Recognizing food types through sensor signals for unseen users remains remarkably challenging, despite extensive recent studies. The efficacy of prior machine learning techniques is dwarfed by giant variations of data collected from multiple participants, partly because users have varied chewing habits and wear sensor devices in various manners. This work treats the problem as an instance of the domain adaptation problem, where each user represents a domain. We develop the first multi-source domain adaptation (MSDA) method for food-typing recognition, which consists of three major components: stratified normalization, a multi-source domain adaptor, and adaptive ensemble learning. New techniques are developed for each component. Using a real-world dataset comprised of 15 participants, we demonstrate that our method achieves
This content will become publicly available on September 30, 2025
FPGAs have been shown to operate reliably within harsh radiation environments by employing single-event upset (SEU) mitigation techniques, such as configuration scrubbing, triple-modular redundancy, error correction coding, and radiation aware implementation techniques. The effectiveness of these techniques, however, is limited when using complex system-level designs that employ complex I/O interfaces with single-point failures. In previous work, a complex SoC system running Linux applied several of these techniques only to obtain an improvement of 14
- Award ID(s):
- 1738550
- PAR ID:
- 10548179
- Publisher / Repository:
- ACM
- Date Published:
- Journal Name:
- ACM Transactions on Reconfigurable Technology and Systems
- Volume:
- 17
- Issue:
- 3
- ISSN:
- 1936-7406
- Page Range / eLocation ID:
- 1 to 21
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
more » « less
\(1.33\times\) \(2.13\times\) -
more » « less
In this article, we show how a single function,
join , can be used to implement parallelbalanced binary search trees (BSTs ) simply and efficiently. Based onjoin , our approach applies to multiple balanced tree data structures, and a variety of functions for ordered sets and maps. We describe our technique as an algorithmic framework calledjoin-based algorithms . We show that thejoin function fully captures what is needed for rebalancing trees for a variety of tree algorithms, as long as the balancing scheme satisfies certain properties, which we refer to asjoinable trees. We discuss four balancing schemes that are joinable: AVL trees, red-black trees, weight-balanced trees, and treaps. We present a variety of tree algorithms that apply to joinable trees, includinginsert ,delete ,union ,intersection ,difference ,split ,range ,filter , and so on, most of them also parallel. These algorithms are generic across balancing schemes. Many algorithms are optimal in the comparison model, and we provide a general proof to show the efficiency in work for joinable trees. The algorithms are highly parallel, all with polylogarithmic span (parallel dependence). Specifically, the set-set operationsunion ,intersection , anddifference have work\( O(m\log (\frac{n}{m}+1)) \) \( n \) \( m\le n \) We implemented and tested our algorithms on the four balancing schemes. In general, all four schemes have quite similar performance, but the weight-balanced tree slightly outperforms the others. They have the same speedup characteristics, getting around 73
\( \times \) -
more » « less
Hyperdimensional computing (HDC) is a computing paradigm inspired by the mechanisms of human memory, characterizing data through high-dimensional vector representations, known as hypervectors. Recent advancements in HDC have explored its potential as a learning model, leveraging its straightforward arithmetic and high efficiency. The traditional HDC frameworks are hampered by two primary static elements: randomly generated encoders and fixed learning rates. These static components significantly limit model adaptability and accuracy. The static, randomly generated encoders, while ensuring high-dimensional representation, fail to adapt to evolving data relationships, thereby constraining the model’s ability to accurately capture and learn from complex patterns. Similarly, the fixed nature of the learning rate does not account for the varying needs of the training process over time, hindering efficient convergence and optimal performance. This paper introduces
\(\mathsf {TrainableHD} \) \(\mathsf {TrainableHD} \) \(\mathsf {TrainableHD} \) \(\mathsf {TrainableHD} \) \(\mathsf {TrainableHD} \) \(\mathsf {TrainableHD} \) -
more » « less
Current computing device authentication often presents accessibility barriers for people with
upper extremity impairments (UEI) . In this article, we present a framework calledAccessible image-Association-based Authentication for Computing devices (A3C) , a novel recognition-based graphical authentication framework specifically designed for people with UEI to authenticate to their computing devices. A3C requires users to provide a set of primary images the user knows that are recognizable to them and subsequently associate each primary image with a secondary image. To evaluate the efficacy of the A3C framework, we instantiated the framework by implementing a version of A3C calledA3C-FA , which uses images of faces of people the user knows as the primary image and animal images as the secondary image. We then performed three studies to evaluate A3C-FA: a shoulder-surfing attack study (N ), a close-adversary attack study (\(=\) N ), and a usability study with people with UEI (\(=\) N ). We found that A3C was robust against both shoulder-surfing and close-adversary attacks. We also performed a detailed study to evaluate the accessibility of A3C-FA. Our participants reported that A3C-FA was more usable and more secure than the authentication approaches with which they were familiar. Based on these findings, we suggest four areas of future research to further improve the design of the A3C framework.\(=\) -
more » « less
Dense matrix multiply (MM) serves as one of the most heavily used kernels in deep learning applications. To cope with the high computation demands of these applications, heterogeneous architectures featuring both FPGA and dedicated ASIC accelerators have emerged as promising platforms. For example, the AMD/Xilinx Versal ACAP architecture combines general-purpose CPU cores and programmable logic with AI Engine processors optimized for AI/ML. An array of 400 AI Engine processors executing at 1 GHz can provide up to 6.4 TFLOPS performance for 32-bit floating-point (FP32) data. However, machine learning models often contain both large and small MM operations. While large MM operations can be parallelized efficiently across many cores, small MM operations typically cannot. We observe that executing some small MM layers from the BERT natural language processing model on a large, monolithic MM accelerator in Versal ACAP achieved less than 5% of the theoretical peak performance. Therefore, one key question arises:
How can we design accelerators to fully use the abundant computation resources under limited communication bandwidth for end-to-end applications with multiple MM layers of diverse sizes? We identify the biggest system throughput bottleneck resulting from the mismatch between massive computation resources of one monolithic accelerator and the various MM layers of small sizes in the application. To resolve this problem, we propose the CHARM framework to compose
multiple diverse MM accelerator architectures working concurrently on different layers within one application. CHARM includes analytical models which guide design space exploration to determine accelerator partitions and layer scheduling. To facilitate system designs, CHARM automatically generates code, enabling thorough onboard design verification. We deploy the CHARM framework on four different deep learning applications in FP32, INT16, and INT8 data types, including BERT, ViT, NCF, and MLP, on the AMD/Xilinx Versal ACAP VCK190 evaluation board. Our experiments show that we achieve 1.46 TFLOPS, 1.61 TFLOPS, 1.74 TFLOPS, and 2.94 TFLOPS inference throughput for BERT, ViT, NCF, and MLP in FP32 data type, respectively, which obtain 5.29\(\times\) \(\times\) \(\times\) \(\times\) https://github.com/arc-research-lab/CHARM
