhary, Piyush Vinothini, A. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India

ISBN: (纸本)9789819721467

The identification of diseases in plants is crucial for sustaining crop yield and securing global food resources. This study delves into the utilization of deep learning methodologies to precisely detect diseases in tomato plant leaves. Focused on the PlantVillage dataset, a comprehensive collection of tomato plant leaf images categorized as healthy or diseased is analyzed. Augmentation techniques, encompassing random transformations like rotations, flips, and zooms, are employed to diversify the training dataset, aiming to improve the models’ accuracy and generalization capacities. The deep learning models, including AlexNet, DenseNet, LeNet, and two bespoke models, undergo training with well-suited loss functions and are optimized using appropriate techniques. Assessment of the models’ performance involves metrics such as accuracy, loss, recall, precision, and F1 score, calculated on distinct validation sets. The outcomes indicate that the specifically tailored models for disease detection outperform established architectures. Notably, Custom Model 2 achieves an accuracy of 86.10% and an F1 score of 85%, while Custom Model 3 attains an accuracy of 86.84% and an F1 score of 86%. Contrastingly, AlexNet records an accuracy of 79% and an F1 score of 79.29%, DenseNet exhibits an accuracy of 89% and an F1 score of 88%, and LeNet scores an accuracy of 81% and an F1 score of 82%. This study underscores the potential of deep learning in precisely identifying plant diseases in tomato leaves, contributing to the advancement of sophisticated diagnostic techniques. Implementing these models in agricultural systems holds promise for proactive disease identification, safeguarding crops, and ensuring global food stability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A smart agriculture framework for IoT based plant decay detection using smart croft algorithm

引用

Materials Today: Proceedings 2022年 62卷 4758-4763页

作者： Gupta, Bhavya Madan, Gazal Quadir Md, Abdul School of Computer Science and Engineering Vellore Institute of Technology Chennai India

Internet of things (IOT) is an assuring technology which provides systematic and logical solutions towards the revolution of various realms. Various researches and analysis have been conducted and numerous methods have been incorporated to apply IoT technology on agronomical fields. IoT can play a vital role in timely detection of declining plant health so that appropriate measures can be taken. It is a huge step towards smart agriculture. In this paper we propose a model to build up an automated framework which will recognize the crop decay in the initial phase which is imperceptible to naked human eyes. This model helps in prevention of huge losses and also save a lot of time and labor. The proposed model builds a recognition framework using sensors like humidity, moisture, temperature and color of the plant leaf. The data from the sensors is sent to Arduino to Cloud which then analyzes the data and helps in identifying the plant decay. In the upcoming years, the internet of things will be a crucial bit in the smart farming system. © 2022

关键词： Moisture

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Weather Prediction

Deep Learning Techniques for Weather Prediction

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Dhanalakshmi, R. Paul, Tushar School of Computer Science and Engineering Vellore Institute of Technology Centre for Cyber Physical Systems Chennai India Masters of Computer Application Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331510022

Human activities are directly impacted by weather occurrences. Forest fires, high air temperatures that lead to drought, and extreme weather events caused by global warming all make life more difficult for humans. Precautions against such climatic calamities require weather forecast models that are both accurate and effective. As a result, creating models that accurately forecast the weather is crucial. The creation of effective models of deep learning-based weather forecasting was greatly aided by technological advancements. This study suggested a hybrid weather prediction model based on convolutional and recurrent neural networks, which had a decent success rate. The dataset named Jena, which comprises 14 parameters, extensive meteorological information that has not been used for predicting the weather, was subjected to the suggested hybrid model. The experimental findings were compared using well-known machine learning, deep learning, and statistical techniques such CNN, Integrated Moving Average with Auto-Regression, LSTM, RNN, Random Forest, Multilayer Perceptrons and SVM. These comparisons showed that the suggested hybrid model had the best prediction outcome across the board. For instance, the suggested hybrid model produced the following findings based on the weather forecast data for Jena. © 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

Optimized Crop Prediction System using Feature Selection Techniques with Machine Learning Classifiers 1

Optimized Crop Prediction System using Feature Selection Tec...

引用

1st International Conference on Intelligent Technologies for Sustainable Electric and Communications Systems, iTech SECOM 2023

作者： Sagana, C. Keerthika, P. Devendran, K. Thangatamilan, M. Karthikheyan, A.V. Magendraprasat, M.G. Mathiyalagan, M. Kongu Engineering College Computer Science and Engineering Erode India Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350371185

The Crop Prediction System stands as a pioneering milestone in precision agriculture, harnessing the capabilities of data-driven decision-making to revolutionize crop forecasting and resource allocation. This comprehensive project meticulously collects and pre-processes data, employing feature selection techniques to streamline data input for machine learning models. An ensemble model, skillfully constructed, exemplifies the potential for precise crop recommendations, carrying wide-ranging implications for sustainable agriculture. The project unfolds with an introduction to the significance of precision agriculture, the process of data collection and pre-processing, and the incorporation of feature selection methods. Subsequently, it delves into the machine learning phase, exploring the performance of various classifiers and the selection of a robust ensemble model. Hyperparameter tuning and optimization techniques refine the system's accuracy and efficiency. The project is underscored by a user-friendly interface, ensuring accessibility to a diverse range of users. This innovation transcends borders, enabling farmers to make informed decisions and resource allocation for increased crop yields. The Crop Prediction System offers a glimpse of the future, where data-driven technologies are poised to revolutionize agriculture practices worldwide, promising a more sustainable, productive, and economically stable future. © 2023 IEEE.

关键词： Forecasting

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：