检索结果-内蒙古大学图书馆

International Conference of Advanced Informatics: Concept, Theory and Application (ICAICTA)

作者： Arief Purnama Muharram Dicky Levenus Tahapary Yeni Dwi Lestari Randy Sarayar Valerie Josephine Dirjayanto Master Program of Informatics School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Metabolic Disorder Cardiovascular and Aging Research Center Faculty of Medicine Indonesia Medical Education and Research Institute Universitas Indonesia Jakarta Indonesia Ophthalmology Department Faculty of Medicine Cipto Mangunkusumo General Hospital Universitas Indonesia Jakarta Indonesia Faculty of Medicine Universitas Indonesia Jakarta Indonesia

Diabetes, especially T2DM, continues to be a significant health problem. One of the major concerns associated with diabetes is the development of its complications. Diabetic nephropathy, one of the chronic complication of diabetes, adversely affects the kidneys, leading to kidney damage. Diagnosing diabetic nephropathy involves considering various criteria, one of which is the presence of a pathologically significant quantity of albumin in urine, known as albuminuria. Thus, early prediction of albuminuria in diabetic patients holds the potential for timely preventive measures. This study aimed to develop a supervised learning model to predict the risk of developing albuminuria in T2DM patients. The selected supervised learning algorithms included Naive Bayes, Support Vector Machine (SVM), decision tree, random forest, AdaBoost, XGBoost, and Multi-Layer Perceptron (MLP). Our private dataset, comprising 184 entries of diabetes complications risk factors, was used to train the algorithms. It consisted of 10 attributes as features and 1 attribute as the target (albuminuria). Upon conducting the experiments, the MLP demonstrated superior performance compared to the other algorithms. It achieved accuracy and f1-score values as high as 0.74 and 0.75, respectively, making it suitable for screening purposes in predicting albuminuria in T2DM. Nonetheless, further studies are warranted to enhance the model's performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Supervised Learning Models for Early Detection of Albuminuria Risk in Type-2 Diabetes Mellitus Patients

arXiv

引用

arXiv 2023年

作者： Muharram, Arief Purnama Tahapary, Dicky Levenus Lestari, Yeni Dwi Sarayar, Randy Dirjayanto, Valerie Josephine Master Program of Informatics School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia Metabolic Disorder Cardiovascular and Aging Research Center Indonesia Medical Education and Research Institute Faculty of Medicine Universitas Indonesia Jakarta Indonesia Ophthalmology Department Faculty of Medicine Universitas Indonesia Cipto Mangunkusumo General Hospital Jakarta Indonesia Faculty of Medicine Universitas Indonesia Jakarta Indonesia

Diabetes, especially T2DM, continues to be a significant health problem. One of the major concerns associated with diabetes is the development of its complications. Diabetic nephropathy, one of the chronic complication of diabetes, adversely affects the kidneys, leading to kidney damage. Diagnosing diabetic nephropathy involves considering various criteria, one of which is the presence of a pathologically significant quantity of albumin in urine, known as albuminuria. Thus, early prediction of albuminuria in diabetic patients holds the potential for timely preventive measures. This study aimed to develop a supervised learning model to predict the risk of developing albuminuria in T2DM patients. The selected supervised learning algorithms included Naïve Bayes, Support Vector Machine (SVM), decision tree, random forest, AdaBoost, XGBoost, and Multi-Layer Perceptron (MLP). Our private dataset, comprising 184 entries of diabetes complications risk factors, was used to train the algorithms. It consisted of 10 attributes as features and 1 attribute as the target (albuminuria). Upon conducting the experiments, the MLP demonstrated superior performance compared to the other algorithms. It achieved accuracy and f1-score values as high as 0.74 and 0.75, respectively, making it suitable for screening purposes in predicting albuminuria in T2DM. Nonetheless, further studies are warranted to enhance the model’s performance. © 2023, CC BY-SA.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

The Deep Learning Approach For American Sign Language Detection

The Deep Learning Approach For American Sign Language Detect...

