A lightweight convolutional neural network (CNN) model for diatom classification: DiatomNet.

Diatoms are a type of algae with many species. Accurate and quick classification of diatom species is important in many fields, such as water quality analysis and weather change forecasting. Traditional methods for diatom classification, specifically morphological taxonomy and molecular detection, are time-consuming and may not provide satisfactory performance. However, in recent years, deep learning has demonstrated impressive performance in this task, just like other image classification problems. On the other hand, networks with more layers do not guarantee increased accuracy. While increasing depth can be useful in capturing complex features and patterns, it also introduces challenges such as vanishing gradients, overfitting, and optimization challenges. Therefore, in our work, we propose DiatomNet, a lightweight convolutional neural network (CNN) model that can classify diatom species accurately while requiring low computing resources. A recently introduced dataset consisting of 3,027 diatom images and 68 diatom species is used to train and evaluate the model. The model is compared with well-known and successful CNN models (i.e., AlexNet, GoogleNet, Inceptionv3, ResNet18, VGG16, and Xception) and their customized versions obtained with transfer learning. The comparison is based on several success metrics: accuracy, precision, recall, F-measure, number of learnable parameters, training, and prediction time. Eventually, the experimental results reveal that DiatomNet outperforms the other models regarding all metrics with just a few exceptions. Therefore, it is a lightweight but strong candidate for diatom classification tasks.

Classification models for SPECT myocardial perfusion imaging.

OBJECTIVE: The main goal of this work is to develop computer-aided classification models for single-photon emission computed tomography (SPECT) myocardial perfusion imaging (MPI) to identify perfusion abnormalities (myocardial ischemia and/or infarction). METHODS: Two different classification models, namely, deep learning (DL)-based and knowledge-based, are proposed. The first type of model utilizes transfer learning with pre-trained deep neural networks and a support vector machine classifier with deep and shallow features extracted from those networks. The latter type of model, on the other hand, aims to transform the knowledge of expert readers to appropriate image processing techniques including particular color thresholding, segmentation, feature extraction, and some heuristics. In addition, the summed stress and rest images from 192 patients (age 26-96, average age 61.5, 38% men, and 78% coronary artery disease) were collected to constitute a new dataset. The visual assessment of two expert readers on this dataset is used as a reference standard. The performances of the proposed models were then evaluated according to this standard. RESULTS: The maximum accuracy, sensitivity, and specificity values are computed as 94%, 88%, and 100% for the DL-based model and 93%, 100%, and 86% for the knowledge-based model, respectively. CONCLUSION: The proposed models provided diagnostic performance close to the level of expert analysis. Therefore, they can aid in clinical decision making for the interpretation of SPECT MPI regarding myocardial ischemia and infarction.

A low-computational approach on gaze estimation with eye touch system.

Among various approaches to eye tracking systems, light-reflection based systems with non-imaging sensors, e.g., photodiodes or phototransistors, are known to have relatively low complexity; yet, they provide moderately accurate estimation of the point of gaze. In this paper, a low-computational approach on gaze estimation is proposed using the Eye Touch system, which is a light-reflection based eye tracking system, previously introduced by the authors. Based on the physical implementation of Eye Touch, the sensor measurements are now utilized in low-computational least-squares algorithms to estimate arbitrary gaze directions, unlike the existing light reflection-based systems, including the initial Eye Touch implementation, where only limited predefined regions were distinguished. The system also utilizes an effective pattern classification algorithm to be able to perform left, right, and double clicks based on respective eye winks with significantly high accuracy. In order to avoid accuracy problems for sensitive sensor biasing hardware, a robust custom microcontroller-based data acquisition system is developed. Consequently, the physical size and cost of the overall Eye Touch system are considerably reduced while the power efficiency is improved. The results of the experimental analysis over numerous subjects clearly indicate that the proposed eye tracking system can classify eye winks with 98% accuracy, and attain an accurate gaze direction with an average angular error of about 0.93 °. Due to its lightweight structure, competitive accuracy and low-computational requirements relative to video-based eye tracking systems, the proposed system is a promising human-computer interface for both stationary and mobile eye tracking applications.