Abstract Several studies have attempted to solve traveling salesman problems (TSPs) using various deep learning techniques. Among them, Transformer-based models show state-of-the-art performance even for large-scale Traveling Salesman Problems (TSPs). However, they are based on fully-connected attention models and suffer from large computational complexity and GPU memory usage. Our work is the first CNN-Transformer model based on a CNN embedding layer and partial self-attention for TSP. Our CNN-Transformer model is able to better learn spatial features from input data using a CNN embedding layer compared with the standard Transformer-based models. It also removes considerable redundancy in fully-connected attention models using the proposed partial self-attention. Experimental results show that the proposed CNN embedding layer and partial self-attention are very effective in improving performance and computational complexity. The proposed model exhibits the best performance in real-world datasets and outperforms other existing state-of-the-art (SOTA) Transformer-based models in various aspects. Our code is publicly available at https://github.com/cm8908/CNN_Transformer3 .

In many cyber-physical systems (CPS), one of the primary challenges is how to disseminate many sensor streams to collaborating entities in a timely, reliable, and scalable manner. However, in CPS, communication and related computation is often unstable and constitutes a serial bottleneck when multiple sensor streams need to be distributed. In this paper, we propose a novel publish-subscribe middleware architecture, called parallel data distribution service (PDDS), to address this problem. To bypass this serial bottleneck effectively, PDDS exploits state-space models for sensor streams both at a publisher and its subscribers. These models are used to estimate true states of monitored physical processes without actual communication. This approach not only reduces the communication overhead significantly, but also provides the tolerance against potential delays and instability in communication. Further, with the model-based methods, many sensor streams can be accessed in parallel since sensor streams can bypass a serial bottleneck, such as network stacks. At the middleware layer, PDDS processes the model-related computation, such as the state estimation, in parallel using modern embedded general-purpose computing on graphics processing units, enabling highly scalable and energy-efficient processing of massive sensor streams. The proposed approach is implemented in a data distribution service middleware using CUDA. Our evaluation results show that the proposed approach can achieve significant energy savings and much higher scalability compared to baseline approaches.

Our understanding on a silicon chip is limited due to low measurement resolution or model-silicon miscorrelation including variations. This paper shows that chips are better understood by combining noisy measurement results and model information through a mathematical algorithm. Our proposed method learns segment delays in logic circuits from quantized path delay measurements using ridge regression. During the learning process, we take advantage of both nominal segment delays and the delay sensitivity with respect to variations. We also interpret the ridge regression in Bayesian context and in doing so, propose an analytic formula to set the regularization parameter of the ridge regression. For the silicon measurement environments where low measurement resolution is the dominant source of measurement noise, this formula allows us to predict post-silicon results more accurately and speed up the algorithm eliminating inefficient and inaccurate cross-validation. We also demonstrate our method in enhancing the resolution of already measured path delays. We learn segment delays from quantized path delay measurements and predict the path delays prior to the quantization. Our simulation results show that the predicted path delays are much closer to actual values than the measured values and the nominal values.