引用

Creative Communication and Innovative Technology (ICCIT), IEEE

作者： Gusti Pangestu Yaya Heryadi Lukas Wayan Suparta Yulyani Arifin Computer Science Department BINUS Graduate Program Computer Science. Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia Computer Science Department BINUS Graduate Program Computer Science Bina Nusantara University Jakarta Indonesia Cognitive Engineering Research (CERG) Faculty of Engineering Universitas Katolik Indonesia Atma Jaya Jakarta Indonesia Department of Electrical Engineering Faculty of Industrial Technology Institut Teknologi Nasional Yogyakarta Yogyakarta Indonesia

Sign language has importance rule to deal with communication process especially with impairments hearing people. Sign language detection also attract lot of researchers to join the challenge of research to detect and recognize the sign language in the field of Computer Science. Hence, there is still no any standard approach and method to recognize the meaning in every pose of sign language. This research proposed a mechanism to detect Alphabet American Sign Language by utilizing Convolutional Neural Network (CNN) process. The CNN approach was chosen based on the ability and capability to recognize image. In this research, MNIST dataset is used for traning and testing process. The proposed CNN architecture produced 97% of accuracy that outperform the previous research using the same dataset which made this architecture promising.

关键词： Deep learning Computer science Image recognition Gesture recognition Computer architecture Auditory system Assistive technologies

来源：评论

学校读者我要写书评

暂无评论

Impact of CLAHE-based image enhancement for diabetic retinopathy classification through deep learning

引用

Procedia Computer Science 2023年 216卷 57-66页

作者： Mira Hayati Kahlil Muchtar Roslidar Novi Maulina Irfan Syamsuddin Gregorius Natanael Elwirehardja Bens Pardamean Department of Electrical and Computer Engineering Universitas Syiah Kuala Banda Aceh 23111 Indonesia Telematics Research Center (TRC) Universitas Syiah Kuala Banda Aceh 23111 Indonesia Faculty of Medicine Universitas Syiah Kuala Banda Aceh 23111 Indonesia Department of Computer and Networking Engineering Politeknik Negeri Ujung Pandang Makassar 90245 Indonesia Bioinformatics and Data Science Research Center Bina Nusantara University Jakarta 11480 Indonesia Computer Science Department BINUS Graduate Program – Master of Computer Science Program Bina Nusantara University Jakarta 11480 Indonesia

Diabetic retinopathy (DR) is a type of diabetes mellitus that attacks the retina of the eye. DR will cause patients to experience blindness slowly. Generally, DR can be detected by using a special instrument called an ophthalmoscope to view the inside of the eyeball. However, in conditions where there is a very small difference between the normal image and the DR image, computer-based assistance is needed for maximizing image reading value. In this research, a method of image quality improvement will be carried out which will then be integrated with a classification algorithm based on deep learning. The results of image improvement using Contrast Limited Adaptive Histogram Equalization (CLAHE) shows that the average accuracy of the method on several models is very competitive, 91% for the VGG16 model, 95% for InceptionV3, and 97% for EfficientNet compared to the results original image which only has an accuracy of 87% for VGG16 model, 90% for InceptionV3 model, and 95% for EfficientNet. However, in ResNet34 better accuracy is obtained in the original image with an accuracy of 95% while in the CLAHE image the accuracy value is only 84%. The results of this comprehensive evaluation and recommendation of famous backbone networks can be useful in the computer-aided diagnosis of diabetic retinopathy.

关键词： Diabetic retinopathy Deep Learning CNN Image Enhancement CLAHE

来源：评论

学校读者我要写书评

暂无评论

A full-custom fully implantable cochlear implant system validated in vivo with an animal model

Communications Engineering

引用

Communications engineering 2024年第1期3卷 132页

作者： Uluşan, Hasan Yüksel, M. Berat Topçu, Özlem Yiğit, H. Andaç Yılmaz, Akın M. Doğan, Mert Gülhan Yasar, Nagihan Kuyumcu, İbrahim Batu, Aykan Göksu, Nebil Uğur, M. Birol Külah, Haluk Department of Electrical and Electronics Engineering Middle East Technical University Ankara Turkey METU-MEMS Research and Applications Center Ankara Turkey Department of Otorhinolaryngology Faculty of Medicine Gazi University Ankara Turkey Micro-Nano Technologies Graduate Program Middle East Technical University Ankara Turkey

Realizations of fully implantable cochlear implants (FICIs) for providing adequate solution to esthetic concerns and frequent battery replacement have lacked of addressing system level criteria as a complete device. Here, we present a full-custom FICI that considers design of both an implantable sensor for wide range sound sensing and a signal conditioning circuit for electrical stimulation of the auditory nerve. The microelectromechanical system (MEMS)-based acoustic sensor utilizes multiple cantilever beam structures to sense and filter the mechanical vibrations on the ossicular chain. The area optimized bilayer design of the piezoelectric sensor met with the volume limitation in the middle ear while achieving high signal-to-noise-ratio. The sensor outputs are processed by a current mode low-power signal conditioning circuit that stimulates the auditory neurons through intracochlear electrodes. The FICI is validated with an in vivo model where the electrical auditory brainstem response (eABR) of the animal was observed while applying sound excitation. The eABR results demonstrate that the system is able to evoke responses in the auditory nerves of a guinea pig for sound range of 45–100 dB SPL within the selected frequency bands. © The Author(s) 2024.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comparison on the use of Perlin-noise and Gaussian noise based augmentation on X-ray classification of lung cancer patient 1

A comparison on the use of Perlin-noise and Gaussian noise b...

