检索结果-内蒙古大学图书馆

5th International Conference on computer Vision, Image and Deep Learning, CVIDL 2024

作者： Peng, Bo Dong, Chen Tianjin University of Technology School of Computer Science and Engineering Tianjin China

ISBN: (纸本)9798350373820

Time series clustering is a complex unsupervised data mining and analysis technique that can be applied to various fields such as signal processing, financial analysis, and more. However, time series data often contain missing values due to reasons such as sensor failures, data corruption, or intentional omissions in the real world. Traditional generative imputation methods operate independently from subsequent clustering tasks, and their performance relies on the combination with the clustering method, lacking a deeper connection. Efficiently integrating imputation and clustering tasks into a unified framework remains a formidable challenge. This paper presents a novel model that harmonizes the imputation and clustering processes, referred to as the Conditional Dual-Discriminator Generative Adversarial Network for Incomplete Time Series Data Imputation and Clustering (TsCDD-GAN). The TsCDD-GAN model leverages advanced bi-directional Recurrent Units (Bidirectional RNN) as the generator to learn and impute missing data, integrating two discriminators. The first discriminator assists the generator in producing more authentic values, while the second, a conditional discriminator, extracts clustering information from the latent representations of the data. This enables the generator to not only generate more realistic values but also ensure that the imputed data exhibit cluster-friendly characteristics. Through experiments conducted on the UCR time series dataset, our model has demonstrated better performance in terms of imputation accuracy on incomplete datasets. © 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

Voting Ensemble: Performance Improvement for Intrusion Detection System 3

Voting Ensemble: Performance Improvement for Intrusion Detec...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Rajathi, C. Rukmani, P. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350372120

In the present digital world, security has become increasingly challenging. Many organizations rely on security mechanisms to safeguard their resources from intrusion. However, previous research indicates that despite the implementation of several security measures, organizations still face security breaches. Therefore, organizations must adopt an effective security mechanism. One such mechanism is the Intrusion Detection System (IDS), which examines network traffic to protect an organization from potential attacks. To handle the large volume of network traffic, a well-organized classification system is necessary. Machine learning classification, among the various approaches used in research, provides an effective and efficient solution for detecting intrusion and enhancing security. Despite significant efforts, IDS still faces challenges due to the nature of the concept drifting. To mitigate this issue, a hybrid ensemble approach is proposed. This approach combines the Majority Rule Ensemble (MRE) and Probability Consensus Ensemble (PCE). The ensemble is constructed using various classification algorithms such as Logistic Regression (LR), Naive Bayes (NBC), K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree (DT), and Random Forest (RF). Each algorithm was individually built on the training dataset. The hybrid ensemble, which employs the MRE and PCE as aggregation methods, is then prepared by fitting it to the dataset. The proposed model's effectiveness is assessed using Network Security Laboratory - Knowledge Discovery and Databases (NSL-KDD) and a real-time testbed dataset. The results from the proposed hybrid ensemble show the improvement in the model's performance and the adaptability to the drifting nature of the intrusion dataset compared to a standalone model. © 2024 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

A Novel Intelligent Task Offloading Scheme for Multi-Controller Environment in Software Defined Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第12期12卷 20018-20029页

作者： Hussain, Mir Wajahat Sangaiah, Arun Kumar Reddy, K. Hemant Kumar Roy, Diptendu Sinha Alenazi, Mohammed J.F. Javvaji, Pavan Kumar Department of Computer Science and Engineering Alliance College of Engineering and Design Alliance University Karnataka Anekal562106 India International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan School of Engineering and Technology Sunway University Selangor Petaling Jaya47500 Malaysia University Centre for Research and Development Chandigarh University Punjab Mohali140413 India School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati522237 India Department of Computer Science and Engineering National Institute of Technology Meghalaya 793003 India College of Computer and Information Sciences Department of Computer Engineering King Saud University Riyadh11451 Saudi Arabia

