检索结果-内蒙古大学图书馆

SSC-CF: Semantic similarity and clustering-based collaborative filtering for expert recommendation in community question answering websites

引用

International Journal of Information technology (Singapore) 2023年第8期15卷 4243-4257页

作者： Paramasivam, Aarthi Nirmala, S. Jaya Department of Computer Science and Engineering National Institute of Technology Tamilnadu Tiruchirappalli 620015 India

Community question answering forums allow users to find knowledge on a topic of interest by asking questions and getting answers from experts. However, it can be challenging to find experts who are knowledgeable in a particular subject, especially when there are millions of questions and thousands of new queries every *** paper proposes a novel expert recommendation system called Semantic Similarity and Clustering-based Collaborative Filtering (SSC-CF). SSC-CF addresses two key drawbacks of collaborative filtering: scalability and sparsity. Sparsity is addressed by using matrix factorization. In matrix factorization, latent features are identified to detect similarity and generate a prediction based on both the question and the user entities. Whereas a clustering method is employed to group users and questions with shared interests to address scalability. The recommendation system’s accuracy is further improved by incorporating semantic similarity. SSC-CF is evaluated on three Stack Exchange sites: gaming, physics, and scifi. The results clearly show that the proposed technique, SSC-CF, is effective in addressing both scalability and sparsity. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Community question answering Expert recommendation Natural language processing Scalability Sparsity

来源：评论

学校读者我要写书评

暂无评论

Optimizing Lyme Bacterial Disease Identification with Fine-Tuned EfficientnetB0 Model 4

Optimizing Lyme Bacterial Disease Identification with Fine-T...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Shandilya, Gunjan Anand, Vatsala Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science Punjab India

ISBN: (纸本)9798350387490

Lyme disease is a vector-borne infection spread by tick bites, and because of its many clinical presentations and similarities to other illnesses, it can be difficult to diagnose. Erythema migrans, a recognizable rash that, if left untreated, might result in more serious skin issues, is one of the early symptoms. If the infection caused by Lyme disease worsens, it can lead to cognitive, heart-related symptoms. and rheumatologic issues. This might make diagnosis more difficult and affect patient outcomes. To overcome these diagnostic issues, this research looks into the automatic identification of Lyme disease using transfer learning techniques. An automated system for Lyme disease diagnosis that is accurate and has been designed by applying transfer learning on medical and health imaging datasets. This method achieves an outstanding accuracy of 98.55% with minimal loss by using a pretrained EfficientNetB0 model that has been fine-tuned. With a 98% of recall and precision rate, the model performs extremely well. For this category classification job, the dataset on skin diseases has been used. technology development may greatly increase the accuracy and consistency of Lyme disease diagnosis, resulting in more rapid medication and improved treatment results for patients. © 2024 IEEE.

关键词： EfficientNetB0 Erythema migrans Lyme disease Pathogens Tick-borne Transfer learning (T.L) Vector-borne

来源：评论

学校读者我要写书评

暂无评论

Backpropagation Shuffled Leaping Neural Network Implementation in Classification of DDoS Packet Flow Traffic in Data Mining

引用

SN computer science 2024年第8期5卷 1-7页

作者： Umamaheswari, N. Kumutha, K. Kalaivani, M.S. Ramya, R. Tagore College of Arts and Science Tamilnadu Chennai India Department of Computer Application- PG Vels Institute of Science Technology and Advanced Studies Tamilnadu Chennai India Department of Computer science and Engineering Bannari Amman Institute of Technology Tamil Nadu Erode India

