检索结果-内蒙古大学图书馆

2022 International Conference on Electronics and Renewable Systems, ICEARS 2022

作者： Subbalakshmi, S. Madhavi, K. Jntua University Dept. of Computer Science and Engineering Andra Pradesh Anathapuramu India

ISBN: (纸本)9781665484251

The development of in-network services in the IT industry influences cloud usage rapidly for storage and distribution. As such new computing and service technology needed data owners to entrust their important data to place in the cloud service provider (CSP), in such case, the concerns surrounding the data security and privacy for the outsourced data is the biggest challenge. But it has become a widespread and apparent trend to utilize cloud services for data outsourcing. However, in consideration of the widespread interest in cloud computing, data security is the primary concern regarding the storage of cloud data is related to reliability and privacy, which are considered to be major difficulties to the acceptance of the cloud. To facilitate these issues and challenges, in this paper a Unique Key Integrity Agreement (UKIA) Approach has been presented. It initially investigates the issues and challenges to provide secure and reliable data storage and access methods in cloud computing. The UKIA proposes a framework to have secure and private data exchange between the data owner and consumer in support of an intermediate domain service provider to offer data storage and privacy access in the cloud. It implements a secure authorization model for the intermediate domain service providers, which will confine the required reliability and privacy assurance for the data owners for data storage, and a UKIA method for secure and private data access. The experiment analysis performs an asymptotic complexity comparison of the results to indicate the security goals with the practical efficiency of the computation in the security and privacy needs. © 2022 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Data-driven Forecasting of Weather in Bangladesh Leveraging Transformer Network and Strong Inter-feature Correlation 25

Data-driven Forecasting of Weather in Bangladesh Leveraging ...

引用

25th International Conference on computer and Information Technology, ICCIT 2022

作者： Islam, Zahidul Fariha, Raisa Islamic University of Technology Dept. of Computer Science and Engineering Gazipur1704 Bangladesh

ISBN: (纸本)9798350346022

Accurate weather forecasting is indispensable for countries like Bangladesh because of their reliance on agriculture and vulnerability to frequently occurring natural disasters such as floods, cyclones, and riverbank erosion. Bangladesh has a fairly regular annual weather pattern where the weather features, such as temperature, humidity, and rainfall, are highly correlated. Leveraging this inter-feature correlation between temperature and rainfall, we propose a flexible transformer based neural network that can forecast monthly temperature or rainfall by analyzing the past few data-points of any one or both of these weather features. We evaluated the proposed method using a public dataset called Bangladesh Weather Dataset which contains 115 years of Bangladesh weather data comprising month-wise average temperature and rainfall measurements. Our method demonstrates substantial improvements over the previously proposed approaches for this task in both metrics- mean squared error and mean absolute error. Our proposed transformer network is also significantly more lightweight and computationally efficient and accurate. This transformer aided method would pave a way to understand and leverage the complex relationship between the weather features and open up possibilities of coming up with even more robust methods of forecasting weather data. © 2022 IEEE.

关键词： Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

AI Based Biometrics Recognition with a Hyperspectral Image Sensor 2

AI Based Biometrics Recognition with a Hyperspectral Image S...

引用

2nd International Conference on Robotics, Automation and Artificial Intelligence, RAAI 2022

作者： Nakazawa, Ryo Premachandra, Chinthaka Shibaura Institute of Technology Dept. of Electrical Engineering and Computer Science Tokyo Japan

ISBN: (纸本)9781665459440

In information security, facial recognition technology is one of the most familiar authentication technologies in our daily life. However, the recent development in the field of Artificial Intelligence has made it easy to generate a human face image from a small number of images, which poses a threat to individual information security. This is known as deep faking, and is a problem for future information security. As a solution for this issue, we develop a face recognition technique based on highdimensional images using a hyperspectral sensor (HSI). Unlike ordinary two-dimensional sensors, the high-dimensional data acquired here is a huge cube-shaped data with spectral wavelength information. In order to perform authentication using highdimensional images, we generated images for each wavelength band by dividing the wavelength information into pseudo-bands and created classification models for each band. Inference is performed on a single high-dimensional image using multiple trained classification models, and authentication is based on the majority vote of the models. We confirmed the effectiveness of these methods through validation experiments. © 2022 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Monolithic 3D Printed Micro-Optofluidic Device for Two-phase Flow Monitoring and Bioapplications

Monolithic 3D Printed Micro-Optofluidic Device for Two-phase...

