检索结果-内蒙古大学图书馆

Maximum Demand Forecasting in the Delhi Region using Machine Learning

Maximum Demand Forecasting in the Delhi Region using Machine...

2023 International Conference on the Confluence of Advancements in Robotics, Vision and Interdisciplinary technology Management, IC-RVITM 2023

作者： Sujaykumar Reddy, M. Gopakumar, G. Vellore Institute of Technology Department of Computer Science & Engineering Vellore India National Institute of Technology Department of Computer Science & Engineering Calicut India

ISBN: (纸本)9798350306088

The National Capital Territory (NCT) of India, Delhi, is home to New Delhi, the country's capital. Being a significant political and economic hub, Delhi experiences unique considerations in terms of power consumption. As of May 31st, 2023, the highest recorded power demand in Delhi occurred on June 29th, 2022, reaching a peak of 7770 MW. The dataset used in this paper is the daily Power-Supply-Position (PSP) reports generated by the NLDC, GRID Energy Sector, India which is a division of the Ministry of Power. This paper forecasts the maximum demand produced by Delhi taking in consideration of the Producers side by using various Machine Learning Algorithms with different pre-processing techniques such as data Imputation and Transformation Techniques and MAPE (mean-absolute-percentage-error) is used as a metric to evaluate models. The results suggest that Gradient Boosting Regressor with 7 days shift feature extraction gives the highest accuracy through Linear-Interpolation-imputation for univariate data. © 2023 IEEE.

关键词： Electric power utilization

来源：评论

学校读者我要写书评

暂无评论

Video Based Cricket Shot Classification using modified LRCN Approach

Video Based Cricket Shot Classification using modified LRCN ...

引用

2024 IEEE Silchar Subsection Annual Conference, SILCON 2024

作者： Krithiga, R. Ramesh, Balaji Sriraam, C. Lionel Donato, L. Rojesh, S. School of Computer Science and Engineering Vellore Institute of Technology TamilNadu Chennai India

ISBN: (纸本)9798331540821

In recent years, advancements in Artificial Intelligence (AI) have caused major transformations in the realm of cricket analysis. From player performance evaluation to strategic decision-making, AI technologies have revolutionized how cricket is understood and played. In this paper, we focus on the task of classifying cricket shots using video data, leveraging deep learning methodologies. The proposed model aims to classify cricket videos into five distinct shot categories, utilizing the CricShot10 dataset originally comprising ten shot classes. With approximately 100-150 video clips per shot type, we streamline the classification task by selecting five fundamental shots for analysis. To accomplish this, we propose a modified architecture of the popular architecture combining Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks, commonly referred to as Long-Term Recurrent Convolutional Network (LRCN). Additionally, we integrate techniques such as MaxPooling2D, Dropout, Flatten, and Dense layers to enhance the model's performance and robustness. Through this proposal, we not only contribute to the field of cricket analysis but also demonstrate the efficacy of deep learning approaches in video-based sports analytics. © 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

Decentralization System Using Smart Blockchain with Secure Hash

引用

SN computer science 2023年第5期4卷 620页

作者： Tiwari, Meher Gayatri Devi Kumar, Kakelli Anil School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore 632014 India

Blockchain decentralization is a reference to decision making and transferring of data control. It is derived as a distributed network from a centralized network, either in an individual, organization, or group. The decentralized system reduces the user’s trust level, which has to be shown by one another. Instead, they confine the functionality of the system network to be degraded. This determines the ability to control the decentralized system using smart contracts. In this paper, we propose a blockchain decentralization system on the smart contracts produced by the blocks. This is called smart blockchain. Smart blockchain or Smart chain is the new generation of blockchain network that allows one or more than a smart contract. The decentralized system of smart contracts here collects the data accurately and flawlessly. The decentralized nature of smart blockchain ensures that there is no single point of control or failure, making it resistant to tampering, hacking, and other malicious activities. Simultaneously this decentralization method helps store and register the data in new blocks. The complete process of a transaction is automatic, without any human interaction. The blockchain used in networks like Ethereum, etc., can be entirely replaced by the smart blockchain or smart chain. The deployment and registration done in smart contracts are overcome with the smart blockchain. We have worked on the four processes in this paper. They are new_block, new_transaction, last_block, and hash. Using the flask framework, the requests are communicated and satisfied on the HTTP Protocol. The further assessment of this decentralized system enabling the smart blockchain can bring a difference in application research, such as Smart Homes using IoT technology. Smart blockchain technology evaluates security, complexity, privacy, integrity, and implementation protocols. Additionally, we experimentally show the protocols’ outperformance towards multiple blocks of a blockchain. © 2

关键词： Blockchain Decentralization Security Smart Blockchain Smart contracts Transactions

来源：评论

学校读者我要写书评

暂无评论

Diabetic Retinopathy Detection using Deep Learning Framework and Explainable Artificial Intelligence Technique 14

Diabetic Retinopathy Detection using Deep Learning Framework...

