The increasing acceptance of Electric Vehicles (EVs) leads to significant challenges for traditional forecasting methods due to external variables such as weather conditions, availability of renewable energy sources, and real-time traffic data. These factors affect the forecasting accuracy because of the unpredictable nature of renewable energy sources and weather. Conventional methods have limitations in terms of adapting dynamic conditions, leading to problems in allocating power and managing energy in EV Charging Stations (EVCS). To address these challenges, we propose a novel AI-driven approach called Dynamic Allocation and Management Optimization (DYNAMO), which integrates cutting-edge demand forecasting, power allocation, and efficiency-enhanced methods for smart city EV infrastructure. DYNAMO uses a Lite Transformer Gated Recurrent Unit (LT-GRU) for advanced demand prediction by considering critical factors like the number of incoming EVs, session duration, and station usage frequency. In LT-GRU, we integrate the strengths of transformer attention mechanism and sequential data processing of GRU to improve the prediction accuracy by capturing the long-term dependencies and prioritizing the important features even though in dynamic conditions. Additionally, an Intelligent Central Manager (ICM) groups EVCS into high, moderate, and low demand clusters, allowing for dynamic optimization of charging infrastructure. Furthermore, a Game Theory-based Deep Reinforcement Learning (GT-DRL) approach is employed, which considers variables such as vehicle demand, battery capacity, charging speed, and weather conditions, while preventing overloads and outages. Our approach not only enhances the operational efficiency of EVCS but also contributes to the development of more sustainable and reliable EV charging networks. Overall, the proposed framework’s ability to adapt in real-time ensures that it can support the increasing demand for EV infrastructure, minimize inefficiencies, and improve user experience.

As sustainable development gains attention, integrating carbon-intelligent computing into fault diagnosis systems has emerged as a critical strategy to reduce energy consumption and carbon footprints. This approach uses artificial intelligence (AI) and the Internet of Things (IoT) to optimize task scheduling, aligning it with low-carbon energy sources based on time and location. In fault diagnosis, energy-intensive tasks, such as data processing and model inference, can be scheduled during periods of abundant renewable energy, thereby minimizing emissions. However, drilling machines operate under complex conditions that generate nonstationary noise, which distorts signals and complicates fault diagnosis. Therefore, this article combines bidirectional long short-term memory (BiLSTM) with the Kolmogorov-Arnold network (KAN) and integrates Wavelet Transform and Convolutional Autoencoder, proposing a highly robust fault diagnosis model for drilling machines, named WCBK. The Wavelet Transform converts pressure time-series data, which contains fault information, into time-frequency images, facilitating the detection of fault frequency components. The Convolutional Autoencoder preserves essential features while removing noise by learning low-dimensional representations of the signal, effectively capturing local features in time-frequency images through local connections to enhance denoising performance. Finally, the composite deep learning network, which combines BiLSTM and KAN, achieves highly robust fault diagnosis under complex working conditions. The effectiveness of the proposed WCBK model was validated through ablation experiments, experiments on different individuals, experiments on different parts, and model adaptability evaluations. In experiments involving different individuals and parts, the WCBK model improved fault diagnosis accuracy by 10.9% and 8.8%, respectively, compared to existing models.

Trajectory prediction is a crucial challenge in autonomous vehicle motion planning and decision-making techniques. However, existing methods face limitations in accurately capturing vehicle dynamics and interactions. To address this issue, this article proposes a novel approach to extracting vehicle velocity and acceleration, enabling the learning of vehicle dynamics and encoding them as auxiliary information. The VDI-LSTM model is designed, incorporating graph convolution and attention mechanisms to capture vehicle interactions using trajectory data and dynamic information. Specifically, a dynamics encoder is designed to capture the dynamic information, a dynamic graph is employed to represent vehicle interactions, and an attention mechanism is introduced to enhance the performance of LSTM and graph convolution. To demonstrate the effectiveness of our model, extensive experiments are conducted, including comparisons with several baselines and ablation studies on real-world highway datasets. Experimental results show that VDI-LSTM outperforms other baselines compared, which obtains a 3% improvement on the average RMSE indicator over the five prediction steps.

Distributed learning empowers social media platforms to handle massive data for image sentiment classification and deliver intelligent services. However, with the increase of privacy threats and malicious activities, three major challenges are emerging: securing privacy, alleviating straggler problems, and mitigating Byzantine attacks. Although recent studies explore coded computing for privacy and straggler problems, as well as Byzantine-robust aggregation for poisoning attacks, they are not well-designed against both threats simultaneously. To tackle these obstacles and achieve an efficient Byzantine-robust and straggler-resilient distributed learning framework, in this article, we present Byzantine-robust and cost-effective distributed machine learning (BCML), a codesign of coded computing and Byzantine-robust aggregation. To balance the Byzantine resilience and efficiency, we design a cosine-similarity-based Byzantine-robust aggregation method tailored for coded computing to filter out malicious gradients efficiently in real time. Furthermore, trust scores derived from similarity are published to the blockchain for the reliability and traceability of social users. Experimental results show that our BCML can tolerate Byzantine attacks without compromising convergence accuracy with lower time consumption, compared with the state-of-the-art approaches. Specifically, it is 6x faster than the uncoded approach and 2x faster than the Lagrange coded computing (LCC) approach. Besides, the cosine-similarity-based aggregation method can effectively detect and filter out malicious social users in real time.

