检索结果-内蒙古大学图书馆

Monitoring of Heart and Respiration Rate Using a 3D Knitted T-shirt with Textile-based Electrodes

IFAC-PapersOnLine 2024年第30期58卷 49-54页

作者： Nada Al-azzawi Irem Yunculer Asli Tuncay Atalay Ozgur Atalay Gökhan Ince Faculty of Computer and Informatics Engineering Computer Engineering Department Istanbul Technical University Istanbul 34469 Turkey Faculty of Textile Technologies and Design Textile Engineering Department Istanbul Technical University Istanbul 34437 Turkey

The emergence of e-textiles has facilitated impressive growth in the field of wearable technologies in recent years. Textile-based electrodes enabled long-period electrocardiogram monitoring within the health care field as they are less irritant to the skin and can be naturally embedded into the clothes. Beyond the specific health-oriented applications, physiological signals monitoring is also beneficial during other activities such as daily activities and sports. In this work, a system of a knitted t-shirt embedded with textile electrodes that targets measuring heart rate and respiration rate during various positions and activities is created. The performance of the implemented system is benchmarked against the performance of an off-the-shelf product using root mean square error. It has been shown that the proposed system can achieve good performance with heart rate respiration rate values close to that of the benchmark device.

关键词： E-textile technology smart t-shirt wearable technology heart rate monitoring ECG ECG derived respiration

来源：评论

学校读者我要写书评

暂无评论

A Mixed Reality Interface for Tactical Data Management in Geographic Information Systems 7

A Mixed Reality Interface for Tactical Data Management in Ge...

引用

7th International Conference on computer Science and engineering, UBMK 2022

作者： Keskin, Fatih Ince, Gokhan Istanbul Technical University Faculty of Computer and Informatics Engineering Istanbul Turkey Aselsan A.Ş.

ISBN: (数字)9781665470100

ISBN: (纸本)9781665470100

The requirements of security systems evolve as the complexity of risks and dangers increases in modern times. Due to the nature of security operations, the operator's stress and cognitive load increase, as the operators must strictly report events that occur in certain situations. In this paper, we present an alternative interface design for a command and control software traditionally used in regional security systems. We propose a mixed reality application that uses holograms and superimposition methods to enhance the operator's experience. The proposed interface is tested on four different security operation scenarios which are operational planning, unit tracking, surveillance, and alarm detection. According to the results of applied questionnaires such as NASA TLX, PSSUQ, and SUS, it has been observed that the created interface is more informative and more usable compared to the traditional command and control software in terms of security operations. © 2022 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation of Morphological Brain Network Using Multi-variate Normal Distribution 7

Data Augmentation of Morphological Brain Network Using Multi...

引用

7th International Conference on computer Science and engineering, UBMK 2022

作者： Celik, Mustafa Rekik, Islem Istanbul Technical University Basira Lab Faculty of Computer and Informatics Engineering Istanbul Turkey

ISBN: (数字)9781665470100

ISBN: (纸本)9781665470100

Multi-view Brain Networks (MBNs) have made a significant contribution to the diagnosis of neurological disorders using computers. MBNs can boost the classification accuracy of neurological disorders such as Alzheimer's disease (AD) by capturing diverse characteristics from multiple perspectives of a population. MBNs provide rich data diversity and better generalization for the classifier models, but the classifiers require large-sized dataset to avoid being over-trained. Moreover, it is challenging to collect clinical data because it is scarce and expensive. In this work, we present a method that augments fake (i.e., synthetic) data samples to boost the neurological disorder classification models. It has been shown that the classifiers trained on our synthetic samples achieve better results than those trained on synthetic samples of traditional data augmentation techniques. © 2022 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

QoS-Aware Load Balancing Scheme in Dense Wi-Fi 6 WLANs 1

引用

8th EAI International Conference on Industrial Networks and Intelligent Systems, INISCOM 2022

作者： Ak, Elif Canberk, Berk Computer Engineering Department Istanbul Technical University Istanbul Turkey Artificial Intelligence and Data Engineering Department Computer and Informatics Faculty Istanbul Technical University Istanbul Turkey

