检索结果-内蒙古大学图书馆

2nd International Conference on Computing, Communication, and Learning, CoCoLe 2023

作者： Naveena, Prathi Dash, Sandeep Kumar Department of Computer Science and Engineering National Institute of Technology Mizoram Aizawl India

ISBN: (纸本)9783031569975

With the profligate progress of graph-based data in numerous areas essential to observe the similarities among the graph pairs is indispensable to speed up the search outcomes. The existence of near-duplicate text documents plays an imperative role in performance degradation while integrating information from diverse sources. The main issue is determining the similarity among the graphs from massive datasets. The principal goal of this paper is to enhance search optimization with improved indexing and condensed pairwise comparisons with the help of the proposed Graph Similarity Self Join of Documents (GSSJD) technique is formed by uniting the prefix filtering strategy to the traditional inverted index method. Experiments were carried out on the dataset to authenticate that our proposed approach illustrates the optimized results in speed and time. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

An autoencoder based unsupervised clustering approach to analyze the effect of E-learning on the mental health of Indian students during the Covid-19 pandemic

引用

Multimedia Tools and Applications 2024年 1-21页

作者： Banerjee, Pritha Jana, Chandan Saha, Jayita Chowdhury, Chandreyee Computer Application and Science Institute of Engineering and Management West Bengal Kolkata700091 India Computer Science and Engineering Jadavpur University West Bengal Kolkata700032 India Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal Karnataka Bengaluru560064 India

Due to the Covid-19 pandemic, the education system in India has changed to remote that is, online study mode. Though there are works on the effect of teaching learning on Indian students, the effect of online mode and associated mental state, particularly when the entire country is going through a crisis could not be found in the literature. Our goal is to analyze data and find some pattern through which we can understand the effectiveness of the online study and also try to figure out the stress level. The dataset we collected from 500 undergraduate college students during April-May, 2021 is in questionnaire format. Our contribution in this paper are - (i) publishing a dataset of student feedbacks, and (ii) designing a data processing pipeline involving autoencoders followed by clustering approach. The dataset is in text format so for our analysis we have converted the dataset into a numerical format using the concept of a binary bag of words. Dimensionality reduction is applied through autoencoder for an effective latent space representation. Finally, for finding patterns out of this dimensionally reduced feature space, we have applied unsupervised learning algorithms - kMeans and DBSCAN. A thorough analysis of the clustering process reveals that the absence of social communication in purely online education provokes isolation irrespective of the urban or rural background of the students. However, it could supplement offline classes as a substantial number of students welcomed the concept of online learning as reported in the data. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

QoS-Aware Flow Routing with Minimizing Active Links and Rule Capacity Constraints in SDN Networks 22

QoS-Aware Flow Routing with Minimizing Active Links and Rule...

引用

22nd International Symposium on Network Computing and Applications, NCA 2024

作者： Kamboj, Priyanka Pal, Sujata Department of Computer Science and Engineering Indian Institute of Technology Punjab Ropar India

ISBN: (纸本)9798331510183

The growing demand for digitization necessitates modifications to current Internet technologies to effectively support Internet of Things (IoT) applications and services. Software-defined networking (SDN) supports network abstraction and dynamic management through a central controller. The ternary content addressable memory (TCAM) memory used in the OpenFlow switches is very costly and limits the flow table size. The limited size of TCAM memory motivates us to think about the flow rule replacement in SDN switches. This paper introduces a routing approach to meet traffic flow requirements in the SDN networks, consisting of two main phases – routing path selection and flow rule replacement. In the first phase, we formulate a minimum cost routing problem to minimize the network’s active links as an integer linear program (ILP) in SDN networks. We then introduce a greedy heuristic-based solution to solve the ILP in polynomial time. In the second phase, we propose a flow rule replacement method that utilizes idle timeout settings to prevent overflow in the flow tables of SDN switches. The simulation results indicate that our proposed approach reduces active links by 15%, 24%, 34% in the Goodnet topology, and by 11%, 23%, 33% in the Sprint topology as compared to benchmark schemes ROSA, LARAC, and SPD, respectively. Additionally, we analyze the impact of idle timeout on flow table entries within both our proposed approach and the benchmark schemes. ©2024 IEEE.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

PUF-based Lightweight Mutual Authentication Scheme for IoT-based Smart Grids 18

PUF-based Lightweight Mutual Authentication Scheme for IoT-b...

