Diabetes mellitus (DM) is one of the major diseases that cause death worldwide and lead to complications of diabetic foot ulcers (DFU). Improper and late handling of a diabetic foot patient can result in an amputation of the patient’s foot. Early detection of DFU symptoms can be observed using thermal imaging with a computer-assisted classifier. Previous study of DFU detection using thermal image only achieved 97% of accuracy, and it has to be improved. This article proposes a novel framework for DFU classification based on thermal imaging using deep neural networks and decision fusion. Here, decision fusion combines the classification result from a parallel classifier. We used the convolutional neural network (CNN) model of ShuffleNet and MobileNetV2 as the baseline classifier. In developing the classifier model, firstly, the MobileNetV2 and ShuffleNet were trained using plantar thermogram datasets. Then, the classification results of those two models were fused using a novel decision fusion method to increase the accuracy rate. The proposed framework achieved 100% accuracy in classifying the DFU thermal images in binary classes of positive and negative cases. The accuracy of the proposed Decision Fusion (DF) was increased by about 3.4% from baseline ShuffleNet and MobileNetV2. Overall, the proposed framework outperformed in classifying the images compared with the state-of-the-art deep learning and the traditional machine-learning-based classifier.

In cross-spectral iris recognition, different spectral bands are used to obtain rich information of the human iris. Previous studies on cross-spectral iris recognition are based primarily on feature-based approaches, which are prone to the changes in parameters in the feature extraction process, such as spatial position and iris image acquisition conditions. These parameters can degrade iris recognition performance. In this paper, we present a phase-based approach for cross-spectral iris recognition using phase-only correlation (POC) and band-limited phase-only correlation (BLPOC). A phase-based iris recognition system recognizes an iris using the phase information contained in the iris image; therefore, its performance is not affected by feature extraction parameters. However, the performance of a phase-based cross-spectral iris recognition is strongly influenced by specular reflection. Different illumination conditions may produce different iris images from the same subject. To overcome this challenge, we integrate a photometric normalization technique -homomorphic filtering- with phase-based cross-spectral iris recognition. The experimental results reveal that the proposed technique achieved an excellent matching performance with an equal error rate of 0.59% and a genuine acceptance rate of 95%.

Facial recognition has a significant application for security, especially in surveillance technologies. In surveillance systems, recognizing faces captured far away from the camera under various lighting conditions, such as in the daytime and nighttime, is a challenging task. A system capable of recognizing face images in both daytime and nighttime and at various distances is called Cross-Spectral Cross Distance (CSCD) face recognition. In this paper, we proposed a phase-based CSCD face recognition approach. We employed Homomorphic filtering as photometric normalization and Band Limited Phase Only Correlation (BLPOC) for image matching. Different from the state-of-the-art methods, we directly utilized the phase component from an image, without the need for a feature extraction process. The experiment was conducted using the Long-Distance Heterogeneous Face Database (LDHF-DB). The proposed method was evaluated in three scenarios: (i) cross-spectral face verification at 1m, (ii) cross-spectral face verification at 60m, and (iii) cross-spectral face verification where the probe images (near-infrared (NIR) face images) were captured at 1m and the gallery data (face images) was captured at 60 m. The proposed CSCD method resulted in the best recognition performance among the CSCD baseline approaches, with an Equal Error Rate (EER) of 5.34% and a Genuine Acceptance Rate (GAR) of 93%.

The article’s subject matter is to classify Electroencephalography (EEG) signals in Autism Spectrum Disorder (ASD) sufferers. The goal is to develop a classification model using Machine Learning (ML) algorithms that are often implemented in Brain-Computer Interfaces (BCI) technology. The tasks to be solved are as follows: pre-processing the EEG dataset signal to separate the source signal from the noise/artifact signal to produce an observation signal that is free of noise/artifact; obtaining an effective feature comparison to be used as an attribute at the classification stage; and developing a more optimal classification method for detecting people with ASD through EEG signals. The methods used are: one of the wavelet techniques, namely the Continuous Wavelet Transform (CWT), which is a technique for decomposing time-frequency signals. CWT began to be used in EEG signals because it can describe signals in great detail in the time-frequency domain. EEG signals are classified into two scenarios: classification of CWT coefficients and classification of statistical features (mean, standard deviation, skewness, and kurtosis) of CWT. The method used for classifying this research uses ML, which is currently very developed in signal processing. One of the best ML methods is Support Vector Machine (SVM). SVM is an effective super-vised learning method to separate data into different classes by finding the hyper-plane with the largest margin among the observed data. The following results were obtained: the application of CWT and SVM resulted in the best classification based on CWT coefficients and obtained an accuracy of 95% higher than the statistical feature-based classification of CWT, which obtained an accuracy of 65%. Conclusions. The scientific contributions of the results obtained are as follows: 1) EEG signal processing is performed in ASD children using feature extraction with CWT and classification with SVM; 2) the combination of these signal classification methods can improve system performance in ASD EEG signal classification; 3) the implementation of this research can later assist in detecting ASD EEG signals based on brain wave characteristics.

Classification of stunted and normal children using novel facial image database and convolutional neural network

Performance analysis of DMF teeth detection using deep learning: A comparative study with clinical examination as quasi experimental study