检索结果-内蒙古大学图书馆

2023 International Conference on Cognitive Computing and Complex Data, ICCD 2023

作者： Guan, Qianjun Yu, Kun Wang, Haoran Li, Qiangqiang Gao, Shihong Huaiyin Institute of Technology Faculty of Computer and Software Engineering Huai'an Jiangsu China

ISBN: (纸本)9798350306293

GhostNet is proposed by Huawei Noah's Ark Laboratory in CVPR2020, which can be used with the same accuracy, with less speed and less computation than SOTA method. This convolution is a low-cost operation used to decrease the amount of computation and related parameters. Ghost convolution can be used as an alternative to traditional convolution operations because they have the same accuracy. However, utilize significantly less computation and a much smaller parameter count. GSConv(Group-Shared Convolution) is a convolution operation based on group shared weights. This operation achieves efficient parallel convolution operations by grouping convolution kernels. In this way, the parameters used and calculation complexity of the model can be reduced to some extent. This makes the network more computationally efficient and smaller in model size while maintaining accuracy. The algorithm can detect the location of protective clothing quickly and efficiently, and its accuracy and efficiency have been verified. Because the algorithm adopts lightweight network structure, real-time detection can be realized on lowpower devices efficiently. The model architecture enhances the performance based on the YOLOv5 target detection algorithm by incorporating additional features. So that the model can maintain a high precision, which is crucial for the protective clothing detection algorithm. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

K-Means Post-Training Optimizer

K-Means Post-Training Optimizer

引用

2024 Innovations in Intelligent Systems and Applications Conference, ASYU 2024

作者： Isikoglu, Bora Kubatova, Meerim Cetin, Aydin Computer Engineering Department Gazi University Graduate School of Natural and Applied Sciences Ankara Turkey Computer Engineering Department Gazi University Faculty of Technology Ankara Turkey

ISBN: (纸本)9798350379433

We present a novel approach to optimize artificial intelligence (AI) models using unsupervised learning, specifically utilizing the k-means clustering algorithm with varying cluster parameters. The proposed method aims to enhance the performance of the initial model by iteratively evaluating it after adding new features to the original dataset. The novelty is the use of k-means model outputs as a new feature. By tracking the k-means model outputs we find the best tuning parameters to make the best testing evaluation results and feed the outputs back into the original feature set. This iterative process continues until the accuracy of the meta-model reaches a convergence point. The methodology is designed to uncover latent patterns within the data through the exploration of different cluster configurations, fostering a dynamic feature extraction process. We demonstrate the effectiveness of our approach on the Diabetes Dataset, and Wisconsin Breast Cancer Detection Dataset showcasing improvements in model accuracy as a result of the iterative integration of evaluation data. Our experimental results highlight the adaptability and robustness of the proposed method. Additionally, we discuss the implications of our findings for various applications and provide insights into potential avenues for future research in the realm of unsupervised learning for post-training model optimization. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimal allocation and sizing of shunt active power filter in radial distribution systems using particle swarm optimization 20

Optimal allocation and sizing of shunt active power filter i...

引用

20th International Conference on Smart Technologies, EUROCON 2023

作者： Primorac, Mario Klaic, Zvonimir Znidarec, Matej Adric, Adric Osijek Faculty of Electrical Engineering Computer Science and Information Technology Osijek Croatia

ISBN: (纸本)9781665463973

The reduction of harmonics in terms of improving power quality is usually achieved using passive or active filters. Due to their advantages over passive filters, active power filters (APF) are receiving increased attention from researchers focusing on optimal sizing and allocation of APFs in the network with the aim of reducing total harmonic distortion. This paper proposes methodology for determining optimal size, location and settings of APF while observing total harmonic distortion of voltage (THDV). It emphasizes the importance of controlling individual harmonic distortion (IHD). Furthermore, due to the different nature of the injection of harmonics into the radial distribution system (RDS), proposed methodology takes into account the load variation as well as changes in generation of the PV systems as distributed generation (DG). Optimal settings of APF is determined using particle swarm optimization (PSO) method. Evaluation of the proposed method is performed on three different study cases. Results show that variation of generation and consumption have significant impact on sizing, allocation and settings of the APFs. Furthermore, results pointed out that in apart from observing THDV, it is also necessary to observe IHD. © 2023 IEEE.

