检索结果-内蒙古大学图书馆

International Conference on Advanced Robotics (ICAR)

作者： Nikolaos Stathoulopoulos Emanuele Pagliari Luca Davoli George Nikolakopoulos Department of Computer Electrical and Space Engineering Robotics and AI Group Luleå University of Technology Luleå Sweden Department of Engineering and Architecture Internet of Things (IoT) Lab University of Parma Parma Italy

This paper presents a framework addressing the challenge of global localization in autonomous mobile robotics by integrating LiDAR-based descriptors and Wi-Fi finger-printing in a pre-mapped environment. This is motivated by the increasing demand for reliable localization in complex scenarios, such as urban areas or underground mines, requiring robust systems able to overcome limitations faced by traditional Global Navigation Satellite System (GNSS)-based localization methods. By leveraging the complementary strengths of LiDAR and Wi-Fi sensors used to generate predictions and evaluate the confidence of each prediction as an indicator of potential degradation, we propose a redundancy-based approach that enhances the system's overall robustness and accuracy. The proposed framework allows independent operation of the LiDAR and Wi-Fi sensors, ensuring system redundancy. By combining the predictions while considering their confidence levels, we achieve enhanced and consistent performance in localization tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Train with Automatic Functioning based on IoT with Solar Energy Source

A Train with Automatic Functioning based on IoT with Solar E...

引用

2023 International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2023

作者： Padmakala, S. Alkawak, Omar A. Reddy, G. Vidya Sagar Narendranathan, S.K. Muthuraman, M.S. Sendilvelan, S. Saveetha School of Engineering Simats Department of Computer Science and Engineering Tamil Nadu Chennai India Al-Mustaqbal University College Department of Air Conditioning and Refrigeration Technical Engineering Babil Hilla Iraq School of Architecture Koneru Lakshmaiah Educational Foundation Andhra Pradesh Guntur India Agni College of Technology Department of Mechanical Engineering Tamil Nadu Chennai India Psna College of Engineering and Technology Department of Mathematics Tamil Nadu Dindigul India Dr. M.G.R Educational and Research Institute Department of Mechanical Engineering Tamil Nadu Chennai India

ISBN: (纸本)9781665474511

The railway industry is one of the most sustainable modes of transport. To reduce the carbon footprints, renewable energy sources are initiated. The proposal of attaching solar panels to railway sleepers, smart garbage bin, lighting, automatic closing and opening of doors that are accompanied with real time monitoring system with multiple technologies. Among the multiple technology the Internet of Things (IoT) plays a significant role by sending information and monitoring the overall functions. The solar energy obtained is used to generate electricity and further they are stored in battery for future usage. © 2023 IEEE.

关键词： Carbon footprint

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Networks and Efficiency in High-Dimensional EEG Classification 1st

Recurrent Neural Networks and Efficiency in High-Dimensional...

引用

1st International Conference on Bioengineering and Biomedical Signal and Image Processing, BIOMESIP 2021

作者： León, Javier Escobar, Juan José González, Jesús Ortega, Julio Arrabal-Campos, Francisco Manuel Ortiz, Andrés Damas, Miguel Department of Computer Architecture and Technology CITIC University of Granada Granada Spain Department of Engineering University of Almería Almería Spain Department of Communications Engineering University of Málaga Málaga Spain

ISBN: (纸本)9783030881627

The performance of neural networks has granted deep learning a place at the forefront of machine learning in the last decade. Although these models are computationally intensive, their advantage is recognized in a wide array of applications. Nonetheless, the large amount of learnable parameters in neural networks can be a disadvantage for small and high-dimensional datasets. In this context, the relationship between solution quality and model complexity gains significance due to overfitting concerns. This is precisely the case of Electroencephalography (EEG), where the data consists in relatively few patterns obtained from multiple electrode readings. In this paper, we take a look at two widely-known types of Recurrent Neural Networks (RNNs), namely Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), which are evaluated on three EEG Motor Imagery (MI) datasets by measuring not only classification accuracy, but also time and energy consumption. Although the results are not entirely competitive with the state-of-the-art in the datasets considered, the interaction that occurs between the size of the networks and their accuracy provides us with valuable insight about network structure design in the context of the curse of dimensionality. © 2021, Springer Nature Switzerland AG.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