The Internet of Vehicles (IoV), equipped with sensors, generates vast amounts of data, demanding rigorous computation and network. The cloud computing platform meets these stringent computation requirements, but it has a significant latency that fog computing effectively handles. Software Defined Network (SDN) has become the de facto standard for next-generation networking due to its unique and flexible features, which handle the network pre-requisites in an agile manner. Task Offloading (TO) is a crucial issue in Software Defined-IoV (SDIoV), particularly when the vehicle's resources are insufficient. Fog nodes schedule offloaded tasks;however, neglecting computational and network details during task scheduling can lead to longer completion times, thereby restricting the functionality of SD-IoV due to its time-sensitive nature. Therefore, this paper introduces two proactive Intelligent Task Offloading (ITO' and ITO) schemes. These schemes schedule tasks onto fog nodes with enhanced computational capabilities, dynamically enable the network through the ovs-ofctl SDN utility, and consider vehicle mobility during task scheduling. Experiments with Mininet show that the proposed (ITO' and ITO) schemes improve performance in terms of CPU availability, bandwidth, and throughput by 5.2 times, 50% and (30.7-13.9)% more than the existing scheme. They also reduce average packet loss, delay, Round Trip Time (RTT), and offloaded node time selection by (45.35-21.3)%, (50-33.3)%, (53.9-9.9)% and (43.2-26.06)% which demonstrates the efficacy of the proposed scheme. © 2025 IEEE.

关键词： Fog computing

来源：评论

学校读者我要写书评

暂无评论

Enhanced Interpupillary Distance Identification for Children Using YOLOv5 and YOLOX Object Detection Models

Enhanced Interpupillary Distance Identification for Children...

引用

2024 International Conference on Integration of Emerging Technologies for the Digital World, ICIETDW 2024

作者： Sandhya, P. Padmaja, V. Srivats, R. Kalyanasundaram, V. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331541170

Interpupillary distance (IPD), which is the distance between the centers of the pupils of the eyes, is a key measurement in many applications, including optics, virtual reality, and medicine. Measuring IPD in adults is generally easier than measuring it in children due to adults' more stable eye positions and greater cooperation during the measurement process. Additionally, adults have a longer attention span, which aids in maintaining focus. Historically, technological options for accurately measuring IPD in children have been limited compared to those available for *** this work, we present a novel approach to accurately measure the IPD of children aged 5 to 15 years using an object detection model. Data were personally collected from students in this age group and subsequently pre-processed and annotated using labelImg software. The YoloV5 and YoloX models were employed for object detection, with YoloV5 demonstrating superior performance on the dataset. This model was utilized to locate the centers of the pupils and calculate the IPD using the Euclidean distance method between the centers of the bounding boxes for the detected pupils. The model accurately detected IPD while accounting for even the slightest variations in different eye movements and gazes, providing precise results. Additionally, a chin rest and a brief flash were incorporated as a gaze correction methodology to further enhance measurement accuracy. The precise measurement of IPD enables the customization of spectacles for children, ensuring better fit and comfort. © 2024 IEEE.

关键词： Eye movements

来源：评论

学校读者我要写书评

暂无评论

Disaster Scene Classification with Deep Learning: A Keras-Based Approach Utilizing Robotic Systems

Disaster Scene Classification with Deep Learning: A Keras-Ba...

引用

2024 IEEE Students Conference on engineering and Systems, SCES 2024

作者： Arora, Gautam Bhavadharini, R.M. School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350374711

This study presents an innovative technique that leverages convolutional neural networks (CNNs), an advanced computer vision methodology, to enhance the timely detection and classification of natural disasters. The objective is to develop a dependable model capable of categorizing various disaster- related photos and videos, such as cyclones, earthquakes, floods, and wildfires, by employing extensive datasets and sophisticated CNN architectures like Visual Geometry Group (VGG) including VGG16 and VGG19. A significant advancement introduced in this research is the seamless integration of robotics, enabling autonomous data collection and real-time decision-making at disaster sites. Through a technique encompassing model development and data preprocessing, the effectiveness of our approach in disaster scene classification is demonstrated. The findings exhibit remarkable performance: post 48 training epochs, the VGG19 model achieved an impressive 97% accuracy, while the VGG16 model achieved a commendable 93% accuracy. These outcomes underscore the potential of CNNs to revolutionize disaster management strategies and pave the way for swifter and more efficient responses to mitigate the impact of natural disasters on society. © 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