关键词： Power quality

来源：评论

学校读者我要写书评

暂无评论

Energy Preserving Techniques for CPS in Smart Healthcare System 13

Energy Preserving Techniques for CPS in Smart Healthcare Sys...

引用

13th International Conference on System Modeling and Advancement in Research Trends, SMART 2024

作者： Srivastava, Jyoti Routray, Sidheswar School of Engineering Indrashil University Department of Computer Science and Engineering Gujarat Rajpur Mehsana India Ganpat University Faculty of Engineering and Technology Department of Computer Engineering Gujarat Kherwa Mehsana India School of Technology Pandit Deendayal Energy University Department of Computer Science and Engineering Gandhinagar382007 India

ISBN: (纸本)9798350380583

Cyber Physical System (CPS) enhances the functionality of various cyber and physical equipment of Smart Healthcare System (SHS) and provides automation in the healthcare sector using Artificial Intelligence (AI) techniques. SHS collects medical data with the help of sensors or actuators equipped with smart medical devices that act as the physical component of CPS, then processes and analyzes these medical data with the help of cyber components of CPS to provide automation in health monitoring, doctor consultancy, medical prescriptions, medicine delivery and various other perspectives of the healthcare sector. These advancements in the healthcare sector result in great assistance for healthcare individuals like doctors, patients, nursing staff, etc, but at the same time deal with very sensitive parameters like time, efficiency, reliability, security, etc, that need to be managed with utmost accuracy for preserving each life in this global smart healthcare environment. There can be various efficiency parameters in CPS enabled SHS namely the number of hops, average energy consumption, resource utilization, etc, This work elaborately defines various characteristics of CPS in SHS, efficiency parameters, and major challenges for the successful implementation of CPS enabled SHS. © 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

A Hybrid Cybersecurity Algorithm for Digital Image Transmission over Advanced Communication Channel Models

引用

computers, Materials & Continua 2024年第4期79卷 201-241页

作者： Naglaa F.Soliman Fatma E.Fadl-Allah Walid El-Shafai Mahmoud I.Aly Maali Alabdulhafith Fathi E.Abd El-Samie Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Electronics and Communications Faculty of EngineeringZagazig UniversityZagazig44519Egypt Security Engineering Lab Computer Science DepartmentPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt

The efficient transmission of images,which plays a large role inwireless communication systems,poses a significant challenge in the growth of multimedia ***-quality images require well-tuned communication *** Single Carrier Frequency Division Multiple Access(SC-FDMA)is adopted for broadband wireless communications,because of its low sensitivity to carrier frequency offsets and low Peak-to-Average Power Ratio(PAPR).Data transmission through open-channel networks requires much concentration on security,reliability,and *** data need a space away fromunauthorized access,modification,or *** requirements are to be fulfilled by digital image watermarking and *** paper ismainly concerned with secure image communication over the wireless SC-FDMA systemas an adopted communication *** introduces a robust image communication framework over SC-FDMA that comprises digital image watermarking and encryption to improve image security,while maintaining a high-quality reconstruction of images at the receiver *** proposed framework allows image watermarking based on the Discrete Cosine Transform(DCT)merged with the Singular Value Decomposition(SVD)in the so-called DCT-SVD *** addition,image encryption is implemented based on chaos and DNA *** encrypted watermarked images are then transmitted through the wireless SC-FDMA *** linearMinimumMean Square Error(MMSE)equalizer is investigated in this paper to mitigate the effect of channel fading and noise on the transmitted *** subcarrier mapping schemes,namely localized and interleaved schemes,are compared in this *** study depends on different channelmodels,namely PedestrianAandVehicularA,with a modulation technique namedQuadratureAmplitude Modulation(QAM).Extensive simulation experiments are conducted and introduced in this paper for efficient transmission of encrypted watermarked *** addition,different variants of SC-FDMA bas