引用

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

作者： Posham, Uppamma Bhattacharya, Sweta School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798350344837

Diabetic retinopathy (DR) is a serious eye condition induced by diabetes that can result in eyesight. In order to overcome the vision impairment of diabetes mellitus patients, it is essential for early age prevention by medical practitioners. In the traditional approach, ophthalmologists conduct various screening tests to detect DR but fail to achieve accurate and conclusive diagnosis due to the associated time consuming processes. In order to eliminate such burden on the ophthalmologists, deep learning and machine learning techniques have evolved rapidly playing a significant role in the classification of diabetic and non diabetic patients. In this paper, the proposed framework implements a publicly available Benchmark APTOS 2019 Gaussian-filtered DR image dataset using a customized CNN model, yielding an enhanced accuracy of 98 %. In addition, the framework also employs a LIME explainer visualization model to provide enhanced transparency and interpretability to the generated predictions. This eliminates the 'blackbox' -ed nature of the predicted results from the traditional ML process and enables healthcare providers to take clinical decisions with confidence providing visual representations of the significant features that contribute towards an outcome. © 2024 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Classifier Based Approach for Crowd Anomaly Detection

引用

computers, Materials & Continua 2022年第7期72卷 349-364页

作者： Sofia Nishath P.S.Nithya Darisini School of Computer Science and Engineering Vellore Institute of TechnologyChennai600127India

Crowd Anomaly Detection has become a challenge in intelligent video surveillance system and *** video surveillance systems make extensive use of data mining,machine learning and deep learning *** this paper a novel approach is proposed to identify abnormal occurrences in crowded situations using deep *** this approach,Adaptive GoogleNet Neural Network Classifier with Multi-Objective Whale Optimization Algorithm are applied to predict the abnormal video frames in the crowded *** use multiple instance learning(MIL)to dynamically develop a deep anomalous ranking *** technique predicts higher anomalous values for abnormal video frames by treating regular and irregular video bags and video *** use the multi-objective whale optimization algorithm to optimize the entire process and get the best *** performance parameters such as accuracy,precision,recall,and F-score are considered to evaluate the proposed technique using the Python simulation *** simulation results show that the proposed method performs better than the conventional methods on the public live video dataset.

关键词： Abnormal event detection adaptive GoogleNet neural network classifier multiple instance learning multi-objective whale optimization algorithm

来源：评论

学校读者我要写书评

暂无评论

Insights on Improving Reasoning and Increasing Capabilities in Large Language Models 6th

Insights on Improving Reasoning and Increasing Capabilities ...

引用

6th International Conference on Computational Intelligence in Pattern Recognition, CIPR 2024

作者： Krisshna, S. Varun Sendhil, R. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Chennai India

ISBN: (纸本)9789819780891

Large Language models (LLMs) based on the Transformer architecture are designed to understand and generate human-like text by learning patterns and relationships from vast amounts of textual data. These models have been reported to have "sparks" of artificial general intelligence owing to their very attractive properties such as high generalization and performance in unseen data. These models have demonstrated strong capabilities in generalization and performance on novel data, leading some to speculate they may contain early sparks of artificial general intelligence. However, true AGI remains an unachieved goal requiring breakthroughs beyond current techniques. LLMs have poor mathematical reasoning capabilities, inherit biases present in training data, and can hallucinate and deliver false information. In this chapter, we discuss several methods that improve the current state-of-the-art models through the use of external tools such as web browsing, better prompting techniques, scaling, using Reinforcement learning (RL) and tree-based search algorithms. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Tropical Cyclone Intensity Prediction Using Deep Learning Techniques- A Survey 4

Tropical Cyclone Intensity Prediction Using Deep Learning Te...

引用

4th IEEE International Conference on Applied Electromagnetics, Signal Processing, and Communication, AESPC 2024

作者： Ilayaraja, V. Rajamohana, S.P. Jagadeesan, S. Aishwarya, V. Rakesh, M. School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore632 014 India School of Engineering & Technology Pondicherry University Department of Computer Science Puducherry Karaikal India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Department of Software and Systems Engineering Tamil Nadu Vellore632 014 India

ISBN: (纸本)9798331528171

Tropical cyclones, characterized by strong winds and heavy rainfall, threaten human life in coastal regions crucial to the economy, including fisheries, agriculture, tourism, and infrastructure. Their frequent occurrence impacts communities reliant on these industries for livelihoods. Accurate estimation of tropical cyclone intensity is vital for disaster preparedness, risk assessment, and timely evacuations. Recent advancements in machine learning and deep learning have been applied to predict cyclone intensity from satellite images, providing insights into cyclone dynamics and enhancing disaster response. This paper analyzes recent research on intensity estimation using various machine learning algorithms and discusses future prospects for improving accuracy and reliability. © 2024 IEEE.

