检索结果-内蒙古大学图书馆

Artificial Intelligence and Image Processing (IWAIIP), International Workshop on

作者： Muh. Hafidh Ilmi Nafi’An Fitra Abdurrachman Bachtiar Budi Darma Setiawan Informatics Engineering Department Computer Science Faculty Brawijaya University Malang Indonesia

Facial emotion recognition is one of the artificial intelligence implementations used to recognize emotions based on data learned by computers. Unlike humans, who can recognize a person’s emotions directly, computers need several trainings procedures conducted by humans to be able to recognize a person’s emotions. Previous research has proposed various methods with deep learning and traditional machine learning approaches to classify emotions based on faces. Some studies obtained relatively high accuracy, but on evaluation by cross-validation, the results were much lower than the accuracy obtained. Therefore, this study proposes an approach using a modified MobileNetV2 deep learning architecture in the residual layer by adding a Convolutional Block Attention Module (CBAM) to improve accuracy and data generalization. This experiment uses the Karolinska Directional Emotional Faces (KDEF) public benchmark dataset. Preprocessing is done with image augmentation to enrich the training data by resizing, center cropping, random horizontal flipping, random affine, and random rotation. The proposed method is evaluated by 5-fold cross-validation and compared with MobileNetV2 without modification and state-of-the-art methods. Experimental results show that the proposed model outperform all comparative methods by achieving a 5 -fold cross-validation accuracy of 94.387%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Experiences with New Musical Instruments through Microphenomenology

Exploring Experiences with New Musical Instruments through M...

引用

International Conference on New Interfaces for Musical Expression, NIME 2022

作者： Reed, Courtney N. Nordmoen, Charlotte Martelloni, Andrea Lepri, Giacomo Robson, Nicole Zayas-Garin, Eevee Cotton, Kelsey Mice, Lia McPherson, Andrew School of Electronic Engineering & Computer Science Queen Mary University of London London United Kingdom Max Planck Institute for Informatics Saarland Informatics Campus Saarbrücken Germany KTH Royal Institute of Technology Stockholm Sweden

This paper introduces micro-phenomenology, a research discipline for exploring and uncovering the structures of lived experience, as a beneficial methodology for studying and evaluating interactions with digital musical instruments. Compared to other subjective methods, micro-phenomenology evokes and returns one to the moment of experience, allowing access to dimensions and observations which may not be recalled in reflection alone. We present a case study of five micro-phenomenological interviews conducted with musicians about their experiences with existing digital musical instruments. The interviews reveal deep, clear descriptions of different modalities of synchronic moments in interaction, especially in tactile connections and bodily sensations. We highlight the elements of interaction captured in these interviews which would not have been revealed otherwise and the importance of these elements in researching perception, understanding, interaction, and performance with digital musical instruments. © 2022, International Conference on New Interfaces for Musical Expression. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

Sustainable Solutions for Organ Donation and Procurement via Regional Collaboration System

Sustainable Solutions for Organ Donation and Procurement via...

引用

Mobile Computing and Sustainable informatics (ICMCSI), International Conference on

作者： Farzana Akter Mily Md Shamsul Arefin Department of Computer Science & Engineering Bangladesh University of Business and Technology Dhaka Bangladesh Department of Electrical & Electronic Engineering Bangladesh University of Business and Technology Dhaka Bangladesh

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

The severe shortage of organs requires the efficient management and collaboration of practices. Therefore, this paper introduces the Regional Collaboration System (RCS) to deal with this critical issue. The system aims at enhancing organ donation and procurement with the perspective of coordination of regional healthcare organizations. The primary purpose is to assist patients in finding suitable hospitals, donors, and doctors, in their region to carry out a seamless transplantation process. This system has been developed using Visual Studio 2022, SQL Server 2019 Express, and C# for a robust and scalable solution. Key features include an administrative panel, advanced search options, and the user interface to make it easy for administrators, patients, donors, and doctors to use. Moreover, the system also provides a medical history management platform that enables the patients to maintain a record of their history for future use via the administrative panel. This comprehensive approach is designed to improve transplant outcomes, minimize waiting times, and enhance organ availability. By effectively addressing the crisis in organ shortages, RCS holds a great potential to bring revolutionary changes in the existing structure of organ donation and transplantation, thereby saving more lives and hence fostering equality in access to health resources.

