检索结果-内蒙古大学图书馆

Personalized Video Prefetching Mechanism Based on User Viewing History in Edge Computing Environment

Transactions of the Korean Institute of Electrical Engineers 2023年第5期72卷 620-627页

作者： Moon, YangChan Lim, Mingyu Dept. of Smart ICT Convergence Konkuk University Korea Republic of Dept. of Computer Science and Engineering Konkuk University Korea Republic of

The personalized video service collects and analyzes user information to provide differentiated services for each user. Additionally, it is impossible to avoid delays when sending a video from a server to a client. However, if prefetching is performed at the edge node, transmission delay can be reduced, and personalized service can be provided by utilizing user information at each edge node. In this paper, we propose a personalized video service based on edge nodes. The proposed method operates so that the edge node performs personalized prefetching in which the number of prefetching is adjusted by calculating the weights of five selection criteria based on the user's viewing record. We found that the proposed method has the highest prefetching accuracy through implementation and experiments using the simulation of user behavior of selecting and viewing videos. © 2023 Korean Institute of Electrical Engineers. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

N-Queens Convergence: A Tactical Framework for Efficient Target-Directed Drone Formations and Attacks 7

N-Queens Convergence: A Tactical Framework for Efficient Tar...

引用

7th IEEE International Conference on Computational Systems and Information Technology for Sustainable Solutions, CSITSS 2023

作者： Kumar, Preethika Ajay Pes University Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350343144

This study introduces a novel methodology for enhancing the efficiency of Unmanned Aerial Vehicle (UAV) formations in order to achieve accurate target engagements. The concept draws inspiration from the N-Queens puzzle. By incorporating unmanned aerial vehicle (UAV) positioning into a simulated chessboard and expanding it to include a target in the (N + 1)th column, the algorithm produces arrangements that guarantee effective engagement with the target. Significantly, this particular technique ensures the absence of overlapping pathways among UAVs during strikes, hence augmenting operational safety. The methodology employed in this study involves the construction of formations through the generation of permutations for all possible queen positions. Subsequently, the eligible queen configurations are determined by filtering based on the diagonal lines of attack. The method has been tested on N values as high as 10. This study explores the intersection of combinatorial problem-solving with military applications, providing novel insights and tactics for deploying UAVs that minimize collisions. © 2023 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Understanding Facial Expression of Children with Autism Using Learning Theory

Understanding Facial Expression of Children with Autism Usin...

引用

2023 IEEE Asia-Pacific Conference on computer science and Data engineering, CSDE 2023

作者： Zaman, Anushka Khan, Evea Zerin Rabiul Alam, Md. Golam Chakrabarty, Amitabha Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350341072

It is challenging for autistic individuals to gather socially and empathically, as we understand, so this subject matter differs from the identification of a common human facial expression. In our research, we have taken pictures of children and teenagers from school of special children based in Bangladesh, aged between 5 to 20 with Autism Spectrum Disorder (ASD) and identified their emotions from their images. Our objective is to find a technique that will allow their emotions to be accurately perceived and thus, make it easy for them including other individuals around them to interact socially without any barriers. In our paper, we implemented VGG16 and six Machine Learning Algorithms along with one Feature Extraction technique to detect Facial Expression of children with autism. The proposed system has showcased an accuracy of 75% for VGG16, 68% for Random Forest Classifier, 61% for Random Forest Classifier along with PCA, 61% for Support Vector Machine (SVM) and 67% for SVM with PCA, 56% for Logistic Regression and 53% for Logistic Regression along with PCA, 52% for Linear Discriminant Analysis (LDA) and 54% for LDA with PCA, 46% for Decision Tree and 50% for Decision Tree along with PCA and 46% for Gaussian Naïve Bayes and 38% for Gaussian Naïve Bayes along with PCA. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Analysis of Fictional Character Backstories Using Natural Language Processing and Deep Learning 26

Analysis of Fictional Character Backstories Using Natural La...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Tanvir, Sifat Khan, Md. Rafid Jahan Oyshi, Ishmam Ishan Tonmoy, Md. Sahil Zaman Rafi, Mashrafi Brac University Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

With the overwhelming successes of industries like Marvel and DC over the years, fictional characters have become more and more popular among the general mass. However, generation of new fictional characters do not seem to be as appealing as before. This paper revolves around the idea of generating fictional character backstories using GPT-3.5. A dataset consisting of AI generated pre-existing and newly created fictional characters has been prepared. A sequential neural network model was designed by the authors and pre-trained using the popular Superheroes NLP dataset from Kaggle. The proposed model and some state-of-the-art pre-trained text classification BERT models have been compared side by side. The AI generated dataset has been used as the test data to see how the models perform in identifying the moral alignment of the characters. A comparative analysis is also done between the two datasets. © 2023 IEEE.

