Klasifikasi Mutu Telur Burung Puyuh Berdasarkan Warna dan Tekstur Menggunakan Metode K-Nearest Neighbor (KNN) dan Fusi Informasi

Kualitas produk merupakan faktor utama untuk menjamin keberlangsungan satu usaha peternakan. Perusahaan telur puyuh yang memiliki ribuan burung Puyuh seperti CV. NS Quail Farm mampu memproduksi ribuan telur dalam sehari karena seekor burung Puyuh mampu menghasilkan 250-300 butir telur per tahun. Penyeleksian ribuan telur-telur tersebut dilakukan secara tradisional oleh para pekerja peternakan sehingga kualitas telur-telur hasil seleksi bergantung pada perspektif masing-masing pekerja. Guna memperoleh telur hasil seleksi dengan kualitas yang sama, maka dibangun sebuah sistem pencitraan digital untuk pemilihan telur burung Puyuh berdasarkan fitur warna dan tekstur kulit telur menggunakan metode klasifikasi K-Nearest Neighbor (KNN) yang dikombinasikan dengan fusi informasi. 300 data citra telur burung Puyuh diolah menggunakan normalisasi Red, Green, Blue (RGB) dan Otsu thresholding guna memperoleh fitur warna dan fitur tekstur yang kemudian difusikan menjadi fitur terfusi tunggal sebagai masukan pengklasifikasi KNN. Dari hasil-hasil penelitian, disimpulkan bahwa sistem berhasil mengklasifikasikan mutu telur Baik, Sedang, dan Buruk dengan akurasi rata-rata sebesar 77,78%. Disamping itu, klasifikasi dengan fusi informasi mampu mengungguli klasifikasi tanpa fusi informasi sebesar 11,11% pada nilai yang sama yakni 7 dan fusi informasi juga mampu mempercepat proses klasifikasi sebesar 0,22 detik dibandingkan terhadap klasifikasi tanpa fusi informasi.AbstractThe quality of product us a primary factor to ensure the sustainability of a farm business. A company which has thousands of quail such as CV. NS Quail is capable of producing thousand quail eggs in a day because a quail is able to produce 250-300 eggs per year. The selection of the eggs is carried out traditionally by the farm workers so that the quality of the selected eggs are depended on the perspective of each worker. In order to obtain the same quality of the selected eggs, a digital imaging system for quail egg selection based on color feature and texture feature using K-Nearest Neighbor (KNN) combined with information fusion is developed. 300 image data of quail egg was processed using Red, Green, Blue (RGB) and Otsu thresholding to obtain color feature and texture feature which then were fused to become single fused feature as the input to KNN classifier. From the research results, it is concluded that the system was managed to classify egg quality as good, medium, and bad with an accuracy of 77,78%. In addition, the classification with information fusion was able to outperform the classification without information fusion by 11.11% at the same value of 7 and information fusion is also able to accelerate classification process by 0.22 seconds compared to that of without information fusion.

Download Full-text

Pengenalan Jenis Tanaman Mangga Berdasarkan Bentuk dan Tekstur Daun Menggunakan Kecerdasan Artifisial K-NearestNeighbor (KNN) dan Fusi Informasi

Jurnal Teknologi Informasi dan Ilmu Komputer ◽

10.25126/jtiik.2021844392 ◽

2021 ◽

Vol 8 (4) ◽

pp. 777

Author(s):

Arwin Datumaya Wahyudi Sumari ◽

Muhammad Rifky Syahbana ◽

Mustika Mentari

Keyword(s):