All web applications remember the ultimate goal of storage services, Distributed Denial of Service (DDoS), to achieve high security from various attacks. The client-server application reduces fees and runs the elite registration gadget, while the notable part assumes that it is manufactured using a grant application. Analysis of the traceback data is difficult in the previous system, and then it containsa common DDoS attack *** DDoS attacks involving different network layers such as (SIDDoS (SQL (Structured Query Language) injection), HTTP (HyperText Transfer Protocol) flood, TCP (Transmission Control Protocol) are recommended here as there are signs that new datasets of common datasets are not being collected in the proposed system. The DDoS attack classification consists of three main steps: preprocessing, trace out the source IP address, Backpropagation Shuffled Leaping Neural Network (BSLNN) based on maintaining the specifications’ integrity. The preprocessing is the first step based on the Gabor Filter used to remove the data’s noise and the second Adaboost Random Optimal Selection method to analyzethe packet flow’s relative frequency. The third step is the Backpropagation Shuffled Leaping Neural Network (BSLNN) classification of traceback data maintaining the specifications analysis’s integrity. The proposed system achieves good periodic study of packet flow accuracy and time complexity. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Adaboost random optimal selection Backpropagation Shuffled Leaping Neural Network (BSLNN) Gabor filter Preprocessing Trace out the source IP address

来源：评论

学校读者我要写书评

暂无评论

Envisioning Educational Success Through Advanced Analytics and Intelligent Performance Prediction 10

Envisioning Educational Success Through Advanced Analytics a...

引用

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

作者： Sureshkumar, T. Charanya, J. Kumaresan, T. Rajeshkumar, G. Kavin Kumar, P. Anuj, B. Nehru Institute of Technology Department of Information Technology Coimbatore641 105 India Department of Computer Science and Engineering Erode638 401 India Bannari Amman Institute of Technology Department of Computer Science and Engineering Sathyamangalam638 401 India Bannari Amman Institute of Technology Dept of Cse Sathyamangalam India Bannari Amman Institute of Technology Department of Computer Technology Sathyamangalam India

ISBN: (纸本)9798350353068

The accurate prediction of students academic success holds significance in enhancing educational outcomes. The study focuses on overcoming the challenge of assessing whether a student will successfully pass the final exam, taking into account a range of socio-economic and academic factors. Every student's journey is different, and it is influenced by various factors such as their socioeconomic background, academic abilities, and personal experiences. To evaluate their performance, we use various machine learning algorithms such as KNN, Naive Bayes, SVM, AdaBoost, and Naive Bayes - and assess their performance using key metrics such as ROC curve, confusion matrix, precision, recall, and F1 score. The F1 score offers a balanced assessment of precision and recall, offering insights into overall model accuracy. Precision and recall focus specifically on the model's ability to correctly identify positive instances and capture all actual positive instances, respectively. ROC curves demonstrate the balance between the rates of correctly identifying true positives and incorrectly identifying false positives, allowing for a nuanced assessment of classifier performance. The confusion matrix further breaks down true positives, true negatives, false positives, and false negatives, enhancing our understanding of algorithmic effectiveness. Through a comprehensive comparison of these classification methods, our goal is to identify the most accurate approach for predicting student outcomes, thus contributing valuable insights to educational institutions and policymakers aiming to implement effective strategies for student success and academic improvement. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Enhancing Vehicular Communication systems: Predicting Signal-to-Noise Ratio Using Machine Learning Models

Enhancing Vehicular Communication Systems: Predicting Signal...

引用

2024 IEEE International Conference on Electronic systems and Intelligent Computing, ICESIC 2024

作者： Begum, Almas Rajendra Thilahar, C. Monikaa, R. Gopinath, M. Ruth Naveena, N. Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Saveetha Engineering College Department of Computer Science and Engineering Chennai India Easwari Engineering College Department of Computer Science and Engineering Chennai India Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Information Technology Chennai India Hindustan Institute of Technology and Science Department of Mathematics Chennai India

