检索结果-内蒙古大学图书馆

Artificial Neural Networks for Recognition of Brain Tumors on MRI images 16th

Artificial Neural Networks for Recognition of Brain Tumors o...

16th International Conference on Information and Communication Technologies in Education, Research, and Industrial Applications, ICTERI 2020

作者： Kondratenko, Yuriy Sidenko, Ievgen Kondratenko, Galyna Petrovych, valentyn Taranov, Mykyta Sova, Ivan Intelligent Information Systems Department Petro Mohyla Black Sea National University 68th Desantnykiv Street 10 Mykolaiv54003 Ukraine

ISBN: (纸本)9783030775919

In this paper, artificial neural networks for recognition of brain tumors on MRI images are analyzed. This analysis allows to choose the most appropriate neural network architecture and various preprocessing techniques to increase the precision of tumor instance recognition. Understanding the image and extracting information from it to accomplish some result is an important area of application in digital image technology. image recognition has quickly found its use in medicine and specifically oncology. Precise recognition masks may not be critical in other cases, but marginal recognition errors in medical images may render the results unreliable for clinical use. Therefore, biomedical problems require much higher boundary detection precision to improve further analysis. various methods and algorithms for image recognition and segmentation are considered. The advantages and disadvantages of neural network architectures (ResNet, U-Net, SegNet, YOLO v3) are considered and analyzed in more detail. Additionally, the analysis of data preprocessing methods was carried out, as well as a study of the input data. Comparison of different artificial neural networks algorithms and architectures will achieve the highest accuracy of recognition. During the comparison, a system of the U-Net architecture with additional processing methods was selected as the final model. Its accuracy reached 94%, which is a significant result compared to manual image recognition. © 2021, Springer Nature Switzerland AG.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Post-Analytical Methods for Using Data Proceedings for Defense of Collective systems

引用

SCIENTIFIC AND TECHNICAL INFORMATION processing 2020年第1期47卷 29-35页

作者： Syuntyurenko, O. v. Russian Acad Sci All Russian Inst Sci & Tech Informat VINITI Moscow 125315 Russia

Theoretical and applied aspects of using analytical post-processing methods using multidimensional data analysis to protect resources in shared systems are investigated. New approaches, algorithms, and procedures of this process are considered on the basis of registration statistics and multidimensional data analysis, which allow counteracting the implementation of implicit indirect methods of unauthorized access (or other actions) to information. A method of evaluating the quality of monitored indicators, as well as the stationary state of the system of indicators that characterize the "image" of the user in the system, is proposed. Questions of perception of results of data post-processing by a decision maker (security service administrator) are analyzed. A method of graphical visualization of results of registration and analytical processing of fixed data is presented.

关键词： analytical post-processing shared system information resources data analysis risks and threats unauthorized actions information security visualization

来源：评论

学校读者我要写书评

暂无评论

Human Detection using ROI of an image

Human Detection using ROI of an Image

引用

Smart systems for Electrical, Electronics, Communication and Computer Engineering (ICSSEECC), International Conference on

作者： R Kartik v Megadarshini S Kavisri R Manimegalai Department of EEE PSG Institute of Technology and Applied Research Tamilnadu India

ISBN: (数字)9798350378177

ISBN: (纸本)9798350378184

Efficient human presence detection within specified Regions of Interest (ROIs) is essential to many real-world applications, including as resource allocation, security surveillance, and crowd monitoring. In this paper, we present a robust human pres-ence detection system leveraging advanced techniques, notably YOLOv8, for accurate and real-time object detection. Our system addresses the challenges associated with traditional methods by focusing on multi-scale detection windows and efficient merging of nearby detections to refine results. We introduce a streamlined approach for ROI definition and utilize transfer learning to adapt YOLOv8 to specific human presence detection tasks. Extensive experiments on diverse datasets demonstrate the effectiveness and robustness of our system, showcasing superior performance in terms of accuracy, real-time processing, and adaptability to chal-lenging scenarios. Additionally, we implemented four algorithms, including Histogram of Oriented Gradients (HOG) [1], Roboflow 3.0 object detection algorithm, YOLOv5, and YOLOv8. After thorough examination, we determined that YOLOv8 showed the most favorable outcomes in terms of both precision and speed. Hence, we opted for YOLOv8 as the primary algorithm for our system aimed at detecting human presence. This decision was informed by its superior performance across diverse datasets and its capability to address the challenges associated with traditional methods.