ANALYSIS OF CONCRETE CRACKS AND FATIGUE IN SMART CITIES USING YOLOV3

ANALYSIS OF CONCRETE CRACKS AND FATIGUE IN SMART CITIES USIN...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering, RMKMATE 2023

作者： Archana, U. Sharma, Sarvdaman Singh, Sitesh Kumar Sureshkumar, R. Senthilkumar, P. Harish Babu, T. Department of Computer Science and Design R.M.K. Engineering College Chennai India Department of Civil Engineering University Institute of Engineering and Technology University of Jammu Jammu & Kashmir India Department of Civil Engineering Wollega University Oromia Nekemte Ethiopia Department of Electronics and Communication Engineering Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Chennai India KL School of Architecture Koneru Lakshmaiah Education Foundation Greenfield Vaddeswaram Andhra Pradesh Guntur India Department of Electrical and Electronics Engineering Sethu Institute of Technology Tamilnadu India

ISBN: (纸本)9798350305708

This study focuses on the application of the YOLOv3 (You Only Look Once version 3) object detection algorithm for the analysis of concrete cracks and fatigue within Smart Cities. Concrete infrastructure plays a crucial role in urban environments, and its structural integrity is paramount for ensuring public safety and sustainable development. The proposed approach utilizes YOLOv3 to identify and localize instances of concrete cracks and signs of fatigue in images and videos captured from various urban settings. By leveraging deep learning techniques, this research aims to enhance the efficiency and accuracy of monitoring and maintaining concrete structures, contributing to the overall resilience and longevity of Smart Cities. The findings of this study present valuable insights into the potential of utilizing advanced computer vision methods for proactive infrastructure management in the urban landscape. © 2023 IEEE.

关键词： Concrete cracks Fatigue analysis Infrastructure monitoring Smart Cities YOLOv3

来源：评论

学校读者我要写书评

暂无评论

Side-channel Attacks on Memristive Circuits Under External Disturbances

Side-channel Attacks on Memristive Circuits Under External D...

引用

Asian Test Symposium (ATS)

作者： Li-Wei Chen Xianyue Zhao Ziang Chen Nan Du Ilia Polian Institute of Computer Architecture and Computer Engineering University of Stuttgart Stuttgart Germany Department of Quantum Detection Institute for Solid State Physics Friedrich Schiller University Jena Leibniz Institute of Photonic Technology (IPHT) Jena Germany

Quick progress in memristive technologies has led to their consideration for several potential applications, many of which are security-critical. New possibilities of memristors, including their unique combination of non-volatile storage and compute capabilities, make them particularly attractive to edge applications, which are physically exposed to their users and therefore to potential attackers. Therefore, practical deployment of memristive circuitry for, e.g., cryptographic (sub-)modules or on-chip neural network inference, is only feasible when their vulnerability to physical attacks is understood and addressed. We evaluate experimentally one relevant class of physical attacks, namely side-channel attacks, under varying external conditions, namely temperature and magnetic fields. Using a small cryptographic construction, we evaluate both white-box and black-box attack varieties, using respective cryptanalytic techniques. Our results show that, while non-nominal conditions can complicate attacks, the information leakage remains and the secrets are extractable with additional knowledge about the memristive devices. This suggests the need to consider possible external disturbances during security evaluation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Swarm Intelligence in Internet of Medical Things 10

Swarm Intelligence in Internet of Medical Things

引用

10th IEEE Jubilee International Conference on Computational Cybernetics and Cyber-Medical Systems, ICCC 2022

作者： Roshanzamir, Mohamad Darbandy, Mohammad Tayarani Roshanzamir, Mahdi Alizadehsani, Roohallah Shoeibi, Afshin Ahmadian, Davood Fasa University Faculty of Engineering Department of Computer Engineering Fasa74617-81189 Iran Islamic Azad University Taft School of Architecture Taft*** Iran University of Tabriz Department of Electrical and Computer Engineering Tabriz Iran VIC Australia K. N. Toosi University of Technology FPGA Laboratory Faculty of Electrical Engineering Tehran Iran University of Tabriz Faculty of Mathematics Statistics and Computer Sciences Tabriz Iran

