检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Nagarajan, S. Ramprasath, M. Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Chengalpattu India

ISBN: (纸本)9798350305708

Medical imaging is capturing pictures of bodily components for diagnostic or research reasons. Because of advancements in image-handling techniques, which include picture recognition, examination, and upgrading, clinical imaging is expanding swiftly. Picture division is a vital subject in picture handling and PC vision with applications, for example, scene grasping, clinical picture examination, mechanical discernment, video observation, expanded reality, and picture pressure, among numerous others. Numerous picture segmentation methods have been created and are available in the literature. There has been a lot of work done to develop techniques for segmenting pictures using deep-learning models since they have proved effective in various vision applications. Deep learning has turned into a functioning exploration point in the field of clinical picture examination. Compared to the laborious and lengthy conventional technique, deep learning (DL) automatic detection algorithms can speed up diagnostics, increase test accuracy, lower expenses, and lessen the workload on the radiologist. Kidney segmentation is an integral part of any non-intrusive computer-assisted diagnostic (CAD) system for rapidly recognising severe renal repudiation because of the intensity of inhomogeneity brought on by errors in the image capture process, efficient kidney segmentation is challenging in evaluating and therapeutic planning of kidney-related disorders. This article addresses recent developments in DL-based kidney tumor segmentation systems. We highlight their fundamental components and numerous approaches as we discuss the main medical image kinds, segmentation methods, and evaluation standards for segmentation outcomes in kidney tumor++ segmentation. © 2023 IEEE.

关键词： Automatic Detection algorithms Computer-Assisted diagnostic system Deep Learning Kidney tumor segmentation Vision applications

来源：评论

学校读者我要写书评

暂无评论

Inductive Lottery Ticket Learning for Graph Neural Networks

引用

Journal of Computer science & Technology 2024年第6期39卷 1223-1237页

作者： Yong-Duo Sui Xiang Wang Tianlong Chen Meng Wang Xiang-Nan He Tat-Seng Chua School of Data Science University of Science and Technology of ChinaHefei 230027China Department of Electrical and Computer Engineering The University of Texas at AustinAustin 78712U.S.A School of Computer Science and Information Engineering Hefei University of TechnologyHefei 230009China School of Computing National University of SingaporeSingapore

Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplored. The recent work Unified GNN Sparsification (UGS) studies lottery ticket learning for GNNs, aiming to find a subset of model parameters and graph structures that can best maintain the GNN performance. However, it is tailed for the transductive setting, failing to generalize to unseen graphs, which are common in inductive tasks like graph classification. In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity. To prune the input graphs, we design a predictive model to generate importance scores for each edge based on the input. To prune the model parameters, it views the weight’s magnitude as their importance scores. Then we design an iterative co-pruning strategy to trim the graph edges and GNN weights based on their importance scores. Although it might be strikingly simple, ICPG surpasses the existing pruning method and can be universally applicable in both inductive and transductive learning settings. On 10 graph-classification and two node-classification benchmarks, ICPG achieves the same performance level with 14.26%–43.12% sparsity for graphs and 48.80%–91.41% sparsity for the GNN model.

关键词： lottery ticket hypothesis graph neural networks neural network pruning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Chatbot for Hospital Recommendation System 2

Intelligent Chatbot for Hospital Recommendation System

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Rajkumar, K. Ragupathi, T. Karthikeyan, S. School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Kattankulathur India Department of Computer Science and Engineering Bangalore562112 India

ISBN: (纸本)9798350371055

The main objective of this project is to create a user-friendly intelligent chatbot for Medical guidance and support. This application has been classified into two different modes based on user preference, those are Online and Offline modes of interaction. In the Online mode of interaction, there is no need for any automation, there will be a real person at the other end answering user queries. Users can even ask for untrained data and will receive instant replies. This application is similar to a normal chat application, but the main disadvantage is that a real person is needed at the other end at all times. In the Offline mode of conversation which is entirely automated the user will be performing an interaction with the chatbot itself. The chatbot must consist of data sets and trained data collection, in this process there is no need for any real person, the chatbot itself will reply instantly based on the trained data. The chatbot will be more accurate when a large number of data is trained. This application is compatible with working in various browsers and varied networks. The Admin of the application plays a significant role. Admin can access all the given functions and is responsible for data training. data training plays a vital role in this application, the trained data will be used by the chatbot while answering user queries i.e. Offline mode. This chatbot application can be accessed by several users at the same time, where IP address plays the main role. The main function of this application is that user can post their corresponding queries and the application will be providing relevant information based on queries. The Latest Modern chatbots are used in applications where simple interaction is needed, for example, service and marketing technology to provide answers such as products, services, and consultancy. If the customer's queries don't match with the trained data sets, the customer will be escalated to manual interaction i.e. Online mode. © 2024 IE