Automated Email and SMS Notification System for Unauthorized Entry using Yolov9 10

Automated Email and SMS Notification System for Unauthorized...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Dhanuka, Eeshaan Dhavakumar, P. Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350353068

Security breaches present a serious risk in a variety of settings, thus strong detection and alerting systems are required to efficiently reduce risks. This study proposes a novel way for developing an Automated Email and SMS Notification System customized for unauthorized entrance detection using the YOLOv9 object identification model. By utilizing the capabilities of YOLOv9, the system quickly detects unwanted people or things in the monitored areas and sends out automatic emails and SMS notifications to selected stakeholders. Our technology improves security measures by combining cutting-edge machine learning techniques with communication technologies. This allows for the rapid response to possible attacks through real-time notifications. Test results show that the system is effective in identifying unwanted entries and reducing false positives, strengthening security protocols in many contexts. © 2024 IEEE.

关键词： Electronic mail

来源：评论

学校读者我要写书评

暂无评论

An Integrated Dynamic Behavior Analysis and Adaptive Detection Framework for Enhanced Cloud Malware Detection

An Integrated Dynamic Behavior Analysis and Adaptive Detecti...

引用

2024 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Keerthika Devi, S. Sandhya, G.R. Krithika, J. Joseph, Linda School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331543617

As malware threats continue to evolve and pose significant risks to cloud computing environments, there is a pressing need for advanced detection systems that can effectively address these challenges. This research introduces the Dynamic Behavior Analysis and Adaptive Detection Network (DBA-ADN), a novel framework designed to enhance malware detection through a combination of dynamic behavior analysis and adaptive detection techniques. DBA-ADN integrates real-time behavioral data with sophisticated adaptive algorithms to achieve superior detection performance. The study involves a comprehensive comparison of DBA-ADN against several benchmark systems, including MDCD, GloVe with CNN, CloudIntellMal, Hybrid Deep Learning Models, and DenseNet-121. The results reveal that DBA-ADN outperforms these established methods, achieving an impressive accuracy of 98.20% and an F1 Score of 0.99. This enhanced performance is attributed to DBA-ADN's ability to accurately identify both known and novel malware threats while minimizing false positives and false negatives. The framework's innovative approach addresses key limitations observed in existing solutions, as difficulties in handling sophisticated malware and inefficiencies in traditional detection techniques. By leveraging dynamic behavior analysis and adaptive algorithms, DBA-ADN not only improves detection accuracy but also reduces the complexity of deployment compared to its counterparts. The findings highlight DBA-ADN's potential to set a new benchmark in malware detection within cloud environments, offering a robust solution to the ongoing challenges of cybersecurity. This research contributes significantly to the field by providing a highly effective and adaptable approach to malware detection, laying the groundwork for future advancements and continued innovation in the domain. © 2024 IEEE.

关键词： Cloud security

来源：评论

学校读者我要写书评

暂无评论

An Unified Approach for Traffic Sign Classificationand Flow Prediction using Deep Learning Technique 15

An Unified Approach for Traffic Sign Classificationand Flow ...

引用

15th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2024

作者： Kavitha, D. Lekhana, Kommareddy Rajeshri, Vigrahala Rushitha, Chennareddygari School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798331300579

