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.

Optimizing techniques for discovering molecular structures with desired properties is crucial in artificial intelligence (AI)-based drug discovery. Combining deep generative models with reinforcement learning has emerged as an effective strategy for generating molecules with specific properties. Despite its potential, this approach is ineffective in exploring the vast chemical space and optimizing particular chemical properties. To overcome these limitations, we present Mol-AIR, a reinforcement learning-based framework using adaptive intrinsic rewards for effective goal-directed molecular generation. Mol-AIR leverages the strengths of both history-based and learning-based intrinsic rewards by exploiting random distillation network and counting-based strategies. In benchmark tests, Mol-AIR demonstrates improved performance over existing approaches in generating molecules having the desired properties, including penalized LogP, QED, and celecoxib similarity, without any prior knowledge. We believe that Mol-AIR represents a significant advancement in drug discovery, offering a more efficient path to discovering novel therapeutics.

The fundamental properties of long-range (LoRa) performance have been revealed by previous research, but advanced issues remain unresolved. This paper tackles three technical challenges that are confronted when establishing a LoRa network on a smart energy campus testbed in Korea. First, the communication range of LoRa in a combined indoor and outdoor environment has yet to be determined. To address this problem, this study builds a LoRa testbed from which we measure the propagation properties of radio signals in a combined environment. Then, we establish a simplified path loss model for LoRa PHY and compute the communication range. Next, national regulations enforce the use of the Listen-Before-Talk (LBT) scheduling scheme, but its performance has never been examined. This paper enumerates the impacts of LBT, threshold values, back-off algorithms, and application parameters on LoRa Medium Access Control (MAC) performance. Last, the application parameters required by the smart energy scenario influence LoRa performance, but their impacts have been scarcely reported. Based on the application parameters and experimental results, this paper proposes a strategy to deploy LoRa gateway(s) and nodes on the campus. To the best of the authors’ knowledge, this is the first work that considers performance issues when establishing a LoRa network on a real-world application testbed.

The success of Transformer-based models has encouraged many researchers to learn CAD models using sequence-based approaches. However, learning CAD models is still a challenge, because they can be represented as complex shapes with long construction sequences. Furthermore, the same CAD model can be expressed using different CAD construction sequences. We propose a novel contrastive learning-based approach, named ContrastCAD, that effectively captures semantic information within the construction sequences of the CAD model. ContrastCAD generates augmented views using dropout techniques without altering the shape of the CAD model. We also propose a new CAD data augmentation method, called a Random Replace and Extrude (RRE) method, to enhance the learning performance of the model when training an imbalanced training CAD dataset. Experimental results show that the proposed RRE augmentation method significantly enhances the learning performance of Transformer-based autoencoders, even for complex CAD models having very long construction sequences. The proposed ContrastCAD model is shown to be robust to permutation changes of construction sequences and performs better representation learning by generating representation spaces where similar CAD models are more closely clustered. Our codes are available at https://github.com/cm8908/ContrastCAD .