scholarly journals Identification of Freshness of Marine Fish Based on Image of Hue Saturation Value and Morphology

Jurnal INFORM ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 40-48
Author(s):  
Ekojono Ekojono ◽  
Al Wegi Herman ◽  
Mentari Mustika
Keyword(s):  
Nearest Neighbor ◽  
The Body ◽  
K Nearest Neighbor ◽  
The People ◽  
Image Conversion ◽  
Object Part ◽  
A Cell ◽  
Protein Amino Acids ◽  
Image Object ◽  
Rgb Image

Euthynus is one of the fish that is widely consumed for the enjoyment of the people of Indonesia or abroad, because of its very soft quality, easy to obtain, and contains a lot of essential protein amino acids that are good for the body. This research aims to identify the freshness of the fish purchased based on the eyes and fish gills. The initial process of identifying the freshness of fish uses several methods. Image input process through image object taking using a cell phone camera. The image object is used to determine the value of the RGB image object. RGB color extraction clarifies the value obtained from the image object before proceeding to the next process. Image resize is the process of cutting the image on the desired object part. Image conversion using the HSV method was used to determine the freshness of fish in the gills. The Local Binary Pattern method is used to determine the freshness of the fisheye. The next step is to refine the RGB image into Morphology. The KNN (K-Nearest Neighbor Method) method is used to group objects based on learning data closest to the object. The journal analysis results on the comparison of methods, after 45 trials for each method, found that the Hue Saturation Value method obtained the highest success by 90% and for the texture value obtained 85% success.

scholarly journals PERANCANGAN SISTEM KLASIFIKASI UDANG BERACUN PADA JENIS UDANG TENGGEK MENGGUNAKAN METODE K-NEAREST NEIGHBOR (K-NN).

2020 ◽  
Vol 6 (1) ◽  
pp. 1-7
Author(s):  
Lisa Afrinanda ◽  
Ilyas Ilyas
Keyword(s):  
Data Mining ◽  
Image Processing ◽  
Nearest Neighbor ◽  
The Body ◽  
K Nearest Neighbor ◽  
Class A ◽  
The People ◽  
Average Accuracy ◽  
Class B

Shrimp is one of the seafood which is nutrient-rich needed by the body. However, due to the frequent case of the infected Tenggek-shrimp appeared, it makes people beware to consume it. The classification of Tenggek-shrimp by using image processing of the computer be able to classify the types of shrimp whether poisonous or not. The data mining techniques can be used to classify shrimp based on RGB colors (red, green, blue) and texture (energy, contrast, correlation, homogeneity). The class of Tenggek-shrimp is divided into two, The fresh Tenggek-shrimps that are caught naturally (Class A) and the poisoned Tenggek-shrimps that are caught by using the poison (Class B). The method used in this study is K-Nearest Neighbor (K-NN). This classification system is expected to help the people in selecting good and safe Tenggek-shrimp for consumption. Based on the evaluation results using the holdout method, obtained an average accuracy of 63% with an accuracy of identification of toxic tenggek shrimp of 71.66%, and the accuracy of identification of natural fresh shrimp is about 60%.

scholarly journals Skin Cancer Detection and Classification using KNN Technique

2021 ◽  
Vol 9 (VI) ◽  
pp. 3520-3527
Author(s):  
Apeksha R Swamy
Keyword(s):  
Skin Cancer ◽  
Cancer Detection ◽  
Nearest Neighbor ◽  
Early Stage ◽  
The Body ◽  
K Nearest Neighbor ◽  
Fast Evaluation ◽  
Efficient Treatment ◽  
Medical Computer ◽  
Skin Cancer Detection

Skin cancer is a major health issue worldwide. Skin cancer detection at an early stage is key for an efficient treatment. Lately, it is popular that, deadly form of skin cancer among the other types of skin cancer is melanoma because it's much more likely to spread to other parts of the body if not identified and treated early. The advanced medical computer vision or medical image processing take part in increasingly significant role in clinical detection of different diseases. Such method provides an automatic image analysis device for an accurate and fast evaluation of the sore. The steps involved in this project are collecting skin cancer images from PH2 database, preprocessing, segmentation using thresholding, feature extraction and then classification using K-Nearest Neighbor technique (KNN). The results show that the achieved classification accuracy is 92.7%, Sensitivity 100% and 84.44% Specificity.

scholarly journals Application of K-Nearest Neighbor Algorithm on Classification of Disk Hernia and Spondylolisthesis in Vertebral Column

