In this study, we propose a system that enables gesture operation of an electronic musical instrument while holding drumsticks by utilizing video recognition technology. Electronic musical instruments allow manipulation of parameters such as pitch and audio effects. Conventionally, in order to operate an electronic musical instrument, it is necessary to release the drumstick from the hand and operate it directly, making it difficult to operate an electronic musical instrument during a performance. This system can recognize gestures and manipulate parameters of electronic instruments while playing. The challenges in this research are to develop gestures that are easy to learn and to reduce the impact of misrecognition on the performance. We developed a gesture recognition technique that uses features created from the detection of drumstick and hand landmarks. We also developed recognizable gestures based on stick trick and drumstick waving motions. In an evaluation experiment with three drummers as subjects, five of the six gestures were found to be easy to learn. Recognition accuracy was also evaluated using video images of the gestures being performed during the performance, and three of the gestures that were easy to learn achieved the target accuracy.

In recent years, food adulteration—the mixing of one brand of meat with another brand of meat—is a significant issue. One approach to detecting such fraud is to monitor the relationship between livestock weight and the weight of its edible parts through a food traceability system. However, conventional methods often fail when fraudsters carefully adjust the weight transferred from one brand to another so that both brands remain within normal ranges. In this study, we propose two fraud detection methods that focus on distributional changes in both livestock weight and edible-part weight. Specifically, one uses a likelihood ratio to detect shifts caused by continuous adulteration, and the other uses correlation to detect a change from very weak correlation to a strong negative correlation caused by brand-to-brand meat transfers. Evaluation experiments show that when the frequency of adulteration exceeded 17.2%, our method achieved the target true positive rate. These results show the effectiveness of our proposed approach.

A method using electromyograms to estimate muscle fatigue associated with exercise has been proposed. Muscles can be classified into three types: fast, intermediate, and slow, each of which being activated by physiological metabolic mechanisms that correlate with fatigue. The percentage of muscle fibers in use, which correlates with muscle fatigue, can thus be calculated using frequency analysis. In some participants, this muscle fatigue analysis method failed because actual muscle fatigue did not correlate with percentage of muscle fibers used. Assuming that this phenomenon was due to the characteristics of the subcutaneous fatty tissues between the muscle and skin surface, we attempted to cluster the participants based on their physical characteristics, construct a correction model using physical characteristics as explanatory variables within the clusters, and correct the percentage of muscle fibers used. Consequently, the muscle fatigue in all seven participants, which initially deviated from the ratio of muscle fibers used, was adjusted to align with the expected pattern, thereby enhancing the validity of the muscle fatigue analysis.

Gamma-aminobutyric acid (GABA) is one of the functional foods that have good effects on human health. Although some studies reported the anti-stress effects of GABA by evaluating autonomic nervous activity via heart rate variability (HRV), no stress task was conducted during the experiments. Additionally, the HRV analysis methods used in these studies did not consider the non-stationarity and non-linearity in the HRV data. In this study, we investigated the effect of a single intake of GABA on autonomic nervous activity after mild mental stress by HRV analysis using the wavelet transform. HRV data were obtained from seven males by recording electrocardiograms before and 30, 45, and 60 min after GABA or placebo intake. As a stress task, a modified version of the Uchida- Kraepelin test was performed for 17 min starting 13 min after the intake. HRV indices were calculated using the wavelet transform. A significant decrease in the relative HF power (one of the HRV indices) was confirmed after stress in the placebo condition, but not in the GABA condition. This suggests that GABA intake may suppress the decrease in parasympathetic nervous activity that occurs after mild mental stress.

In this paper, a method to design an inverse LQR with a retarded state predictor for systems with time-delay in state and input is proposed. A feedback law is constructed by using the predictor which has a same state time-delay as the one in the systems. It is shown that the resulting closed-loop system is asymptotically stable and the proposed feedback law is an optimal control that minimizes a quadratic cost functional. Furthermore, we show that the constructed regulator has good robustness as same as an ordinary finite-dimensional LQR. Finally, numerical examples are given to evaluate the effectivity of the proposed method.

