检索结果-内蒙古大学图书馆

3rd International Conference for Innovation in Technology, INOCON 2024

作者： Vagale, Ghanashyam Prajwal, G.K. Kumar, Rohit Dharishini, P. Padma Priya Ramaiah University of Applied Sciences Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350381931

This paper presents an innovative framework that employs camera-captured visual data to detect and suggest optimal sitting postures. The framework consists of two crucial components: a video capture object and an object detection system that incorporates Deep Learning to enhance efficiency and reliability. The camera initially captures the user's posture image, which is then subjected to video processing to extract video metadata. Subsequently, the object is created by extracting the image from the video, and the object detection algorithm is applied to provide posture recommendations. The algorithm continually monitors posture correctness and provides suggestions to improve it as necessary, ultimately benefiting the user's daily life and mitigating potential long-term problems. Additionally, the algorithm can be further developed to recognize posture patterns and suggest corrective exercises or techniques. Furthermore, the algorithm's efficiency can be enhanced by optimizing landmark detection for more effective outcomes. This cutting-edge framework offers immense potential for improving posture and overall health, and its development can significantly enhance the quality of life for individuals. © 2024 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Gastrointestinal Diseases Classification Using Deep Transfer Learning and Features Optimization

引用

computers, Materials & Continua 2023年第4期75卷 2227-2245页

作者： Mousa Alhajlah Muhammad Nouman Noor Muhammad Nazir Awais Mahmood Imran Ashraf Tehmina Karamat College of Applied Computer Science King Saud University(Almuzahmiyah Campus)Riyadh11543Saudi Arabia Department of Computer Science HITEC UniversityTaxila47080Pakistan Department of Computer Engineering HITEC UniversityTaxila47080Pakistan Department of Software Engineering Foundation University IslamabadIslamabad44000Pakistan

Gastrointestinal diseases like ulcers, polyps’, and bleeding areincreasing rapidly in the world over the last decade. On average 0.7 millioncases are reported worldwide every year. The main cause of gastrointestinaldiseases is a Helicobacter Pylori (H. Pylori) bacterium that presents in morethan 50% of people around the globe. Many researchers have proposeddifferent methods for gastrointestinal disease using computer vision *** of them focused on the detection process and the rest of themperformed classification. The major challenges that they faced are the similarityof infected and healthy regions that misleads the correct classificationaccuracy. In this work, we proposed a technique based on Mask Recurrent-Convolutional Neural Network (R-CNN) and fine-tuned pre-trainedResNet-50 and ResNet-152 networks for feature extraction. Initially, the region ofinterest is detected using Mask R-CNN which is later utilized for the trainingof fine-tuned models through transfer learning. Features are extracted fromfine-tuned models that are later fused using a serial approach. Moreover, anImproved Ant Colony Optimization (ACO) algorithm has also opted for thebest feature selection from the fused feature vector. The best-selected featuresare finally classified using machine learning techniques. The experimentalprocess was conducted on the publicly available dataset and obtained animproved accuracy of 96.43%. In comparison with state-of-the-art techniques,it is observed that the proposed accuracy is improved.

关键词： Diseases deep learning endoscopy gastrointestinal tract transfer learning

来源：评论

学校读者我要写书评

暂无评论

INTEROPERABILITY PLATFORMS: A COMPONENT BASED APPROACH TO DERIVE FUNCTIONAL CLASSIFICATION 9

INTEROPERABILITY PLATFORMS: A COMPONENT BASED APPROACH TO DE...