关键词： YOLO Accuracy Surveillance Transfer learning Merging Real-time systems Robustness

来源：评论

学校读者我要写书评

暂无评论

Pre-processing Techniques and Model Aggregation for Plant Disease Prevention

Pre-processing Techniques and Model Aggregation for Plant ...

引用

International Conference on Practical Applications of Agents and Multi-Agent systems, PAAMS 2023

作者： Marco-Detchart, C. Rincon, J.A. Julian, v. Carrascosa, C. Camino de Vera s/n Valencia46022 Spain Camí de Vera s/n Valencia46022 Spain

ISBN: (纸本)9783031375927

image processing techniques have become increasingly popular in plant disease classification. However, one of the major challenges in this field is accurately identifying and classifying different diseases based on plant images. Pre-processing techniques such as smoothing and sharpening can play a crucial role in improving the accuracy of disease classification. These techniques can enhance the quality of the images and reduce noise, making it easier for machine learning algorithms to extract meaningful features from the images. In this context, these techniques can significantly improve the overall accuracy of plant disease classification systems. This paper aims to explore the potential of preprocessing techniques such as smoothing and sharpening in enhancing the quality of plant images for disease classification. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Predictable Multi-Core Implementation of Multi-Rate Sensor Fusion for High-Precision Positioning systems

Predictable Multi-Core Implementation of Multi-Rate Sensor F...

引用

American Control Conference (ACC)

作者： Chaitanya Jugade Sajid Mohamed Dip Goswami Andrew Nelson Gijs van Der veen Kees Goossens Department of Electrical Engineering Eindhoven University of Technology (TU/e) ITEC B.V. The Netherlands

ISBN: (数字)9798350382655

ISBN: (纸本)9798350382662

The high-precision and high-speed positioning systems require position feedback with high accuracy at a higher frequency. As reported in recent literature, high accuracy and high operating frequency can be achieved by fusing multiple position sensor data, e.g., the linear encoder (less robust/accurate, but fast) and object detection using camera images (accurate, but slow due to heavy processing load). Typically, image-based object detection incurs a significant computational delay due to computationally intensive processes and is the main performance bottleneck. Moreover, the computation delay varies when implemented on industrial platforms and degrades the performance of the closed-loop control system. In this paper, we present scheduling techniques such as parallelism and pipelining considering predictable multi-core platforms for such a multi-sensor positioning system. On the one hand, the predictable platform nearly removes the variation in execution time, making the delay constant. On the other hand, the parallel and pipeline schedules reduce the computation delay, translating to a shorter sampling period and better closed-loop performance. Furthermore, we perform a design space exploration on various parameters and control performance considering an industrial case study of semiconductor die-bonding equipment.

关键词： Schedules Accuracy Processor scheduling Process control Object detection Sensor fusion Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Stress Concentration Evaluation of a Plate with Symmetrical U-Notches Under Tensile Load Using TSA and a Lepton IR Camera 1

引用

Society-for-Experimental-Mechanics (SEM) Annual Conference and Exposition on Experimental and Applied Mechanics

作者： Paiva, v. E. L. Rosa, D. G. G. Gonzales, G. L. G. Freire, J. L. F. Pontifical Catholic Univ Rio de Janeiro Dept Mech Engn PUC Rio Rio De Janeiro Brazil Dept Civil Engn Rua Marques de Sao Vicente Rio De Janeiro RJ Brazil

