scholarly journals Implementasi Algoritma You Only Look Once (YOLO) untuk Deteksi Korban Bencana Alam

2021 ◽  
Vol 8 (4) ◽  
pp. 787
Author(s):  
Moechammad Sarosa ◽  
Nailul Muna
Keyword(s):  
Image Processing ◽  
Natural Disasters ◽  
Natural Disaster ◽  
Test Data ◽  
Detection System ◽  
Training Data ◽  
Test Results ◽  
Disaster Victim ◽  
Rapid Evacuation

<p class="Abstrak">Bencana alam merupakan suatu peristiwa yang dapat menyebabkan kerusakan dan menciptakan kekacuan. Bangunan yang runtuh dapat menyebabkan cidera dan kematian pada korban. Lokasi dan waktu kejadian bencana alam yang tidak dapat diprediksi oleh manusia berpotensi memakan korban yang tidak sedikit. Oleh karena itu, untuk mengurangi korban yang banyak, setelah kejadian bencana alam, pertama yang harus dilakukan yaitu menemukan dan menyelamatkan korban yang terjebak. Penanganan evakuasi yang cepat harus dilakukan tim SAR untuk membantu korban. Namun pada kenyataannya, tim SAR mengalami kendala selama proses evakuasi korban. Mulai dari sulitnya medan yang dijangkau hingga terbatasnya peralatan yang dibutuhkan. Pada penelitian ini sistem diimplementasikan untuk deteksi korban bencana alam yang bertujuan untuk membantu mengembangkan peralatan tim SAR untuk menemukan korban bencana alam yang berbasis pengolahan citra. Algoritma yang digunakan untuk mendeteksi ada atau tidaknya korban pada gambar adalah <em>You Only Look Once</em> (YOLO). Terdapat dua macam algoritma YOLO yang diimplementasikan pada sistem yaitu YOLOv3 dan YOLOv3 Tiny. Dari hasil pengujian yang telah dilakukan didapatkan <em>F1 Score</em> mencapai 95.3% saat menggunakan YOLOv3 dengan menggunakan 100 data latih dan 100 data uji.</p><p class="Abstrak"> </p><p class="Abstrak"><strong><em>Abstract</em></strong></p><p class="Abstrak"> </p><p class="Abstract"><em>Natural disasters are events that can cause damage and create havoc. Buildings that collapse and can cause injury and death to victims. Humans can not predict the location and timing of natural disasters. After the natural disaster, the first thing to do is find and save trapped victims. The handling of rapid evacuation must be done by the SAR team to help victims to reduce the amount of loss due to natural disasters. But in reality, the process of evacuating victims of natural disasters is still a lot of obstacles experienced by the SAR team. It was starting from the difficulty of the terrain that is reached to the limited equipment needed. In this study, a natural disaster victim detection system was designed using image processing that aims to help find victims in difficult or vulnerable locations when directly reached by humans. In this study, a detection system for victims of natural disasters was implemented which aims to help develop equipment for the SAR team to find victims of natural disasters based on image processing. The algorithm used is You Only Look Once (YOLO). In this study, two types of YOLO algorithms were compared, namely YOLOv3 and YOLOv3 Tiny. From the test results that have been obtained, the F1 Score reaches 95.3% when using YOLOv3 with 100 training data and 100 test data.</em></p>

Implementation of Backpropagation for Ulap-ulap Pattern Recognition

2021 ◽  
Vol 9 (3) ◽  
pp. 405
Author(s):  
Ni Luh Yulia Alami Dewi ◽  
I Wayan Santiyasa
Keyword(s):  
Image Processing ◽  
Pattern Recognition ◽  
Data Collection ◽  
Test Data ◽  
Training Data ◽  
Image Pattern