关键词： Procurement Visualization Collaboration Organizations User interfaces Organ transplantation History Servers informatics Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Blockchain based Secure System for the Internet of Drones (IoD) 6

Blockchain based Secure System for the Internet of Drones (I...

引用

6th International Conference on electronics, Communication and Aerospace Technology, ICECA 2022

作者： Maurya, Sudhanshu Rauthan, M.M.S. Verma, Rohan Ahmad, R. Badlishah Hemvati Nandan Bahuguna Garhwal University Department of Computer Science and Engineering Uttarakhand Srinagar India Universiti Malaysia Perlis Faculty of Electronic Engineering and Technology Perlis Malaysia

ISBN: (纸本)9781665482714

At present, drones are being used at a higher rate than ever. Frequently, they have been often used in military services. Therefore, it is the need of the hour to increase the smartness, privacy, and security of drones as they provide confidentiality and validity in the transmission of data. This research study has suggested and implemented a blockchain-based secure system for the internet of drones. It provides seamless authentication and registration for drones with better data storage security. The proposed method is evaluated on dummy drones to check the security and confidentiality of the system. © 2022 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

A Divide and Conquer Based Data Aggregation Technique for WBANs 4th

A Divide and Conquer Based Data Aggregation Technique for WB...

引用

4th International Conference on Advanced informatics for Computing Research, ICAICR 2020

作者： Roopali Kumar, Rakesh Department of Informatics Computer Science and Engineering NITTTR Chandigarh India Department of Computer Science and Engineering Central University of Haryana Mahendargarh India

ISBN: (纸本)9789811636523

WBANs monitor health data in an on demand and timely fashion and require effective communication of data from source to sink. In today’s tough times with pandemic taking its toll all over the globe, personalized data from smart wearable devices is empowering medical fraternity to make health care decisions with new insights. The latest wearable devices are capable of monitoring detailed physiological parameters, therefore promoting diagnosing patients from afar. The data transmission using wearable or implanted sensor nodes consume more energy and minimize network lifetime. Various solutions have been proposed by researchers to address issues such as interference, energy consumption, body movement, network lifetime, propagation delay and quality of services. However, issues still prevail in WBANs. In this paper, we have proposed a data aggregation technique using divide and conquer method which increases effectiveness of ubiquitous health care systems. The proposed data aggregation technique efficiently communicates data to the sink node, optimizes residual energy of sensor nodes, packet delivery ration, average delay and longevity of networks. The proposed technique reduces the number of packets to be transmitted by 28–29% and enhances network lifetime by 63% as compared to the other state-of-the-art techniques. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Analysis and Prediction of COVID-19 datasets using Machine Learning Algorithms 1

Analysis and Prediction of COVID-19 datasets using Machine L...

引用

1st International Conference on Electrical, electronics, Information and Communication Technologies, ICEEICT 2022

作者： Lasya, K. Lakshmi Lahari, D. Akarsha, R. Lavanya, A. Prakash, Kolla.Bhanu Tran, Duc-Tan Koneru Lakshmaiah Education Foundation Vaddeswaram Department of Computer Science and Engineering AP Vijayawada India Phenikaa University Faculty of Electrical and Electronic Engineering Hanoi Viet Nam

ISBN: (纸本)9781665436472

The devastating spread caused by Severe Acute Respiratory Disorder - Coronavirus (SARS-CoV-2) which is also known as COVID-2019 has brought global threat to our society. Every country is making immense efforts to stop the spread of the deadly disease through the use of finance, infrastructure and data sources, as well as protective devices, life-risk treatments, as well as other sources. Researchers studying artificial intelligence focus their skills to create mathematical models for studying the scourge of this disease using and shared data. In order to improve the wellbeing of our society. This article proposes using model of deep and machine-learning to understand its daily exponential behavior, as well as the prediction of the future impact of the COVID-2019 across nations using the live data of the Johns Hopkins dashboard © 2022 IEEE.