引用

Electric And Power engineering (EPEi), IEEE International Conference And Exposition On

作者： Lorena Saitta Emanuela Cutuli Giovanni Celano G Claudio Tosto Francesca Guarino Gianluca Cicala Maide Bucolo dept.of Civil Engineering and Architecture University of Catania Catania Italy dept. of Electrical Electronic and Computer Science Engineering University of Catania Catania Italy dept. of Biomedical and Biotechnological Science University of Catania Catania Italy

ISBN: (数字)9798350356199

ISBN: (纸本)9798350356205

In this work, a biocompatible 3D printed micro-optofluidic (MoF) device designed for monitoring two-phase flows is presented. It was manufactured using the Projection Micro-Stereolithography (PμSL) 3D printing technique combined with a biocompatible resin. This device successfully monitored both an air-water slug-flow and a two-phase mixture of micrometric eukaryotic yeast cells (Saccharomyces cerevisiae) suspended in a phosphate-buffered saline (PBS) solution. Its working principle relies on the absorption phenomenon, since different light transmissions are correlated to either the fluid or the cells interfering with a laser beam in a microchannel section. To accomplish this, the MoF device was designed with two micrometric slots for the insertion of optical fibers to capture the light signal. Both the micro-optical and microfluidic components, each 200 μm in size, were integrated into the MoF device as a monolithic structure. A wide experimental campaign was performed on the MoF device investigating different flow rates and cells concentrations. The optimal operative condition for achieving the most robust working ability were determined using a Design of Experiments (DoE) approach.

关键词： Performance evaluation Fluids Biomedical optical imaging Voltage measurement Cells (biology) Three-dimensional printing Stability analysis Real-time systems Biomedical monitoring Monitoring

来源：评论

学校读者我要写书评

暂无评论

An Automatic Prediction of Elevator Capacity Using ML to Customize the Total Capacity

An Automatic Prediction of Elevator Capacity Using ML to Cus...

引用

Computing, Power and Communication Technologies (IC2PCT), IEEE International Conference on

作者： Navjot Singh Talwandi Anubhav Tripathi Shanu Khare Dept of Computer Science Engineering Chandigarh University Punjab India

Elevators serve as vital components in modern buildings, yet optimizing passengers’ waiting time remains a crucial challenge. This study proposes a machine learning-based approach to enhance the efficiency of elevator systems by minimizing the waiting time experienced by passengers. By leveraging historical data and predictive models, this research aims to optimize elevator operations, considering factors such as traffic patterns, peak hours, and user demand. The implementation of machine learning algorithms enables the system to dynamically adjust elevator scheduling strategies, ultimately reducing waiting times and enhancing user experience. The findings highlight the potential of machine learning techniques in revolutionizing elevator management for improved passenger satisfaction and operational efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Healthcare Operations With Big Data and AI 1

Optimizing Healthcare Operations With Big Data and AI

引用

1st International Conference on Artificial Intelligence for Innovations in Healthcare Industries, ICAIIHI 2023

作者： Dubey, Krati Esnaashariyeh, Ali Nahak, Kirti Hodade, Dipali Nagnath Shrivastava, Kapil Jorvekar, Ganesh Manipal University Jaipur Department of Information Technology Jaipur India Institute of Management and Entrepreneurship Development Pune India Kalinga University Dept of Computer Science & Engineering Chhattisgarh Raipur India Shree Ramchandra College of Engineering Department of Engineering and Applied Science Maharashtra Pune412216 India Department of Computer Engineering and Applications GLA University Mathura India Sanjivani K.B.P. Polytechnic Computer Technology Kopargaon India