Ulap-ulap is one of the symbols used to indicate that a building has been carried out Mlaspas ceremony. Mlaspas is one of the ceremonies performed to purify and clean a building. Ulap-ulap itself consists of various types depending on the building where it is placed, for example the ulap-ulap placed on the Pelinggih building will be different from the ulap-ulap placed on the Bale building. So that the pattern contained in each type of Ulap-ulap is different. The purpose of this research is to be able to do pattern recognition on Ulap-ulap images. The method used in this study is Backpropagation, and for its implementation, the MATLAB 7.5.0 (R2007b) application is used. This study used 18 images of Ulap-ulap, including 15 training data and 6 test data. The stages of the process carried out are for Ulap-ulap pattern recognition, the first is data collection, then image processing, and finally the pattern recognition. Recognition of the Ulap-ulap image pattern with Backpropagation, resulted in an accuracy of 83.333%.

scholarly journals Detection Of Spam Comments On Instagram Using Complementary Naïve Bayes

2019 ◽  
Vol 13 (3) ◽  
pp. 263
Author(s):  
Nur Azizul Haqimi ◽  
Nur Rokhman ◽  
Sigit Priyanta
Keyword(s):  
Social Media ◽  
Support Vector Machine ◽  
Test Data ◽  
Training Data ◽  
Classification Method ◽  
Support Vector ◽  
Test Results ◽  
Imbalanced Dataset ◽  
Web Based ◽  
F Measure

Instagram (IG) is a web-based and mobile social media application where users can share photos or videos with available features. Upload photos or videos with captions that contain an explanation of the photo or video that can reap spam comments. Comments on spam containing comments that are not relevant to the caption and photos. The problem that arises when identifying spam is non-spam comments are more dominant than spam comments so that it leads to the problem of the imbalanced dataset. A balanced dataset can influence the performance of a classification method. This is the focus of research related to the implementation of the CNB method in dealing with imbalance datasets for the detection of Instagram spam comments. The study used TF-IDF weighting with Support Vector Machine (SVM) as a comparison classification. Based on the test results with 2500 training data and 100 test data on the imbalanced dataset (25% spam and 75% non-spam), the CNB accuracy was 92%, precision 86% and f-measure 93%. Whereas SVM produces 87% accuracy, 79% precision, 88% f-measure. In conclusion, the CNB method is more suitable for detecting spam comments in cases of imbalanced datasets.

scholarly journals Sistem Pengelompokan Siswa Berdasarkan Tingkat Kedisiplinan Menggunakan Metode Naïve Bayes Classifier

2021 ◽  
Vol 9 (2) ◽  
pp. 50
Author(s):  
Budi Hartanto ◽  
Sri Tomo
Keyword(s):  
Test Data ◽  
Educational Process ◽  
Training Data ◽  
Student Discipline ◽  
Test Results ◽  
Bayes Classifier ◽  
Bayes Method ◽  
Important Thing ◽  
Class Test

Discipline is a very important thing in the educational process. Discipline will succeed if it is applied to students correctly. Student discipline is that every student follows every rule and order that has been set by the school. At SMK Muhammadiyah 2 Sukoharjo student discipline. Declining discipline at SMK Muhammadiah 2 Sukoharjo is marked by the increase in points of violation from students. The purpose of this study was to apply the nave Bayes method in the classification of student discipline levels at SMK Muhammadiyah 2 Sukoharjo. With this information will be obtained that can be used for information on which students need to be given Counseling Guidance to provide direction and guidance to students. The attributes used are cases of fights, not attending apples, not carrying out picket, not entering without explanation, arriving late, noisy in class. Test results with 490 records with a portion of 75% training data and 25% test data. And produces an accuracy of 76%.

scholarly journals Gorontalo Medicinal Plants Image Identification System Using Artificial Neural Network with Back Propagation

2018 ◽  
Vol 2 (2) ◽  
Author(s):  
Mukhlisulfatih Latief ◽  
Rampi Yusuf
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Artificial Neural Network ◽  
Medicinal Plants ◽  
Digital Image Processing ◽  
Test Data ◽  
Digital Image ◽  
Back Propagation ◽  
Training Data ◽  
Artificial Neural

