Alzheimer’s disease (AD) is a disease that develops gradually, ultimately causing deterioration of brain functions. Thus, early diagnosis is essential for treating and managing AD. Magnetic-resonance-imaging (MRI)-based AD diagnosis classifies the stage of AD according to the extent of atrophy caused to a patient’s hippocampal and entorhinal cortex. In this case, the shape of the patient’s brain serves as a crucial feature. Therefore, in this paper, we propose an ensemble convolutional neural network (CNN) model that can classify the AD stage according to the shape of a patient’s brain. The proposed model is structured by combining a convolutional layer part of the visual geometry group network (VGGNet) model, with proven performance in image classification, and a 1D CNN model into a pipeline. Here, the 1D CNN applies the line segment feature analysis (LFA) algorithm to MRI images to transform the visual line segment information of the images into vectors and record strong features indicating the shape of the brain. This is followed by 1D CNN model training. Notably, the 1D CNN model can carefully observe the brain shape owing to the parallel connection of ten 1D convolutional layers with LFA features. Subsequently, the brain shape information is combined with features obtained from the original image through the VGGNet to improve the model performance compared to that of existing methods. To evaluate the performance of the proposed ensemble CNN model, MRI datasets collected from Kaggle are used to evaluate and compare the proposed model with existing image classification methods and methods proposed in related studies. The experimental results reveal that the proposed model demonstrates superior performance with an accuracy of 0.986 and a loss of 0.0385.

As people communicate with each other, they use gestures and facial expressions as a means to convey and understand emotional state. Non-verbal means of communication are essential to understanding, based on external clues to a person’s emotional state. Recently, active studies have been conducted on the lifecare service of analyzing users’ facial expressions. Yet, rather than a service necessary for everyday life, the service is currently provided only for health care centers or certain medical institutions. It is necessary to conduct studies to prevent accidents that suddenly occur in everyday life and to cope with emergencies. Thus, we propose facial expression analysis using line-segment feature analysis-convolutional recurrent neural network (LFA-CRNN) feature extraction for health-risk assessments of drivers. The purpose of such an analysis is to manage and monitor patients with chronic diseases who are rapidly increasing in number. To prevent automobile accidents and to respond to emergency situations due to acute diseases, we propose a service that monitors a driver’s facial expressions to assess health risks and alert the driver to risk-related matters while driving. To identify health risks, deep learning technology is used to recognize expressions of pain and to determine if a person is in pain while driving. Since the amount of input-image data is large, analyzing facial expressions accurately is difficult for a process with limited resources while providing the service on a real-time basis. Accordingly, a line-segment feature analysis algorithm is proposed to reduce the amount of data, and the LFA-CRNN model was designed for this purpose. Through this model, the severity of a driver’s pain is classified into one of nine types. The LFA-CRNN model consists of one convolution layer that is reshaped and delivered into two bidirectional gated recurrent unit layers. Finally, biometric data are classified through softmax. In addition, to evaluate the performance of LFA-CRNN, the performance was compared through the CRNN and AlexNet Models based on the University of Northern British Columbia and McMaster University (UNBC-McMaster) database.

Breast cancer is known to be common in many developed countries. It is reported as the most common type of cancer in the US, affecting one in eight women. In Korea, thyroid cancer is the most common type of cancer, followed by breast cancer in women. Considering this, early detection and accurate diagnosis of breast cancer are crucial for reducing the associated death rate. Recently, cancer diagnosis systems using medical images have attracted significant attention. Medical imaging methods, such as computed tomography and magnetic resonance imaging, can reveal the overall shape, heterogeneity, and growth speed of carcinoma and are, thus, more commonly employed for diagnoses. Medical imaging has gained popularity since a recent study identified that it could reflect the gene phenotype of a patient. However, an aided diagnosis system based on medical images requires high-specification equipment to analyze high-resolution data. Therefore, this article proposes an edge extraction algorithm and a modified convolutional recurrent neural network (CRNN) model to accurately assess breast cancer based on medical imaging. The proposed algorithm extracts line-segment information from a breast mass image. The extracted line segments were classified into 16 types. Each type was uniquely labeled and compressed. The image compressed in this process was used as the input for the modified CRNN model. Traditional deep learning models were used to evaluate the performance of the proposed algorithm. The results show that the proposed model had the highest accuracy and lowest loss (99.75% and 0.0257, respectively).

