检索结果-内蒙古大学图书馆

Hyperparameter tuning for malaria detection using convolution neural network

AIP Conference Proceedings 2024年第1期3132卷

作者： Windra Swastika Gregorius Guntur Sunardi Putra Romy Budhi Widodo Rehmadanta Sitepu Informatics Study Program Universitas Ma Chung Malang Indonesia Pharmaceutical Science and Biomedicine Universitas Ma Chung Malang Indonesia

Malaria is an infectious disease caused by a parasite known as Plasmodium, which infects red blood cells. Malaria detection can be done by using a Blood Smear examination through a microscope. The patient's blood sample will be stained with fluorescence and then viewed using a microscope to see the presence of Plasmodium parasites in the blood. Computer vision and deep learning method can also be used to detect malaria from red blood cell images. Previous studies showed convolution neural network (CNN) model can accurately detect malaria from red blood cell images. However, the CNN architecture and parameters played an important role in increasing accuracy. This study investigated the effect of hyperparameter tuning toward accuracy, precision, recall, f1-score and Matthew Correlation Coefficient (MCC). Two architectures, Rajaraman and BaselineNet were used for the experiment and grid searching technique to find the best hyperparameter used in this research. The best hyperparameter for Rajaraman architecture were 30 epochs, ADAMAX optimizer, 32 batch-size, and 0.01 learning rate with 96.7% accuracy. The best hyperparameter for BaselineNet architecture were 20 epochs, SGD optimizer, 0.1 learning rate and 32 batch size. Overall, the hyperparameter tuning can increase 1.93% for Rajaraman architecture and 0.36% for BaselineNet architecture compared to non-tuning hyperparameter.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Extraction of corn seed image texture using machine learning method

引用

AIP Conference Proceedings 2024年第1期2987卷

作者： Yampi R. Kaesmetan Fuzy Yustika Manik Wisard Kalengkongan Informatics Techniques Study Program STIKOM Uyelindo Kupang Kupang Indonesia Faculty of Computer Sciences and Information Technology Universitas Sumatera Utara Medan Indonesia Information System Study Program Universitas Sam Ratulangi Manado Manado Indonesia

Indonesia is the largest corn exporter in the world. Corn (Zea mays I.) Problems in determining the selection of corn seed to replant, especially corn in East Nusa Tenggara, are still a critical issue. The things that affect the quality of corn are found: the seeds are damaged, the seeds are dull, the seeds are dirty, the beans are broken due to the drying process, and the shell of the corn. The determination of the quality of corn grains usually is done manually with visual observation. The manual system requires a long time and produces good quality products that are not consistent due to the limitation of visual fatigue and differences in the perception of each observer. This research uses image texture extraction comparison with statistical methods I orde (color moment) and orde statistics II (GLCM) to select the corn seed. Orde statistics I (color moment) shows the emergence of the value of the degree of gray probability pixels in an image, while orde statistics II (GLCM) shows the relationship between two probability pixels forming a concurrence matrix from the image data. This research is expected to help the process of classification in determining the corn seed. The algorithm k of the nearest neighbor (K-NN) who used to research the classification of the object of the image that will be examined. The results of this study successfully performed using k-Nearest neighbor (k-NN) with a distance of euclidean distance and k=1 with the extraction of the color moment got the highest accuracy is 88%, and the extraction GLCM to characterize the homogeneity of 75.5%, correlation of 78.67%, a contrast of 65.75% and energy of 63.82% with an average accuracy of 70.93%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prototype Design of Smart Diabetic Shoes with Lora Module Communication

Prototype Design of Smart Diabetic Shoes with Lora Module Co...

引用

Computer Science, Information Technology and Engineering (ICCoSITE), International Conference on

作者： Purwono Purwono Asmat Burhan Khoirun Nisa’ Sony Kartika Wibisono Iis Setiawan Mangkunegara Pramesti Dewi Alfian Ma’Arif Iswanto Suwarno Department of Informatics Universitas Harapan Bangsa Purwokerto Indonesia Department of Anesthesiology Nursing Universitas Harapan Bangsa Purwokerto Indonesia Department of Information Technology Universitas Harapan Bangsa Purwokerto Indonesia Nursing Study Program Universitas Harapan Bangsa Purwokerto Indonesia Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta Indonesia Department of Engineer Professional Program Universitas Muhammadiyah Yogyakarta Yogyakarta Indonesia

