检索结果-内蒙古大学图书馆

Junior Conference on Lighting (Lighting)

作者： Plamen Stanchev Gergana Vacheva Nikolay Hinov Departement of Information Technology in industry Faculty of Computer Systems and Technologies Technical University of Sofia Sofia Bulgaria Departement of Power Electronics Faculty of Electronic Engineering and Technologies Technical University of Sofia Sofia Bulgaria

In the presented article, an assessment and measurements were realized to determine the energy efficiency of a medium-sized industrial enterprise. Real data from a three-shift plant was used. An assessment of the current electricity consumption was made and an energy audit was carried out to reduce electricity costs. The main goal of the current research is to ensure the basic functionality of the buildings, as well as the production-technological process, ensuring minimum electricity costs and maximum efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Edge Computing Enabled Smart Warehouse Management System for Food Processing Industries

Edge Computing Enabled Smart Warehouse Management System for...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Gowrishankar V Veena P Ponmurugan P Annapoorani B T Vijayakumar P Siva Ramkumar M Department of Electronics and Communication Engineering Velalar College of Engineering and Technology Erode India Department of Electrical and Electronics Engineering K S R Institute for Engineering and Technology Tiruchengode India Department of Research Meenakshi Academy of Higher Education and Research Chennai Department of Electronics and Communication Engineering Bannari Amman Institute of Technology Sathyamangalam India Department of Master of Computer Applications Kongu Engineering College Perundurai Tamil Nadu Department of Electrical and Electronics Engineering Faculty of Engineering Karpagam Academy of Higher Education Coimbatore India

Food safety is a primary concern across all global platforms, and food storage is a crucial and essential part of management. This clarifies that food warehousing should be fully automated or has some management system. Good food storage plays a vital role in food security, which is affected by food waste and food loss. As a result, it is critical to identify and remove microbial contamination before it spreads to other items. To end that, we propose an edge computing-enabled intelligent warehouse system with an ESP32 microcontroller and micropython. The food commodities studied in the other papers were fish, dairy, fresh food products, crop-field cucumber, seafood, wine, and pre-packaged food. The various gas sensors are used to detect microbial growth, food decay, and shelf life. Humidity and temperature sensors are employed to monitor the warehouse environment, along with RFID technology to track food items. Multiple nodes accessible via Telegram and dashboard notifications will be put in the building to enable law enforcement collaboration. These nodes will exchange information on the building's structure. Compared to the traditional warehouse management system, the proposed edge computing-enabled IoT warehouse shelves reduce waste and contamination in fruit and vegetable chambers. Designs are experimented with different sets of fruits and vegetables. Continuous live monitoring and an alert system demonstrate the effectiveness of the proposed innovative framework compared with an existing management system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CWDM communication system based inline erbium-doped fiber amplifiers with the linear geometrical polarization model

引用

Journal of Optical Communications 2024年 45卷 s431-s443页

作者： Eid, Mahmoud M. A. Sorathiya, Vishal Lavadiya, Sunil Parmar, Juveriya Patel, Shobhit K. Ali, Shaimaa Ahmed Rashed, Ahmed Nabih Zaki Department of Electrical Engineering College of Engineering Taif University Taif Saudi Arabia Department of Information and Communication Technology Marwadi University Rajkot India Department of Physics Marwadi University Rajkot360003 India Department of Electronics and Communication Engineering Marwadi University Rajkot360003 India Department of Computer Engineering Marwadi University Rajkot360003 India Electronics and Electrical Communications Engineering Department Faculty of Electronic Engineering Menoufia University Menouf32951 Egypt

Optical fiber coarse wavelength division multiplexing (CWDM) with erbium-doped fiber inline-amplifiers for the linear polarization geometrical model is studied in this paper for fiber system optimization by using the Optisystem simulation software. Signal gain (SG), noise figure (NF), and signal/noise are measured against CWDM optical fiber variations. The erbium-doped fiber amplifier (EDFA) is based on the Giles model which solves the steady-state rate equations for SG and signal absorption parameters with the cross-section area of the amplifier itself. The signal is optimized at EDFA length of 6 m, 10 Gb/s data rates (DRs) transmission and 10 km CWDM fiber optic length (FOL). Max. Q factor is degraded and min. BER is upgraded with both CWDM optical FLs and higher DRs transmission increase. © 2021 Walter de Gruyter GmbH, Berlin/Boston.

