检索结果-内蒙古大学图书馆

4th International Conference on Recent Innovations in Computing, ICRIC 2021

作者： Rathor, Sandeep Hasan, Afreen Omar, Ankur Department of Computer Engineering and Applications GLA University Mathura India

ISBN: (纸本)9789811688911

Each day an enormous number of people get missing from kids to senior citizens because of some mental illness or Alzheimer’s or Dementia. Out of all, most of them are trackless. Therefore, an artificial intelligence-based technique is proposed in this paper. It helps to find missing persons and can be used by the government officials like police or the common people. If a person goes missing, relatives of that person can visit the nearest police station and provide the details of the missing person which includes a photo (picture). When any person got such a missing person then, they can capture a picture of that person and upload it in our proposed model. Now, our proposed model tries to find that match in our database using the face recognition encoding technique. If a match is found, the proposed model will inform police officers along with the current location of the missing person. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Analyzing Performance of Pre-Trained Models in Detecting Sentiments of Code Mixed Manglish Text Reviews from Social Media

Analyzing Performance of Pre-Trained Models in Detecting Sen...

引用

2022 International Conference on Computing, Communication, Security and Intelligent Systems, IC3SIS 2022

作者： Bhagya, Sree S Nadera, Beevi S TKM College of Engineering Department of Computer Applications Kollam India

ISBN: (数字)9781665468831

ISBN: (纸本)9781665468831

In the context of social media and multilingual community, code mixing is a common sociolinguistic occurrence. Analyzing code mixed texts from social media is a vital language processing task for applications such as part-of-speech tagging, named entity recognition, sentiment analysis, conversational systems, and machine translation. Very limited code mixed datasets are available for low-resourced languages like Malayalam, Tamil, Telugu etc. The corpora available in the area of code switching contributed significantly to the advancement of research in this field. This work focuses on processing code mixed Mangish text reviews, which is a mixture of Malayalam and English languages, represented in Roman script. Also it evaluates the performance of different pre-Trained models like mBERT, DistilBERT(multilingual), RoBERTa, XLM and XLNET to determine the sentiment class of Manglish text reviews from the Dravidian code mix repository and identify which performs better in the context. © 2022 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Drones in FANETs using Queueing Model

Performance Evaluation of Drones in FANETs using Queueing Mo...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Ghosh, Akash Dash, Bibhuti Bhusan Patra, Sudhansu Shekhar Pandey, Trilok Nath Pattanayak, Binod Kumar De, Utpal Chandra School of Computer Applications Kiit Deemed to Be University Bhubaneswar India School of Computer Science and Engineering Vit Chennai India Iter Soa Deemed to Be University Department of Computer Science and Engineering Bhubaneswar India

ISBN: (纸本)9798350313987

When conventional communication routes are unavailable or malfunctioning, mobile adhoc networks (MANETs) are essential for establishing communication. These networks can be easily and cheaply built whenever necessary because they don't require any pre-existing infrastructure. In some extreme situations (such as floods, battle zones, rescue operations, etc.), MANETs cannot be used. Lacking a fixed infrastructure in some situations, flying ad hoc networks (FANETs) can be quite useful for establishing communication. In FANETs, many drones are connected one to another directly or through middle nodes. In this research work, the arrival rate of events during the catastrophe, the drone's service rate, the waiting buffer of the system is considered and various performance measures such as the waiting time of the requests in the waiting buffer, the waiting time of the requests in the system, average queue length and the drones' idle time have all been considered. The ideal number of drones should be used to handle catastrophic occurrences and reduce casualties by adopting the queuing model. © 2023 IEEE.

关键词： Catastrophe Drones Flying ad-hoc networks Performance Measures Queueing Model

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis of Different Machine Learning Techniques For Medical Insurance Premium Prediction 1

A Comparative Analysis of Different Machine Learning Techniq...

引用

1st International Conference on Cognitive, Green and Ubiquitous Computing, IC-CGU 2024

作者： Dash, Satyabrata Panigrahi, Bhawani Sankar Sanikommu, Vijay Venkata Bhaskar Reddy Madhavi, B.K. Sahoo, Susanta Kumar Department of Computer Science & Engineering Vishakhapatnam India Vardhman College of Engineeing Department of Information Technology Telangana Hyderabad India Ramachandra College of Engineering Department of Computer Science & engineering Andhra Pradesh Eluru India Indira Gandhi Institute of Technology Department of Computer Science Engineering & Applications Odisha Sarang India

ISBN: (纸本)9798350361780

Predicting health insurance premiums is a crucial task for both insurance companies and policyholders. This paper explores the use of regression approaches to predict health insurance premiums. The study uses a dataset of insurance premiums and related variables, including age, gender, BMI, and location to determine the factors that have the biggest effects on insurance rates. The study found that age and BMI were the main predictors of insurance rates, with gender and location having a relatively little influence. To create predictive models, the study combined various regression approaches, including logistic regression, Random Forest Regression, Decision Tree Regression, Gradient Boosting Regression, and linear regression. The predictive models were highly accurate, with a mean absolute error of less than 5% across all examined samples. The findings have significant implications for both insurers and customers, as accurate premium pricing is essential for insurers to maintain their financial health and offer customers coverage at reasonable prices. Accurate premium forecasts help policyholders plan their spending wisely for insurance costs and make informed decisions regarding their healthcare coverage. © 2024 IEEE.