Diabetes is a disease that affects many people in the world. Diabetes mellitus is a type of metabolic disease in a person who suffers from blood glucose levels with extreme conditions, namely insufficient insulin production in the human body. Monitoring diabetes is an important concern for researchers because it can be useful for improving the quality of the nursing service system. One of the common conditions in diabetic patients is ulceration which is difficult to detect on time. Technology can minimize the total cost of monitoring chronic diseases such as Diabetes continuously and on time. This research focuses on solutions to produce IoT-based smart diabetic shoes that utilize pressure sensors and the temperature of the feet of people with diabetic feet. Smart diabetic shoes are made using the Lora E32 module to be applied to areas with poor internet connections. The results of the testing carried out for 60 seconds in this study succeeded in detecting the area of the foot that experienced the greatest pressure, which was located on the rear footrest with a portion of pressure of around 25 – 28% of the total body weight. The patient's foot temperature increases when the pedestal load is greater. The Lora E32 module also functions as a media transmitter and receiver at a distance of 2.2 km in sending sensor data.

关键词： Temperature sensors Pressure sensors Transmitters Web services Footwear Receivers Diabetes

来源：评论

学校读者我要写书评

暂无评论

Determining level of lies with GSR and heart rate parameters using Tsukamoto’s fuzzy logic method

引用

AIP Conference Proceedings 2023年第1期2693卷

作者： William Steven Halim Agung Teady Matius Surya Mulyana Lukman Hakim Evaria Sipayung Informatics Study Program Technology and Design Faculty Bunda Mulia University Jakarta Indonesia Digital Business Study Program Technology and Design Faculty Bunda Mulia University Jakarta Indonesia

Humans need communication for survival in this community group is the fact that humans are social creatures. By communicating with each other, people indirectly exchange information, but any information provided is not completely correct based on actual events or facts. By saying that it is not appropriate, the information provided to the recipient becomes a problem so that the emergence of new information that is wrong or often referred to as lying. To reduce the occurrence of errors in analyzing the information received, a tool is needed to detect information conveyed from someone’s words based on the level of someone’s lies. This research was conducted using the Arduino Mega tool that applies the Tsukamoto fuzzy logic method that works with two GSR and Heartrate sensors as input to determine the level of someone’s lies. From the results of this study by testing 30 times, it was found that the accuracy of Tsukamoto’s fuzzy logic in determining the level of lies was 73.33%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification of heart disease trigger factors using Naive Bayes method to predict the risk of heart disease using IoT-based heart rate sensors

引用

AIP Conference Proceedings 2023年第1期2693卷

作者： Jeffrey Jahja Halim Agung Teady Matius Surya Mulyana Lukman Hakim Evaria Sipayung Informatics Study Program Technology and Design Faculty Bunda Mulia University Jakarta Indonesia Digital Business Study Program Technology and Design Faculty Bunda Mulia University Jakarta Indonesia

Heart disease is a very dangerous disease, and threatens the life of the sufferer, heart disease can also cause other diseases such as hypoxemia which is a condition that occurs because the oxygen content in the blood is not enough so that it can cause damage to important organs in the body such as the brain and kidneys, a person’s risk of heart disease can be predicted in several ways, by calculating the heart rate per minute or using classification methods. The method used in this research is the Naive Bayes classification method, with the Naive Bayes method the probability of each attribute is calculated and classified into the specified class. The system developed by the author is a web-based system to predict a person’s risk of heart disease, by classifying trigger factors such as diabetes, blood pressure cholesterol, and in addition to heart rate and blood oxygen content (Spo2). Input used in the system made by the author in the form of heart rate per minute, blood oxygen content (Spo2), cholesterol, diabetes, and blood pressure. The system is made using an IoT-based prototype tool designed by the author to take the user’s heart rate and blood oxygen content (Spo2) input values. The conclusion obtained in this study is that by using the Naive Bayes method, the prediction of a person’s risk of heart disease can be predicted and has an accuracy of 96%, with 100 test data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forecasting the amount of plywood sales using holt’s double exponential smoothing

引用

AIP Conference Proceedings 2023年第1期2693卷

作者： Nico Santosa Halim Agung Teady Matius Surya Mulyana Lukman Hakim Evaria Sipayung Informatics Study Program Technology and Design Faculty Bunda Mulia University Jakarta Indonesia Digital Business Study Program Technology and Design Faculty Bunda Mulia University Jakarta Indonesia

