Dual-Path Attention Compensation U-Net for Stroke Lesion Segmentation

For the segmentation task of stroke lesions, using the attention U-Net model based on the self-attention mechanism can suppress irrelevant regions in an input image while highlighting salient features useful for specific tasks. However, when the lesion is small and the lesion contour is blurred, attention U-Net may generate wrong attention coefficient maps, leading to incorrect segmentation results. To cope with this issue, we propose a dual-path attention compensation U-Net (DPAC-UNet) network, which consists of a primary network and auxiliary path network. Both networks are attention U-Net models and identical in structure. The primary path network is the core network that performs accurate lesion segmentation and outputting of the final segmentation result. The auxiliary path network generates auxiliary attention compensation coefficients and sends them to the primary path network to compensate for and correct possible attention coefficient errors. To realize the compensation mechanism of DPAC-UNet, we propose a weighted binary cross-entropy Tversky (WBCE-Tversky) loss to train the primary path network to achieve accurate segmentation and propose another compound loss function called tolerance loss to train the auxiliary path network to generate auxiliary compensation attention coefficient maps with expanded coverage area to perform compensate operations. We conducted segmentation experiments using the 239 MRI scans of the anatomical tracings of lesions after stroke (ATLAS) dataset to evaluate the performance and effectiveness of our method. The experimental results show that the DSC score of the proposed DPAC-UNet network is 6% higher than the single-path attention U-Net. It is also higher than the existing segmentation methods of the related literature. Therefore, our method demonstrates powerful abilities in the application of stroke lesion segmentation.

Direction-of-Arrival Dependency of Active Noise Cancellation Headphones

The evolving field of ear-mounted hearing devices manifests in more people wearing headphones, hearing aids or hearables in daily life. One of their purposes is to reduce the increasing burden of ambient noise. Their passive attenuation of noise can be supplemented by using Active Noise Cancellation (ANC). It uses acoustic anti-phase compensation. The occurring ambient noises in daily life can have a highly time-variant nature, e.g. with varying direction of arrival. In this contribution, we investigate the direction-dependency of ANC systems based on acoustic device-specific head related transfer functions (DHRTF). The DHRTF were measured with a fast measurement system for HRTF. We focus on in-ear headphones as the acoustic front-end. The headphones comprise two microphones; an outer microphone for ambient sounds and an inner microphone, which faces the eardrum. The transfer function between these two microphones is called the primary path. For the ANC system, we investigate optimal time-invariant feedforward filtering that depends on the primary path. Therefore, changes in the primary path due to varying directions of arrival may degrade the performance. The DHRTF measurements reveal differences in magnitude and phase of the primary path. Evaluations show that the attenuation performance depends on the direction of arrival.

Introduction

This book delves into the life and times of piano virtuoso Fannie Bloomfield-Zeisler. When Fannie Bloomfield embarked on her career as a pianist in 1883, she was greeted with a very different and much smaller musical world. There were fewer music conservatories. The primary path to professional eminence ran narrowly through elite European training and mastery of the German–Austrian repertoire. This book explores Bloomfield-Zeisler's life and career and how she became one of the foremost pianists of her generation. It presents anecdotes that humanize Bloomfield-Zeisler and make her more than a public figure. It also offers insights into her personality in ways that would only be possible if someone knew her well. This introduction discusses a number of historical trends that coalesced to make Bloomfield-Zeisler's career more achievable than it would have been even a few decades earlier: the most significant of these were the increasing presence of classical music in U.S. life and the rise of the “new woman.” It also provides an overview of the chapters that follow.

A Multipath Routing Protocol Based on Bloom Filter for Multihop Wireless Networks

On-demand multipath routing in a wireless ad hoc network is effective in achieving load balancing over the network and in improving the degree of resilience to mobility. In this paper, the salvage capable opportunistic node-disjoint multipath routing (SNMR) protocol is proposed, which forms multiple routes for data transmission and supports packet salvaging with minimum overhead. The proposed mechanism constructs a primary path and a node-disjoint backup path together with alternative paths for the intermediate nodes in the primary path. It can be achieved by considering the reverse route back to the source stored in the route cache and the primary path information compressed by a Bloom filter. Our protocol presents higher capability in packet salvaging and lower overhead in forming multiple routes. Simulation results show that SNMR outperforms the compared protocols in terms of packet delivery ratio, normalized routing load, and throughput.