检索结果-内蒙古大学图书馆

Medical image enhancement using histogram equalization techniques

AIP Conference Proceedings 2023年第1期2591卷

作者： Zobeda Hatif Naji AL-Azzawi Wisam Hayder Mahdi Shaimaa Khamees Ahmed Waqas Saad Yasin 1Department of Computer Engineering College of Engineering University of Diyala Iraq 2Department of Communications Engineering College of Engineering University of Diyala Iraq

Due to the rapid development in digital technology, image enhancement has become a necessity to extract data and use it in many fields that may be medical, agricultural security, and many other fields. There are many Image enhancement technique used in image processing. The proposed method have been presented in this paper attempt to improve the performance of histogram equalization with different kind of medical image by using Gaussian filter and gamma where combined together to improve the illumination, contrast of images ,reduce the noise, and also improve image quality coefficients. Try to measure the entropy of image and compare the result of output image with input image and to give desired result. The quality coefficients for the medical images processed with the HE and Gaussian filter and Gamma with certain value, according to the scientific proof. When the image quality was improved, the visual perception was improved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and implementation virtual environment network base on DMVPN

引用

AIP Conference Proceedings 2023年第1期2591卷

作者： Ahmed Abbas Fadel Safa Ihsan Matloob Mohamed Ibrahim Shujaa 1Department of Computer Engineering Techniques AL-Mustafa University College Iraq 2Department of Computer Engineering Techniques Middle Technical University (MTU) Iraq

Due to network advancements and network user growth, network security challenges and approaches have grown in the recent years. The current trend of network security focuses on those networks which are operating over the internet (web-based). Since unpredictable users can be presented over the internet networks from various places, malicious activities are highly expected. Several technologies were produced for ensuring the required security and privacy enforcement. Virtual private network is proposed for ensuring the required security over particular connections over wide networks. In this work proposed use the "show dmvpn" to make sure the connectivity of dmvpn works fine (10.20.20.2, 10.30.30.2 is referred as NBMA (non-broadcast multiple access network) these Internet Protocol (ip's) assigned in spokes routers in their physical interfaces and connecting directly in ISP routers and routed with default route.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Effectiveness of Image-Based Classifiers for On-Site Identification of Lichens in Reserved Forest

SSRN

引用

SSRN 2024年

作者： Sankar, Karthikumar Rajaram, Shyam Kumar Karuppiah, Ponmurugan Periyasami, Govindasami Karthikeyan, Perumal Selvi, Chengathir M. Selvan, Basil Tamil E. Department of Computer Science and Engineering Mepco Schlenk Engineering College Tamil Nadu Sivakasi626005 India Department of Biotechnology Kamaraj College of Engineering and Technology S.P.G.C.Nagar K.Vellakulam Tamil Nadu Virudhunagar626001 India Department of Botany and Microbiology College of Science King Saud University P.O. Box 2455 Riyadh11451 Saudi Arabia 2Department of Chemistry College of Science King Saud University P.O. Box 2455 Riyadh11451 Saudi Arabia Department of Chemistry and Biochemistry Ohio State University 170A CBEC 151 Woodruff Avenue ColumbusOH43210 United States Department of Computer Science and Engineering Kamaraj College of Engineering and Technology S.P.G.C.Nagar K.Vellakulam Tamil Nadu Virudhunagar626001 India

The collection and identification of lichen samples within the reserved forest pose significant challenges, leading researchers to seek alternative methodologies. In this context, an in-depth study was conducted using two approaches to evaluate the efficacy of several network models for the identification of lichens in digital images. In the initial method, a total of 119 lichen images, comprising 15 images from experimental work and additional images from open sources, were employed for the traditional classification approach utilizing MATLAB. In which, 90 different features were extracted from various color models such as RGB, YCbCr, HSV, CMYK, LAB, YIQ and subjected for classification in ANN model, which resulted 76.6% accuracy for the class of lichen family. In another approach, each species of lichen images was augmented using generative augmentation tool and subjected for multiclass deep learning network models, precisely transfer learning model. In total, 10410 images comprising 5 thallus type, 8 order and 77 distinct lichen species were used to train three different network models (VGG16, VGG19, ***50). It was found that ***50 model exhibited highest sensitivity (>0.99) and precision. The class lichen thallus type achieved a maximum accuracy of 86.6%, while the order exhibited 80%. Overall, the lichen species under the order of Laccanorals with fruticose thallus type showed highest classification accuracy in all the three models attempted in this study. The study concluded that utilizing transfer learning with a multilayer perceptron model proved to be more effective and accurate for the lichen dataset, especially when dealing with greater complexity in picture information. The obtained results were comparable to those of other recent deep learning approaches. © 2024, The Authors. All rights reserved.