ISBN: (数字)9781665481779

ISBN: (纸本)9781665481779

Advancement in information and communication technology leads to different communication channels. One of them is the Internet of Things (IoT) which plays an important role in the new world. The Internet of Medical Things (IoMT) is the sub-branch of IoT which focuses on the communication between medical devices to share their data and information. It helps the healthcare industry to present better services for physicians and patients. It improves the quality of life by increasing the quality and decreasing the time and cost of services. An important challenge in IoMT is optimization in its different sub-problems and Swarm Intelligence (SI) algorithms are the best solution for them. In this paper, we tried to investigate the status of using SI in IoMT. Its applications and their corresponding performance were analyzed and investigated. The reported results show that using SI can efficiently solve the optimization problems in IoMT. © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Flower automata pattern-based discrimination of fibromyalgia from control subjects using fusion of sleep EEG and ECG signals

引用

IEEE Access 2025年 13卷 99032-99047页

作者： Barua, Prabal Datta Kobayashi, Makiko Dogan, Sengul Baygin, Mehmet Tuncer, Turker Paul, Jose Kunnel Iype, Thomas Acharya, U.R. Australia Kumamoto University Graduate School of Science and Technology Kumamoto860-8555 Japan Kumamoto860-8555 Japan Firat University Technology Faculty Department of Digital Forensics Engineering Elazig Turkey Erzurum Technical University Faculty of Engineering and Architecture Department of Computer Engineering Erzurum Turkey Government Medical College Department of Neurology Kerala Thiruvananthapuram India University of Southern Queensland School of Mathematics Physics and Computing Springfield Australia

Electroencephalogram (EEG) and electrocardiogram(ECG) signals provide vital insights into brain and heart activity and are widely used in automated medical diagnostics. This study introduces a novel, multimodal fibromyalgia detection system developed by the fusion of EEG and ECG signals recorded during sleep stages 2 and 3. The novelty of the model is the use of dynamic and interpretable feature engineering framework comprising of two innovations: (i) Flower Automata Pattern (FAP) for self-organized pattern-based feature extraction, and (ii) Attention-Driven Wavelet Transform and Absolute Maximum Pooling (ADWTAMP) method for signal decomposition and compression. Three feature selection strategies—Neighborhood Component Analysis (NCA), Chi2, and the intersection of NCA and Chi2 (NCA˄Chi2) —are employed to generate robust feature vectors, which are classified using k-nearest neighbors (kNN) and support vector machine (SVM) under the leave-one-record-out cross-validation (LORO CV) scheme. The final decision is derived through an iterative voting and greedy fusion approach. The proposed model achieved classification accuracies of 99.36% and 98.37% for sleep stages 2 and 3, respectively. Key advantages of the model include its high accuracy, low computational requirements (CPU-only execution), and explainable architecture. To the best of our knowledge, this is the first multimodal automata-based classification framework designed for fibromyalgia detection. © 2013 IEEE.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

A New IoT-Based Smart Greenhouse for Cultivation of Water Convolvulus

A New IoT-Based Smart Greenhouse for Cultivation of Water Co...

引用

International Electrical Engineering Congress (iEECON)

作者： Prayoot Akkaraekthalin Tanee Somwong Nonchanutt Chudpooti Nuttawut Hirun Suwaluck. Meesomklin Department of Electrical and Computer Engineering Faculty of Engineering King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Electronic and Telecommunications Engineering Faculty of Engineering and Architecture Rajamangala University of Technology Suvarnabhumi Nonthaburi Thailand Department of Industrial Physics and Medical Instrumentation Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand Department of Electronics Engineering Technology College of Industrial Technology King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (数字)9798331543952

ISBN: (纸本)9798331543969

This paper presents a new IOT system for monitoring and controlling plant cultivation in greenhouse system. The system aims to regulate and monitor the environmental conditions suitable for plant cultivation in real-time. The system utilizes sensors to measure environmental conditions, such as soil moisture sensor, light intensity sensor, temperature sensor, and air humidity sensor. The Node MCU ESP32 is used for processing and controlling these operations. The system is designed to send notifications through Line application and allows farmers to monitor the system's performance and plant growth in real-time via a smartphone application. It can utilize the Blynk IoT application on a smartphone for remotely monitoring and controlling the environmental conditions and provides historical data. This experiment demonstrates that the designed system can successfully cultivate plants and promote better growth compared to traditional cultivation methods with a 13.38% improvement. Additionally, it provides convenience and ease of management for plant cultivation.