关键词： BERT Neural Network NLP RoBERTa Sequential Model

来源：评论

学校读者我要写书评

暂无评论

Detection and Prevention of Phishing Attacks on Banking Website 1

Detection and Prevention of Phishing Attacks on Banking Webs...

引用

1st International Conference on Futuristic Technologies, INCOFT 2022

作者： Jaswal, Prajwal Sharma, Shweta Bindra, Naveen Krishna, C. Rama NITTTR Dept.of CSE Chandigarh India Punjab Engineering College Dept.of CSE Chandigarh India PGI Dept.of Computer Center Chandigarh India

ISBN: (纸本)9781665450461

Phishing is a type of social engineering attack to trick users to reveal their personal information. Attackers deploy malicious software by creating phished websites which seems to be exactly like genuine websites. Given the dramatically increasing number of phishing attacks on banking websites, it becomes crucial to detect and prevent the users from these attacks. Unfortunately, humans are not adept at performing the security checks necessary for secure website identification, and one mistake can lead to a user's entire online account being compromised. In this paper, we propose a novel framework for detection and prevention of phishing attacks on banking website. Our proposed framework is specific towards protecting the banking website against phishing attacks. For client side, we develop a plugin to validate the legitimacy of banking Uniform Resource Locator (URL). For bank side, we develop a web portal which acts as an interface by the bank representative to add, delete, and edit URLs in the database. On server side, an administrator is responsible for managing the complete database such as maintenance of the web portal, credential generation for bank representative, etc. The results show that our proposed framework effectively detects and prevents the phishing attacks on banking website with a best case time complexity of Ω(1) and worst case time complexity of ON(if the URL is in database) and the best case time complexity of Ω(N) and worst case time complexity of O(N∗M) (if the URL is not in database and contain malicious keywords). © 2022 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Efficient Model for Multiview classification for diagnosis of Brain Tumors.

Efficient Model for Multiview classification for diagnosis o...

引用

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

作者： Anil Kumar, B. Chandrakala, B.M. Shruthi, B.V. Rv Institute of Tech & Management Dept of Computer Science & Engineering Bangalore India Dayananda Sagar College of Engineering Dept of Information Science & Engineering Bengaluru India Nitte Meenakashi Institute of Technology Dept of Computer Science & Engineering Bangalore India

ISBN: (纸本)9798350306088

Brain tumors are caused mainly by DNA abnormalities, which result in aberrant cell division, prolonged cell lifespans, and the creation of aggregative masses inside the brain. Such tumors prevent the brain from operating at its best, sometimes resulting in long-term problems. These tumors' genesis (primary or secondary) and malignancy (benign or malignant) are used to classify them. While some might not be immediately lethal, their growth or contact with healthy brain tissue might cause damage. Investigations into various approaches, such as conventional medical imaging and artificial intelligence (AI), mainly using deep learning (DL) and transfer learning (TL), is prompted by efforts to identify and categorize brain tumors. Implementing the EfficientNetB0 model, which is famous for its adaptability and efficacy, is an excellent demonstration of this strategy. This work uses a well-curated dataset of 3264 photos from various classes to closely analyze the use of the EfficientNetB0 TL model to identify and classify brain tumors from MRI scans. The model's adaptability and accuracy are meticulously examined using a dual-pronged strategy incorporating transfer learning and fine-tuning, yielding an astounding accuracy of 98.5%. Accuracy and loss charts illustrate the model's learning development in vivid detail, and a well-defined confusion matrix provides extensive insights into categorization effectiveness across various tumor classifications. The achievement of a 98.5% accuracy rate highlights the potential paradigm change made possible by AI and TL in the diagnosis and classification of brain tumors. This accomplishment confirms the efficacy of such sophisticated procedures and promises to speed up diagnosis, enable prompt therapies, and improve patient prognoses. The combination of AI and TL heralds a new era of precision medicine, ready to reshape the field of brain tumor care as research in this area grows. © 2023 IEEE.

关键词： Brain

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Clustering based Cluster Head Selection for IoT enabled WSNs 10

Fuzzy Clustering based Cluster Head Selection for IoT enable...

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Gangwar, Saumitra Prasad, Ikkurthi Bhanu Pal, Vipin Yogita Yadav, Satyendra Singh Nit Meghalaya Dept. of Computer Science and Engineering Shillong India

ISBN: (纸本)9789380544472

This work presents a fuzzy mechanism for selecting the optimum cluster head (CH) inside a cluster. During the preliminary simulations, different parameters with different weights are taken into account to make sure that the best CH is chosen, which ameliorates the wireless sensor network (WSN) lifetime. Fuzzy c-means (FCM) clustering is used in the proposed work to select a CH based on the remaining energy ratio, the distance to the sink, the node history, and the node degree. By varying the weights for the above parameters using a brute-force approach, the best-performing weights have been acquired that extend the longevity of a WSN. The simulation results confirm that by incorporating the above-mentioned parameters, network stability is improved by 140.10% and 45.09% as compared to LEACH and FCM, respectively. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Tagging Speech for Words in Low Resourced Monolingual Contexts of Sanskrit Shlokas

Tagging Speech for Words in Low Resourced Monolingual Contex...