关键词： Automated Intelligent Chat IP Address Offline mode Online mode Trained data

来源：评论

学校读者我要写书评

暂无评论

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Song, Jianqing Huang, Jianguo Jiang, Wenyu Zhang, Baoming Li, Shuangjie Wang, Chongjun State Key Laboratory of Novel Software Technology Nanjing University China Department of Statistics and Data Science Southern University of Science and Technology China College of Computing and Data Science Nanyang Technological University Singapore

Graph Neural Networks have achieved remarkable accuracy in semi-supervised node classification tasks. However, these results lack reliable uncertainty estimates. Conformal prediction methods provide a theoretical guarantee for node classification tasks, ensuring that the conformal prediction set contains the ground-truth label with a desired probability (e.g., 95%). In this paper, we empirically show that for each node, aggregating the non-conformity scores of nodes with the same label can improve the efficiency of conformal prediction sets while maintaining valid marginal coverage. This observation motivates us to propose a novel algorithm named Similarity-Navigated Adaptive Prediction Sets (SNAPS), which aggregates the non-conformity scores based on feature similarity and structural neighborhood. The key idea behind SNAPS is that nodes with high feature similarity or direct connections tend to have the same label. By incorporating adaptive similar nodes information, SNAPS can generate compact prediction sets and increase the singleton hit ratio (correct prediction sets of size one). Moreover, we theoretically provide a finite-sample coverage guarantee of SNAPS. Extensive experiments demonstrate the superiority of SNAPS, improving the efficiency of prediction sets and singleton hit ratio while maintaining valid coverage. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CareerBoost: A Hybrid RAG-NLP Job Recommendation Framework 8

CareerBoost: A Hybrid RAG-NLP Job Recommendation Framework

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Deshmukh, Sanskruti Bajaj, Aaryaman Vishwakarma Institute of Technology Department of Artificial Intelligence and Data Science Pune India Srm Institute of Science and Technology Department of Computing Technologies Chennai Kattankulathur India

ISBN: (纸本)9798350376425

The proposed system presents a novel approach to job recommendation and resume enhancement, leveraging advanced Natural Language Processing (NLP) techniques and Retrieval-Augmented Generation (RAG). We introduce a comprehensive system that combines semantic search, FAISS-based similarity matching, and a fine-tuned GPT-2 model to provide personalized job recommendations and actionable resume improvement suggestions. The evaluation, conducted through offline metrics and online A/B testing with 5,000 users, demonstrates significant improvements over traditional keyword-matching approaches. The RAG-based system achieved a 25.8% increase in recommendation relevance (Precision@10), a 45.7% increase in user engagement, and a 41.2% increase in job application rates. Furthermore, users who applied the system's resume enhancement suggestions saw a 9.0% improvement in subsequent job matches. These results highlight the potential of AI-driven systems to revolutionize online recruitment and career development, while also emphasizing the need for ongoing consideration of ethical implications and fairness in AI-assisted hiring processes. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

SAND: semi-automated adaptive network defense via programmable rule generation and deployment

引用

science China(Information sciences) 2022年第7期65卷 121-138页

作者： Haoyu CHEN Deqing ZOU Hai JIN Shouhuai XU Bin YUAN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabHubei Engineering Research Center on Big Data Security School of Cyber Science and EngineeringHuazhong University of Science and Technology Department of Computer Science University of Colorado at Colorado Springs

Cyber security is dynamic as defenders often need to adapt their defense postures. The state-ofthe-art is that the adaptation of network defense is done manually(i.e., tedious and error-prone). The ideal solution is to automate adaptive network defense, which is however a difficult problem. As a first step towards automation, we propose investigating how to attain semi-automated adaptive network defense(SAND). We propose an approach extending the architecture of software-defined networking, which is centered on providing defenders with the capability to program the generation and deployment of dynamic defense rules enforced by network defense tools. We present the design and implementation of SAND, as well as the evaluation of the prototype implementation. Experimental results show that SAND can achieve agile and effective dynamic adaptations of defense rules(less than 15 ms on average for each operation), while only incurring a small performance overhead.

关键词： network defense adaptive defense automated defense programmable defense security services software-defined networking security management

来源：评论

学校读者我要写书评

暂无评论

Fraud Detection in Financial Transactions: A Machine Learning Approach 9

Fraud Detection in Financial Transactions: A Machine Learnin...