In modern society, the real-time emotion adaptive driving system for providing safety to drivers and emotion-based services are being researched. However, in the service process have problem of personal information might get leaked. Therefore, a robust personal information protection method is required for face recognition services based on real-time images. In this study, we propose a real-time streaming image based PingPong256 (PP2) algorithm, line-segment feature analysis (LFA), convolutional recurrent neural network (CRNN) model for facial sentiment analysis. The proposed method applied the PP2 algorithm to images for encryption and decryption for the security of the real-time images collected by image devices. For transmitting images to a server, LFA, as a dimensionality reduction algorithm, is used to extract facial information. PP2 encrypts and decrypts an image through a linear feedback shift register with a different length and sets a random value other than 0 so that inferring the initial value of encryption becomes difficult, and then executes the random operations approximately 1,000 times. The LFA analyzes the line segments of an image, assigns a different unique number depending on its type, and cumulatively adds them to generate a Line-Segment map (LS-map) with a size of $16\times16$ . The LS-map is used as an input of the CRNN model designed in this study, and the facial expressions are classified. Performance evaluation compares the accuracy of face recognition by using the proposed method with the loss rate for other models. Performance evaluation renders excellence to the accuracy of face recognition and loss rate comparison.

HAR technology uses computer and machine vision to analyze human activity and gestures by processing sensor data. The 3-axis acceleration and gyro sensor data are particularly effective in measuring human activity as they can calculate movement speed, direction, and angle. Our paper emphasizes the importance of developing a method to expand the recognition range of human activity due to the many types of activities and similar movements that can result in misrecognition. The proposed method uses 3-axis acceleration and gyro sensor data to visually define human activity patterns and improve recognition accuracy, particularly for similar activities. The method involves converting the sensor data into an image format, removing noise using time series features, generating visual patterns of waveforms, and standardizing geometric patterns. The resulting data (1D, 2D, and 3D) can simultaneously process each type by extracting pattern features using parallel convolution layers and performing classification by applying two fully connected layers in parallel to the merged data from the output data of three convolution layers. The proposed neural network model achieved 98.1% accuracy and recognized 18 types of activities, three times more than previous studies, with a shallower layer structure due to the enhanced input data features.

Recently, demand for handwriting recognition, such as automation of mail sorting, license plate recognition, and electronic memo pads, has exponentially increased in various industrial fields. In addition, in the image recognition field, methods using artificial convolutional neural networks, which show outstanding performance, have been applied to handwriting recognition. However, owing to the diversity of recognition application fields, the number of dimensions in the learning and reasoning processes is increasing. To solve this problem, a principal component analysis (PCA) technique is used for dimensionality reduction. However, PCA is likely to increase the accuracy loss due to data compression. Therefore, in this paper, we propose a line-segment feature analysis (LFA) algorithm for input dimensionality reduction in handwritten text recognition. This proposed algorithm extracts the line segment information, constituting the image of input data, and assigns a unique value to each segment using 3 × 3 and 5 × 5 filters. Using the unique values to identify the number of line segments and adding them up, a 1-D vector with a size of 512 is created. This vector is used as input to machine-learning. For the performance evaluation of the method, the Extending Modified National Institute of Standards and Technology (EMNIST) database was used. In the evaluation, PCA showed 96.6% and 93.86% accuracy with k-nearest neighbors (KNN) and support vector machine (SVM), respectively, while LFA showed 97.5% and 98.9% accuracy with KNN and SVM, respectively.