Information Fusion ◽

Local Binary Pattern ◽

Nearest Neighbor ◽

Imaging System ◽

Leaf Shape ◽

Texture Feature ◽

Image Data ◽

K Nearest Neighbor ◽

Speed Up ◽

The Right

Memilih tanaman mangga yang sesuai dengan yang diinginkan menjadi sebuah tantangan dihadapkan pada tanaman marga Mangifera yang ada saat ini. Kesalahan pemilihan jenis tanaman mangga dapat menyebabkan kekecewaan pada pembeli dan menurunkan kepercayaan kepada penjual tanaman mangga karena dapat dianggap memberikan jenis tanaman yang salah. Permasalahannya adalah jenis tanaman mangga dapat diketahui setelah tanaman tersebut berbuah. Oleh karena itu, dalam upaya mereduksi kesalahan dalam pemilihan sebelum melakukan pembelian tanaman mangga, maka dirancang dan dibangun sebuah sistem pencitraan digital untuk pengenalan jenis tanaman mangga berdasarkan bentuk dan tekstur daun menggunakan metode Kecerdasan Artifisial K-Nearest Neighbor (KNN) yang digabungkan dengan Fusi Informasi guna memperoleh hasil klasifikasi dengan akurasi yang lebih baik. Data citra daun empat macam daun tanaman mangga yakni jenis Gadung, Lalijiwo, Golek dan Irwin, diproses menggunakan metode Local Binary Pattern (LBP) dan Entropy untuk ekstraksi fitur tekstur, dan metode Rectangularity untuk ekstraksi fitur bentuk. Kedua macam fitur tersebut difusikan menjadi masukan bagi pengklasifikasi KNN. Berdasarkan dari hasil-hasil pengujian, K-NN berhasil mengenali keempat jenis tanaman mangga tersebut dengan akurasi tertinggi sebesar 70% pada nilai K = 5, K = 9, K = 10 dan K = 11. Dari hasil pengujian juga diperoleh hasil bahwa fusi informasi mampu mempercepat sistem mengenali jenis tanaman mangga sebesar 0,11 detik. AbstractChoosing the right desired Mango plant is a challenge faced with various types of the existing Mangifera clan plants. The wrong choice of Mango plant species can end up with buyer disappointment and reduce the trust to the seller because it can be considered as providing the wrong type of plant. This happened because the type of Mango plant can only be identified after it bears fruit. In the effort to reduce such error, a digital imaging system was designed and built for recognizing the types of Mango plants based on the leaf shape and texture using Artificial Intelligence’s K-Nearest Neighbor (KNN) combined with Information Fusion to accelerate the classification with a consistent classification results. The image data consists of four kinds of Mango plant leaves, namely Gadung, Lalijiwo, Golek and Irwin. The leaf texture feature was extracted using the Local Binary Pattern (LBP) and Entropy methods, while the leaf shape feature was extracted using the Rectangularity method. The two features are fused as the input for the KNN classifier. Based on the test results, KNN was able to identify the four types of the Mango plant with the highest accuracy of 70% at values of K = 5, K = 9, K = 10, and K = 11. Besides that, it is also obtained a result that, the information fusion is able to speed up the recognition the types of Mango by 0.11 seconds.

Download Full-text

IMPLEMENTASI ALGORITMA K-NEAREST NEIGHBOR UNTUK PENENTUAN KELULUSAN MAHASISWA TEPAT WAKTU

JURNAL PERANGKAT LUNAK ◽

10.32520/jupel.v2i1.944 ◽

2020 ◽

Vol 2 (1) ◽

pp. 1-14

Author(s):

Torkis Nasution

Keyword(s):

