检索结果-内蒙古大学图书馆

Machine learning IoT based framework for analysing heart disease prediction

AIP Conference Proceedings 2023年第1期2523卷

作者： A. K. Velmurugan K. Padmanaban A. M. Senthil Kumar H. Azath Murugan Subbiah 1Computer Science and Engineering KoneruLakshmaiah Education Foundation Green Field Vaddeswaram Guntur Dist. Vijayawada Andhra Pradesh-522502 India 2Computer Science and Engineering Vel Tech RangarajanDrSagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India 3School of Computing Science and Engineering VIT Bhopal University India 4Vee Eee Technologies Chennai Tamil Nadu India

Coronary illness forecast is exceptionally fundamental in the present climate. Different explores have, as of now, been done to anticipate coronary illness from the huge dataset. IoT environment essentially produces information from various sensors and predicts the illness plausibility accordingly. Different synthetic dataset content diverse body boundaries extricated by explicit sensor esteem, the significant pretended by machine learning (ML) algorithm. This paper proposes coronary illness prediction with the mix of IoT and hybrid ML approach, which integrates the ANN with RNN. This examination has a sufficient degree for progress due to most boundaries, for example, increment record, blood vessel firmness, increment pressure, and so on. The proposed RNN gives better arrangement and infection expectation precision over the other ML calculations. This framework considered synthetic data, which is essentially used to anticipate coronary illness probability and prediction. The trial investigation shows the viability of the proposed methodology over other existing methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based segmentation and analysis of pneumothorax using chest X-ray images

引用

AIP Conference Proceedings 2022年第1期2555卷

作者： Meenu Gupta Karan Jakhar Avneet Kaur Fadi Al-Turjman 1Computer Science and Engineering Department Chandigarh University Mohali Punjab India 2Research Centre for AI and IoT Near East University Nicosia Mersin 10 Turkey

Segmentation of problematic area is important for many computer visions aided detection tasks. The medical field has benefited a lot from current advancements in computer vision techniques. Pneumothorax is such a condition that if its diagnosis and treatment are not done on time then it can be deadly. Chest X-rays images help in the diagnosis of this deadly disease. But to diagnose an expert and experienced radiologist is required and many people don’t have instant access to such a facility. Some of the cases in which a person can be suffering from this condition are accidents and, in those cases, a quick diagnosis is required. The paper explores image segmentation techniques to assist doctors in taking instant decisions if a particular individual is suffering from pneumothorax or not. Segmentation models predict a mask indicating a problematic area. With the help of this mask, doctors can make decisions on whether to operate or not. Two models Mask RCNN and U-net with Xception net backbone are compared in this paper. 12047 chest X-ray images were collected from Kaggle and out of those 9638 images were utilised for training and 2409 were utilised for testing and validation purpose. The performance measurement was done using Dice Coefficient and IoU matrices. The work in this paper focuses on deep learning and methods of segmentation and does not claim any medical validation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi fractal features along with empirical wavelet transform for detecting glaucoma

引用

AIP Conference Proceedings 2022年第1期2483卷

作者： Hussam Y. Abdulwahed Arkan Jassim Mohammed 1Computer Engineering Techniques College of Information TechnologyImam Ja’afar Al-Sadiq University Iraq 2Department of Mathematics College of Science-Al-Mustansiriah University Iraq

The main objective of this paper is to look further into the prospect of retinal image analysis aiming for the detection and tracing of glaucoma. The computer-based component analysis entails the use of image processing techniques in order to pre-process, identify and segment the region of interest, feature extraction as well as classification from the data-set images. The structural deformation of the optic disc and cup parts, one of the primary signs of glaucoma, necessitates high specificity in the segmentation procedure. As a solution to this issue, multi-fractal features as a non-morphological aspect are obtained in the proposed method from the enhanced optic disc area. Furthermore, the extracted image is decomposed using the Empirical Wavelet Transform to acquire different bands sub images. Subsequently, multifractal features where extracted. The resultant features are classified using a variety of classifiers. Among (Least Squares Support Vector Machine, Naive Bayes, Logistic Regression classifiers) Least Square Support Vector Machine outperforms all classifiers in terms of output. The proposed method has been investigated using different data-sets which includes regular and glaucoma images. Using Least Squares Support Vector, this proposed approach achieves a sensitivity of 86.71 percent in classifying glaucoma images and total accuracy of 89.94 percent.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Processing arabic font using cubic spline with periodic end conditions

引用

AIP Conference Proceedings 2022年第1期2386卷

作者： Salah J. Mohamed Auras K. Hameed Nibras W. Jawad 1Computer Science Department Al-Ma’moon University College Baghdad-Iraq 2Department of Computer Science College of Science for Women University of Baghdad Baghdad-Iraq 3Department of Computer Engineering Techniques Al-Ma’moon University College Baghdad-Iraq

