Pengaruh Seleksi Fitur Citra Terhadap Klasifikasi Tingkat Kesegaran Daging Sapi Lokal

Abstract

Identifying beef manually has some drawbacks because human visual has limitations and there are differences of human perception in assessing object quality. Several researches developed beef quality assessment methods based on image feature extraction. However, not all features support for obtaining the classification results that have high accuracy. The efficiency will be achieved if the classification analyzes only the relevant features. Therefore, a feature selection process is required to select relevant features and to eliminate irrelevant features to obtain more accurate and faster classification results. One of the feature selection algorithms is the F-Score which is a simple technique that measures the discrimination of two sets of real numbers. The features with the lowest ranking from the F-Score will be eliminated one by one until the most relevant features are obtained. The test is carried out by analyzing the classification results in the form of sensitivity, specificity, and accuracy values. The results of this research showed that by using the F-Score feature, the most relevant features for the classification of freshness level of local beef are obtained using the K-Nearest Neighbor (KNN) method. These features include the average color intensity R and standard deviation with a sensitivity of 0.8, a specificity of 0.93, and an accuracy of 86%. Keywords: Classification, Fiture Selection, F-Score, K-Nearest Neighbor, Local beef

Optimasi Klasifikasi Fonem Menggunakan Backpropagation Neural Network dan Principal Component Analysis

“…Data acquisition is a technique of taking or collecting data or images that will be processed using a computer [12]. The image collection process was carried out by recording a video in real-time with a test person saying a few sentences.…”

“…The weighting in this test used an activation function that was influenced by the number of layer neurons, as shown in (12).…”

“…𝑧_𝑖𝑛 𝑗 = 𝑣 𝑗0 + ∑ 𝑥 𝑖 . 𝑣 𝑖𝑗 𝑛 𝑖=1 (12) where 𝑧_𝑖𝑛 𝑗 = value to calculate the hidden layer 𝑥 𝑖 = i's input layer value 𝑣 𝑖𝑗 = the weight between the input layer and hidden layer. EN-40…”

Implementation of Random Forest on Face Recognition Using Isomap Features

“…Jika instance positif dikelompokkan sebagai positif maka disebut sebagai true positive (TP) dan jika instance positif dikelompokkan sebagai negatif disebut false positive (FP). Jika instance negatif dinyatakan sebagai negatif maka disebut sebagai true negative (TN) dan jika instance negatif diprediksi positif maka disebut false negative (FN) [20]. Dengan demikian, secara matematis tingkat Akurasi dihitung dengan formula pada persamaan (4).…”

Meat Image Classification Using Deep Learning With Resnet152v2 Architecture

“…Same with Celvin's research, namely using chicken meat, to build a classification model with the K-(KNN) method (Surudin et al, 2020). Another study was conducted by Titin (2021) using the K-Nearest Neighbor (KNN) method by carrying out a feature selection process using the F-Score to select relevant features and eliminate irrelevant features in classifying the freshness level of beef (Yulianti et al, 2021). The third study used a classification technique to obtain the results of the image classification of chicken meat.…”