Nearest Neighbor ◽

K Nearest Neighbor ◽

Academic Quality ◽

K Value ◽

Entrance Exam ◽

Maximum Accuracy ◽

Data Clusters ◽

New Students ◽

Data Group

The selection was an attempt College to get qualified prospective students. Test data for new students able to describe the quality of academic and connect to graduate on time. Recognizing the academic quality of students is required in the implementation of the lecture to obtain optimal results. Real conditions today, timely graduation has not achieved optimally, need to be improved to reach the limits of reasonableness. Data that has no need to do a classification based on academic quality, in order to obtain predictions timely graduation. Therefore, proposed an effort to resolve the problem by applying the K-Nearest Neighbor algorithm to re-clustering the test result data for new students. The procedure is to determine the amount of data clusters, determining the center point of the cluster, calculate the distance of the object with the centroid, classifying objects. If the new data group calculation results together with the results of calculation of new data group then finished its calculations. The data will be used in clustering is the result of the entrance exam for new students 3 years old, and has been declared STMIK Amik Riau. This study aims to predict the graduation on time or not. Results of research on testing the value of k, maximum accuracy is obtained when k = 5, reaching 99.25%. Accuracy will decline if the k value the greater the more inaccurate results. The data will be used in clustering is the result of the entrance exam for new students 3 years old, and has been declared STMIK Amik Riau. This study aims to predict the graduation on time or not. Results of research on testing the value of k, maximum accuracy is obtained when k = 5, reaching 99.25%. Accuracy will decline if the k value the greater the more inaccurate results. The data will be used in clustering is the result of the entrance exam for new students 3 years old, and has been declared STMIK Amik Riau. This study aims to predict the graduation on time or not. Results of research on testing the value of k, maximum accuracy is obtained when k = 5, reaching 99.25%. Accuracy will decline if the k value the greater the more inaccurate results.

Download Full-text

Land Cover Classification Using the Proposed Texture Model and Fuzzy k-NN Classifier

Optimization Techniques for Problem Solving in Uncertainty - Advances in Data Mining and Database Management ◽

10.4018/978-1-5225-5091-4.ch009 ◽

2018 ◽

pp. 226-261

Author(s):

Jenicka S.

Keyword(s):

Nearest Neighbor ◽

Confusion Matrix ◽

Texture Feature ◽

Image Texture ◽

Kappa Statistics ◽

Grey Level ◽

Classification Problems ◽

K Nearest Neighbor ◽

Texture Model ◽

Proposed Model

Texture feature is a decisive factor in pattern classification problems because texture features are not deduced from the intensity of current pixel but from the grey level intensity variations of current pixel with its neighbors. In this chapter, a new texture model called multivariate binary threshold pattern (MBTP) has been proposed with five discrete levels such as -9, -1, 0, 1, and 9 characterizing the grey level intensity variations of the center pixel with its neighbors in the local neighborhood of each band in a multispectral image. Texture-based classification has been performed with the proposed model using fuzzy k-nearest neighbor (fuzzy k-NN) algorithm on IRS-P6, LISS-IV data, and the results have been evaluated based on confusion matrix, classification accuracy, and Kappa statistics. From the experiments, it is found that the proposed model outperforms other chosen existing texture models.

Download Full-text

KLASIFIKASI PENGGUNAAN PROTOKOL KOMUNIKASI PADA TRAFIK JARINGAN MENGGUNAKAN ALGORITMA K-NEAREST NEIGHBOR

Majalah Ilmiah Teknologi Elektro ◽

10.24843/mite.1601.10 ◽

2016 ◽

Vol 16 (1) ◽

pp. 67

Author(s):

Komang Kompyang Agus Subrata ◽

I Made Oka Widyantara ◽

Linawati Linawati

Keyword(s):