Forecasting is a science used to predict future events, forecasting activities are business functions used to predict sales or use of a product so it will be more efficient. Therefore, in a business, a forecasting system is needed to help predict the number of sales of an item, so that prediction can be used to estimate the supply of goods to be purchased or a profit. One of the forecasting methods that can be used in forecasting sales of goods is Holt’s Double Exponential Smoothing. This forecasting technique is used on data that has a trend but is not affected by seasons. In this method, 2 weight smoothing factors are used, namely α for level smoothing weights and β for weight smoothing trends From the results of this study using 28 months of data, from November 2018 to February 2021 obtained from Jaya Mandiri which is engaged in selling plywood. The prediction error value obtained using the Mean Absolute Percentage method during the train process was 4.651% while during the validation process an error was 4.989%. For alpha parameter with a value of 0.8 and beta of 0.2, the alpha and beta parameters used in the calculation have been searched automatically and the optimal alpha and beta values. The conclusion of this study are Holt’s Double Exponential Smoothing can be applied to these cases because the MAPE produced is below 10% both during processing and validation. This application is also successful in determining the optimal alpha and beta parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Atmospheric dynamics and early warning system low level windshear for airport runway hazard mitigations 10

Atmospheric dynamics and early warning system low level wind...

引用

10th International Seminar on New Paradigm and Innovation of Natural Sciences and itsApplication, ISNPINSA 2020

作者： Gernowo, R. Subagio, A. Adi, K. Widodo, A.P. Widodo, C.E. Putranto, A.B. Department of Physics Faculty of Science and Mathematics Diponegoro University Indonesia Department of Informatics Faculty of Science and Mathematics Diponegoro University Indonesia Study Program of Automation Engineering Technology Vocational School Diponegoro University Jl. Prof. Soedarto SH. Tembalang Semarang50275 Indonesia

Natural disaster nowadays often occur in Indonesia due to climate change, especially those related to atmospheric dynamics anomalies. The statutory event of atmospheric turbulence statistically is quite significant in its improvement. This is an important issue to conduct research both in the analysis of atmospheric dynamics and early detection solutions for these events. The Windshear phenomenon is an atmospheric turbulence disaster that occurs below an altitude of 3000 feet, often known as low level windshear (LLWS), which is very dangerous for planes taking take-off or landing. Its effect on the aircraft will result in increased airflow on the wings, so this increased airflow will result in a sudden increase in aircraft speed. If the pilot is not aware of the indication of the windshear, he will instinctively throttle back to reduce/compensate for the aircraft's speed. However, once the plane passes through the wind shear zone, the wind suddenly turns into a downdraft. The design of windshear early detection devices have been developed to complement research on the dynamics of the atmosphere. The results obtained are anomalous changes in temperature and atmospheric pressure at this time, and the windshear sensor can detect it well. © Published under licence by IOP Publishing Ltd.

关键词： Aircraft

来源：评论

学校读者我要写书评

暂无评论

The study of Coastline Changing and Total Suspended Solid Distribution Based on the Remote Sensing Data in Teluk Lamong Multipurpose Port Terminal 8

The Study of Coastline Changing and Total Suspended Solid Di...

引用

8th International Seminar on Ocean and Coastal Engineering, Environmental and Natural Disaster Management, ISOCEEN 2020

作者： Pratikto, Widi Agoes Fitriadhy, Ahmad Maulana, Muhammad Ilham Huda, Abiyani Choirul Putri, Destyariani Liana Simatupang, Liany Ayu Wahyudi, Nazariano Rahman Laksono, Rendatiyarso Dewi, Anggie Vibriyanti Rossari Ocean Engineering Departement Faculty of Marine Technology Institut Teknologi Sepuluh Nopember Surabaya60111 Indonesia Department of Maritime Technology Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Malaysia Ocean Engineering Study Program Institut Teknologi Kalimantan Kalimantan Timur76127 Indonesia

