Trainable Quaternion Extended Kalman Filter with Multi-Head Attention for Dead Reckoning in Autonomous Ground Vehicles.

Extended Kalman filter (EKF) is one of the most widely used Bayesian estimation methods in the optimal control area. Recent works on mobile robot control and transportation systems have applied various EKF methods, especially for localization. However, it is difficult to obtain adequate and reliable process-noise and measurement-noise models due to the complex and dynamic surrounding environments and sensor uncertainty. Generally, the default noise values of the sensors are provided by the manufacturer, but the values may frequently change depending on the environment. Thus, this paper mainly focuses on designing a highly accurate trainable EKF-based localization framework using inertial measurement units (IMUs) for the autonomous ground vehicle (AGV) with dead reckoning, with the goal of fusing it with a laser imaging, detection, and ranging (LiDAR) sensor-based simultaneous localization and mapping (SLAM) estimation for enhancing the performance. Convolution neural networks (CNNs), backward propagation algorithms, and gradient descent methods are implemented in the system to optimize the parameters in our framework. Furthermore, we develop a unique cost function for training the models to improve EKF accuracy. The proposed work is general and applicable to diverse IMU-aided robot localization models.

DXM-TransFuse U-net: Dual cross-modal transformer fusion U-net for automated nerve identification.

Accurate nerve identification is critical during surgical procedures to prevent damage to nerve tissues. Nerve injury can cause long-term adverse effects for patients, as well as financial overburden. Birefringence imaging is a noninvasive technique derived from polarized images that have successfully identified nerves that can assist during intraoperative surgery. Furthermore, birefringence images can be processed under 20 ms with a GPGPU implementation, making it a viable image modality option for real-time processing. In this study, we first comprehensively investigate the usage of birefringence images combined with deep learning, which can automatically detect nerves with gains upwards of 14% over its color image-based (RGB) counterparts on the F2 score. Additionally, we develop a deep learning network framework using the U-Net architecture with a Transformer based fusion module at the bottleneck that leverages both birefringence and RGB modalities. The dual-modality framework achieves 76.12 on the F2 score, a gain of 19.6 % over single-modality networks using only RGB images. By leveraging and extracting the feature maps of each modality independently and using each modality's information for cross-modal interactions, we aim to provide a solution that would further increase the effectiveness of imaging systems for enabling noninvasive intraoperative nerve identification.

Robust Multimodal Emotion Recognition from Conversation with Transformer-Based Crossmodality Fusion.

Decades of scientific research have been conducted on developing and evaluating methods for automated emotion recognition. With exponentially growing technology, there is a wide range of emerging applications that require emotional state recognition of the user. This paper investigates a robust approach for multimodal emotion recognition during a conversation. Three separate models for audio, video and text modalities are structured and fine-tuned on the MELD. In this paper, a transformer-based crossmodality fusion with the EmbraceNet architecture is employed to estimate the emotion. The proposed multimodal network architecture can achieve up to 65% accuracy, which significantly surpasses any of the unimodal models. We provide multiple evaluation techniques applied to our work to show that our model is robust and can even outperform the state-of-the-art models on the MELD.

Musical Emotion Recognition with Spectral Feature Extraction based on a Sinusoidal Model with Model-based and Deep-learning approaches.

This paper presents a method for extracting novel spectral features based on a sinusoidal model. The method is focused on characterizing the spectral shapes of audio signals using spectral peaks in frequency sub-bands. The extracted features are evaluated for predicting the levels of emotional dimensions, namely arousal and valence. Principal component regression, partial least squares regression, and deep convolutional neural network (CNN) models are used as prediction models for the levels of the emotional dimensions. The experimental results indicate that the proposed features include additional spectral information that common baseline features may not include. Since the quality of audio signals, especially timbre, plays a major role in affecting the perception of emotional valence in music, the inclusion of the presented features will contribute to decreasing the prediction error rate.