Quality Of Service ◽

Network Traffic ◽

Network Architecture ◽

Nearest Neighbor ◽

Computer Network ◽

Data Communication ◽

Data Capture ◽

K Nearest Neighbor ◽

High Level

ABSTRACT—Network traffic internet is data communication in a network characterized by a set of statistical flow with the application of a structured pattern. Structured pattern in question is the information from the packet header data. Proper classification to an Internet traffic is very important to do, especially in terms of the design of the network architecture, network management and network security. The analysis of computer network traffic is one way to know the use of the computer network communication protocol, so it can be the basis for determining the priority of Quality of Service (QoS). QoS is the basis for giving priority to analyzing the network traffic data. In this study the classification of the data capture network traffic that though the use of K-Neaerest Neighbor algorithm (K-NN). Tools used to capture network traffic that wireshark application. From the observation of the dataset and the network traffic through the calculation process using K-NN algorithm obtained a result that the value generated by the K-NN classification has a very high level of accuracy. This is evidenced by the results of calculations which reached 99.14%, ie by calculating k = 3. Intisari—Trafik jaringan internet adalah lalu lintas komunikasi data dalam jaringan yang ditandai dengan satu set aliran statistik dengan penerapan pola terstruktur. Pola terstruktur yang dimaksud adalah informasi dari header paket data. Klasifikasi yang tepat terhadap sebuah trafik internet sangat penting dilakukan terutama dalam hal disain perancangan arsitektur jaringan, manajemen jaringan dan keamanan jaringan. Analisa terhadap suatu trafik jaringan komputer merupakan salah satu cara mengetahui penggunaan protokol komunikasi jaringan komputer, sehingga dapat menjadi dasar penentuan prioritas Quality of Service (QoS). Dasar pemberian prioritas QoS adalah dengan penganalisaan terhadap data trafik jaringan. Pada penelitian ini melakukan klasifikasi terhadap data capture trafik jaringan yang di olah menggunakan Algoritma K-Neaerest Neighbor (K-NN). Aplikasi yang digunakan untuk capture trafik jaringan yaitu aplikasi wireshark. Hasil observasi terhadap dataset trafik jaringan dan melalui proses perhitungan menggunakan Algoritma K-NN didapatkan sebuah hasil bahwa nilai yang dihasilkan oleh klasifikasi K-NN memiliki tingkat keakuratan yang sangat tinggi. Hal ini dibuktikan dengan hasil perhitungan yang mencapai nilai 99,14 % yaitu dengan perhitungan k = 3. DOI: 10.24843/MITE.1601.10

Download Full-text

Transfer Learning-Based Search Model for Hot Pepper Diseases and Pests

Agriculture ◽

10.3390/agriculture10100439 ◽

2020 ◽

Vol 10 (10) ◽

pp. 439 ◽

Cited By ~ 1

Author(s):

Helin Yin ◽

Yeong Hyeon Gu ◽

Chang-Jin Park ◽

Jong-Han Park ◽

Seong Joon Yoo

Keyword(s):

Nearest Neighbor ◽

Image Data ◽

Performance Comparison ◽

Classification Model ◽

Search Model ◽

Hot Pepper ◽

Final Decision ◽

Image Search ◽

K Nearest Neighbor ◽

Search Results

The use of conventional classification techniques to recognize diseases and pests can lead to an incorrect judgment on whether crops are diseased or not. Additionally, hot pepper diseases, such as “anthracnose” and “bacterial spot” can be erroneously judged, leading to incorrect disease recognition. To address these issues, multi-recognition methods, such as Google Cloud Vision, suggest multiple disease candidates and allow the user to make the final decision. Similarity-based image search techniques, along with multi-recognition, can also be used for this purpose. Content-based image retrieval techniques have been used in several conventional similarity-based image searches, using descriptors to extract features such as the image color and edge. In this study, we use eight pre-trained deep learning models (VGG16, VGG19, Resnet 50, etc.) to extract the deep features from images. We conducted experiments using 28,011 image data of 34 types of hot pepper diseases and pests. The search results for diseases and pests were similar to query images with deep features using the k-nearest neighbor method. In top-1 to top-5, when using the deep features based on the Resnet 50 model, we achieved recognition accuracies of approximately 88.38–93.88% for diseases and approximately 95.38–98.42% for pests. When using the deep features extracted from the VGG16 and VGG19 models, we recorded the second and third highest performances, respectively. In the top-10 results, when using the deep features extracted from the Resnet 50 model, we achieved accuracies of 85.6 and 93.62% for diseases and pests, respectively. As a result of performance comparison between the proposed method and the simple convolutional neural network (CNN) model, the proposed method recorded 8.62% higher accuracy in diseases and 14.86% higher in pests than the CNN classification model.

