检索结果-内蒙古大学图书馆

10th IEEE International Conference on Data science and Advanced Analytics, DSAA 2023

作者： Saxena, Shruti Chandra, Joydeep Indian Institute of Technology Patna Deaprtment of Computer Science and Engineering Patna India

ISBN: (纸本)9798350345032

Network alignment, the task of identifying the same entities across multiple networks, has recently gained immense popularity in industry and academia. However, most existing alignment methods consider networks static, merely a snapshot of the time-evolving real networks where the nodes, links, and attributes are bound to change over time. The existing methods cannot capture these intrinsic dynamic network changes and cannot be applied directly to the evolving real-network scenario. Even extending these static methods to update their model parameters by retraining dynamically suffers from high computational complexity or simple sequential training suffers from compromised predictions due to distribution drifts in the networks. Moreover, dealing with a pair of evolving networks poses extra challenges of their domain differences and different evolution rates and patterns. Hence to overcome these challenges, we propose EvoAlign, an end-to-end information replay-based continual learning framework built upon Graph Neural Networks (GNNs) for the alignment of evolving networks. EvoAlign employs the concept of uncertainty in model predictions to identify and address two key aspects: detecting new patterns and preserving historical patterns. It also uses a novel shift-induced regularizer to handle distribution drift and domain differences in evolving networks. We empirically show that our method outperforms the existing state-of-the-art alignment methods on three real datasets. © 2023 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Recent Advancements in Structural Health Monitoring using Optical Sensor

Recent Advancements in Structural Health Monitoring using Op...

引用

2023 IEEE International Conference on Device Intelligence, Computing and Communication Technologies, DICCT 2023

作者： Agarwal, Sajal Srivastava, Gargi Rajiv Gandhi Institute of Petroleum Technology Deaprtment of Electronics Engineering Jais India Rajiv Gandhi Institute of Petroleum Technology Deaprtment of Computer Science and Engineering Jais India

ISBN: (纸本)9781665474924

Civil structure monitoring is a mandatory field of research now a days due to the adverse effects of environmental change on the civil structures for various industries. Optical sensing is a well-established field in structural monitoring, however recent advancements in fiber sensing technique are marvelous and open new possibilities of better monitoring. In this study these advancements are reviewed based on the materials used in optical sensors. © 2023 IEEE.

关键词： Optical sensors

来源：评论

学校读者我要写书评

暂无评论

Predicting Fetal Weight and Pregnancy Advisory Using Deep Learning Algorithm 3

Predicting Fetal Weight and Pregnancy Advisory Using Deep Le...

引用

3rd Odisha International Conference on Electrical Power Engineering, Communication and Computing technology, ODICON 2024

作者： Rajesh Sharma, R. Abebe, Mesfin Zenebe, Mendistu Teshale, Haymanot Sungheetha, Akey Gandasala, G.S. Pradeep Alliance University Department of Computer Science and Engineering Bangalore India Adama Science and Technology University Adama Ethiopia Wachamo University Department of Computer Science Hossana Ethiopia Alliance University Deaprtment of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350354379

For the benefit of the unborn kid and the mother, controlling pregnancy and making correct fetal weight predictions are essential. To address this, this study, proposes a deep learning model that effectively combines multimodal data, such as text-based medical records and ultrasound images to predict fetal weight and provide personalized pregnancy advisory services. The model is trained on a sizable dataset that includes information from the mother's clinical evaluation and images from fetal ultrasounds that were gathered from Nigst Elleni Hospital in Hossana and the Ethiopian Demographic and Health Survey 2016, respectively. We ran tests on a real-world dataset of expectant mothers and compared several models to assess the effectiveness of our suggested framework. In this study, we used multiclass target classes. The results revealed that combining CNN, LSTM, MLP, Autoencoder, or DBN models significantly improved accuracy in classifying and predicting fetal weight. With scores of 92.3%, 93.4%, 92.2%, and 92.8%, respectively, the CNN and LSTM fusion model coupled yielded the best results in terms of accuracy, precision, recall, and F1 score. Additionally, this model demonstrated the lowest MAE, MSE, RMSE, and the highest R2, measuring 0.45, 0.34, 0.58, and 0.5, respectively. © 2024 IEEE.

关键词： Ultrasonic imaging

来源：评论

学校读者我要写书评

暂无评论

Multimodal Misinformation Mitigation using Convolutional and Knowledge Transfer Learning Approach 3

Multimodal Misinformation Mitigation using Convolutional and...

