检索结果-内蒙古大学图书馆

The development of assisted- visually impaired people robot in the indoor environment based on deep learning

Multimedia Tools and Applications 2024年第3期83卷 6555-6578页

作者： Hsieh, Yi-Zeng Ku, Xiang-Long Lin, Shih-Syun Department of Electrical Engineering National Taiwan University of Science and Technology Taipei City106 Taiwan Department of Computer Science and Engineering National Taiwan Ocean University Keelung City Taiwan

The indoor positioning for visually impaired people has influence on their daily life in unknown indoor environment. This study designs the robot that can assist the blind walking safety and navigate in indoor environment by a single camera. The sense classification is proposed to position the blind in indoor environment by proposed convolutional neural network framework and integrate the semantic segmentation to find the road surface through a depth camera to guide the blind walking. The proposed vision-based sense classification method is compared with the traditional WiFi triangular-positioning method, and the average error of x-y coordinate position result as (9.25,3.65) is better. From the experiment, the designed robot can help the visually impaired people to indoor navigation in unknown indoor environment. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

IoT Revolution: Exploring the Impact of loT Based Embedded System Technology on Healthcare, Agriculture and Business Startups in Smart Village 2

IoT Revolution: Exploring the Impact of loT Based Embedded S...

引用

2nd International Conference on Power, electrical, Electronics and Industrial Applications, PEEIACON 2024

作者： Gupta, Rittik Das Debnath, Sourav Gupta, Riva Das Chowdhury, Mrithika Department of Electrical and Electronic Engineering Dhaka Bangladesh Department of Electrical and Electronic Engineering Dhaka Bangladesh Department of Economics Chattogram Bangladesh Department of Computer Science and Engineering Chattogram Bangladesh

ISBN: (纸本)9798331517984

The paper illustrates the development of an integrated Internet of Things (IoT) gadget with smart agricultural and healthcare systems, as well as the possibility for their startup firms to build a smart village. The system comprises a carefully designed front end powered by Arduino and NodeMCU microcontrollers. It has a number of high-precision sensors, including the DS18B20 for body temperature, the Max30102 for heart rate and oxygen level, the FC-28 for soil moisture, the DHT-11 for temperature of the environment and maintaining humidity, the dust sensor for air quality detection, and calibrated MQ sensors for gas detection of CH4, H2S, and NH3. The back end simply interfaces with the Blynk application, ThingSpeak, and Google spreadsheet as data storage for detailed data visualization and real-time monitoring via smart devices. A rigorous sensor validation process that was carried out, indicating that this device's measurements align statistically with those of commercially available sensors, as validated by paired sample t-tests, Q-Q plot and descriptive data analysis in SPSS software. The prototypic data analysis system is also a key aspect of this research. Our proposed research not only supports the usefulness of our technology, but also gives a direction for future users to correctly evaluate their data. The integrated IoT device exhibits its utilization for smart healthcare and precision agriculture systems for the purpose of smart village. The combination of IoT along with startup enterprises is extending unique notions that could improve global food sustainability and individual well-being. This paper displays the potential for startups to develop innovative IoT, health, and agriculture solutions that will shape a future where technology improves lives and ensures food security. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

Visual Question Answering with Cascade of Self- and Co-Attention Blocks 27th

Visual Question Answering with Cascade of Self- and Co-At...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Mishra, Aakansha Anand, Ashish Guha, Prithwijit Department of Computer Science and Engineering IIT Guwahati Guwahati India Department of Electrical Engineering IIT Guwahati Guwahati India

ISBN: (纸本)9783031784941

Recent advancements in Visual Question Answering (VQA) have been driven by the integration of complex attention mechanisms. This work introduces a novel approach aimed at enhancing multi-modal representations through dense interactions between visual and textual inputs in an alternating fashion. The proposed model features an attention framework that incorporates both self-attention and co-attention mechanisms, strategically applied to image and text modalities. Self-attention modules capture contextual dependencies among objects in images and words in questions, crucial for accurate inference of answers. Meanwhile, co-attention mechanisms facilitate effective cross-modal interactions between images and text. To extract fine-grained information from both modalities, we introduce a Cascade of Self- and Co-Attention blocks (CSCA). This architecture is evaluated extensively on prominent benchmarks including VQA2.0, TDIUC, and GQA datasets. Experimental results, including comprehensive ablation studies, highlight the effectiveness of the model’s key components and the cascading nature of attention mechanisms in enhancing performance across diverse VQA tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

PC-DeepNet: A GNSS Positioning Error Minimization Framework Using Permutation-Invariant Deep Neural Network