关键词： Health insurance

来源：评论

学校读者我要写书评

暂无评论

Blood Cell Classification and Counting in Hematology through Deep Learning 4

Blood Cell Classification and Counting in Hematology through...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Ananthi, P. Devi, K. Nirmala Ramya, T.E. Shanmugapriya, P. Aradhya, T. Kongu Engineering College Department of Computer Technology Perundurai Tamil Nadu Erode India Madanapalle Institute of Technology & Science Department of Computer Applications India Kongu Engineering College Perundurai Tamil Nadu Erode India

ISBN: (纸本)9798331540364

Medical diagnosis is one of the areas that has been greatly influenced by the progress of computer vision technologies. This study presents a unique approach for the detection and counting of blood cells in hematology: You Only Look One algorithm version 7 (YOLOv7). YOLO is designed for real-time object detection, making it ideal for applications such as blood vessel detection where speed is critical. The architecture allows the model to process images faster than other recognition models, such as R-CNN or SSD, which is very important for situations that require fast results, such as analysis automatic blood at clinical sites. The purpose of the proposed method is to overcome the shortcomings of conventional methods and to accurately and quickly identify blood cells in mechanical images. The YOLOv7 model has been utilizedbecause it can detect objects in real-time with highprecision and speed. The methodology for bloodcell counting involves the use of YOLOv7 togenerate bounding boxes around each detectedblood cell in an image, where the count of these bounding boxes directly corresponds to the number of cells. This advancement in hematology not onlyimproves blood cell analysis efficiency but also expedites the process of diagnosing and planningtreatment in various medical situations. This paper details how YOLOv7 was modified and adjusted to meet the specific requirements of hematologicalimage analysis, including training models, preparing datasets, and evaluating performance. The study also addresses the potential impact of this technology on clinical workflows, highlightinghow it might help medical practitioners make decisions more quickly and intelligently. Hematology analysis systems including YOLOv7 are able to improve laboratory diagnostics and help patients by providing better care and results. This workconcludes by demonstrating the revolutionary potential of YOLOv7 in blood cell identificationand counting in hematology, paving the way for accurate and better

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Prediction Using Advance Machine Learning Algorithms 8

Breast Cancer Prediction Using Advance Machine Learning Algo...

引用

8th International Conference on Advanced Computing and Communication Systems, ICACCS 2022

作者： Jain, Vinod Agrawal, Mayank Gla University Department of Computer Engineering and Applications Mathura India

ISBN: (纸本)9781665408165

Breast cancer is very common type of cancer now a day. It is observed in many of the women and responsible for many deaths in recent days. In this work the power of machine learning classifiers is applied in prediction of breast cancer. Three machine learning classifiers LR, KNN and Decision Tree are applied on a standard data set and their prediction accuracy is calculated. From the experiment it is concluded that the LR algorithms is best for breast cancer prediction. © 2022 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Using ARO and LSTM Algorithms

引用

SN computer Science 2025年第1期6卷 1-11页

作者： Bhagat, Amit Dangi, Dharmendra Suman, Vaibhav Dixit, Dheeraj Kumar Sharma, Suvarna Department of Computer Applications MANIT Madhya Pradesh Bhopal India Department of Information Technology IIIT Madhya Pradesh Bhopal India Department of Computer Science & Engineering LNCT University Madhya Pradesh Bhopal India Department of Computer Science & Engineering MITS Madhya Pradesh Gwalior India Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

There has been an exponential increase in social media content over the past few years due to the popularity of social media platforms. However, this has also resulted in the dissemination of intentionally false information, or fake news, which can have significant negative effects on society. As a result, detecting fake news has become an important issue that requires attention. Promoting trust in the global community is crucial to preventing the spread of false information in mass media. A study report suggests a reliable technique for identifying false news in order to remedy this. The author has thoughtfully chosen two distinct datasets: the Buzzfeed dataset, which is an assortment of news articles from Buzzfeed News, and the ISOT dataset, which is a collection of social media postings and articles from other sources. The author thoroughly analyzed a variety of content kinds and assessed the efficacy of various approaches and methods for processing and categorizing them using the datasets. The study found that these datasets have accuracy rates of 99% and 97.8% respectively. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： ARO algorithm Fake news detection LSTM Pre-processing

