Many emerging sensor network applications operate in challenging environments wherein the base station is unavailable. Data generated from such intermittently connected sensor networks (ICSNs) must be stored inside the network for some unpredictable time before uploading opportunities become available. Consequently, sensory data could overflow the limited storage capacity available in the entire network, making discarding valuable data inevitable. To overcome such overall storage overflow in ICSNs, we propose and study a new algorithmic framework calleddataaggregation foroverall storageoverflow ($\text {DAO}^{2}$). Utilizing spatial data correlation that commonly exists among sensory data,$\text {DAO}^{2}$employs data aggregation techniques to reduce the overflow data size while minimizing the total energy consumption in data aggregation. At the core of our framework are two new graph theoretical problems that have not been studied. We refer to them astravelingsalesmenplacementproblem ($\text {TSP}^{2}$) and quota traveling salesmen placement problem (Q-$\text {TSP}^{2}$). Different from the well-known multiple traveling salesman problem (mTSP) and its variants, which mainly focus on the routing of multiple salesmen initially located at fixed locations,$\text {TSP}^{2}$and Q-$\text {TSP}^{2}$must decide the placement as well as the routing of the traveling salesmen. We prove that both problems are NP-hard and design approximation, heuristic, and distributed algorithms. Our algorithms outperform the state-of-the-art data aggregation work with base stations by up to 71.8% in energy consumption.

Recent advances have enabled automatic sound recognition systems for deaf and hard of hearing (DHH) users on mobile devices. However, these tools use pre-trained, generic sound recognition models, which do not meet the diverse needs of DHH users. We introduce ProtoSound, an interactive system for customizing sound recognition models by recording a few examples, thereby enabling personalized and fine-grained categories. ProtoSound is motivated by prior work examining sound awareness needs of DHH people and by a survey we conducted with 472 DHH participants. To evaluate ProtoSound, we characterized performance on two real-world sound datasets, showing significant improvement over state-of-the-art (e.g., +9.7% accuracy on the first dataset). We then deployed ProtoSound's end-user training and real-time recognition through a mobile application and recruited 19 hearing participants who listened to the real-world sounds and rated the accuracy across 56 locations (e.g., homes, restaurants, parks). Results show that ProtoSound personalized the model on-device in real-time and accurately learned sounds across diverse acoustic contexts. We close by discussing open challenges in personalizable sound recognition, including the need for better recording interfaces and algorithmic improvements.

Smartwatches have the potential to provide glanceable, always-available sound feedback to people who are deaf or hard of hearing. In this paper, we present a performance evaluation of four low-resource deep learning sound classification models: MobileNet, Inception, ResNet-lite, and VGG-lite across four device architectures: watch-only, watch+phone, watch+phone+cloud, and watch+cloud. While direct comparison with prior work is challenging, our results show that the best model, VGG-lite, performed similar to the state of the art for non-portable devices with an average accuracy of 81.2% (SD=5.8%) across 20 sound classes and 97.6% (SD=1.7%) across the three highest-priority sounds. For device architectures, we found that the watch+phone architecture provided the best balance between CPU, memory, network usage, and classification latency. Based on these experimental results, we built and conducted a qualitative lab evaluation of a smartwatch-based sound awareness app, called SoundWatch (Figure 1), with eight DHH participants. Qualitative findings show support for our sound awareness app but also uncover issues with misclassifications, latency, and privacy concerns. We close by offering design considerations for future wearable sound awareness technology.