引用

18th IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2024

作者： Khatua, Manas Das, Sreeparna Rana, Pratik Manoj Indian Institute of Technology Guwahati Department of Computer Science and Engineering Guwahati India

ISBN: (纸本)9798350391725

Smart grids have paved the way for the amalgamation of electricity and the Internet of Things (IoT). IoT enables communication of important data, such as electricity consumption, between the smart meter and the server. At the same time, it makes the system vulnerable to cyber-attacks as the IoT devices are resource-constrained in nature and not equipped with adequate in-built security. Thus, secure and lightweight authentication schemes are of utmost need. Existing literature on lightweight authentication schemes are either computationally heavy specifically during authentication operations or need high communication and storage requirements. This paper mainly focuses on authentication phase as it is executed many times in the lifespan of an IoT device compared to the device registration phase. To address the above issues, this paper proposes a lightweight mutual authentication scheme that can protect the system from various attacks such as man-in-the-middle (MITM) and replay attacks. The proposed scheme uses physically unclonable function (PUF) primitives of IoT devices to alleviate the long-term storage requirement in the devices and further makes the scheme secure by achieving operational asymmetry. Unlike many existing schemes, our proposed scheme performs the device enrolment phase through the insecure channel as in many real-world applications. We have verified the security of the proposed scheme through formal and informal analysis. Further, we have done a test-bed implementation and analysis using off-the-shelf available hardware to represent IoT devices. In all the analysis, it is observed that the proposed scheme is lightweight and secure compared to the state-of-the-art schemes. © 2024 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

An Internet of Things-Based Proxy Re- Encryption Method for Safe Data Sharing Based on Blockchain 2

An Internet of Things-Based Proxy Re- Encryption Method for ...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Shashikala, S.V. Amith, D. Disha, T.S. Lekhana, H.L. Likith, R. Department of Computer Science and Engineering BGS Institute of Technology Adichunchanagiri university India

ISBN: (数字)9798350383867

ISBN: (纸本)9798350383867

Internet of Things has developed, one of its most beneficial uses in cloud computing has been data sharing. Even though this technology has attracted attention, one of its ongoing challenges is data security since improper usage of data can result in several losses. Here, we offer a proxy re-encrypt technique for secured cloud data sharing. Data holders can transfer their encrypt files to the cloud using identity-base encryption, where it is accessed by authorized users using proxy re-encrypt construction. Because Due to their restricted resource availability, Internet of Things devices use edge devices as proxy servers manage computationally demanding tasks. We also leverage the power of centric information network to efficiently distribute cached content in the proxy and optimize network bandwidth. Additionally, blockchain technology a game-changing innovation that permits decentralization in data sharing is the foundation of our system architecture. It offers fine-grained access control over data while reducing bottlenecks in centralized systems. Our method to assuring data confidentiality, integrity, and security appears promising based on the security study and evaluation of our system. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Unlocking the Mysteries of the Deep: Leveraging the Power of MobileNet and YOLOv5 for Efficient and Accurate Sea Cucumber Detection in Underwater Environments

Unlocking the Mysteries of the Deep: Leveraging the Power of...

引用

2024 International Conference on Recent Innovation in Smart and Sustainable technology, ICRISST 2024

作者： Vignesh, S. Dhamodaran, S. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350309140

In the realm of marine biology and underwater research, the discovery and understanding of marine species play a pivotal role in unraveling the mysteries of the deep ocean. This research endeavors to advance the field by harnessing the capabilities of deep learning through the fusion of MobileNet and YOLOv5, two cutting-edge neural network architectures. This study focuses on sea cucumber detection, a task vital for ecosystem assessment, biodiversity studies, and habitat analysis. MobileNet, known for its efficiency and compactness, is employed for feature extraction, while YOLOv5, recognized for its real-time object detection prowess, is adapted for classification. By synergizing these models, authors achieve a highly efficient and accurate sea cucumber detection system tailored to the challenges of underwater environments. This research introduces a meticulously curated dataset comprising sea cucumber images sourced from various underwater ecosystems, offering a comprehensive representation of these enigmatic creatures. Authors present a detailed methodology for data preprocessing, including Gray-Level Co-occurrence Matrix (GLCM) analysis for texture features, and image augmentation techniques to enhance model robustness using Google Images. Subsequently, the fusion of MobileNet and YOLOv5 capitalizes on MobileNet's ability to extract discriminative features efficiently and YOLOv5's real-time detection capabilities. The experimental results showcase remarkable accuracy and efficiency in sea cucumber detection, exceeding the performance of traditional methods and single-model approaches with accuracy of 97.39%. The proposed system not only accurately classifies sea cucumber species but also provides valuable insights into their ecological roles and habitats. © 2024 IEEE.