ISBN: (纸本)9798331522988

Vehicle communication systems facilitate both vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) connections, playing a crucial role in Intelligent Transportation systems. Accurate estimation of signal-to-noise ratio (SNR) is necessary for modern communication systems to be reliable and efficacious. This study aims to identify which machine learning model achieves the highest accuracy in predicting SNR. The analysis focuses on three different models: Random Forest, Gradient Boosting, and Linear Regression. The models were built using a comprehensive dataset containing wireless measurements from the iV2V industrial testbeds. The iV2I+ dataset records data from an industrial site where it acquires around 16∼h of the autonomous cleaning robot connected to a private cellular network, meanwhile, the iV2V has accumulated about 10 hours in side-link situations between three Automated Guided Vehicles (AGVs). It is an appropriate dataset for machine learning purposes because it provides information on positional data, wireless Quality of Service (QoS) measurements, and physical layer characteristics in detail. The models were analyzed based on performance measures including R2 Score, Root Mean Squared Error (RMSE), and Mean Squared Error (MSE). The Random Forest model outperformed all other models we tested with an MSE of 0.0058, which translates to an RMSE of 0.0762 and an R2 score over the roof.9997 Yes, they performed well also but Random Forest outperformed Gradient Boosting and Linear Regression in all the metrics. Random Forest was the good model that this study could get which is constructed by other models as well, depicting its goodness for designing machine learning algorithms to forecast SNR over a vehicular communication system. Results provide means to develop methods for enhanced communication efficiency and reliability that can be helpful while building safer, more effective transportation systems where ITS plays a significant role. © 2024 IEEE.

关键词： Vehicle to infrastructure

来源：评论

学校读者我要写书评

暂无评论

Latest Innovations in Intelligent Network-on-Chip Architectures: A Systematic Review 17

Latest Innovations in Intelligent Network-on-Chip Architectu...

引用

17th IEEE/ACM International Workshop on Network on Chip Architectures, NoCArc 2024

作者： Kakoulli, Elena Neapolis University Pafos Intelligent Systems Laboratory Department of Computer Science Pafos Cyprus Cyprus University of Technology Electrical Engineering and Computer Engineering and Informatics Limassol Cyprus

ISBN: (纸本)9798331506421

This review investigates the latest advancements in intelligent Network-on-Chip (NoC) architectures, focusing on innovations from 2022 to 2024. The integration of Artificial Intelligence (AI) and Machine Learning (ML) into NoC designs has driven significant improvements in performance, scalability, energy efficiency, and security. Key contributions include AI/ML-driven techniques to optimize routing, reduce latency, manage power consumption, and enhancing security against emerging threats. Despite these advancements, challenges such as computational overhead and integration complexities remain. This review consolidates these findings, addresses existing challenges, and proposes future research directions to further leverage AI and ML for developing robust and adaptable NoC architectures. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Techniques for Monuments Identification

Artificial Intelligence Techniques for Monuments Identificat...

引用

2024 International Conference on Innovations and Challenges in Emerging Technologies, ICICET 2024

作者： Surya, U. Subashree, E. Shobana, G. St. Joseph's Institute of Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350319019

Effective management is essential to the conservation of historic sites, especially when it comes to the selection of monuments. Using the advanced You Only Look Once (YOLOv8) paradigm, this research study ushers in the era of Artificial Intelligence (AI) by achieving pinpoint identification. The goal is to create an AI-powered device that continuously monitors and provides real-time data on accuracy. Focusing its coverage primarily on Tamil Nadu monuments and a variety of diverse historical settlements located around the Indian subcontinent, the compiled dataset is evidence of this, producing an impressive mean Average Precision (mAP) score of 91.5%. The exposition foreshadows significant advancements in monument detection by providing comprehensive insights as well as introducing a voice component. continuation and historical research. The successful application of AI to monument recognition has significant implications for tourism, urban planning, and cultural preservation. It provides a useful tool for the precise and quick designation and preservation of various monuments. In summary, the goal of the project is to push the boundaries of antiquarian research and cultural preservation. © 2024 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Vehicle Target Detection with an Integrated Attention Mechanism 3

Vehicle Target Detection with an Integrated Attention Mechan...