关键词： Cybersecurity applications image transmission channel models modulation techniques watermarking and encryption

来源：评论

学校读者我要写书评

暂无评论

Using Bearing-Only Measurements of an Underwater Observer Robot for Passive Tracking of a Highly Maneuvering Target Using Interactive Multiple-Model Cubature Kalman Filter 11

Using Bearing-Only Measurements of an Underwater Observer Ro...

引用

11th RSI International Conference on Robotics and Mechatronics, ICRoM 2023

作者： Ebrahimi, Mohsen Bonadaki, Seyed Mohammad Mehdi Dehghan Malek Ashtar University of Technology Faculty of Electrical and Computer Engineering Tehran Iran

ISBN: (纸本)9798350308105

Tracking of underwater moving targets by underwater robots requires the continuous use of passive observation of the target angle over time. In this case, the improvement of target position estimation depends on the movement of the submarine robot to increase the field of view. In order to protect the observer bot from being seen by the other party, passive BOT measurements are used in this paper. Since the motion of a target may have several models, one of the best choices is the interactive multiple model (IMM) filter. On the other hand, due to the non-linearity of the measurement equations and the target motion equations, the Cubature Kalman filter (CKF) can be used to improve the tracking accuracy. By combining these filters, in this paper, the IMM- CKF filter is used to track a highly maneuverable target in a situation where there is only one measurement from the observing robot at any time. © 2023 IEEE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

A Review on the Applications of Natural Language Processing in Healthcare 4

A Review on the Applications of Natural Language Processing ...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Warbhe, Mohan K. Verma, Prateek Faculty of Engineering and Technology Department of Computer Science and Design Sawangi Maharashtra Wardha442001 India Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Sawangi Maharashtra Wardha442001 India

ISBN: (纸本)9798331529635

In healthcare, Natural Language Processing (NLP) is a technique to improve clinical decision support, patient care, and medical research. By automating clinical recording, NLP enhances the calibre of medical records and professional communication. It makes Electronic Health Records (EHRs) easier to use by facilitating quick and easy data entry, retrieval, and access to vital patient data that helps with precise diagnosis and efficient treatment planning. Through the analysis of patient-specific data, NLP supports clinical decision support by delivering prompt recommendations. Chatbots and virtual assistants managing repetitive duties like booking appointments also improve patient connection. NLP makes it easier to analyse vast amounts of literature for medical research, facilitating the extraction and summary of important discoveries. Healthcare data processing requires text preparation, sentiment analysis, Named Entity Recognition (NER), semantic parsing, and Natural Language Generation (NLG). However, there are obstacles to overcome, like bias, ethical concerns, system integration, privacy, and data quality. The healthcare industry can use NLP to enhance patient outcomes, promote personalized medication, and streamline healthcare delivery by guaranteeing interoperability and setting standards. © 2024 IEEE.

关键词： Challenges of NLP in Healthcare Future treads of NLP for healthcare Healthcare NLP

来源：评论

学校读者我要写书评

暂无评论

Ontological Modelling and Social Networks: From Expert Validation to Consolidated Domains 1

引用

23rd International Conference on Computational Science, ICCS 2023

作者： Pileggi, Salvatore Flavio School of Computer Science Faculty of Engineering and IT University of Technology Sydney Ultimo Australia