In this paper, UAVs are used to enlarge the positioning range and eliminate the blind area for object localization. The motion parameters of transceivers are considered to be unavailable, and the localization problem is highly nonlinear to the unknown parameters. To this end, the semidefinite relaxation (SDR) technique is proposed to solve the localization problem. Since the constrained relationship among the variables is difficult to be fully included in the stage-one SDR problem, we develop a novel two-stage SDR solution for this localization problem. The performance of the two-stage SDR solution is proven to be close to the Cramér-Rae Lower Bound (CRLB) accuracy at the small noise levels. The simulated results show that the two-stage SDR solution performs better than the closed-form solution, especially at high noise levels.

PLC control programs are vulnerable to real-time threats, where attackers can disrupt the backhaul/front-end network of industrial production by creating numerous loops or I/O operations, leading to severe consequences. Therefore, formal verification of PLC control logic at the binary level is essential. In this study, we introduce a framework designed for formal verification of PLC control logic at the binary level. Our verification framework is based on simulation execution, which extracts the core control logic from PLC binary code. Initially, we develop an efficient framework for automating the parsing of PLC programs at the binary level and constructing their control flow graphs (CFGs). Next, we devise an algorithm to transform the reversed PLC assembly program into an smv model, a widely accepted formal verification tool. Subsequently, we generate real-time requirements relevant to industrial production and perform formal verification on the constructed models. To assess the real-time performance of our framework in safeguarding PLC systems, we implement a prototype and evaluated it across various representative ICS scenarios. The evaluation results demonstrate the capability of our proposed approach to effectively detect synchronization threats in PLC logic control programs.

The convergence of transformative technologies, including the Internet of Things (IoT), Big Data, and Artificial Intelligence (AI), has driven private edge cloud systems to the forefront of research efforts. The access to massive terminals and the emergence of personalized services pose serious challenges for efficient resource management in power private edge cloud systems. To address the challenge of inequitable resource allocation in the private edge cloud, this work proposes an intelligent resource allocation strategy with a slicing and auction approach. By formalizing the resource allocation problem as a Mixed Integer Nonlinear Programming (MINLP) puzzle, the method transforms it into a hierarchical allocation challenge for Mobile Network Operators (MNOs), Mobile Virtual Network Operators (MVNOs), and power terminals. The proposed Multi-hop Progressive Auction Algorithm (MPAA) addresses the sliced resource allocation problem between MNOs and MVNOs. Furthermore, a Terminal Resource Allocation Strategy (TRAS) based on improved particle swarm optimization is proposed to solve the spectrum resource allocation problem between MVNOs and power terminals. Extensive simulation results show that the bidding overhead of MPAA is reduced by 6.12% and the average terminal satisfaction of TRAS is improved by about 1.3% compared to conventional methods, thus improving the utilization of wireless resources within the power AIoT.

Machine learning is playing an increasingly important role in education. This article examines its potential to bring about transformative change in this field. By using machine learning algorithms, physical education teachers can gather and analyze data on student performance and behavior. This enables them to create personalized learning experiences that cater to the unique needs of each student. Machine learning can also track and assess student progress, providing educators with valuable insights into the effectiveness of their teaching strategies. Furthermore, it can optimize the design of physical education curricula and assessments, making them more efficient and effective. Additionally, machine learning offers a more objective and accurate approach to evaluating and grading students. This paper discusses the challenges and opportunities associated with integrating machine learning into physical education, including ethical considerations and potential limitations.

Artificial intelligence has been utilized to analyze patients' electroencephalograms (EEG) to diagnose depression. However, attackers can deduce patients' privacy after analyzing patients' EEG time series. Therefore, researchers propose to operate ciphertext calculation in depression diagnosis models based on homomorphic encryption. Nevertheless, homomorphic encryption requires consistent private keys during training, which could result in other participants decrypting the ci-phertexts. Additionally, existing EEG-based models neglect the relationship among electrode positions during EEG acquisition. To address these issues, we propose a novel training strategy for the depression diagnosis model based on fully homomorphic en-cryption (FHE) and electrode topology. Specifically, we establish a training strategy that prioritizes the privacy of patients' EEG data without compromising the cost-effectiveness of the diagnosis model. Furthermore, we incorporate the attention mechanism of electrode topology into our model to improve its performance and verify the relationship among topology locations. Our proposed model outperforms the original convolution neural network model, achieving higher accuracy in depression diagnosis and identifying virtual electrode channels for the first time.

With the rapid development of loT technology, various loT devices enter our daily life. The continuously increasing scale of the massive loT devices in both of numbers and types further bring heavy pressure on loT network management and security. Therefore, how to accurately identify and efficiently manage so massive loT devices has become a challenge. In this paper, we propose BcllS, Blockchain-based Intelligent Identification Scheme of Massive loT Devices. It applies a decentralized identification architecture and realizes learning sustainably as well as efficiently identifying by updating the identification model constantly according to the ledger which is maintained by all gateways collaboratively. Experiments show that the identification accuracy can achieve up to 99.5 %.