检索结果-内蒙古大学图书馆

Innovative Practices in Technology and Management (ICIPTM), international conference on

作者： Kanksha Kaur Omdev Dahiya School of Computer Science and Engineering Lovely Professional University Punjab India

The use of data mining techniques to answer important educational questions is done with educational data mining that may be related to predicting students' performance or assessment. The purpose of these remains to address the goal of meeting and fulfilling the learning objectives. learning analytics is a new approach for teachers to think about education and involves the visualization of data about students to improve learning. It is related to management strategies that prioritize quantitative measurements, which can sometimes be at odds with a teaching-focused approach to education. The purpose of this study is to perform a systematic literature review of the various techniques used in both educational data mining and learning analytics. The area of educational data mining utilizes data mining techniques to examine educational data. Meanwhile, learning analytics centers on utilizing data to gain knowledge about learning processes and student performance. The review will consider various techniques, including statistical methods, machine learning algorithms, and data visualization techniques, which are commonly used. The goal is to identify the most effective techniques for analyzing educational data and improving student learning outcomes. By performing a systematic literature review, this study will provide an overview of the current state of research in educational data mining and learning analytics. It will also identify gaps in the literature and suggest areas for future research. Ultimately, the findings of this study will be of great value to researchers, educators, and policymakers who are interested in using data to enhance the learning experience. For performing this, a few research questions have been designed to select relevant studies. In this study, the research articles from a decade, 2012 to 2022, are taken into consideration. From the overall search results, 41 studies have been taken into consideration that has addressed the scope and significan

关键词： Epidemics Systematics machine learning algorithms Statistical analysis Bibliographies Education Data visualization

来源：评论

学校读者我要写书评

暂无评论

StraightLine: An End-to-End Resource-Aware Scheduler for machine learning application Requests

StraightLine: An End-to-End Resource-Aware Scheduler for Mac...

引用

Artificial Intelligence, Internet of Things and Cloud Computing Technology (AIoTC), international conference on

作者： Cheng-Wei Ching Boyuan Guan Hailu Xu Liting Hu Department of Computer Science and Engineering University of California Santa Cruz Santa Cruz CA USA Geographic Information System (GIS) Center of Florida International University Miami FL USA Department of Computer Engineering and Computer Science California State University Long Beach CA USA

ISBN: (数字)9798331530280

ISBN: (纸本)9798331530297

The life cycle of machine learning (ML) applications consists of two stages: model development and model deployment. However, traditional ML systems (e.g., training-specific or inference-specific systems) focus on one particular stage or phase of the life cycle of ML applications. These systems often aim at optimizing model training or accelerating model inference, and they frequently assume homogeneous infrastructure, which may not always reflect real-world scenarios that include cloud data centers, local servers, containers, and serverless platforms. We present StraightLine, an end-to-end resource-aware scheduler that schedules the optimal resources (e.g., container, virtual machine, or serverless) for different ML application requests in a hybrid infrastructure. The key innovation is an empirical dynamic placing algorithm that intelligently places requests based on their unique characteristics (e.g., request frequency, input data size, and data distribution). In contrast to existing ML systems, StraightLine offers end-to-end resource-aware placement, thereby it can significantly reduce response time and failure rate for model deployment when facing different computing resources in the hybrid infrastructure.

关键词： Training Cloud computing Technological innovation Schedules Heuristic algorithms machine learning Containers Data models Time factors Servers

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Performance of machine learning Algorithms for Real-Time Data Analysis Under Optimization

Analyzing the Performance of Machine Learning Algorithms for...

引用

Smart Generation Computing, Communication and Networking (SMART GENCON), international conference on

作者： V.J. Vijayalakshmi Senthilkumar K Riddhi R. Mirajkar Adlin Jebakumari S Manish Kumar Goyal Nitin N. Sakhare Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Department of Electronics and Communication Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Information Technology Vishwakarma Institute of Information Technology Pune INDIA Department of Computer Science and Information Technology Jain Bangalore Karnataka India Department of Computer Science & Application Vivekananda Global University Jaipur India Department of Computer Engineering Vishwakarma Institute of Information Technology Pune INDIA

In current years, studies has shifted away from conventional statistical methods to include more sophisticated gadget studying algorithms including support vector machines, random forests, and deep getting to know for real-time statistics analysis. But, such algorithms have their very own precise challenges, particularly associated with optimization and performance. This studies paper seeks to discover the challenges posed by applying gadget studying algorithms to actual-time datasets and talk the tactics and strategies to optimize the algorithms for stepped forward performance. Using numerous optimization strategies inclusive of evolutionary algorithms, simulated annealing, and evolutionary techniques are introduced to beautify the performance of the machine mastering algorithms. Additionally, the usage of go-validation, hyper parameter tuning, and ensemble methods to enhance the accuracy and pace of the algorithms is investigated. This paper additionally presents an in depth evaluation of the results received from exceptional optimization strategies with regards to overall performance. In the end, potential areas for in addition studies are discussed in detail.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Integration Of Computational With Physical System Through machine learning

Integration Of Computational With Physical System Through Ma...

