No abstract

In this paper, we present a multimodal emotion recognition framework called EmotionMeter that combines brain waves and eye movements. To increase the feasibility and wearability of EmotionMeter in real-world applications, we design a six-electrode placement above the ears to collect electroencephalography (EEG) signals. We combine EEG and eye movements for integrating the internal cognitive states and external subconscious behaviors of users to improve the recognition accuracy of EmotionMeter. The experimental results demonstrate that modality fusion with multimodal deep neural networks can significantly enhance the performance compared with a single modality, and the best mean accuracy of 85.11% is achieved for four emotions (happy, sad, fear, and neutral). We explore the complementary characteristics of EEG and eye movements for their representational capacities and identify that EEG has the advantage of classifying happy emotion, whereas eye movements outperform EEG in recognizing fear emotion. To investigate the stability of EmotionMeter over time, each subject performs the experiments three times on different days. EmotionMeter obtains a mean recognition accuracy of 72.39% across sessions with the six-electrode EEG and eye movement features. These experimental results demonstrate the effectiveness of EmotionMeter within and between sessions.

Various delivery vectors have been integrated within biologically derived membrane systems to extend their residential time and reduce their reticuloendothelial system (RES) clearance during systemic circulation. However, rational design is still needed to further improve the in situ penetration efficiency of chemo-drug-loaded membrane delivery-system formulations and their release profiles at the tumor site. Here, a macrophage-membrane-coated nanoparticle is developed for tumor-targeted chemotherapy delivery with a controlled release profile in response to tumor microenvironment stimuli. Upon fulfilling its mission of tumor homing and RES evasion, the macrophage-membrane coating can be shed via morphological changes driven by extracellular microenvironment stimuli. The nanoparticles discharged from the outer membrane coating show penetration efficiency enhanced by their size advantage and surface modifications. After internalization by the tumor cells, the loaded drug is quickly released from the nanoparticles in response to the endosome pH. The designed macrophage-membrane-coated nanoparticle (cskc-PPiP/PTX@Ma) exhibits an enhanced therapeutic effect inherited from both membrane-derived tumor homing and step-by-step controlled drug release. Thus, the combination of a biomimetic cell membrane and a cascade-responsive polymeric nanoparticle embodies an effective drug delivery system tailored to the tumor microenvironment.