检索结果-内蒙古大学图书馆

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Rustum, Rubeena Laxmi, Vaddepally Navya, Siripuram Naveena, G. Sravanya, V. Gokaraju Rangaraju Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India

ISBN: (纸本)9798350397253

This study introduces a small companion Robot and with some of its interesting features. Sentiment Analysis by facial expressions and sentences, Object detection by YOLOv3 algorithm, Sentiment Analysis by which the robot can recognize all organisms face and detect the emotion by facial expressions by using CNN algorithm and cv2, speech recognition to recognize the sentiment of the sentences. The Robot is made by using various sensors and actuators like 8∗8 LED matrix which displays the emotion on the screen, it can move forward and backward by the geared DC motors and are implemented features of the Robot by using various types of Machine Learning Algorithms. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Visualization of Human Action Recognition: By Hidden Markov Model and Convolution Neural Network 1

引用

3rd Biennial International Conference on Future Learning Aspects of Mechanical engineering, FLAME 2022

作者： Ahmed, Aleem Jain, Garima Sharma, Amritanshu Hashim, Md. Raj, Aditya Department of Computer Science and Engineering Noida Institute of Engineering and Technology Greater Noida201310 India

ISBN: (数字)9789819930333

ISBN: (纸本)9789819930326

Humanity’s recognition action from a visual standpoint content is a difficult task as different types of problems arise in the recognition of human action. In the realm of computer vision, human action recognition (HAR) has reached a significant milestone. The advancement of technology allows us to address this issue and makes it a viable topic of research. A lot of research has already been done on HAR, and still, a lot is left. In this context, the focus of this survey is on the various types of HAR approaches that have been developed in the recent ten years. This paper uses a hidden Markov model based on several algorithms to solve the problem of human action recognition. We are comparing two techniques of HAR to find the best out of them. The hidden Markov model and the convolution neural network are two types of neural network. A convolutional neural network (CNN) capable of recognizing local patterns in input data is trained to recognize human actions from the local patterns in the feature representation. We found out that CNN is a better algorithm for recognizing human actions as it shows the body’s movement and body joints in two different aspects of the CNN graph. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

Holistic Knowledge Framework for Improving PC Design using Big Data Analytics 7

Holistic Knowledge Framework for Improving PC Design using B...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Rajendran, T. Vignesh, O. Priyadharsini, V. Jagadeesh, K. Rajalakshmi Institute of Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Easwari Engineering College Department of Electronics and Communication Engineering Chennai India Akshaya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Coimbatore India GRT Institute of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Tiruttani India

ISBN: (纸本)9798350397253

Cyberspace is massively expanding every day, and the users of these digital devices are looking for more innovative applications to ease their day-to-day work. The main objective of any device is to use available system resources at a maximum optimum level and give high performance to the users. Especially in personal computers (PC), there is still a massive gap in the user experience and utilization of available system resources. There are several situations where error conditions and system responsiveness lag. Over several years the digital world evolved and provided high-performance computing. Furthermore, the PC design enhancements could be carryout through the participation of PC users. That could be accomplished by collecting the system performance indicators, system behavior and properties, software application usage, user working log, and other wide range of real-time data from the PC. These telemetry data needed to be retrieved from an extensive array of PCs then these datasets would be reposited on the centralized servers. By applying the big data analytical methods and other mining algorithms over these extensive datasets to identify the hidden patterns and discover more knowledge about the key indicators that would help improve PC performance and user experiences. Through this knowledge acquisition model, the organizations and research institutions could develop the most resilient and adoptable PC designs and software applications developments. © 2023 IEEE.

关键词： Personal computers

来源：评论

学校读者我要写书评

暂无评论

Enhancement of Photovoltaic Dust Detection Using Deep Learning Technique

Enhancement of Photovoltaic Dust Detection Using Deep Learni...