来源：评论

学校读者我要写书评

暂无评论

Software Reliability Assessment Using Hybrid Neuro-Fuzzy Model

引用

computer Systems Science & engineering 2022年第6期41卷 891-902页

作者： Parul Gandhi Mohammad Zubair Khan Ravi Kumar Sharma Omar H.Alhazmi Surbhi Bhatia Chinmay Chakraborty Department of Computer Applications Manav Rachna International Institute of Research and StudiesFaridabad121006India Department of Computer Science College of Computer Science and EngineeringTaibah UniversityMadinahSaudi Arabia Department of Computer Applications Chandigarh Group of CollegesLandran140307India College of Computer Sciences and Information Technology King Faisal UniversitySaudi Arabia Department of Electronics&Communication Engineering Birla Institute of TechnologyMesra JharkhandIndia

Software reliability is the primary concern of software developmentorganizations, and the exponentially increasing demand for reliable softwarerequires modeling techniques to be developed in the present era. Small unnoticeable drifts in the software can culminate into a disaster. Early removal of theseerrors helps the organization improve and enhance the software’s reliability andsave money, time, and effort. Many soft computing techniques are available toget solutions for critical problems but selecting the appropriate technique is abig challenge. This paper proposed an efficient algorithm that can be used forthe prediction of software reliability. The proposed algorithm is implementedusing a hybrid approach named Neuro-Fuzzy Inference System and has also beenapplied to test data. In this work, a comparison among different techniques of softcomputing has been performed. After testing and training the real time data withthe reliability prediction in terms of mean relative error and mean absolute relativeerror as 0.0060 and 0.0121, respectively, the claim has been verified. The resultsclaim that the proposed algorithm predicts attractive outcomes in terms of meanabsolute relative error plus mean relative error compared to the other existingmodels that justify the reliability prediction of the proposed model. Thus, thisnovel technique intends to make this model as simple as possible to improvethe software reliability.

关键词： Software quality reliability neural networks fuzzy logic neuro-fuzzy inference system

来源：评论

学校读者我要写书评

暂无评论

EEG Signal Analysis for Emotional Classification 3

EEG Signal Analysis for Emotional Classification

引用

3rd International Conference on Electronics and Sustainable Communication Systems, ICESC 2022

作者： Nanthini, K. Pyingkodi, M. Sivabalaselvamani, D. Kaviya Kongu Engineering College Department of Computer Applications TamilNadu India

ISBN: (数字)9781665479714

ISBN: (纸本)9781665479714

Electroencephalography (EEG) uses electrodes to assess neuronal activity in various brain areas. Emotion is a state that encompasses human feelings, thoughts, and behavior, and it may be found in all aspects of daily life. The proposed study reviews the deep learning techniques for automatically extracting the spatial elements, which explain the functional link between EEG data at distinct electrodes. The proposed work of this study is to examine single and ensemble approaches for classifying emotional events using EEG inspiration information. The dataset which is generated through business product known as MUSE EEG headband with 4 electrode resolution, support on some states of mind recognized via cognitive behavioral learning, grouped into three feasible states which include effective, neutral, and poor. High-quality and terrible emotional states are invoked the use of video clips with evident valence, in addition to neutral resting information and not using a stimulation, eager about one minute in keeping with consultation. Five indicators have been recovered from EEG headbands using the desired set of traits. Of the set of 2548 capabilities, a subset of 63 capabilities, selected based on their statistics benefit values, have been shown to be the handiest whilst utilized with ensemble classifiers along with Gated Recurrent gadgets and long brief-time period reminiscence in Recurrent Neural Networks. As it uses sequential RNN's are significantly used in natural language and speech recognition packages to method time series facts. A basic accuracy of approximately ninety seven.18% of checking out accuracy for GRU and 95.13% accuracy for LSTM has been received. © 2022 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Image Captioning: Methods and Evaluation Metrics 2

Image Captioning: Methods and Evaluation Metrics

引用

2nd IEEE International Conference on Intelligent Technologies, CONIT 2022

作者： Sharma, Himanshu Srivastava, Swati Applications Gla University Department of Computer Engineering Mathura India

ISBN: (数字)9781665484077

ISBN: (纸本)9781665484077

In computer Vision, image captioning is one of the most fascinating topics. Image captioning simply says generating sentences from a given picture. The process of generating captions from images includes two processes. One of them is image processing and the other one is natural language processing. In this, we use CNN that is a Convolution neural network, and RNN is a recurrent neural network. We use CNN for drawing out properties from the given picture and RNN for creating language. Though, the process is a bit complex and difficult, though we have put in a good amount of time in planning and research for the contentment of every attribute of it. The paper contains a comprehensive study of different models that are used for image captioning. Models that we will be discussing will be the Retrieval-Based Model, Template-Based Model, CNN-RNN based model, and CNN-CNN Model. © 2022 IEEE.

关键词： computer vision

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：