scholarly journals Machine Learning Models for Cultural Heritage Image Classification: Comparison Based on Attribute Selection

Information ◽  
2019 ◽  
Vol 11 (1) ◽  
pp. 12 ◽  
Author(s):  
Radmila Janković
Keyword(s):  
Cultural Heritage ◽  
Image Classification ◽  
Multilayer Perceptron ◽  
Nearest Neighbor ◽  
Classification Performance ◽  
Attribute Selection ◽  
K Nearest Neighbor ◽  
Large Sets ◽  
Before And After ◽  
Computationally Intensive

Image classification is one of the most important tasks in the digital era. In terms of cultural heritage, it is important to develop classification methods that obtain good accuracy, but also are less computationally intensive, as image classification usually uses very large sets of data. This study aims to train and test four classification algorithms: (i) the multilayer perceptron, (ii) averaged one dependence estimators, (iii) forest by penalizing attributes, and (iv) the k-nearest neighbor rough sets and analogy based reasoning, and compares these with the results obtained from the Convolutional Neural Network (CNN). Three types of features were extracted from the images: (i) the edge histogram, (ii) the color layout, and (iii) the JPEG coefficients. The algorithms were tested before and after applying the attribute selection, and the results indicated that the best classification performance was obtained for the multilayer perceptron in both cases.

scholarly journals Cell morphology-based machine learning models for human cell state classification

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Yi Li ◽  
Chance M. Nowak ◽  
Uyen Pham ◽  
Khai Nguyen ◽  
Leonidas Bleris
Keyword(s):  
Machine Learning ◽  
Flow Cytometry ◽  
Multilayer Perceptron ◽  
Nearest Neighbor ◽  
Annexin V ◽  
Classification Performance ◽  
Training Data ◽  
Support Vector ◽  
Apoptotic Cells ◽  
K Nearest Neighbor

AbstractHerein, we implement and access machine learning architectures to ascertain models that differentiate healthy from apoptotic cells using exclusively forward (FSC) and side (SSC) scatter flow cytometry information. To generate training data, colorectal cancer HCT116 cells were subjected to miR-34a treatment and then classified using a conventional Annexin V/propidium iodide (PI)-staining assay. The apoptotic cells were defined as Annexin V-positive cells, which include early and late apoptotic cells, necrotic cells, as well as other dying or dead cells. In addition to fluorescent signal, we collected cell size and granularity information from the FSC and SSC parameters. Both parameters are subdivided into area, height, and width, thus providing a total of six numerical features that informed and trained our models. A collection of logistical regression, random forest, k-nearest neighbor, multilayer perceptron, and support vector machine was trained and tested for classification performance in predicting cell states using only the six aforementioned numerical features. Out of 1046 candidate models, a multilayer perceptron was chosen with 0.91 live precision, 0.93 live recall, 0.92 live f value and 0.97 live area under the ROC curve when applied on standardized data. We discuss and highlight differences in classifier performance and compare the results to the standard practice of forward and side scatter gating, typically performed to select cells based on size and/or complexity. We demonstrate that our model, a ready-to-use module for any flow cytometry-based analysis, can provide automated, reliable, and stain-free classification of healthy and apoptotic cells using exclusively size and granularity information.

scholarly journals Data Attribute Selection with Information Gain to Improve Credit Approval Classification Performance using K-Nearest Neighbor Algorithm

2017 ◽  
pp. 13
Author(s):  
Ivandari Ivandari ◽  
Tria Titiani Chasanah ◽  
Sattriedi Wahyu Binabar ◽  
M. Adib Adib Al Karomi
Keyword(s):  
Credit Card ◽  
Nearest Neighbor ◽  
Information Gain ◽  
Classification Performance ◽  
Attribute Selection ◽  
K Nearest Neighbor ◽  
K Nearest Neighbors ◽  
Community Needs ◽  
Public Data ◽  
Calculation Results

