Alzheimer’s dementia is a progressive neurodegenerative disease that causes cognitive and physical impairment. It severely deteriorates the quality of life in affected individuals. An early diagnosis can assist immensely in better management of their healthcare needs. In recent years, there has been a renewed impetus in development of automated methods for recognition of various disorders by leveraging advancements in artificial intelligence. Here, we propose a multimodal system that can identify linguistic and paralinguistic traits of dementia using an automated screening tool. We show that bag-of-deep-neural-embeddings and ensemble learning offer a viable approach to objective assessment of dementia. The developed system is tested on the Alzheimer’s Dementia Recognition Challenge dataset, where it achieved a new state-of-the-art (SOTA) performance for the classification task and matched the current SOTA for the regression task. These results highlight the efficacy of our proposed system for facilitating an early diagnosis of dementia.

In this paper, integration of silicon oxycarbide (SiOC) and silicon nitride (Si₃N₄) platforms was demonstrated to realize ultra-efficient thermal tuning of photonic integrated circuits. Si₃N₄ being a fascinating photonic material with moderate refractive index (n ≈ 2) and ultra-low loss, lacks thermo-optic coefficient that makes thermal phase actuators long and dissipate high powers. Integration of SiOC coating with a comparable refractive index (n = 2.2) boosts the effective thermo-optic efficiency of Si₃N₄ photonic circuits by almost an order of magnitude with no additional loss. An SiOC layer was deposited by the reactive RF magnetron sputtering technique from the SiC target at room temperature. The structural, chemical and optical characterizations of the sputter deposited SiOC layer were performed with SEM, AFM, EDS and spectroscopic ellipsometry. The results of SiOC-coated Si₃N₄ and pristine Si₃N₄ photonic devices were discussed and compared. SiOC was demonstrated as an enabling platform for low-loss and power-efficient thermal phase actuators in conventional photonic technologies with application in reconfigurable photonic systems.

This report provides a brief description of our proposed solution for the Vocal Burst Type classification task of the ACII 2022 Affective Vocal Bursts (A-VB) Competition. We experimented with two approaches as part of our solution for the task at hand. The first of which is based on convolutional neural networks trained on Mel Spectrograms, and the second is based on average pooling of deep acoustic embeddings from a pretrained wav2vec2 model. Our best performing model achieves an unweighted average recall (UAR) of 0.5190 for the test partition, compared to the chance-level UAR of 0.1250 and a baseline of 0.4172. Thus, an improvement of around 20% over the challenge baseline. The results reported in this document demonstrate the efficacy of our proposed approaches to solve the AV-B Type Classification task.