ISBN: (纸本)9798350330915

To improve patient care and operational effectiveness, this study investigates the implementation of big data along with artificial intelligence (AI) into medical operations. Utilizing a deductive technique and an interpretive approach, this study collects secondary data from reliable sources using a descriptive design. While AI applications concentrate on clinical decision support, tailored treatment strategies, and predictive analytics, Big Data integration includes health records, medical imaging, genome-wide data, and patient-generated information. Private data, interconnection, biases in AI systems, and resource limitations are some of the difficulties. Transparency, justice, and patient autonomy are all important ethical considerations. Strong data security protocols, continuous attempts to mitigate prejudice, interdisciplinary training, and open governance frameworks are among the suggestions offered. Future research should focus on interoperability standards © 2023 IEEE.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Parallelized 0/1 Knapsack Algorithm Optimization in CPU-GPU-Based Heterogeneous System with Algorithm-based Fault Tolerance

Parallelized 0/1 Knapsack Algorithm Optimization in CPU-GPU-...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Marzan Binte Abid Shuvo Shaha Upama Kabir Md. Fahim Arefin Dept. of Computer Science and Engineering University of Dhaka Bangladesh

A heterogeneous high-performance computing (HPC) system is an aggregation of CPUs and GPUs through high-speed interconnection. As graphics processing units (GPUs) can conduct rapid mathematical and vector operations due to their hardware properties, GPU-based heterogeneous systems can optimize algorithms that show data parallelism. Since the dynamic programming (DP) solution of the 0/1 knapsack algorithm is inherently data-parallel, this paper optimized the algorithm to maximize the advantages of a GPU-based parallel environment. Furthermore, this research identified that the algorithm was well suited to four distinct GPU-launch approaches. Among them, the “single-cell calculation by single thread with a single kernel launch” approach outperforms others by reducing the complexity from O( $n$ *w) to O( $n$ ). Besides, these HPC systems are susceptible to the slightest of errors. Checkpoint recovery (CP/R) is the most commonly used fault tolerance and recovery system, which suffers from huge checkpoint and recovery overhead. To reduce this overhead in CPU-GPU-based heterogeneous systems, an algorithm-based fault tolerance (ABFT) technique has been proposed for a particular class of algorithm: 0/1 knapsack. The experimental results verify the feasibility of the proposed ABFT technique and demonstrate that the system can recover from failures with minimal overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

computer Vision-based Interactive Autism Detection System using Deep Learning

Computer Vision-based Interactive Autism Detection System us...

引用

Computing, Applications and Systems (COMPAS), IEEE International Conference on

作者： Badhon Parvej Sikder Md Mahbub Alam Faizul Islam Fahim Md. Naimul Pathan Muhammad Aminur Rahaman Dept of Computer Science and Engineering Green University of Bangladesh Bangladesh

ISBN: (数字)9798331529765

ISBN: (纸本)9798331529772

Autism Spectrum Disorder (ASD) is a multifaceted neurodevelopmental disorder that influences communication, language abilities, and social interactions, affecting both verbal and nonverbal exchanges. Identifying and diagnosing ASD at an early stage is essential for creating timely educational strategies, providing family assistance, and ensuring suitable medical care is available. Early screening can facilitate the development of optimal therapeutic strategies at the right time. By analyzing facial features, significant markers encoded in human faces can be studied to identify ASD. In this research, we gathered facial images of children with ASD from publicly available sources and employed deep-learning classifiers to sort them. Furthermore, the classifier was utilized to differentiate various ASD subgroups, relying exclusively on the autistic image data. The need for automated diagnosis techniques for ASD has become increasingly *** address this, we made use of a dataset containing 2,940 facial images of children with autism and those who are typically developing. We evaluated the outcomes of existing methods and enhanced the VGG16 model to improve its training and fitting processes. Through substantial modifications to variables such as epoch number and batch size, we increased the accuracy from 77% to 86.3%, while also calculating metrics like precision, specificity, and sensitivity. Moreover, we optimized the training and testing procedures compared to the base code. To enhance the evaluation of the results, we calculated several metrics, such as true positive, true negative, false positive, and false negative rates, in addition to accuracy, precision, sensitivity, and specificity. These results were documented in the *** file. Additionally, we implemented the VGG19 CNN model and compared its performance with VGG16. The deep learning approach achieved the highest accuracy of 88% with VGG19, followed by 86.3% with VGG16.