关键词： Tropical cyclone

来源：评论

学校读者我要写书评

暂无评论

Prediction of Diseases in Potato Plant using Pre-trained and Traditional Machine Learning Models 4

Prediction of Diseases in Potato Plant using Pre-trained and...

引用

4th International Conference for Emerging technology, INCET 2023

作者： Sahu, Swati Laxmi Chintala Bhargavi, Renta Vellore Institute of Technology School of Computer Science and Engineering Chennai India Vellore Institute of Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350335750

Potato, among the most vegetables is commercially significant and well-known vegetable which is known for its high nutritional content and delicious flavor. India is one of the world's leading producers of potato. Unfortunately, plant diseases in potato have been one of the causes of decreased production. So, it is necessary to detect them. Collecting images of plants diseases is a big challenge as it is a very time-consuming process. Often, we do not have sufficient data to train our deep learning models, so data augmentation techniques are used for increasing the dataset which lead to poor generalization. This study focuses on detecting whether the plant is healthy or diseased. In this proposed method, limited dataset is used for potato plant disease classification without using any data augmentation techniques. Popular pre-trained models - VGG16, InceptionResNetV2, ResNet50V2 are used for feature extraction and traditional machine learning algorithms - XGBoost, Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Random Forest are used as classifiers. From the study, it is observed that the combination of VGG16 model as a feature extractor and SVM as a classifier achieved the highest accuracy of 93% compared to rest of the combination of models and algorithms. The method proposed in this study can be used for potato plant disease detection with limited dataset. © 2023 IEEE.

关键词： Vegetables

来源：评论

学校读者我要写书评

暂无评论

Enhancing Online Learning: A Pose and Emotion-Based Approach for Student Attention Monitoring 5th

Enhancing Online Learning: A Pose and Emotion-Based Approac...

引用

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

作者： Chingapurathu, Sarath Krishna Jeganathan, L. Janaki Meena, M. School of Computer Science and Engineering Vellore Institute of Technology TN Chennai600127 India

ISBN: (纸本)9789819747108

With the increasing popularity and preference of online classes, teachers are at a disadvantage of losing face-time with students and are faced with the challenge of monitoring their students’ attention levels remotely. This research, VisioFocus, presents a non-invasive student monitoring system using deep learning and computer vision to measure and analyze the attention levels of students. It has two main components namely Pose Estimation and Emotion Recognition which processes the captured facial images of the student through the webcam at 15 frames per second to measure the attention level. The Pose Estimation model uses pure computer vision and the Emotion Recognition model uses a modified ResNet deep convolutional network that could classify emotions portrayed into 6 different labels at about 70% accuracy. This research proposes a novel and reliable approach to measuring attention levels, which will have a significant impact on the education field. The analytical survey of attention levels after each lecture will enable educators to tailor their teaching approach to specific students, resulting in better academic development. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

An Automated Recommendation Model for E-Commerce Web Application Using Machine Learning 2

An Automated Recommendation Model for E-Commerce Web Applica...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Sheik Abdullah, A. Suseendhar, B. John, Sharon Jefrin, Tanisha School of Computer Science and Engineering Vellore Institute of Technology Chennai Chennai India

ISBN: (纸本)9798350366570

The rapid evolution of the Internet and technological advancements have revolutionized the retail landscape, giving rise to e-commerce as a dominant force in the industry. In response to the increasing demand for online shopping, businesses are compelled to develop innovative, user-friendly web applications to cater to evolving consumer needs. This abstract introduces an innovative e-commerce web application designed to transform the online shopping experience. Leveraging cutting-edge technologies, intuitive user interfaces, and personalized recommendations, our web application aims to enhance convenience, engagement, and customer satisfaction. Through a comparative analysis, we demonstrate that our solution surpasses existing methods. Our e-commerce web application boasts intuitive search and filtering capabilities, empowering users to easily navigate through a vast product catalogue. Moreover, sophisticated recommendation algorithms, driven by machine learning techniques, provide personalized product suggestions based on users' browsing and purchasing history, significantly enhancing the overall shopping experience. The web application ensures seamless performance, even during peak traffic periods and also offers integrated secure payment gateways for customers confidence and peace of mind while completing transactions. By combining advanced technology with user-centric design, this e-commerce web application sets a new standard for online shopping, promising increased convenience, engagement and satisfaction for users. © 2024 IEEE.

关键词： Marketplaces

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：