引用

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

作者： Rathod, Nachiket Ramteke, Prabhakar H.V.P.M 'S College of Engineering and Technology Deaprtment of Computer Science and Engineering Amravati Mahrashtra Amravati India

ISBN: (纸本)9798350396157

In the era of information proliferation and digital media, the battle against the spread of misinformation has evolved into a critical challenge. This work presents an inclusive exploration of the pinnacle in misinformation mitigation, employing a multimodal method that integrates textual and visual data. Advanced techniques in knowledge transfer learning are used to develop and evaluate models for Misinformation detection based on textual content, images, and their fusion. DistilFND, a distillation of diverse models specialized in different modalities, is a focal point of proposed research. The paper involves a systematic analysis of training and testing these models on a shared dataset, enabling a comparison of their performance and the provision of insightful evaluations. Cohen's Kappa scores and ROC-AUC scores are also computed to gauge the models' efficacy. This extensive study marks a significant advance in misinformation mitigation, with knowledge transfer learning and multimodal fusion serving as pivotal elements of progress. By means of a sequence of detailed experiments and evaluation metrics, this work enhances to an improved understanding of how knowledge transfer learning, multimodal fusion, and pinnacle models can boost the correctness of Misinformation detection. The results and insights in this work aid the ongoing efforts to combat the detrimental impacts of misinformation in the digital sphere. © 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

Robot Navigation Using Reinforcement Learning with Multi Attention Fusion in Crowd 1st

Robot Navigation Using Reinforcement Learning with Multi At...

引用

1st International Conference on Cognitive Computation and Systems, ICCCS 2022

作者： Li, Linxiang Chen, Yang Sun, Fuchun Guo, Run School of Electrical Engineering Yanshan University Qinhuangdao China Deaprtment of Computer Science and Technology Tsinghua University Beijing China

ISBN: (纸本)9789819927883

Due to the complex human movement and social behavior norm, robot reaching target point with collision-free in crowd safely and quickly is a challenging problem, which can be considered as human-robot interaction. In this paper, focusing on human-friendly navigation in crowd, we propose to (i) design a reinforcement learning based fusion model of Transformer network and attention module for mobile robot to achieve collision-free navigation task, (ii) adopt probability grid map as environment expression to rich robot perception information, and (iii) use an attention-based Transformer encoder to learn the human-robot interaction. A motion planning framework based on multi attention fusion mechanism is designed to learn the information of human-robot interaction and human-human interaction. Neighboring humans are assigned different importance to improve robot navigation performance. Finally, simulation experiments are conducted to demonstrate the effectiveness of the proposed method which can accurately predict human movement and make mobile robot navigate socially with collision-free. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Medical ChatBot Assistance for Primary Clinical Guidance using Machine Learning Techniques 5

Medical ChatBot Assistance for Primary Clinical Guidance usi...

引用

5th International Conference on Innovative Data Communication Technologies and Application, ICIDCA 2024

作者： Sreedhar Kumar, S. Ahmed, Syed Thouheed Fathima, Afifa Salsabil Nishabai, M. Sophia, S. KGF Karnataka 563120 India Deaprtment of Electrical Engineering Indian Institute of Technology Telangana Hyderabad India School of Computer Science and Engineering REVA University Bengaluru India

Hospitals serve as critical hubs for global healthcare, offering essential medical services. However, a pressing issue is the lack of 24/7 medical facilities in rural areas, particularly during the overnight hours. To bridge this gap, we propose the Robotic Medical Support ChatBot (RMSCB) system. This innovative online platform leverages machine learning to autonomously predict medical diagnoses and provide temporary solutions, accessible at any time. The RMSCB system comprises three key stages: pre-processing, training, and classification. In the pre-processing stage, relevant keywords are extracted using the Pre-Fixed Stopping Words Model (PFSWM). The training stage categorizes pre-processed questions into classes based on the Pre-Fixed Class Label Model (PFCLM), associating medical solutions via the Pre-Fixed Answer and Question Model (PFAQM). In the classification stage, the RMSCB processes clinical questions from patients via mobile or personal systems, mapping and identifying solutions based on probability. Experimental results demonstrate the efficacy of the RMSCB system, offering timely first aid medication information and alleviating the need for immediate physician consultation. This technological solution addresses critical healthcare gaps, especially in regions with limited access to continuous medical services. © 2024 The Authors. Published by Elsevier B.V.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Integrating Blockchain technology for Enhanced Security and Trust in Remote IoT Healthcare Systems 3

Integrating Blockchain Technology for Enhanced Security and ...

引用

3rd Odisha International Conference on Electrical Power Engineering, Communication and Computing technology, ODICON 2024

作者： Ellappan, V. Rajesh Sharma, R. Sungheetha, Akey Karthick, K. Karthick, S. Pradeep Ghantasala, G.S. Mahendra Institute of Technology Department of Ece Namakkal India Alliance University Department of Ece Bangalore India Alliance University Department of Computer Science and Engineering Bangalore India Gmr Institute of Technology Department of EEE Rajam India Alliance University Deaprtment of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350354379

The proposed method goals to deal with the important issues of facts privacy, personal records security, and reliability of clinical facts in allotted health care systems Blockchain generation allows decentralized structures states hand and without problems set up, disposing of risks associated with unique vulnerabilities and increasing stakeholder self-assurance. Internet of Things (IoT) devices, accepted companies, and healthcare providers all serve as nodes in a personal, permissioned blockchain network. This community guarantees the safety and integrity of data received with the aid of IoT sensors, rejecting undesirable changes. Smart contracts enable the automated execution and enforcement of facts sharing agreements, get admission to regulations, and privacy policies.... New cryptographic solutions cope with the security and reliability challenges of the Internet of Things (IoT) and healthcare structures. Algorithms allow confidentiality evaluation and collaborative selection-making. This protects patient privacy and presents smooth records float and treatment. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Defective Motes Uncovering and Retrieval for Optimized Network 6

Defective Motes Uncovering and Retrieval for Optimized Netwo...