关键词： Fungi

来源：评论

学校读者我要写书评

暂无评论

Visual-infrared image monitoring system for moving object detection, classification and tracking using deep learning technique

引用

AIP Conference Proceedings 2023年第1期2651卷

作者： Maad Issa Al Tameemi Bashra Kadhim Oleiwi 1Department of Computer Engineering University of Baghdad Baghdad Iraq 2Department of Control and Systems Engineering University of Technology-Iraq Baghdad Iraq

In this work, the issue of moving object detection, classification, and tracking in both visual-infrared images and video streams is considered. The proposed system utilizing deep learning-based You Look Only Once -version3 (YOLOv3) algorithm as multilayers of CNN model, OpenCV, and CAMEL dataset and collected dataset as video sequence of a visual-infrared dataset. The proposed object detector system pre-trained on the dataset for streaming videos and different sizes and types of images as visual_ thermal as RGB images of different object classes and carried out by Python codes. The first part of the proposed system is to make the object or person detection and surround it by rectangle box, the center of the detected person is then specified in the second part, finally, calculate the relative accuracy of detected person and added it to the rectangle box. The obtained results proved the success of the proposed system in achieving objects detection, classification, and tracking within visual-infrared surveillance scenarios and gave satisfactory results with high accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of classifiers for non communicable diseases

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： S. Srinivasan S. Selvakumar Pacha Shobha Rani D. JayaKumar 1Department of Computer Science and Engineering R.M.D Engineering College Kavaraipettai Tamil Nadu India 2Department of Computer Science and Engineering Visvesvaraya College of Engineering and Technology Hyderabad Telangana India

Non-Communicable Diseases (NCD) has been drastically increased across the world in the recent years. Diseases that are not transmissible from one person to another are known as Non-Communicable Diseases (NCDs). Parkinson's disease, Autoimmune Disorders, Strokes, Heart Diseases, Cancers, Diabetes are examples of NCDs. It is found that certain Non-Communicable Diseases are believed to be exacerbated by lifestyle and climate which cause of death in the world. Many Machine Learning methods such as Nave Bayes, Support Vector Machine have been applied to predict NCDs. The aim of this paper is to predict the Non-Communicable Diseases (NCDs) and evaluate the performance of the key classifiers in terms of Prediction accuracy, Kappa and F-Measure. The progress in computer training and AI can remarkably help the analysis of Non-Communicable Diseases (NCDs). Nevertheless, the intrinsic complication of black-box samples controls the understanding of the sample. Consequently, likely regulative concerns arise. Furthermore, the lack of faith inside the therapeutic society is obvious due to the absence of understanding of how and why a sample prophesies. This research illustrates how sample-cynical ways of explainable AI (XAI) can assist give descriptions to assume black-box samples on NCDs information collection better.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A blockchain based virtual machine detection system app market

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： Karthikeyan Palaniappan V. Anantha Krishna M. Ramasubramanian T. K. S. Rathish Babu 1Department of Centre for System Design Computer Science and Engineering Chennai Institute of Technology Chennai Tamil Nadu India 2Department of Computer Science and Engineering Sridevi Women's Engineering College Hyderabad Telangana India

Smartphone malware's rapid development suggests malicious programme developers moving from standard PC systems to smart phone computers. Technology experts are now also developing new methods of anti-malware for adequate security. For the identification of smart phone dangerous applications, this study proposes a Blockchain-based malware mitigation framework (B2MDF) (app stores). For the ultimate judgement, the system combines two internal and external proprietary block chains to establish a private dual blockchain and a blockchain alliance. Blocks produced from both static and dynamically driven function removers are stored in the private internal blockchain stores, whilst blocks for current models are detected in the external blockchain stores. B2MDF also exchanges function blocks with third parties, which allows providers of anti-malware to offer more exact *** rating permissions, we employed the idea of information value. Furthermore, because blockchain has great dependability and cheap cost, we developed a consensus-based blockchain framework for generating more concrete predictions. The top 45 permissions, rated by Information Value, are used to obtain this accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Weibull distribution analysis of wind power-generating potential on the southwest coast of Aceh, Indonesia

引用

AIP Conference Proceedings 2023年第1期2613卷

作者： Herdian Saputra Ira Devi Sara Suriadi Marwan M. Yanis 1Department of Electrical and Computer Engineering Faculty of Engineering Universitas Syiah Kuala Banda Aceh Indonesia 2Department of Geophysical Engineering Faculty of Engineering Universitas Syiah Kuala Banda Aceh Indonesia