The purpose of this research is to design the application of digital image processing system to identify the image of medicinal plants of Gorontalo region using artificial neural network method using back propagation. This research used a digital image processing method with segmentation and extraction techniques. Segmentation process was carried out using thresholding method. Furthermore, a process of characteristic extraction from medicinal plants drawings was carried out using feature and color feature extractions to obtain the value of metric, eccentricity, hue, saturation and value. these five values were used as parameters for input neurons and one output neuron which denoted the class of the medicinal plants image. Data of this research consisted of 91 images which had been divided into two types, training data and test data. The training data consisted of 80 images and the test data consisted of eleven images. A network architecture was obtained from the training result and it provided the highest accuracy level (100%) and least number of iteration with a number of 50 neurons on hidden layer and 143 epochs. The testing result showed a lower accuracy of 54.54%.

scholarly journals Implementasi fuzzy weighted product penyusunan aksi rehabilitasi rekonstruksi pasca bencana berbasis decision support system dynamic

JURNAL ELTEK ◽  
2020 ◽  
Vol 18 (1) ◽  
pp. 1
Author(s):  
Agung Teguh Almais ◽  
Fatchurrohman Fatchurrohman ◽  
Khadijah Fahmi Hayati Holle
Keyword(s):  
Decision Support ◽  
Decision Support System ◽  
Natural Disasters ◽  
Test Data ◽  
Support System ◽  
System Dynamic ◽  
Test Results ◽  
The Government

Penyusunan aksi rehabilitasi rekonstruksi pasca bencana alam dilakukan untuk mengetahui jenis kerusakan dan besarnya kerugian pasca bencana alam yang harus ditanggung pemerintah. Agar jenis kerusakan dan besarnya kerugian pasca bencana alam sesuai data yang dilapangan maka dilakukan penelitian yang mengimplementasikan Decision Support System Dynamic (DSSD) dengan metode Fuzzy-Weighted Product (F-WP). Hasil dari pengujian menghasilkan tiga jenis data yang berbeda yaitu data uji yang sama dengan data pola, data uji yang tidak sama dengan data pola, dan data uji yang tidak bisa diterpakan untuk pengujian. Masing-masing jenis data uji tersebut memilik prosentase yaitu 73% data uji yang sama dengan data pola, 22% data uji yang tidak sama dengan data pola, dan 5% merupakan data yang tidak dapat digunakan sebagai data uji. Dari hasil pengujian tersebut dapat disimpulkan bahwa metode Fuzzy-Weighted Product (F-WP) dapat diterapkan pada Decision Support System Dynamic (DSSD) untuk membantu surveyor dalam melakukan penyusunan aksi rehabilitasi rekonstruksi pasca bencana alam.   Preparation of rehabilitation reconstruction actions after natural disasters is carried out to determine the types of damage and the number of losses after natural disasters that must be borne by the government. So that the type of damage and the magnitude of losses after natural disasters match the data in the field, a study is carried out that implements a Decision Support System Dynamic (DSSD) with the Fuzzy-Weighted Product (F-WP) method. The results of tests produce three types of data that are different, namely the same test data with pattern data, test data that are not the same as pattern data, and test data that cannot be applied for testing. Each type of test data has a percentage that is 73% of the same test data like the pattern data, 22% of the test data are not the same as the pattern data, and 5% are data that cannot be used as test data. From the test results it can be concluded that the Fuzzy-Weighted Product (F-WP) method can be applied to the Decision Support System Dynamic (DSSD) to assist surveyors in carrying out the rehabilitation reconstruction actions after natural disasters.

scholarly journals Image Processing for Public Health Surveillance of Tobacco Point-of-Sale Advertising: A Machine Learning-Based Methodology (Preprint)

2020 ◽  
Author(s):  
Ned English ◽  
Andrew Anesetti-Rothermel ◽  
Chang Zhao ◽  
Andrew Latterner ◽  
Adam Benson ◽  
...  
Keyword(s):  
Public Health ◽  
Machine Learning ◽  
Image Processing ◽  
Detection System ◽  
Methodological Approach ◽  
Machine Learning Algorithms ◽  
Training Data ◽  
Retail Environment ◽  
Data Set ◽  
Point Of Sale

