Hypergravity accelerators are a type of large machinery used for gravity training or medical research. A failure of such large equipment can be a serious problem in terms of safety or costs. This paper proposes a prediction model that can proactively prevent failures that may occur in a hypergravity accelerator. An experiment was conducted to evaluate the performance of the method proposed in this paper. A 4-channel accelerometer was attached to the bearing housing, which is a rotor, and time-amplitude data were obtained from the measured values by sampling. The method proposed in this paper was trained with transfer learning, a deep learning model that replaced the VGG19 model with a Fully Connected Layer (FCL) and Global Average Pooling (GAP) by converting the vibration signal into a short-time Fourier transform (STFT) or Mel-Frequency Cepstral Coefficients (MFCC) spectrogram and converting the input into a 2D image. As a result, the model proposed in this paper has seven times decreased trainable parameters of VGG19, and it is possible to quantify the severity while looking at the defect areas that cannot be seen with 1D.

Background/Aims: Chronic atrophic gastritis (CAG) and metaplastic gastritis (MG) are precancerous conditions of Helicobacter pylori (H. pylori)-related gastric cancer. This study aimed to identify the characteristics of nodular gastritis (NG) showing CAG or MG after nodule regression. Methods: H. pylori-infected patients with NG were included after upper gastrointestinal endoscopy. Patients were excluded if their latest endoscopy had been performed ≤36 months after the initial diagnosis of NG. Small-granular-type NG was defined as the condition with 1-2 mm regular subepithelial nodules. Large-nodular-type NG was defined as those with 3-4 mm, irregular subepithelial nodules. The endoscopic findings after nodule regression were recorded. Results: Among the 97 H. pylori-infected patients with NG, 61 showed nodule regression after a mean follow-up of 73.0±22.0 months. After nodule regression, 16 patients showed a salt-and-pepper appearance and/or transparent submucosal vessels, indicating CAG. Twenty-nine patients showed diffuse irregular elevations and/or whitish plaques, indicating MG. Sixteen patients with other endoscopic findings (14 normal, one erosive gastritis, and one chronic superficial gastritis) showed a higher proportion of H. pylori eradication (12/16, 75.0%) than those in the CAG group (5/16, 31.3%) and MG group (6/29, 20.7%; p=0.001). Patients with small-granular-type NG tended to progress toward CAG (14/27, 51.9%), whereas those with large-nodular-type NG tended to progress toward MG (25/34, 73.5%; p<0.001). Conclusions: In patients with a persistent H. pylori infection, NG tended to progress to CAG or MG when the nodules regressed. Small-granular-type NG tended to progress to CAG, whereas large-nodular-type NG tended to progress to MG.

Hypergravity accelerators are a type of large machinery used for gravity training or medical research. A failure of such large equipment can be a serious problem in terms of safety or costs. This paper proposes a prediction model that can proactively prevent failures that may occur in a hy-pergravity accelerator. The method proposed in this paper was to convert vibration signals to spectograms and perform classification training using a deep learning model. An experiment was conducted to evaluate the performance of the method proposed in this paper. A 4-channel accel-erometer was attached to the bearing housing, which is a rotor, and time-amplitude data were obtained from the measured values by sampling. The data were converted to a two-dimensional spectrogram, and classification training was performed using a deep learning model for four conditions of the equipment: Unbalance, Misalignment, Shaft Rubbing, and Normal. The ex-perimental results showed that the proposed method had a 99.5% F1-Score, which was up to 23% higher than the 76.25% for existing feature-based learning models.

No abstract