Accurate road crack segmentation is critical for ubiquitous intelligence applications in smart city infrastructure maintenance, particularly in UAV-based inspection systems. To address computational constraints on edge devices, we propose Mobile TantivyFormer U-Net: a lightweight network that integrates an Edge Localization Module (ELM) and Mobile TantivyFormer Blocks (MTFB). ELM combines deformable convolution with normalization-free Vision Transformers to enhance edge detection, while MTFB employs efficient additive attention with$O(n)$complexity to reduce parameters by 80 % versus standard Transformers. Our model enables device-edge-cloud orchestration by achieving real-time segmentation on UAVs with seamless cloud integration for large-scale analysis. Evaluations on three datasets show state-of-the-art accuracy (F1-Score: 85.2%) and efficiency (20.47 M parameters), showcasing its viability for ubiquitous intelligent infrastructure monitoring.

Deep learning techniques have demonstrated considerable potential in the field of crack detection. Especially in the emerging smart city infrastructure applications, it is very widespread, among which the crack detection of crowdsourcing mobile terminals is an innovative urban infrastructure detection model. To address the challenges of achieving precise crack segmentation and overcoming deployment constraints on mobile platforms, we propose a U-Net model that utilizes multiscale global information fusion attention. Multi-Scale Global Information Fusion Attention U-Net introduces a global attention module in the encoder, enabling the model to effectively capture critical crack features and maintain focused attention on target regions. In the meantime, the decoder incorporates a multiscale dilated fusion attention module, leveraging various dilation rates and combining dual attention mechanisms. This design effectively captures both detailed information on crack defects and extensive contextual features, facilitating efficient global context modeling. Our crowdsourcing-based mobile detection framework enables real-time, large-scale crack monitoring with unprecedented coverage density. Evaluations on four datasets show state-of-the-art accuracy (IoU: 76.02%, Dice: 86.33%) and efficiency (${2.85M}$parameters), showcasing its viability for ubiquitous intelligent infrastructure monitoring.

Facial paralysis, as a common nerve system disease, seriously affects the patients' facial muscle function and appearance. Accurate facial paralysis grading is of great significance for the formulation of personalized treatment. Existing artificial intelligence based grading methods extensively focus on static image classification, which fails to capture the dynamic facial movements. Additionally, due to private concerns, building comprehensive facial paralysis datasets is challenging, making it impractical to fully train a robust model from scratch. Finally, maintaining precision and inference speed on edge devices remains a key challenge. To address these shortcomings, we propose MLST-Net, a novel and explainable three-stage deep-learning method based on multi-task learning. In the first stage, the pre-trained model is used to extract the facial static appearance structure and dynamic texture changes. The second stage fuses the proxy task results to construct a unified face semantic expression and outputs the "with or without facial paralysis" simple task results. In the third stage, we use spatial-temporal disentanglement to capture the spatial-temporal combinatorial-dependencies in video sequences. Finally, we input the classifier to get the results of complex tasks of facial paralysis classification. Compared with all advanced methods, MLST-Net is computationally inexpensive and achieves state-of-the-art results on the 1241 public dataset videos. It significantly benefits the digital diagnosis of facial palsy and offers innovative and explainable ideas for video-based digital medical treatment.

This paper proposes a general unmanned aerial vehicle (UAV)-to-ground (U2G) channel model. The proposed model is consistent with real scenarios by considering the impacts of flight altitude and UAV posture on channel gain. Machine learning and ray tracing (RT) techniques are employed to improve the generation method of altitude-dependent parameters, i.e., path loss (PL) and shadow fading (SF). In addition, posture-related fuselage shadowing coefficient (FSC) is introduced to modify the channel gain, and three-dimensional (3D) geometry modeling of the fuselage is conducted to calculate the FSC. Numerical simulation results show that the flight altitude and UAV posture have obvious effects on channel gain. The proposed model with modified channel gain can effectively describe the PL, SF, and received power under fuselage shadowing. The validity and advantage of the improved channel gain are verified by comparing the simulation results with the measured ones.

Unmanned aerial vehicle (UAV)-to-ground (U2G) channel models play a pivotal role in reliable communications between UAV and ground terminal. This paper proposes a three-dimensional (3D) non-stationary hybrid model including large-scale and small-scale fading for U2G multiple-input-multiple-output (MIMO) channels. Distinctive channel characteristics under U2G scenarios, i.e., 3D trajectory and posture of UAV, fuselage scattering effect (FSE), and posture variation fading (PVF) are incorporated into the proposed model. The channel parameters, i.e., path loss (PL), shadow fading (SF), path delay, and path angle, are generated incorporating machine learning (ML) and ray tracing (RT) techniques to capture the structure-related characteristics. In order to guarantee the physical continuity of channel parameters such as Doppler phase and path power, the time evolution methods of inter- and intra- stationary intervals are proposed. Key statistical properties, including temporal auto-correction function (ACF), power delay profile (PDP), level crossing rate (LCR), average fading duration (AFD), and stationary interval (SI), are analyzed with the impact of the change of fuselage and posture variation. It is demonstrated that both posture variation and fuselage scattering have crucial effects on channel characteristics. The validity and practicability of the proposed model are verified by comparing the simulation results with the measured ones.

The application of automation technology and artificial intelligence technology has promoted the improvement of the business capabilities of enterprises in industrial scenarios. Compared with the improvement or innovation of the business process, in recent years, part of academic research and practical applications has also shifted their attention from a single point of business intelligence perspective to a comprehensive intelligent upgrade of the industrial system. To the best of our knowledge, however, there is little research on the concept and model of the industrial intelligent system (IIS). To make up for the lack, this article presents the concept and reference model of IIS by analyzing the intelligentization requirement of the industrial systems. Different from academic research on general intelligent system capabilities, the reference model given emphasizes factors that need to be considered when implementing IIS in the industry. By analyzing the reference model, knowledge as the core driving force of IIS is recognized. Then, the four main forms of knowledge in IIS, as well as the role and key technologies of knowledge in different stages of IIS, are discussed in detail. In addition, several important potential applications of IIS are pointed out in this article.

Developing effective and accurate model to handle complex uncertainties of linguistic assessments in multicriteria decision making (MCDM) has important theoretical significance and practical value of engineering. This paper proposes a novel hesitant fuzzy linguistic hybrid cloud (HFLHC) model that integrates hesitant fuzzy linguistic term set and cloud model to handle the hesitancy, fuzziness, and randomness of linguistic expression. The normal cloud and trapezium cloud are integrated to represent hybrid-length linguistic variables of HFLHC model, which can effectively avoid evaluation information loss and distortion. Aiming at applying HFLHC model to MCDM, some hybrid operations for normal cloud and trapezium cloud are developed. Moreover, an improved method for aggregating multiple linguistic concepts into an integrated trapezium cloud in HFLHC model is proposed, with consideration of the different representation region of each linguistic concept. Furthermore, a novel HFLHC-based best-worst method is proposed to obtain optimal criteria weights with developing a HFLHC optimization programming model and a modified consistency ratio. Finally, an illustrative example of sustainable supplier selection is presented. Several comparative analyses demonstrate that our method can provide more consistency and greater reliability.