The National Energy Master Plan sets the target that by 2050 the development of renewable energy for Wind Energy Power Plants reaches 60.647 GW throughout Indonesia, while for Aceh Province, it is predicted that wind energy will be able to generate 894 MW. To map this energy potential, further research is still needed to get the best position for the development of Wind Power Plants. This study aims to map the potential of wind energy in the coastal areas of Southwestern Aceh using the Maximum Likelihood method of the Weibull distribution to analyze wind speed from the data provided by the European Center for Medium-Range Weather Forecast (ECMWF). The area of study covers several districts including Aceh Jaya, Aceh Barat, Nagan Raya, Aceh Barat Daya, Aceh Selatan, Aceh Singkil and Simeulue. The average wind on Weibull distribution for Simeulue is 2.48 m/s with a frequency of 26%, Aceh Singkil 1.54 m/s with a frequency of 40%, Aceh Selatan 1.55 m/s with a frequency of 48%, Aceh Barat Daya 1.55 m/s with a frequency of 50%, Nagan Raya 2 m/s with a frequency of 36%, Aceh Barat 1.54 m/s with a frequency of 38% and Aceh Jaya 2.49 m/s with a frequency of 31%. Meanwhile, the wind power capability ranges from 4,590 watts/m2 – 26,040 watts/m2, making the whole site a low-class wind suitability as a wind power generator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparing of the effect of changing weather factors on FSO communication system performance using iterative improvement technique

引用

AIP Conference Proceedings 2023年第1期2591卷

作者： Alaa Thaer Lateef Hayder A. Naser Aqeel Kamil Kadhim 1Ministry of Science & Technology Baghdad Iraq 2Department of Computer Techniques Engineering Imam Al-Kadhum College Baghdad Iraq

The issue of providing a communications system, with large frequencies within the range, is one of the main challenges that are required to be provided to users of the free-space optical communications service. In this work, the factors affecting the quality of performance of a free communication system (10 Gbps) were investigated and studied. The obtained results of this system are compared with two wavelengths 1550 nm and 850 nm in terms of farthest data transmission distance, BER, factor of quality and chart of eye in different weather situations using an iterative optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The development of autonomous drone for document delivery in IPB University

引用

AIP Conference Proceedings 2023年第1期2482卷

作者： Carli Apriansyah Hutagalung Karlisa Priandana Kudang Boro Seminar 1Department of Computer Science Faculty of Mathematics and Natural Sciences IPB University Indonesia 2Department of Mechanical and Biosystem Engineering Faculty of Agricultural Engineering and Technology IPB University Indonesia

This study aims to design an autonomous hexacopter drone that can be used to deliver documents in IPB University, to replace conventional oil-fueled transportation. The hexacopter drone is designed with autopilot control using a point-to-point flight system based on GPS coordinates. Preliminary research was conducted to examine the delivery of documents between the Faculty of Mathematics and Natural Sciences (FMIPA) and the Faculty of Agricultural Technology (FATETA). The experimental results showed that the maximum payload of the designed drone is 1 kg. The drone flight tests showed that the drone can reach its destination with good performance. The average error for the unloaded flight test from FMIPA to FATETA is 1.02 m, while from FATETA to FMIPA is 0.53 m. Meanwhile, the average error for flight tests with a maximum payload (1 kg) from FMIPA to FATETA is 1.97 m, while from FATETA to FMIPA is 0.703 m.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and analysis of a compact dual-band printed rectenna circuit at WiFi and GSM frequencies for microwave power transmission

引用

AIP Conference Proceedings 2023年第1期2591卷

作者： Ahmed Abdul-Kadhem Salih Abdulkareem S. Abdullah 1Computer Technology Engineering Department College of Information Technology Unversity of Imam'Jafer AL-Sadiq Nassiriya Iraq 2Department of Electrical Engineering College of Engineering University of Basrah Basrah Iraq

In this paper, a dual-band printed rectenna of compact size (38×24) mm2 has been designed and analyzed to work at GSM frequency of 900 MHz and WiFi frequency of 2.4 GHz for wireless power transmission. The purpose of this design is to harvest energy at two different frequencies to increase the probability of receiving power from ambient field. The antenna part of this rectenna is printed on FR4 substrate and has the shape of meander line with two arms for double-band operation. The rectifier part of this rectenna consisted of impedance matching network, AC-to-DC conversion circuit and a DC filter. The design and simulation results of this rectenna have been done with the help of CST 2019 and ADS 2018 software packages. At a received input power of -30 dBm and a load resistance of 1900 Ω, the maximum conversion efficiencies obtained by this rectenna at frequencies of 900 MHz and 2.4 GHz are found as 23% and 42% respectively.

关键词：

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：