引用

9th International Conference on Big Data Analytics, Data Mining and Computational Intelligence, BigDaCI 2024, the 10th International Conference on Connected Smart Cities, CSC 2024 and the 16th International Conference on e-Health, EH 2024, Part of the 18th Multi Conference on computer science and Information Systems 2024, MCCSIS 2024

作者： Staemmler, Martin Department of Electrical Engineering and Computer Science University of Applied Sciences Stralsund Germany

ISBN: (纸本)9789898704597

Interoperability platforms (IOPs) have been and are continuously designed, deployed and used for a variety of scopes, from simple data integration, reducing heterogeneity between data sources, data management systems without and with archival function up to allowing for process support and supporting data analysis. Furthermore, the scope depends on the intended use in acute care or research or both of them as well as on the stakeholders involved from health care professionals, external cooperating organizations and up to the involvement of patients. The objective of the paper is to derive a functional classification reflecting not only the IOP development over the last years but also anticipating upcoming designs. As such, four functional levels which build on top of each other have been identified: (i) management of unstructured data, (ii) management of structured data, (iii) process support, and (iv) data analysis. For each level, the respective system architecture is sketched, including functional components and references to relevant standards, profiles, and means for semantic annotation. Furthermore, the functional classification is applied to a set of projects and initiatives and allows assigning them to functional levels, thus enabling functional discrimination. © 2024 Big Data Analytics, Data Mining and Computational Intelligence. All Rights Reserved.

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Explain the Explainer: Interpreting Model-Agnostic Counterfactual Explanations of a Deep Reinforcement Learning Agent

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1443-1457页

作者： Chen, Ziheng Silvestri, Fabrizio Tolomei, Gabriele Wang, Jia Zhu, He Ahn, Hongshik Stony Brook University Department of Applied Mathematics and Statistics Stony BrookNY11794 United States Sapienza University of Rome Department of Computer Engineering The Department of Computer Science Rome00185 Italy Xi'An Jiaotong-Liverpool University Department of Intelligent Science Suzhou215000 China Rutgers University-New Brunswick Department of Computer Science PiscatawayNJ08854 United States

Counterfactual examples (CFs) are one of the most popular methods for attaching post hoc explanations to machine learning models. However, existing CF generation methods either exploit the internals of specific models or depend on each sample's neighborhood;thus, they are hard to generalize for complex models and inefficient for large datasets. This article aims to overcome these limitations and introduces ReLAX, a model-agnostic algorithm to generate optimal counterfactual explanations. Specifically, we formulate the problem of crafting CFs as a sequential decision-making task. We then find the optimal CFs via deep reinforcement learning (DRL) with discrete-continuous hybrid action space. In addition, we develop a distillation algorithm to extract decision rules from the DRL agent's policy in the form of a decision tree to make the process of generating CFs itself interpretable. Extensive experiments conducted on six tabular datasets have shown that ReLAX outperforms existing CF generation baselines, as it produces sparser counterfactuals, is more scalable to complex target models to explain, and generalizes to both the classification and regression tasks. Finally, we show the ability of our method to provide actionable recommendations and distill interpretable policy explanations in two practical real-world use cases. © 2020 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Single-Valued Neutrosophic Graph with Heptapartitioend Structure

引用

Neutrosophic Sets and Systems 2025年 80卷 728-748页

作者： Fathi, Hanaa Myvizhi, M. Abdelhafeez, Ahmed Abdellah, Mohamed Refaat Eassa, Mohamed Sawah, Mohamed S. Elbehiery, Hussam College of Information Technology Amman Arab University Amman Jordan KPR Institute of Engineering and Technology Tamilnadu Coimbatore India Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan The Department of Computer Science College of Information Technology Misr University for Science and Technology Cairo Egypt Department of Computer Science Faculty of Information Technology Ajloun National University P.O.43 Ajloun26810 Jordan

This study applies single-valued neutrosophic sets, which extend the frameworks of fuzzy and intuitionistic fuzzy sets, to graph theory. We introduce a new category of graphs called Single-Valued Heptapartitioned Neutrosophic Graphs (SVHNG) and investigate their characteristics through comprehensive proofs and illustrative examples. © 2025, University of New Mexico. All rights reserved.