关键词： Training Deep learning Autism Accuracy Sensitivity Computational modeling computer architecture Sensitivity and specificity Convolutional neural networks Testing

来源：评论

学校读者我要写书评

暂无评论

Exploring Students' Attitudes Towards Robotics Technology in STEM Education: A Machine Learning-Based Prediction Analysis 4

Exploring Students' Attitudes Towards Robotics Technology in...

引用

4th IEEE International Conference on Emerging Techniques in Computational Intelligence, ICETCI 2024

作者： El Aziz, Mahmoud I. Abd Elshewey, Ahmed M. Tarek, Zahraa El-Kenawy, El-Sayed M. Ghazy, Ahmed M. Bhatnagar, Roheet Shams, Mahmoud Y. Kafrelsheikh University Faculty of Education Department of Curriculum Instruction and Educational Technology Kafrelsheikh33511 Egypt Suez University Faculty of Computers and Information Computer Science Department Suez Egypt Mansoura University Faculty of Computers and Information Computer Science Department Mansoura35561 Egypt Delta Higher Institute of Engineering and Technology Dept. of Communications and Electronics Mansoura35111 Egypt Manipal University Department of Computer Science and Engineering Rajasthan Jaipur India Kafrelsheiku University Faculty of Artificial Intelligence Dept. of Machine Learning 33516 Egypt

ISBN: (纸本)9798350387063

The aim of this paper is to predict the extent to which students will accept robotics technology in future teaching plans. The study involves students engaging in a two-week project-based learning program on robotics technology, after which they will decide whether it is suitable for them. To achieve this, the paper uses several prediction algorithms based on Machine Learning (ML), including Linear Regression (LR), Ridge Regression (RR), Elastic Net (EN) regression, and K-Nearest Neighbor (KNN) models. The sample group consists of 35 students from STEM high schools in Egypt. The research findings indicate that the students have gained confidence and satisfaction in robotics technology and believe it will have significant value in the future. The prediction results obtained from the ML regression models support these findings. The dataset used in the study includes seven input features and one target output representing the total prediction values of accepting and rejecting robotics technology in STEM schools. The regression models LR, RR, EN, and KNN achieve determination coefficients (R2) of 99.99%, 98.80%,99.20%, and 85.60%, respectively. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Sign Language Recognition by using Spatio-Temporal Features

引用

Procedia computer science 2024年 233卷 353-362页

作者： Renjith S Manazhy Rashmi Sumi Suresh M S Dept. of Computer Science and Engineering Amrita Vishwa Vidyapeetham Amritapuri 690525 India Dept. of Electronics and Communication Engineering Amrita Vishwa Vidyapeetham Amritapuri 690525 India Dept. of Computer Science and Engineering University at Bufalo New York City USA

The recognition of sign language has significant importance as an application that addresses the communication challenges faced by those within the Deaf and hard-of-hearing populations. This study introduces a methodology for the identification of sign language using spatio-temporal attributes, specifically concentrating on two distinct sign language datasets: the CSL (Chinese Sign Language) alphabet and the ArSL (Arabic Sign Language) alphabet. The study's objective is to create a powerful recognition system capable of reliably identifying sign language motions. A combination of spatio-temporal characteristics collected from video sequences of sign language motions is used in the suggested technique. These characteristics capture the spatial layout as well as the temporal dynamics of the motions, allowing the model to recognise signals with more precision. Experiments were carried out on the CSL and ArSL alphabet datasets to validate the method's efficacy. The findings of the trials are encouraging. The suggested system recognized CSL alphabet signs with an accuracy of 90.87% and ArSL alphabet signs with an accuracy of 89.46%. These high accuracy rates show the power of the spatiotemporal feature-based method for sign language identification. The system's success on two different sign languages implies that it is adaptable and useful in a wide variety of sign language applications. This study contributes to the evolution of assistive technology, making sign language recognition more accessible and efficient for those who communicate using sign language. Furthermore, the findings pave the way for additional research into spatiotemporal feature-based approaches in sign language recognition, with potential applications in real-world settings such as sign language interpretation and communication support.

关键词： Sign Language Classification Spatio-temporal features Time Distributed CNN

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：