BACKGROUND With a rapidly evolving tobacco retail environment, it is increasingly necessary to understand the point of sale (POS) advertising environment as part of tobacco surveillance and control. Advances in machine learning and image processing suggest the ability for more efficient and more nuanced data capture than previously available. OBJECTIVE To employ machine learning algorithms to discover both the presence of tobacco advertising in photographs of tobacco POS advertising, as well as their location in the photograph. METHODS We first collected images of the interiors of tobacco retailers in West Virginia and the District of Columbia during 2016 and 2018. The clearest photos were selected and used to create a training and test data set. We then used a pre-trained image classification network model, Inception V3,to discover the presence of tobacco logos, as well as a unified object detection system, You Only Look Once (YOLO), to identify logo locations. RESULTS Our model was successful in identifying the presence of advertising within images, with a classification accuracy of over 75% for 8 of the 42 brands. Discovering the location of logos within a given photo was more challenging due to the relatively small training data set, resulting in a mean Average Precision (mAP) score of 72% and Intersection over Union (IOU) of 62%. CONCLUSIONS Our research provides evidence for a novel methodological approach that tobacco researchers and other public health practitioners can apply in the collection and processing of data for tobacco or other POS surveillance efforts. The resulting surveillance information can inform policy adoption, implementation, and enforcement. Limitations notwithstanding, our analysis shows the promise of using machine learning as part of a suite of tools to understand the tobacco retail environment, make policy recommendations, and design public health interventions at the municipal or other jurisdictional scale.

scholarly journals Akurasi Klasifikasi Pengguna terhadap Hotspot WiFi dengan Menggunakan Metode K-Nearest Neighbour

2021 ◽  
pp. 128-133
Author(s):  
Raemon S Saljumairi ◽  
Sarjon Defit ◽  
S Sumijan ◽  
Yusma Elda
Keyword(s):  
Test Data ◽  
Euclidean Distance ◽  
Nearest Neighbor ◽  
Access Point ◽  
Training Data ◽  
Test Results ◽  
K Nearest Neighbor ◽  
Accuracy Rate ◽  
3 Dimensional

The Current wireless technology is used to find out where the user is in the room. Utilization of WiFi strength signal from the Access Point (AP) can provide information on the user position in a room. Alternative determination of the user's position in the room using WiFi Receive Signal Strength (RSS). This research was conducted by comparing the distance between users to 2 or more APs using the euclidean distance technique. The Euclidean distance technique is used as a distance calculator where there are two points in a 3-dimensional plane or space by measuring the length of the segment connecting two points. This technique is best for representing the distance between the users and the AP. The collection of RSS data uses the Fingerprinting technique. The RSS data was collected from 20 APs detected using the wifi analyzer application, from the results of the scanning, 709 RSS data were obtained. The RSS value is used as training data. K-Nearest Neighbor (K-NN) uses the Neighborhood Classification as the predictive value of the new test data so that K-NN can classify the closest distance from the new test data to the value of the existing training data. Based on the test results obtained an accuracy rate of 95% with K is 3. Based on the results of research that has been done that using the K-NN method obtained excellent results, with the highest accuracy rate of 95% with a minimum error value of 5%

scholarly journals DETECTION OF TRAFFIC DENSITY WITH IMAGE PROCESSING USING PIN HOLE ALGORITHM

2022 ◽  
Vol 23 (1) ◽  
pp. 244-257
Author(s):  
Mochamad Aditya Irawanto ◽  
Casi Setianingsih ◽  
Budhi Irawan
Keyword(s):  
Image Processing ◽  
Traffic Congestion ◽  
Detection System ◽  
Traffic Density ◽  
Test Results ◽  
Traffic System ◽  
The Road ◽  
Congestion Detection ◽  
Grid Division ◽  
Good Detection