Credit is one of the modern economic behaviors. In practice, credit can be either borrowing a certain amount of money or purchasing goods with a gradual payment process and within an agreed timeframe. Economic conditions that are less supportive and high community needs make people choose to buy goods with this credit process. Unfortunately the high needs sometimes are not in line with the ability to make payments in accordance with the initial agreement. Such condition causes the payment process to be disrupted or also called the term “bad credit”. This research uses public data of credit card dataset from UCI repository and private data that is dataset of credit approval from local banking. The information gain algorithm is used to calculate the weights of each of the attributes. From the calculation results note that all attributes have different weights. This study resulted in the conclusion that not all data attributes influence the classification result. Suppose attribute A1 to UCI dataset as well as loan type attribute on local dataset that has information gain weight 0 (zero). The result of classification using K-Nearest Neighbors algorithm shows that there is an increase of 7.53% for UCI dataset and 3.26% for local dataset after feature selection on both datasets.

scholarly journals KLASIFIKASI CITRA REKAMAN SINYAL ELEKTROKARDIOGRAM MENGGUNAKAN METODE ANALISIS TEKSTUR, K-NN DAN MULTILAYER PERCEPTRON

2016 ◽  
Vol 7 (1) ◽  
pp. 233
Author(s):  
Mohamad Sofie ◽  
Achmad Rizal
Keyword(s):  
Multilayer Perceptron ◽  
Nearest Neighbor ◽  
Grey Level ◽  
K Nearest Neighbor

Sinyal elektrokardiogram (EKG) memiliki informasi yang menggambarkan kondisi kesehatan jantung. Beragai teknik analisis sinyal EKG dikembangkan untuk mengetahui kelainan di jantung secara ototmatis. Pada kenyataannya di Indonesia, kebanyakan perangkat EKG hanya menghasilkan rekaman berupa kertas EKG sehingga metode pengolahan sinyal tidak bisa diterapkan. Pada penelitian ini dilakukan pengenalan kelainan jantung melalui citra rekaman EKG menggunakan analisis tekstur. Garis sinyal EKG yang tergambar dalam citra rekaman EKG diharapkan bisa dibedakan antara kondisi yang satu dengan yang lain. Untuk ekstraksi ciri digunakan ciri statistik orde 1 dan grey level co-occurence matrix (GLCM) pada arah 0o, 45o, 90o, dan 135o. Untuk klasifikasi digunakan K-nearest neighbor (K-NN) dan multilayer perceptron (MLP). Akurasi yang dihasilkan mencapai 44.12% untuk lima kelas data dan 65.82% untuk dua kelas data. Penggunaan teknik pengolahan ctra terbukti mampu meningkatkan akurasi yang semula rendah.Kata kunci: analisis tekstur, K-NN, multilayerperceptron, citra rekaman EKG, pengolahan citra.

scholarly journals A High Performace of Local Binary Pattern on Classify Javanese Character Classification

2018 ◽  
Vol 5 (1) ◽  
pp. 8 ◽  
Author(s):  
Ajib Susanto ◽  
Daurat Sinaga ◽  
Christy Atika Sari ◽  
Eko Hari Rachmawanto ◽  
De Rosal Ignatius Moses Setiadi
Keyword(s):  
Feature Extraction ◽  
Image Classification ◽  
Local Binary Pattern ◽  
Nearest Neighbor ◽  
Classification Algorithm ◽  
K Nearest Neighbor ◽  
Characteristic Extraction ◽  
Research Objects ◽  
Character Classification

The classification of Javanese character images is done with the aim of recognizing each character. The selected classification algorithm is K-Nearest Neighbor (KNN) at K = 1, 3, 5, 7, and 9. To improve KNN performance in Javanese character written by the author, and to prove that feature extraction is needed in the process image classification of Javanese character. In this study selected Local Binary Patter (LBP) as a feature extraction because there are research objects with a certain level of slope. The LBP parameters are used between [16 16], [32 32], [64 64], [128 128], and [256 256]. Experiments were performed on 80 training drawings and 40 test images. KNN values after combination with LBP characteristic extraction were 82.5% at K = 3 and LBP parameters [64 64].

scholarly journals A New Approach to Fall Detection Based on Improved Dual Parallel Channels Convolutional Neural Network

Sensors ◽  
2019 ◽  
Vol 19 (12) ◽  
pp. 2814 ◽  
Author(s):  
Xiaoguang Liu ◽  
Huanliang Li ◽  
Cunguang Lou ◽  
Tie Liang ◽  
Xiuling Liu ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Nearest Neighbor ◽  
Fall Detection ◽  
Classification Performance ◽  
Daily Activities ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Linear Discriminant ◽  
Parallel Channels