关键词： Erbium doped fiber amplifiers

来源：评论

学校读者我要写书评

暂无评论

Machine Learning based Comparative Analysis of Cervical Cancer Risk Classifications Algorithms

Machine Learning based Comparative Analysis of Cervical Canc...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Tania Ganguly Peeta Basa Pati K. Deepa Tripty Singh Tolga Özer Department of Computer Science and Engineering Amrita School of Computing Bengaluru India Department of Electrical and Electronics Engineering Amrita School of Engineering Bengaluru India Technology Faculty Electric Electronic Engineering Afyon Kocatepe University Afyonkarahisar Turkey

Cervical cancer is a major health concern for women worldwide, and early detection is essential for successful treatment. Since symptoms often do not appear until later stages, early screening is necessary. Machine learning can help classify cervical cancer risk by analyzing patient datasets and identifying the important factors that predict the likelihood of emerging cervical cancer. This paper evaluates six different machine-learning approaches for analyzing risk factors associated with cervical cancer using a dataset of 838 instances with 36 features. Results show that the SVM classifier performs the best, with an accuracy of 99.60% which emphasize the possibility of utilizing machine learning to enhance the precision of cervical cancer risk assessment. This can result in the development of better screening and prevention techniques for cervical cancer, which can be more effective in identifying and managing this disease.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Inculcation of Sensors in Enhancing Smart Cities: A Review

Inculcation of Sensors in Enhancing Smart Cities: A Review

引用

International Conference on Power Energy, Environment and Intelligent Control (PEEIC)

作者： Trupti V Nandikolmath Sandeep Kumar Jain Savita Yadav Department of Electrical and Electronics Engineering Faculty of Engineering and Technology JAIN (Deemed to be University) Bangalore India Department of Electrical Engineering Vivekananda Global University Jaipur India Department of Computer Science and Engineering (lOT) Noida Institute of Engineering & Technology Greater Noida Uttar Pradesh India

By 2050, experts predict that 75% of people on Earth will live in cities. As such, cities need to be prepared to fulfill the needs of their citizens and provide the best possible services. The idea of a “smart city,” which is an improved system that effectively manages its resources and services via monitoring and communication technology, is often central to the notion of an advanced city. Thus, turning cities into smart entities is a critical step toward global urban sustainability. Beyond creating smart buildings in cities, the main goal is to improve people's quality of life by using newly developed digital technologies and sensing capabilities. The key to smarter communities is their capacity to invest in these technologies, adapt, and socialize in a transparent and inclusive manner while taking into account the needs and values of the local and regional communities. Despite these developments, privacy issues and interruptions in cyber security remain serious weaknesses that need addressed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Pseudonym Mutable Based Privacy for 5G User Identity

引用

computer Systems Science & engineering 2021年第10期39卷 1-14页

作者： Rashid A.Saeed Mamoon M.Saeed Rania A.Mokhtar Hesham Alhumyani S.Abdel-Khalek Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityP.O.Box 11099Taif21944Saudi Arabia Department of Electrical Engineering Faculty of EngineeringAlzaiem Alazhari UniversityKhartoum11111Sudan Department of Communications and Electronics Engineering Faculty of EngineeringUniversity of Modern Sciences(UMS)Sana'a16784Yemen Department of Mathematics College of SciencesTaif UniversityP.O.Box 11099Taif21944Saudi Arabia

Privacy,identity preserving and integrity have become key problems for telecommunication *** privacy threats are expected in 5G networks considering the large number of devices that will be *** Internet of Things(IoT)and long-term evolution for machine type(LTE-m)are growing very fast with massive data traffic the risk of privacy attacks will be greatly *** all the above issues standards’bodies should ensure users’identity and privacy in order to gain the trust of service providers and *** such threats,5G specifications require a rigid and robust privacy *** research studies have addressed user privacy in 5G *** paper proposes a method to enhance user identity privacy in 5G systems through a scheme to protect the international mobile subscriber identity(IMSI)using a mutable mobile subscriber identity(MMSI)that changes randomly and avoids the exchange of *** maintains authentication and key agreement(AKA)structure compatibility with previous mobile generations and improves user equipment(UE)synchronization with home *** proposed algorithm adds no computation overhead to UE or the network except a small amount in the home subscriber server(HSS).The proposed pseudonym mutable uses the XOR function to send the MMSI from the HSS to the UE which is reducing the encryption overhead *** proposed solution was verified by ProVerif.