引用

1st International Symposium on Physics and Applications, ISPA 2020

作者： Haekal, M. Septiawan, R.R. Haryanto, F. Arif, I. Department of Physics Faculty of Sciences and Data Analytics Institut Teknologi Sepuluh Nopember Kampus ITS Sukolilo-Surabaya Jawa Timur60111 Indonesia Computer Engineering Study Program School of Electrical Engineering Telkom University Jl. Telekomunikasi No.1 Jawa Barat Bandung40257 Indonesia Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Jl. Ganeca 10 Jawa Barat Bandung40132 Indonesia

The use of deep learning in medical image classification has become an important study in the past few years. The proper use of this method, however, is still hindered by many problems, one of it being the imbalance of dataset available for training which resulted in small-set database. In this study, the effect of noise-based augmentation on the performance of deep learning based classification will be studied. The noises which were used for the augmentation method were Perlin-noise and Gaussian noise. The modality of medical image used in this study is X-ray. 174 X-ray images (87 cancer, 87 normal) were used in this study and will be classified by using transfer learning from previously trained deep learning architecture. The deep learning architecture used was vgg-19. The images were divided into two groups, 138 (69 cancer, 69 normal) images were used for training phase and 36 (18 cancer, 18 normal) were images used for testing phase. Three deep learning models were used for the classification tasks, the first one was retrained to classify the original images, the second one was retrained by using mix of original images and images with Perlin-noise, and the third one was retrained by using mix of original images and images with Gaussian noise. The results showed that the three models returned similar accuracy of 0.8 which indicate that the use of noise-based augmentation can increase the performance of deep learning in classifying medical images with small set training database. © Published under licence by IOP Publishing Ltd.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Experimental and Theoretical Investigation of Photosensitive ITO/PEDOT:PSS/MEH-PPV/Al Detector

引用

MRS Online Proceedings Library 2020年第1期1190卷 160-165页

作者： Leon R. Pinto Jovana Petrovic Petar Matavulj David K. Chambers Difei Qi Sandra Zivanovic Selmic Institute for Micromanufacturing and Electrical Engineering Program Louisiana Tech University Ruston USA Faculty of Electrical Engineering University of Belgrade Belgrade Serbia

One of widely investigated materials for photodiode, light-emitting device, and solar cell applications is a soluble conjugated polymer poly(2-methoxy-5- (2,9-ethyl-hexyloxy)-1,4-phenylene vinylene) or MEH-PPV. In this paper we present experimental results on MEH-PPV polymer and ITO/PEDOT:PSS/MEH-PPV/Al photodetector, where ITO and PEDOT:PSS stand for indium tin oxide and poly(3,4-ethylenedioxythiophene):poly(styrenesulfonate), respectively. Thin polymer films were fabricated by spin-coating technique. The characterization of the material and devices are done in air at room temperature. The experimental results include optical absorption of MEH-PPV and determination of the optical absorption coefficient, photocurrent dependence on optical power, light wavelength, bias voltage, and polymer thin film thickness. Theoretical modeling is based on drift-diffusion and continuity equations for hole polarons, as well as assumption that the charge carrier recombination process is bimolecular. The bimolecular recombination mechanism implies that the photocurrent depends on the square root of the optical power, which is confirmed with our experimental results.

关键词： polymer optoelectronic simulation

来源：评论

学校读者我要写书评

暂无评论

Range of Motion Detection System in Humans Based on MediaPipe Special Flexion-Extension and Abduction-Adduction Movements

Range of Motion Detection System in Humans Based on MediaPip...