引用

6th International Conference on Computing Methodologies and Communication, ICCMC 2022

作者： Rekha, V.S. Siddaraju Dr Ambedkar Institute of Technology Bangalore India Dr Ambedkar Institute of Technology Deaprtment of Computer Science and Engineering Bangalore India

ISBN: (纸本)9781665410281

Two ways exist in the FDN formation. Either all Functional Devices (FDs) can be within a given area or can be spread into multiple areas. There are limitations on FDs with respect to battery level and range of communication. If the FDs are spread across multiple areas then each area should have a FD which can take ownership of communication with respect to other FDs. Like this process is done across all the areas. In legacy system the selection of FDs was done either randomly in each cycle of data transfer or selection of FD is done based on remaining energy for FDs. The method which needs to have good Goodness ratio will have multiple criteria s in place like residual energy, distance with respect to base station. Also the overall performance of the FDN can be improved by identifying the bad FDs whose remaining energy is low and then replacing few of them so that balancing act is there with respect to FDN optimization and cost of maintained. In this paper FDR (faulty FD detection and recovery) method is proposed which triggers at regular intervals in the FDN and then identifies faulty nodes to be recovered. It is then compared with existing LEACH and Modified LEACH method for several parameters. © 2022 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Design of Hyperparameter Tuned Deep Learning based Automated Fake News Detection in Social Networking Data 6

Design of Hyperparameter Tuned Deep Learning based Automated...

引用

6th International Conference on Computing Methodologies and Communication, ICCMC 2022

作者： Kanagavalli, N. Priya, S. Baghavathi Jeyakumar, D. Rajalakshmi Instittue of Technology Department of Computer Science and Engineering Tamilnadu Chennai India Rajalakshmi Engineering College Deaprtment of Computer Science and Engineering Tamilnadu Chennai India

ISBN: (纸本)9781665410281

Recently, social networks have become more popular owing to the capability of connecting people globally and sharing videos, images and various types of data. A major security issue in social media is the existence of fake accounts. It is a phenomenon that has fake accounts that can be frequently utilized by mischievous users and entities, which falsify, distribute, and duplicate fake news and publicity. As the fake news resulted in serious consequences, numerous research works have focused on the design of automated fake accounts and fake news detection models. In this aspect, this study designs a hyperparameter tuned deep learning based automated fake news detection (HDL-FND) technique. The presented HDL-FND technique accomplishes the effective detection and classification of fake news. Besides, the HDLFND process encompasses a three stage process namely preprocessing, feature extraction, and Bi-Directional Long Short Term Memory (BiLSTM) based classification. The correct way of demonstrating the promising performance of the HDL-FND technique, a sequence of replications were performed on the available Kaggle dataset. The investigational outcomes produce improved performance of the HDL-FND technique in excess of the recent approaches in terms of diverse measures. © 2022 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Speed Limit Constraint-based Green Vehicle Routing Problem (SL-GVRP) - A New Variant of VRP

引用

Procedia computer science 2025年 258卷 1608-1618页

作者： P. Victer Paul Anju Jose R Raju Department of Computer Science and Engineering Indian Institute of Information Technology Kottayam Kerala India Deaprtment of Information Technology Sri Manakula Vinayagar Engineering College Ponducherry India

The Vehicle Routing Problem (VRP) represents a renowned and complex challenge that has been extensively studied in the disciplines of computer science and operations research due to its broad applicability in real-world scenarios. Numerous variants of the VRP have been developed to address specific constraints, reflecting its practical significance. This paper introduces a novel variant called the Speed Limit Constraint-based Green Vehicle Routing Problem (SL-GVRP). The primary objective is to determine the optimal route that minimizes travel time by accounting for both distance and maximum speed limits between city pairs. To tackle this problem, an efficient genetic algorithm-based solution is proposed, incorporating three population seeding techniques: nearest neighbour, and the recent ODV-based EV and VV methods. The study evaluates multiple perspectives, including distance-based, time-based, and speed-based approaches. Experimental tests are conducted using instances from the TSPLIB benchmark dataset, with the analysis focusing on the act of different genetic algorithm implementations for solving the SL-GVRP. Performance is evaluated using criteria like computation time, error rate, and mean error rate.

关键词： green vehicle routing problem speed limit constraint ODV tsplib genetic algorithm

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：