2019 ◽  
Vol 2 (1) ◽  
pp. 57 ◽  
Author(s):  
Irma Handayani
Keyword(s):  
Vertebral Column ◽  
Nearest Neighbor ◽  
Average Length ◽  
Data Classification ◽  
The Body ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Sample Data ◽  
K Nearest Neighbor Algorithm

Vertebral column as a part of backbone has important role in human body. Trauma in vertebral column can affect spinal cord capability to send and receive messages from brain to the body system that controls sensory and motoric movement. Disk hernia and spondylolisthesis are examples of pathologies on the vertebral column. Research about pathology or damage bones and joints of skeletal system classification is rare whereas the classification system can be used by radiologists as a second opinion so that can improve productivity and diagnosis consistency of the radiologists. This research used dataset Vertebral Column that has three classes (Disk Hernia, Spondylolisthesis and Normal) and instances in UCI Machine Learning. This research applied the K-NN algorithm for classification of disk hernia and spondylolisthesis in vertebral column. The data were then classified into two different but related classification tasks: “normal” and “abnormal”. K-NN algorithm adopts the approach of data classification by optimizing sample data that can be used as a reference for training data to produce vertebral column data classification based on the learning process. The results showed that the accuracy of K-NN classifier was 83%. The average length of time needed to classify the K-NN classifier was 0.000212303 seconds.

scholarly journals Implementation Of K-Nearest Neighbor - Certainty Factor For Expert System Detection Of Idiopathic Thrombocytopenic Purpura

2021 ◽  
Vol 328 ◽  
pp. 04009
Author(s):  
Eva Y. Puspaningrum ◽  
Budi Nugroho ◽  
Dwi Putri Safira
Keyword(s):  
Expert System ◽  
Idiopathic Thrombocytopenic Purpura ◽  
Nearest Neighbor ◽  
Autoimmune Disorder ◽  
The Body ◽  
K Nearest Neighbor ◽  
Certainty Factor ◽  
Thrombocytopenic Purpura ◽  
Parameter Values ◽  
Test Scenarios

Idiopathic Thrombocytopenic Purpura (ITP) is an autoimmune disorder. ITP can occur in children and adults. This disease can be fatal because the platelet count is low due to the destruction of excessive platelets so that it can interfere with vital organs and bleeding occurs. The lack of knowledge of ordinary people about ITP disease, so many people assume that bruises and nosebleeds on the body are caused by fatigue. For that, we need a system that can imitate the expertise of an expert in diagnosing this disease based on the symptoms felt. The method used to support the expert system is the K-Nearest Neighbor and Certainty Factor methods which are a combination of 2 methods, where the classification results from the K-Nearest Neighbor method will be given a certainty value by the Certainty Factor method so as to produce a prediction. The results of combining the two methods can produce certainty in the diagnosis. Based on the test results using 3 test scenarios using parameter values k=3, k=5, k=7 and the results obtained the highest accuracy value with parameter value k=7 obtained an accuracy rate of 90,9%.

Analysis on Ensemble Methods for the Prediction of Cardiovascular Disease

2021 ◽  
Vol 11 (10) ◽  
pp. 2529-2537
Author(s):  
C. Murale ◽  
M. Sundarambal ◽  
R. Nedunchezhian
Keyword(s):  
Cardiac Disease ◽  
Nearest Neighbor ◽  
Naive Bayes ◽  
Ensemble Methods ◽  
Naïve Bayes ◽  
K Nearest Neighbor ◽  
Reduced Dimensions ◽  
The People ◽  
Ensemble Algorithms ◽  
Better Than

Coronary Heart disease is one of the dominant sources of death and morbidity for the people worldwide. The identification of cardiac disease in the clinical review is considered one of the main problems. As the amount of data grows increasingly, interpretation and retrieval become even more complex. In addition, the Ensemble learning prediction model seems to be an important fact in this area of study. The prime aim of this paper is also to forecast CHD accurately. This paper is intended to offer a modern paradigm for prediction of cardiovascular diseases with the use of such processes such as pre-processing, detection of features, feature selection and classification. The pre-processing will initially be performed using the ordinal encoding technique, and the statistical and the features of higher order are extracted using the Fisher algorithm. Later, the minimization of record and attribute is performed, in which principle component analysis performs its extensive part in figuring out the “curse of dimensionality.” Lastly, the process of prediction is carried out by the different Ensemble models (SVM, Gaussian Naïve Bayes, Random forest, K-nearest neighbor, Logistic regression, decision tree and Multilayer perceptron that intake the features with reduced dimensions. Finally, in comparison to such success metrics the reliability of the proposal work is compared and its superiority has been confirmed. From the analysis, Naïve bayes with regards to accuracy is 98.4% better than other Ensemble algorithms.

