Facial Expression Recognition (FER) is a challenging task that improves natural human-computer interaction. This paper focuses on automatic FER on a single in-the-wild (ITW) image. ITW images suffer real problems of pose, direction, and input resolution. In this study, we propose a pyramid with super-resolution (PSR) network architecture to solve the ITW FER task. We also introduce a prior distribution label smoothing (PDLS) loss function that applies the additional prior knowledge of the confusion about each expression in the FER task. Experiments on the three most popular ITW FER datasets showed that our approach outperforms all the state-of-the-art methods.

Due to the increase of lung cancer globally, and particularly in Korea, survival analysis for this type of cancer has gained prominence in recent years. For this task, mathematical and traditional machine learning approaches are commonly used by medical doctors. While the deep learning approach has had proven success in computer vision tasks, natural language processing and other AI techniques are also adopted for this task. Due to the privacy issues and management process, data in medicine are difficult to collect, which leads to a paucity of samples. The small number of samples makes it difficult to use deep learning and renders this approach unusable. In this investigation, we propose a network architecture that combines a variational autoencoder (VAE) with the typical DNN architecture to solve the survival analysis task. With a training size of n = 4107, MVAESA achieves a C-index of $0.722$ while CoxCC, CoxPH, and CoxTime achieved scores of $0.713$, $0.703$, and $0.710$, respectively. With a small training size of n = 379, MVAESA achieves a C-index of $0.707$, compared with $0.689$, $0.688$ and $0.690$ for CoxCC, CoxPH, and CoxTime, respectively. The results show that the combination of a VAE with a target task makes the network more stable and that the network could be trained using a small-sized sample.

In recent years, lithium-ion batteries (LIB) have been used widely in portable electronic devices because of their advantages of durability, stability, high-capacity, low-cost, light-weight and smallscale. It makes LIB also deployed in various complex systems, in which efficient prediction of battery data, especially state-of-health (SoH), becomes crucial to ensure that the systems work stably without risks of power interruptions. With the recent improvement of Artificial Intelligence (AI) technologies, many works have been reported using deep learning (DL) models to investigate this problem, since such models can potentially increase their performance with more training data. This is also our direction in this research, which introduces a novel data-driven approach so-called Autoregression Nested Sequence (ARNS). On one hand, we come up with a nested sequence model to efficiently aggregate channel-wise and cycle-wise information, both of which are closely related to the operations of LIB. On the other hand, we incorporate relaxation effects into the model operations to handle peak prediction. To the best of our knowledge, ARNS is the first sophisticated deep learning model that combines all those features into a whole predictive system. The experimental results obtained using the NASA and CALCE datasets confirm significant improvement of ARNS, especially when dealing with peak periods in different SoH of multiple cycles.

Early detection and prediction of cardiac anomalies play an important role in the diagnosis and treatment of cardiovascular diseases. In medicine, electrocardiography provides valuable information for the doctors since they can accurately determine what is happening concerning the heart activities. Nevertheless, electrocardiography classification is a non-trivial challenge due to the specialties of these data as well as the reliability of manual data collection methods. With the recent advancement of the IoT technologies, some wearable IoT devices for electrocardiography monitoring have been developed. However, the data collected from those devices, though possibly automatic, pose more challenging issues for the problem of electrocardiography classification. In this paper, we propose a novel solution for electrocardiography signal classification based on Deep Learning by combining Auto Encoder and Long-Short Term Memory models to handle data collected from intelligent IoT devices Shimmer and VitalSigns Holter.

This paper proposes an alternative approach for synthesizing Vietnamese speech. In order to improve the naturalness and intelligibility of the speech synthesizer, we propose the Vietnamese phoneme model and integrate into an end-to-end model. We employ the pipeline of Tacotron 2 model with attention scheme to generate high-quality speeches. As we replace the character embedding model with Vietnamese phoneme model, we obtain promising results. In addition, we also create a tool for converting Vietnamese text to phoneme sequence. The new phoneme embedding method can also be applied to various languages, while we can take the advantages of state-of-the-art models.