关键词： Temperature sensors Temperature measurement Smart agriculture System performance Green products Sensor systems Real-time systems Sensors Internet of Things Monitoring

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based vehicle image detection using Yolo V5 with Region-Based Convolutional Neural Network

Deep Learning based vehicle image detection using Yolo V5 wi...

引用

Artificial Intelligence For Internet of Things (AIIoT), International Conference on

作者： S. Swapna Rani Aditya Mudigonda S V Hemanth P.N. Sundararajan G. Vinoda Reddy G. Amirthayogam Department of Electronics and Communication Engineering Maturi Venkata Subba Rao (MVSR) Engineering College Hyderabad India JNIAS School of Planning and Architecture Hyderabad Telangana India Department of Computer Science and Engineering Hyderabad Institute of Technology and Management Hyderabad Telangana Department of Electronics and Communication Engineering PSNA College of Engineering and Technology Dindigul Tamil Nadu India Department of Computer Science and Engineering (AI&ML) CMR Technical Campus Kandlakoya Hyderabad Telangana India Department of Information Technology Hindustan Institute of Technology and Science Chennai Tamilnadu India

ISBN: (数字)9798350372120

ISBN: (纸本)9798350372137

Detecting and classifying vehicles is a modern technology with numerous uses. Administration and regulation of traffic is one of the primary uses. Projects utilizing image processing to prevent traffic accidents heavily rely on vehicle monitoring and detection. Monitoring and recording human movement in surveillance situations require the ability to follow moving objects. Considering its significance, it provides a valuable image processing-based vehicle detection technique—a vehicle tracking and detection system based on images. The recently released high-resolution road vehicle dataset supports deep learning-based vehicle detection and monitoring on the Python platform. It includes over 100 well-defined pictures taken from movies from various locations. This data is produced using a range of image processing methods. The most recent iteration of the YOLO model, the v5 model, was employed for detection. R-CNN is additionally utilized for model detection. The four stages in the Region-Based Convolutional Neural Network (RCNN) process are preprocessing, segmentation, feature selection, and classification. The first step is identifying moving vehicles accurately. Preprocessing the original image is necessary. This enhances the image’s quality, valuable information extracted, or unwanted areas cropped out. Segmentation is the second step. The region’s borders are established, and the entire image is divided into numerous smaller areas using a threshold. The vehicle image’s most pertinent aspects or characteristics (features) that aid in precise detection are found in the third stage, feature selection. A region-based convolutional neural network (RCNN) is employed to determine the categorization. The Yolov5 method can be used to identify and categorize items. The Region-based Convolutional Neural Network (RCNN) approach enhances accuracy and temporal complexity over current segmentation algorithms.

关键词： YOLO Deep learning Image segmentation Accuracy Surveillance Transportation Transforms

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Biomarkers Detection Using ‘KnowSeq’ R Package 1st

COVID-19 Biomarkers Detection Using ‘KnowSeq’ R Package

引用

1st International Conference on Bioengineering and Biomedical Signal and Image Processing, BIOMESIP 2021

作者： Bajo-Morales, Javier Castillo-Secilla, Daniel Herrera, Luis Javier Rojas, Ignacio Department of Computer Architecture and Technology University of Granada C.I.T.I.C. Periodista Rafael Gomez Montero 2 Granada18014 Spain

ISBN: (纸本)9783030881627

‘KnowSeq’ R Package includes all the essential tools to carry out transcriptomic analysis, providing intuitive functions to build efficient and robust pipelines. In this paper, its capacities are demonstrated in a practical COVID-19 biomarkers detection problem using RNA-Sequencing data. Through Machine Learning techniques such as feature selection and supervised classification models, a clinical decision system for COVID-19 was developed using four genes proposed as COVID-19 signature: OAS3, CXCL9, IFITM1 and IFIT3. These four genes are highly related to different processes that affect the immune system behaviour and its response when facing viruses such as SARS-CoV-2. The final model reaches an accuracy over 97% when predicting over unseen samples. © 2021, Springer Nature Switzerland AG.

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：