scholarly journals Komparasi Algoritma Naive Bayes dan K-Nearest Neighbor untuk Membangun Pengetahuan Diagnosa Penyakit Diabetes

2021 ◽  
Vol 5 (1) ◽  
pp. 52-59
Author(s):  
Maulidya Dwi Nurmalasari ◽  
Kusrini Kusrini ◽  
Sudarmawan Sudarmawan
Keyword(s):  
Environmental Factors ◽  
Blood Sugar ◽  
Nearest Neighbor ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
The Body ◽  
K Nearest Neighbor ◽  
Lower Blood ◽  
Genetic And Environmental Factors ◽  
Sugar Levels

Diabetes is caused by a deficiency of the hormone insulin, which is secreted by the pancreas to lower blood sugar levels. The factors that trigger the occurrence of diabetes are derived from various factors such as a combination of genetic and environmental factors. The phenomenon of the emergence of various beverage brand outlets can be one of the triggers for blood sugar levels in humans. Normal blood sugar levels in the body range from 70-130 mg/dL before eating, less than 180 mg/dL two hours after eating, less than 100 mg/dL after not eating or surviving for eight hours, and 100-140 mg/dL at bedtime. This research aims to determine which algorithm is suitable for building knowledge about diabetes using the Naïve Bayes and K-Nearest Neighbor (KNN) algorithm. The accuracy results from Naïve Bayes are 85.60% and K- Nearest Neighbor of 91.61%. The results showed that K-Nearest Neighbor proved to have the best accuracy.

scholarly journals Case Based Reasoning Diagnosis Penyakit Difteri dengan Algoritma K-Nearest Neighbor

2018 ◽  
Vol 4 (3) ◽  
pp. 220 ◽  
Author(s):  
Chavid Syukri Fatoni ◽  
Friandy Dwi Noviandha
Keyword(s):  
Nearest Neighbor ◽  
Public Awareness ◽  
Public Knowledge ◽  
Case Based Reasoning ◽  
K Nearest Neighbor ◽  
K Nearest Neighbors ◽  
The Public ◽  
The People ◽  
The Government

Akhir tahun 2017, masyarakat Indonesia ramai dengan maraknya kematian pada anakanak dan orang dewasa akibat penyakit Difteri. Ditemukan sebanyak 12 orang meninggal dunia dari 318 kasus Difteri menurut catatan Dinas Kesehatan Jawa Timur. Padahal di tahun 2016 kasus Difteri di Jawa Timur tercatat sebanyak 4 orang meninggal dunia dari 209 kasus. Hal tersebut menjadi perhatian bagi pemerintah dan tercatat sebagai kejadian luar biasa (KLB). Kenaikan angka kasus Difteri ini disebabkan karena kurangnya kesadaran masyarakat akan pentingnya imunisasi. Semakin banyaknya kasus Difteri yang terjadi dan minimnya pengetahuan masyarakat tentang Difteri, maka dibutuhkan suatu sistem pakar yang mampu membantu masyarakat maupun pemerintah dalam mendiagnosis penyakit Difteri. Penelitian mengenai Difteri ini menggunakan metode algoritma K-Nearest Neighbour (K-NN) dimana dilakukan perhitungan similaritas pada kasus lama dengan kasus baru. Penelitian penyakit Difteri ini disempurnakan dengan menggunakan penalaran berbasis kasus atau Cased Based Reasoning (CBR) agar hasil diagnosis lebih akurat. Output dari penelitian ini yaitu berupa hasil diagnosa penyakit Difteri berdasarkan gejala-gejala yang dialami dengan hasil akurasi pengujiannya sebesar 95,17%.End of 2017, the people of Indonesia enlivened so many of deaths in children and adults due to Diphtheria. Found 12 people died from 318 cases of Diphtheria according to East Java Health Office records. Whereas in the year 2016 Diphtheria cases in East Java recorded and reported as many as 4 people died from 209 cases. It's of particular concern to government and is noted as an extraordinary event (KLB). The increase in the number of Diphtheria cases is due to a lack of public awareness of the importance of immunization. Increasing number of Diphtheria cases and the lack of public knowledge about Diphtheria, it needs an expert system capable of assisting the public and the government in diagnosing Diphtheria. This research on Diphtheria uses the K-Nearest Neighbors (K-NN) algorithm method in which a similarity case study in the old case with new cases is used. The research of Diphtheria disease is enhanced by using casebased reasoning or Cased Based Reasoning (CBR) to make the diagnosis more accurate. The output of this research is the result of diagnosis of Diphtheria disease based on the symptoms experienced by the result of the accuracy of the test is 95,17%.