ISBN: (数字)9783031360305

ISBN: (纸本)9783031360299

Data from Social Networks is a valuable asset within both a scientific and a business world. In the context of this work, ontological modelling from Social Networks is understood as a knowledge building process to generate a shared domain model. Such a technique relies on a balanced co-existence of human intuition/creativity and technological support, referred to as Hybrid Intelligence. Additionally, it assumes collaborative modelling and collective/social intelligence. The method implies a certain degree of uncertainty that is, in principle, inversely proportional to the achieved consensus. There are two clear different convergence points between the proposed process and collective/social intelligence: (i) at a data level, because of the nature of the input which is generated by different individuals, communities, stakeholders and actors;and (ii) at a modelling level, where human and automatically generated inputs, design decisions and validations are expected to involve several contributors, experts, modellers or analysts. Although looking holistically at the modelling process, this paper concisely focuses mostly on the ontological structure and the associated uncertainty, while resulting systems and studies are object of future work. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Behavior-based Feedback Loop for Attentive E-reading (BFLAe): A Real-Time computer Vision Approach 1

Behavior-based Feedback Loop for Attentive E-reading (BFLAe)...

引用

1st IJCAI Workshop and Challenge on Micro-Gesture Analysis for Hidden Emotion Understanding, MiGA 2023

作者： Lee, Yoon Migut, Gosia Specht, Marcus Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Netherlands

This study is built upon a behavior-based framework for real-time attention evaluation of higher education learners in e-reading. Significant challenges in AI model developments for learning analytics have been 1) defining valid indicators and 2) connecting the analytics results to interventions, balancing the generalization and personalization needs. To address this, we utilized a public multimodal WEDAR dataset and trained a neural network model based on real-time features of learners, aiming at predicting learners' moment-to-moment distractions. Real-time features for model training include 30 learners' attention regulation behaviors annotated every second, reaction times to blur stimuli, and page numbers indicating various reading phases. Our preliminary model based on a neural network has achieved 66.26% accuracy in predicting self-reported distractions. Based on the model, we suggest a framework of a Behavior-based Feedback Loop for Attentive e-reading (BFLAe). It has text blur as feedback, a mechanism responsive to learners' distractions that also works as data for next-round feedback. The general feedback implementation rules are established on a statistical analysis conducted on all learners. In addition, we propose a strategy for personalizing feedback using a quartile analysis of individual data, promoting learner-specific feedback. Our framework addresses the high demand for an automated e-learning assistant with non-intrusive data collection based on real-world settings and intuitive feedback provision. The feedback system aims to help learners with longer attention spans and less frequent distractions, leading to more engaging e-reading. © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Modal analysis

来源：评论

学校读者我要写书评

暂无评论

Ensemble Model for Detection and Classification of Brain Tumors 4

Ensemble Model for Detection and Classification of Brain Tum...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information Systems, ICUIS 2024

作者： Bhagyalaxmi, K. Dwarakanath, B. Srm Institute of Science and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Tamilnadu Ramapuram India Srm Institute of Science and Technology Department of Information Technology Tamilnadu Ramapuram India

ISBN: (纸本)9798331529635

Brain tumors, characterized by abnormal cell growth within the brain, present significant challenges for early detection and accurate classification due to their complex and heterogeneous nature. Manual evaluation of MRI scans, though critical, is often laborintensive and prone to errors, highlighting the need for advanced, automated diagnostic methods. Convolutional Neural Networks (CNNs) have demonstrated strong potential in this domain by effectively learning hierarchical features from raw medical images to detect and classify brain tumors. However, single CNN models often encounter difficulties in handling the variability in tumor appearance, such as differences in shape, size, and intensity. To address these challenges, this research proposes an ensemble model that integrates pretrained CNN architectures-ResNet50, Inception, and Xception. The ensemble technique strengthens the adaptability and accuracy of brain tumor identification and categorization by incorporating the advantages of these distinct models. The proposed model was trained and evaluated using a large dataset of 5,316 MRI images, representing a range of brain tumor types, including gliomas, pituitary, meningiomas, and cases no tumor. With a high classification accuracy of 99.39%, our ensemble model proved to be useful in enhancing the reliability of diagnoses and assisting surgeons in making decisions on the treatment of brain tumors. © 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

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：