引用

Advance Computing and Innovative Technologies in Engineering (ICACITE), international conference on

作者： MahsimovQosimkhonIbayevich KhakimovaKamolatkhonRahimjonovna KayumovOdiljonAbduraufovich TurdikulovKhusanboyKhudoynazarovich Department of Geodesy Cartography and Cadastre Fergana Polytechnic Institute Fergana Uzbekistan

The transition of a rice machine mixture from a stand - alone application to a fully integrated manufacturing system is described in this study. In this procedure, load cells that had already been installed situ were switched out, and extra sensitive and electromagnetic translation gauges were used. The Smart Joining Lab at the Division of Metallic Making completely incorporated that one after calibrating into a six-layer democratization framework. Two front-end mortal interactions were created inside this architecture, with the first one acting as a situation tracking system during the turning operation. A robust machine-learning algorithm that was created using Python and is able to not only forecast and adjust the final rolling program of a specified metal sheet but also learn from further steel production timetables executed is visualized in the main graphical interface. Utilizing data from some of the more than 1900 milled steps with various roll spacing height, sheeting size, and roughness parameters, this algorithm was developed using a black box methodology. As a consequence, the created software may extrapolate and parallelize between any of these characteristics as well as various beginning panel depths, acting as a digital system for suggestions based on data on scheduling adjustments for various trying to roll production steps. Additionally, it is conceivable to see how the settings affect the outcome of the milling operation using the third gui. Schoolchildren and other stakeholders can open the viewing because the entire layer system is running on a community college existing system. They could use surroundings to further their understanding of the features and influences of the sheet metal forming as well as computer science and particularly the fundamentals of computer science. This methodology also forms the foundation for the future integrating of data from the field of nanomaterials for the forecasting of the impact of various materials on the rol

关键词：

来源：评论

学校读者我要写书评

暂无评论

computer Big Data Technology and Mathematical Model Applied in Korean Network learning System 2021

Computer Big Data Technology and Mathematical Model Applied ...

引用

2021 3rd international conference on Artificial Intelligence and Advanced Manufacture

作者： Yaqian Wang Shandong Vocational College of Science & Technology China

ISBN: (纸本)9781450385046

In natural language processing systems (including machine translation systems), grammatical and semantic information dictionaries are essential components. From the perspective of language engineering, the article discusses the theoretical basis of the establishment of a language knowledge expression system for Korean information processing, the design concept of the system, the mathematical model of the system library structure, and the technology and strategy of how to use VC language to implement it. The interface legend of the program.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge Computing for IoT Security: Integrating machine learning with Key Agreement

Edge Computing for IoT Security: Integrating Machine Learnin...

引用

Consumer Electronics and computer Engineering (ICCECE), 2021 IEEE international conference on

作者： Tingda Shen Lijiao Ding Jinze Sun Changqiang Jing Feng Guo Chuankun Wu School of information science and engineering Linyi University Linyi China

The Internet of Things (IoT) is one of the most widely used technologies today, the number of IoT connections growing by 18% to 14.4 Billion active endpoints globally. Thus, with such a large scale IoT application, security becomes the focus. The issue of intrusion and interception has been a controversial and much disputed subject within the field of IoT security. The main limitation of IoT security, however, is a single security technology cannot ensure security of the IoT system. The Internet of Things requires diverse technologies applied at different layers to work together to ensure security. Based on these problems, proposed a security solution with integrity is necessary. Edge computing is a great way to solve security problems for resource-constrained devices. This paper proposes a machine learning and cryptography combined IoT security scheme at edge computing, achieves monitoring and detection abnormal behaviors of IoT system and automatically responds at an early stage. Designed a lightweight key management scheme without third-party involvement. The combination of active detection and passive protection for IoT security is achieved. Meanwhile, data for this study were collected using Edge-IIoTset dataset for the prediction of IoT security threats in edge computing networks. In this paper, experiments offers some important insights into the model selection for the prediction of time series data. The models selected include Support Vector machine(SVM), K-Nearest Neighbor(KNN), and Long Short-Term Memory(LSTM) models. The significance of the comparison of several models is to assess their accuracy in detecting IoT communication data. To compares the performance of models, the following performance evaluation parameters were used: Precision, Recall and F1-Score. This study has identified LSTM has better precision in time series data such as communication data, 10% more precision than the other models used in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Sentiment Analysis and Topic Modeling of E-Grocery application Reviews Using Naive Bayes and Support Vector machine: A Case Study of Segari Data Review on the Google Play Store

Sentiment Analysis and Topic Modeling of E-Grocery Applicati...