ISBN: (数字)9783030867454

ISBN: (纸本)9783030867454;9783030867447

It has already been showed that Thermoelastic Stress Analysis (TSA) may be employed as an extremely useful technique in structural integrity assessment applications. Recent developments in the microbolometer technology made possible the commercial offer of very low-cost infrared cameras, one of these being the FLIR Lepton 3.5. Use of such low-cost cameras associated with commercially available software or in-house developed algorithms makes possible to localize anomalies and to determine quantitative results on the stress distribution acting on nominal and hot-spot locations in loaded structures. A further step will widely disseminate IR temperature and TSA measurements and consequent analyses into a powerful low-cost health monitoring tool. The aim of the present work is to demonstrate the use of this experimental technique in the evaluation of the stress concentration caused by a U-notch in a plate under tension load using TSA and a Lepton camera. A MATLAB in-house algorithm was developed for post-processing the measured IR signal. The achieved stress-distribution and stress-concentration results are also compared with those generated by measurement systems that integrate a commercially available software coupled to the FLIR Lepton 3.5 and to a median-cost FLIR A655sc IR camera. Moreover, the paper shows that the low-cost camera can be used in the monitoring of fatigue crack growth as well as in the determination of stress intensity factors for cracks initiated and propagated from the U-notch.

关键词： Thermoelastic stress analysis TSA Lepton 3.5 Stress concentration

来源：评论

学校读者我要写书评

暂无评论

Plant Disease Detection by means of K-Means Clustering and HSv Algorithm

Plant Disease Detection by means of K-Means Clustering and H...

引用

Sustainable Computing and Smart systems (ICSCSS), International Conference on

作者： R. Anirudh Reddy K. Sai Prasanna B. Mani Teja N. Deepak Reddy N. Pranay Sai Reddy N. Shiva Department of ECE B V Raju Institute of Technology Narsapur Medak Dt Telangana

The productivity of agriculture determines the economy of a country. To boost agricultural productivity and improve product quality, plant diseases must be identified. It is seen that the agricultural production is rapidly growing and various techniques are being used for it. One of the emerging technologies is fogponics. In this technology, plants are grown using fog which is directly exposed to roots instead of water. This methodology has a limitation of being infected with diseases due to a lack of nutrition. Plant leaf patterns can be observed visually to diagnose disease using traditional methods; however, they require the use of human resources. image classification is a technique to detect the diseases of plants that are already trained to model. If the disease is detected, then acknowledgment has been sent to the user that the plant is affected by the disease. This dataset must be uploaded to carry out the software implementation, and specific operations must be carried out on it to obtain the findings, namely whether the disease is detected. Regarding real-time applications, any model (Raspberry Pi) is used to hold substantial amounts of data. Devoid of any datasets for model training, a few different techniques are applied to identify anomalous leaf conditions. A color feature of the leaf area is used in image-processing algorithms to detect plant infections and diseases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A validation and Calibration Methodology for Autonomous Navigation of Small Satellites 28

A Validation and Calibration Methodology for Autonomous Navi...

引用

28th IAA Symposium on Small Satellite Missions 2021 at the 72nd International Astronautical Congress, IAC 2021

作者： Ciaglia, S. Benigno, N.R. El Hariry, M. Tricarico, P. Marchese, v. Battezzati, N. Simonetti, S. Argotec Srl Via Cervino 52 Torino10155 Italy

