Immune checkpoint molecules have been identified as crucial regulators of the immune response, which motivated the emergence of immune checkpoint‐targeting therapeutic strategies. However, the prognostic significance of the immune checkpoint molecules PD‐1, CTLA4, TIM‐3 and LAG‐3 remains controversial. The aim of our study was to conduct a systematic assessment of the expression of these immune checkpoint molecules across different cancers in relation to treatment response, tumor‐infiltrating immune cells and survival. Oncomine and PrognoScan database analyses were used to investigate the expression levels and prognostic values of these immune checkpoint molecule genes across various cancers. Then, we used Kaplan–Meier plotter to validate the associations between the checkpoint molecules and cancer survival identified in the PrognoScan analysis. TIMER analysis was used to evaluate immune cell infiltration data from The Cancer Genome Atlas. Finally, we used Gene Expression Profiling Interactive Analysis to investigate the prognostic value of these four checkpoint molecules and assess the correlations between these four checkpoint molecules and genetic markers. These immune checkpoint molecules may potentially serve as prognostic factors and therapeutic targets in breast cancer, ovarian cancer and lung cancer. The prognostic roles of these checkpoint molecules varied greatly across cancers, which implied a noteworthy amount of heterogeneity among tumors, even within the same molecular subtype. In addition, the expression patterns of these checkpoint molecules were closely associated with treatment response and provided some useful direction when choosing chemotherapeutic drugs. These findings enhance our understanding of these checkpoints in cancer treatment and identify strategies to promote synergistic activities in the context of other immunotherapies.

No abstract

Effective emotion recognition algorithms can help machines better understand people and promote the development of human-computer interaction applications. In recent years, many research efforts have used benchmark expression data to train deep neural network models to achieve state-of-art results. These high-accuracy models usually contain hundreds of layers, so they require complex calculations and may not be suitable for real-world scenarios. This paper proposes a lightweight emotion recognition (LER) model to handle the latency problem under natural conditions. The three main contributions of this paper are as follows. 1) The LER model incorporates a densely connected convolution layer and model compression techniques into a framework that eliminates redundancy parameters. 2) Multichannel input is introduced in our work to preprocess the image data, which improves the learning ability of the model. 3) Experiments show that the proposed LER model has better performance on the FER2013 and FERPLUS datasets compared with other lightweight models. Compared with the VGG13 used in previous work, the LER model achieves higher accuracy and reduces the number of parameters by 97 times. Finally, the FERFIN dataset is created, which had fewer noise data and more accurate labels than the FERPLUS dataset.

The high incidence of traffic accidents brings immeasurable losses to life. In order to avoid such crises, researchers and automakers have used many methods to solve this problem. Among them, technology based on visual features is widely used in driver fatigue detection. As fatigue detection plays a vital role in the driving process, the high accuracy of fatigue monitoring is very important. This paper focuses on the method based on convolutional neural network to detect driver fatigue. First, in the face detection part, the Single-Shot Multi-Box Detector algorithm is used to improve the speed and accuracy of face detection to extract the eye and mouth regions; second, the VGG16 network is used to learn fatigue features, which is performed on the NTHU-Drowsy Driver Detection (NTHU-DDD) data set and the other two modified data sets Training test. The main result of this work is that the accuracy of fatigue monitoring is higher than other methods including the original method, with an accuracy rate of over 90%. And it has better generalization ability than the multi-physical feature fusion detection method. At the same time, we propose the fatigue detection method based on convolutional neural network to improve the advanced driver assistance system (ADAS) to make it more robust and reliable decision making.

Graspirng objects is an important capability for humanoid robots. Due to complexity of environmental and diversity of objects, it is difficult for the robot to accurately recognize and grasp multiple objects. In response to this problem, we propose a robotic grasping method that uses the deep learning method You Only Look Once v3 for multi-target detection and the auxiliary signs to obtain target location. The method can control the movement of the robot and plan the grasping trajectory based on visual feedback information. It is verified by experiments that this method can make the humanoid robot NAO grasp the object effectively, and the success rate of grasping can reach 80% in the experimental environment.