引用

IEEE Sensors Journal 2025年第11期25卷 20764-20777页

作者： Humayun Kabir, M. Hasan, Md. Ali Islam, Md. Shafiqul Ko, Kyeongjun Shin, Wonjae Islamic University Department of Electrical and Electronic Engineering Kushtia7003 Bangladesh Korea University School of Electrical Engineering Seoul02841 Korea Republic of Bangladesh University of Business and Technology Department of Computer Science and Engineering Dhaka1216 Bangladesh Hongik University School of Electronics and Electrical Engineering Seoul04066 Korea Republic of

Global navigation satellite systems (GNSS) face significant challenges in urban and sub-urban areas due to non-line-of-sight (NLOS) propagation, multipath effects, and low received power levels, resulting in highly non-linear and non-Gaussian measurement error distributions. In light of this, conventional model-based positioning approaches, which rely on Gaussian error approximations, struggle to achieve precise localization under these conditions. To overcome these challenges, we put forth a novel learning-based framework, PC-DeepNet, that employs a permutation-invariant (PI) deep neural network (DNN) to estimate position corrections (PC). This approach is designed to ensure robustness against changes in the number and/or order of visible satellite measurements, a common issue in GNSS systems, while leveraging NLOS and multipath indicators as features to enhance positioning accuracy in challenging urban and sub-urban environments. To validate the performance of the proposed framework, we compare the positioning error with state-of-the-art model-based and learning-based positioning methods using two publicly available datasets. The results confirm that proposed PC-DeepNet achieves superior accuracy than existing model-based and learning-based methods while exhibiting lower computational complexity compared to previous learning-based approaches. © 2025 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Analyzing energy efficiency of flying objects in Wireless Sensor and Mobile Ad Hoc Networks 5

Analyzing energy efficiency of flying objects in Wireless Se...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Siddiqui, Shams Tabrez Ahmad, Adeel Ahmad, Jorair Haseebuddin, Mohammad Siddiqui, Alighazi Salim, Abu Jazan University College of Engineering and Computer Science Department of Computer Science Jazan Saudi Arabia Jazan University College of Engineering and Computer Science Department of Electrical and Electronics Engineering Jazan Saudi Arabia

ISBN: (纸本)9798350351378

The convergence of flying objects, Mobile Ad Hoc Networks (MANETs), and Wireless Sensor Networks (WSNs) has been made feasible by the widespread proliferation of wireless communication technology. This study delves into the historical development and significant achievements of WSNs and MANETs, with a focus on the incorporation of drones and UAVs to enhance network capabilities. Our main goals involve conducting thorough assessments of communication protocols, routing algorithms, and network architectures in the presence of flying objects. Our particular emphasis is on maximizing energy efficiency. Examining the dynamics of flying objects in WSNs and MANETs, this analysis delves into the various challenges and opportunities that arise. A special emphasis is placed on the management of mobility, the optimization of energy usage, and the effectiveness of routing protocols. The study explores existing protocols such as LEACH, AODV and OLSR, highlighting their benefits and challenges in flying objects. A comparative analysis evaluates adapted protocols based on metrics such as energy efficiency, latency, and reliability. © 2024 IEEE.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing wireless sensing via a target-mounted intelligent reflecting surface

引用

National science Review 2023年第8期10卷 13-14页

作者： Xiaodan Shao Rui Zhang School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Department of Electrical and Computer Engineering National University of Singapore

An intelligent reflecting surface(IRS),or its various equivalents such as an reconfigurable intelligent surface(RIS), is an emerging technology to control radio signal propagation in wireless systems. An IRS is a digitally controlled metasurface consisting of a large number of passive reflecting elements, which are connected to a smart controller to enable dynamic adjustments of the amplitude and/or phase of the incident signal on each element independently [1].

关键词：

来源：评论

学校读者我要写书评

暂无评论

Build to Win: electrical Hardware Opportunities for STEM Education 14

Build to Win: Electrical Hardware Opportunities for STEM Edu...

引用

14th IEEE Integrated STEM Education Conference, ISEC 2024

作者： Monagle, Daniel Ponce, Eric A. Leeb, Steven B. Saathoff, Erik K. Brooks, Dylan E. Krause, Thomas C. Green, Daisy H. Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science United States University of Hawai'i Department of Electrical and Computer Engineering Manoa United States

ISBN: (纸本)9798350352801

engineering outreach and introductory courses are essential for motivating and training the next generation of capable engineers. Accessibility and portability of the infrastructure for a STEM course is critical for spreading STEM education and motivation efforts. The ubiquity of student personal computers and laptops provides a convenient platform for introducing computer programming, but the relatively cumbersome equipment deemed necessary for a hands-on electronics learning environment contributes to the lack of electronic circuit hardware exposure for many K-12 students and university undergraduates. This paper presents the relatively low-cost, versatile, electronics platform we have developed at MIT upon which our new, hands-on introductory STEM electrical engineering course has been built and taught in recent years. This paper focuses its discussion on the power supply and measurement systems we have produced that allow students and instructors to engage in hands-on electric circuit exercises and projects without the requirement for expensive laboratory infrastructure. Example demonstrations of introductory laboratory exercises using our platform are shown. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Analyze and Construction of a Photovoltaic (PV) Power Plant Connected to the Grid to Produce Maximum Power on the Roof of the Building 9

Analyze and Construction of a Photovoltaic (PV) Power Plant ...