关键词： SARS

来源：评论

学校读者我要写书评

暂无评论

Self-Supervise Reinforcement Learning Method for Vacant Parking Space Detection Based on Task Consistency and Corrupted Rewards

引用

IEEE Transactions on Intelligent Transportation Systems 2024年第2期25卷 1346-1363页

作者： Nguyen, Manh-Hung Chao, Tzu-Yin Hsiao, Ching-Chun Li, Yung-Hui Huang, Ching-Chun Hcm University of Technology and Education Faculty of Electrical Electronic Engineering Ho Chi Minh City700000 Viet Nam National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300093 Taiwan Hon Hai Research Institute Ai Research Center New Taipei City114699 Taiwan

This paper proposes a novel task-consistency learning method that enables us to train a vacant space detection network (target task) based on the logic consistency with the semantic outcomes from a flow-based motion behavior classifier (source task) in a parking lot. Note that the source task can introduce false detection during task-consistency learning, which implies noisy rewards or supervision. The target network can be trained in a reinforcement learning setting by appropriately designing the reward mechanism upon semantic consistency. We also introduce a novel symmetric constraint to detect corrupted samples and reduce the effect of noisy rewards. Unlike conventional corrupted learning methods that use only training losses to identify corrupted samples, our symmetric constraint also explores the relationship among training samples to improve performance. Compared with conventional supervised detection methods, the main contribution of our work is the ability to learn a vacant space detector via semantic consistency rather than supervised labels. The dynamic learning property allows the proposed detector to be easily deployed and updated in various lots without heavy human loads. Experiments demonstrate that our noisy task consistency mechanism can be successfully applied to train a vacant space detector from scratch. © 2000-2011 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Remagnetization Strategies for Induction Machines Operating with Reduced Flux Levels

Remagnetization Strategies for Induction Machines Operating ...

引用

2022 International Conference on Electrical Machines, ICEM 2022

作者： Abouzeid, Ahmed F. Guerrero, Juan M. Vicente, Iban Muniategui, Iker Endemaño, Aitor Briz, Fernando The Department of Electrical Electronic and Computer Engineering University of Oviedo Gijón Spain The Department of Electrical Engineering Port-Said University Egypt The Department of Traction Systems Ingeteam Power Technology Zamudio Spain

ISBN: (数字)9781665414326

ISBN: (纸本)9781665414326

Induction Machines (IMs) drives are the preferred option for high-speed railway traction drives. Electric drives in this application can work for certain periods of time with light load levels. It is possible in this case to decrease the flux level to reduce the stator current and consequently both joule and hysteresis losses. A drawback of this approach is that if a torque increase is demanded, the machine must be firstly remagnetized. Remagnetization time is determined by the rotor time constant and the applied magnetizing current. Due to the relatively large values of the rotor time constant, fast torque changes are not feasible, which eventually penalizes the dynamic response of the drive. This paper presents strategies for the remagnetization of Induction Machines. Though proposed methods are primarily intended for railways traction, they can be easily extended to other uses of IM drives. © 2022 IEEE.