引用

2024 International Conference on Advances in Modern Age Technologies for Health and engineering science, AMATHE 2024

作者： Gracia, R. Lillian Priyadharsini, C. Caroline, B.Elizabeth Karunya Institute Of Technology And Sciences Division Of Computer Science And Engineering Coimbatore India Ifet College Of Engineering Division Of Electronics And Communication Engineering Villupuram India

ISBN: (纸本)9798350371567

The dust collection on solar panels situated in solar parks is a common problem faced by PV system operators, particularly in arid and dusty regions. Dust deposition reduces the transparency of the panel surface, leading to decreased sunlight absorption and thus reduced energy conversion efficiency. Traditional methods for detecting dust accumulation involve manual inspection or periodic cleaning schedules, both of which are labor-intensive, time-consuming, and often inefficient. Recent developments in deep learning and machine vision have made autonomous dust detection techniquesfeasible. Numerous techniques have been employed to identify and measure dust on solar panels, such as machine learning models and image processing algorithms. In this paper, the dataset of clean and dusty images of the solar panels utilized wasapplied to four state of the art models and then the EfficientnetB0 model was proposed to detect the dust over the solar panels. On comparing the EfficientnetB0 model with the other state of the art models, EfficientnetB0 yielded an impressive accuracy rate of approximately 85.92%. Further research and development in this field hold the potential to revolutionize the maintenance and operation of solar power plants, contributing to a greener and more sustainable future. © 2024 IEEE.

关键词： Solar panels

来源：评论

学校读者我要写书评

暂无评论

An Approach to Predict and Classify Retinopathy Stages in Diabetic Patients Using Deep Learning 3

An Approach to Predict and Classify Retinopathy Stages in Di...

引用

3rd International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies, ICAECT 2023

作者： Rani, V.Vasudha Anupama, V. Santosh, M. Computer Science and Engineering GMR Institute of Technology Rajam India Lendi Institute of Engineering and Technology Department of CSE Jonnada India

ISBN: (纸本)9781665494007

Diabetic-caused retinopathy is a disease that damages the blood vessels that are present in the part of retina of the eyes and might lead to permanent blindness in people who have diabetes. Ophthalmologists use the fundus images of the eyes, which are the patients identify this disease. However, manual detection of this abnormality is very time taking, cost-consuming, and has a higher probability of resulting in errors. Thus, to prevent this, a Deep Learning model is proposed to detect Diabetic caused retinopathy by using high-resolution fundus images which as a result decreases the chances of misdiagnosis. Initially, fundus images are pre-processed by using the Contrast limited adaptive histogram equalization (CLAHE) model and histogram-based segmentation model. In the next step, features from the pre-processed images are extracted. However, it becomes very difficult for the individual models to identify the behind features that are complicated and those can only classify Diabetic Retinopathy's various stages at low accuracy. Thus, to resolve this an ensemble of three deep Convolution Neural Network (CNN) models (Inceptionv3, Xception, and DenseNet121) is developed which will encode the rich features and improve the classification for different stages of DR like normal, mild, moderate, severe and PDR (Proliferative Diabetic Retinopathy). The results show that the proposed ensemble model detects all the Diabetic Retinopathy stages, not like the individual models and performs better comparatively. This improvement can thus reduce time, effort, and labor in healthcare services and will also increase the final decision accuracy. © 2023 IEEE.

关键词： Blood vessels

来源：评论

学校读者我要写书评

暂无评论

Identification and Containment of Intrusion Attacks in an IIoT Network based on Machine Learning and Blockchain technology 2

Identification and Containment of Intrusion Attacks in an II...

引用

2nd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2024

作者： Motamarri, Nikhita Satish, G. Uma, H.R. Barve, Amit Patil, Harshal Taqui, Syed Noeman Potti Sreeramulu Chalavadhi Mallikarjuna Rao College of Engineering and Technology Department of Computer Science and Engineering Vijayawada Andhra Pradesh 520001 India Sree Dattha Institute of Engineering and Science Department of Electrical and Electronics Engineering Sheriguda Ibrahimpatnam Telangana Hyderabad501510 India BGS Institute of Technology Adichunchanagiri University Department of Computer Science and Engineering Mandya Karnataka 571448 India Parul Institute of Engineering and Technology Parul University Department of Computer Science and Engineering Gujarat 391760 India Department of Computer Science and Engineering Pune Maharashtra 412115 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of VLSI Microelectronics Tamilnadu Chennai602105 India

