Che-Cheng Chang

IoT edge actuation requires records that remain auditable after an incident. We present a crypto-agile provenance framework that keeps decision records and signatures off-chain while a Sui Move contract stores a 32-byte SHA-256 anchor, bounded metadata, and a one-byte scheme identifier. Public keys and their ledger-time validity windows are registered on-chain for historical auditing. For a fixed multi-key endpoint, measured commitment gas is identical across Ed25519, ML-DSA-44, and SLH-DSA-SHA2-128f despite a 267-fold signature-size range; it also remains unchanged across a 3301-fold record-size range. Different endpoint key sets introduce up to 5.66% variation through state-rewrite costs on the evaluated localnet. On a Raspberry Pi 5, the mean of three ML-DSA-44 run medians is 0.65 ms, with a signing-latency coefficient of variation of approximately 78% and substantial upper tails. Additional crossed key-by-message measurements show no nominally significant ML-DSA key-factor result on the Pi, but two nominally significant ML-DSA-44 key-factor results in the desktop sessions, one of which remains significant after Bonferroni correction across 72 comparisons. These results do not establish key independence or a variance upper bound; they support budgeting for observed signing tails while preserving uncertainty about persistent key effects. The framework establishes tamper evidence and conditional endpoint attribution, not physical truthfulness of telemetry or the time a signature was created.

Various renewable energy sources, along with corresponding large-scale batteries, have been integrated into power grids, making renewable energy bidding and battery control critical in the real-time energy market. However, most bidding and control problems have been studied separately despite their accompanying impact on the total profit of renewable energy producers. Recently, a Reinforcement Learning (RL) strategy has been proposed to investigate renewable energy bidding and battery control jointly. It determines bidding values based on the battery’s error compensability and then applies additional battery control to the energy arbitrage process. Based on the same experimental scenarios, we present a method that incorporates the attention mechanism into long short-term memory reinforcement learning to increase total profits. We also consider various settings for our models to conduct a comprehensive survey. According to the experimental results, our method achieves significant performance gains over existing strategies, producing cumulative profits of over 400 k for solar energy and more than 200 k for wind energy. These results highlight the superior ability to balance real-time bidding precision and battery utilization efficiency, leading to higher profitability and stability in renewable energy market participation.

Reinforcement Learning (RL) enables learning optimal decision-making strategies by maximizing cumulative rewards. Deep reinforcement learning (DRL) enhances this process by integrating deep neural networks (DNNs) for effective feature extraction from high-dimensional input data. Unlike prior studies focusing on algorithm design, we investigated the impact of different feature extractors, DNNs, on DRL performance. We propose an enhanced feature extraction model to improve control effectiveness based on the proximal policy optimization (PPO) framework in autonomous driving scenarios. Through a comparative analysis of well-known convolutional neural networks (CNNs), MobileNet, SqueezeNet, and ResNet, the experimental results demonstrate that our model achieves higher cumulative rewards and better control stability, providing valuable insights for DRL applications in autonomous systems.

Monitoring sediment concentration (SC) is a challenge in water resource management due to environmental complexities and sensor limitations. Hence, developing a monitoring technology that is easy to operate, high precision, and cost-effective is forward-looking. This research is based on convolutional neural networks and further introduces the concepts of residual block and global average pooling layer to develop a prediction model (CNN-SCP, Convolutional Neural Networks-Sediment Concentration Prediction) to predict sediment concentration. Here, residual blocks (RB) mitigate the vanishing gradient problem and enhance feature propagation for improved stability and convergence. Also, the global average pooling layer reduces parameters, prevents overfitting, and enhances generalization by replacing fully connected layers with spatial averaging, improving model robustness and efficiency. As a result, the proposed model improves the performance of primitive convolutional neural networks, which are apparently better than the existing ones in the literature regarding many metrics, such as MAE is 115.42 and 263.67, MAPE is 6.38 and 14.67, RMSE is 134.24 and 294.51, and CC is 0.97 and 0.90, respectively, by comparing the 5RBs and previous. These results demonstrate the potential of CNN-SCP for future real-time sediment monitoring and early warning system deployment.

Autonomous driving technology is developing rapidly, particularly in vision-based approaches that rely on cameras to monitor the environment. However, one of the critical challenges for autonomous vehicles is the ability to adapt to different weather conditions, as environmental factors such as clouds, fog, rain, sand, shine, snow, and the sunrise significantly impact their perceptual capabilities. Control strategies of the vehicles must be dynamically adjusted based on real-time weather conditions to ensure safe and efficient driving. For the strategies, we developed a novel weather perception model to improve the adaptability of autonomous driving systems. The model is more lightweight than an existing study, as it is computationally efficient with enhanced performance. Moreover, the model detects a weather type, improving its robustness, and providing reliable weather awareness for autonomous driving.

Computer vision applications require high-quality reproductions of original images, typically demanding complex models with many trainable parameters and floating-point operations. This increases computational load and restricts deployment on resource-constrained devices. Therefore, we designed a new dilation depthwise super-resolution (DDSR) model that is composed of dilation convolution, depthwise separable convolution, and residual connection, to overcome the predicaments. Compared with the well-known model, fast super-resolution convolutional neural network (FSRCNN), the developed DDSR shows better performance in evaluations and You Only Look Once (YOLO v8) confidence scores. Most importantly, the architecture of the developed DDSR has 55% trainable parameters, 19% floating-point operations per second (FLOPs) of one-channel FSRCNN, 27% of the trainable parameters, and 8% of the FLOPs of three-channel FSRCNN.

Positioning systems and algorithms are essential for drones. The global positioning system (GPS) is the most common method for drone positioning, but the GPS is not always precise or available. For visual-based positioning, convolutional neural networks (CNNs) are often used to match geometric features in drone positioning. However, seasonal lighting is not considered, although its changes can affect the results. Hence, by incorporating critical components into a CNN, a new architecture is designed to position a drone accurately despite seasonal lighting variations. The experimental results show that the developed method solves issues in drone positioning with high accuracy and stability.

Natural language processing (NLP) has numerous applications and has been extensively developed in deep learning. In recent years, language models such as Transformer, BERT, and GPT have frequently been the foundation for related research. However, relatively few studies have focused on evaluating the quality of generated sentences. While traditional evaluation methods like BLEU can be applied, the challenge is that there is no ground truth reference for generated sentences, making it difficult to establish a reliable evaluation criterion. Therefore, this study examines the content generated by Bidirectional Encoder Representations and related recurrent methods based on the Transformer model. Specifically, we focus on analyzing sentence fluency by assessing the degree of part-of-speech (PoS) matching and the coherence of PoS context ordering. Determining whether the generated sentences align with the expected PoS structure of the model is crucial, as it significantly impacts the readability of the generated text.

Given that the Global Positioning System (GPS) may not always be precise or available, it would be advantageous for drone positioning to utilize a vision-based approach. It analyzes geometric features to determine the drone’s position and identify its flight path. In the literature, an existing vision-based study is proposed to position the drone by a shallow Convolutional Neural Network (CNN). However, they only consider a constant viewpoint (towards the north). This is not practical when implemented in the real world. Hence, we start to examine the impact of viewpoint variations. While the drone’s cameras capture images, these changing viewpoints will affect the accuracy and stability of models. In this paper, MobileNetV2 is the base for creating a classification mechanism for accurate and stable position estimation. Our findings illustrate the importance and relationship of various training data among the different performances of the model. The model achieves only 17% accuracy without applying rotational augmentation in the most practical scenario. However, the accuracy significantly improves by incorporating rotational augmentation with 15-degree increments to 95%.