引用

9th International Conference on Technology and Energy Management, ICTEM 2024

作者： Karimi, Hamed Siadatan, Alireza Sepehrinour, Maryam Chaharmahali, Ehsan Shahid Beheshti University Department of Electrical and Computer Science Tehran Iran York University Department of Electrical and Computer Science Toronto Canada Western Kentucky University Department of Electrical Engineering Bowling GreenKY United States Science and Culture University Department of Electrical Engineering Tehran Iran

ISBN: (纸本)9798350329797

This paper is for technical studies and optimal selection for the angle of the panels and the feasibility of building a 20 kW power plant connected to the grid in the electricity distribution company of Tehran province with geographic coordinates of 1181 m above sea level, longitude and latitude 35° 41' 29'', 51° 26' 53'',taking into account the lack of shadow conditions and selecting the back-to-back distance in the rows of each panel for ease of maintenance and repairs and absorbing the most sunlight and producing it by photovoltaic arrays into energy and injecting it to the national grid. Also, the correct selection of electrical equipment such as inverter, panel, the optimal selection of the voltage produced by the strings compared to the working voltage of the inverter, which is one of the most important parts of the construction of this power *** power plant produces 35.920 MWh/yr of electricity annually and has reduced greenhouse gas emissions by 3875 Kg per month. Therefore, it can be effective in encouraging investment in the construction of these small power plants in the residential sector. and its results and the amount of production of this power plant during one year show the optimal design and construction of this solar site. © 2024 IEEE.

关键词： Solar power generation

来源：评论

学校读者我要写书评

暂无评论

Exploring Genetic Programming in Image Processing: Challenges and Enhanced Techniques 19

Exploring Genetic Programming in Image Processing: Challenge...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Chang, Feng-Cheng Huang, Hsiang-Cheh Department of Computer Science and Information Engineering Tamkang University Taiwan Department of Electrical Engineering National University of Kaohsiung Taiwan

ISBN: (纸本)9798331507817

In recent years, the advancement of AI has been primarily driven by neural networks, which, despite their success, pose challenges in terms of explainability and high-power consumption. Genetic Programming (GP) offers an interpretable alternative, although its complexity has limited its practical application. This paper explores the potential of GP through experiments on a simple image filtering task, aiming to understand its properties and limitations. We also investigate the integration of transformer concepts into the GP process. Preliminary results suggest that while GP faces convergence challenges, the introduction of symbolic transformers may enhance its effectiveness in image processing tasks. These findings open up new possibilities for optimizing GP in future applications. © 2025 IEEE.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Fair Probabilistic Multi-Armed Bandit With Applications to Network Optimization

IEEE Transactions on Machine Learning in Communications and ...

引用

IEEE Transactions on Machine Learning in Communications and Networking 2024年 2卷 994-1016页

作者： Guo, Zhiwu Zhang, Chicheng Li, Ming Krunz, Marwan The University of Arizona Department of Electrical and Computer Engineering TucsonAZ87521 United States The University of Arizona Department of Computer Science TucsonAZ85721 United States

Online learning, particularly Multi-Armed Bandit (MAB) algorithms, has been extensively adopted in various real-world networking applications. In certain applications, such as fair heterogeneous networks coexistence, multiple links (individual arms) are selected in each round, and the throughputs (rewards) of these arms depend on the chosen set of links. Additionally, ensuring fairness among individual arms is a critical objective. However, existing MAB algorithms are unsuitable for these applications due to different models and assumptions. In this paper, we introduce a new fair probabilistic MAB (FP-MAB) problem aimed at either maximizing the minimum reward for all arms or maximizing the total reward while imposing a fairness constraint that guarantees a minimum selection fraction for each arm. In FP-MAB, the learning agent probabilistically selects a meta-arm, which is associated with one or multiple individual arms in each decision round. To address the FP-MAB problem, we propose two algorithms: Fair Probabilistic Explore-Then-Commit (FP-ETC) and Fair Probabilistic Optimism In the Face of Uncertainty (FP-OFU). We also introduce a novel concept of regret in the context of the max-min fairness objective. We analyze the performance of FP-ETC and FP-OFU in terms of the upper bound of average regret and average constraint violation. Simulation results demonstrate that FP-ETC and FP-OFU achieve lower regrets (or higher objective values) under the same fairness requirements compared to existing MAB algorithms. © 2024 The Authors.

关键词： Wireless sensor 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：