In general, patients who are unwell do not know with which outpatient department they should register, and can only get advice after they are diagnosed by a family doctor. This may cause a waste of time and medical resources. In this paper, we propose an attention-based bidirectional long short-term memory (Att-BiLSTM) model for service robots, which has the ability to classify outpatient categories according to textual content. With the outpatient text classification system, users can talk about their situation to a service robot and the robot can tell them which clinic they should register with. In the implementation of the proposed method, dialog text of users in the Taiwan E Hospital were collected as the training data set. Through natural language processing (NLP), the information in the dialog text was extracted, sorted, and converted to train the long-short term memory (LSTM) deep learning model. Experimental results verify the ability of the robot to respond to questions autonomously through acquired casual knowledge.

This study implements Fuzzy logic-based obstacle avoidance and human tracking on an omnidirectional mobile system for service robots. The mobile system could be separated and combined with the robot which can be controlled remotely and switched to go forward and avoid obstacles in an indoor environment automatically. The system is able to track and go to the user according to the user's position. The omnidirectional wheel was adapted in the power system to perform translating and spinning movements. The translating movement enables the robot to avoid obstacles faster and flexibly in paths. With the spinning movement, the robot can quickly find the direction of the object. Finally, the experiments show that the proposed system has good performance in service environments.

Taiwanese is one of the main languages spoken by Taiwanese. Taiwanese was commonly used language in Taiwan before, but now it is facing the dilemma of declining. Therefore, maintaining traditional culture in the ever-changing trend is a major issue. In this study, we developed the Taiwanese speech recognition system which the Kaldi Toolkit was used to implement. The Taiwanese corpus was collected by Taiwan Taiwanese National Reading Competition and Classmate Recording, and about 11 hours of audio files were collected in total. Because the training data is a small dataset, two data augmentation methods are used to increase the training data, so that the acoustic model can be more robust and more effective training. One method is speed perturbation, which speeds up the original data by 1.1 times and slows it down by 0.9 times. Another method is to use multi-condition training data to simulate the reverberation of the original speech and add background noise. The background noise includes music, speech, and noise. The acoustic model is trained for different hybrid deep neural network architectures which can use the advantages of each neural network by hybrid different neural networks, such as CNN-LSTM-TDNN. In the experimental results, the CER in the domain of language modeling reaches 3.95%, and the CER of the online decoding test is 3.06%. Compared with other research on Taiwanese speech recognition of similar dataset size, the recognition results are better than other studies.

Advances in artificial intelligence-based autonomous applications have led to the advent of domestic robots for smart elderly care; the preliminary critical step for such robots involves increasing the comprehension of robotic visualizing of human activity recognition. In this paper, discrete hidden Markov models (D-HMMs) are used to investigate human activity recognition. Eleven daily home activities are recorded using a video camera with an RGB-D sensor to collect a dataset composed of 25 skeleton joints in a frame, wherein only 10 skeleton joints are utilized to efficiently perform human activity recognition. Features of the chosen ten skeleton joints are sequentially extracted in terms of pose sequences for a specific human activity, and then, processed through coordination transformation and vectorization into a codebook prior to the D-HMM for estimating the maximal posterior probability to predict the target. In the experiments, the confusion matrix is evaluated based on eleven human activities; furthermore, the extension criterion of the confusion matrix is also examined to verify the robustness of the proposed work. The novelty indicated D-HMM theory is not only promising in terms of speech signal processing but also is applicable to visual signal processing and applications.

Medication safety has been a important research in many decays. If there is a mistake in the process of packaging medicines, it may cause great harm to patients. This research is aimed at the development of automatic drug image verification functions. Our system is composed of two stages. The first stage is arbitrary axis-aligned object detector, which is mainly based on deep residual network and feature pyramid network(FPN). The detector predicts the rotation bounding boxes for drugs by multi-scale feature maps generated by FPN. Then, the rotation bounding boxes are axially aligned, and the drug image is cropped according to axis-aligned bounding box. The second stage is feature matcher, which is based on feature embedding network. The embedding feature extracted by feature embedding network is combined with the geometric feature obtained by arbitrary axis-aligned object detector to determine whether the drug in image is belonging to expected category that user specify. Our system can detect multiscale rotating drugs and can identify drugs at any position, angle, and placement surface. And due to the addition of geometric features, it can effectively identify drugs with similar appearance but different sizes. Finally, according to the experimental results, a high accuracy rate of 0.047% FAR can be obtained.