The article constitutes the outlines capture of the digital Arabic character images which is appropriate for non-Roman (Arabic) fonts. The external boundaries of Arabic font character (ع) have been traced and boundaries of holes of a specific Arabic characters such as (و), the three interpolated curves of the Arabic character (ه). For (ك) character trace parent (ل) and their child (ء) and (..) in Arabic character ((ي) were outlined by the modification of Jacobs stopping criteria along with the tracing Moore-Neighbor algorithm. Moreover, a new algorithm has been presented using picewise cubic Hermite spline interpolation (PCHIP) to process the margins of characters and shapes. This algorithm is significant in computer graphics. Sample plots have been included to illustrate the power, effictiveness and flexiblility of this algorithm. Hermite spline algorithm is more suitable for few nodes on the outline of characters or shapes. The modified algorithm can be categorized in terms, types: capture a given set of data points.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid data mining technique based breast cancer prediction

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： K. Padmanaban A. M. Senthil Kumar H. Azath A. K. Velmurugan Murugan Subbiah 1Computer Science and Engineering KoneruLakshmaiah Education Foundation Green Field Vaddeswaram Guntur Dist. Vijayawada Andhra Pradesh 522502 India 2Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science And Technology Chennai Tamil Nadu India 3School of Computing Science and Engineering VIT Bhopal University India 4Embedded System Vee Eee Technologies Chennai Tamil Nadu India

In recent days, Breast malignancy has been considered the main real for death in ladies when contrasted with any remaining diseases. Bosom malignant growth has turned into the most unsafe sort of disease among ladies on the planet. Early discovery of bosom malignant change is fundamental in diminishing life misfortunes. This paper intends to present a hybrid data mining strategy that incorporates K-Nearest Neighbour (KNN) and Support Vector Machine SVM to build up a precise arrangement model for Breast malignant growth forecast, to utilize the important data in clinical information, particularly which is typically overlooked by a large portion of the current techniques when they focus on high expectation exactness’s We have done trials on WBC information. Examination results show that the proposed hybrid information mining strategy has higher expectation exactness than those techniques. Various strategies for bosom disease location are investigated, and their exactness is thought about. We induce that the SVM-based hybrid methods are more appropriate in addressing bosom disease expectations with these outcomes. We suggest utilizing these methodologies with incomparable arrangement issues.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A review on efficient EEG pattern recognition using machine learning and deep learning methods and its application

引用

AIP Conference Proceedings 2022年第1期2555卷

作者： Anson Antony Abir Bhattacharjee Soham Thakur Shreeanant Bharadwaj Shivam Sonawane Mritunjay Tomar 1Computer Engineering JSPM Rajarshi Shahu College of Engineering Puna India 2School of Computer Science and Engineering VIT Vellore India 3Electrical and Electronics Engineering Maharaja Agrasen Institute of Technology Delhi India 4Acropolis Institute of Technology and Research Indore India

With the good development of robotic technology, good communication of robots regarded as the most sought after achievement by researchers these days. If the robot can identify the feelings and intentions of the contact person, which can lead to more robots useful. Electroencephalography (EEG) is considered one of the most effective recording methods the emotions and motives of the brain user. The various types of machine learning are as follows used successfully to separate EEG data accurately. K-closest neighbor, Besesi network, Artificial Neural and Support Vector Machine networks are within the appropriate machine learning methods for classifying EEG data. The purpose of this concept is to explore different machine learning techniques to differentiate EEG data associated with specific emotional / emotional conditions. Different ways based on differences signal-processing techniques are studied Different numbers of EEG data elements are used to identify those that give the best results different classification techniques. Various methods are designed to format the database for EEG data. Formatted data sets were tested in various machine learning techniques in order to find out which process can place EEG data accurately according to it emotional / emotional conditions. On the other hand, this study is to study the electronic learning methods by various EEG tools. Continuous EEG is an exciting approach to cerebral function performance testing in intensive care unit and more. A systematic approach of this work derives various important outcome on EEG.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Erratum: “Enhanced acoustic pressure sensors based on coherent perfect absorber-laser effect” [J. Appl. Phys. 129, 104902 (2021)]

引用

Journal of Applied Physics 2021年第22期129卷

作者： Mohamed Farhat Waqas W. Ahmad Abdelkrim Khelif Khaled N. Salama Ying Wu 1Computer Electrical and Mathematical Science and Engineering (CEMSE) Division King Abdullah University of Science and Technology (KAUST) Thuwal 23955-6900 Saudi Arabia 2Institut FEMTO-ST CNRS Universite de Bourgogne Franche-Comte 25000 Besancon France 3Sensors Lab Advanced Membranes & Porous Materials Center (AMPMC) King Abdullah University of Science and Technology (KAUST) Thuwal 23955 Saudi Arabia