ISBN: (数字)9783031088780

ISBN: (纸本)9783031088773

Nowadays, increasing mobile and wireless usage demand accelerates new enhancements on IEEE 802.11 family to provide concurrent transmission and high efficiency. Thus, IEEE 802.11ax is released with the aim to improve overall throughput in dense WLANs considering the overlapping channel interference. However, the current WLANs suffer from uneven load distribution among the Access Points (AP). Because a station simply connects to the AP with the highest received signal strength indication (RSSI) in a legacy association way. And RSSI might not be the only criteria in the current WLANs due to the variety of application requirements and high date rates. Therefore, we propose a complete association scheme called Access Controller (AC) to manage admission, association, and adaptive carrier sensitivity control as a whole. The station from an overloaded AP is handed to a less loaded AP by considering various crucial metrics such as packet delivery ratio, fairness, RSSI, throughput, and round trip time. After effective load balancing, we adaptively tune the carrier sensitivity threshold to enhance concurrent transmission in IEEE 802.11ax WLANs. The results show that the proposed AC scheme outperforms in terms of fairness and per-station throughput in dense WiFi6 scenarios with over 500 stations. © 2022, ICST Institute for computer Sciences, Social informatics and Telecommunications engineering.

关键词： Wireless local area networks (WLAN)

来源：评论

学校读者我要写书评

暂无评论

An Augmented Reality Environment for Testing Cockpit Display Systems 7th

An Augmented Reality Environment for Testing Cockpit Displa...

引用

7th International Conference on computer-Human Interaction Research and Applications, CHIRA 2023

作者： Potur, Caner İnce, Gökhan MGEO Test and Verification Directorate ASELSAN Inc. Ankara Turkey Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

ISBN: (纸本)9783031493676

In the avionics industry, software test automation is a crucial component, as it plays a significant role in accelerating the development process. Since all automation systems are error-prone, the automation systems that affect flight safety should be supervised by humans as they must be reliable. In this study, an augmented reality based software verification system is designed to observe the visual verification of cockpit screens and detect possible automation errors. In the designed system, an observer can instantly see the test steps and automation results using an augmented reality headset as a hologram on the cockpit screen and can report the errors they observe in test automation. The performance of the proposed system was analyzed qualitatively and quantitatively. The experimental results demonstrated that the use of augmented reality in cockpit display verification systems accelerated the testing process, reduced users’ cognitive load, and improved the system’s usability. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

DO DEEP NEURAL NETWORKS UTILIZE THE WEIGHT SPACE EFFICIENTLY?

arXiv

引用

arXiv 2024年

作者： Koyun, Onur Can Töreyin, Behçet Ugur Department of Computer Engineering Faculty of Computer and Informatics Istanbul Technical University Istanbul Turkey Department of Artificial Intelligence and Data Engineering Faculty of Computer and Informatics Istanbul Technical University Istanbul Turkey

Deep learning models like Transformers and Convolutional Neural Networks (CNNs) have revolutionized various domains, but their parameter-intensive nature hampers deployment in resource-constrained settings. In this paper, we introduce a novel concept utilizes column space and row space of weight matrices, which allows for a substantial reduction in model parameters without compromising performance. Leveraging this paradigm, we achieve parameter-efficient deep learning models.. Our approach applies to both Bottleneck and Attention layers, effectively halving the parameters while incurring only minor performance degradation. Extensive experiments conducted on the ImageNet dataset with ViT and ResNet50 demonstrate the effectiveness of our method, showcasing competitive performance when compared to traditional models. This approach not only addresses the pressing demand for parameter efficient deep learning solutions but also holds great promise for practical deployment in real-world scenarios. © 2024, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Evaluating Gaze Detection for Children with Autism Using the ChildPlay-R Dataset

Evaluating Gaze Detection for Children with Autism Using the...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Nursena Boluk Hatice Kose Department of Computer Engineering Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey Department of Artificial Intelligence and Data Engineering Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

ISBN: (数字)9798350394948

ISBN: (纸本)9798350394955

This study focuses on detecting two-dimensional (2D) gaze points in interactions between children both with and without autism and adults. Within the scope of this objective, a novel subset called ChildPlay-R has been created based on the open-source ChildPlay dataset. This new dataset includes explicitly the interactions of children with and without autism with adults in similar uncontrolled environments and relevant 2D gaze points. Moreover, the analyses using the Modified Spatiotemporal Gaze Detection (M-STGD) model, compared to the traditional Spatiotemporal Gaze Architecture (STGA), reveal significant improvements in the Area Under the Curve values and out-of-sample precision. These advancements indicate the M-STGD model's potential to provide a deeper understanding of the social engagement patterns of children with autism. This study contributes to the automatic detection of 2D gaze points in social interactions and supports the social development of children with autism.