关键词： 5G MMSI IMSI AKA privacy user identity

来源：评论

学校读者我要写书评

暂无评论

A Supervised Machine Learning Approach for Short-Term Forecasting and Demand Response Optimization for Enhancing Energy Flexibility in Smart home

A Supervised Machine Learning Approach for Short-Term Foreca...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： P Glaret Subin V Gomathy Krishnakumar Ramasamy R Dhivya U Arun Kumar S Shargunam Department of Electronics and Communication Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Vadapalani Campus Chennai Tamilnadu India Department of EEE Kathir College of Engineering Coimbatore Tamilnadu India Department of Electrical and Electronics Engineering Sri Ramakrishna Engineering College Coimbatore Tamil Nadu India Information Technology M.Kumarasamy College of Engineering Karur Tamilnadu India Department of Electrical and Electronics Engineering Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Virudhunagar Srivilliputhur Tamilnadu India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

This research investigates supervised machine learning algorithms for short-term energy forecast in smart homes. A dataset involving energy consumption in the house was used and it was analyzed across 10-times using the Support Vector Machine, k-Nearest Neighbors, Gradient Boosting Machines, and Ensemble Methods. Results show that the performance of the Support Vector Machine was significantly higher with a mean, standard deviation, and maximum accuracy of 0.84, 0.02, and 0.88. Notably, the SVM had the minimum mean absolute error of 0.035 and root mean square error at 0.045. The coefficient of determination was also high, between 0.72 and 0.76, across 10-times of iteration. Thus, the SVM model is more accurate and reliable for forecasting energy consumption in the house. Although k-NN, GBM, and Ensemble Methods also showed considerable success, the abovementioned information proves that SVM is the most beneficial algorithm for smart home energy forecasting for the short-term. These outcomes can help design efficient energy management systems as they inform practitioners about the effectiveness of this method for energy consumption optimization to decrease costs and increase user comfort. Knowing which algorithms are capable of producing the high-quality results helps to design highly efficient short-term and long-term energy management solutions that satisfy the needs and preferences of smart home users, making the energy as sustainable and efficient as possible.

关键词： Support vector machines Energy consumption Machine learning algorithms Accuracy Smart homes Predictive models Ensemble learning

来源：评论

学校读者我要写书评

暂无评论

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

arXiv

引用

arXiv 2023年

作者： Hao, Zhiwei Guo, Jianyuan Han, Kai Tang, Yehui Hu, Han Wang, Yunhe Xu, Chang School of information and Electronics Beijing Institute of Technology China Huawei Noah’s Ark Lab Canada School of Computer Science Faculty of Engineering The University of Sydney Australia

Knowledge distillation (KD) has proven to be a highly effective approach for enhancing model performance through a teacher-student training scheme. However, most existing distillation methods are designed under the assumption that the teacher and student models belong to the same model family, particularly the hint-based approaches. By using centered kernel alignment (CKA) to compare the learned features between heterogeneous teacher and student models, we observe significant feature divergence. This divergence illustrates the ineffectiveness of previous hint-based methods in cross-architecture distillation. To tackle the challenge in distilling heterogeneous models, we propose a simple yet effective one-for-all KD framework called OFA-KD, which significantly improves the distillation performance between heterogeneous architectures. Specifically, we project intermediate features into an aligned latent space such as the logits space, where architecture-specific information is discarded. Additionally, we introduce an adaptive target enhancement scheme to prevent the student from being disturbed by irrelevant information. Extensive experiments with various architectures, including CNN, Transformer, and MLP, demonstrate the superiority of our OFA-KD framework in enabling distillation between heterogeneous architectures. Specifically, when equipped with our OFA-KD, the student models achieve notable performance improvements, with a maximum gain of 8.0% on the CIFAR-100 dataset and 0.7% on the ImageNet-1K dataset. PyTorch code1 and checkpoints can be found at https://***/Hao840/OFAKD. Copyright © 2023, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Improving Bandwidth Utilization for Underwater Fiber Optic Networks Through Intelligent Optimization Techniques

Improving Bandwidth Utilization for Underwater Fiber Optic N...