Download Full-text

A SCALABLE CLUSTERING METHOD FOR CATEGORICAL SEQUENCE DATA

International Journal of Computational Methods ◽

10.1142/s0219876205000417 ◽

2005 ◽

Vol 02 (02) ◽

pp. 167-180

Author(s):

SEUNG-JOON OH ◽

JAE-YEARN KIM

Keyword(s):

Nearest Neighbor ◽

Sequence Data ◽

Clustering Algorithms ◽

K Nearest Neighbor ◽

Clustering Method ◽

Scalable Clustering ◽

Log Files ◽

Web Access ◽

Better Than

Clustering of sequences is relatively less explored but it is becoming increasingly important in data mining applications such as web usage mining and bioinformatics. The web user segmentation problem uses web access log files to partition a set of users into clusters such that users within one cluster are more similar to one another than to the users in other clusters. Similarly, grouping protein sequences that share a similar structure can help to identify sequences with similar functions. However, few clustering algorithms consider sequentiality. In this paper, we study how to cluster sequence datasets. Due to the high computational complexity of hierarchical clustering algorithms for clustering large datasets, a new clustering method is required. Therefore, we propose a new scalable clustering method using sampling and a k-nearest-neighbor method. Using a splice dataset and a synthetic dataset, we show that the quality of clusters generated by our proposed approach is better than that of clusters produced by traditional algorithms.

Download Full-text

K-NN supervised learning algorithm in the predictive analysis of the quality of the university administrative service in the virtual environment

Indonesian Journal of Electrical Engineering and Computer Science ◽

10.11591/ijeecs.v25.i1.pp521-528 ◽

2022 ◽

Vol 25 (1) ◽

pp. 521

Author(s):

Omar Freddy Chamorro-Atalaya ◽

Guillermo Morales Romero ◽

Adrián Quispe Andía ◽

Beatriz Caycho Salas ◽

Elizabeth Katerin Auqui Ramos ◽

...

Keyword(s):

Predictive Model ◽

Engineering Students ◽

Nearest Neighbor ◽

Learning Algorithm ◽

Confusion Matrix ◽

Area Under The Curve ◽

Operational Characteristic ◽

K Nearest Neighbor ◽

Administrative Service

The objective of this study is to analyze and discuss the metrics of the predictive model using the K-nearest neighbor (K-NN) learning algorithm, which will be applied to the data on the perception of engineering students on the quality of the virtual administrative service, such as part of the methodology was analyzed the indicators of accuracy, precision, sensitivity and specificity, from the obtaining of the confusion matrix and the receiver operational characteristic (ROC) curve. The collected data were validated through Cronbach's Alpha, finding consistency values higher than 0.9, which allows to continue with the analysis. Through the predictive model through the Matlab R2021a software, it was concluded that the average metrics for all classes are optimal, presenting a precision of 92.77%, sensitivity 86.62%, and specificity 94.7%; with a total accuracy of 85.5%. In turn, the highest level of the area under the curve (AUC) is 0.98, which is why it is considered an optimal predictive model. Having carried out this study, it is possible to contribute significantly to the decision-making of the higher institution in relation to the improvement of the quality of the virtual administrative service.

Download Full-text

METODE KLASIFIKASI MUTU JAMBU BIJI MENGGUNAKAN KNN BERDASARKAN FITUR WARNA DAN TEKSTUR

Jurnal Teknosains ◽

10.22146/teknosains.26972 ◽

2017 ◽

Vol 6 (2) ◽

pp. 113

Author(s):

Taftyani Yusuf Prahudaya ◽

Agus Harjoko

Keyword(s):