引用

Electronic and Electrical Engineering and Intelligent System (ICE3IS), international conference on

作者： Jefka Dhammananda Indra Budi Aris Budi Santoso Faculty of Computer Science Universitas Indonesia Jakarta Indonesia

Segari is a customer-centric company with a core value of being obsessed with its customers. The lack of human resources and the abundance of customer reviews that need to be analyzed hinder the process of extracting information from these reviews. Therefore, a machine learning model is needed to automatically perform sentiment analysis and topic modeling. The information extracted from sentiment analysis can be used as a reference to maintain service quality based on positive sentiments, while the results of negative sentiments can be used for evaluation to improve Segari's services and application. The data used on this research were customer reviews from the Google Play Store. The model development process includes data collection, data labeling, data preprocessing, feature extraction, sentiment classification model, model evaluation, and topic modeling. The researcher utilized two classification algorithms, NB and SVM, on a total of 10,507 reviews. The data shows that 74.37% express positive sentiments, while 25.63% express negative sentiments. The results of the study indicate that SVM with oversampling achieved the best model performance, with a recall of 89.98%. Additionally, the researcher used LDA to identify topics related to customer perspectives on Segari, which will be communicated to the relevant team. The analysis revealed that some customers are satisfied while others are disappointed with the product delivery process, application, prices, promotions, and vouchers. Customers generally expressed satisfaction with the quality and freshness of the products. Some customers felt disappointed due to missing or incomplete items in their orders, also to customer service.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A combined feature extraction model using SIFT and LBPfor offline signature verification system

A combined feature extraction model using SIFT and LBPfor of...

引用

international conference for Convergence in Technology

作者： Bhushan S. Thakare Hemant R. Deshmukh Sant Gadge Baba Amravati University Amravati India Dept. of Computer Engineering Dr. Rajendra Gode Institute of Technology & Research Amravati India

Increasing demand of security application in realtime scenario has grown rapidly during last decade. In this field, bio-metric applications are considered as most promising technique for user identity verification and identification. Other that bio-metric systems, signature based user verification systems are also used widely in various application such as banking systems use signature based transaction. This process of verifying signatures is called as offline signature verification. Several techniques have been introduced in this field but the performance of verification depends on the significant feature extraction technique. To deal with this issue, here we presented a combined approach for feature extraction where SIFT (Scale Invariant Feature Transform) and improved LBP (Local Binary Pattern) are combined together to obtain the robust feature model. furthermore, a classification study is also presented to measure the performance of proposed approach. Experimental study shows that proposed approach obtains promising performance for signature verification system.

关键词： offline signature SIFt feature LBP feaute machine learning

来源：评论

学校读者我要写书评

暂无评论

iSeePlus : A cost effective smart assistance archetype based on deep learning model for visually impaired

引用

JOURNAL OF INFORMATION & OPTIMIZATION SCIENCES 2020年第7期41卷 1741-1756页

作者： Virmani, Deepali Gupta, Charu Bamdev, Pakhi Jain, Prateek Guru Gobind Singh Indraprastha Univ Dept Comp Sci & Engn Bhagwan Parshuram Inst Technol Sect 17 New Delhi 110089 India

In this paper, a unique smart assistance aid, iSeePlus, for visually impaired people is presented. iSeePlus, as a prototype product, is equipped with smart glasses (iSee Glasses), a smart stick (iStick) and an android application which will be initially used to set up the device. The smart glasses are trained on proposed deep learning models to provide features like face detection and recognition, emotion detection and image captioning with a click of a specifically placed buttons on the device. The proposed prototype product also supports reading texts from images via Google Cloud Vision API and allows the user to send alert texts with his current location to the saved emergency contacts. The iStick is an integrated accessory that comes with iSeePlus which creates vibrations to alert the user of any incoming obstacle within the range of 25 cm. The android application will be used to set up the device at initial stages as it helps to add a database of known people and the emergency contacts. Presently, iSeePlus, has an accuracy of 98.03% on face detection and recognition model, FDREnet, 68.5% on emotion detection with ExpressNet and 65.7% on image captioning with CaptionMeNet BLUE-1: 65.7). With the help of iSeePlus, people suffering from visual impairment will now be able to do their day-to-day chores independently up to a significant degree.

关键词： Deep learning computer vision machine learning Android application Raspberry Pi3 Visual impairment Assistive technology Convolution neural network

来源：评论

学校读者我要写书评

暂无评论

Labour Exploitation Investigation using Satellite based Vessel Monitoring Systems

Labour Exploitation Investigation using Satellite based Vess...

引用

Computing, Analytics and Networks (Indo-Taiwan ICAN), Indo – Taiwan 2nd international conference on

作者： P. Karthikeyan Pao-Ann Hsiung Department of Computer Science and Information Engineering National Chung Cheng University Chiayi Taiwan

ISBN: (纸本)9781665499453

Taiwan is one of the most extensive distant water fishing (DWF) and has more than 1,000 ships producing 40 billion N.T. dollars. More than 90% of Taiwanese fishermen are recruited from Indonesia, the Philippines, and Vietnam. However, labour exploitation has become a severe problem in the Taiwan distant water fishing (DWF) industry. The Taiwan government recently amended the law and stipulated that multiple CCTV cameras be installed on DWF vessels to protect against labour abuse. Current technology only records videos captured by CCTV cameras. Thus, detecting labour abuse is nearly impossible. To resolve this problem, we have developed a deep neural network model to predict labour abuse in DWF. The developed model uses satellite-based vessel monitoring systems data for the predictions of labour abuse. The proposed deep neural network model gives better prediction than logistic regression, support vector machine, Random Forest and decision tree.

关键词： Deep learning Industries Analytical models Satellites Computational modeling Neural networks Predictive models

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：