There is a typo in Eq. (2) of the original paper.1 The corrected form of this equation is

关键词：

来源：评论

学校读者我要写书评

暂无评论

Splicing detection in color image based on deep learning of wavelet decomposed image

引用

AIP Conference Proceedings 2020年第1期2290卷

作者： Ali Retha Hasoon Khayeat Ahmed Abdulhadi Al-Moadhen Mustafa Ridha Hassoon Khayyat 1Computer Science Department College of Science University of Kerbala Karbala Iraq 2Department of Electrical and Electronic Engineering/ College of Engineering University of Kerbala Karbala Iraq 3State company for filling and gas services ministry of oil Karbala Iraq

Image splicing is done by duplicate part(s) of an image and pasted in a different image. This basic technique is very common in image forgery therefore it reduced the user confidence in the digital image. The need for a reliable and effective method to detect this type of counterfeiting has been increased. Splicing detection in colour image based on Deep Learning of Haar wavelet decomposed image is developed in this work. The colour image is converted to grayscale and decomposed into 1st level (LL1, LH1, HL1, and HH1). Then to detect splicing, we used the semantic segmentation of the decomposed image. Consider that the Convolutional Neural Network model was used to segment the decomposed LL1 image. The SegNet is applied to boost the semantic segmentation and utilize the classification in our proposed approach. The experimental work confirmed the efficiency of the suggested method where the forgery (splicing) detected in 89% of the tested images with a very high percentage of localization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving students’ mathematical problem-solving ability using differentiated instruction approach

引用

AIP Conference Proceedings 2022年第1期2468卷

作者： Ade Evi Fatimah Muhammad Daut Siagian Suwanto Fitry Wahyuni Azrina Purba 1Computer Informatics Engineering Education Study Program STKIP Al-Maksum Langkat Jl. Sei Batang Serangan Kwala Bingai Kec. Stabat Kabupaten Langkat Sumatera Utara 20811 Indonesia 2Mathematics Education Study Program Universitas Islam Sumatera Utara Jl. Sisingamangaraja Teladan- Medan Sumatera Utara 20217 Indonesia 3Mathematics Education Study Program STKIP Asy-Syafi’iyah Internasional Medan Jl. Karya Tani No. 1 Pangkalan Masyhur Kec. Medan Johor Kota Medan Sumatera Utara 20146 Indonesia 4Corporate Management Study Program Akademi Perniagaan dan Perusahaan APIPSU Medan Jalan Rasmi No. 28 Medan Sumatera Utara 20123 Indonesia 5Science Education Study Program STKIP Al-Maksum Langkat Jl. Sei Batang Serangan Kwala Bingai Kec. Stabat Kabupaten Langkat Sumatera Utara 20811 Indonesia

Problem-solving abilities are very important in mathematics, not only for those who will study mathematics in the future but also for those who will apply it in other fields of study and in everyday life because in the process of learning and solving it, students can gain experience using knowledge and skills already possessed to be applied in solving non-routine problems. This study aims to analyze and describe students' mathematical problem-solving abilities through the application of the Differentiated Instruction approach. This research is quantitative research with a quasi-experimental method. This research was conducted in one of the Vocational High Schools in Deli Serdang Regency, North Sumatra, for grade 10 students consisting of two classes, namely the control class and the experimental class, where each class consisted of 24 students. The sampling technique with cluster random sampling was used to collect data. Data collection is done by giving a test on trigonometry material. Data analysis was performed using a two-way ANOVA test. The results of this study indicate that the increase in mathematical problem-solving abilities of students who receive learning using the Differentiated Instruction approach is better than students who receive direct learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The assembling of electrical socket for electricity usage monitor and electronic device control with ESP8266 microcontroller basis

引用

AIP Conference Proceedings 2019年第1期2169卷

作者： Muhammad Faisal Akbar Pandu Wilantara Muhammad Ikhsan Hasan Ikhtiarta Ridwan Siskandar Inna Novianty Irzaman 1Computer Engineering School of Vocational Science IPB Jl Kumbang no. 14 Kota Bogor 16151 Indonesia 2Departement of Physics FMIPA IPB Jl Meranti Kampus IPB Dramaga Bogor 16680 Indonesia

Electrical socket to monitor the electricity usage and control the electronic control based on ESP8266 microcontroller was successfully made. This tool was assisted by PZEM-004T module to monitor electrical power consumption. Electricity consumption monitoring and electronic device controlling were carried out through Android application. This electrical socket assembling was necessary to minimize the excessive electric use. Assembling of electrical socket starts with making an electronic circuit design, casing design, and Android applications that are continuing with the component manufacturing process. The measurement result of electrical energy was done by using a device made with energy meter showed measurement errors with an average error of 5.31%

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：