引用

9th International Conference on science, Technology, Engineering and Mathematics, ICONSTEM 2024

作者： Patel, Shashank Pandey, Mudita Rajeswari, D. School of Computing College of Engineering And Technology Srm Institute of Science And Technology Department of Data Science And Business Systems Chennai Kattankulathur603203 India

ISBN: (纸本)9798350365092

Financial fraud presents substantial risks to individuals and financial institutions globally, necessitating efficient detection mechanisms to mitigate probable fatalities. In this study, the development and evaluation of machine learning (ML) models for detecting fraudulent activities in mobile money transactions are investigated. Using a synthetic dataset, realworld transaction scenarios involving a variety of transaction kinds and features are simulated. The effectiveness of many machine learning (ML) methods, such as LGBM, random forests, XGBoost, and logistic regression, in spotting fraudulent transactions is investigated through data preparation, feature engineering, and model-building procedures. Employing techniques such as SMOTE-Tomek resampling and hyperparameter tuning enhances the performance and robustness of our models. Our results reveal that the XGBoost classifier emerges as the top-performing model, exhibiting a remarkable accuracy of 99.95%. The findings underscore the potential of MLbased approaches to bolster security and trust in mobile financial services, contributing to the ongoing advancement of fraud detection methodologies in the financial sector. © 2024 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Classification using CNN and Transfer Learning (TL) 7

Skin Cancer Classification using CNN and Transfer Learning (...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Patel, Shashank Pandey, Mudita Rajeswari, D. Srm Institute of Science And Technology School of Computing College of Engineering And Technology Department of Data Science And Business Systems Chennai Kattankulathur603203 India

ISBN: (纸本)9798350359299

Skin cancer is a predominant and possibly lethal condition that distresses people across the world. Primary detection and precise finding are crucial for leveraging efficacious treatment and enhanced patient consequences. This research study explores the application off Artificial Intelligence (AI) resolutions for the primary finding and analysis of skin cancer. The study leverages a dataset of dermatological images and employs various ML methods, including Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and decision trees, to analyse the existence of skin cancer with a higher degree of accuracy. By utilizing a combination of image processing and feature extraction, the AI model demonstrates higher performance in classifying skin lesions into malignant or benign categories. The proposed model has achieved an accuracy rate of 98.52%, making the AI-based system a promising tool for dermatologists and healthcare professionals. © 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

Signs to Speech 2

Signs to Speech

引用

2nd IEEE International Conference on Networking and Communications, ICNWC 2024

作者： Vardhan, Harsh Harsavardhan, S. Lakshmi, M. SRM Institute of Science and Technology School of Computing College of Engineering and Technology Department of Data Science and Business Systems Kattankulathur Chennai603203 India

ISBN: (纸本)9798350365269

This research introduces an innovative Sign Language to Speech Conversion Model using Convolutional Neural Networks (CNNs) to address communication barriers for the people who are deaf and unable to hear properly. The model employs deep learning for the automatic extraction of spatial patterns from sign language images. A diverse sign language dataset is carefully curated, undergoing Pre-processing for improved quality. The CNN architecture, designed for adaptability, captures local and global features, enabling accurate *** the training phase, the model learns to map sign language gestures to spoken language representations. Performance evaluation methods which include accuracy, recall, precision and F1 score, demonstrate the effectiveness of the model. Results underscore the significance for the deaf community. The discussion explores broader implications in education, healthcare, and social interactions, acknowledging limitations and proposing future research *** conclusion, the Sign Language to Speech Conversion Model contributes to sign language recognition, offering an advanced solution for communication barriers and promoting inclusivity in diverse social settings. © 2024 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Effortless learning: leveraging summarization and tabulation for automated note making

引用

Multimedia Tools and Applications 2024年 1-26页

作者： Arivarasi, A. Srinivasan, R. Rajeswari, D. Govindasamy, Alagiri School of Electronics Engineering Vellore Institute of Technology Tamil Nadu Chennai600127 India Department of Computing Technologies School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603203 India Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur603203 India Future Connect Technologies Pvt. Ltd Tamil Nadu Kanchipuram600034 India

In this fast-paced Digital Age, Natural Language Processing (NLP) can prove beneficial in consuming quality information efficiently. With the ever-growing number of learning resources, it is becoming onerous for students to choose the best-suited learning resource. Furthermore, many students find it difficult to understand and retain highly factual information. To overcome these issues, this paper proposes a novel Automated TExt Summarization of scholastic text in Table format (Auto-TEST) to provide information at a glance by mimicking the student’s style of note-making. The Auto-TEST framework is achieved through two steps which is Summarization and Tabulation. Initially, the Extractive Single Document Text Summarization (ESDTS) method is adopted to identify the salient information from the non-fictional (scholastic) text which is extracted and grouped together to form a concise summary. A Named Entity Recognition (NER) method is implemented to extract noun chunks and then arrange them in a tabulation format that aids in memorizing essential facts and figures by enabling effortless retrieval. The performance of the Auto-TEST framework is gauged by using scholastic domain-specific dataset using ROUGE as an evaluation metric. The extracted entities gives an average Recall of 71.40%, an average Precision score of 75.80% and an average F-score of 73.54% for the dataset respectively. © 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

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：