引用

3rd International Conference on Cloud Computing, Big Data Application and Software engineering, CBASE 2024

作者： Wang, Yuzhuo Wang, Haihui Hu, Po Hu, Yuanzhong School of Computer Science and Engineering School of Artificial Intelligence Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798331506582

To address the problems of traditional vehicle detection models regarding equipment requirements, detection accuracy, and overlapping target leakage rate, this study proposes an improved vehicle target detection algorithm for YOLOv8. Firstly, we introduce EMA, an attention mechanism for cross-space learning, to improve the attention to feature information. Secondly, it combines EMA with the C2f module in the Neck network to fuse more important feature information, obtaining more accurate vehicle feature information. Finally, it uses the MPDloU loss function to speed up the model's convergence and improve detection accuracy. Experiments conducted on Pascal VOC and MS COCO datasets show that the performance of the improved algorithm proposed in this paper exceeds that of the original model. The enhanced model's mAP reaches 85.71%, 3.27% higher than the original model, improving vehicle target detection accuracy and being highly practical. © 2024 IEEE.

关键词： attention mechanism MPDIoU vehicle detection YOLOv8

来源：评论

学校读者我要写书评

暂无评论

A General Comparative Study of Various Video Compression Standards Based on Their Features, Working Mechanism and Usage Applications 2nd

A General Comparative Study of Various Video Compression Sta...

引用

2nd International Conference on Advances in Computational Intelligence and Informatics, ICACII 2023

作者： Kavitha, K.K. Venkatapur, Rekha B. Department of Computer Science and Engineering K S Institute of Technology Karnataka Bengaluru560109 India

ISBN: (纸本)9789819747269

Digital video stand as one of the most prominent means of communication currently. It is due to their engaging capacity to convey a substantial amount of information in a compact format. Every year, there are continuous advancements in video capture, rendering, and display technologies, resulting in an exponential increase in the volume of videos being produced every day. Simultaneously, numerous video content providers encounter the challenge of meeting user expectations for higher-quality videos while maintaining costs at the same level or reducing them. High-quality videos tend to be quite large in terms of file size, resulting in extended upload times, impractical hosting expenses and a requirement for high-speed bandwidth from users and viewers. Consequently, digital videos must undergo processing before transmission, as they often contain significant redundancies. This preprocessing aims to optimize storage usage and fulfil bandwidth requirements more efficiently. Video compression is a method for reducing redundancies in visual data by identifying and representing these redundancies using far fewer binary digits or bits. It involves the elimination of various types of redundancies found in video frames by reducing the total number of bits required to represent each frame. Currently, there are numerous video compression standard techniques and codec that feature structured and logical mechanisms. This review work offers a comparative analysis of such established video compression standards and techniques based on various aspects. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Multimodal multi-label text classification based on bidirectional Transformer 5

Multimodal multi-label text classification based on bidirect...

引用

5th International Conference on Robotics and computer Vision, ICRCV 2023

作者： Wang, Leiluo Chen, Xiangyang Ye, Zi Jiang, Shukai School of Computer Science and Engineering Wuhan Institute of Technology Wuhan China School of Computer Science and Engineering Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan Institute of Technology Wuhan China

ISBN: (纸本)9798350326369

Research on multi-label classification has developed from traditional single-modal analysis to complex classification using multiple modalities. However, single-modal input models are insufficient for effectively analyzing the increasingly rich multi-modal data on the Internet. Therefore, a ResNeXt-Bert method is proposed: introducing models for image and text information input to overcome the limitations of single-modal input data. The ResNeXt is used to extract features of images, and contextual embedding is input using early fusion method, and then fed into a pre-trained multi-layer bidirectional Transformer encoder model for classification. On the MM-IMDB dataset for studying multi-label classification problems, the micro F1 value reached 64.7%, which is better than other models. The experimental results show that introducing image and text information can indeed improve the multi-label text classification ability of the model. © 2023 IEEE.

关键词： Classification (of information)

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：