关键词： Heptapartitioend Neutrosophic Set Neutrosophic Graph Neutrosophic Sets SVHN-Graph

来源：评论

学校读者我要写书评

暂无评论

A Secure Framework for WSN-IoT Using Deep Learning for Enhanced Intrusion Detection

引用

computers, Materials & Continua 2024年第10期81卷 471-501页

作者： Chandraumakantham Om Kumar Sudhakaran Gajendran Suguna Marappan Mohammed Zakariah Abdulaziz S.Almazyad School of Computer Science&Engineering Vellore Institute of TechnologyChennai CampusChennai600127India School of Electronics&Engineering Vellore Institute of TechnologyChennai CampusChennai600127India Department of Computer Sciences and Engineering College of Applied ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Computer Engineering College of Computer and Information SciencesKing Saud UniversityRiyadh11543Saudi Arabia

The security of the wireless sensor network-Internet of Things(WSN-IoT)network is more challenging due to its randomness and self-organized *** detection is one of the key methodologies utilized to ensure the security of the *** intrusion detection mechanisms have issues such as higher misclassification rates,increased model complexity,insignificant feature extraction,increased training time,increased run time complexity,computation overhead,failure to identify new attacks,increased energy consumption,and a variety of other factors that limit the performance of the intrusion system *** this research a security framework for WSN-IoT,through a deep learning technique is introduced using Modified Fuzzy-Adaptive DenseNet(MF_AdaDenseNet)and is benchmarked with datasets like NSL-KDD,UNSWNB15,CIDDS-001,Edge IIoT,Bot *** this,the optimal feature selection using Capturing Dingo Optimization(CDO)is devised to acquire relevant features by removing redundant *** proposed MF_AdaDenseNet intrusion detection model offers significant benefits by utilizing optimal feature selection with the CDO *** results in enhanced Detection Capacity with minimal computation complexity,as well as a reduction in False Alarm Rate(FAR)due to the consideration of classification error in the fitness *** a result,the combined CDO-based feature selection and MF_AdaDenseNet intrusion detection mechanism outperform other state-of-the-art techniques,achieving maximal Detection Capacity,precision,recall,and F-Measure of 99.46%,99.54%,99.91%,and 99.68%,respectively,along with minimal FAR and Mean Absolute Error(MAE)of 0.9%and 0.11.

关键词： Deep learning intrusion detection fuzzy rules feature selection false alarm rate accuracy wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Classification using a Spiking Neural Network: A Review

引用

IEIE Transactions on Smart Processing and Computing 2023年第1期12卷 64-71页

作者： Park, Yuntae Sunarya, Unang Yang, Geunbo Lee, Choongseop Baek, Jaewoo Baek, Suwhan Park, Cheolsoo Department of Computer Engineering KwangWoon University Korea Republic of School of Applied Science Telkom University Bandung Indonesia

In this paper, different types of spiking neural network (SNN) and the methods to teach them are addressed. The spiking neural network is especially designed in a biologically plausible way. Like other neural networks, SNNs trained with certain learning methods have been used for image processing, data mining, and classification, etc. Unlike other neural networks, the SNN uses one-bit spike information, and one of its main advantages is reducing energy consumption. Copyrights © 2023 The Institute of Electronics and Information Engineers.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Collaborative Search With Knowledge Sharing And Summarization 4

Collaborative Search With Knowledge Sharing And Summarizatio...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Mohan, Venkateshwaran Sivaganesan, D. Balasubramaniam, S. Vikhas, S.G. Dhinesh, S.P. Psg Institute of Technology and Applied Research Department of Computer Science and Engineering Coimbatore India Dr Mahalingam College of Engineering and Technology Department of Computer Science and Engineering Pollachi India Psg College of Technology Department of Computer Science and Engineering Coimbatore India Sri Krishna Arts and Science College Department of Computer Science Coimbatore India

ISBN: (纸本)9798331540364

A collaborative search engine is used for a group of users who want to search information together for various group activities. This will be time saving as the users can split the work between them. Summarization is the process of condensing a document into a shorter version which will contain the important details about the document. This will be useful to quickly get the main ideas without having to go through the entire document. Our main aim is to combine collaborative search with document summarization so that it will be helpful when users in a group want to quickly read the summary of the documents whenever required. In the collaborative search, the results will be re-ranked based on the user's interaction with the system, so that feedback driven ranking of results is attained and the users in a session will be able to view pages that were even ranked by their co-mates. This re-raking process is done by obtaining the user's interest on a particular page using decision logic and updating it in the priority queue. User's meta-data like page size, click-through rate, time spent and scrolling speed of the document will be calculated and these will be used as parameters for the decision logic to find the interest level of the user. Extractive summarization is implemented with the concept of Maximum Independent Set. The raw text document is first converted into a graph having its sentences as nodes and the edge weight is the similar instances between sentences. Then graph MIS is identified and removed after which the top-n sentences are fetched upon its eigenvector centrality value and the summary is generated. © 2024 IEEE.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