引用

2023 Innovations in Power and Advanced Computing Technologies, i-PACT 2023

作者： Hegde, Thanmayi S. Vindhya, V. Badri Prasad, V.R. Dept. Computer Science and Engineering PES University Bengaluru India

ISBN: (纸本)9798350325188

Natural Language Processing is widely used in Machine translation which helps in replacing many tedious and difficult tasks and producing qualitative and efficient results. Sanskrit is one of the primitive languages of India. It is also the oldest, purest and most systematic language in the world. It is a magical language which helps in generating different words from a single word by prefixing and suffixing the word with different helper words to same root word. Shloka in Sanskrit are phrases or words that represent a poem or a hymn. The famous texts written entirely in shlokas are the "Ramayana" and "Mahabharata." This paper aims to generate the POS tags for each word in Sanskrit Shlokas using various machine learning and deep learning algorithms thus helping in understanding the actual verbal beauty of Sanskrit Shlokas in widely spoken language English. The proposed work implements Parts of Speech Tagging for words in Sanskrit Shlokas using Conditional Random Field, Gaussian NB and Bi-directional LSTM models. Of the implemented approaches, Bi-directional LSTM gives the best result. © 2023 IEEE.

关键词： Bidirectional Long Short-Term Memory Networks Character Embeddings Conditional Random Fields Corpus building for Sanskrit Data Preprocessing Deep learning Gaussian Navie Bayes Machine translation systems Natural Language Translation Parts of speech tagging (POS)

来源：评论

学校读者我要写书评

暂无评论

Research Collaborator Recommendation System based on citations and Influential citations 5

Research Collaborator Recommendation System based on citatio...

引用

5th International Conference on Inventive Research in Computing Applications, ICIRCA 2023

作者： Jagadishwari, V. James, Rohan Rakshith Abraham, Rohan Cmr Institute of Technology Dept of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350321425

Recommendation systems are tools that use various factors to suggest items or ideas to users. These systems often rely on networking and filtering, a technique that utilizes algorithms to analyze user reviews and provide personalized recommendations to users with similar preferences. In this work, a recommendation system to assist with the identification of research collaborators based on their areas of interest and published papers has been explored. With the use of the DBLP database, important attributes such as domain, and citation scores are considered to build a research collaboration system. Three different formulae are used to compute research scores (R_Scores) and the scholars are ranked based on these scores and recommendations are made on the basis of the ranks. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Towards Better Misogyny Detection in Bangla: Improved Dataset and Cutting-Edge Model Evaluation 6

Towards Better Misogyny Detection in Bangla: Improved Datase...

引用

6th International Conference on Sustainable Technologies for Industry 5.0, STI 2024

作者： Roy, Debopriya Deb Noumi, Israt Moyeen Rahman, Md. Aminur Ahsanullah University of Science and Technology Dept of Computer Science and Engineering Bangladesh

ISBN: (纸本)9798331531973

Misogyny is hatred, disdain, or prejudice toward women or girls. It can be verbal abuse, aggression, harassment, or discrimination. In Bengali NLP, the scarcity of well-balanced datasets for misogyny detection is a significant problem. While there has been previous work in this area for the Bangla language, the existing dataset, which only contains 2258 comments, has proven insufficient for robust detection, resulting in suboptimal performance in classification models. To tackle this, we have carefully curated a dataset from different sources, including social media and different websites. This dataset features five categories of misogynistic comments (Discredit, Stereotype & Objectification, Sexual Harassment, Threats of violence, Dominance & Derailing) and one category of Non-misogynistic comments. We evaluated the performance of multiple Machine Learning models such as SVM(Support Vector Machine), Naive Bayes, KNN, Decision Tree, and Random Forest. Bangla BERT base and Bangla BERT Electra, two Deep Learning models, were also used for classification. Additionally, we employed ensemble approaches using Bangla BERT embeddings (Bangla BERT Base and BERT-base-multilingual-cased) with models like LSTM, Bi-LSTM, and CNN+LSTM. Among them, Bi-LSTM with BERT (Bert-base-multilingual-cased) Embeddings achieves the highest accuracy, 91.24%, in classifying misogynistic comments. The new improved dataset has been made publicly available as Ben-Misog to help the Bengali Natural Language Processing community progress. © 2024 IEEE.

关键词： Support vector machines

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：