In this paper, we propose a design method of an I-PD controller which can construct servo systems for linear multivariable systems. The equation for determining the parameter matrices of an I-PD controller (the design equation of an I-PD controller) in the proposed method is a linear matrix equation, which is obtained based on the idea of matching an I-PD control law to the state feedback control law that construct servo systems for multivariable systems. The parameter matrices of an I-PD controller is obtained by solving this linear matrix equation. Moreover, we show the relation between the design equation of an I-PD controller in the proposed method and the design equation of an I-PD controller obtained from the integral type servo control law. We consider the effectiveness of the I-PD controller obtained by the proposed method based on this relation. The usefulness of the proposed method is confirmed through simulation.

Fracturing technology, one of the key technologies to increase oil and gas production, is now widely used in the oil and gas recovery industry. However, during large-scale fracturing operations in shale gas horizontal wells, various downhole accidents often occur, especially sand plugging accidents. These accidents not only seriously affect the safety of the operation but also lead to a significant increase in fracturing costs. Due to the randomness of the abnormal changes in the fracturing curve and the substantial hysteresis when the sand-carrying fluid enters the formation, the accident characteristics of the curve are not prominent, which often leads to false or late reports of the accident by manual judgment. Firstly, based on the curve characteristics of fracturing construction data, the relationship between the long time series affected by the discharge fluctuation and the type of fracturing stage is investigated, and a stage identification model based on the LSTM-FCN-Attention Network is established, which is integrated with the standard deviation-based discharge fluctuation monitoring algorithm to realize the delineation of the sensitive stage of sand plugging in the fracturing of a single-stage well. Then, based on the temporal characteristics of oil pressure and discharge, the time series to matrix mapping method and Gramian Angular Field (GAF) were used to construct the 3D data and fused by Convolutional Block Attention Module (CBAM) DenseNet121 to construct a CBAM-DenseNet121-based oil pressure anomaly state recognition model to recognize the accidents in the sensitive phase of sand plugging. The experimental results verified that the accuracy of the sand plug recognition method proposed in this paper reached 93.65%, and the misclassification rate was lower than 3.50%. In practical application scenarios, this method can effectively recognize accidents and remind construction personnel to make further corresponding decisions to avoid serious losses caused by accidents.

In face-to-face group classes, it is challenging for teachers to pay attention to all the students at all times. This study attempted to estimate the pose and body orientation of students by acquiring their skeletal joint points using OpenPose and judge the unusual behavior of students by capturing a video of the classroom from a bird's-eye view. Furthermore, this study introduces a method for tracking individuals using coordinates derived from each frame processed by OpenPose, along with a pose matching technique based on the Mahalanobis distance applied to seven predefined pose template vectors. Moreover, this study proposes a method for estimating the body orientation based on the angle of the line connecting the shoulders of a person. These methods were evaluated using four different videos. One of the videos was recorded in an actual elementary education classroom. Consequently, the accuracy of pose estimation exceeded 87.0%, that of body orientation estimation was 97.0%, and unusual behavior judgements were almost always made successfully.

Warning sounds are designed to capture human attention, often diverting focus from tasks requiring sustained concentration. This change induces other attention, directing cognitive resources to the sound source. However, warning sounds may cause panic by evoking fear or anxiety, potentially impairing judgment and resulting in erroneous actions. This study investigates cognitive reappraisal as a strategy to reduce negative effects. Event-related potential (ERP) is calculated from electroencephalogram (EEG) , and psychological methods are employed to further explore the influence of warning sounds. These findings provide insight into enhancing the effectiveness of auditory warnings while minimizing negative responses.

Vehicle license plates contain a variety of information. Therefore, they are used in various systems such as crime prevention and transportation. In this paper, we use the BasicVSR++ model to sharpen vehicle license plates by super-resolution processing. Since the area of the region name is smaller than that of the number, the proposed method improves visibility by weighting the loss function according to the area during training.