Takayuki Yumoto

In this research, we propose a method for estimating the degree of injury from text documents that describe accidents. It is assumed that a text document to be input consists of a few sentences. The proposed method is to estimate the degree of injury by solving a classification problem using machine learning techniques. The data used in this research is the accident data published in the Accident Information Data Bank System. The text in the “Summary of the accident” field is used as an input. In the proposed method, an input text is represented as a distributed representation using the generic language model called BERT. As a model for BERT, we use a pre-trained model trained using the Japanese Wikipedia. To improve the performance of the task of estimating the degree of injury, we introduce the following four ideas; (1) the class weights, (2) the ordinal classification, (3) the multitasking learning, and (4) the fine-tuning model with token label estimation. We examined the effects of using and not using these ideas on the accuracy, Macro F1, RMSE, and confusion matrices for the task of estimating the degree of injury. The results showed that Macro F1 and RMSE are improved when (1) the class weights and (2) the ordinal classification are introduced. In addition, the accuracy is improved when (3) the multitasking learning is introduced.

In this paper, a support-vector-machine(SVM)- based method of detecting stenosis is presented for fallopian tubal models. It copes with stenosis detection as classification of data prepared from results of ultrasonic measurements conducted for tubal models. Under assumption that waves reflected at the second and third boundary surfaces of the models potentially include characteristics associated with blocked sections (i.e., stenosis), the method determines the time range having the reflected waves, by referring to maximal values on envelope curves of them The determined range is divided into regular short intervals, and the difference between maximum value and minimum value on envelope curves is calculated for each interval. The ten-dimensional data used to SVM learning and stenosis detection is prepared from the frequency distribution of the number of the short intervals versus difference values. Experimental results establish that the method can achieves favorable accuracies in checking occurrence of stenosis and in identifying tubal model types.

In this paper, a method of achieving high accuracy in discriminating right and left eyes is proposed for ophthalmic surgery. A VGG16 convolutional neural network is employed to construct a main classifier. The data presented to the main classifier are some frames sampled at regular intervals from surgery videos. Before classifying the frames to be examined, the proposed method determines whether they are suitable or not to improve the discrimination accuracy as high as possible. In other words, the frames causing erroneous discrimination are omitted. The determination of frames depends on image characteristics associated with lightness values and edges, and on positions of eyelid speculums in them. It is based on SegNet neural networks. The proposed method determines the frames to be presented, if rectangular areas specified by bent parts of the speculums adequately appear in the predefined regions inside them. Experimental results reveal that the proposed method achieves the favorable discrimination accuracy with a small number of data in training SegNet networks compared with another method.

In this paper, a method of determining examinations is proposed for ophthalmologic outpatients, using feedforward neural network (NN for short). The determination is based on the data classification. The proposed method defines four classes of ophthalmologic examinations. It prepares data for NN training and examination determination from handwriting sentences in outpatients' interview sheets. A set of the training data is prepared in the form of a matrix. The words extracted from the sentences are assigned to the matrix columns, while each sheet (or sentences in it) is assigned to a matrix rows. Entries in the matrix takes binary values meaning whether extracted words appear in the sentences in the sheet. The proposed method also the ages of outpatients as entries. NN training is conducted according to the normal backpropagation algorithm using a row as one of the training data. The trained NN has four output neurons each of which takes the value belonging to the range [0, 1]. The class of data to be examined is determined by searching the neuron at which the largest value appears in the output layer. Experimental results comprehensively establish that the proposed method can achieve higher percentages of concordance than other methods.