ISBN: (纸本)9798350327533

The Blockchain technology is leveraged to establish a secure and tamper-resistant decentralized ledger, providing a transparent and immutable record of all transactions and communications within the IoT network. By implementing smart contracts, we ensure the integrity and authenticity of device interactions, mitigating the risk of unauthorized access and data manipulation. Complementing the Blockchain, Machine Learning (ML) algorithms are employed to analyze and identify patterns indicative of malicious activities. The proposed system employs anomaly detection models, trained on historical data, to continuously monitor and adapt to emerging threats. This dynamic threat detection mechanism enhances the ability of the IoT network to recognize and respond to sophisticated intrusion attempts in real-Time. Furthermore, the proposed framework incorporates a decentralized identity management system using Blockchain, ensuring that only authenticated and authorized devices can participate in the IoT network. This not only safeguards against unauthorized access but also protects the privacy and integrity of the data generated and exchanged by IoT devices. To validate the effectiveness of our approach, we conducted experiments in a simulated IoT environment, considering various attack scenarios. The results demonstrate a significant improvement in the overall security posture of the IoT network, with reduced false positives and swift identification of intrusions. In conclusion, the integration of Blockchain and ML techniques provides a robust and adaptive defense mechanism for IoT device networks. This holistic approach addresses the challenges of security, privacy, and data integrity, paving the way for a more resilient and trustworthy IoT ecosystem in the face of evolving cyber threats. © 2024 IEEE.

关键词： Blockchain Integrity Internet of Things (IoT) Intrusion Intrusion Detection System Machine Learning Security

来源：评论

学校读者我要写书评

暂无评论

Star Profile and Audience Interest-Based Movie Rating Prediction Model 8

Star Profile and Audience Interest-Based Movie Rating Predic...

引用

8th IEEE International Conference on Information and Communication technology, CICT 2024

作者： Vyas, Avani Sharma, Shivani Dr B R Ambedkar National Institute of Technology Jalandhar Department of Information Technology Jalandhar India Thapar Institute of Engineering and Technology Department of Computer Science Engineering Patiala India

ISBN: (纸本)9798331531539

In today's entertainment era, several movies are produced over a year. We all try to get a review of any movie before planning to watch it. Much work has been done in the past for early movie success prediction but most of them are from the production perspective. However, the audience perspective is still unexplored. Further, most of the predictive models work with some basic features such as genre, cast, comments, reviews, and production house. However, a few important factors such as current audience interest shift, the social influence of the star, and personal liking of a person are much more important in predicting the rating of a movie. In this work, we propose an advanced movie rating prediction cross model, which could rate movies according to general as well as some fine-tuned features. This helps in providing a fair prediction of a movie according to global and personal audience interests. We collected a wide range of data from the Web, and social media along with the IMDb dataset. A comparative analysis of the proposed model with existing benchmark schemes has been done. Significant improvement in movie rating and success prediction is observed with an accuracy of 87%. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

READS: Resource efficient attack detection system for drones

引用

Multimedia Tools and Applications 2024年 1-20页

作者： Vishnu, Aditya Arora, Sumedha Kerala University of Digital Sciences Innovation and Technology Kerala Thiruvananthapuram India Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahemdabad India