The intelligent traffic monitors are devloped and became more interst in recent years. A detection system in the monitoring traffic system is proposed using different algorithms. Pin Hole Algorithm used to detect the car that passes  the road (the studied area). A fixed camera mounted at predetermined point used with known height (of the camera), the intensity of the light, and the visibility of the camera. The classification process is important to know the traffic congestion status. The traffic congestion status will be sent to the server address already provided.  In the congestion detection test results were obtained with an accuracy value of 85% using the 64x64 grid division and obtaining good detection results for susceptible light intensity values between 5430 and 41379 LUX with an accuracy value of between 60% and 90%. ABSTRAK: Sejak beberapa tahun ini, sistem pengawasan trafik pintar telah dibina dan terus berkembang luas. Sistem pengesanan dalam sistem trafik pengawasan telah dicadangkan menggunakan pelbagai algoritma. Algoritma lubang pin digunakan bagi mengesan kereta yang melalui jalan (kawasan kajian). Kamera dipasang tetap pada titik tertentu iaitu dengan menyelaras ketinggian kamera, keamatan cahaya, dan kebolehlihatan kamera. Proses klasifikasi sangat penting bagi menentukan status kesesakan trafik. Status kesesakan trafik akan dihantar ke alamat pelayan yang telah disediakan. Nilai ketepatan ujian pengesanan kesesakan yang diperoleh adalah 85% iaitu menggunakan pembahagi grid 64x64 dan dapatan kajian menunjukkan pengesanan yang baik bagi nilai keamatan cahaya antara 5430 dan 41379 LUX dengan nilai ketepatan antara 60% dan 90%.

scholarly journals Evaluation of automated cephalometric analysis based on the latest deep learning method

2021 ◽  
Author(s):  
Hye-Won Hwang ◽  
Jun-Ho Moon ◽  
Min-Gyu Kim ◽  
Richard E. Donatelli ◽  
Shin-Jae Lee
Keyword(s):  
Deep Learning ◽  
Test Data ◽  
Training Data ◽  
Superior Performance ◽  
Cephalometric Analysis ◽  
Data Sets ◽  
Learning Method ◽  
Test Results ◽  
Classification Rate ◽  
Data Set

ABSTRACT Objectives To compare an automated cephalometric analysis based on the latest deep learning method of automatically identifying cephalometric landmarks (AI) with previously published AI according to the test style of the worldwide AI challenges at the International Symposium on Biomedical Imaging conferences held by the Institute of Electrical and Electronics Engineers (IEEE ISBI). Materials and Methods This latest AI was developed by using a total of 1983 cephalograms as training data. In the training procedures, a modification of a contemporary deep learning method, YOLO version 3 algorithm, was applied. Test data consisted of 200 cephalograms. To follow the same test style of the AI challenges at IEEE ISBI, a human examiner manually identified the IEEE ISBI-designated 19 cephalometric landmarks, both in training and test data sets, which were used as references for comparison. Then, the latest AI and another human examiner independently detected the same landmarks in the test data set. The test results were compared by the measures that appeared at IEEE ISBI: the success detection rate (SDR) and the success classification rates (SCR). Results SDR of the latest AI in the 2-mm range was 75.5% and SCR was 81.5%. These were greater than any other previous AIs. Compared to the human examiners, AI showed a superior success classification rate in some cephalometric analysis measures. Conclusions This latest AI seems to have superior performance compared to previous AI methods. It also seems to demonstrate cephalometric analysis comparable to human examiners.

When Mother Earth Rises Up

2013 ◽  
Vol 44 (4) ◽  
pp. 271-277 ◽  
Author(s):  
Simona Sacchi ◽  
Paolo Riva ◽  
Marco Brambilla
Keyword(s):  
Free Will ◽  
Natural Disasters ◽  
Natural Disaster ◽  
Mental States ◽  
Disaster Victims ◽  
Willingness To Help ◽  
Mother Earth

Anthropomorphization is the tendency to ascribe humanlike features and mental states, such as free will and consciousness, to nonhuman beings or inanimate agents. Two studies investigated the consequences of the anthropomorphization of nature on people’s willingness to help victims of natural disasters. Study 1 (N = 96) showed that the humanization of nature correlated negatively with willingness to help natural disaster victims. Study 2 (N = 52) tested for causality, showing that the anthropomorphization of nature reduced participants’ intentions to help the victims. Overall, our findings suggest that humanizing nature undermines the tendency to support victims of natural disasters.

Sign in / Sign up

Export Citation Format

Share Document