关键词： Induction machine

来源：评论

学校读者我要写书评

暂无评论

Multi-Criteria Prediction Mechanism for Vehicular Wi-Fi Offloading

引用

computers, Materials & Continua 2021年第11期69卷 2313-2337页

作者： Mahmoud Alawi Raed Alsaqour Abdi Abdalla Maha Abdelhaq Mueen Uddin Department of Computer Engineering and IT Faculty of EngineeringZanzibar UniversityZanzibarTanzania Department of Information Technology College of Computing and InformaticsSaudi Electronic UniversityRiyadh93499Saudi Arabia Department of Electronics and Telecommunications Engineering College of ICTUniversity of Dar es SalaamTanzania Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadh84428Saudi Arabia Faculty of Science Universiti Brunei DarussalamNegara Brunei Darussalam

The growing demands of vehicular network applications,which have diverse networking and multimedia capabilities that passengers use while traveling,cause an overload of cellular *** scenario affects the quality of service(QoS)of vehicle and non-vehicle ***,wireless fidelity access points Wi-Fi access point(AP)and fourth generation long-term evolution advanced(4G LTE-A)networks are broadly ***-Fi APs can be utilized by vehicle users to stabilize 4G LTE-A ***,utilizing the opportunistic Wi-Fi APs to offload the 4G LTE-A networks in a vehicular ad hoc network environment is a relatively difficult *** condition is due to the short coverage of Wi-Fi APs and weak deployment strategies of *** studies have proposed that offloading mechanisms depend on the historical Wi-Fi connection patterns observed by an interest vehicle in making an offloading ***,depending solely on the historical connection patterns affects the prediction accuracy and offloading ratio of most existing mechanisms even when AP location information is *** present study proposed a multi-criteria wireless availability prediction(MWAP)mechanism,which utilizes historical connection patterns,historical data rate information,and vehicular trajectory computation to predict the next available AP and its expected data capacity in making offloading *** proposed mechanism is decentralized,where each vehicle makes the prediction by *** characteristic helps the vehicle users make a proactive offloading decision that maintains the QoS for different applications.A simulation utilizing MATLAB was conducted to evaluate the performance of the proposed mechanism and benchmark it with related state-of-the-art mechanisms.A comparison was made based on the prediction error and offloading ratio of the proposed mechanism in several *** MWAP mechanism exhibited a lower prediction error(i.e.,below 20%)and higher offloading rat

关键词： Vehicular network markov predictor 4G LTE-A Wi-Fi offloading prediction model heterogeneous network

来源：评论

学校读者我要写书评

暂无评论

Smart Fibers for Energy Transformation and Storing

Smart Fibers for Energy Transformation and Storing

引用

2023 Advances in Science and engineering Technology International Conferences, ASET 2023

作者： Al Jaghoub, Haya Rami Almallahi, Maryam Nooman Obaideen, Khaled Moustafa, Asmaa Al Nassan, Wafaa Ramadan, Omar H. Bonny, Talal University of Sharjah Industrial Engineering and Engineering Management Sharjah United Arab Emirates United Arab Emirates University Department of Mechanical and Aerospace Engineering Al Ain United Arab Emirates Rise University of Sharjah Sustainable Energy & Power Systems Research Centre Sharjah United Arab Emirates Ahram Canadian University Faculty of Engineering Giza Egypt University of Sharjah Department of Computer Engineering Sharjah United Arab Emirates University of Sharjah Department of Electrical and Electronic Engineering Sharjah United Arab Emirates

ISBN: (纸本)9781665454742

Fibers have been a crucial element in the development of textiles. This is attributed to the numerous advantages fibers provide, including the production of stronger and long-lasting cloths. Moreover, synthetic fibers are perceived as highly flexible and cost-effective materials. Due to the expansion in portable and wearable devices, the creation of intelligent and versatile fibers has been significantly boosted. Additionally, due to the intrinsic materials of fibers, such as semiconductors and electroactive materials, it is feasible to create fiber electronics. As a result, this paper focuses on fiber electronics and especially the sources of energy supply for these fibers. This paper initially starts to introduce the development of functional fibers in energy conversion and storage, with an emphasis on supercapacitors, solar cells, and nanogenerator batteries. Thereafter, the significance of fiber-shaped energy conversion and smart structural design for storage devices is examined. © 2023 IEEE.

关键词： Supercapacitor

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：