Unmanned Aerial Vehicles (UAVs), commonly known as aerial drones, have gained popularity due to their versatility and applications in various industries. However, their increasing use has raised concerns about cybersecurity and the vulnerability of networked UAVs to malicious attacks. A deep learning-based Attack Detection System (ADS) is essential for mitigating cyber threats to UAVs. It can provide proactive protection even against unknown attacks. Also, for resource constraints of UAVs, ADS must be resource-efficient to optimize the deep learning model for embedded hardware, making a low code footprint. Therefore, this work focuses on developing a Resource Efficient Attack Detection System (READS) for drones that uses a lite deep learning-based network activity classification algorithm for detecting cyber threats on UAVs. The entire system has been implemented in three phases, where the first phase includes dataset training. The second phase involves running multiple conventional models to choose the best conventional model for intrusion detection using accuracy, precision, and recall. This is followed by phase three, which converts the selected conventional Dense Neural Network (DNN) model into a lite weight (Tiny) model that works on UAVs. The selected Lite DNN model is evaluated on a real-time testbed. The optimized model could lower the storage space and generates 97.69% accuracy. The proposed system consumes 30% of the original power. Hence, it allows efficient threat detection while minimizing the impact on UAV resources. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

AFSTGCN:Prediction for multivariate time series using an adaptive fused spatial-temporal graph convolutional network

引用

Digital Communications and Networks 2024年第2期10卷 292-303页

作者： Yuteng Xiao Kaijian Xia Hongsheng Yin Yu-Dong Zhang Zhenjiang Qian Zhaoyang Liu Yuehan Liang Xiaodan Li School of Information and Control Engineering China University of Mining and TechnologyXuzhou221116China Department of Informatics University of LeicesterLeicesterLE17RHUK The Affiliated Changshu Hospital of Soochow University Changshu215500China School of Computer Science and Engineering Changshu Institute of TechnologySuzhou215500China

The prediction for Multivariate Time Series(MTS)explores the interrelationships among variables at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other ***,it is important to construct a digital twin ***,existing methods do not take full advantage of the potential properties of variables,which results in poor predicted *** this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)***,we fuse the spatial-temporal graph based on the interrelationship of spatial ***,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding ***,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)*** module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like *** dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature information to enhance the predicted *** on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step performance compared with eight other deep learning models.

关键词： Adaptive adjacency matrix Digital twin Graph convolutional network Multivariate time series prediction Spatial-temporal graph

来源：评论

学校读者我要写书评

暂无评论

Improving long-tail classification via decoupling and regularisation

引用

CAAI Transactions on Intelligence technology 2025年第1期10卷 62-71页

作者： Shuzheng Gao Chaozheng Wang Cuiyun Gao Wenjian Luo Peiyi Han Qing Liao Guandong Xu School of Computer Science and Technology Harbin Institute of TechnologyShenzhenChina Peng Cheng Laboratory ShenzhenChina Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies Harbin Institute of TechnologyShenzhenChina Faculty of Engineering and Information Technology University of Technology SydneySydneyNew South WalesAustralia

Real-world data always exhibit an imbalanced and long-tailed distribution,which leads to poor performance for neural network-based *** methods mainly tackle this problem by reweighting the loss function or rebalancing the ***,one crucial aspect overlooked by previous research studies is the imbalanced feature space problem caused by the imbalanced angle *** this paper,the authors shed light on the significance of the angle distribution in achieving a balanced feature space,which is essential for improving model performance under long-tailed ***,it is challenging to effectively balance both the classifier norms and angle distribution due to problems such as the low feature *** tackle these challenges,the authors first thoroughly analyse the classifier and feature space by decoupling the classification logits into three key components:classifier norm(*** magnitude of the classifier vector),feature norm(*** magnitude of the feature vector),and cosine similarity between the classifier vector and feature *** this way,the authors analyse the change of each component in the training process and reveal three critical problems that should be solved,that is,the imbalanced angle distribution,the lack of feature discrimination,and the low feature *** from this analysis,the authors propose a novel loss function that incorporates hyperspherical uniformity,additive angular margin,and feature norm *** component of the loss function addresses a specific problem and synergistically contributes to achieving a balanced classifier and feature *** authors conduct extensive experiments on three popular benchmark datasets including CIFAR-10/100-LT,ImageNet-LT,and iNaturalist *** experimental results demonstrate that the authors’loss function outperforms several previous state-of-the-art methods in addressing the challenges posed by imbalanced and longtailed datasets,t

关键词： computer vision image classification long-tailed data machine learning

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：