Falls are the major cause of fatal and non-fatal injury among people aged more than 65 years. Due to the grave consequences of the occurrence of falls, it is necessary to conduct thorough research on falls. This paper presents a method for the study of fall detection using surface electromyography (sEMG) based on an improved dual parallel channels convolutional neural network (IDPC-CNN). The proposed IDPC-CNN model is designed to identify falls from daily activities using the spectral features of sEMG. Firstly, the classification accuracy of time domain features and spectrograms are compared using linear discriminant analysis (LDA), k-nearest neighbor (KNN) and support vector machine (SVM). Results show that spectrograms provide a richer way to extract pattern information and better classification performance. Therefore, the spectrogram features of sEMG are selected as the input of IDPC-CNN to distinguish between daily activities and falls. Finally, The IDPC-CNN is compared with SVM and three different structure CNNs under the same conditions. Experimental results show that the proposed IDPC-CNN achieves 92.55% accuracy, 95.71% sensitivity and 91.7% specificity. Overall, The IDPC-CNN is more effective than the comparison in accuracy, efficiency, training and generalization.

Comparative analysis of breast cancer detection in mammograms and thermograms

2015 ◽  
Vol 60 (1) ◽  
Author(s):  
Marina Milosevic ◽  
Dragan Jankovic ◽  
Aleksandar Peulic
Keyword(s):  
Nearest Neighbor ◽  
Region Of Interest ◽  
Texture Features ◽  
Classification Performance ◽  
Support Vector ◽  
K Nearest Neighbor ◽  
Characteristic Analysis ◽  
Analysis Society ◽  
Fold Cross Validation ◽  
Neighbor Classifier

AbstractIn this paper, we present a system based on feature extraction techniques for detecting abnormal patterns in digital mammograms and thermograms. A comparative study of texture-analysis methods is performed for three image groups: mammograms from the Mammographic Image Analysis Society mammographic database; digital mammograms from the local database; and thermography images of the breast. Also, we present a procedure for the automatic separation of the breast region from the mammograms. Computed features based on gray-level co-occurrence matrices are used to evaluate the effectiveness of textural information possessed by mass regions. A total of 20 texture features are extracted from the region of interest. The ability of feature set in differentiating abnormal from normal tissue is investigated using a support vector machine classifier, Naive Bayes classifier and K-Nearest Neighbor classifier. To evaluate the classification performance, five-fold cross-validation method and receiver operating characteristic analysis was performed.

scholarly journals WINkNN: Windowed Intervals’ Number kNN Classifier for Efficient Time-Series Applications

Mathematics ◽  
2020 ◽  
Vol 8 (3) ◽  
pp. 413 ◽  
Author(s):  
Chris Lytridis ◽  
Anna Lekova ◽  
Christos Bazinas ◽  
Michail Manios ◽  
Vassilis G. Kaburlasos
Keyword(s):  
Time Series ◽  
Ad Hoc ◽  
Nearest Neighbor ◽  
Classification Performance ◽  
Human Robot Interaction ◽  
Time Series Classification ◽  
K Nearest Neighbor ◽  
Time Dimension ◽  
Knn Classifier ◽  
Benchmark Datasets

Our interest is in time series classification regarding cyber–physical systems (CPSs) with emphasis in human-robot interaction. We propose an extension of the k nearest neighbor (kNN) classifier to time-series classification using intervals’ numbers (INs). More specifically, we partition a time-series into windows of equal length and from each window data we induce a distribution which is represented by an IN. This preserves the time dimension in the representation. All-order data statistics, represented by an IN, are employed implicitly as features; moreover, parametric non-linearities are introduced in order to tune the geometrical relationship (i.e., the distance) between signals and consequently tune classification performance. In conclusion, we introduce the windowed IN kNN (WINkNN) classifier whose application is demonstrated comparatively in two benchmark datasets regarding, first, electroencephalography (EEG) signals and, second, audio signals. The results by WINkNN are superior in both problems; in addition, no ad-hoc data preprocessing is required. Potential future work is discussed.

Sign in / Sign up

Export Citation Format

Share Document