Cerebral micro-bleedings (CMBs) are small chronic brain hemorrhages that have many side effects. For example, CMBs can result in long-term disability, neurologic dysfunction, cognitive impairment and side effects from other medications and treatment. Therefore, it is important and essential to detect CMBs timely and in an early stage for prompt treatment. In this research, because of the limited labeled samples, it is hard to train a classifier to achieve high accuracy. Therefore, we proposed employing Densely connected neural network (DenseNet) as the basic algorithm for transfer learning to detect CMBs. To generate the subsamples for training and test, we used a sliding window to cover the whole original images from left to right and from top to bottom. Based on the central pixel of the subsamples, we could decide the target value. Considering the data imbalance, the cost matrix was also employed. Then, based on the new model, we tested the classification accuracy, and it achieved 97.71%, which provided better performance than the state of art methods.

No abstract

No abstract

In the current natural environment, due to the complexity of the background and the high similarity of the color between immature green tomatoes and the plant, the occlusion of the key organs (flower and fruit) by the leaves and stems will lead to low recognition rates and poor generalizations of the detection model. Therefore, an improved tomato organ detection method based on convolutional neural network (CNN) has been proposed in this paper. Based on the original Faster R-CNN algorithm, Resnet-50 with residual blocks was used to replace the traditional vgg16 feature extraction network, and a K-means clustering method was used to adjust more appropriate anchor sizes than manual setting, to improve detection accuracy. The test results showed that the mean average precision (mAP) was significantly improved compared with the traditional Faster R-CNN model. The training model can be transplanted to the embedded system, which lays a theoretical foundation for the development of a precise targeting pesticide application system and an automatic picking device.

The aim of this study was to compare a computerized, laser‐scanning Cavity Preparation Skill Evaluation System (CPSES) with conventional teachers’ eye‐hand grading assessment of dental students’ Class I cavity preparation evaluations. Thirty‐eight cavity preparations of lower left first molars made by junior dental students at a dental school in China were tested from September 2013 to November 2014. The outline and retention form, smoothness, depth, wall angulation, and cavity margin index of the preparations were evaluated by CPSES and then by teachers’ eye‐hand grading. The mean difference in scores for each method was considered, as was the variability of scores within each method. Compared with the teachers’ eye‐hand grading method, CPSES provided objective evaluation results that had statistically significant differences (p<0.05). A questionnaire was also designed and distributed to the students; the response rate was 100%. The results indicated that most of the students recognized CPSES effects in the preclinical teaching; 92.1% perceived that CPSES provided high simulation and appropriate practice guidance for them; and 94.7% reported that the evaluation results provided by CPSES gave targeted and objective recommendations. These findings suggest that CPSES can consistently and reliably scan a student's tooth preparation, compare it to a theoretically ideal preparation, and provide objective feedback. The application of CPSES in preclinical operative training can help students better understand the desired parameters for occlusal cavity preparation skills and encourage students in their self‐paced learning and independent practice.

No abstract

No abstract

No abstract