Looking forward to the abovementioned conditions, this research is needed to elaborate on the effects of the reclamation to the marine resources in Teluk Lamong Multipurpose Port Terminal as the reclaimed product. In order to describe the impact of the port development, this study will analyze the shoreline changing, the current pattern modeling, as well as the Total Suspended Solid (TSS) modeling using the remote sensing data. The several numbers of expected objectives through this study are to get the set of scientific information on the shoreline changing in Teluk Lamong Multipurpose Port Terminal in the year of 2012 and 2020, to get the figure of current pattern in Teluk Lamong Multipurpose Port Terminal in the year of 2012 and 2020, and to elaborate TSS concentration through the modeling approach in Teluk Lamong Multipurpose Port Terminal in the year of 2012 and 2020. Hence, there is a set of methodologies and tools to cooperate with the information before and after the reclamation. The use of the Digital Shoreline Analysis System (DSAS) software to analyze coastline conditions. The using of Mike 21 to analyze the current pattern and TSS concentrations. In addition to the TSS analysis, it will also need a set of remote sensing data from the Google Earth Engine (GEE). The modeling and calculation give information about the End Point Rate (EPR) values and TSS values. The EPR values are 107.5 m/year, 59,625 m/year and 10,375 m / year. The TSS values are 0-20 mg/L, 20.1-40 mg/L, 40.1-80 mg/L, 80.1-120 mg/L and >120.1 mg/L. Moreover, the result shows the different values among the length of coastline, the current pattern, and TTS in the years 2012 and 2020. The difference in the coastline reaches 950 m at this latest 8 years. While it also brings the changing to the current pattern and sediment transport which show through its current velocity and sediment content per liter of seawater during high and low tide accordingly. © Published under licence by IOP Publishing

关键词： Sediment transport

来源：评论

学校读者我要写书评

暂无评论

Modeling Object Recognition in Newborn Chicks using Deep Neural Networks 43

Modeling Object Recognition in Newborn Chicks using Deep Neu...

引用

43rd Annual Meeting of the Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci 2021

作者： Lee, Donsuk Pak, Denizhan Wood, Justin N. Department of Informatics Indiana University BloomingtonIN47408 United States Cognitive Science Program Indiana University BloomingtonIN47408 United States Center for the Integrated Study of Animal Behavior Indiana University BloomingtonIN47408 United States Department of Neuroscience Indiana University BloomingtonIN47408 United States

In recent years, the brain and cognitive sciences have made great strides developing a mechanistic understanding of object recognition in mature brains. Despite this progress, fundamental questions remain about the origins and computational foundations of object recognition. What learning algorithms underlie object recognition in newborn brains? Since newborn animals learn largely through unsupervised learning, we explored whether unsupervised learning algorithms can be used to predict the view-invariant object recognition behavior of newborn chicks. Specifically, we used feature representations derived from unsupervised deep neural networks (DNNs) as inputs to cognitive models of categorization. We show that features derived from unsupervised DNNs make competitive predictions about chick behavior compared to supervised features. More generally, we argue that linking controlled-rearing studies to image-computable DNN models opens new experimental avenues for studying the origins and computational basis of object recognition in newborn animals. © Cognitive Science Society: Comparative Cognition: Animal Minds, CogSci *** rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

K-Nearest Neighbor method for detecting egg quality conditions using Raspberry Pi 2

K-Nearest Neighbor method for detecting egg quality conditio...

引用

2nd Annual Conference of Science and Technology, ANCOSET 2020

作者： Ahsan, M. Nugraha, D.A. Yunus, A. Budianto, A.E. Setyaningsih, W. Firniawan, A. Susilowati, M. Informatics Study Program Faculty of Science and Technology Universitas PGRI Kanjuruhan Malang Jl. S. Supriadi No. 48 Malang Jawa Timur Indonesia Program Studi Sistem Informasi Fakultas Sain Dan Teknologi Universitas Ma Chung Malang Jl. Villa Puncak Tidar Blok N No. 1 Dau Jawa Timur Malang Indonesia

Food production in Indonesia is very strong and constrained, such as rice, corn, eggs and so on. Eggs that are consumed every day by Indonesian citizens, many consumers of egg food are not alert to the condition or condition of the eggs, whether they are feasible or expired. There are many studies related to the nature of eggs, egg quality and others, in part there is no modeling tool for detecting egg quality conditions based on raspberry pi using the K-Nearest Neighbor method which can be used to see good or bad eggs. In this study, the Raspberry Pi was used as the main component with the aid of a camera as an image capture on eggs using training data of 100 egg samples consisting of 50 good eggs and 50 bad eggs in order to get maximum accuracy. With the help of 2 led as a light source and the software uses the Python language. The purpose of this study was to obtain the expected accuracy by collecting 20 eggs randomly to get a percentage (17/20) ∗ 100 = 85%. © Published under licence by IOP Publishing Ltd.

关键词： Light sources

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：