引用

Electronic and electrical engineering and Intelligent System (ICE3IS), International Conference on

作者： Muhamad Yusvin Mustar Bintang Surya Tryatmojo Maulana Hidayat Rama Okta Wiyagi Maria Ulfa Meiky Fredianto Muhammad Ihsan Department of Electrical Engineering Universitas Muhammadiyah Yogyakarta Indonesia Center of Artificial Intelligence and Robotic Studies Research and Innovation Institute Universitas Muhammadiyah Yogyakarta Indonesia Postgraduate Program Master of Hospital Administration Universitas Muhammadiyah Yogyakarta Indonesia Faculty of Medicine and Health Sciences Universitas Muhammadiyah Yogyakarta Indonesia

This research offers an alternative for health workers to monitor the rehabilitation of a patient's Range of Motion (ROM) without using a goniometer instrument and attaching various sensors to the patient's body, based on a detection system using the MediaPipe library. The developed detection system measures angles concerning the patient's body ROM patterns. The algorithm in the MediaPipe library helps to produce line graphs of landmark pose which are then processed using the trigonometric gradient equation so that it can have to measure angles from ROM. The angle of ROM measured includes Flexion-Extension and Abduction-Adduction movements of the arms, legs, and body. The results of testing the detection system between the goniometer measurements and the detection results differ from the Right Arm Elbow Flexion-Extension movement to the Trunk Flexion-Extension movement having an angle difference. The most significant angle difference is in the Right Arm Elbow Abduction - Adduction movement of 9.1388°, and the minor difference is in the Right Leg Hip Abduction - Adduction movement of 2.15°. The most significant overall system error is in the Left Arm Elbow Flexion - Extension movement, with a general system error of 27%. The minor system error in Left Arm Elbow Abduction - Adduction movement is 11 %.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Utilization plastic waste using pyrolysis fixed bed 1

Utilization plastic waste using pyrolysis fixed bed

引用

1st International Conference on Design, Energy, Materials and Manufacture, ICDEMM 2018

作者： Swamardika, I.B.A. Winaya, I.N.S. Hartati, R.S. Study Program of Electrical Engineering Faculty of Engineering University of Udayana Indonesia Study Program of Mechanical Engineering Faculty of Engineering University of Udayana Indonesia

This investigative research aims to convert urban non-organic waste fuels such as plastic waste into energy using fixed bed pyrolysis technology. Pyrolysis fixed bed (PFB) is one of the most efficient technologies for converting various types of undegradable solid waste into thermal energy and liquid fuels with high efficiency. The study was conducted on a lab-scale PFB reactor with dimensions of 15 cm and 55 cm in diameter and bed height respectively. The reactor is equipped with a cooling and decomposition system to accommodate liquid and gas products. Reactor temperature variations using an external heater were tested and quartz sands were selected as a bed material to improve the temperature function of the PFB reactor so as the maximum quality and quantity of liquid product were obtained. The fuel properties of the derived oil were tested including their physical properties, calorific value, elemental measurement (CHNOS) analysis. The results of the study showed that the increase in temperature resulted in an increased pyrolysis performance which was indicated by the increased volume and liquid caloric value. © Published under licence by IOP Publishing Ltd.

关键词： Pyrolysis

来源：评论

学校读者我要写书评

暂无评论

Android Based Heart-rate Monitoring System using ECG Sensor 2

Android Based Heart-rate Monitoring System using ECG Sensor

引用

2nd International Conference on Sustainable engineering and Creative Computing, ICSECC 2020

作者： Rosalina Selina, Grace Mandala, Rila Faculty of Computing Information Technology Study Program President University Bekasi Indonesia School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (纸本)9781728175881

This research aims to help the user monitor their heart’s condition and notify other people in case of an emergency due to an abnormal heartbeat (normal heartbeat around 60-100 beats per minute). From the heart rate graph, the user could do a consultation with an expert in the nearest hospital using a map feature that will show the nearest hospital with a 1 KM radius from the user’s current location. The heart is undeniably an essential part of the human body system. The heart's missions are to pump blood to the lungs to expel the waste carbon dioxide that resulted from the respiration and pump blood that will deliver oxygen throughout the human body's circulation system. While the blood that carries oxygen being pumped throughout the human body, the heart will provide the oxygen to all cells. Body cells need to use oxygen to get the energy from food through a process called cellular respiration. Monitoring our heartbeat and pulse rate can increase people’s awareness about their heart’s health, motivating, and encouraging people to maintain a healthy eating plan and exercise. This research will be implemented ECG Sensor. The sensor will then send the data to the android application via HC-06 Bluetooth module. Monitoring the heart rate and analyzing the user’s heartbeat will be done in the android with a microcontroller device's help. © 2020 IEEE.

关键词： Electrocardiograms

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：