scholarly journals Diagnosing Diabetes with Extended Binary Cuckoo Search and k-Nearest Neighbor Classifier

2020 ◽  
Vol 55 (2) ◽  
Author(s):  
Shaymaa Abdul Hussein Shnain ◽  
Zahraa Modher Nabat ◽  
May A. Salih ◽  
Baydaa Jaffer Al Khafaji
Keyword(s):  
Nearest Neighbor ◽  
Cuckoo Search ◽  
Disease Diagnosis ◽  
The Body ◽  
Common Disease ◽  
K Nearest Neighbor ◽  
Using Data ◽  
Early Diagnosis Of Diabetes ◽  
Neighbor Classification ◽  
Neighbor Classifier

Diabetes is a common disease that develops at different ages. Sometimes the body of an individual who has diabetes either doesn’t need insulin or is resistant against insulin. Today, medical scientists and doctors face large amount of data. Since disease diagnosis is not simple work, in order to make a suitable decision, the doctor should investigate the patients’ tests’ results and the decisions that have been made for patients with the same status before. Using data-mining methods can help the early diagnosis of diabetes, which helps prevent this disease and a lot of its complications, such as cardiovascular disease, vision problems and nephrogenic disease. In this approach, k-nearest neighbor classification is used for classification and extended binary cuckoo search uses UC Irvine Machine Learning Repository UCI learning storage to select the diagnosis features of diabetes disease in a dataset of diabetes diseases. For classifying diabetes diseases, the research provides a system of diagnosis by utilizing the binary cuckoo search-optimized rough collections-based reduction of features and the classifier of k-nearest neighbor.

scholarly journals Implementasi Algoritma Naïve Bayes dan K-Nearest Neighbor Dalam Menentukan Tingkat Keberhasilan Immunotherapy Untuk Pengobatan Penyakit Kanker Kulit

2021 ◽  
Vol 21 (1) ◽  
pp. 259
Author(s):  
F Lia Dwi Cahyanti ◽  
Windu Gata ◽  
Fajar Sarasati
Keyword(s):  
Skin Cancer ◽  
Success Rate ◽  
Nearest Neighbor ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
The Body ◽  
Ultraviolet Rays ◽  
Test Results ◽  
K Nearest Neighbor ◽  
Process Data

Cancer is a disease that grows in the skin tissue where this condition is characterized by changes in the skin, such as the appearance of lumps, spots, or moles with abnormal sizes, one of the causes of skin cancer is exposure to ultraviolet rays from the sun. One of the treatments for skin cancer is immunotherapy, the immunotherapy method is the treatment of disease by activating or suppressing the immune system in the body. In this study, a comparison with data mining methods for classification was carried out, namely Naïve Bayes and K-Nearest Neighbor to predict the success rate of immunotherapy in curing skin cancer. In the testing process, the researcher uses the Weka application to process data and conduct tests. The results of the tests that have been carried out show that the K-Nearest Neighbor model has the best accuracy value of 91.1111%. while Naïve Bayes obtained a smaller accuracy value, namely 82.2222%. From the test results, it can be concluded that the K-Nearest Neighbor method has better accuracy in determining the success rate of immunotherapy.

scholarly journals Performance Modeling of Classification Techniques on Movie Sentiments

2019 ◽  
Vol 9 (2) ◽  
pp. 1125-1131
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Performance Modeling ◽  
Nearest Neighbor ◽  
Hybrid Approach ◽  
K Nearest Neighbor ◽  
Classification Techniques ◽  
The People ◽  
Data Survey ◽  
Precision And Accuracy

The sentiment-based social media represents a goldmine approach for analyzing the performance of the products, hotels, movies, politics, etc. Large opinions of the people are found over movie comments that are honest, informative, and casual as compared to the formal type of data-survey modeling using magazines or reports. The work proposed is based on the rating of movies. This paper analyzes the performance of classifiers for the prediction of sentiment class i.e., positive and negative by using artificial neural network, k-nearest neighbor and hybrid approach. The success of these classification techniques depends mainly on the appropriate extraction of the set of characteristics used to detect sentiments. Hybrid of two or more classifiers is mainly used to enhance the results. In the proposed experiment Hybrid of ANN and KNN shows improvement in precision and accuracy than other classifiers.

Sign in / Sign up

Export Citation Format

Share Document