Advanced artificial intelligence (AI) solutions deployed in the environment of space-air-ground integrated vehicular networks (SAGVNs) are instrumental in achieving efficient coordination between connected electric vehicles (EVs) and distributed networks. This study addresses this challenge by leveraging a Large Language Model (LLM) based hybrid dispatching framework for formulating dispatching strategies, where the need for commonsense understanding by EV drivers is paramount. This paper proposes a framework LLM-D3PG, LLM-guided dual Deep Deterministic Policy Gradient, which empowers EV drivers to articulate their expectations for AI-generated dispatching strategies using natural language instructions. These instructions serve as guidance for the generation of dispatching strategies within complex distributed network scenarios. According to this strategy, the proposed framework seamlessly integrates the decision-making capabilities of LLM with multiple D3PG models to generate a large number of candidate dispatching strategies and then uses the whale optimization algorithm to optimize these strategies to achieve better dispatching results. Comprehensive experimental results demonstrate the effectiveness of the proposed framework and show outperformance in comparison to some existing methods for power dispatching tasks with the random connection of EVs in SAGVNs.

The progress in Natural Language Processing (NLP) using Large Language Models (LLMs) has greatly improved medical sentiment analysis of patient feedback extraction from health-related question and answer. However, using LLMs to analyze such data often requires significant training data and computational resources, resulting in considerable increases in training costs and durations, which is one of the primary issues in applying LLMs to real-world healthcare scenarios. To tackle these challenges, a novel optimization algorithm named KAdam-EnGPT4LLM, based on Kalman filters and Adaptive Moment Estimation, is proposed to enhance training efficiency and reduce training costs of LLMs for analyzing patient feedback sentiment. Furthermore, the optimization algorithm KAdam-EnGPT4LLM is employed in training the LLM model GPT4ALL for medical sentiment analysis, resulting in the development of GPT4ALL-MediSentAly-KAdam, which leds to faster convergence and more stable training specifically for medical questions and answer in the context of healthcare. The results show that our GPT4ALL-MediSentAly-KAdam with the optimization algorithm KAdam-EnGPT4LLM achieved better performance that include the best Accuracy, Recall, F1-score, and Runtime for both datasets, outperforming traditional fine-tuned LLMs such as the classic GPT4ALL, Ada, Babbage, Curie, and Duvinci.

The integration of digital twin technology and the Metaverse has attracted widespread attention in the field of consumer health. Meanwhile, the immersive virtual world, Metaverse, has been increasingly used as a series of consumer health platforms. Photoplethysmography (PPG), as a convenient and low-cost digital twin interaction technology, has become one of the important physiological interaction technologies in the field of consumer health in the Metaverse. In this paper, we propose a PPG signal period detection (PSCD) algorithm based on the concavity of rising branches in PPG signals. By backward differentiation, the pattern of the rate of change of PPG amplitude is captured. Then, the time domain energy distribution is obtained through envelope extraction. The PSCD algorithm can identify all major valleys in the PPG signal based on long tail characteristics. Each cycle of the PPG signal is correctly divided due to changes in the envelope and physiological representation of arterial volume caused by left ventricular ejection from the ascending branch. Finally, the experimental results show that the accuracy of the proposed PSCD algorithm is higher than the other four classic algorithms.

Predicting urban traffic is of great importance to smart city systems and public security; however, it is a very challenging task because of several dynamic and complex factors, such as patterns of urban geographical location, weather, seasons, and holidays. To tackle these challenges, we are stimulated by the deep-learning method proposed to unlock the power of knowledge from urban computing and proposed a deep-learning model based on neural network, entitled Capsules TCN Network, to predict the traffic flow in local areas of the city at once. Capsules TCN Network employs a Capsules Network and Temporal Convolutional Network as the basic unit to learn the spatial dependence, time dependence, and external factors of traffic flow prediction. In specific, we consider some particular scenarios that require accurate traffic flow prediction (e.g., smart transportation, business circle analysis, and traffic flow assessment) and propose a GAN-based superresolution reconstruction model. Extensive experiments were conducted based on real-world datasets to demonstrate the superiority of Capsules TCN Network beyond several state-of-the-art methods. Compared with HA, ARIMA, RNN, and LSTM classic methods, respectively, the method proposed in the paper achieved better results in the experimental verification.

As a kind of transportation in a smart city, urban public bicycles have been adopted by major cities and bear the heavy responsibility of the “last mile” of urban public transportation. At present, the main problem of the urban public bicycle system is that it is difficult for users to rent a bike during peak h, and real-time monitoring cannot be solved adequately. Therefore, predicting the demand for bicycles in a certain period and performing redistribution in advance is of great significance for solving the lag of bicycle system scheduling with the help of IoT. Based on the HOSVD-LSTM prediction model, a prediction model of urban public bicycles based on the hybrid model is proposed by transforming the source data (multiple time series) into a high-order tensor time series. Furthermore, it uses the tensor decomposition technology (HOSVD decomposition) to extract new features (kernel tenor) from higher-order tensors. At the same time, these kernel tenors are directly used to train tensor LSTM models to obtain new kernel tenors. The inverse tensor decomposition and high-dimensional, multidimensional, and tensor dimensionality reduction were introduced. The new kernel tenor obtains the predicted value of the source sequence. Then the bicycle rental amount is predicted.

Internet of Things will play a vital role in the public transport systems to achieve the concepts of smart cities, urban brains, etc., by mining continuously generated data from sensors deployed in public transportation. In this sense, smart cities applied artificial intelligence techniques to offload data for social governance. Bicycle sharing is the last mile of urban transport. The number of the bike in the sharing stations, to be rented in future periods, is predicted to get the vehicles ready for deployment. It is an important tool for the implementation of smart cities using artificial intelligence technologies. We propose a DBSCAN‐TCN model for predicting the number of rentals at shared bicycle stations. The proposed model first clusters all shared bicycle stations using the DBSCAN clustering algorithm. Based on the results of the clustering, the data on the number of shared bicycle rentals are fed into a TCN neural network. The TCN neural network structure is optimized. The effects of convolution kernel size and Dropout rate on the model performance are discussed. Finally, the proposed DBSCAN‐TCN model is compared with the LSTM model, Kalman filtering model, and autoregressive moving average model. Through experimental validation, the proposed DBSCAN‐TCN model outperforms the traditional three models in terms of two metrics, root mean squared logarithmic error, and error rate, in terms of prediction performance.