Prediction of Insurance Claims for Health Sector using Machine Learning Techniques 3

Prediction of Insurance Claims for Health Sector using Machi...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Pragatheeswari, E. Kavitha, M.N. Saranya, S.S. Dhanushree, D. Jasmitha, S. Abiradhie, P.V. Department of Computer Technology Kongu Engineering College Perundurai Erode India Department of Computer Science and Design Kongu Engineering College Perundurai Erode India Department of Computer Science and Engineering PSG Institute of Technology and Applied Research Coimbatore India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

Nowadays, health issues play a tremendous role in day-to-day life and the medical expenditure to get treatment becomes more difficult for the ordinary people. Health insurance has become a vital aspect of people's lives. In this massive community, to access healthcare services such as insurance policies, LIC, ICICI, HDFC ERGO, Star Healthcare are benefits for claiming an amount for their medical expenses. The dataset encompasses three categories, such as generalized data, hospitalized data and claim data. Each record in the dataset represents an individual’s health insurance charges along with corresponding demographic and health-related characteristics. In this paper, Machine Learning techniques are used to group the claim amount that has been adopted by the individuals based on the hospitalized expenditure and insurance charges paid by the individuals. In the health sector, machine learning techniques are used to forecast insurance claims by building predictive models from historical data on claims, patient demographics, treatment types, and results. By predicting future claims based on trends seen in the data, these models help insurance firms better manage risk and allocate resources. In case of a fresher to this concept, it feels challenging to understand whereas generating as a pattern can be more flexible to acquire knowledge about how much amount has been claimed. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Learned, uncertainty-driven adaptive acquisition for photon-efficient scanning microscopy

引用

Optics Express 2025年第6期33卷 12269-12287页

作者： Ye, Cassandra Tong Han, Jiashu Liu, Kunzan Angelopoulos, Anastasios Griffith, Linda Monakhova, Kristina You, Sixian The Department of Electrical Engineering and Computer Science CambridgeMA02139 United States Fu Foundation School of Engineering and Applied Science Columbia University in The City of New York New YorkNY10027 United States University of California Berkeley Department of Electrical Engineering and Computer Science BerkeleyCA94720 United States Department of Biological Engineering Massachusetts Institute of Technology CambridgeMA02139 United States

Scanning microscopy systems, such as confocal and multiphoton microscopy, are powerful imaging tools for probing deep into biological tissue. However, scanning systems have an inherent trade-off between acquisition time, field of view, phototoxicity, and image quality. This often results in noisy measurements when fast, large field of view, and/or gentle imaging is needed. Deep learning could be used to denoise noisy microscopy measurements, but these algorithms can be prone to hallucination, which can be disastrous for medical and scientific applications. We propose a method to simultaneously denoise and predict pixel-wise uncertainty for scanning microscopy systems, improving algorithm trustworthiness and providing statistical guarantees for deep learning predictions. Furthermore, we propose to leverage this learned, pixel-wise uncertainty to drive an adaptive acquisition technique that rescans only the most uncertain regions of a sample, saving time and reducing the total light dose to the sample. We demonstrate our method on experimental confocal and multiphoton microscopy systems, showing that our uncertainty maps can pinpoint hallucinations in the deep learned predictions. Finally, with our adaptive acquisition technique, we demonstrate up to 16× reduction in acquisition time and total light dose while successfully recovering fine features in the sample and reducing hallucinations. We are the first to demonstrate distribution-free uncertainty quantification for a denoising task with real experimental data and the first to propose adaptive acquisition based on reconstruction uncertainty. © 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement.

关键词： Pixels

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：