关键词： Biotic

来源：评论

学校读者我要写书评

暂无评论

Personalized Travel Itinerary Generator System

Personalized Travel Itinerary Generator System

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Nithyasri Prabha, S. Nivash, V. Yogitha, R. Kalaiarasi, G. Selvi, M. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350375237

The Travel Itinerary Generator is designed to make vacation planning more efficient by considering individual preferences. By using details like destination, budget, and interests provided by users, the system creates personalized travel plans. Users can specify preferences for hotel amenities and food, and the system then recommends five hotels, two daily attractions, and dining options. Utilizing a data science pipeline that includes web scraping, data analysis, user profiling, and three recommendation algorithms (Restricted Boltzmann Machine, Alternating Least Squares, and a hybrid model), this innovative system streamlines itinerary creation while also providing valuable insights into the integration of data-driven methodologies. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Skin Lesion Classification using Pre-Trained Neural Networks

Deep Learning for Skin Lesion Classification using Pre-Train...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Anjali, M. Sowmya, P. Nitte Meenakshi Institute of Technology Department of Computer Science and Engineering Bangalore India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360660

The increasing prevalence of skin cancer underscores the importance of accurate and efficient diagnostic tools. Deep Convolutional Neural Networks (DCNN) have demonstrated remarkable success in computer vision tasks, particularly in skin cancer classification. However, adapting these networks to specific domains, such as dermatoscopic images, poses challenges. This project addresses the need for robust skin cancer classification by fine-tuning DCNNs pre-trained on ImageNet for the specific task of identifying 7 types of skin lesions using the HAM10000 dataset, which contains 10,000 dermatoscopic images. To comprehensively assess the efficiency of different fine-tuning strategies, a comparative analysis is conducted across multiple architectures, including the baseline model, VGG16, Inception V3, InceptionResNetV2, and DenseNet201. The initial examination involves fine-tuning the top layers of each architecture. Subsequently, a more intricate analysis is performed by fine-tuning all layers for Inception V3, InceptionResNetV2, and DenseNet201. This study aimed to improve dermatological image classification by combining cross-learning and ensemble learning. The ensemble included the best versions of Inception V3 and DenseNet 201, achieving an accuracy of 88.52% on the test set and 88.8% on the validation set. The fitting of the whole model improved the results and the speed of convergence. © 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

Walmart Sales Forecasting Using Time Series Analysis

Walmart Sales Forecasting Using Time Series Analysis

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Shrieenidhi, A.M. Ruba Roshini, S. Ranjana, P. Hindustan Institute Of Technology And Science Department Of Computer Science And Engineering Chennai India

ISBN: (纸本)9798350364828

The field of retail analytics concentrates on Walmart's challenging issue of forecasting sales by utilizing advanced time series analysis. Walmart is attempting to leverage time series models because it understands how important precise sales projections are for revenue optimization, inventory control, and customer pleasure. By the usage of EDA and Feature engineering, which is capable of capturing underlying trends, temporal patterns, seasonality (Holiday, Weekly Sales, CPI), the impact of external factors (Prominent Holidays) and aiming to improve sales, optimize budgeting and resource allocation, inventory management, business planning is achieved. The principal aim is to provide Walmart a future forecasted sales using traditional time series model such ARIMA & SARIMA. Statistical metrics such as MAE, MSE, RMSE, WMAE have been adopted to evaluate the quality of the model. By refining sales forecasting through advanced time series models and meticulous evaluation, Walmart anticipates not only enhanced operational efficiency but also an elevated customer experience, reinforcing its position as a retail industry leader. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Evaluating Human Emotions Using Image Processing and Brain Waves 3

Evaluating Human Emotions Using Image Processing and Brain W...

引用

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Abirami, R. Privadharshini, S. Aroul Canessane, R. Jany Shabu, S.L. Refonaa, J. Gayathri, S. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350396157

Human sentiments are analyzed based on two prominent technologies, electroencephalography and image processing. Electroencephalography helps in detecting the brains activity by attaching the electrodes to the scalp. The neurons are charged with ions and constantly emit them. When charged ions repel and propagate this repulsion, a brain wave is produced at a unique frequency depending on the state of mind. Image processing helps in determining the characteristics of facial expression using mathematical operations and functions. This includes capturing image or more appropriately 20 signals. The output of image processing yields the characteristics of the image. The combined output of both Electroencephalography device and image processing are mapped together to genuinely analyze the human emotions. © 2024 IEEE.

关键词： Electroencephalography

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：