Nearest Neighbor ◽

Texture Features ◽

Psidium Guajava ◽

K Nearest Neighbor ◽

Average Value ◽

Quality Classification ◽

Defect Area ◽

Class B ◽

Sorting Process

Guava (Psidium guajava L.) is a fruit that has many health benefits. Guava also has commercial value in Indonesia and has a large market share. This indicates that the commodity of guava has been consumed by society extensively. This time the sorting process is still done manually which still has many shortcomings. This classification gives the classification results are less accurate and inconsistent due to the carelessness of humans. Grading process in the marketing sector is essential. Improper grading potentially detrimental to farmers because all the fruit quality were priced the same. Therefore, we need a consistent classification system.The system uses image processing to extract the color and texture features of guava. As a quality classification KNN method (K-Nearest Neighbor) is used. This system will classify guava into four quality classes, namely the super class, class A, class B, and external quality. KNN designed with input 7 features extraction which is the average value of RGB (Red, Green, and Blue), total defect area, and the GLCM value (entropy, homogeneity, and contrast) with the 4 outputs of quality. From the test results showed that the classification method is able to classify the quality of guava. The highest accuracy is obtained in testing K = 3 with 91.25% accuracy rate.

Download Full-text

Analysis K-Nearest Neighbor Algorithm for Improving Prediction Student Graduation Time

SinkrOn ◽

10.33395/sinkron.v4i2.10480 ◽

2020 ◽

Vol 4 (2) ◽

pp. 42

Author(s):

Rizki Muliono ◽

Juanda Hakim Lubis ◽

Nurul Khairina

Keyword(s):

Higher Education ◽

Nearest Neighbor ◽

Training Data ◽

K Nearest Neighbor ◽

Nearest Neighbor Algorithm ◽

Study Program ◽

Sample Data ◽

Student Graduation ◽

K Nearest Neighbor Algorithm

Higher education plays a major role in improving the quality of education in Indonesia. The BAN-PT institution established by the government has a standard of higher education accreditation and study program accreditation. With the 4.0-based accreditation instrument, it encourages university leaders to improve the quality and quality of their education. One indicator that determines the accreditation of study programs is the timely graduation of students. This study uses the K-Nearest Neighbor algorithm to predict student graduation times. Students' GPA at the time of the seventh semester will be used as training data, and data of students who graduate are used as sample data. K-Nearest Neighbor works in accordance with the given sample data. The results of prediction testing on 60 data for students of 2015-2016, obtained the highest level of accuracy of 98.5% can be achieved when k = 3. Prediction results depend on the pattern of data entered, the more samples and training data used, the calculation of the K-Nearest Neighbor algorithm is also more accurate.

Download Full-text

Classification of lung condition for early diagnosis of pneumonia and tuberculosis based on embedded system

Bulletin of Electrical Engineering and Informatics ◽

10.11591/eei.v10i3.3033 ◽

2021 ◽

Vol 10 (3) ◽

pp. 1262-1270

Author(s):

Rizal Maulana ◽

Alfatehan Arsya Baharin ◽

Hurriyatul Fitriyah

Keyword(s):

Carbon Dioxide ◽

Embedded System ◽

Nearest Neighbor ◽

Image Data ◽

Early Research ◽

K Nearest Neighbor ◽

X Ray ◽

Lung Condition ◽

Chest X Ray

The lungs are the main organs in the respiratory system that have a function as a place for exchange of oxygen and carbon dioxide. Due to the importance of lung function, indications of lung disorders must be detected and diagnosed early. Research on the classification of lung conditions generally uses chest x-ray image data. Where a time-consuming procedure is needed to obtain the data. In this research, an embedded system to diagnose lung conditions was designed. The system was made to be easy to use independently and provides real-time examination results. This system uses parameters of body temperature, oxygen saturation, fingernail color and lung volume in classifying lung conditions. There are three conditions that can be classified by the system, that is healthy lungs, pneumonia and tuberculosis. The k-nearest neighbor method was used in the classification process in the designed system. The dataset used was 51 data obtained from the hospital. Each data already has a label in the form of lung condition based on the doctor’s diagnosis. The proposed system has an accuracy of 88.24% in classifying lung conditions.

Download Full-text