In addition to exploiting small satellites in the Earth orbit, space agencies and private companies have started adopting SmallSats also for deep space, mainly to support more complex missions. Autonomous operations are one of the key challenges these missions demand, either because of the communication delay or because a very fast response to external conditions is required. To properly design, tune and test such spacecrafts, complex validation systems are needed, to replicate in the most effective way the mission scenarios. This paper presents the methodology adopted by Argotec to validate and calibrate the autonomous navigation capability of its microsatellites, in particular the LICIACube spacecraft, aimed at acquiring scientific images during the forthcoming NASA DART (Double Asteroid Redirection Test) mission. Argotec's micro-satellite relies on an image processing system for object detection, and an attitude control algorithm, used to track the target asteroid at a high angular speed. The proposed system, that have been adopted by Argotec also for other missions, consists of two main parts: a software environment used to test and tune the image processing pipeline and the control algorithms, and a Hardware-In-the-Loop (HIL) setup that is used to validate the flight navigation software within a realistic simulation of the mission environment. Preliminary results show that the methodology described in this paper is effective for validating the algorithms, and that is a valuable strategy for parameters calibration even when the system is already deployed in space. © 2021 International Astronautical Federation, IAF. All rights reserved.

关键词： Navigation

来源：评论

学校读者我要写书评

暂无评论

Comparison of the Neural Networks with Crosscorrelation Algorithm for the Displacements on images Estimation

Comparison of the Neural Networks with Crosscorrelation Algo...

引用

Wave Electronics and its Application in Information and Telecommunication systems (WECONF)

作者： v. v. Pinchukov A. Yu. Poroykov E. v. Shmatko A. D. Bogachev N. Yu. Sivov Department of Physics Named After V.A. Fabrikant National Research University "Moscow Power Engineering Institute" Moscow Russia

In this paper three methods for determining displacements on images are compared. Two of them are neural networks designed for Particle image velocimetry images processing. The third method is classic cross-correlation approach. For estimation the accuracy of the algorithms synthetic data were used. Based on the obtained simulation results, it can be concluded that the use of neural networks is promising both for fluid dynamics and solid mechanics applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Leveraging Convolutional Neural Networks (CNNs) for Real-Time Object Detection and Classification in IoT-Enabled Smart Bins for Efficient E-Waste Collection and Sorting

Leveraging Convolutional Neural Networks (CNNs) for Real-Tim...

引用

Innovations in High Speed Communication and Signal processing (IHCSP), International Conference on

作者： varsha K.S M.Ashok Kumar Sandeep Kumar Davuluri Monika Gorkhe Lakshman Kumar Kanulla Sankari v Saveetha School of Law Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai India Department of Information Technology Velagapudi Rama Krishna Siddhartha Engineering College (Deemed to be University) Vijayawada Department of Information Technology Solution Architect University of the Cumberlands Chicago Illinois Symbiosis Skills and Professional Department of BBA Fintech School of BFSI Symbiosis Skills and Professional University Pune India Information Technology University of the Cumberlands Leander Texas United States Department of AI&DS K. Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798350368949

ISBN: (纸本)9798350368956

The rapid growth of electronic waste (e-waste) poses significant environmental and logistical challenges, as discarded electronics contain valuable resources and hazardous materials. Effective management and recycling of e-waste are essential to mitigate environmental impact and recover valuable materials. This is a very important factor in the light of the fact that the generation of e-waste is currently on the rise. To the best of our knowledge, this paper puts forward a new technique for efficient Real-time Object Detection and Classification in Smart IoT bins using CNNs which is implemented using python and accuracy is 98%. The proposed system incorporates the most recent CNN algorithms in order to tag and sort e-waste items as they are placed in the smart bins. The building enable the use of modern CNN models like Faster R-CNN, YOLO and SSD for real-time image analysis on the bin’s camera system. These models are subsequently refined using a large dataset of e-waste images to increase the models’ capabilities of identifying different electronic parts and gadgets. It also comprising a light-weight edge compute architecture so that the object detection, as well as its classification, can happen at a very fast speed thereby eliminating the delays inherent in feedback. Using IoT technology in the smart bins allows the bins to connect to the waste management system to relay details of the type and amount of e-waste being dumped. It helps in decisions to be made as to which direction to take the collection trucks, as well as sorting procedures to be followed at recycling facilities.

关键词： YOLO Waste management Technological innovation Computational modeling Signal processing algorithms Electronic waste Real-time systems Recycling Convolutional neural networks Sorting

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：