引用

Paradigm Shift in Information Technologies with Innovative Applications in Global Scenario (ICPSITIAGS), IEEE International Conference on

作者： Nitin N. Sakhare Rakesh Kumar Yadav Rajesh A Inzimam ul Hassan Vinithra Banu. T Maheswaran S Department of Computer Engineering Vishwakarma Institute of Information Technology Pune INDIA Maharishi School of Engineering and Technology Maharishi University of Information Technology UP India Department of Computer Science Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be University) Karnataka India Department of Computer Science & Engineering Vivekananda Global University Jaipur India Department of Mechanical Engineering Prince Shri Venkateshwara Padmavathy Engineering College Chennai Department of Electronics and Communication Engineering Kongu Engineering College Erode Tamil Nadu INDIA

ISBN: (数字)9798350329773

ISBN: (纸本)9798350329780

Underwater Fiber Optic Networks (UFONs) are getting increasingly more important because of the emergence of the marine economic system, the enlargement of ocean exploration sports, and the need for reliable net get entry to. However, their bandwidth utilization is negative due to insufficient useful resource allocation techniques, constrained community design facts, and restricted expertise about consumer traffic styles. This paper proposes clever optimization techniques to improve the bandwidth usage of UFONs. These strategies are primarily based on gadget studying strategies along with neural networks and particle-swarm optimization. Numerous performance metrics are used to assess the proposed techniques. Simulations and experiments are performed to compare the overall performance of the proposed techniques with conventional techniques. Effects show the proposed smart optimization strategies are able to enhancing the bandwidth utilization of UFONs by means of as much as sixteen%. The proposed shrewd optimization strategies can provide significant enhancements for actual-time aid allocation, dynamic network control, and monitoring of underwater traffic styles.

关键词： Optical fibers Scalability Bandwidth Throughput Resource management Reliability Particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

AI-based Flexible Online Laboratory Learning System for Post-COVID-19 Era: Requirements and Design

AI-based Flexible Online Laboratory Learning System for Post...

引用

2021 International Mobile, Intelligent, and Ubiquitous Computing Conference, MIUCC 2021

作者： Elmesalawy, Mahmoud M. Atia, Ayman Yousef, Ahmed Mohamed Fahmy El-Haleem, Ahmed M. Abd Anany, Mohamed G. Elmosilhy, Noha A. Salama, Abdullah I. Hamdy, Alaa Zoghby, Helmy M. El Din, Eman Serag El Helwan University Faculty of Engineering Electronics and Communications Engineering Department Cairo Egypt Helwan University HCI-LAB Faculty of Computers and Artificial Intelligent Computer Science Department Cairo Egypt Giza Egypt Fayoum University Faculty of Specific Education Education Technology Department Fayoum Egypt Electronics and Communications Engineering Department Cairo Egypt Helwan University Faculty of Engineering Computer and Systems Engineering Department Cairo Egypt Misr International University Faculty of Computer Science Cairo Egypt Helwan University Faculty of Engineering Electrical Power and Machines Engineering Department Cairo Egypt Network Planning Department Cairo Egypt

ISBN: (纸本)9781665412438

The worldwide outbreak due to COVID-19 pandemic has led to a great interest in e-learning. However, the lack of suitable online laboratory management systems has posed a particular challenge for sectors that need laboratory activities such as engineering, science and technology. In this paper, the requirements and design for a flexible AI-based laboratory learning system (LLS) that can support online laboratory experimentations are presented. The elicitation of the LLS design requirements is decided based on a conducted survey for a set of LLS features. The LLS is designed with the flexibility to support various types of online experimentations such as virtual or remote controlled experiments using either desktop or web applications. The virtualization technique is used to manage the laboratory resources and allow multiple users to access the LLS. Moreover, the proposed LLS introduces the use of AI techniques to provide efficient virtual lab assistant and adaptive assessment process. © 2021 IEEE.

关键词： COVID-19

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：