Many researchers use electroencephalograms (EEGs) to study brain activity in the context of seizures, epilepsy, and lie detection. It is desirable to eliminate EEG artifacts to improve signal collection. In this paper, we propose an emotion recognition system for human brain signals using EEG signals. We measure EEG signals relating to emotion, divide them into five frequency ranges on the basis of power spectrum density, and eliminate low frequencies from 0 to 4 Hz to eliminate EEG artifacts. The resulting calculations of the frequency ranges are based on the percentage of the selected range relative to the total range. The calculated values are then compared to standard values from a Bayesian network, calculated from databases. Finally, we show the emotion results as a human face avatar.

No abstract

No abstract

No abstract

-With the continuous aging of the populations in developed countries, the medical requirements of the aged are expected to increase. In this paper, a ring-type pulse oximeter finger sensor and a 24-hour ambulatory heart rate monitoring system for the aged are presented. We also demonstrate the feasibility of extracting accurate heart rate variability measurements from photoelectric plethysmography signals gathered using a ring-type pulse oximeter sensor attached to the finger. We designed the heart rate sensor using a CPU with built-in ZigBee stack for simplicity and low power consumption. We also analyzed the various distorted signals caused by motion artifacts using a FFT, and designed an algorithm using a least squares estimator to calibrate the signals for better accuracy.

The Convolutional Neural Network(CNN) can be divided into two stages: feature extraction and classification. The hyperparameters such as kernel size, number of channels, and stride in the feature extraction step affect the overall performance of CNN as well as determining the structure of CNN. In this paper, we propose a method to optimize the hyperparameter in CNN feature extraction stage using Parameter-Setting-Free Harmony Search (PSF-HS) algorithm. After setting the overall structure of CNN, hyperparameter was set as a variable and the hyperparameter was optimized by applying PSF-HS algorithm. The simulation was conducted using MATLAB, and CNN learned and tested using mnist data. We update the parameters for a total of 500 times, and it is confirmed that the structure with the highest accuracy among the CNN structures obtained by the proposed method classifies the mnist data with an accuracy of 99.28%.

Advances in machine learning and artificial intelligence have led to many promising solutions for challenging issues in agriculture. One of the remaining challenges is to develop practical applications, such as an automatic sorting system for after-ripening crops such as tomatoes, according to ripeness stages in the post-harvesting process. This paper proposes a novel method for detecting tomato ripeness by utilizing multiple streams of convolutional neural network (ConvNet) and their stochastic decision fusion (SDF) methodology. We have named the overall pipeline as SDF-ConvNets. The SDF-ConvNets can correctly detect the tomato ripeness by following consecutive phases: (1) an initial tomato ripeness detection for multi-view images based on the deep learning model, and (2) stochastic decision fusion of those initial results to obtain the final classification result. To train and validate the proposed method, we built a large-scale image dataset collected from a total of 2712 tomato samples according to five continuous ripeness stages. Five-fold cross-validation was used for a reliable evaluation of the performance of the proposed method. The experimental results indicate that the average accuracy for detecting the five ripeness stages of tomato samples reached 96%. In addition, we found that the proposed decision fusion phase contributed to the improvement of the accuracy of the tomato ripeness detection.

No abstract