Important Features Selection and Classification of Adult and Child from Handwriting Using Machine Learning Methods

Abstract

The classification of different age groups, such as adult and child, based on handwriting is very important due to its various applications in many different fields. In forensics, handwriting classification helps investigators focus on a certain category of writers. This paper aimed to propose a machine-learning (ML)-based approach for automatically classifying people as adults or children based on their handwritten data. This study utilized two types of handwritten databases: handwritten text and handwritten pattern, which were collected using a pen tablet. The handwritten text database had 57 subjects (adult: 26 vs. child: 31). Each subject (adult or child) wrote the same 30 words using Japanese hiragana characters. The handwritten pattern database had 81 subjects (adult: 42 and child: 39). Each subject (adult or child) drew four different lines as zigzag lines (trace condition and predict condition), and periodic lines (trace condition and predict condition) and repeated these line tasks three times. Handwriting classification of adult and child is performed in three steps: (i) feature extraction; (ii) feature selection; and (iii) classification. We extracted 30 features from both handwritten text and handwritten pattern datasets. The most efficient features were selected using sequential forward floating selection (SFFS) method and the optimal parameters were selected. Then two ML-based approaches, namely, support vector machine (SVM) and random forest (RF) were applied to classify adult and child. Our findings showed that RF produced up to 93.5% accuracy for handwritten text and 89.8% accuracy for handwritten pattern databases. We hope that this study will provide the evidence of the possibility of classifying adult and child based on handwriting text and handwriting pattern data.

Implementation of a Fusion Classification Model for Efficient Pen-Holding Posture Detection

“…Accuracy: As described by (17), this is the ratio of correctly classified test samples (CCTS) to all test samples (ATS). All test samples are combined and cleaned of the eight erroneous PHP samples plus the correct PHP samples.…”

“…TabNet [16] is a simulated decision tree network specialized for processing tabular data. The classification of TabNet is slightly superior to that of Random Forest [17]. The sample used in this paper also consists of tabular data, and its form is a one-dimensional feature vector trained in terms of features.…”

ECG signal processing by feature selection with classification based on machine learning architectures in cardiovascular disease detection

“…As a result, it becomes extremely accurate at detecting fiducial detection. Work [8] is being done to analyse fusion beats using ANNs in order to diagnose the patient quickly and accurately. They combined the common MIT -BIH arrhythmia database with a MATLAB-based FFNN.…”

Automatic Gender and Age Classification from Offline Handwriting with Bilinear ResNet

“…The study with the KNN classifier provides evidence that it is possible to detect user age groups based on the words they write with their fingers on touchscreens. Research in [41] applied SVM and Random Forests to automatically classify people as adults or children based on their handwritten data, collected using a pen tablet.…”