关键词： Autism Analytical models Adaptation models Accuracy Two-dimensional displays Face recognition Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Application of Vector Based Memory Prompt engineering Using Personality Psychology in Language Model of Conservational Interfaces

Application of Vector Based Memory Prompt Engineering Using ...

引用

IEEE Signal Processing and Communications Applications (SIU)

作者： Evren Dağlarlı Erke Arıbaş Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

ISBN: (数字)9798350388961

ISBN: (纸本)9798350388978

The psychology of personality is a part of psychology analyzing personality and its diversity for the people. It’s purpose is to depict how individuals are pesonally various due to psychological motives. Personality type refers to the psychological classification of people into various classes. Personality traits are distinguished from personality types, that come in various degrees. Many theories related to personality are available, but most of them include several and sometimes many sub theories. Constructing the Myers–Briggs Type Indicator (MBTI) and The Big Five (BF) personality traits is crucial in personality pyscology. Our objective is twofold. Firstly, it is planned to develop a correlation model between MBTI and BF personality traits and apply it to conversational interfaces’ language models. Secondly, it is aimed to extend this approach to time-sensitive design by utilizing fixed-effect analysis, which is particularly useful when analyzing data from multiple individuals across various time points. The results show distinct observations, as seen in popular language models like ChatGPT.

关键词： Correlation Psychology Signal processing Chatbots Vectors Prompt engineering

来源：评论

学校读者我要写书评

暂无评论

Design of Fixed Wing Autonomous Figting UAV

Design of Fixed Wing Autonomous Figting UAV

引用

International Artificial Intelligence and Data Processing Symposium (IDAP)

作者： Evren Dağlarlı Erke Arıbaş Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey

ISBN: (数字)9798331531492

ISBN: (纸本)9798331531508

In this paper, the design of fixed-wing autonomous UAVs is aimed. The goal is to lock onto rival UAVs during the competition, avoid these locks with aggressive maneuvers, and perform the designated tasks autonomously. Autonomous Aircraft System; It consists of a ground control station, ground antenna, controller, and autonomously operating aircraft components. In the declaration, the system’s performance features, mechanical and aerodynamic design, flight control systems and communication systems are detailed. In addition, the UAV’s autonomous locking, image processing and task performance capabilities are presented, supported by tests and analysis. The final system architecture and performance analysis results show that the UAV meets the design requirements.

关键词： Communication systems Image processing Systems architecture Process control Autonomous aerial vehicles Data processing Control systems Performance analysis Aircraft Aerospace control

来源：评论

学校读者我要写书评

暂无评论

DEEP NEURAL NETWORKS AS A TOOL TO ESTIMATION OF COSMIC RADIATION DOSE RECEIVED ON FLIGHT

引用

UPB Scientific Bulletin, Series A: Applied Mathematics and Physics 2022年第2期84卷 187-202页

作者： Yilmaz, Ayberk Yilmaz Alan, Hatice Faydasiçok, Özlem Amon Susam, Lidya Şamli, Rüya Akkuş, Baki Erol, Aydın Güdekli, Ertan İnci, Çisem İlayda Emirhan, Mehmet Erhan Dept.of Physics Faculty of Science Istanbul University Turkey Institute of Accelerator Technologies Ankara University Ankara Turkey Dept. of Mathematics Faculty of Science Istanbul University Istanbul Turkey Department of Computer Engineering Istanbul University-Cerrahpasa Istanbul Turkey Dept. of Physics Yıldız Technical University-Davutpasa Turkey

Cosmic radiation is an ionizing radiation produced when primary protons and α particles from outside the solar system interact with components of the earth's atmosphere. Cosmic radiation is a general term for radiation produced by high-energy subatomic particles from outer space and, more importantly, secondary (ionizing) radiation from the sun and high-energy subatomic particles that react with nitrogen, oxygen, and other elements in the atmosphere. In this study, Deep Neural Networks (DNNs) via Multilayer Perceptrons (MLPs) were used to estimate the radiation doses due to cosmic radiation for different domestic flights related with istanbul and Ankara Airports in Turkey. Dose values were calculated with the CARI-7A program and DNNs. The parameters for calculating dose rates are latitude, longitude and dept.. The results obtained compared and discussed. © 2022, Politechnica university of Bucharest. All rights reserved.

关键词： Deep neural networks

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：