Efficient and safe traffic management is an important concern in modern urban environments. To address this challenge, we propose an integrated deep learning based solution that unifies traffic sign classification and traffic flow prediction using the LeNet architecture. The seamless fusion of these two critical tasks enables a holistic approach to traffic management, benefiting autonomous vehicles, traffic control systems, and road safety. In this unified approach, LeNet, a seminal convolutional neural network (CNN), serves as the backbone for traffic sign classification. Lenet Network is a very famous kind of configuration of convolutional neural networks that can be used to classify *** this paper, we have used Lenet to classify traffic signs, mainly used for selfdriving cars. Leveraging LeNet's capability to recognize traffic signs with high accuracy, we train it on a comprehensive dataset comprising 43 different classes of traffic signs. This dataset encompasses a wide range of shapes, colors, and conditions, allowing the LeNetbased classifier not only to identify individual traffic signs but also to provide valuable context for downstream traffic flow prediction. Extensive experiments on diverse datasets validate the effectiveness of our unified approach. We demonstrate superior traffic sign classification accuracy using LeNet, surpassing previous state-of- art methods. Additionally, our traffic flow prediction capabilities exhibit impressive accuracy and robustness across various traffic scenarios. Traffic flow prediction helps people for effective route planning so that the people can chose their routes to save and fuel and it helps to reduce traffic congestion. This research represents a significant step toward enhancing traffic management systems efficiency and safety by leveraging deep learning techniques. Our unified approach, combining LeNet- based traffic sign classification with traffic flow prediction, holds great promise for smarter and more r

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Prophet and NeuralProphet compared with Indian inflation data 11

Prophet and NeuralProphet compared with Indian inflation dat...

引用

11th IEEE International Conference on Signal Processing and Integrated Networks, SPIN 2024

作者： Subburaj, Brindha Agrawal, Aditya Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350308433

The word inflation is a commonly used expression to describe the overall increase in the costs of products and services in the market over time. In this research work, we will look at inflation as a whole, as well as for various population categories and goods within each population group. We will investigate demographic groups such as urban, rural, and combined, and we will compute the real Consumer Price Index (CPI) using the Reserve Bank of India's (RBI) weighted average technique. This research used statistics from 2011 to 2022. The RBI calculates the real CPI using a weighted average technique that takes into consideration the relative significance of various commodities within a population category. This technique is used to guarantee that the CPI accurately reflects the actual expense of living for the population group under consideration. It is essential to observe, that inflation varies significantly between various population groups and commodities. Because of higher living expenses and a higher demand for goods and services, urban areas generally have higher inflation rates. Rural regions, on the other hand have lower inflation rates because of reduced living expenses and lower demand for products and services. We can obtain a clearer grasp of how inflation impacts various segments of the population by analyzing data for these distinct population *** the basis of inflation statistics, this article compares two time-series forecasting models, Prophet and NeuralProphet. Both algorithms will be tested on the same data and their accuracy in forecasting will be contrasted. The root mean squared error (RMSE) and Mean absolute error (MAE) will be used as comparative statistics to assess accuracy. The performance of Prophet and NeuralProphet is evaluated in time-series forecasting and to look into the possible benefits of using parallelism on Prophet. This study's results will cast light on the relative strengths of these techniques. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

The Method for Detecting Abnormal Actions in Industrial Robots Based on Robots Spatio-Temporal Graph Normalizing Flow 5

The Method for Detecting Abnormal Actions in Industrial Robo...

引用

5th International Symposium on computer engineering and Intelligent Communications, ISCEIC 2024

作者： Xiao, Wen Chen, Deng School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331518677

Rapid detection and response to abnormal movements of industrial robots can effectively reduce the risk of injury. Abnormal action detection requires modeling and distinguishing the complex and variable action patterns of industrial robots, which needs to take into account the spatio-temporal coupling and dynamic characteristics of industrial robots' actions, while efficient processing of spatio-temporal features and complex dynamics models requires a large amount of computational resources, which limits the accuracy and response speed of detection. To this end, we propose a robots spatio-temporal graph normalized flow (RSTG-NF) model for abnormal action detection of industrial robots. The model uses a Robots Spatio-Temporal Convolutional Network (RSTGC) to capture and differentiate the complex action relationships and motion patterns of industrial robots actions in both temporal and spatial dimensions. The frame-level action sequences are placed in a bi-directional mapping between the high-dimensional data space and the low-dimensional potential space through normalized flow, and the anomaly scores are evaluated based on the mapped data distributions for localization and detection of anomalies. Extensive experiments on a home-made six-axis industrial robots action dataset (IRADs) show an AUC score of 92.18% for frame-level detection and an inference speed of 79 FPS. © 2024 IEEE.

关键词： Industrial robots

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：