Robots must be able to recognize human emotions to improve the human-robot interaction (HRI). This study proposes an emotion recognition system for a humanoid robot. The robot is equipped with a camera to capture users' facial images, and it uses this system to recognize users' emotions and responds appropriately. The emotion recognition system, based on a deep neural network, learns six basic emotions: happiness, anger, disgust, fear, sadness, and surprise. First, a convolutional neural network (CNN) is used to extract visual features by learning on a large number of static images. Second, a long short-term memory (LSTM) recurrent neural network is used to determine the relationship between the transformation of facial expressions in image sequences and the six basic emotions. Third, CNN and LSTM are combined to exploit their advantages in the proposed model. Finally, the performance of the emotion recognition system is improved by using transfer learning, that is, by transferring knowledge of related but different problems. The performance of the proposed system is verified through leave-one-out cross-validation and compared with that of other models. The system is applied to a humanoid robot to demonstrate its practicability for improving the HRI.

This study proposed a new processing method to predict breast cancer on the basis of nine individual attributes, including age, body mass index, glucose, insulin, and a homeostasis model assessment. First, principal component analysis (PCA) was used to identify valuable parts of the data and further reduce the dimensions of the data. The cumulative proportion of the top five major components was 99.89%. The multilayer perceptron network (MLP) method was then used to extract characteristics included in the data, and the structure of the network was designed for the exploration of how data developed as the dimensions increased or decreased. As such, the model was established to first explore (high dimensional) and then develop (low dimensional) data. After training and learning, the models could segregate the representative attributes and numbers, and the characteristic data were then used as classifiers through transfer learning techniques using support vector machines. To verify the proposed method, the experiment performed $k$ -fold cross-validation 50 times on average. Experimental results verified the proposed method with 10-fold cross-validation using the dataset of Manuel Gomes from the University Hospital Centre of Coimbra, and an accuracy of 86.97% was achieved. The results indicate that the proposed series of processes and methods can effectively and powerfully examine the incidence of breast cancer. Furthermore, the data processed using only the PCA method as well as the characteristics extracted through the PCA method then combined with MLP after learning were analyzed. The differences displayed for the visual technique characteristics of the t-distributed stochastic neighbor embedding were compared.

This paper proposes the implementation of fuzzy motion control based on reinforcement learning (RL) and Lagrange polynomial interpolation (LPI) for gait synthesis of biped robots. First, the procedure of a walking gait is redefined into three states, and the parameters of this designed walking gait are determined. Then, the machine learning approach applied to adjusting the walking parameters is policy gradient RL (PGRL), which can execute real-time performance and directly modify the policy without calculating the dynamic function. Given a parameterized walking motion designed for biped robots, the PGRL algorithm automatically searches the set of possible parameters and finds the fastest possible walking motion. The reward function mainly considered is first the walking speed, which can be estimated from the vision system. However, the experiment illustrates that there are some stability problems in this kind of learning process. To solve these problems, the desired zero moment point trajectory is added to the reward function. The results show that the robot not only has more stable walking but also increases its walking speed after learning. This is more effective and attractive than manual trial-and-error tuning. LPI, moreover, is employed to transform the existing motions to the motion which has a revised angle determined by the fuzzy motion controller. Then, the biped robot can continuously walk in any desired direction through this fuzzy motion control. Finally, the fuzzy-based gait synthesis control is demonstrated by tasks and point- and line-target tracking. The experiments show the feasibility and effectiveness of gait learning with PGRL and the practicability of the proposed fuzzy motion control scheme.

This study proposes an automatic classifier for detecting the multiclass probabilities of hepatitis C virus (HCV) incidence based on patients’ blood attributes. The purpose of this study is to establish an artificial intelligence-based model that can identify HCV patients and detect the disease in early stage for future treatments. This model can be applied by using clinical data and keeps the performance from imbalanced datasets. The innovation in this article lies in considering the “unbalanced data” existing in medical record-based clinical data. Synthetic minority oversampling technique (SMOTE) algorithm was further employed to derive corresponding solutions. This objective was achieved using a cascade two-stage method combining the random forest (RF) and logistic regression (LR) algorithms. Two models were trained by applying the RF (Model 1) and LR (Model 2) to raw and preprocessed data, respectively. The artificial bee colony (ABC) algorithm was then used to determine the optimal threshold value required for filtering and separation, that is, the optimal combination of both models. The two-stage mixing algorithm combines algorithms of different search dimensions, thus integrating the strengths of those algorithms. The critical threshold value for separating Model 1 and Model 2 was obtained through an optimized search using the ABC algorithm. After conducting 10-fold Monte Carlo cross-validation experiments 50 times (for mean values), data from the recent pandemic were used to verify the proposed method. To evaluate the quantitative results, indicators, such as prediction accuracy, precision, recall, F1-score, and Matthews correlation coefficient, were compared with those of the latest algorithms used in relevant fields. The results indicate that the proposed model, named Cascade RF-LR (with SMOTE), can be used to detect the multiclass probabilities of HCV incidence using the ABC algorithm, thereby improving the effectiveness of relevant treatments.

Kinematic and dynamic modelling and corresponding control design of a four‐wheel‐independent steering and four‐wheel‐independent driving (4WIS4WID) mobile robot are presented in this study. Different from the differential or car‐like mobile robot, the 4WIS4WID mobile robot is controlled by four steering and four driving motors, so the control scheme should possess the ability to integrate and manipulate the four independent wheels. A trajectory tracking control scheme is developed for the 4WIS4WID mobile robot, where both non‐linear kinematic control and dynamic sliding‐mode control are designed. All of the stabilities of the kinematic and dynamic control laws are proved by Lyapunov stability analysis. Finally, the feasibility and validity of the proposed trajectory tracking control scheme are confirmed through computer simulations.